System

Abstract

A system is provided.SOLUTION: A system comprising: means for generating a user profile based on a favorite genre and a desired atmosphere received from a user; means for managing a reading history using the user profile; recommendation means including natural language processing and a machine learning algorithm for selecting an optimal recommended cartoon based on the user profile and the reading history; and means for presenting the recommended cartoon selected by the recommendation means to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In the digital comic market, the number of manga titles available to choose from is so large that it is difficult for users to find works that match their preferences and the atmosphere they want to read. This creates a need for readers to be able to quickly find the manga that best suits them from the many options available and to provide a satisfying reading experience. Publishers also face the challenge of accurately understanding readers' interests and conducting effective promotions. [Means for solving the problem]

[0005] To solve these problems, the present invention provides a system that includes: means for generating a user profile based on the user's preferred genres and preferred reading atmospheres; means for managing a reading history using the user profile; recommendation means including natural language processing and machine learning algorithms for selecting optimal manga recommendations based on the user profile and reading history; and means for presenting the recommended manga selected by the recommendation means to the user. This allows users to easily find the manga that best suits their individual interests and psychological tendencies, and enables publishers to accurately grasp readers' interests and conduct effective promotions.

[0006] A "user profile" is an individual database generated based on information including the user's preferences and desired reading atmosphere.

[0007] "Reading history" is data that includes historical information about the manga that the user has read so far.

[0008] "Natural language processing" is a technology that allows computers to understand and process human language.

[0009] A "machine learning algorithm" is an algorithm that learns patterns from data and makes predictions and classifications for unknown data.

[0010] The "recommendation means" is a means for selecting the most suitable manga to recommend based on the user profile and reading history.

[0011] A "genre" is a category of manga that is classified based on a particular theme or style.

[0012] The "desired reading atmosphere" refers to information about a particular emotion or atmosphere that a user feels like reading.

[0013] A "system" is a set of devices or programs in which multiple components or means are combined to achieve a specific function. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0022] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0035] This invention relates to a system that recommends the most suitable manga based on a user's preferred genre and desired reading atmosphere. The system generates an individual user profile based on information input by the user and manages their reading history. It also uses natural language processing and machine learning algorithms to recommend the most suitable manga for each user and presents the results to the user.

[0036] System Configuration

[0037] The system consists of the following main components:

[0038] 1. A terminal for receiving input from a user

[0039] 2. A server that processes input information and manages user profiles and reading histories

[0040] 3. A recommendation method that uses natural language processing and machine learning algorithms to select recommended manga.

[0041] Program processing overview

[0042] 1. User Registration

[0043] Users register and input their preferred genres and preferred reading atmosphere, which creates a personalized profile for the user.

[0044] The terminal organizes this input information and sends it to the server.

[0045] The server generates a user profile based on the received information and stores it in a database.

[0046] 2. Add reading history

[0047] When a user reads a manga, the information is sent to the server via the terminal.

[0048] The server updates the user's reading history and adds the latest reading information to the user's profile.

[0049] 3. Manga Recommendations

[0050] When a user requests a recommendation for a new manga, the device sends the request to the server.

[0051] The server analyzes user profiles and reading histories and uses natural language processing and machine learning algorithms to select recommended manga.

[0052] The recommendation results are sent from the server to the terminal, which then displays them to the user.

[0053] Specific examples

[0054] For example, a user registers with the ID "user123" and enters "fantasy" as their preferred genre and "exciting" as the desired reading atmosphere. The device organizes this information and sends it to the server. The server creates a user profile based on the received information and saves it in the profile of "user123."

[0055] Next, when the user finishes reading "Manga1," the information is sent from the terminal to the server, which adds "Manga1" to the reading history of "user123."

[0056] When the user subsequently requests a recommendation for a new manga, the server analyzes the profile and reading history of user "user123" and uses natural language processing and machine learning algorithms to recommend "Manga2," "Manga3," and "Manga4." The recommendation results are then sent to the device, which displays them to the user.

[0057] ---

[0058] The above is an embodiment of the present invention. This system allows users to quickly find manga that best suits their preferences and the atmosphere they want to read, improving their reading experience. It also allows publishers to accurately grasp readers' interests and promote their works more effectively.

[0059] The processing flow will be explained below.

[0060] Step 1:

[0061] The user registers by entering their ID, preferred genre, and desired reading atmosphere.

[0062] Step 2:

[0063] The device receives the input information and sends it to the server in a format that creates a data packet containing the user's ID, preferred genre, and desired reading atmosphere.

[0064] Step 3:

[0065] The server analyzes the received data and generates a user profile, including the user ID, preferred genre, and preferred reading atmosphere, which is then stored in a database.

[0066] Step 4:

[0067] The user selects a manga and begins reading.

[0068] Step 5:

[0069] When a user finishes reading a manga, the device acquires that information. Specifically, it records the title and ID of the manga that the user has finished reading.

[0070] Step 6:

[0071] The device sends the reading history information to the server, generating a data packet containing the user ID and the ID of the manga that has been read.

[0072] Step 7:

[0073] The server analyzes the received reading history data and updates the user profile. Specifically, it adds the new manga ID to the user's reading history list.

[0074] Step 8:

[0075] A user requests a recommendation for a new manga. The user sends a recommendation request through the terminal.

[0076] Step 9:

[0077] The device receives the recommendation request and sends it to the server. Specifically, it generates a recommendation request data packet including the user ID.

[0078] Step 10:

[0079] The server receives recommendation requests, analyzes the user's profile and reading history, and generates a list of recommendations based on the user's preferences using natural language processing and machine learning algorithms.

[0080] Step 11:

[0081] The server sends the generated recommendation list to the device. Specifically, it generates a data packet containing the titles and IDs of the recommended manga.

[0082] Step 12:

[0083] The terminal receives the recommendation list and displays it to the user through a graphical user interface.

[0084] Step 13:

[0085] The user reviews the list of recommended manga and selects the manga they want to read next.

