system

Abstract

Provide a system. [Solution] a means for users to input their preferences and past browsing history; means for transmitting the preferences and past browsing history to a server; A means for analyzing user preferences using a generating AI based on the preferences and past browsing history; means for generating a list of recommended content based on the analysis results; A means of collecting additional information related to the content we recommend; and means for transmitting the list of recommended content and additional information to a user; means for displaying the list of recommended content and additional information to a user; A system including:

Description

[Technical Field]

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

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

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

[0004] Conventional recommendation systems have difficulty providing appropriate content based on user preferences. Specifically, they have problems such as not being able to fully reflect the user's preferences and past browsing history, and lacking related additional information. Another issue is the lack of a way for users to enjoy the recommended content more deeply. There is a need for a system that can solve these problems and provide users with a more personalized experience. [Means for solving the problem]

[0005] The present invention provides a means for a user to input preferences and past browsing history and a means for transmitting the preferences and past browsing history to a server. The present invention also provides a means for analyzing user preferences using a generation AI based on the preferences and past browsing history, thereby enabling accurate identification of user preferences. The present invention also provides a means for generating a list of recommended content based on the analysis results and a means for collecting additional information related to the recommended content. This allows users to deeply understand and enjoy the recommended content. Specifically, the additional information may include comments from directors or writers, interviews, and behind-the-scenes information, helping users to deeply understand the content. Furthermore, the recommended content may include videos and manga, allowing for a wide range of user preferences to be accommodated. In this way, the present invention provides users with a personalized experience and solves the problems inherent in the prior art.

[0006] "User" refers to an individual who uses this system and provides their preferences and past browsing history.

[0007] "Preferences" refer to the tendencies or preferences that a user has toward specific content (e.g., genres, authors, directors, etc.).

[0008] "Past browsing history" is information that includes a list of content that a user has previously viewed or read.

[0009] "Terminal" refers to a device used by a user (e.g., a smartphone, tablet, PC, etc.) and is a means for inputting and receiving user data.

[0010] A "server" is a computer system responsible for receiving data sent by a user, analyzing it, and returning the necessary information.

[0011] "Generative AI" refers to artificial intelligence technology that analyzes and generates optimal content based on a user's preferences and past browsing history.

[0012] "Analyzing preferences" refers to the process of identifying content that a user might like based on the preferences they have entered and their past browsing history.

[0013] "Recommended Content" refers to content that is recommended for viewing or reading and is provided to the user based on the analysis results.

[0014] "Generating a list" refers to the process of compiling multiple recommended pieces of content in a list format based on the results of AI analysis.

[0015] "Additional Information" means director or writer commentary, interviews, behind-the-scenes information, and similar information related to the recommended content.

[0016] "Transmitting" refers to the act of moving data from one device to another.

[0017] "Display" refers to the act of presenting information on a terminal in a form that can be viewed by a user. [Brief explanation of the drawings]

[0018] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7]FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0019] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0020] First, the terms used in the following description will be explained.

[0021] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0022] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0023] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0024] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0025] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0029] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0030] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0031] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0032] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0033] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0036] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0037] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0038] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0039] This invention is a system that analyzes user preferences and past browsing history to provide customized manga and movie recommendations. This system is composed of users, terminals, and servers, and by clearly dividing the roles of each, it achieves advanced recommendation functionality.

[0040] First, users input their preferences and browsing history, and the user's device receives this data, formats it, and sends it to the server.

[0041] The server uses a generative AI to analyze the received data. The generative AI uses natural language processing (NLP) and machine learning algorithms to understand the user's preferences. For example, if a user likes action movies and has watched many "superhero movies" in the past, the AI ​​can determine that the user particularly likes action-themed superhero movies.

[0042] Next, the server generates a list of recommendations for appropriate manga and movies based on the analysis results. For example, if it determines that the user likes superhero movies, it will list superhero movies such as "Guardians of the Galaxy" and "Batman."

[0043] Additionally, the server collects additional information about the recommended film, such as director and writer comments, interviews, behind-the-scenes information, etc. For example, for a recommendation of "Guardians of the Galaxy," providing an interview with the director and behind-the-scenes information about filming can help users better understand and enjoy the film.

[0044] The server compiles this information and sends it to the user's device as the final content, where it displays the received information in a user interface for easy access. For example, it displays a list of recommended movies along with behind-the-scenes stories and comments about each movie.

[0045] Therefore, the present invention allows users to receive recommendations for manga and movies that are tailored to their preferences, and to enjoy the works even more through in-depth related information.

[0046] The processing flow will be explained below.

[0047] Step 1:

[0048] The user inputs their preferences and past viewing history. For example, the user inputs information such as "I like action movies" or "The movie I watched recently was a superhero movie."

[0049] Step 2:

[0050] The terminal formats the user's input data, specifically converting it into the appropriate data model so that subsequent processing can proceed smoothly.

[0051] Step 3:

[0052] The device sends the formatted data to the server, where it is transmitted using a secure communications protocol.

[0053] Step 4:

[0054] Before the server analyzes the received user data, it performs preprocessing such as shaping and filtering the data, for example, removing noise and inconsistencies in the input data.

[0055] Step 5:

[0056] The server passes the preprocessed data to the generation AI, which analyzes the user's preferences. The generation AI uses natural language processing and machine learning algorithms to identify the user's preferences, taking into account data from other users with similar preferences.

[0057] Step 6:

[0058] The server generates a list of recommended content based on the results of AI analysis. For example, if it determines that the user likes action movies, it will list movies such as "Batman" and "Iron Man."

[0059] Step 7:

[0060] The server collects additional information about the content it recommends, such as director and writer comments, interviews, and behind-the-scenes information, to help users better understand the work.

[0061] Step 8:

[0062] The server assembles the generated content list and additional information into a data packet, compressing and encrypting the data as necessary.

[0063] Step 9:

[0064] The server sends the data packet to the terminal, which again transmits the data using a secure communications protocol.

[0065] Step 10:

[0066] The terminal decompresses and decrypts the received data packets and verifies their contents, checking for inconsistencies and errors.

[0067] Step 11:

[0068] The device will then display the decompressed and decrypted data in a user interface, where the user can view a list of recommended content and related additional information.

[0069] Step 12:

[0070] Users can select content they are interested in. For example, if a user selects "Batman," they can view details and related information about the work.

[0071] Through these steps, the system of the present invention can provide customized content recommendations based on the user's preferences and related additional information.

[0072] Example 1

[0073] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0074] Conventional recommendation systems have difficulty accurately understanding user preferences and providing appropriate content. They also lack the functionality to provide related information that users are interested in. This has limited the improvement in user satisfaction and made it difficult to increase the frequency of system use.

[0075] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0076] In this invention, the server includes means for a user to input preferences and past browsing history, means for formatting the preferences and past browsing history and transmitting the formatted information to the server, means for analyzing the user's preferences using a generative AI model based on the preferences and past browsing history, means for generating a list of recommended content based on the analysis results, means for collecting additional information related to the recommended content, means for transmitting the list of recommended content and the additional information to the user, and means for displaying the list of recommended content and the additional information to the user, thereby enabling the provision of content and related information tailored to the user's individual preferences.

[0077] "User" refers to an individual or group of people who use this system to receive content recommendations.

[0078] "Preferences" refer to preferences such as genres or themes that a user is particularly interested in and tends to enjoy in preference to other things.

[0079] "Past browsing history" refers to a record of content that a user has previously viewed or read.

[0080] "Formatting" refers to the process of preparing data according to certain rules, so that the data can be sent correctly to the server.

[0081] A "server" is a part of an information processing system that responds to requests from clients via a network, analyzing data and providing information.

[0082] A "generative AI model" refers to an artificial intelligence model that uses machine learning algorithms and natural language processing techniques to analyze data and understand user preferences.

[0083] "Analysis" refers to the process of analyzing collected data in detail and deriving useful information and patterns from it.

[0084] "Recommended content" refers to entertainment media such as movies and manga that are selected by AI based on the user's preferences and past browsing history and recommended to the user.

[0085] "Additional Information" is supplemental information related to the recommended content, such as director's commentary, interviews, and behind-the-scenes information.

[0086] "Transmission" refers to the act of a terminal transferring data to a server, or the act of a server transferring data to a user.

[0087] "Display" refers to the visualization of the received data and recommended content on the user interface of the terminal.

[0088] This invention is a system that analyzes user preferences and past browsing history to provide customized content recommendations. This system is composed of a user, a terminal, and a server, and by clearly dividing the roles of each, it achieves advanced recommendation functionality.

[0089] First, the user inputs their preferences and browsing history. This input is done using a device such as a smartphone or PC. The input data is formatted by the device and organized as structured data in JSON format or similar. The device then sends the formatted data to the server.

[0090] The server uses a generative AI model to analyze the received data. The generative AI model is implemented using Python libraries such as Scikit-learn and TENSORFLOW (registered trademark). Specifically, it uses natural language processing (NLP) technology and machine learning algorithms to deeply analyze the user's preferences. For example, if a user likes action movies and has watched many "superhero movies" in the past, the AI ​​will determine that the user particularly likes action-themed superhero movies.

[0091] Next, the server generates a recommendation list of appropriate content based on the analysis results. When generating this list, the server uses content information stored in a database such as MySQL (registered trademark). For example, if it is determined that the user likes superhero movies, it will list related works such as "Superhero Movie A" and "Superhero Movie B."

[0092] The server also collects additional information about the recommended content, such as comments from directors and writers, interviews, and behind-the-scenes information. This information is collected using web scraping techniques, specifically using Beautiful Soup and Scrapy. For example, for a recommendation of "Superhero Movie A," the server collects interviews with the director and behind-the-scenes information about filming.

[0093] This information is then compiled and sent to the device, which then displays it in a user interface for easy access. For example, the device could display a list of recommended movies along with behind-the-scenes stories and comments about each one.

[0094] Below are some examples of prompt sentences to input into the generative AI model.

[0095] Example prompt sentence:

[0096] "If a user likes action movies and has watched a lot of 'action movie A' and 'action movie B' in the past, what other movies can we recommend?"

[0097] As described above, the present invention realizes the provision of content and related information that are tailored to the individual preferences of a user.

[0098] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0099] Step 1:

[0100] Users input their preferences and past viewing history. The input data is provided in the form of genres, specific movie or manga titles, and viewing dates and times. This results in input data formats such as "Action Movies," "Movie A," and "2022-01-01."

[0101] Step 2:

[0102] The device receives the data entered by the user and formats it. The formatted data is saved in JSON format with the following structure: {"genre": "Action", "history": [{"title": "Movie A", "date": "2022-01-01"},{"title": "Movie B", "date": "2022-02-01"}]}. The formatted data is sent to the server.

[0103] Step 3:

[0104] The server receives the JSON-formatted data sent from the device. The received data undergoes appropriate data preprocessing before being passed to the generative AI model. This includes data normalization and filtering of unnecessary information. This preprocessing results in a clean dataset for analysis.

[0105] Step 4:

[0106] The server analyzes the preprocessed data using a generative AI model, which uses Python libraries (such as Scikit-learn and TensorFlow). This analysis helps understand the user's preferences and arrives at a conclusion, such as "the user particularly likes action movies."

[0107] Step 5:

[0108] The server generates a list of appropriate content based on the analysis results. It queries and retrieves related content from movie and manga data stored in a database management system (e.g., MySQL). For example, it searches for works tagged with "action" and "hero movies" based on the analysis results and lists "Content A" and "Content B."

[0109] Step 6:

[0110] The server collects additional information related to the recommended content. Specifically, it uses web scraping tools such as Beautiful Soup and Scrapy to collect director interviews and behind-the-scenes information. For example, for "Content A," it collects "director interview articles" and "behind-the-scenes articles."

[0111] Step 7:

[0112] The server formats the generated recommendation list and the collected additional information into the final content. The formatted data is converted back into JSON format, with the format "{"recommended": ["Content A", "Content B"], "additional_info": {"Content A": ["Director's Interview", "Behind the Scenes"]}}".

[0113] Step 8:

[0114] The server transmits the final content to the terminal, thereby transmitting data of detailed recommendation information to be provided to the user.

[0115] Step 9:

[0116] The device displays the final content in a user interface, allowing the user to visually view a list of recommended content and related additional information, such as a poster of a recommended movie and related director interviews or behind-the-scenes information.

[0117] (Application example 1)

[0118] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0119] Conventional content distribution services have difficulty in appropriately recommending content that matches a user's preferences, and lack a system that provides detailed background information or expert interviews about the recommended content. This makes it difficult for users to find content that is tailored to their preferences, and they lack opportunities to gain a deeper understanding of or be moved by the content.

[0120] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0121] In this invention, the server includes means for inputting a user's preferences and past browsing history, means for transmitting the preferences and past browsing history to the server, means for analyzing the user's preferences using a generation AI based on the preferences and past browsing history, means for generating a list of recommended content based on the analysis results, means for collecting additional information related to the recommended content, means for displaying the list of recommended content and the additional information on a user interface, and means for providing expert interviews and production background information for the recommended content. This allows users to optimally search for content that matches their preferences and obtain in-depth information about that content.

[0122] "Preferences" are personal tastes and interests that a user has for a particular type of content (for example, video works or digital comics).

[0123] "Past browsing history" refers to a record of content that a user has previously viewed or read.

[0124] "Generative AI" is an artificial intelligence technology that uses natural language processing and machine learning algorithms to analyze user preferences and provide optimal recommendations.

[0125] "Analysis results" refers to data and information about a user's preferences that the generating AI generates based on the user's preferences and past browsing history.

[0126] "Recommended content" refers to content such as video works and digital comics that are recommended to users based on the analysis results.

[0127] "Additional information" refers to supplementary information related to the recommended content, such as director or writer comments, expert interviews, and production background information.

[0128] "User interface" refers to the screens and methods of operation that allow a user to access content lists and additional information.

[0129] "Expert Interviews" refers to interview articles that include expert insights and inside stories related to the recommended content.

[0130] "Production Background Information" refers to detailed information about the production process and background of the recommended content.

[0131] "Digital comics" refers to manga and graphic novels available in e-book format.

[0132] This invention is a system that analyzes a user's preferences and past browsing history to provide customized content recommendations (video works and digital comics). This system is composed of a user, a terminal, and a server, and by clearly dividing the roles of each, it achieves advanced recommendation functionality.

[0133] First, the user inputs their preferences and browsing history. This input is done on a device such as a smartphone or tablet. The device receives this data, formats it, and sends it to the server. The software on the device uses Python and the requests library.

[0134] The server uses a generative AI to analyze the received data. This generative AI uses natural language processing (NLP) and machine learning algorithms to understand the user's preferences. Web frameworks such as Flask are used as server-side software. For example, if a user likes action movies and has watched many "superhero movies" in the past, the generative AI will determine that the user particularly likes action-themed superhero movies.

[0135] Next, the server generates a list of appropriate content recommendations based on the analysis results. For example, if it determines that the user likes superhero movies, it will list superhero movies such as "space adventure movies" and "city defender movies." The server also collects additional information about the recommended content. This additional information includes comments from directors and writers, expert interviews, and production background information. For example, for a recommendation of "space adventure movies," it will provide an interview with the director and background story of the filming.

[0136] The server compiles this information and sends it to the user's device as the final content. The user's device displays the received information in a user interface for easy access. For example, it displays a list of recommended movies or manga along with detailed information about each piece of content.

[0137] As a concrete example, the following prompt sentence is input to the generative AI model:

[0138] User preferences: Action, Hero

[0139] User's past browsing history: Avengers, Spider-Man, Batman

[0140] Based on this input, the generative AI will provide the following output:

[0141] Recommended content:

[0142] Title: Space adventure movie

[0143] Description: A heroic adventure to save the universe

[0144] Director's interview: The director talks about the background of the production

[0145] Title: City Guardian Movie

[0146] Description: A hero's challenge to protect the city

[0147] Director's Interview: The Director Discusses His New Hero Image

[0148] As described above, the system of the present invention allows users to receive recommendations for content that matches their preferences, and to enjoy works even more through in-depth information related to the content.

[0149] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0150] Step 1:

[0151] Users input their preferences and past viewing history. Using a smartphone or tablet, users input their preferences (e.g., action, superheroes) and the shows they have watched in the past (e.g., Avengers, Spider-Man). After inputting, this data is stored on the device.

[0152] Step 2:

[0153] The device sends input data to the server. Using Python and the requests library, the device formats the user's preferences and past browsing history into JSON format and sends it to the server via an HTTP POST request. In this setup, the data sent is in the following format:

[0154] {

[0155] "preferences": ["Action", "Hero"],

[0156] "history": ["Avengers", "Spider-Man"]

[0157] }

[0158] Step 3:

[0159] The server analyzes the received data. The server receives the HTTP request using a web framework such as Flask, and then analyzes the data using generative AI (e.g., GPT). Specifically, it uses natural language processing (NLP) and machine learning algorithms to understand the user's preferences and generate an analysis result. As a result of this analysis, it is determined that the user likes action superhero movies.

[0160] Step 4:

[0161] The server generates a list of recommended content based on the analysis results. Based on the analysis results of the generative AI, the server creates a list of optimal movies and digital comics. For example, content such as "space adventure movies" and "city guardian movies" will be listed.

[0162] Step 5:

[0163] The server collects additional information related to the content it recommends. For example, the server collects director and author comments, expert interviews, and production background information for the recommended content. For example, the server obtains information about the director's interview and the filming background of a "space adventure movie."

[0164] Step 6:

[0165] The server sends a list of recommended content and additional information to the device. After all the information is collected, the server compiles it and sends it to the user's device in JSON format.

[0166] Step 7:

[0167] The device displays the received information in a user interface. The device displays the received list of recommended content and additional information in a user interface for easy access by the user. For example, a list of recommended movies or manga can be displayed along with detailed information about each piece of content (such as an interview with the director or background information on the production).

[0168] Through the above processing steps, the user can optimally search for content that matches his or her preferences, and can also obtain in-depth information about that content.

[0169] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0170] This invention is a system that provides customized manga and movie recommendations by utilizing real-time emotional data in addition to user preferences and past browsing history. This system is composed of a user, a terminal, a server, and an emotional engine.

[0171] First, users input their preferences and past browsing history into the device, and real-time emotional data expressed by users while watching or browsing is also collected. This may be done using wearable devices, cameras, microphones, etc.

[0172] The device formats this data and sends it to the server. The server receives the data and performs preprocessing such as formatting and filtering. Next, the emotion engine in the server analyzes the user's emotion data and understands their emotional state. For example, it can extract information such as whether the user is enjoying or nervous while watching a movie.

[0173] The server uses generative AI to analyze user preferences based on the emotion data obtained from the emotion engine, as well as the user's preferences and past browsing history. The generative AI uses natural language processing and machine learning algorithms to identify content that the user is likely to like. In this process, the emotion data more accurately reflects the user's real-time preferences, helping to select the most suitable content.

[0174] The server then generates a list of recommended content based on the analysis results. If the emotional data indicates that the user is relaxed, relaxing content will be selected. Depending on the emotion, additional information (comments from directors and writers, interviews, behind-the-scenes information, etc.) will also be selected and added to the list.

[0175] The server assembles the generated content list and additional information into a data packet and sends it to the user's device. The device unpacks and decrypts the received data, verifies the content, and displays it on the user interface. This allows the user to easily view the recommended content and related information.

[0176] For example, if emotional data indicates that a user likes action movies and is enjoying them in real time, the server can recommend movies like "The Avengers" and "Batman," along with director interviews and behind-the-scenes information.

[0177] As described above, the system of the present invention provides users with a personalized experience and allows them to enjoy content more deeply by making advanced recommendations based on user preferences and real-time emotional data.

[0178] The processing flow will be explained below.

[0179] Step 1:

[0180] The user inputs their preferences and past viewing history into the device, such as "I like action movies" or "The movie I saw recently was a superhero movie."

[0181] Step 2:

[0182] The device formats the user's input data and converts it into an appropriate data format, for example, converting the input data into JSON or XML.

[0183] Step 3:

[0184] The device sends the formatted data to the server using a secure communication protocol such as HTTPS.

[0185] Step 4:

[0186] The device's camera and microphone, or a wearable device, can be used to collect real-time emotional data from the user, for example, by measuring heart rate and skin temperature to estimate the user's emotional state.

[0187] Step 5:

[0188] The device transmits real-time emotion data to a server, again using a secure communication protocol.

[0189] Step 6:

[0190] The server preprocesses the user data (preferences, browsing history, and emotion data) received by the server. Specifically, it removes redundancies and noise from the data and formats it.

[0191] Step 7:

[0192] The emotion engine in the server analyzes the user's emotion data and identifies their current emotional state, for example, recognizing whether the user is "relaxed" or "excited."

[0193] Step 8:

[0194] The server passes the user's preference and emotional data to the AI ​​for analysis. The AI ​​then uses natural language processing and machine learning algorithms to select the most appropriate content based on the user's preferences and current emotional state.

[0195] Step 9:

[0196] The server generates a list of recommended content based on the analysis results. For example, if it is determined that the user is in a "relaxed" state and likes "action movies," it will list relaxing action movies such as "Guardians of the Galaxy" and "Iron Man."

[0197] Step 10:

[0198] Collect additional information related to the content recommended by the server, such as director and writer comments, interviews, and behind-the-scenes information.

[0199] Step 11:

[0200] The server packages the generated content list and additional information into a data packet, which may include compressing and / or encrypting the data.

[0201] Step 12:

[0202] The server sends the data packets to the terminal, again using a secure communications protocol.

[0203] Step 13:

[0204] The terminal decompresses and decrypts the data packets it receives and checks the integrity of the contents, for example, checking that the data is not corrupted and that it contains all the required information.

[0205] Step 14:

[0206] The device will then display the decompressed and decrypted data in a user interface, where the user can view a list of recommended content and related additional information.

[0207] Step 15:

[0208] Users select the content they are interested in. For example, if they select "Guardians of the Galaxy," they can view details about the movie, as well as related comments and interviews.

[0209] Through these steps, the system of the present invention realizes advanced recommendations based on user preferences and real-time emotional data, providing users with a personalized entertainment experience.

[0210] Example 2

[0211] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0212] Conventional recommendation systems often make recommendations based solely on a user's browsing history and preferences, and are unable to provide personalized recommendations that take into account real-time emotional states. Another issue is that they do not provide sufficient additional information related to the recommended content, making it difficult for users to fully enjoy the content.

[0213] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0214] In this invention, the server includes means for collecting user preferences, past browsing history, and real-time emotional data, means for transmitting this data to the server, means for preprocessing and shaping the data, means for analyzing the emotional data to understand the user's emotional state, means for analyzing the user's preferences based on the emotional data, preferences, and past browsing history using a generative AI, means for generating a list of recommended content based on the analysis results, means for collecting additional information related to the recommended content, means for transmitting this list of recommended content and additional information to the user, and means for displaying them to the user. This enables more individually optimized content recommendations that reflect the user's real-time emotional state and the provision of related additional information.

[0215] A "user" is an entity that utilizes the system to input preferences, past browsing history, and real-time emotional data.

[0216] "Preferences" are data of favorable preferences for specific genres or types of content entered by the user.

[0217] "Past viewing history" is history data of content that a user has viewed or read in the past.

[0218] "Real-time emotional data" is data that indicates the real-time emotional state expressed by a user while viewing or browsing content.

[0219] A "terminal" is a device that a user uses to input preferences, past browsing history, and real-time emotional data and transmit it to a server.

[0220] A "server" is a device that receives data sent from a user, analyzes and processes it, generates a list of content and additional information, and sends it back to the user's terminal.

[0221] An "emotion engine" is a technology that analyzes real-time emotional data and understands the user's emotional state.

[0222] "Generative AI" is an algorithm that uses artificial intelligence to analyze user preferences based on input data and select the most appropriate content.

[0223] "Recommended content" refers to entertainment information such as movies and manga that the generative AI has analyzed and determined to be suitable for the user.

[0224] "Additional Information" is additional information related to the recommended content, such as creator or producer comments, interviews, behind-the-scenes information, etc.

[0225] The "content list" is a list of multiple pieces of content recommended to the user and their corresponding additional information.

[0226] "Data preprocessing" is a process of formatting received data and filtering out unnecessary data.

[0227] The present invention is a system that provides customized content recommendations using user preferences, past browsing history, and real-time emotion data. This system is composed of a user, a terminal, a server, and an emotion engine.

[0228] First, users input their preferences and browsing history into their devices. Specifically, they input data such as their favorite genres and the movies and manga they have recently watched. In addition, wearable devices, cameras, microphones, etc. are used to collect real-time emotional data. For example, a wearable device measures heart rate, a camera recognizes facial expressions, and a microphone analyzes voice tone.

[0229] The terminal formats this data and sends it to the server. This transmission uses the HTTPS protocol to ensure data security. The server first formats the received data and performs preprocessing such as filtering. Specifically, it uses Python and SQL to normalize the data and handle missing values.

[0230] Next, the emotion engine in the server analyzes the real-time emotion data. The emotion engine uses Python and machine learning libraries (e.g., Pytorch and TensorFlow) to understand the user's emotional state. For example, it determines whether the user is enjoying or nervous while watching a movie.

[0231] The server then uses a generative AI model to analyze user preferences based on their preferences, past browsing history, and emotional data. The generative AI model (e.g., BERT or GPT) uses natural language processing and machine learning algorithms to select the most suitable content for the user. The server then analyzes the user's preferences by inputting a prompt. For example, the prompt could be "action movies I like when I'm relaxed."

[0232] The server generates a list of recommended content based on the analysis results. If the user is in a relaxed state, it will select relaxing movies or manga, and collect additional information (such as comments from the creators or producers, interviews, and behind-the-scenes information) to add to the list. This list and additional information are then organized into a data packet and sent to the device.

[0233] The device will decompress and decrypt this data, verify the content, and then display it on the user interface, allowing users to easily view the recommended content and related information.

[0234] For example, if the emotional data indicates that the user likes action movies and is enjoying watching them, the server can input a prompt such as, "I like action movies, so please generate a list of movies that I recommend to you when you're currently enjoying them," into the generative AI model. As a result, the server can recommend movies such as "Batman" and "Inception," and also provide interviews with directors and behind-the-scenes information.

[0235] As described above, the system of the present invention utilizes real-time emotional data in addition to user preferences and browsing history to provide individually optimized content recommendations to users, allowing users to enjoy a deeper, more personalized experience.

[0236] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0237] Step 1:

[0238] Users use the device to input their preferences and past browsing history, including data such as their favorite genres and recently viewed movies and comics. Wearable devices, cameras, and microphones are also used to collect real-time emotional data. For example, wearable devices can collect heart rate data, cameras can analyze facial expressions, and microphones can analyze tone of voice.

[0239] Input: User preferences, past browsing history, real-time sentiment data

[0240] Output: Formatted user data (JSON format)

[0241] Step 2:

[0242] The device formats the collected user data, specifically converting preferences, browsing history, and sentiment data into an appropriate data format (e.g., JSON), making the data more consistent and easier to work with.

[0243] Input: User preferences, past browsing history, real-time sentiment data

[0244] Output: Formatted user data (JSON format)

[0245] Step 3:

[0246] The device sends the formatted data to the server, using the HTTPS protocol to ensure data security.

[0247] Input: Formatted user data (JSON format)

[0248] Output: Data sent to the server

[0249] Step 4:

[0250] The server first formats the received data and performs preprocessing such as filtering, etc. Specifically, it uses Python and SQL to normalize the data, handle missing values, convert data types, etc.

[0251] Input: Data sent to the server

[0252] Output: Preprocessed data

[0253] Step 5:

[0254] The emotion engine in the server analyzes the received real-time emotion data and uses machine learning libraries (Pytorch and TensorFlow) to understand the user's emotional state (e.g., enjoying, nervous, etc.).

[0255] Input: Preprocessed data (especially real-time emotion data)

[0256] Output: Parsed emotional state

[0257] Step 6:

[0258] The server uses a generative AI model to analyze user preferences based on their preferences, past browsing history, and emotional data. It uses natural language processing (NLP) and machine learning algorithms (e.g., BERT and GPT) to select the most suitable content for the user. It generates a prompt and inputs it into the generative AI. For example, "Action movies I like in a relaxed state."

[0259] Input: Preferences, past browsing history, analyzed emotional state

[0260] Output: A list of content that best suits the user

[0261] Step 7:

[0262] The server generates a list of recommended content based on the analysis results. For example, if you are in a relaxing state, it will select relaxing movies or manga. It also collects additional relevant information (comments from the creators, interviews, behind-the-scenes information) and adds it to the list.

[0263] Input: A list of content that best suits the user

[0264] Output: A list of recommended content and additional information

[0265] Step 8:

[0266] The server configures the generated content list and additional information into a data packet and transmits it to the user's terminal.

[0267] Input: List of recommended content and additional information

[0268] Output: Data packets sent to the terminal

[0269] Step 9:

[0270] The device decompresses and decrypts the received data packets, verifies the contents, and then displays the data on the user interface (UI), allowing the user to easily view the recommended content and related information.

[0271] Input: Data packets sent to the terminal

[0272] Output: A list of recommended content and additional information displayed in a user interface.

[0273] (Application example 2)

[0274] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0275] Conventional content recommendation systems recommend content based on user preferences and past browsing history, but do not take into account real-time emotional changes. This makes it difficult to provide content that best suits the user's current psychological state, potentially resulting in a poor user experience. Furthermore, the provision of related information is limited, resulting in a one-sided content viewing experience.

[0276] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for the user to input preferences and past browsing history, means for transmitting the preferences, past browsing history, and real-time emotional data to the server, and means for analyzing the user's preferences using a generation AI based on the preferences, past browsing history, and real-time emotional data. This enables more accurate content recommendations suited to the user's current emotional state, and makes it possible to enrich the content viewing experience by providing related information.

[0277] A "user" is an individual who utilizes the system to receive content recommendations.

[0278] "Preferences" refers to information indicating a user's tendency or taste to prefer content of a particular genre or type.

[0279] "Past viewing history" is log data of content that a user has previously viewed or read.

[0280] "Real-time emotional data" refers to data collected in real time about the emotional state that a user shows while viewing content.

[0281] A "server" is a computer system that processes data received from a user and returns analytical results.

[0282] "Generative AI" is an artificial intelligence technology that uses natural language processing and machine learning algorithms to analyze user preferences and recommend the most appropriate content.

[0283] "Analysis results" refers to data obtained by the server using generated AI to analyze user preferences, browsing history, and real-time emotional data.

[0284] A "list of recommended content" is a series of content that is generated by the server based on the analysis results and recommended to the user.

[0285] "Additional information" is supplemental information related to the recommended content that enriches the user's viewing experience.

[0286] A "wearable device" is a hardware device worn by a user for collecting emotional data.

[0287] The "camera" is a device that analyzes the user's movements and facial expressions to collect real-time emotional data.

[0288] A "microphone" is a voice input device for analyzing the emotional state of a user from their voice.

[0289] "Media content" is a general term for viewable digital content such as video and audio.

[0290] "System" means an integrated mechanism for consistently collecting, analyzing, recommending, and displaying user data.

[0291] The present invention is a system that recommends optimal content by utilizing a user's preferences, past browsing history, and real-time emotional data. This system is composed of a user, a terminal, a server, and an emotional engine for analyzing the emotional data.

[0292] First, users input their preferences and browsing history into devices such as smartphones or tablets. While the user is viewing content, real-time emotional data is also collected. This emotional data is collected using hardware such as wearable devices, cameras, and microphones. Specifically, the EmotionRecognition library is used for facial recognition and voice analysis.

[0293] The device formats the collected preferences, past browsing history data, and real-time emotion data and sends them to the server. The server receives this data and first performs preprocessing such as data shaping and filtering. The emotion engine then analyzes the emotion data to understand the user's emotional state.

[0294] Machine learning algorithms and natural language processing techniques are used for data preprocessing and sentiment analysis. After this, the server analyzes the user's preferences using generative AI to identify the content the user is currently looking for. Generative AI can use frameworks such as TensorFlow and PyTorch.

[0295] Based on the analysis results, the server generates a list of recommended content, such as manga or movies that are optimized for the user's preferences and emotional state. In addition, related additional information (such as creator comments, interviews, and behind-the-scenes information) is also collected and added to the list of recommended content.

[0296] The server assembles the generated content list and additional information into a data packet and sends it to the user's device. The device then decompresses and decrypts the received data, verifies the content, and displays it on the user interface. This allows the user to easily view the recommended content and related information.

[0297] As a specific example, if a user likes action movies and there is real-time emotional data showing that they are enjoying the movie, the server can recommend movies such as "Action Movie 1" and "Action Movie 2," and also provide interviews with directors and behind-the-scenes information about filming.

[0298] Example prompt sentence:

[0299] "Recommend the best action movies to users based on their current emotional data and past viewing history."

[0300] The system enables advanced recommendations that are optimized for a user's preferences and real-time emotional state, providing a more personalized content experience.

[0301] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0302] Step 1:

[0303] Users use their smartphones or tablets to input their preferences and past browsing history, including their preferred genres (e.g., action, comedy) and the titles of movies and manga they have watched in the past.

[0304] Step 2:

[0305] While the user is watching, we use a wearable device, camera, and microphone to collect real-time emotional data. We use the EmotionRecognition library to analyze the emotional state (e.g., enjoying, nervous) and generate this emotional data.

[0306] Step 3:

[0307] The device formats the user's preferences, past browsing history, and real-time emotion data and sends them to the server, for example, structuring the data in JSON format and sending the data to the server using an HTTP request.

[0308] Step 4:

[0309] The server performs preprocessing such as formatting and filtering of the data received from the terminal. Specifically, it removes unnecessary data, standardizes the format, and formats the data in a way that makes it easier to process.

[0310] Step 5:

[0311] The emotion engine in the server analyzes the received emotion data to understand the user's real-time emotional state. This analysis uses machine learning algorithms to extract the user's emotional state (e.g., enjoying, nervous).

[0312] Step 6:

[0313] The server uses generative AI based on emotion data obtained from the emotion engine, as well as preferences and past browsing history to analyze user preferences, and identifies the most suitable content using frameworks such as TensorFlow and PyTorch.