[0086] Example 1

[0087] 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."

[0088] Currently, users face challenges in quickly finding the most appropriate information based on their preferences and desired reading atmosphere. Furthermore, it is difficult to generate and manage profiles that accurately reflect users' interests and psychological tendencies, which reduces the accuracy of recommendations. Furthermore, there is a need for an efficient recommendation method to promote the discovery of new information.

[0089] 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.

[0090] In this invention, the server includes: means for generating a user profile based on the user's preferred genres and desired reading style received from the user; means for managing a reading history using the user profile; means for managing reading start information and reading completion information based on the reading history information; recommendation means including natural language processing and machine learning algorithms for selecting optimal recommended information based on the user profile and reading history; means for presenting the recommended information selected by the recommendation means to the user; and means for analyzing prompt sentences that receive recommendation requests from the user. This allows users to quickly find information that best suits their preferences and desired reading style, improving the user experience. It also enables the generation and management of highly accurate profiles that reflect the user's interests and psychological tendencies, and promotes the discovery of new information.

[0091] A "user profile" is data that compiles individual information including a user's preferred genres, preferred reading style, reading history, and so on.

[0092] "Reading history" is a record of the comics and books that a user has read, and is data that includes information on when the user started reading and when the user finished reading.

[0093] "Natural language processing" is a technology for analyzing text data entered by a user and understanding its meaning and intent.

[0094] A "machine learning algorithm" is an algorithm that learns patterns and relationships from large amounts of data and makes predictions and recommendations.

[0095] "Recommendation means" refers to methods and technologies for selecting and presenting optimal information to a user based on the user's profile and reading history.

[0096] A "prompt sentence" is a text sentence that describes a question or request that a user makes to the system.

[0097] A "parsing means" is a technique or method for parsing a prompt or other input data and understanding its meaning.

[0098] "Information" refers to data such as recommended manga and books provided to users.

[0099] This invention relates to a system that recommends the most suitable manga based on a user's preferred genre and desired reading atmosphere. This system generates an individual user profile based on information input by the user and manages their reading history. It also uses natural language processing and machine learning algorithms to recommend the most suitable manga for each user and presents the results to the user.

[0100] The system consists of the following main components:

[0101] 1. A terminal for receiving input from a user

[0102] 2. A server that processes input information and manages user profiles and reading histories

[0103] 3. A recommendation method that uses natural language processing and machine learning algorithms to select recommended manga.

[0104] Hardware and Software Environment

[0105] 1. Terminal - A device that receives user input, such as a smartphone or PC.

[0106] 2. Server - The server that processes and stores the data. Specifically, we use cloud-based servers (e.g., Amazon Web Services (AWS)).

[0107] 3. Natural language processing models - for example, BERT or GPT-3 - are used to analyze user input.

[0108] 4. Machine learning algorithms - for example, using Collaborative Filtering and Content-Based Filtering to recommend manga.

[0109] System Operation

[0110] User Registration

[0111] A user registers using a terminal and inputs their preferred genre and preferred reading atmosphere. This information is sent from the terminal to the server, and the server generates a user profile based on the received information and stores it in a database. For example, if a user likes the "fantasy" genre and prefers an "exciting" atmosphere, a profile can be generated by inputting this information.

[0112] Add reading history

[0113] When a user reads a manga, that information is sent to the server via the terminal. The server records the user's reading history in a database and adds the latest reading information to the user's profile. For example, when a user finishes reading a title called "Manga1," that reading history is sent to the server and added to the user's profile.

[0114] Manga Recommendations

[0115] When a user requests a recommendation for a new manga, the device sends the request to the server. The server analyzes the user's profile and reading history, and recommends the most suitable manga using natural language processing models and machine learning algorithms. The recommendation results are sent from the server to the device and displayed to the user. For example, if a user enters the prompt "I want to read a fantasy and exciting manga," the system will recommend "Manga2," "Manga3," and "Manga4."

[0116] Examples of prompt statements

[0117] When a user inputs a prompt such as "I want to read an exciting fantasy manga. Can you recommend some?", the system analyzes it using a natural language processing model and makes the best recommendations. This allows users to quickly find the manga that best suits their preferences and the atmosphere they want to read.

[0118] In this way, the present invention improves the user experience and provides an environment in which users can efficiently discover manga that suit their tastes.

[0119] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0120] Step 1:

[0121] The user registers using a terminal. The user enters their ID, password, preferred genre (e.g., "fantasy"), and desired reading atmosphere (e.g., "exciting") into the input form on the terminal. This information is registered on the terminal as input data.

[0122] Input: User ID, password, preferred genre, desired reading atmosphere

[0123] Specific operation: Fill in the information in the input form and press the "Register" button to complete the entry.

[0124] Output: The terminal organizes the input information and generates data in JSON format.

[0125] Step 2:

[0126] The device sends the information entered by the user to the server, where it is encrypted and securely transmitted using the HTTPS protocol.

[0127] Input: JSON formatted data entered by the user

[0128] Specific operation: The device formats the JSON data and sends it to the server via an HTTPS request.

[0129] Output: The server receives the JSON data.

[0130] Step 3:

[0131] The server analyzes the received information and generates a user profile, storing the data according to an internal database schema based on the genre and atmosphere information received.

[0132] Input: JSON format data received from the terminal

[0133] Specific operation: The server deserializes the received data, generates a user profile, and saves it in the database.

[0134] Output: The generated user profile is stored in a database.

[0135] Step 4:

[0136] The user starts reading a manga through the device. The user uses the search function in the system to select a manga (e.g., "Manga1") and clicks to read it.

[0137] Input: User's search keyword or manga selection status

[0138] Specific action: The user selects a manga from the search box or list and presses the "Read" button.

[0139] Output: Information about the selected manga will be displayed on the device.

[0140] Step 5:

[0141] The device sends information about the comic the user has started reading to the server, including the comic's ID and the user ID.

[0142] Input: User's selected manga ID and user ID

[0143] Specific operation: The device formats the selection information and sends it to the server via an HTTPS request.