[0314] Step 7:

[0315] Based on the analysis, the server generates a list of recommended content, including movies and manga optimized for the user's emotional state and preferences.

[0316] Step 8:

[0317] The server collects additional information related to the recommended content (e.g., director's comments, interviews, behind-the-scenes information) and adds it to the list of recommended content.

[0318] Step 9:

[0319] The server then assembles the generated content list and additional information into a data packet and sends it to the terminal. The data is compressed and sent in the form of an HTTP response.

[0320] Step 10:

[0321] The terminal decompresses and decrypts the received data packets and verifies their contents, specifically by checking the data integrity and making any necessary formatting changes.

[0322] Step 11:

[0323] The terminal displays a list of verified recommended content and additional information on a user interface, allowing the user to easily browse the recommended content and related information.

[0324] Example prompt: "Recommend the best action movie for the user based on their current emotional data and past viewing history."

[0325] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0326] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0327] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0328] [Second embodiment]

[0329] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0330] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0331] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0332] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0333] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0334] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0335] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0336] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0337] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0338] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0339] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0340] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0341] This invention is a system that analyzes user preferences and past browsing history to provide customized manga and movie recommendations. This system is composed of users, terminals, and servers, and by clearly dividing the roles of each, it achieves advanced recommendation functionality.

[0342] First, users input their preferences and browsing history, and the user's device receives this data, formats it, and sends it to the server.

[0343] The server uses a generative AI to analyze the received data. The generative AI uses natural language processing (NLP) and machine learning algorithms to understand the user's preferences. For example, if a user likes action movies and has watched many "superhero movies" in the past, the AI ​​can determine that the user particularly likes action-themed superhero movies.

[0344] Next, the server generates a list of recommendations for appropriate manga and movies based on the analysis results. For example, if it determines that the user likes superhero movies, it will list superhero movies such as "Guardians of the Galaxy" and "Batman."

[0345] Additionally, the server collects additional information about the recommended film, such as director and writer comments, interviews, behind-the-scenes information, etc. For example, for a recommendation of "Guardians of the Galaxy," providing an interview with the director and behind-the-scenes information about filming can help users better understand and enjoy the film.

[0346] The server compiles this information and sends it to the user's device as the final content, where it displays the received information in a user interface for easy access. For example, it displays a list of recommended movies along with behind-the-scenes stories and comments about each movie.

[0347] Therefore, the present invention allows users to receive recommendations for manga and movies that are tailored to their preferences, and to enjoy the works even more through in-depth related information.

[0348] The processing flow will be explained below.

[0349] Step 1:

[0350] The user inputs their preferences and past viewing history. For example, the user inputs information such as "I like action movies" or "The movie I watched recently was a superhero movie."

[0351] Step 2:

[0352] The terminal formats the user's input data, specifically converting it into the appropriate data model so that subsequent processing can proceed smoothly.

[0353] Step 3:

[0354] The device sends the formatted data to the server, where it is transmitted using a secure communications protocol.

[0355] Step 4:

[0356] Before the server analyzes the received user data, it performs preprocessing such as shaping and filtering the data, for example, removing noise and inconsistencies in the input data.

[0357] Step 5:

[0358] The server passes the preprocessed data to the generation AI, which analyzes the user's preferences. The generation AI uses natural language processing and machine learning algorithms to identify the user's preferences, taking into account data from other users with similar preferences.

[0359] Step 6:

[0360] The server generates a list of recommended content based on the results of AI analysis. For example, if it determines that the user likes action movies, it will list movies such as "Batman" and "Iron Man."

[0361] Step 7:

[0362] The server collects additional information about the content it recommends, such as director and writer comments, interviews, and behind-the-scenes information, to help users better understand the work.

[0363] Step 8:

[0364] The server assembles the generated content list and additional information into a data packet, compressing and encrypting the data as necessary.

[0365] Step 9:

[0366] The server sends the data packet to the terminal, which again transmits the data using a secure communications protocol.

[0367] Step 10:

[0368] The terminal decompresses and decrypts the received data packets and verifies their contents, checking for inconsistencies and errors.

[0369] Step 11:

[0370] The device will then display the decompressed and decrypted data in a user interface, where the user can view a list of recommended content and related additional information.

[0371] Step 12:

[0372] Users can select content they are interested in. For example, if a user selects "Batman," they can view details and related information about the work.

[0373] Through these steps, the system of the present invention can provide customized content recommendations based on the user's preferences and related additional information.

[0374] Example 1

[0375] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0376] Conventional recommendation systems have difficulty accurately understanding user preferences and providing appropriate content. They also lack the functionality to provide related information that users are interested in. This has limited the improvement in user satisfaction and made it difficult to increase the frequency of system use.

[0377] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0378] In this invention, the server includes means for a user to input preferences and past browsing history, means for formatting the preferences and past browsing history and transmitting the formatted information to the server, means for analyzing the user's preferences using a generative AI model based on the preferences and past browsing history, means for generating a list of recommended content based on the analysis results, means for collecting additional information related to the recommended content, means for transmitting the list of recommended content and the additional information to the user, and means for displaying the list of recommended content and the additional information to the user, thereby enabling the provision of content and related information tailored to the user's individual preferences.

[0379] "User" refers to an individual or group of people who use this system to receive content recommendations.

[0380] "Preferences" refer to preferences such as genres or themes that a user is particularly interested in and tends to enjoy in preference to other things.

[0381] "Past browsing history" refers to a record of content that a user has previously viewed or read.

[0382] "Formatting" refers to the process of preparing data according to certain rules, so that the data can be sent correctly to the server.

[0383] A "server" is a part of an information processing system that responds to requests from clients via a network, analyzing data and providing information.

[0384] A "generative AI model" refers to an artificial intelligence model that uses machine learning algorithms and natural language processing techniques to analyze data and understand user preferences.

[0385] "Analysis" refers to the process of analyzing collected data in detail and deriving useful information and patterns from it.

[0386] "Recommended content" refers to entertainment media such as movies and manga that are selected by AI based on the user's preferences and past browsing history and recommended to the user.

[0387] "Additional Information" is supplemental information related to the recommended content, such as director's commentary, interviews, and behind-the-scenes information.

[0388] "Transmission" refers to the act of a terminal transferring data to a server, or the act of a server transferring data to a user.

[0389] "Display" refers to the visualization of the received data and recommended content on the user interface of the terminal.

[0390] This invention is a system that analyzes user preferences and past browsing history to provide customized content recommendations. This system is composed of a user, a terminal, and a server, and by clearly dividing the roles of each, it achieves advanced recommendation functionality.

[0391] First, the user inputs their preferences and browsing history. This input is done using a device such as a smartphone or PC. The input data is formatted by the device and organized as structured data in JSON format or similar. The device then sends the formatted data to the server.

[0392] The server uses a generative AI model to analyze the received data. The generative AI model is implemented using the Python libraries Scikit-learn and TensorFlow. Specifically, it uses natural language processing (NLP) techniques and machine learning algorithms to deeply analyze the user's preferences. For example, if a user likes action movies and has watched many "superhero movies" in the past, the AI ​​will determine that the user particularly likes action-themed superhero movies.

[0393] Next, the server generates a list of appropriate content recommendations based on the analysis results. When generating this list, the server uses content information stored in a database such as MySQL. For example, if it determines that the user likes superhero movies, it will list related works such as "Superhero Movie A" and "Superhero Movie B."

[0394] The server also collects additional information about the recommended content, such as comments from directors and writers, interviews, and behind-the-scenes information. This information is collected using web scraping techniques, specifically using Beautiful Soup and Scrapy. For example, for a recommendation of "Superhero Movie A," the server collects interviews with the director and behind-the-scenes information about filming.

[0395] This information is then compiled and sent to the device, which then displays it in a user interface for easy access. For example, the device could display a list of recommended movies along with behind-the-scenes stories and comments about each one.

[0396] Below are some examples of prompt sentences to input into the generative AI model.

[0397] Example prompt sentence:

[0398] "If a user likes action movies and has watched a lot of 'action movie A' and 'action movie B' in the past, what other movies can we recommend?"

[0399] As described above, the present invention realizes the provision of content and related information that are tailored to the individual preferences of a user.

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

[0401] Step 1:

[0402] Users input their preferences and past viewing history. The input data is provided in the form of genres, specific movie or manga titles, and viewing dates and times. This results in input data formats such as "Action Movies," "Movie A," and "2022-01-01."

[0403] Step 2:

[0404] The device receives the data entered by the user and formats it. The formatted data is saved in JSON format with the following structure: {"genre": "Action", "history": [{"title": "Movie A", "date": "2022-01-01"},{"title": "Movie B", "date": "2022-02-01"}]}. The formatted data is sent to the server.

[0405] Step 3:

[0406] The server receives the JSON-formatted data sent from the device. The received data undergoes appropriate data preprocessing before being passed to the generative AI model. This includes data normalization and filtering of unnecessary information. This preprocessing results in a clean dataset for analysis.

[0407] Step 4:

[0408] The server analyzes the preprocessed data using a generative AI model, which uses Python libraries (such as Scikit-learn and TensorFlow). This analysis helps understand the user's preferences and arrives at a conclusion, such as "the user particularly likes action movies."

[0409] Step 5:

[0410] The server generates a list of appropriate content based on the analysis results. It queries and retrieves related content from movie and manga data stored in a database management system (e.g., MySQL). For example, it searches for works tagged with "action" and "hero movies" based on the analysis results and lists "Content A" and "Content B."

[0411] Step 6:

[0412] The server collects additional information related to the recommended content. Specifically, it uses web scraping tools such as Beautiful Soup and Scrapy to collect director interviews and behind-the-scenes information. For example, for "Content A," it collects "director interview articles" and "behind-the-scenes articles."

[0413] Step 7:

[0414] The server formats the generated recommendation list and the collected additional information into the final content. The formatted data is converted back into JSON format, with the format "{"recommended": ["Content A", "Content B"], "additional_info": {"Content A": ["Director's Interview", "Behind the Scenes"]}}".

[0415] Step 8:

[0416] The server transmits the final content to the terminal, thereby transmitting data of detailed recommendation information to be provided to the user.

[0417] Step 9:

[0418] The device displays the final content in a user interface, allowing the user to visually view a list of recommended content and related additional information, such as a poster of a recommended movie and related director interviews or behind-the-scenes information.

[0419] (Application example 1)

[0420] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0421] Conventional content distribution services have difficulty in appropriately recommending content that matches a user's preferences, and lack a system that provides detailed background information or expert interviews about the recommended content. This makes it difficult for users to find content that is tailored to their preferences, and they lack opportunities to gain a deeper understanding of or be moved by the content.

[0422] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0423] In this invention, the server includes means for inputting a user's preferences and past browsing history, means for transmitting the preferences and past browsing history to the server, means for analyzing the user's preferences using a generation AI based on the preferences and past browsing history, means for generating a list of recommended content based on the analysis results, means for collecting additional information related to the recommended content, means for displaying the list of recommended content and the additional information on a user interface, and means for providing expert interviews and production background information for the recommended content. This allows users to optimally search for content that matches their preferences and obtain in-depth information about that content.

[0424] "Preferences" are personal tastes and interests that a user has for a particular type of content (for example, video works or digital comics).

[0425] "Past browsing history" refers to a record of content that a user has previously viewed or read.

[0426] "Generative AI" is an artificial intelligence technology that uses natural language processing and machine learning algorithms to analyze user preferences and provide optimal recommendations.

[0427] "Analysis results" refers to data and information about a user's preferences that the generating AI generates based on the user's preferences and past browsing history.

[0428] "Recommended content" refers to content such as video works and digital comics that are recommended to users based on the analysis results.

[0429] "Additional information" refers to supplementary information related to the recommended content, such as director or writer comments, expert interviews, and production background information.

[0430] "User interface" refers to the screens and methods of operation that allow a user to access content lists and additional information.

[0431] "Expert Interviews" refers to interview articles that include expert insights and inside stories related to the recommended content.

[0432] "Production Background Information" refers to detailed information about the production process and background of the recommended content.

[0433] "Digital comics" refers to manga and graphic novels available in e-book format.

[0434] This invention is a system that analyzes a user's preferences and past browsing history to provide customized content recommendations (video works and digital comics). This system is composed of a user, a terminal, and a server, and by clearly dividing the roles of each, it achieves advanced recommendation functionality.

[0435] First, the user inputs their preferences and browsing history. This input is done on a device such as a smartphone or tablet. The device receives this data, formats it, and sends it to the server. The software on the device uses Python and the requests library.

[0436] The server uses a generative AI to analyze the received data. This generative AI uses natural language processing (NLP) and machine learning algorithms to understand the user's preferences. Web frameworks such as Flask are used as server-side software. For example, if a user likes action movies and has watched many "superhero movies" in the past, the generative AI will determine that the user particularly likes action-themed superhero movies.

[0437] Next, the server generates a list of appropriate content recommendations based on the analysis results. For example, if it determines that the user likes superhero movies, it will list superhero movies such as "space adventure movies" and "city defender movies." The server also collects additional information about the recommended content. This additional information includes comments from directors and writers, expert interviews, and production background information. For example, for a recommendation of "space adventure movies," it will provide an interview with the director and background story of the filming.

[0438] The server compiles this information and sends it to the user's device as the final content. The user's device displays the received information in a user interface for easy access. For example, it displays a list of recommended movies or manga along with detailed information about each piece of content.

[0439] As a concrete example, the following prompt sentence is input to the generative AI model:

[0440] User preferences: Action, Hero

[0441] User's past browsing history: Avengers, Spider-Man, Batman

[0442] Based on this input, the generative AI will provide the following output:

[0443] Recommended content:

[0444] Title: Space adventure movie

[0445] Description: A heroic adventure to save the universe

[0446] Director's interview: The director talks about the background of the production

[0447] Title: City Guardian Movie

[0448] Description: A hero's challenge to protect the city

[0449] Director's Interview: The Director Discusses His New Hero Image

[0450] As described above, the system of the present invention allows users to receive recommendations for content that matches their preferences, and to enjoy works even more through in-depth information related to the content.

[0451] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0452] Step 1:

[0453] Users input their preferences and past viewing history. Using a smartphone or tablet, users input their preferences (e.g., action, superheroes) and the shows they have watched in the past (e.g., Avengers, Spider-Man). After inputting, this data is stored on the device.

[0454] Step 2:

[0455] The device sends input data to the server. Using Python and the requests library, the device formats the user's preferences and past browsing history into JSON format and sends it to the server via an HTTP POST request. In this setup, the data sent is in the following format:

[0456] {

[0457] "preferences": ["Action", "Hero"],

[0458] "history": ["Avengers", "Spider-Man"]

[0459] }

[0460] Step 3:

[0461] The server analyzes the received data. The server receives the HTTP request using a web framework such as Flask, and then analyzes the data using generative AI (e.g., GPT). Specifically, it uses natural language processing (NLP) and machine learning algorithms to understand the user's preferences and generate an analysis result. As a result of this analysis, it is determined that the user likes action superhero movies.

[0462] Step 4:

[0463] The server generates a list of recommended content based on the analysis results. Based on the analysis results of the generative AI, the server creates a list of optimal movies and digital comics. For example, content such as "space adventure movies" and "city guardian movies" will be listed.

[0464] Step 5:

[0465] The server collects additional information related to the content it recommends. For example, the server collects director and author comments, expert interviews, and production background information for the recommended content. For example, the server obtains information about the director's interview and the filming background of a "space adventure movie."

[0466] Step 6:

[0467] The server sends a list of recommended content and additional information to the device. After all the information is collected, the server compiles it and sends it to the user's device in JSON format.

[0468] Step 7:

[0469] The device displays the received information in a user interface. The device displays the received list of recommended content and additional information in a user interface for easy access by the user. For example, a list of recommended movies or manga can be displayed along with detailed information about each piece of content (such as an interview with the director or background information on the production).

[0470] Through the above processing steps, the user can optimally search for content that matches his or her preferences, and can also obtain in-depth information about that content.

[0471] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0472] This invention is a system that provides customized manga and movie recommendations by utilizing real-time emotional data in addition to user preferences and past browsing history. This system is composed of a user, a terminal, a server, and an emotional engine.

[0473] First, users input their preferences and past browsing history into the device, and real-time emotional data expressed by users while watching or browsing is also collected. This may be done using wearable devices, cameras, microphones, etc.

[0474] The device formats this data and sends it to the server. The server receives the data and performs preprocessing such as formatting and filtering. Next, the emotion engine in the server analyzes the user's emotion data and understands their emotional state. For example, it can extract information such as whether the user is enjoying or nervous while watching a movie.

[0475] The server uses generative AI to analyze user preferences based on the emotion data obtained from the emotion engine, as well as the user's preferences and past browsing history. The generative AI uses natural language processing and machine learning algorithms to identify content that the user is likely to like. In this process, the emotion data more accurately reflects the user's real-time preferences, helping to select the most suitable content.

[0476] The server then generates a list of recommended content based on the analysis results. If the emotional data indicates that the user is relaxed, relaxing content will be selected. Depending on the emotion, additional information (comments from directors and writers, interviews, behind-the-scenes information, etc.) will also be selected and added to the list.

[0477] The server assembles the generated content list and additional information into a data packet and sends it to the user's device. The device unpacks and decrypts the received data, verifies the content, and displays it on the user interface. This allows the user to easily view the recommended content and related information.

[0478] For example, if emotional data indicates that a user likes action movies and is enjoying them in real time, the server can recommend movies like "The Avengers" and "Batman," along with director interviews and behind-the-scenes information.

[0479] As described above, the system of the present invention provides users with a personalized experience and allows them to enjoy content more deeply by making advanced recommendations based on user preferences and real-time emotional data.

[0480] The processing flow will be explained below.

[0481] Step 1:

[0482] The user inputs their preferences and past viewing history into the device, such as "I like action movies" or "The movie I saw recently was a superhero movie."

[0483] Step 2:

[0484] The device formats the user's input data and converts it into an appropriate data format, for example, converting the input data into JSON or XML.

[0485] Step 3:

[0486] The device sends the formatted data to the server using a secure communication protocol such as HTTPS.

[0487] Step 4:

[0488] The device's camera and microphone, or a wearable device, can be used to collect real-time emotional data from the user, for example, by measuring heart rate and skin temperature to estimate the user's emotional state.

[0489] Step 5:

[0490] The device transmits real-time emotion data to a server, again using a secure communication protocol.

[0491] Step 6:

[0492] The server preprocesses the user data (preferences, browsing history, and emotion data) received by the server. Specifically, it removes redundancies and noise from the data and formats it.

[0493] Step 7:

[0494] The emotion engine in the server analyzes the user's emotion data and identifies their current emotional state, for example, recognizing whether the user is "relaxed" or "excited."

[0495] Step 8:

[0496] The server passes the user's preference and emotional data to the AI ​​for analysis. The AI ​​then uses natural language processing and machine learning algorithms to select the most appropriate content based on the user's preferences and current emotional state.

[0497] Step 9:

[0498] The server generates a list of recommended content based on the analysis results. For example, if it is determined that the user is in a "relaxed" state and likes "action movies," it will list relaxing action movies such as "Guardians of the Galaxy" and "Iron Man."

[0499] Step 10:

[0500] Collect additional information related to the content recommended by the server, such as director and writer comments, interviews, and behind-the-scenes information.

[0501] Step 11:

[0502] The server packages the generated content list and additional information into a data packet, which may include compressing and / or encrypting the data.

[0503] Step 12:

[0504] The server sends the data packets to the terminal, again using a secure communications protocol.

[0505] Step 13:

[0506] The terminal decompresses and decrypts the data packets it receives and checks the integrity of the contents, for example, checking that the data is not corrupted and that it contains all the required information.

[0507] Step 14:

[0508] The device will then display the decompressed and decrypted data in a user interface, where the user can view a list of recommended content and related additional information.

[0509] Step 15:

[0510] Users select the content they are interested in. For example, if they select "Guardians of the Galaxy," they can view details about the movie, as well as related comments and interviews.

[0511] Through these steps, the system of the present invention realizes advanced recommendations based on user preferences and real-time emotional data, providing users with a personalized entertainment experience.

[0512] Example 2

[0513] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0514] Conventional recommendation systems often make recommendations based solely on a user's browsing history and preferences, and are unable to provide personalized recommendations that take into account real-time emotional states. Another issue is that they do not provide sufficient additional information related to the recommended content, making it difficult for users to fully enjoy the content.

[0515] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0516] In this invention, the server includes means for collecting user preferences, past browsing history, and real-time emotional data, means for transmitting this data to the server, means for preprocessing and shaping the data, means for analyzing the emotional data to understand the user's emotional state, means for analyzing the user's preferences based on the emotional data, preferences, and past browsing history using a generative AI, means for generating a list of recommended content based on the analysis results, means for collecting additional information related to the recommended content, means for transmitting this list of recommended content and additional information to the user, and means for displaying them to the user. This enables more individually optimized content recommendations that reflect the user's real-time emotional state and the provision of related additional information.

[0517] A "user" is an entity that utilizes the system to input preferences, past browsing history, and real-time emotional data.

[0518] "Preferences" are data of favorable preferences for specific genres or types of content entered by the user.

[0519] "Past viewing history" is history data of content that a user has viewed or read in the past.

[0520] "Real-time emotional data" is data that indicates the real-time emotional state expressed by a user while viewing or browsing content.

[0521] A "terminal" is a device that a user uses to input preferences, past browsing history, and real-time emotional data and transmit it to a server.

[0522] A "server" is a device that receives data sent from a user, analyzes and processes it, generates a list of content and additional information, and sends it back to the user's terminal.

[0523] An "emotion engine" is a technology that analyzes real-time emotional data and understands the user's emotional state.

[0524] "Generative AI" is an algorithm that uses artificial intelligence to analyze user preferences based on input data and select the most appropriate content.

[0525] "Recommended content" refers to entertainment information such as movies and manga that the generative AI has analyzed and determined to be suitable for the user.

[0526] "Additional Information" is additional information related to the recommended content, such as creator or producer comments, interviews, behind-the-scenes information, etc.

[0527] The "content list" is a list of multiple pieces of content recommended to the user and their corresponding additional information.

[0528] "Data preprocessing" is a process of formatting received data and filtering out unnecessary data.

[0529] The present invention is a system that provides customized content recommendations using user preferences, past browsing history, and real-time emotion data. This system is composed of a user, a terminal, a server, and an emotion engine.

[0530] First, users input their preferences and browsing history into their devices. Specifically, they input data such as their favorite genres and the movies and manga they have recently watched. In addition, wearable devices, cameras, microphones, etc. are used to collect real-time emotional data. For example, a wearable device measures heart rate, a camera recognizes facial expressions, and a microphone analyzes voice tone.

[0531] The terminal formats this data and sends it to the server. This transmission uses the HTTPS protocol to ensure data security. The server first formats the received data and performs preprocessing such as filtering. Specifically, it uses Python and SQL to normalize the data and handle missing values.

[0532] Next, the emotion engine in the server analyzes the real-time emotion data. The emotion engine uses Python and machine learning libraries (e.g., Pytorch and TensorFlow) to understand the user's emotional state. For example, it determines whether the user is enjoying or nervous while watching a movie.

[0533] The server then uses a generative AI model to analyze user preferences based on their preferences, past browsing history, and emotional data. The generative AI model (e.g., BERT or GPT) uses natural language processing and machine learning algorithms to select the most suitable content for the user. The server then analyzes the user's preferences by inputting a prompt. For example, the prompt could be "action movies I like when I'm relaxed."

[0534] The server generates a list of recommended content based on the analysis results. If the user is in a relaxed state, it will select relaxing movies or manga, and collect additional information (such as comments from the creators or producers, interviews, and behind-the-scenes information) to add to the list. This list and additional information are then organized into a data packet and sent to the device.

[0535] The device will decompress and decrypt this data, verify the content, and then display it on the user interface, allowing users to easily view the recommended content and related information.

[0536] For example, if the emotional data indicates that the user likes action movies and is enjoying watching them, the server can input a prompt such as, "I like action movies, so please generate a list of movies that I recommend to you when you're currently enjoying them," into the generative AI model. As a result, the server can recommend movies such as "Batman" and "Inception," and also provide interviews with directors and behind-the-scenes information.

[0537] As described above, the system of the present invention utilizes real-time emotional data in addition to user preferences and browsing history to provide individually optimized content recommendations to users, allowing users to enjoy a deeper, more personalized experience.

[0538] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0539] Step 1:

[0540] Users use the device to input their preferences and past browsing history, including data such as their favorite genres and recently viewed movies and comics. Wearable devices, cameras, and microphones are also used to collect real-time emotional data. For example, wearable devices can collect heart rate data, cameras can analyze facial expressions, and microphones can analyze tone of voice.

[0541] Input: User preferences, past browsing history, real-time sentiment data

[0542] Output: Formatted user data (JSON format)

[0543] Step 2:

[0544] The device formats the collected user data, specifically converting preferences, browsing history, and sentiment data into an appropriate data format (e.g., JSON), making the data more consistent and easier to work with.

[0545] Input: User preferences, past browsing history, real-time sentiment data

[0546] Output: Formatted user data (JSON format)

[0547] Step 3:

[0548] The device sends the formatted data to the server, using the HTTPS protocol to ensure data security.

[0549] Input: Formatted user data (JSON format)

[0550] Output: Data sent to the server

[0551] Step 4:

[0552] The server first formats the received data and performs preprocessing such as filtering, etc. Specifically, it uses Python and SQL to normalize the data, handle missing values, convert data types, etc.

[0553] Input: Data sent to the server

[0554] Output: Preprocessed data

[0555] Step 5:

[0556] The emotion engine in the server analyzes the received real-time emotion data and uses machine learning libraries (Pytorch and TensorFlow) to understand the user's emotional state (e.g., enjoying, nervous, etc.).

[0557] Input: Preprocessed data (especially real-time emotion data)

[0558] Output: Parsed emotional state

[0559] Step 6:

[0560] The server uses a generative AI model to analyze user preferences based on their preferences, past browsing history, and emotional data. It uses natural language processing (NLP) and machine learning algorithms (e.g., BERT and GPT) to select the most suitable content for the user. It generates a prompt and inputs it into the generative AI. For example, "Action movies I like in a relaxed state."

[0561] Input: Preferences, past browsing history, analyzed emotional state

[0562] Output: A list of content that best suits the user

[0563] Step 7:

[0564] The server generates a list of recommended content based on the analysis results. For example, if you are in a relaxing state, it will select relaxing movies or manga. It also collects additional relevant information (comments from the creators, interviews, behind-the-scenes information) and adds it to the list.

[0565] Input: A list of content that best suits the user

[0566] Output: A list of recommended content and additional information

[0567] Step 8:

[0568] The server configures the generated content list and additional information into a data packet and transmits it to the user's terminal.

[0569] Input: List of recommended content and additional information

[0570] Output: Data packets sent to the terminal

[0571] Step 9:

[0572] The device decompresses and decrypts the received data packets, verifies the contents, and then displays the data on the user interface (UI), allowing the user to easily view the recommended content and related information.

[0573] Input: Data packets sent to the terminal

[0574] Output: A list of recommended content and additional information displayed in a user interface.

[0575] (Application example 2)

[0576] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0577] Conventional content recommendation systems recommend content based on user preferences and past browsing history, but do not take into account real-time emotional changes. This makes it difficult to provide content that best suits the user's current psychological state, potentially resulting in a poor user experience. Furthermore, the provision of related information is limited, resulting in a one-sided content viewing experience.

[0578] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for the user to input preferences and past browsing history, means for transmitting the preferences, past browsing history, and real-time emotional data to the server, and means for analyzing the user's preferences using a generation AI based on the preferences, past browsing history, and real-time emotional data. This enables more accurate content recommendations suited to the user's current emotional state, and makes it possible to enrich the content viewing experience by providing related information.

[0579] A "user" is an individual who utilizes the system to receive content recommendations.

[0580] "Preferences" refers to information indicating a user's tendency or taste to prefer content of a particular genre or type.

[0581] "Past viewing history" is log data of content that a user has previously viewed or read.

[0582] "Real-time emotional data" refers to data collected in real time about the emotional state that a user shows while viewing content.

[0583] A "server" is a computer system that processes data received from a user and returns analytical results.

[0584] "Generative AI" is an artificial intelligence technology that uses natural language processing and machine learning algorithms to analyze user preferences and recommend the most appropriate content.

[0585] "Analysis results" refers to data obtained by the server using generated AI to analyze user preferences, browsing history, and real-time emotional data.

[0586] A "list of recommended content" is a series of content that is generated by the server based on the analysis results and recommended to the user.

[0587] "Additional information" is supplemental information related to the recommended content that enriches the user's viewing experience.

[0588] A "wearable device" is a hardware device worn by a user for collecting emotional data.

[0589] The "camera" is a device that analyzes the user's movements and facial expressions to collect real-time emotional data.

[0590] A "microphone" is a voice input device for analyzing the emotional state of a user from their voice.

[0591] "Media content" is a general term for viewable digital content such as video and audio.

[0592] "System" means an integrated mechanism for consistently collecting, analyzing, recommending, and displaying user data.

[0593] The present invention is a system that recommends optimal content by utilizing a user's preferences, past browsing history, and real-time emotional data. This system is composed of a user, a terminal, a server, and an emotional engine for analyzing the emotional data.

[0594] First, users input their preferences and browsing history into devices such as smartphones or tablets. While the user is viewing content, real-time emotional data is also collected. This emotional data is collected using hardware such as wearable devices, cameras, and microphones. Specifically, the EmotionRecognition library is used for facial recognition and voice analysis.

[0595] The device formats the collected preferences, past browsing history data, and real-time emotion data and sends them to the server. The server receives this data and first performs preprocessing such as data shaping and filtering. The emotion engine then analyzes the emotion data to understand the user's emotional state.

[0596] Machine learning algorithms and natural language processing techniques are used for data preprocessing and sentiment analysis. After this, the server analyzes the user's preferences using generative AI to identify the content the user is currently looking for. Generative AI can use frameworks such as TensorFlow and PyTorch.

[0597] Based on the analysis results, the server generates a list of recommended content, such as manga or movies that are optimized for the user's preferences and emotional state. In addition, related additional information (such as creator comments, interviews, and behind-the-scenes information) is also collected and added to the list of recommended content.

[0598] The server assembles the generated content list and additional information into a data packet and sends it to the user's device. The device then decompresses and decrypts the received data, verifies the content, and displays it on the user interface. This allows the user to easily view the recommended content and related information.

[0599] As a specific example, if a user likes action movies and there is real-time emotional data showing that they are enjoying the movie, the server can recommend movies such as "Action Movie 1" and "Action Movie 2," and also provide interviews with directors and behind-the-scenes information about filming.

[0600] Example prompt sentence:

[0601] "Recommend the best action movies to users based on their current emotional data and past viewing history."

[0602] The system enables advanced recommendations that are optimized for a user's preferences and real-time emotional state, providing a more personalized content experience.

[0603] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0604] Step 1:

[0605] Users use their smartphones or tablets to input their preferences and past browsing history, including their preferred genres (e.g., action, comedy) and the titles of movies and manga they have watched in the past.

[0606] Step 2:

[0607] While the user is watching, we use a wearable device, camera, and microphone to collect real-time emotional data. We use the EmotionRecognition library to analyze the emotional state (e.g., enjoying, nervous) and generate this emotional data.

[0608] Step 3:

[0609] The device formats the user's preferences, past browsing history, and real-time emotion data and sends them to the server, for example, structuring the data in JSON format and sending the data to the server using an HTTP request.

[0610] Step 4:

[0611] The server performs preprocessing such as formatting and filtering of the data received from the terminal. Specifically, it removes unnecessary data, standardizes the format, and formats the data in a way that makes it easier to process.

[0612] Step 5:

[0613] The emotion engine in the server analyzes the received emotion data to understand the user's real-time emotional state. This analysis uses machine learning algorithms to extract the user's emotional state (e.g., enjoying, nervous).

[0614] Step 6:

[0615] The server uses generative AI based on emotion data obtained from the emotion engine, as well as preferences and past browsing history to analyze user preferences, and identifies the most suitable content using frameworks such as TensorFlow and PyTorch.

[0616] Step 7:

[0617] Based on the analysis, the server generates a list of recommended content, including movies and manga optimized for the user's emotional state and preferences.

[0618] Step 8:

[0619] The server collects additional information related to the recommended content (e.g., director's comments, interviews, behind-the-scenes information) and adds it to the list of recommended content.

[0620] Step 9:

[0621] The server then assembles the generated content list and additional information into a data packet and sends it to the terminal. The data is compressed and sent in the form of an HTTP response.

[0622] Step 10:

[0623] The terminal decompresses and decrypts the received data packets and verifies their contents, specifically by checking the data integrity and making any necessary formatting changes.

[0624] Step 11:

[0625] The terminal displays a list of verified recommended content and additional information on a user interface, allowing the user to easily browse the recommended content and related information.

[0626] Example prompt: "Recommend the best action movie for the user based on their current emotional data and past viewing history."

[0627] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0628] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0629] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0630] [Third embodiment]

[0631] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0632] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0633] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0634] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0635] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0636] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0637] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0638] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0639] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0640] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0641] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0642] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0643] This invention is a system that analyzes user preferences and past browsing history to provide customized manga and movie recommendations. This system is composed of users, terminals, and servers, and by clearly dividing the roles of each, it achieves advanced recommendation functionality.

[0644] First, users input their preferences and browsing history, and the user's device receives this data, formats it, and sends it to the server.

[0645] The server uses a generative AI to analyze the received data. The generative AI uses natural language processing (NLP) and machine learning algorithms to understand the user's preferences. For example, if a user likes action movies and has watched many "superhero movies" in the past, the AI ​​can determine that the user particularly likes action-themed superhero movies.

[0646] Next, the server generates a list of recommendations for appropriate manga and movies based on the analysis results. For example, if it determines that the user likes superhero movies, it will list superhero movies such as "Guardians of the Galaxy" and "Batman."

[0647] Additionally, the server collects additional information about the recommended film, such as director and writer comments, interviews, behind-the-scenes information, etc. For example, for a recommendation of "Guardians of the Galaxy," providing an interview with the director and behind-the-scenes information about filming can help users better understand and enjoy the film.