[0144] Output: The server receives the selection information.

[0145] Step 6:

[0146] The server updates the user's reading history based on the received information. The server updates the database to add the new reading history to the user's profile.

[0147] Input: Received manga ID and user ID

[0148] Specific behavior: The server executes a database query to add a new reading history.

[0149] Output: The updated user's reading history is stored in the database.

[0150] Step 7:

[0151] The user requests a recommendation for a new manga. The user issues the request by clicking the "Recommend Manga" button.

[0152] Input: Recommendation request

[0153] What happens: The user presses a button to request a recommendation.

[0154] Output: A recommendation request is sent from the device to the server.

[0155] Step 8:

[0156] The device sends recommendation request information, including the user ID, to the server.

[0157] Input: Recommendation request with user ID

[0158] What it does: It formats the recommendation request and sends it to the server via an HTTPS request.

[0159] Output: The server receives the recommendation request.

[0160] Step 9:

[0161] The server analyzes user profiles and reading histories, uses natural language processing models to extract keywords related to the user's preferences and reading history, and uses machine learning algorithms to select the most suitable manga recommendations.

[0162] Input: User profile and reading history

[0163] How it works: Natural language processing models analyze profile data, and machine learning algorithms select the best recommendations.

[0164] Output: A list of recommended manga is generated.

[0165] Step 10:

[0166] The server transmits the selected recommendation results to the terminal.

[0167] Input: Recommended manga list

[0168] Specific operation: The recommendation list is formatted and sent to the device as an HTTPS response.

[0169] Output: The terminal receives the recommendation results.

[0170] Step 11:

[0171] The device displays the recommendation results to the user, who can then check the recommended manga (e.g., "Manga2," "Manga3," "Manga4").

[0172] Input: Recommended manga list received from the server

[0173] Specific operation: Display the recommendation results on the user interface.

[0174] Output: The recommended manga is displayed to the user.

[0175] (Application example 1)

[0176] 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."

[0177] Conventional manga recommendation systems have difficulty recommending appropriate manga because they do not fully consider users' preferences or reading history. Furthermore, they are insufficient as a means for users to discover new manga, limiting the improvement of the reading experience. Furthermore, due to the lack of use across a variety of devices and the lack of AI technology, optimal recommendations to users are delayed and accuracy is reduced.

[0178] 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.

[0179] In this invention, the server includes: a means for generating a user profile based on the user's preferred genres and desired reading style; a means for managing a reading history using the user profile; a recommendation means including natural language processing and machine learning algorithms for selecting optimal manga recommendations based on the user profile and reading history; a means for presenting the recommended manga selected by the recommendation means to the user; a means including an application to be installed on a smartphone; a means for processing and storing data using a cloud server; and a means for optimizing the recommendation results using a generative AI model. This allows users to quickly find the optimal manga based on their preferences and reading history, improving their reading experience. Furthermore, the use of the cloud server and generative AI model improves the accuracy and processing speed of recommendation results.

[0180] A "user profile" is a collection of information about an individual user that is generated based on the user's preferred genres and preferred reading atmosphere.

[0181] "Reading history" is a record of the manga that a user has read so far, and is data that is managed as part of a user profile.

[0182] The "recommendation method" is a system that uses natural language processing and machine learning algorithms to select the most suitable manga based on the user's profile and reading history, and presents it to the user.

[0183] "Natural language processing" is a technology that allows computers to understand, generate, and manipulate human language, and in this system it is used to analyze the genre and atmosphere of manga.

[0184] A "machine learning algorithm" is a computational method that learns from data, extracts patterns and rules, and makes predictions and classifications for new data.

[0185] The "application installed on a smartphone" is software that allows users to access the system using their smartphone to receive manga recommendations and manage their reading history.

[0186] A "cloud server" is a remote server utilized over the Internet, and is an infrastructure for processing and storing data.

[0187] A "generative AI model" is an artificial intelligence model that has been trained in advance using large amounts of data, and is a technology used to optimize manga recommendation results.

[0188] This invention is a system that recommends the most suitable manga based on the user's preferred genre and desired reading atmosphere.

[0189] System configuration

[0190] The system consists of the following main components:

[0191] 1. A device (smartphone) for receiving input from the user

[0192] 2. A server (cloud server) that processes input information and manages user profiles and reading histories

[0193] 3. A recommendation method (generative AI model) that uses natural language processing and machine learning algorithms to select recommended manga.

[0194] Hardware and Software Configuration

[0195] Hardware:

[0196] Smartphone

[0197] Cloud servers (e.g., Amazon Web Services, Microsoft Azure, Google Cloud Platform)

[0198] software:

[0199] Smartphone app development environment (iOS: Swift, Android: Kotlin)

[0200] Natural language processing libraries (e.g. TensorFlow, spaCy)

[0201] Machine learning algorithms (e.g., scikit-learn, PyTorch)

[0202] Database (e.g. MongoDB, MySQL)

[0203] Program processing overview

[0204] 1. User Registration:

[0205] Users register and input their preferred genres and the atmosphere they want to read. The smartphone organizes this information and sends it to the cloud server, which then creates a user profile based on the information it receives and stores it in a database.

[0206] 2. Add reading history:

[0207] When a user reads a manga, the information is sent to the cloud server via their smartphone. The server updates the user's reading history and adds the latest reading information to the user's profile.

[0208] 3. Manga Recommendations:

[0209] When a user requests a new manga recommendation, the smartphone device sends the request to a cloud server. The server analyzes the user's profile and reading history, and uses natural language processing and machine learning algorithms to select the most suitable manga. The server then optimizes the recommendation results using a generative AI model and sends the results to the smartphone device for display to the user.

[0210] Specific examples

[0211] For example, a user registers with the ID "user123" and enters "fantasy" as their preferred genre and "exciting" as the atmosphere they want to read. The smartphone organizes this information and sends it to the cloud server. The server creates a user profile based on the received information and saves it in the profile for "user123."