[0648] The server compiles this information and sends it to the user's device as the final content, where it displays the received information in a user interface for easy access. For example, it displays a list of recommended movies along with behind-the-scenes stories and comments about each movie.

[0649] Therefore, the present invention allows users to receive recommendations for manga and movies that are tailored to their preferences, and to enjoy the works even more through in-depth related information.

[0650] The processing flow will be explained below.

[0651] Step 1:

[0652] The user inputs their preferences and past viewing history. For example, the user inputs information such as "I like action movies" or "The movie I watched recently was a superhero movie."

[0653] Step 2:

[0654] The terminal formats the user's input data, specifically converting it into the appropriate data model so that subsequent processing can proceed smoothly.

[0655] Step 3:

[0656] The device sends the formatted data to the server, where it is transmitted using a secure communications protocol.

[0657] Step 4:

[0658] Before the server analyzes the received user data, it performs preprocessing such as shaping and filtering the data, for example, removing noise and inconsistencies in the input data.

[0659] Step 5:

[0660] The server passes the preprocessed data to the generation AI, which analyzes the user's preferences. The generation AI uses natural language processing and machine learning algorithms to identify the user's preferences, taking into account data from other users with similar preferences.

[0661] Step 6:

[0662] The server generates a list of recommended content based on the results of AI analysis. For example, if it determines that the user likes action movies, it will list movies such as "Batman" and "Iron Man."

[0663] Step 7:

[0664] The server collects additional information about the content it recommends, such as director and writer comments, interviews, and behind-the-scenes information, to help users better understand the work.

[0665] Step 8:

[0666] The server assembles the generated content list and additional information into a data packet, compressing and encrypting the data as necessary.

[0667] Step 9:

[0668] The server sends the data packet to the terminal, which again transmits the data using a secure communications protocol.

[0669] Step 10:

[0670] The terminal decompresses and decrypts the received data packets and verifies their contents, checking for inconsistencies and errors.

[0671] Step 11:

[0672] The device will then display the decompressed and decrypted data in a user interface, where the user can view a list of recommended content and related additional information.

[0673] Step 12:

[0674] Users can select content they are interested in. For example, if a user selects "Batman," they can view details and related information about the work.

[0675] Through these steps, the system of the present invention can provide customized content recommendations based on the user's preferences and related additional information.

[0676] Example 1

[0677] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0678] Conventional recommendation systems have difficulty accurately understanding user preferences and providing appropriate content. They also lack the functionality to provide related information that users are interested in. This has limited the improvement in user satisfaction and made it difficult to increase the frequency of system use.

[0679] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0680] In this invention, the server includes means for a user to input preferences and past browsing history, means for formatting the preferences and past browsing history and transmitting the formatted information to the server, means for analyzing the user's preferences using a generative AI model based on the preferences and past browsing history, means for generating a list of recommended content based on the analysis results, means for collecting additional information related to the recommended content, means for transmitting the list of recommended content and the additional information to the user, and means for displaying the list of recommended content and the additional information to the user, thereby enabling the provision of content and related information tailored to the user's individual preferences.

[0681] "User" refers to an individual or group of people who use this system to receive content recommendations.

[0682] "Preferences" refer to preferences such as genres or themes that a user is particularly interested in and tends to enjoy in preference to other things.

[0683] "Past browsing history" refers to a record of content that a user has previously viewed or read.

[0684] "Formatting" refers to the process of preparing data according to certain rules, so that the data can be sent correctly to the server.

[0685] A "server" is a part of an information processing system that responds to requests from clients via a network, analyzing data and providing information.

[0686] A "generative AI model" refers to an artificial intelligence model that uses machine learning algorithms and natural language processing techniques to analyze data and understand user preferences.

[0687] "Analysis" refers to the process of analyzing collected data in detail and deriving useful information and patterns from it.

[0688] "Recommended content" refers to entertainment media such as movies and manga that are selected by AI based on the user's preferences and past browsing history and recommended to the user.

[0689] "Additional Information" is supplemental information related to the recommended content, such as director's commentary, interviews, and behind-the-scenes information.

[0690] "Transmission" refers to the act of a terminal transferring data to a server, or the act of a server transferring data to a user.

[0691] "Display" refers to the visualization of the received data and recommended content on the user interface of the terminal.

[0692] This invention is a system that analyzes user preferences and past browsing history to provide customized content recommendations. This system is composed of a user, a terminal, and a server, and by clearly dividing the roles of each, it achieves advanced recommendation functionality.

[0693] First, the user inputs their preferences and browsing history. This input is done using a device such as a smartphone or PC. The input data is formatted by the device and organized as structured data in JSON format or similar. The device then sends the formatted data to the server.

[0694] The server uses a generative AI model to analyze the received data. The generative AI model is implemented using the Python libraries Scikit-learn and TensorFlow. Specifically, it uses natural language processing (NLP) techniques and machine learning algorithms to deeply analyze the user's preferences. For example, if a user likes action movies and has watched many "superhero movies" in the past, the AI ​​will determine that the user particularly likes action-themed superhero movies.

[0695] Next, the server generates a list of appropriate content recommendations based on the analysis results. When generating this list, the server uses content information stored in a database such as MySQL. For example, if it determines that the user likes superhero movies, it will list related works such as "Superhero Movie A" and "Superhero Movie B."

[0696] The server also collects additional information about the recommended content, such as comments from directors and writers, interviews, and behind-the-scenes information. This information is collected using web scraping techniques, specifically using Beautiful Soup and Scrapy. For example, for a recommendation of "Superhero Movie A," the server collects interviews with the director and behind-the-scenes information about filming.

[0697] This information is then compiled and sent to the device, which then displays it in a user interface for easy access. For example, the device could display a list of recommended movies along with behind-the-scenes stories and comments about each one.

[0698] Below are some examples of prompt sentences to input into the generative AI model.

[0699] Example prompt sentence:

[0700] "If a user likes action movies and has watched a lot of 'action movie A' and 'action movie B' in the past, what other movies can we recommend?"

[0701] As described above, the present invention realizes the provision of content and related information that are tailored to the individual preferences of a user.

[0702] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0703] Step 1:

[0704] Users input their preferences and past viewing history. The input data is provided in the form of genres, specific movie or manga titles, and viewing dates and times. This results in input data formats such as "Action Movies," "Movie A," and "2022-01-01."

[0705] Step 2:

[0706] The device receives the data entered by the user and formats it. The formatted data is saved in JSON format with the following structure: {"genre": "Action", "history": [{"title": "Movie A", "date": "2022-01-01"},{"title": "Movie B", "date": "2022-02-01"}]}. The formatted data is sent to the server.

[0707] Step 3:

[0708] The server receives the JSON-formatted data sent from the device. The received data undergoes appropriate data preprocessing before being passed to the generative AI model. This includes data normalization and filtering of unnecessary information. This preprocessing results in a clean dataset for analysis.

[0709] Step 4:

[0710] The server analyzes the preprocessed data using a generative AI model, which uses Python libraries (such as Scikit-learn and TensorFlow). This analysis helps understand the user's preferences and arrives at a conclusion, such as "the user particularly likes action movies."

[0711] Step 5:

[0712] The server generates a list of appropriate content based on the analysis results. It queries and retrieves related content from movie and manga data stored in a database management system (e.g., MySQL). For example, it searches for works tagged with "action" and "hero movies" based on the analysis results and lists "Content A" and "Content B."

[0713] Step 6:

[0714] The server collects additional information related to the recommended content. Specifically, it uses web scraping tools such as Beautiful Soup and Scrapy to collect director interviews and behind-the-scenes information. For example, for "Content A," it collects "director interview articles" and "behind-the-scenes articles."

[0715] Step 7:

[0716] The server formats the generated recommendation list and the collected additional information into the final content. The formatted data is converted back into JSON format, with the format "{"recommended": ["Content A", "Content B"], "additional_info": {"Content A": ["Director's Interview", "Behind the Scenes"]}}".

[0717] Step 8:

[0718] The server transmits the final content to the terminal, thereby transmitting data of detailed recommendation information to be provided to the user.

[0719] Step 9:

[0720] The device displays the final content in a user interface, allowing the user to visually view a list of recommended content and related additional information, such as a poster of a recommended movie and related director interviews or behind-the-scenes information.

[0721] (Application example 1)

[0722] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0723] Conventional content distribution services have difficulty in appropriately recommending content that matches a user's preferences, and lack a system that provides detailed background information or expert interviews about the recommended content. This makes it difficult for users to find content that is tailored to their preferences, and they lack opportunities to gain a deeper understanding of or be moved by the content.

[0724] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0725] In this invention, the server includes means for inputting a user's preferences and past browsing history, means for transmitting the preferences and past browsing history to the server, means for analyzing the user's preferences using a generation AI based on the preferences and past browsing history, means for generating a list of recommended content based on the analysis results, means for collecting additional information related to the recommended content, means for displaying the list of recommended content and the additional information on a user interface, and means for providing expert interviews and production background information for the recommended content. This allows users to optimally search for content that matches their preferences and obtain in-depth information about that content.

[0726] "Preferences" are personal tastes and interests that a user has for a particular type of content (for example, video works or digital comics).

[0727] "Past browsing history" refers to a record of content that a user has previously viewed or read.

[0728] "Generative AI" is an artificial intelligence technology that uses natural language processing and machine learning algorithms to analyze user preferences and provide optimal recommendations.

[0729] "Analysis results" refers to data and information about a user's preferences that the generating AI generates based on the user's preferences and past browsing history.

[0730] "Recommended content" refers to content such as video works and digital comics that are recommended to users based on the analysis results.

[0731] "Additional information" refers to supplementary information related to the recommended content, such as director or writer comments, expert interviews, and production background information.

[0732] "User interface" refers to the screens and methods of operation that allow a user to access content lists and additional information.

[0733] "Expert Interviews" refers to interview articles that include expert insights and inside stories related to the recommended content.

[0734] "Production Background Information" refers to detailed information about the production process and background of the recommended content.

[0735] "Digital comics" refers to manga and graphic novels available in e-book format.

[0736] This invention is a system that analyzes a user's preferences and past browsing history to provide customized content recommendations (video works and digital comics). This system is composed of a user, a terminal, and a server, and by clearly dividing the roles of each, it achieves advanced recommendation functionality.

[0737] First, the user inputs their preferences and browsing history. This input is done on a device such as a smartphone or tablet. The device receives this data, formats it, and sends it to the server. The software on the device uses Python and the requests library.

[0738] The server uses a generative AI to analyze the received data. This generative AI uses natural language processing (NLP) and machine learning algorithms to understand the user's preferences. Web frameworks such as Flask are used as server-side software. For example, if a user likes action movies and has watched many "superhero movies" in the past, the generative AI will determine that the user particularly likes action-themed superhero movies.

[0739] Next, the server generates a list of appropriate content recommendations based on the analysis results. For example, if it determines that the user likes superhero movies, it will list superhero movies such as "space adventure movies" and "city defender movies." The server also collects additional information about the recommended content. This additional information includes comments from directors and writers, expert interviews, and production background information. For example, for a recommendation of "space adventure movies," it will provide an interview with the director and background story of the filming.

[0740] The server compiles this information and sends it to the user's device as the final content. The user's device displays the received information in a user interface for easy access. For example, it displays a list of recommended movies or manga along with detailed information about each piece of content.

[0741] As a concrete example, the following prompt sentence is input to the generative AI model:

[0742] User preferences: Action, Hero

[0743] User's past browsing history: Avengers, Spider-Man, Batman

[0744] Based on this input, the generative AI will provide the following output:

[0745] Recommended content:

[0746] Title: Space adventure movie

[0747] Description: A heroic adventure to save the universe

[0748] Director's interview: The director talks about the background of the production

[0749] Title: City Guardian Movie

[0750] Description: A hero's challenge to protect the city

[0751] Director's Interview: The Director Discusses His New Hero Image

[0752] As described above, the system of the present invention allows users to receive recommendations for content that matches their preferences, and to enjoy works even more through in-depth information related to the content.

[0753] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0754] Step 1:

[0755] Users input their preferences and past viewing history. Using a smartphone or tablet, users input their preferences (e.g., action, superheroes) and the shows they have watched in the past (e.g., Avengers, Spider-Man). After inputting, this data is stored on the device.

[0756] Step 2:

[0757] The device sends input data to the server. Using Python and the requests library, the device formats the user's preferences and past browsing history into JSON format and sends it to the server via an HTTP POST request. In this setup, the data sent is in the following format:

[0758] {

[0759] "preferences": ["Action", "Hero"],

[0760] "history": ["Avengers", "Spider-Man"]

[0761] }

[0762] Step 3:

[0763] The server analyzes the received data. The server receives the HTTP request using a web framework such as Flask, and then analyzes the data using generative AI (e.g., GPT). Specifically, it uses natural language processing (NLP) and machine learning algorithms to understand the user's preferences and generate an analysis result. As a result of this analysis, it is determined that the user likes action superhero movies.

[0764] Step 4:

[0765] The server generates a list of recommended content based on the analysis results. Based on the analysis results of the generative AI, the server creates a list of optimal movies and digital comics. For example, content such as "space adventure movies" and "city guardian movies" will be listed.

[0766] Step 5:

[0767] The server collects additional information related to the content it recommends. For example, the server collects director and author comments, expert interviews, and production background information for the recommended content. For example, the server obtains information about the director's interview and the filming background of a "space adventure movie."

[0768] Step 6:

[0769] The server sends a list of recommended content and additional information to the device. After all the information is collected, the server compiles it and sends it to the user's device in JSON format.

[0770] Step 7:

[0771] The device displays the received information in a user interface. The device displays the received list of recommended content and additional information in a user interface for easy access by the user. For example, a list of recommended movies or manga can be displayed along with detailed information about each piece of content (such as an interview with the director or background information on the production).

[0772] Through the above processing steps, the user can optimally search for content that matches his or her preferences, and can also obtain in-depth information about that content.

[0773] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0774] This invention is a system that provides customized manga and movie recommendations by utilizing real-time emotional data in addition to user preferences and past browsing history. This system is composed of a user, a terminal, a server, and an emotional engine.

[0775] First, users input their preferences and past browsing history into the device, and real-time emotional data expressed by users while watching or browsing is also collected. This may be done using wearable devices, cameras, microphones, etc.

[0776] The device formats this data and sends it to the server. The server receives the data and performs preprocessing such as formatting and filtering. Next, the emotion engine in the server analyzes the user's emotion data and understands their emotional state. For example, it can extract information such as whether the user is enjoying or nervous while watching a movie.

[0777] The server uses generative AI to analyze user preferences based on the emotion data obtained from the emotion engine, as well as the user's preferences and past browsing history. The generative AI uses natural language processing and machine learning algorithms to identify content that the user is likely to like. In this process, the emotion data more accurately reflects the user's real-time preferences, helping to select the most suitable content.

[0778] The server then generates a list of recommended content based on the analysis results. If the emotional data indicates that the user is relaxed, relaxing content will be selected. Depending on the emotion, additional information (comments from directors and writers, interviews, behind-the-scenes information, etc.) will also be selected and added to the list.

[0779] The server assembles the generated content list and additional information into a data packet and sends it to the user's device. The device unpacks and decrypts the received data, verifies the content, and displays it on the user interface. This allows the user to easily view the recommended content and related information.

[0780] For example, if emotional data indicates that a user likes action movies and is enjoying them in real time, the server can recommend movies like "The Avengers" and "Batman," along with director interviews and behind-the-scenes information.

[0781] As described above, the system of the present invention provides users with a personalized experience and allows them to enjoy content more deeply by making advanced recommendations based on user preferences and real-time emotional data.

[0782] The processing flow will be explained below.

[0783] Step 1:

[0784] The user inputs their preferences and past viewing history into the device, such as "I like action movies" or "The movie I saw recently was a superhero movie."

[0785] Step 2:

[0786] The device formats the user's input data and converts it into an appropriate data format, for example, converting the input data into JSON or XML.

[0787] Step 3:

[0788] The device sends the formatted data to the server using a secure communication protocol such as HTTPS.

[0789] Step 4:

[0790] The device's camera and microphone, or a wearable device, can be used to collect real-time emotional data from the user, for example, by measuring heart rate and skin temperature to estimate the user's emotional state.

[0791] Step 5:

[0792] The device transmits real-time emotion data to a server, again using a secure communication protocol.

[0793] Step 6:

[0794] The server preprocesses the user data (preferences, browsing history, and emotion data) received by the server. Specifically, it removes redundancies and noise from the data and formats it.

[0795] Step 7:

[0796] The emotion engine in the server analyzes the user's emotion data and identifies their current emotional state, for example, recognizing whether the user is "relaxed" or "excited."

[0797] Step 8:

[0798] The server passes the user's preference and emotional data to the AI ​​for analysis. The AI ​​then uses natural language processing and machine learning algorithms to select the most appropriate content based on the user's preferences and current emotional state.

[0799] Step 9:

[0800] The server generates a list of recommended content based on the analysis results. For example, if it is determined that the user is in a "relaxed" state and likes "action movies," it will list relaxing action movies such as "Guardians of the Galaxy" and "Iron Man."