[0212] Next, when the user finishes reading "Manga1," the smartphone sends the information to the cloud server, which adds "Manga1" to the reading history of "user123."

[0213] Later, when the user requests a recommendation for a new manga, the cloud server analyzes the profile and reading history of user “user123” and selects the most suitable manga using natural language processing and machine learning algorithms.

[0214] Example prompts for generative AI models

[0215] Please recommend the best manga based on the following user profile.

[0216] User Profile:

[0217] ID: user123

[0218] Favorite genre: Fantasy

[0219] Reading mood: Exciting

[0220] Reading history: Manga1, Manga2, Manga3

[0221] Output the best manga recommendation results.

[0222] In this way, this system allows users to quickly find the manga that best suits their preferences and the atmosphere they want to read. Furthermore, by utilizing cloud servers and generative AI models, the accuracy and processing speed of recommendation results are improved, greatly improving the user's reading experience.

[0223] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0224] Step 1:

[0225] A user registers and inputs their preferred genre and preferred reading style. The device then organizes the input information and sends it to the cloud server. The input data includes the user ID, preferred genre, and preferred reading style. The cloud server receives this information, generates a user profile, and saves it in the database. As a result, individual user profiles are stored in the database.

[0226] Step 2:

[0227] When a user reads a manga, that information is sent to the cloud server via the device. The input data is the user ID and the title of the manga read. The cloud server receives this and adds the user's reading history to the user profile stored in the database. This updates the latest reading history information.

[0228] Step 3:

[0229] When a user requests a recommendation of a new manga, the device sends the request to the cloud server. The input data is the user ID. The cloud server extracts the user profile and reading history from the database and uses them for analysis. Specifically, it processes the data to recommend the most suitable manga to the user using a generative AI model. Here, natural language processing technology is used to analyze the user's profile information and reading history.

[0230] Step 4:

[0231] The cloud server inputs the prompt sentences into the generative AI model to obtain the optimal recommendation results. The input data is as follows:

[0232] Please recommend the best manga based on the following user profile.

[0233] User Profile:

[0234] ID: user123

[0235] Favorite genre: Fantasy

[0236] Reading mood: Exciting

[0237] Reading history: Manga1, Manga2, Manga3

[0238] Output the best manga recommendation results.

[0239] The generative AI model analyzes this prompt and generates the most suitable manga title. The generated result is a list of the most suitable manga titles.

[0240] Step 5:

[0241] The cloud server sends the generated recommendation results to the device, which receives them and displays them to the user. The output data is a list of recommended manga titles, allowing the user to view the best manga recommendation results based on their preferences.

[0242] Through the above processing steps, the system recommends the most suitable manga based on the user's preferences and reading history, improving the reading experience.

[0243] 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.

[0244] This invention relates to a system that combines a user's preferred genres and desired reading atmosphere with an emotion engine that recognizes the user's emotions. The system generates an individual user profile based on the user's input information and real-time emotion data, and manages their reading history. It also uses natural language processing and machine learning algorithms to recommend the most suitable manga for each user and presents the results to the user.

[0245] System Configuration

[0246] The system consists of the following main components:

[0247] 1. A terminal for receiving input from a user

[0248] 2. A server that processes input information and emotion data and manages user profiles and reading histories

[0249] 3. Emotion engine that recognizes and analyzes user emotion data

[0250] 4. A recommendation method that uses natural language processing and machine learning algorithms to select recommended manga.

[0251] Program processing overview

[0252] 1. User Registration

[0253] Users register and input their preferred genres and preferred reading atmosphere, which creates an individual user profile.

[0254] The terminal receives this input information, as well as the user's facial expression data, voice data, and other emotional data, and transmits them to the server.

[0255] The server generates a user profile based on the received information and emotion data and stores it in a database.

[0256] 2. Emotion Data Analysis

[0257] The emotion engine analyzes the user's emotion data in real time and provides the results to the server.

[0258] The server updates the user profile with the analysis results to reflect the user's psychological tendencies.

[0259] 3. Add reading history

[0260] When a user reads a manga, the information and emotional data are sent to the server via the device.

[0261] The server updates the user's reading history and adds the latest reading information and emotion data to the user profile.

[0262] 4. Manga Recommendations

[0263] When a user requests a recommendation for a new manga, the device sends the request to the server.

[0264] The server analyzes user profiles, emotional data, and reading history, and uses natural language processing and machine learning algorithms to select recommended manga.

[0265] The recommendation results are sent from the server to the terminal, which then displays them to the user.

[0266] Specific examples

[0267] For example, a user registers with the ID "user123" and enters "fantasy" as their preferred genre and "exciting" as the atmosphere they want to read. The device organizes this information along with the user's facial expression and voice data, and sends it to the server. The server generates a user profile based on the received information and emotional data, and saves it in the profile for "user123."

[0268] The emotion engine then analyzes the facial expression and voice data of user "user123" in real time and provides the analysis results to the server, which then updates the profile based on this data to reflect the user's psychological tendencies.

[0269] After that, when the user finishes reading "Manga1," the information and emotional data from the reading session are sent from the device to the server. The server updates the reading history and emotional data of "user123."

[0270] When a user requests a recommendation for a new manga, the server analyzes the profile, emotional data, and reading history of user "user123," and uses natural language processing and machine learning algorithms to recommend "Manga2," "Manga3," and "Manga4." The recommendation results are sent to the device, which then displays them to the user.

[0271] ---

[0272] The above is an embodiment of the present invention. This system allows users to quickly find the manga that best suits their tastes and desired reading atmosphere, as well as real-time emotional data, providing a highly satisfying reading experience. It also allows publishers to accurately grasp readers' interests and emotions and effectively promote their works.

[0273] The processing flow will be explained below.

[0274] Step 1:

[0275] The user registers by entering their ID, preferred genre, and desired reading atmosphere.

[0276] Step 2:

[0277] The device receives the input information and organizes it according to a format, specifically creating a data packet containing the user's ID, preferred genre, and desired reading atmosphere.

[0278] Step 3:

[0279] The terminal transmits the organized data packets to the server.

[0280] Step 4:

[0281] The server analyzes the received data and generates a user profile, specifically storing the user ID, preferred genre, and preferred reading atmosphere in a database.

[0282] Step 5:

[0283] The device collects emotional data such as facial expressions and voice data from the user in real time and transmits it to the server.

[0284] Step 6:

[0285] The emotion engine analyzes the received emotion data and provides the results to the server. Specifically, it recognizes emotions from the user's facial expressions and voice and generates analysis results.

[0286] Step 7:

[0287] The server updates the user profile based on the analysis of the emotional data, specifically adding the emotional data to the profile to reflect the user's psychological tendencies.

[0288] Step 8:

[0289] The user selects a manga and reads it. Emotional data is collected while the user is reading.

[0290] Step 9:

[0291] The terminal transmits the user's reading history information and emotional data during reading to the server.

[0292] Step 10:

[0293] The server updates the user profile based on the reading history and emotion data. Specifically, it adds the ID and emotion data of the new manga to the user profile.

[0294] Step 11:

[0295] A user requests a recommendation for a new manga. The user sends a recommendation request through the terminal.

[0296] Step 12:

[0297] The device receives the recommendation request and sends it to the server. Specifically, it generates a recommendation request data packet including the user ID.

[0298] Step 13:

[0299] The server receives recommendation requests and analyzes user profiles, emotional data, and reading history, using natural language processing and machine learning algorithms to generate a list of recommendations based on the user's preferences.

[0300] Step 14:

[0301] The server sends the generated recommendation list to the device. Specifically, it generates a data packet containing the titles and IDs of the recommended manga.

[0302] Step 15:

[0303] The terminal receives the recommendation list and displays it to the user through a graphical user interface.

[0304] Step 16:

[0305] The user reviews the list of recommended manga and selects the manga they want to read next.

[0306] Example 2

[0307] 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."

[0308] Conventional recommendation systems make recommendations based on the user's preferences and desired reading atmosphere, but they do not fully consider the user's emotions or psychological tendencies, making it difficult to increase user satisfaction. In addition, there is a need for more accurate recommendations by utilizing real-time emotional data.

[0309] 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.

[0310] In this invention, the server includes: means for generating user information based on the user's preferred types and desired reading atmospheres received from the user; means for managing a reading history using the user information and emotion data; recommendation means including natural language processing and machine learning algorithms for selecting optimal recommended materials based on the user information and reading history; means for presenting the recommended materials selected by the recommendation means to the user; emotion analysis means for analyzing the user's current emotion data in real time; and update means for reflecting the analysis results of the emotion analysis means in the user information. This enables recommendations that take the user's emotions and psychological tendencies into consideration, providing a highly satisfying reading experience.

[0311] "User" refers to an individual who uses this system to receive manga recommendations.

[0312] "Favorite types" refers to the genres and categories of manga that users want to read, which they enter when registering.

[0313] "Desired reading atmosphere" refers to a specific emotion or tone of the manga that a user wants to read (e.g., exciting, relaxing).

[0314] "User information" refers to a profile generated based on the user's input preferences, desired reading atmosphere, and emotional data.

[0315] "Emotion data" refers to data that quantifies emotions derived from the user's facial expressions and voice.

[0316] "Reading history" refers to information including a record of the manga that the user has read in the past and emotional data at the time.

[0317] "Server" refers to the computer system that processes data and executes the recommendation algorithms of the System.

[0318] "Natural language processing" refers to algorithms and techniques for analyzing text information and understanding its meaning.

[0319] A "machine learning algorithm" refers to a computational method for automatically learning from data and finding patterns.

[0320] "Recommendation means" refers to the part of the system that uses user information, reading history, natural language processing, and machine learning algorithms to recommend the most suitable manga to users.

[0321] "Emotion analysis means" refers to the part of the system that analyzes the user's emotion data in real time and generates the results.

[0322] The "update means" refers to the part of the system that reflects the results of the emotion analysis means in the user information and keeps that information up to date.

[0323] "Recommended Materials" refers to manga recommended based on a user's profile and emotional data.

[0324] The present invention is a system that analyzes real-time emotional data in addition to the user's preferred types and desired reading atmosphere to recommend the most suitable manga to the user. The following describes the detailed procedure for specifically implementing the present invention.

[0325] System Configuration

[0326] The system consists of the following main components:

[0327] 1. A terminal for receiving input from a user

[0328] 2. A server that processes input information and emotion data and manages user profiles and reading histories

[0329] 3. Emotion analysis method for recognizing and analyzing user emotion data

[0330] 4. A recommendation method that uses natural language processing and machine learning algorithms to select recommended manga.

[0331] Specific hardware and software used

[0332] Device:

[0333] Use devices such as smartphones, tablets, and PCs to collect user input and emotional data.

[0334] Emotion analysis means:

[0335] Technologies such as Emotion API, Affectiva, and FaceReader are used to analyze emotional data.

[0336] server:

[0337] Data processing and management uses cloud services such as AWS EC2, Google Cloud, and Microsoft Azure.

[0338] Database:

[0339] Databases such as MySQL and PostgreSQL are used to store user profiles and reading history.

[0340] Natural Language Processing and Machine Learning:

[0341] The recommendation algorithm is implemented using Python libraries (NLTK, Scikit-learn, TensorFlow, PyTorch).

[0342] System Operation Overview

[0343] User Registration

[0344] The user uses a terminal to access a new registration form and inputs their preferred genre (e.g., "fantasy") and the atmosphere they want to read (e.g., "exciting"). The terminal collects this input information and sends it to the server along with the user's facial expression and voice data. The server generates user information based on the received data and stores it in a database.

[0345] Emotional Data Analysis

[0346] While a user is logged in to their device, real-time emotional data is collected via the camera and microphone. The device sends this data to a server, which then analyzes the received data using emotion analysis tools. The analysis results are reflected in the user information, and the user profile is updated to the latest version.