[0801] Step 10:

[0802] Collect additional information related to the content recommended by the server, such as director and writer comments, interviews, and behind-the-scenes information.

[0803] Step 11:

[0804] The server packages the generated content list and additional information into a data packet, which may include compressing and / or encrypting the data.

[0805] Step 12:

[0806] The server sends the data packets to the terminal, again using a secure communications protocol.

[0807] Step 13:

[0808] The terminal decompresses and decrypts the data packets it receives and checks the integrity of the contents, for example, checking that the data is not corrupted and that it contains all the required information.

[0809] Step 14:

[0810] The device will then display the decompressed and decrypted data in a user interface, where the user can view a list of recommended content and related additional information.

[0811] Step 15:

[0812] Users select the content they are interested in. For example, if they select "Guardians of the Galaxy," they can view details about the movie, as well as related comments and interviews.

[0813] Through these steps, the system of the present invention realizes advanced recommendations based on user preferences and real-time emotional data, providing users with a personalized entertainment experience.

[0814] Example 2

[0815] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0816] Conventional recommendation systems often make recommendations based solely on a user's browsing history and preferences, and are unable to provide personalized recommendations that take into account real-time emotional states. Another issue is that they do not provide sufficient additional information related to the recommended content, making it difficult for users to fully enjoy the content.

[0817] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0818] In this invention, the server includes means for collecting user preferences, past browsing history, and real-time emotional data, means for transmitting this data to the server, means for preprocessing and shaping the data, means for analyzing the emotional data to understand the user's emotional state, means for analyzing the user's preferences based on the emotional data, preferences, and past browsing history using a generative AI, means for generating a list of recommended content based on the analysis results, means for collecting additional information related to the recommended content, means for transmitting this list of recommended content and additional information to the user, and means for displaying them to the user. This enables more individually optimized content recommendations that reflect the user's real-time emotional state and the provision of related additional information.

[0819] A "user" is an entity that utilizes the system to input preferences, past browsing history, and real-time emotional data.

[0820] "Preferences" are data of favorable preferences for specific genres or types of content entered by the user.

[0821] "Past viewing history" is history data of content that a user has viewed or read in the past.

[0822] "Real-time emotional data" is data that indicates the real-time emotional state expressed by a user while viewing or browsing content.

[0823] A "terminal" is a device that a user uses to input preferences, past browsing history, and real-time emotional data and transmit it to a server.

[0824] A "server" is a device that receives data sent from a user, analyzes and processes it, generates a list of content and additional information, and sends it back to the user's terminal.

[0825] An "emotion engine" is a technology that analyzes real-time emotional data and understands the user's emotional state.

[0826] "Generative AI" is an algorithm that uses artificial intelligence to analyze user preferences based on input data and select the most appropriate content.

[0827] "Recommended content" refers to entertainment information such as movies and manga that the generative AI has analyzed and determined to be suitable for the user.

[0828] "Additional Information" is additional information related to the recommended content, such as creator or producer comments, interviews, behind-the-scenes information, etc.

[0829] The "content list" is a list of multiple pieces of content recommended to the user and their corresponding additional information.

[0830] "Data preprocessing" is a process of formatting received data and filtering out unnecessary data.

[0831] The present invention is a system that provides customized content recommendations using user preferences, past browsing history, and real-time emotion data. This system is composed of a user, a terminal, a server, and an emotion engine.

[0832] First, users input their preferences and browsing history into their devices. Specifically, they input data such as their favorite genres and the movies and manga they have recently watched. In addition, wearable devices, cameras, microphones, etc. are used to collect real-time emotional data. For example, a wearable device measures heart rate, a camera recognizes facial expressions, and a microphone analyzes voice tone.

[0833] The terminal formats this data and sends it to the server. This transmission uses the HTTPS protocol to ensure data security. The server first formats the received data and performs preprocessing such as filtering. Specifically, it uses Python and SQL to normalize the data and handle missing values.

[0834] Next, the emotion engine in the server analyzes the real-time emotion data. The emotion engine uses Python and machine learning libraries (e.g., Pytorch and TensorFlow) to understand the user's emotional state. For example, it determines whether the user is enjoying or nervous while watching a movie.

[0835] The server then uses a generative AI model to analyze user preferences based on their preferences, past browsing history, and emotional data. The generative AI model (e.g., BERT or GPT) uses natural language processing and machine learning algorithms to select the most suitable content for the user. The server then analyzes the user's preferences by inputting a prompt. For example, the prompt could be "action movies I like when I'm relaxed."

[0836] The server generates a list of recommended content based on the analysis results. If the user is in a relaxed state, it will select relaxing movies or manga, and collect additional information (such as comments from the creators or producers, interviews, and behind-the-scenes information) to add to the list. This list and additional information are then organized into a data packet and sent to the device.

[0837] The device will decompress and decrypt this data, verify the content, and then display it on the user interface, allowing users to easily view the recommended content and related information.

[0838] For example, if the emotional data indicates that the user likes action movies and is enjoying watching them, the server can input a prompt such as, "I like action movies, so please generate a list of movies that I recommend to you when you're currently enjoying them," into the generative AI model. As a result, the server can recommend movies such as "Batman" and "Inception," and also provide interviews with directors and behind-the-scenes information.

[0839] As described above, the system of the present invention utilizes real-time emotional data in addition to user preferences and browsing history to provide individually optimized content recommendations to users, allowing users to enjoy a deeper, more personalized experience.

[0840] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0841] Step 1:

[0842] Users use the device to input their preferences and past browsing history, including data such as their favorite genres and recently viewed movies and comics. Wearable devices, cameras, and microphones are also used to collect real-time emotional data. For example, wearable devices can collect heart rate data, cameras can analyze facial expressions, and microphones can analyze tone of voice.

[0843] Input: User preferences, past browsing history, real-time sentiment data

[0844] Output: Formatted user data (JSON format)

[0845] Step 2:

[0846] The device formats the collected user data, specifically converting preferences, browsing history, and sentiment data into an appropriate data format (e.g., JSON), making the data more consistent and easier to work with.

[0847] Input: User preferences, past browsing history, real-time sentiment data

[0848] Output: Formatted user data (JSON format)

[0849] Step 3:

[0850] The device sends the formatted data to the server, using the HTTPS protocol to ensure data security.

[0851] Input: Formatted user data (JSON format)

[0852] Output: Data sent to the server

[0853] Step 4:

[0854] The server first formats the received data and performs preprocessing such as filtering, etc. Specifically, it uses Python and SQL to normalize the data, handle missing values, convert data types, etc.

[0855] Input: Data sent to the server

[0856] Output: Preprocessed data

[0857] Step 5:

[0858] The emotion engine in the server analyzes the received real-time emotion data and uses machine learning libraries (Pytorch and TensorFlow) to understand the user's emotional state (e.g., enjoying, nervous, etc.).

[0859] Input: Preprocessed data (especially real-time emotion data)

[0860] Output: Parsed emotional state

[0861] Step 6:

[0862] The server uses a generative AI model to analyze user preferences based on their preferences, past browsing history, and emotional data. It uses natural language processing (NLP) and machine learning algorithms (e.g., BERT and GPT) to select the most suitable content for the user. It generates a prompt and inputs it into the generative AI. For example, "Action movies I like in a relaxed state."

[0863] Input: Preferences, past browsing history, analyzed emotional state

[0864] Output: A list of content that best suits the user

[0865] Step 7:

[0866] The server generates a list of recommended content based on the analysis results. For example, if you are in a relaxing state, it will select relaxing movies or manga. It also collects additional relevant information (comments from the creators, interviews, behind-the-scenes information) and adds it to the list.

[0867] Input: A list of content that best suits the user

[0868] Output: A list of recommended content and additional information

[0869] Step 8:

[0870] The server configures the generated content list and additional information into a data packet and transmits it to the user's terminal.

[0871] Input: List of recommended content and additional information

[0872] Output: Data packets sent to the terminal

[0873] Step 9:

[0874] The device decompresses and decrypts the received data packets, verifies the contents, and then displays the data on the user interface (UI), allowing the user to easily view the recommended content and related information.

[0875] Input: Data packets sent to the terminal

[0876] Output: A list of recommended content and additional information displayed in a user interface.

[0877] (Application example 2)

[0878] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0879] Conventional content recommendation systems recommend content based on user preferences and past browsing history, but do not take into account real-time emotional changes. This makes it difficult to provide content that best suits the user's current psychological state, potentially resulting in a poor user experience. Furthermore, the provision of related information is limited, resulting in a one-sided content viewing experience.

[0880] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for the user to input preferences and past browsing history, means for transmitting the preferences, past browsing history, and real-time emotional data to the server, and means for analyzing the user's preferences using a generation AI based on the preferences, past browsing history, and real-time emotional data. This enables more accurate content recommendations suited to the user's current emotional state, and makes it possible to enrich the content viewing experience by providing related information.

[0881] A "user" is an individual who utilizes the system to receive content recommendations.

[0882] "Preferences" refers to information indicating a user's tendency or taste to prefer content of a particular genre or type.

[0883] "Past viewing history" is log data of content that a user has previously viewed or read.

[0884] "Real-time emotional data" refers to data collected in real time about the emotional state that a user shows while viewing content.

[0885] A "server" is a computer system that processes data received from a user and returns analytical results.

[0886] "Generative AI" is an artificial intelligence technology that uses natural language processing and machine learning algorithms to analyze user preferences and recommend the most appropriate content.

[0887] "Analysis results" refers to data obtained by the server using generated AI to analyze user preferences, browsing history, and real-time emotional data.

[0888] A "list of recommended content" is a series of content that is generated by the server based on the analysis results and recommended to the user.

[0889] "Additional information" is supplemental information related to the recommended content that enriches the user's viewing experience.

[0890] A "wearable device" is a hardware device worn by a user for collecting emotional data.

[0891] The "camera" is a device that analyzes the user's movements and facial expressions to collect real-time emotional data.

[0892] A "microphone" is a voice input device for analyzing the emotional state of a user from their voice.

[0893] "Media content" is a general term for viewable digital content such as video and audio.

[0894] "System" means an integrated mechanism for consistently collecting, analyzing, recommending, and displaying user data.

[0895] The present invention is a system that recommends optimal content by utilizing a user's preferences, past browsing history, and real-time emotional data. This system is composed of a user, a terminal, a server, and an emotional engine for analyzing the emotional data.

[0896] First, users input their preferences and browsing history into devices such as smartphones or tablets. While the user is viewing content, real-time emotional data is also collected. This emotional data is collected using hardware such as wearable devices, cameras, and microphones. Specifically, the EmotionRecognition library is used for facial recognition and voice analysis.

[0897] The device formats the collected preferences, past browsing history data, and real-time emotion data and sends them to the server. The server receives this data and first performs preprocessing such as data shaping and filtering. The emotion engine then analyzes the emotion data to understand the user's emotional state.

[0898] Machine learning algorithms and natural language processing techniques are used for data preprocessing and sentiment analysis. After this, the server analyzes the user's preferences using generative AI to identify the content the user is currently looking for. Generative AI can use frameworks such as TensorFlow and PyTorch.

[0899] Based on the analysis results, the server generates a list of recommended content, such as manga or movies that are optimized for the user's preferences and emotional state. In addition, related additional information (such as creator comments, interviews, and behind-the-scenes information) is also collected and added to the list of recommended content.

[0900] The server assembles the generated content list and additional information into a data packet and sends it to the user's device. The device then decompresses and decrypts the received data, verifies the content, and displays it on the user interface. This allows the user to easily view the recommended content and related information.

[0901] As a specific example, if a user likes action movies and there is real-time emotional data showing that they are enjoying the movie, the server can recommend movies such as "Action Movie 1" and "Action Movie 2," and also provide interviews with directors and behind-the-scenes information about filming.

[0902] Example prompt sentence:

[0903] "Recommend the best action movies to users based on their current emotional data and past viewing history."

[0904] The system enables advanced recommendations that are optimized for a user's preferences and real-time emotional state, providing a more personalized content experience.

[0905] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0906] Step 1:

[0907] Users use their smartphones or tablets to input their preferences and past browsing history, including their preferred genres (e.g., action, comedy) and the titles of movies and manga they have watched in the past.

[0908] Step 2:

[0909] While the user is watching, we use a wearable device, camera, and microphone to collect real-time emotional data. We use the EmotionRecognition library to analyze the emotional state (e.g., enjoying, nervous) and generate this emotional data.

[0910] Step 3:

[0911] The device formats the user's preferences, past browsing history, and real-time emotion data and sends them to the server, for example, structuring the data in JSON format and sending the data to the server using an HTTP request.

[0912] Step 4:

[0913] The server performs preprocessing such as formatting and filtering of the data received from the terminal. Specifically, it removes unnecessary data, standardizes the format, and formats the data in a way that makes it easier to process.

[0914] Step 5:

[0915] The emotion engine in the server analyzes the received emotion data to understand the user's real-time emotional state. This analysis uses machine learning algorithms to extract the user's emotional state (e.g., enjoying, nervous).

[0916] Step 6:

[0917] The server uses generative AI based on emotion data obtained from the emotion engine, as well as preferences and past browsing history to analyze user preferences, and identifies the most suitable content using frameworks such as TensorFlow and PyTorch.

[0918] Step 7:

[0919] Based on the analysis, the server generates a list of recommended content, including movies and manga optimized for the user's emotional state and preferences.

[0920] Step 8:

[0921] The server collects additional information related to the recommended content (e.g., director's comments, interviews, behind-the-scenes information) and adds it to the list of recommended content.

[0922] Step 9:

[0923] The server then assembles the generated content list and additional information into a data packet and sends it to the terminal. The data is compressed and sent in the form of an HTTP response.

[0924] Step 10:

[0925] The terminal decompresses and decrypts the received data packets and verifies their contents, specifically by checking the data integrity and making any necessary formatting changes.

[0926] Step 11:

[0927] The terminal displays a list of verified recommended content and additional information on a user interface, allowing the user to easily browse the recommended content and related information.

[0928] Example prompt: "Recommend the best action movie for the user based on their current emotional data and past viewing history."

[0929] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0930] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0931] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[0932] [Fourth embodiment]

[0933] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0934] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0935] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0936] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0937] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0938] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0939] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0940] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0941] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0942] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0943] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0944] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0945] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0946] This invention is a system that analyzes user preferences and past browsing history to provide customized manga and movie recommendations. This system is composed of users, terminals, and servers, and by clearly dividing the roles of each, it achieves advanced recommendation functionality.

[0947] First, users input their preferences and browsing history, and the user's device receives this data, formats it, and sends it to the server.

[0948] The server uses a generative AI to analyze the received data. The generative AI uses natural language processing (NLP) and machine learning algorithms to understand the user's preferences. For example, if a user likes action movies and has watched many "superhero movies" in the past, the AI ​​can determine that the user particularly likes action-themed superhero movies.

[0949] Next, the server generates a list of recommendations for appropriate manga and movies based on the analysis results. For example, if it determines that the user likes superhero movies, it will list superhero movies such as "Guardians of the Galaxy" and "Batman."

[0950] Additionally, the server collects additional information about the recommended film, such as director and writer comments, interviews, behind-the-scenes information, etc. For example, for a recommendation of "Guardians of the Galaxy," providing an interview with the director and behind-the-scenes information about filming can help users better understand and enjoy the film.

[0951] The server compiles this information and sends it to the user's device as the final content, where it displays the received information in a user interface for easy access. For example, it displays a list of recommended movies along with behind-the-scenes stories and comments about each movie.

[0952] Therefore, the present invention allows users to receive recommendations for manga and movies that are tailored to their preferences, and to enjoy the works even more through in-depth related information.

[0953] The processing flow will be explained below.

[0954] Step 1:

[0955] The user inputs their preferences and past viewing history. For example, the user inputs information such as "I like action movies" or "The movie I watched recently was a superhero movie."

[0956] Step 2:

[0957] The terminal formats the user's input data, specifically converting it into the appropriate data model so that subsequent processing can proceed smoothly.

[0958] Step 3:

[0959] The device sends the formatted data to the server, where it is transmitted using a secure communications protocol.

[0960] Step 4:

[0961] Before the server analyzes the received user data, it performs preprocessing such as shaping and filtering the data, for example, removing noise and inconsistencies in the input data.

[0962] Step 5:

[0963] The server passes the preprocessed data to the generation AI, which analyzes the user's preferences. The generation AI uses natural language processing and machine learning algorithms to identify the user's preferences, taking into account data from other users with similar preferences.

[0964] Step 6:

[0965] The server generates a list of recommended content based on the results of AI analysis. For example, if it determines that the user likes action movies, it will list movies such as "Batman" and "Iron Man."

[0966] Step 7:

[0967] The server collects additional information about the content it recommends, such as director and writer comments, interviews, and behind-the-scenes information, to help users better understand the work.

[0968] Step 8:

[0969] The server assembles the generated content list and additional information into a data packet, compressing and encrypting the data as necessary.

[0970] Step 9:

[0971] The server sends the data packet to the terminal, which again transmits the data using a secure communications protocol.

[0972] Step 10:

[0973] The terminal decompresses and decrypts the received data packets and verifies their contents, checking for inconsistencies and errors.

[0974] Step 11:

[0975] The device will then display the decompressed and decrypted data in a user interface, where the user can view a list of recommended content and related additional information.

[0976] Step 12:

[0977] Users can select content they are interested in. For example, if a user selects "Batman," they can view details and related information about the work.

[0978] Through these steps, the system of the present invention can provide customized content recommendations based on the user's preferences and related additional information.

[0979] Example 1

[0980] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0981] Conventional recommendation systems have difficulty accurately understanding user preferences and providing appropriate content. They also lack the functionality to provide related information that users are interested in. This has limited the improvement in user satisfaction and made it difficult to increase the frequency of system use.

[0982] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0983] In this invention, the server includes means for a user to input preferences and past browsing history, means for formatting the preferences and past browsing history and transmitting the formatted information to the server, means for analyzing the user's preferences using a generative AI model based on the preferences and past browsing history, means for generating a list of recommended content based on the analysis results, means for collecting additional information related to the recommended content, means for transmitting the list of recommended content and the additional information to the user, and means for displaying the list of recommended content and the additional information to the user, thereby enabling the provision of content and related information tailored to the user's individual preferences.

[0984] "User" refers to an individual or group of people who use this system to receive content recommendations.

[0985] "Preferences" refer to preferences such as genres or themes that a user is particularly interested in and tends to enjoy in preference to other things.

[0986] "Past browsing history" refers to a record of content that a user has previously viewed or read.

[0987] "Formatting" refers to the process of preparing data according to certain rules, so that the data can be sent correctly to the server.

[0988] A "server" is a part of an information processing system that responds to requests from clients via a network, analyzing data and providing information.

[0989] A "generative AI model" refers to an artificial intelligence model that uses machine learning algorithms and natural language processing techniques to analyze data and understand user preferences.

[0990] "Analysis" refers to the process of analyzing collected data in detail and deriving useful information and patterns from it.

[0991] "Recommended content" refers to entertainment media such as movies and manga that are selected by AI based on the user's preferences and past browsing history and recommended to the user.

[0992] "Additional Information" is supplemental information related to the recommended content, such as director's commentary, interviews, and behind-the-scenes information.

[0993] "Transmission" refers to the act of a terminal transferring data to a server, or the act of a server transferring data to a user.

[0994] "Display" refers to the visualization of the received data and recommended content on the user interface of the terminal.

[0995] This invention is a system that analyzes user preferences and past browsing history to provide customized content recommendations. This system is composed of a user, a terminal, and a server, and by clearly dividing the roles of each, it achieves advanced recommendation functionality.

[0996] First, the user inputs their preferences and browsing history. This input is done using a device such as a smartphone or PC. The input data is formatted by the device and organized as structured data in JSON format or similar. The device then sends the formatted data to the server.

[0997] The server uses a generative AI model to analyze the received data. The generative AI model is implemented using the Python libraries Scikit-learn and TensorFlow. Specifically, it uses natural language processing (NLP) techniques and machine learning algorithms to deeply analyze the user's preferences. For example, if a user likes action movies and has watched many "superhero movies" in the past, the AI ​​will determine that the user particularly likes action-themed superhero movies.

[0998] Next, the server generates a list of appropriate content recommendations based on the analysis results. When generating this list, the server uses content information stored in a database such as MySQL. For example, if it determines that the user likes superhero movies, it will list related works such as "Superhero Movie A" and "Superhero Movie B."

[0999] The server also collects additional information about the recommended content, such as comments from directors and writers, interviews, and behind-the-scenes information. This information is collected using web scraping techniques, specifically using Beautiful Soup and Scrapy. For example, for a recommendation of "Superhero Movie A," the server collects interviews with the director and behind-the-scenes information about filming.

[1000] This information is then compiled and sent to the device, which then displays it in a user interface for easy access. For example, the device could display a list of recommended movies along with behind-the-scenes stories and comments about each one.

[1001] Below are some examples of prompt sentences to input into the generative AI model.

[1002] Example prompt sentence:

[1003] "If a user likes action movies and has watched a lot of 'action movie A' and 'action movie B' in the past, what other movies can we recommend?"

[1004] As described above, the present invention realizes the provision of content and related information that are tailored to the individual preferences of a user.

[1005] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1006] Step 1:

[1007] Users input their preferences and past viewing history. The input data is provided in the form of genres, specific movie or manga titles, and viewing dates and times. This results in input data formats such as "Action Movies," "Movie A," and "2022-01-01."

[1008] Step 2:

[1009] The device receives the data entered by the user and formats it. The formatted data is saved in JSON format with the following structure: {"genre": "Action", "history": [{"title": "Movie A", "date": "2022-01-01"},{"title": "Movie B", "date": "2022-02-01"}]}. The formatted data is sent to the server.

[1010] Step 3:

[1011] The server receives the JSON-formatted data sent from the device. The received data undergoes appropriate data preprocessing before being passed to the generative AI model. This includes data normalization and filtering of unnecessary information. This preprocessing results in a clean dataset for analysis.

[1012] Step 4:

[1013] The server analyzes the preprocessed data using a generative AI model, which uses Python libraries (such as Scikit-learn and TensorFlow). This analysis helps understand the user's preferences and arrives at a conclusion, such as "the user particularly likes action movies."

[1014] Step 5:

[1015] The server generates a list of appropriate content based on the analysis results. It queries and retrieves related content from movie and manga data stored in a database management system (e.g., MySQL). For example, it searches for works tagged with "action" and "hero movies" based on the analysis results and lists "Content A" and "Content B."

[1016] Step 6:

[1017] The server collects additional information related to the recommended content. Specifically, it uses web scraping tools such as Beautiful Soup and Scrapy to collect director interviews and behind-the-scenes information. For example, for "Content A," it collects "director interview articles" and "behind-the-scenes articles."

[1018] Step 7:

[1019] The server formats the generated recommendation list and the collected additional information into the final content. The formatted data is converted back into JSON format, with the format "{"recommended": ["Content A", "Content B"], "additional_info": {"Content A": ["Director's Interview", "Behind the Scenes"]}}".

[1020] Step 8:

[1021] The server transmits the final content to the terminal, thereby transmitting data of detailed recommendation information to be provided to the user.

[1022] Step 9:

[1023] The device displays the final content in a user interface, allowing the user to visually view a list of recommended content and related additional information, such as a poster of a recommended movie and related director interviews or behind-the-scenes information.

[1024] (Application example 1)

[1025] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1026] Conventional content distribution services have difficulty in appropriately recommending content that matches a user's preferences, and lack a system that provides detailed background information or expert interviews about the recommended content. This makes it difficult for users to find content that is tailored to their preferences, and they lack opportunities to gain a deeper understanding of or be moved by the content.

[1027] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1028] In this invention, the server includes means for inputting a user's preferences and past browsing history, means for transmitting the preferences and past browsing history to the server, means for analyzing the user's preferences using a generation AI based on the preferences and past browsing history, means for generating a list of recommended content based on the analysis results, means for collecting additional information related to the recommended content, means for displaying the list of recommended content and the additional information on a user interface, and means for providing expert interviews and production background information for the recommended content. This allows users to optimally search for content that matches their preferences and obtain in-depth information about that content.

[1029] "Preferences" are personal tastes and interests that a user has for a particular type of content (for example, video works or digital comics).

[1030] "Past browsing history" refers to a record of content that a user has previously viewed or read.

[1031] "Generative AI" is an artificial intelligence technology that uses natural language processing and machine learning algorithms to analyze user preferences and provide optimal recommendations.

[1032] "Analysis results" refers to data and information about a user's preferences that the generating AI generates based on the user's preferences and past browsing history.

[1033] "Recommended content" refers to content such as video works and digital comics that are recommended to users based on the analysis results.

[1034] "Additional information" refers to supplementary information related to the recommended content, such as director or writer comments, expert interviews, and production background information.

[1035] "User interface" refers to the screens and methods of operation that allow a user to access content lists and additional information.

[1036] "Expert Interviews" refers to interview articles that include expert insights and inside stories related to the recommended content.

[1037] "Production Background Information" refers to detailed information about the production process and background of the recommended content.

[1038] "Digital comics" refers to manga and graphic novels available in e-book format.

[1039] This invention is a system that analyzes a user's preferences and past browsing history to provide customized content recommendations (video works and digital comics). This system is composed of a user, a terminal, and a server, and by clearly dividing the roles of each, it achieves advanced recommendation functionality.

[1040] First, the user inputs their preferences and browsing history. This input is done on a device such as a smartphone or tablet. The device receives this data, formats it, and sends it to the server. The software on the device uses Python and the requests library.

[1041] The server uses a generative AI to analyze the received data. This generative AI uses natural language processing (NLP) and machine learning algorithms to understand the user's preferences. Web frameworks such as Flask are used as server-side software. For example, if a user likes action movies and has watched many "superhero movies" in the past, the generative AI will determine that the user particularly likes action-themed superhero movies.

[1042] Next, the server generates a list of appropriate content recommendations based on the analysis results. For example, if it determines that the user likes superhero movies, it will list superhero movies such as "space adventure movies" and "city defender movies." The server also collects additional information about the recommended content. This additional information includes comments from directors and writers, expert interviews, and production background information. For example, for a recommendation of "space adventure movies," it will provide an interview with the director and background story of the filming.

[1043] The server compiles this information and sends it to the user's device as the final content. The user's device displays the received information in a user interface for easy access. For example, it displays a list of recommended movies or manga along with detailed information about each piece of content.

[1044] As a concrete example, the following prompt sentence is input to the generative AI model:

[1045] User preferences: Action, Hero

[1046] User's past browsing history: Avengers, Spider-Man, Batman

[1047] Based on this input, the generative AI will provide the following output:

[1048] Recommended content:

[1049] Title: Space adventure movie

[1050] Description: A heroic adventure to save the universe

[1051] Director's interview: The director talks about the background of the production

[1052] Title: City Guardian Movie

[1053] Description: A hero's challenge to protect the city

[1054] Director's Interview: The Director Discusses His New Hero Image

[1055] As described above, the system of the present invention allows users to receive recommendations for content that matches their preferences, and to enjoy works even more through in-depth information related to the content.

[1056] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1057] Step 1:

[1058] Users input their preferences and past viewing history. Using a smartphone or tablet, users input their preferences (e.g., action, superheroes) and the shows they have watched in the past (e.g., Avengers, Spider-Man). After inputting, this data is stored on the device.

[1059] Step 2:

[1060] The device sends input data to the server. Using Python and the requests library, the device formats the user's preferences and past browsing history into JSON format and sends it to the server via an HTTP POST request. In this setup, the data sent is in the following format:

[1061] {

[1062] "preferences": ["Action", "Hero"],

[1063] "history": ["Avengers", "Spider-Man"]

[1064] }

[1065] Step 3:

[1066] The server analyzes the received data. The server receives the HTTP request using a web framework such as Flask, and then analyzes the data using generative AI (e.g., GPT). Specifically, it uses natural language processing (NLP) and machine learning algorithms to understand the user's preferences and generate an analysis result. As a result of this analysis, it is determined that the user likes action superhero movies.

[1067] Step 4:

[1068] The server generates a list of recommended content based on the analysis results. Based on the analysis results of the generative AI, the server creates a list of optimal movies and digital comics. For example, content such as "space adventure movies" and "city guardian movies" will be listed.

[1069] Step 5:

[1070] The server collects additional information related to the content it recommends. For example, the server collects director and author comments, expert interviews, and production background information for the recommended content. For example, the server obtains information about the director's interview and the filming background of a "space adventure movie."

[1071] Step 6:

[1072] The server sends a list of recommended content and additional information to the device. After all the information is collected, the server compiles it and sends it to the user's device in JSON format.

[1073] Step 7:

[1074] The device displays the received information in a user interface. The device displays the received list of recommended content and additional information in a user interface for easy access by the user. For example, a list of recommended movies or manga can be displayed along with detailed information about each piece of content (such as an interview with the director or background information on the production).

[1075] Through the above processing steps, the user can optimally search for content that matches his or her preferences, and can also obtain in-depth information about that content.

[1076] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1077] This invention is a system that provides customized manga and movie recommendations by utilizing real-time emotional data in addition to user preferences and past browsing history. This system is composed of a user, a terminal, a server, and an emotional engine.

[1078] First, users input their preferences and past browsing history into the device, and real-time emotional data expressed by users while watching or browsing is also collected. This may be done using wearable devices, cameras, microphones, etc.

[1079] The device formats this data and sends it to the server. The server receives the data and performs preprocessing such as formatting and filtering. Next, the emotion engine in the server analyzes the user's emotion data and understands their emotional state. For example, it can extract information such as whether the user is enjoying or nervous while watching a movie.

[1080] The server uses generative AI to analyze user preferences based on the emotion data obtained from the emotion engine, as well as the user's preferences and past browsing history. The generative AI uses natural language processing and machine learning algorithms to identify content that the user is likely to like. In this process, the emotion data more accurately reflects the user's real-time preferences, helping to select the most suitable content.

[1081] The server then generates a list of recommended content based on the analysis results. If the emotional data indicates that the user is relaxed, relaxing content will be selected. Depending on the emotion, additional information (comments from directors and writers, interviews, behind-the-scenes information, etc.) will also be selected and added to the list.

[1082] The server assembles the generated content list and additional information into a data packet and sends it to the user's device. The device unpacks and decrypts the received data, verifies the content, and displays it on the user interface. This allows the user to easily view the recommended content and related information.

[1083] For example, if emotional data indicates that a user likes action movies and is enjoying them in real time, the server can recommend movies like "The Avengers" and "Batman," along with director interviews and behind-the-scenes information.

[1084] As described above, the system of the present invention provides users with a personalized experience and allows them to enjoy content more deeply by making advanced recommendations based on user preferences and real-time emotional data.

[1085] The processing flow will be explained below.

[1086] Step 1:

[1087] The user inputs their preferences and past viewing history into the device, such as "I like action movies" or "The movie I saw recently was a superhero movie."

[1088] Step 2:

[1089] The device formats the user's input data and converts it into an appropriate data format, for example, converting the input data into JSON or XML.

[1090] Step 3:

[1091] The device sends the formatted data to the server using a secure communication protocol such as HTTPS.

[1092] Step 4:

[1093] The device's camera and microphone, or a wearable device, can be used to collect real-time emotional data from the user, for example, by measuring heart rate and skin temperature to estimate the user's emotional state.

[1094] Step 5:

[1095] The device transmits real-time emotion data to a server, again using a secure communication protocol.

[1096] Step 6:

[1097] The server preprocesses the user data (preferences, browsing history, and emotion data) received by the server. Specifically, it removes redundancies and noise from the data and formats it.

[1098] Step 7:

[1099] The emotion engine in the server analyzes the user's emotion data and identifies their current emotional state, for example, recognizing whether the user is "relaxed" or "excited."

[1100] Step 8:

[1101] The server passes the user's preference and emotional data to the AI ​​for analysis. The AI ​​then uses natural language processing and machine learning algorithms to select the most appropriate content based on the user's preferences and current emotional state.

[1102] Step 9:

[1103] The server generates a list of recommended content based on the analysis results. For example, if it is determined that the user is in a "relaxed" state and likes "action movies," it will list relaxing action movies such as "Guardians of the Galaxy" and "Iron Man."

[1104] Step 10:

[1105] Collect additional information related to the content recommended by the server, such as director and writer comments, interviews, and behind-the-scenes information.

[1106] Step 11:

[1107] The server packages the generated content list and additional information into a data packet, which may include compressing and / or encrypting the data.

[1108] Step 12:

[1109] The server sends the data packets to the terminal, again using a secure communications protocol.

[1110] Step 13:

[1111] The terminal decompresses and decrypts the data packets it receives and checks the integrity of the contents, for example, checking that the data is not corrupted and that it contains all the required information.

[1112] Step 14:

[1113] The device will then display the decompressed and decrypted data in a user interface, where the user can view a list of recommended content and related additional information.

[1114] Step 15:

[1115] Users select the content they are interested in. For example, if they select "Guardians of the Galaxy," they can view details about the movie, as well as related comments and interviews.

[1116] Through these steps, the system of the present invention realizes advanced recommendations based on user preferences and real-time emotional data, providing users with a personalized entertainment experience.

[1117] Example 2

[1118] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1119] Conventional recommendation systems often make recommendations based solely on a user's browsing history and preferences, and are unable to provide personalized recommendations that take into account real-time emotional states. Another issue is that they do not provide sufficient additional information related to the recommended content, making it difficult for users to fully enjoy the content.

[1120] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1121] In this invention, the server includes means for collecting user preferences, past browsing history, and real-time emotional data, means for transmitting this data to the server, means for preprocessing and shaping the data, means for analyzing the emotional data to understand the user's emotional state, means for analyzing the user's preferences based on the emotional data, preferences, and past browsing history using a generative AI, means for generating a list of recommended content based on the analysis results, means for collecting additional information related to the recommended content, means for transmitting this list of recommended content and additional information to the user, and means for displaying them to the user. This enables more individually optimized content recommendations that reflect the user's real-time emotional state and the provision of related additional information.

[1122] A "user" is an entity that utilizes the system to input preferences, past browsing history, and real-time emotional data.

[1123] "Preferences" are data of favorable preferences for specific genres or types of content entered by the user.

[1124] "Past viewing history" is history data of content that a user has viewed or read in the past.