[0347] Add reading history

[0348] When a user finishes reading a manga, the terminal sends the information along with the emotional data from the reading session to the server. The server receives this data and updates the user's reading history and emotional data.

[0349] Manga Recommendations

[0350] When a user requests a new manga recommendation, the request is sent from the device to the server. The server analyzes the user's information, reading history, and emotional data, and uses natural language processing and machine learning algorithms to select the most suitable manga. The recommendation results are sent from the server to the device, which then displays them to the user.

[0351] Specific examples

[0352] For example, a user registers with the ID "user123" and enters "fantasy" as their preferred type of book and "exciting" as the desired reading atmosphere. The device organizes this information, along with facial expression and voice data, and sends it to the server. The server generates a user profile based on the received information and saves it in the profile for "user123."

[0353] The emotion analysis means analyzes the facial expression and voice data of user "user123" in real time and provides the analysis results to the server, which then updates the profile based on this data to reflect the user's psychological tendencies.

[0354] Next, when the user finishes reading "Manga1," that information and the emotional data during reading are sent from the terminal to the server, and the server updates the reading history and emotional data of "user123."

[0355] When a user requests a recommendation for a new manga, the server analyzes the profile, emotional data, and reading history of user "user123," and uses natural language processing and machine learning algorithms to recommend "Manga2," "Manga3," and "Manga4." The recommendation results are sent to the device, which then displays them to the user.

[0356] Prompt Sentence Examples

[0357] Example prompt 1:

[0358] "User123 is looking for manga in the fantasy genre with an exciting atmosphere. Please recommend three manga that fit his needs, taking into account his latest emotional data and reading history."

[0359] Example prompt 2:

[0360] "User ID: user321, Favorite genre: Horror, Recent emotional data: Calm. Based on this information, please recommend two manga."

[0361] The above is a detailed embodiment of the present invention. This system allows users to effectively find the most suitable manga based on their own feelings and preferences, providing a highly satisfying reading experience.

[0362] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0363] Step 1:

[0364] Entering user information and registering

[0365] Users use their device to access a new registration form and enter their preferred genre (e.g., "fantasy") and the atmosphere they want to read (e.g., "exciting").

[0366] Input: User's preferred type, desired reading atmosphere, facial expression data, voice data

[0367] Output: User information sent to the server

[0368] Specific operation: When a user clicks the "Register" button, the device collects form data using JavaScript, captures facial expressions with the camera, and records audio data with the microphone. The device converts the collected data into JSON format and sends it to the server using an HTTP POST request.

[0369] Step 2:

[0370] Saving user information

[0371] The server generates a user profile based on the received information and stores it in a database.

[0372] Input: JSON format user information sent from the terminal

[0373] Output: User profile stored in the database

[0374] What happens: The server receives the request using Python's Flask, parses the data, creates a profile for the user, and saves it in a MySQL database by executing an INSERT query.

[0375] Step 3:

[0376] Collecting Emotional Data

[0377] While the user is logged in to the device, real-time emotional data is collected via the camera and microphone.

[0378] Input: User's facial expression data, voice data

[0379] Output: Emotion data sent from the device to the server

[0380] How it works: When a user logs in to the system and loads a page, the device uses JavaScript to trigger the camera and microphone. Facial expression data and voice data are collected in real time using WebRTC. The device then sends this real-time data to the server using Python's Socket.IO.

[0381] Step 4:

[0382] Emotional Data Analysis

[0383] The server uses an emotion engine to analyze the received data.

[0384] Input: Real-time emotion data sent from the device

[0385] Output: Parsed emotion data, updated user profile

[0386] Specific operation: The server analyzes the received data using Emotion API (or Affectiva, FaceReader) and obtains the results. The server reflects the analysis results in the user profile and updates the database.

[0387] Step 5:

[0388] Add reading history

[0389] When the user finishes reading the manga, the information about the manga is sent from the terminal to the server along with the emotional data recorded during the reading.

[0390] Input: Information about the manga the user has read, emotional data while reading

[0391] Output: Updated reading history, sentiment data

[0392] Specific operation: When the user clicks the "Finished reading" button, the device collects information about the comic (title, ID, etc.). The device then sends the emotion data captured while reading to the server. The server adds the entry to the database and stores the emotion data.

[0393] Step 6:

[0394] Manga Recommendations

[0395] When a user requests a recommendation of a new manga, the request is sent from the terminal to the server.

[0396] Input: User request, user information, reading history, emotional data

[0397] Output: Recommended manga list

[0398] How it works: When a user clicks the "Recommend a new manga" button, the device generates a request in JSON format. The device then sends it to the server using an HTTP POST request. The server receives the request and analyzes it based on the user's profile, reading history, and sentiment data. It then runs natural language processing and machine learning algorithms using Python libraries (such as NLTK, Scikit-learn, and TensorFlow) to generate an optimal list of manga recommendations. The server then returns the recommendation results in JSON format to the device, which then displays them to the user as a web page.

[0399] (Application example 2)

[0400] 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."

[0401] In today's world, it is extremely difficult for users to select content that matches their preferences and current emotions from the vast amount of content available. Furthermore, conventional content recommendation systems are primarily based on a user's past behavioral history and preferences, making it difficult to provide recommendations that reflect real-time emotions and psychological states. This can prevent users from appropriately selecting content that matches their momentary emotions, potentially resulting in a decrease in user satisfaction. To address this issue, a content recommendation system that reflects a user's preferences and emotions in real time is needed.

[0402] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0403] In this invention, the server includes: means for generating a user profile based on the user's preferred genres and desired reading atmosphere received from the user; means including an emotion engine for analyzing emotion data collected via the terminal and reflecting the data in the user profile; means for managing a reading history using the user profile and emotion data; recommendation means including natural language processing and machine learning algorithms for selecting optimal recommended content based on the user profile and reading history; and means for presenting the recommended content selected by the recommendation means to the user. This allows the user to quickly find optimal content based on their preferences and real-time emotions, resulting in a highly satisfying experience.

[0404] A "user profile" refers to data containing individual user information that is generated by integrating information such as the user's preferred genres, the mood they want to read, and real-time emotional data.

[0405] "Emotion data" refers to data related to emotions acquired in real time, such as facial expression data and voice data of a user collected via a terminal.

[0406] An "emotion engine" refers to software or hardware that analyzes collected emotion data and reflects the results in a user profile.

[0407] "Reading history" refers to data that records and manages content that a user has read in the past and emotional data at the time.

[0408] "Natural language processing" refers to the technology that enables computers to understand, generate, and analyze human language.

[0409] "Machine learning algorithms" are algorithms that allow computers to learn from data, find patterns, and make predictions and decisions.

[0410] "Recommendation tool" refers to a system component that uses natural language processing and machine learning algorithms to select the most appropriate content based on user profile, emotional data, and reading history.

[0411] "Content" refers to the general term for information and entertainment consumed by users, such as manga, videos, and music.

[0412] "Terminal" refers to a device that collects emotional data and connects the user to the system.

[0413] A "server" refers to a computer system that performs a series of processes such as managing user profiles and reading history, analyzing emotional data, and recommending content.

[0414] The system embodying this invention creates an individual user profile based on the user's preferred genres and desired reading atmosphere, and recommends optimal content while reflecting the user's real-time psychological state through emotional data.

[0415] System Configuration

[0416] The system includes the following main components:

[0417] 1. Terminal

[0418] A device that receives input from users and collects emotional data. Examples include smartphones and tablets. The device uses a camera and microphone to capture the user's facial expression and voice data, and sends it to a server.

[0419] 2. Server

[0420] It processes input information and emotion data, and manages user profiles and reading histories. Its role is to generate user profiles, manage reading histories, and provide content selected by recommendation means to the device.

[0421] 3. Emotion Engine

[0422] The emotion engine analyzes the user's emotion data in real time and updates the user profile by providing the results to the server. The emotion engine consists of software and hardware that analyzes the user's facial expressions and voice data.

[0423] 4. Recommendation method

[0424] It uses natural language processing (NLP) and machine learning algorithms to select the most suitable content based on the user's profile and reading history. It runs on the server and sends the selected content to the device.

[0425] Program processing

[0426] 1. User Registration

[0427] Users register and input their preferred genres and preferred reading atmospheres. This creates an individual user profile. The device then sends this input information, along with the user's facial expression and voice data, to the server.

[0428] 2. Data analysis and profile generation

[0429] The server generates a user profile based on the received information and emotion data and stores it in a database. The emotion engine analyzes the emotion data in real time and provides the analysis results to the server.

[0430] 3. Reflecting Emotional Data

[0431] Based on the analysis results of the emotion engine, the server updates the user profile to reflect psychological trends. Specifically, it analyzes information obtained from facial expressions and voice to detect and record the user's current emotions.

[0432] 4. Add reading history

[0433] Each time a user consumes content, the device sends the content along with emotional data to the server, which then updates the user's reading history and adds the latest reading information and emotional data to the user profile.

[0434] 5. Content Recommendations

[0435] When a user requests new content recommendations, the server analyzes the user's profile, emotional data, and reading history, and uses natural language processing (NLP) and machine learning algorithms to select the most suitable content. The selected recommendations are then sent to the device, which then displays them to the user.

[0436] Specific examples

[0437] For example, suppose a user registers with the ID "user456" and selects "SF" as their preferred genre and "relaxing" as their preferred reading atmosphere. The device collects this information along with the user's facial expression and voice data and sends it to the server. The server creates a profile for "user456" based on the received information and emotional data.

[0438] The emotion engine then analyzes the facial and voice data of "user456" in real time and provides the results to the server, which then updates the profile based on this data to reflect the user's psychological tendencies.

[0439] After that, when the user finishes reading "MangaX," the device sends the information along with the emotional data from the reading session to the server. The server then updates the reading history and emotional data of "user456."

[0440] Finally, when the user requests a recommendation for a new manga, the server analyzes it and recommends the most suitable "MangaY" and "MangaZ." The recommendation results are sent to the device of "user456," which then displays them to the user.

[0441] Prompt Sentence Examples

[0442] "Recommend MangaY and MangaZ based on the user's preferred genre of SF and the relaxing atmosphere they want to experience while reading."

[0443] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0444] Step 1:

[0445] User Registration

[0446] The user registers and inputs their preferred genre and desired reading atmosphere, which creates an initial profile for the user. The device collects this input information along with the user's facial expression and voice data, and sends it to the server.

[0447] Input: User information (preferred genre, desired reading atmosphere), facial expression data, voice data

[0448] Data processing: An initial user profile is generated based on the input information. Facial expression data and voice data are analyzed by the emotion engine and registered as initial emotion data.

[0449] Output: Generated initial user profile

[0450] Step 2:

[0451] Data analysis and profile generation

[0452] The server generates an initial user profile based on the received information and emotion data and stores it in a database. At this time, the emotion engine analyzes the emotion data in real time and provides the results to the server.

[0453] Input: Initial user profile, emotion data

[0454] Data processing: Data is analyzed using the emotion engine to evaluate the user's emotional state and update the user profile accordingly.

[0455] Output: Updated user profile

[0456] Step 3:

[0457] Emotion data reflection

[0458] The emotion engine analyzes the emotion data acquired in real time, and the server updates the user profile based on the results. The user's current emotional state is reflected in the profile.

[0459] Input: Real-time emotion data

[0460] Data processing: The emotion engine analyzes facial expression and voice data, converts the user's emotions into numerical values, and evaluates them. The evaluation results are sent to the server and reflected in the user profile.

[0461] Output: User profile reflecting emotional data

[0462] Step 4:

[0463] Add reading history

[0464] Every time a user consumes content, that information and emotional data is sent from the device to the server, which then uses this information to update the user's reading history and reflect it in their profile.