[1125] "Real-time emotional data" is data that indicates the real-time emotional state expressed by a user while viewing or browsing content.

[1126] A "terminal" is a device that a user uses to input preferences, past browsing history, and real-time emotional data and transmit it to a server.

[1127] A "server" is a device that receives data sent from a user, analyzes and processes it, generates a list of content and additional information, and sends it back to the user's terminal.

[1128] An "emotion engine" is a technology that analyzes real-time emotional data and understands the user's emotional state.

[1129] "Generative AI" is an algorithm that uses artificial intelligence to analyze user preferences based on input data and select the most appropriate content.

[1130] "Recommended content" refers to entertainment information such as movies and manga that the generative AI has analyzed and determined to be suitable for the user.

[1131] "Additional Information" is additional information related to the recommended content, such as creator or producer comments, interviews, behind-the-scenes information, etc.

[1132] The "content list" is a list of multiple pieces of content recommended to the user and their corresponding additional information.

[1133] "Data preprocessing" is a process of formatting received data and filtering out unnecessary data.

[1134] The present invention is a system that provides customized content recommendations using user preferences, past browsing history, and real-time emotion data. This system is composed of a user, a terminal, a server, and an emotion engine.

[1135] First, users input their preferences and browsing history into their devices. Specifically, they input data such as their favorite genres and the movies and manga they have recently watched. In addition, wearable devices, cameras, microphones, etc. are used to collect real-time emotional data. For example, a wearable device measures heart rate, a camera recognizes facial expressions, and a microphone analyzes voice tone.

[1136] The terminal formats this data and sends it to the server. This transmission uses the HTTPS protocol to ensure data security. The server first formats the received data and performs preprocessing such as filtering. Specifically, it uses Python and SQL to normalize the data and handle missing values.

[1137] Next, the emotion engine in the server analyzes the real-time emotion data. The emotion engine uses Python and machine learning libraries (e.g., Pytorch and TensorFlow) to understand the user's emotional state. For example, it determines whether the user is enjoying or nervous while watching a movie.

[1138] The server then uses a generative AI model to analyze user preferences based on their preferences, past browsing history, and emotional data. The generative AI model (e.g., BERT or GPT) uses natural language processing and machine learning algorithms to select the most suitable content for the user. The server then analyzes the user's preferences by inputting a prompt. For example, the prompt could be "action movies I like when I'm relaxed."

[1139] The server generates a list of recommended content based on the analysis results. If the user is in a relaxed state, it will select relaxing movies or manga, and collect additional information (such as comments from the creators or producers, interviews, and behind-the-scenes information) to add to the list. This list and additional information are then organized into a data packet and sent to the device.

[1140] The device will decompress and decrypt this data, verify the content, and then display it on the user interface, allowing users to easily view the recommended content and related information.

[1141] For example, if the emotional data indicates that the user likes action movies and is enjoying watching them, the server can input a prompt such as, "I like action movies, so please generate a list of movies that I recommend to you when you're currently enjoying them," into the generative AI model. As a result, the server can recommend movies such as "Batman" and "Inception," and also provide interviews with directors and behind-the-scenes information.

[1142] As described above, the system of the present invention utilizes real-time emotional data in addition to user preferences and browsing history to provide individually optimized content recommendations to users, allowing users to enjoy a deeper, more personalized experience.

[1143] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1144] Step 1:

[1145] Users use the device to input their preferences and past browsing history, including data such as their favorite genres and recently viewed movies and comics. Wearable devices, cameras, and microphones are also used to collect real-time emotional data. For example, wearable devices can collect heart rate data, cameras can analyze facial expressions, and microphones can analyze tone of voice.

[1146] Input: User preferences, past browsing history, real-time sentiment data

[1147] Output: Formatted user data (JSON format)

[1148] Step 2:

[1149] The device formats the collected user data, specifically converting preferences, browsing history, and sentiment data into an appropriate data format (e.g., JSON), making the data more consistent and easier to work with.

[1150] Input: User preferences, past browsing history, real-time sentiment data

[1151] Output: Formatted user data (JSON format)

[1152] Step 3:

[1153] The device sends the formatted data to the server, using the HTTPS protocol to ensure data security.

[1154] Input: Formatted user data (JSON format)

[1155] Output: Data sent to the server

[1156] Step 4:

[1157] The server first formats the received data and performs preprocessing such as filtering, etc. Specifically, it uses Python and SQL to normalize the data, handle missing values, convert data types, etc.

[1158] Input: Data sent to the server

[1159] Output: Preprocessed data

[1160] Step 5:

[1161] The emotion engine in the server analyzes the received real-time emotion data and uses machine learning libraries (Pytorch and TensorFlow) to understand the user's emotional state (e.g., enjoying, nervous, etc.).

[1162] Input: Preprocessed data (especially real-time emotion data)

[1163] Output: Parsed emotional state

[1164] Step 6:

[1165] The server uses a generative AI model to analyze user preferences based on their preferences, past browsing history, and emotional data. It uses natural language processing (NLP) and machine learning algorithms (e.g., BERT and GPT) to select the most suitable content for the user. It generates a prompt and inputs it into the generative AI. For example, "Action movies I like in a relaxed state."

[1166] Input: Preferences, past browsing history, analyzed emotional state

[1167] Output: A list of content that best suits the user

[1168] Step 7:

[1169] The server generates a list of recommended content based on the analysis results. For example, if you are in a relaxing state, it will select relaxing movies or manga. It also collects additional relevant information (comments from the creators, interviews, behind-the-scenes information) and adds it to the list.

[1170] Input: A list of content that best suits the user

[1171] Output: A list of recommended content and additional information

[1172] Step 8:

[1173] The server configures the generated content list and additional information into a data packet and transmits it to the user's terminal.

[1174] Input: List of recommended content and additional information

[1175] Output: Data packets sent to the terminal

[1176] Step 9:

[1177] The device decompresses and decrypts the received data packets, verifies the contents, and then displays the data on the user interface (UI), allowing the user to easily view the recommended content and related information.

[1178] Input: Data packets sent to the terminal

[1179] Output: A list of recommended content and additional information displayed in a user interface.

[1180] (Application example 2)

[1181] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1182] Conventional content recommendation systems recommend content based on user preferences and past browsing history, but do not take into account real-time emotional changes. This makes it difficult to provide content that best suits the user's current psychological state, potentially resulting in a poor user experience. Furthermore, the provision of related information is limited, resulting in a one-sided content viewing experience.

[1183] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for the user to input preferences and past browsing history, means for transmitting the preferences, past browsing history, and real-time emotional data to the server, and means for analyzing the user's preferences using a generation AI based on the preferences, past browsing history, and real-time emotional data. This enables more accurate content recommendations suited to the user's current emotional state, and makes it possible to enrich the content viewing experience by providing related information.

[1184] A "user" is an individual who utilizes the system to receive content recommendations.

[1185] "Preferences" refers to information indicating a user's tendency or taste to prefer content of a particular genre or type.

[1186] "Past viewing history" is log data of content that a user has previously viewed or read.

[1187] "Real-time emotional data" refers to data collected in real time about the emotional state that a user shows while viewing content.

[1188] A "server" is a computer system that processes data received from a user and returns analytical results.

[1189] "Generative AI" is an artificial intelligence technology that uses natural language processing and machine learning algorithms to analyze user preferences and recommend the most appropriate content.

[1190] "Analysis results" refers to data obtained by the server using generated AI to analyze user preferences, browsing history, and real-time emotional data.

[1191] A "list of recommended content" is a series of content that is generated by the server based on the analysis results and recommended to the user.

[1192] "Additional information" is supplemental information related to the recommended content that enriches the user's viewing experience.

[1193] A "wearable device" is a hardware device worn by a user for collecting emotional data.

[1194] The "camera" is a device that analyzes the user's movements and facial expressions to collect real-time emotional data.

[1195] A "microphone" is a voice input device for analyzing the emotional state of a user from their voice.

[1196] "Media content" is a general term for viewable digital content such as video and audio.

[1197] "System" means an integrated mechanism for consistently collecting, analyzing, recommending, and displaying user data.

[1198] The present invention is a system that recommends optimal content by utilizing a user's preferences, past browsing history, and real-time emotional data. This system is composed of a user, a terminal, a server, and an emotional engine for analyzing the emotional data.

[1199] First, users input their preferences and browsing history into devices such as smartphones or tablets. While the user is viewing content, real-time emotional data is also collected. This emotional data is collected using hardware such as wearable devices, cameras, and microphones. Specifically, the EmotionRecognition library is used for facial recognition and voice analysis.

[1200] The device formats the collected preferences, past browsing history data, and real-time emotion data and sends them to the server. The server receives this data and first performs preprocessing such as data shaping and filtering. The emotion engine then analyzes the emotion data to understand the user's emotional state.

[1201] Machine learning algorithms and natural language processing techniques are used for data preprocessing and sentiment analysis. After this, the server analyzes the user's preferences using generative AI to identify the content the user is currently looking for. Generative AI can use frameworks such as TensorFlow and PyTorch.

[1202] Based on the analysis results, the server generates a list of recommended content, such as manga or movies that are optimized for the user's preferences and emotional state. In addition, related additional information (such as creator comments, interviews, and behind-the-scenes information) is also collected and added to the list of recommended content.

[1203] The server assembles the generated content list and additional information into a data packet and sends it to the user's device. The device then decompresses and decrypts the received data, verifies the content, and displays it on the user interface. This allows the user to easily view the recommended content and related information.

[1204] As a specific example, if a user likes action movies and there is real-time emotional data showing that they are enjoying the movie, the server can recommend movies such as "Action Movie 1" and "Action Movie 2," and also provide interviews with directors and behind-the-scenes information about filming.

[1205] Example prompt sentence:

[1206] "Recommend the best action movies to users based on their current emotional data and past viewing history."

[1207] The system enables advanced recommendations that are optimized for a user's preferences and real-time emotional state, providing a more personalized content experience.

[1208] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1209] Step 1:

[1210] Users use their smartphones or tablets to input their preferences and past browsing history, including their preferred genres (e.g., action, comedy) and the titles of movies and manga they have watched in the past.

[1211] Step 2:

[1212] While the user is watching, we use a wearable device, camera, and microphone to collect real-time emotional data. We use the EmotionRecognition library to analyze the emotional state (e.g., enjoying, nervous) and generate this emotional data.

[1213] Step 3:

[1214] The device formats the user's preferences, past browsing history, and real-time emotion data and sends them to the server, for example, structuring the data in JSON format and sending the data to the server using an HTTP request.

[1215] Step 4:

[1216] The server performs preprocessing such as formatting and filtering of the data received from the terminal. Specifically, it removes unnecessary data, standardizes the format, and formats the data in a way that makes it easier to process.

[1217] Step 5:

[1218] The emotion engine in the server analyzes the received emotion data to understand the user's real-time emotional state. This analysis uses machine learning algorithms to extract the user's emotional state (e.g., enjoying, nervous).

[1219] Step 6:

[1220] The server uses generative AI based on emotion data obtained from the emotion engine, as well as preferences and past browsing history to analyze user preferences, and identifies the most suitable content using frameworks such as TensorFlow and PyTorch.

[1221] Step 7:

[1222] Based on the analysis, the server generates a list of recommended content, including movies and manga optimized for the user's emotional state and preferences.

[1223] Step 8:

[1224] The server collects additional information related to the recommended content (e.g., director's comments, interviews, behind-the-scenes information) and adds it to the list of recommended content.

[1225] Step 9:

[1226] The server then assembles the generated content list and additional information into a data packet and sends it to the terminal. The data is compressed and sent in the form of an HTTP response.

[1227] Step 10:

[1228] The terminal decompresses and decrypts the received data packets and verifies their contents, specifically by checking the data integrity and making any necessary formatting changes.

[1229] Step 11:

[1230] The terminal displays a list of verified recommended content and additional information on a user interface, allowing the user to easily browse the recommended content and related information.

[1231] Example prompt: "Recommend the best action movie for the user based on their current emotional data and past viewing history."

[1232] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1233] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1234] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1235] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1236] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1237] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1238] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1239] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1240] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1241] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1242] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1243] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1244] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1245] 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.

[1246] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1247] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1248] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1249] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1250] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1251] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1252] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1253] The following is further disclosed regarding the above embodiment.

[1254] (Claim 1)

[1255] a means for users to input their preferences and past browsing history;

[1256] means for transmitting the preferences and past browsing history to a server;

[1257] A means for analyzing user preferences using a generating AI based on the preferences and past browsing history;

[1258] means for generating a list of recommended content based on the analysis results;

[1259] A means of collecting additional information related to the content we recommend; and

[1260] means for transmitting the list of recommended content and additional information to a user;

[1261] means for displaying the list of recommended content and additional information to a user;

[1262] A system including:

[1263] (Claim 2)

[1264] 10. The system of claim 1, wherein the additional information includes comments from directors or writers, interviews, and behind-the-scenes information.

[1265] (Claim 3)

[1266] The system of claim 1 , wherein the recommended content includes videos and cartoons.

[1267] "Example 1"

[1268] (Claim 1)

[1269] a means for users to input their preferences and past browsing history;

[1270] means for formatting and transmitting said preferences and past browsing history to a server;

[1271] A means for analyzing user preferences using a generative AI model based on the preferences and past browsing history;

[1272] means for generating a list of recommended content based on the analysis results;

[1273] means for collecting additional information related to said recommended content;

[1274] means for transmitting the list of recommended content and the additional information to a user;

[1275] means for displaying the list of recommended content and the additional information to a user;

[1276] A system including:

[1277] (Claim 2)

[1278] 10. The system of claim 1, wherein the additional information includes comments from directors or writers, interviews, and behind-the-scenes information.

[1279] (Claim 3)

[1280] The system of claim 1 , wherein the recommended content includes videos and cartoons.

[1281] "Application Example 1"

[1282] (Claim 1)

[1283] a means for users to input their preferences and past browsing history;

[1284] means for transmitting the preferences and past browsing history to a server;

[1285] A means for analyzing user preferences using a generating AI based on the preferences and past browsing history;

[1286] means for generating a list of recommended content based on the analysis results;

[1287] A means of collecting additional information related to the content we recommend; and

[1288] means for transmitting the list of recommended content and additional information to a user;

[1289] means for displaying the list of recommended content and additional information on a user interface;

[1290] For each recommended piece of content, a means to provide expert interviews and background information related to each recommendation;

[1291] A system including:

[1292] (Claim 2)

[1293] 10. The system of claim 1, wherein the additional information includes comments from a director or writer, expert interviews, and production background information.

[1294] (Claim 3)

[1295] The system of claim 1 , wherein the recommended content includes video works and digital comics.

[1296] "Example 2: Combining Emotion Engines"

[1297] (Claim 1)

[1298] a means for users to input their preferences and past browsing history;

[1299] means for collecting said preferences, past browsing history, and real-time emotional data;

[1300] means for transmitting the preferences, past browsing history, and real-time emotion data to a server;

[1301] means for preprocessing and shaping said data;

[1302] means for analyzing the emotion data to understand the user's emotional state;

[1303] means for analyzing user preferences based on the emotion data, preferences, and past browsing history using a generating AI;

[1304] means for generating a list of recommended content based on the analysis results;

[1305] A means of collecting additional information related to the content we recommend; and

[1306] means for transmitting the list of recommended content and additional information to a user;

[1307] means for displaying the list of recommended content and additional information to a user;

[1308] A system including:

[1309] (Claim 2)

[1310] 10. The system of claim 1, wherein the additional information includes comments, interviews, and behind-the-scenes information from the creator or producer.

[1311] (Claim 3)

[1312] The system of claim 1 , wherein the recommended content includes videos and books.

[1313] "Application example 2 when combining emotion engines"

[1314] (Claim 1)

[1315] a means for users to input their preferences and past browsing history;

[1316] means for transmitting the preferences, past browsing history, and real-time emotion data to a server;

[1317] A means for analyzing user preferences using a generating AI based on the preferences, past browsing history, and real-time emotion data;

[1318] means for generating a list of recommended content based on the analysis results;

[1319] A means of collecting additional information related to the content we recommend; and

[1320] means for transmitting the list of recommended content and additional information to a user;

[1321] means for displaying the list of recommended content and additional information to a user;

[1322] means for collecting the real-time emotion data using a wearable device, a camera, or a microphone;

[1323] A system including:

[1324] (Claim 2)

[1325] 10. The system of claim 1, wherein the additional information includes comments from producers or authors, interviews, and behind-the-scenes information.

[1326] (Claim 3)

[1327] The system of claim 1 , wherein the recommended content includes media content and cartoons. [Explanation of symbols]

[1328] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for users to input their preferences and past browsing history; means for transmitting the preferences and past browsing history to a server; A means for analyzing user preferences using a generating AI based on the preferences and past browsing history; means for generating a list of recommended content based on the analysis results; A means of collecting additional information related to the content we recommend; and means for transmitting the list of recommended content and additional information to a user; means for displaying the list of recommended content and additional information to a user; A system including:

2. The system of claim 1 , wherein the additional information includes comments from directors or writers, interviews, and behind-the-scenes information.

3. The system of claim 1 , wherein the recommended content includes videos and cartoons.

Images