[0465] Input: Reading information, emotional data during consumption

[0466] Data processing: Reading information and emotion data are combined and added to the database as a series of historical data. User profiles are updated based on reading history.

[0467] Output: Updated reading history, user profile

[0468] Step 5:

[0469] Content Recommendations

[0470] When a user requests new content recommendations, the server analyzes the user's profile, emotional data, and reading history to recommend the most appropriate content. This is done using natural language processing and machine learning algorithms. The recommended content is then sent to the device and displayed to the user.

[0471] Input: User profile, reading history, real-time emotional data

[0472] Data processing: Analyze data using natural language processing and machine learning algorithms to select the most suitable content. The results are then verified using a generative AI model.

[0473] Output: Recommended content

[0474] Specific prompt examples:

[0475] "Recommend MangaY and MangaZ based on the user's preferred genre of SF and the relaxing atmosphere they want to experience while reading."

[0476] 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.

[0477] 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.

[0478] 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.

[0479] [Second embodiment]

[0480] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0481] 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.

[0482] 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).

[0483] 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.

[0484] 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.

[0485] 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).

[0486] 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.

[0487] 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.

[0488] 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.

[0489] 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.

[0490] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0491] 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."

[0492] This invention relates to a system that recommends the most suitable manga based on a user's preferred genre and desired reading atmosphere. The system generates an individual user profile based on information input by the user and manages their reading history. It also uses natural language processing and machine learning algorithms to recommend the most suitable manga for each user and presents the results to the user.

[0493] System Configuration

[0494] The system consists of the following main components:

[0495] 1. A terminal for receiving input from a user

[0496] 2. A server that processes input information and manages user profiles and reading histories

[0497] 3. A recommendation method that uses natural language processing and machine learning algorithms to select recommended manga.

[0498] Program processing overview

[0499] 1. User Registration

[0500] Users register and input their preferred genres and preferred reading atmosphere, which creates a personalized profile for the user.

[0501] The terminal organizes this input information and sends it to the server.

[0502] The server generates a user profile based on the received information and stores it in a database.

[0503] 2. Add reading history

[0504] When a user reads a manga, the information is sent to the server via the terminal.

[0505] The server updates the user's reading history and adds the latest reading information to the user's profile.

[0506] 3. Manga Recommendations

[0507] When a user requests a recommendation for a new manga, the device sends the request to the server.

[0508] The server analyzes user profiles and reading histories and uses natural language processing and machine learning algorithms to select recommended manga.

[0509] The recommendation results are sent from the server to the terminal, which then displays them to the user.

[0510] Specific examples

[0511] For example, a user registers with the ID "user123" and enters "fantasy" as their preferred genre and "exciting" as the desired reading atmosphere. The device organizes this information and sends it to the server. The server creates a user profile based on the received information and saves it in the profile of "user123."

[0512] Next, when the user finishes reading "Manga1," the information is sent from the terminal to the server, which adds "Manga1" to the reading history of "user123."

[0513] When the user subsequently requests a recommendation for a new manga, the server analyzes the profile and reading history of user "user123" and uses natural language processing and machine learning algorithms to recommend "Manga2," "Manga3," and "Manga4." The recommendation results are then sent to the device, which displays them to the user.

[0514] ---

[0515] The above is an embodiment of the present invention. This system allows users to quickly find manga that best suits their preferences and the atmosphere they want to read, improving their reading experience. It also allows publishers to accurately grasp readers' interests and promote their works more effectively.

[0516] The processing flow will be explained below.

[0517] Step 1:

[0518] The user registers by entering their ID, preferred genre, and desired reading atmosphere.

[0519] Step 2:

[0520] The device receives the input information and sends it to the server in a format that creates a data packet containing the user's ID, preferred genre, and desired reading atmosphere.

[0521] Step 3:

[0522] The server analyzes the received data and generates a user profile, including the user ID, preferred genre, and preferred reading atmosphere, which is then stored in a database.

[0523] Step 4:

[0524] The user selects a manga and begins reading.

[0525] Step 5:

[0526] When a user finishes reading a manga, the device acquires that information. Specifically, it records the title and ID of the manga that the user has finished reading.

[0527] Step 6:

[0528] The device sends the reading history information to the server, generating a data packet containing the user ID and the ID of the manga that has been read.

[0529] Step 7:

[0530] The server analyzes the received reading history data and updates the user profile. Specifically, it adds the new manga ID to the user's reading history list.

[0531] Step 8:

[0532] A user requests a recommendation for a new manga. The user sends a recommendation request through the terminal.

[0533] Step 9:

[0534] The device receives the recommendation request and sends it to the server. Specifically, it generates a recommendation request data packet including the user ID.

[0535] Step 10:

[0536] The server receives recommendation requests, analyzes the user's profile and reading history, and generates a list of recommendations based on the user's preferences using natural language processing and machine learning algorithms.

[0537] Step 11:

[0538] The server sends the generated recommendation list to the device. Specifically, it generates a data packet containing the titles and IDs of the recommended manga.

[0539] Step 12:

[0540] The terminal receives the recommendation list and displays it to the user through a graphical user interface.

[0541] Step 13:

[0542] The user reviews the list of recommended manga and selects the manga they want to read next.

[0543] Example 1

[0544] 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."

[0545] Currently, users face challenges in quickly finding the most appropriate information based on their preferences and desired reading atmosphere. Furthermore, it is difficult to generate and manage profiles that accurately reflect users' interests and psychological tendencies, which reduces the accuracy of recommendations. Furthermore, there is a need for an efficient recommendation method to promote the discovery of new information.

[0546] 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.

[0547] In this invention, the server includes: means for generating a user profile based on the user's preferred genres and desired reading style received from the user; means for managing a reading history using the user profile; means for managing reading start information and reading completion information based on the reading history information; recommendation means including natural language processing and machine learning algorithms for selecting optimal recommended information based on the user profile and reading history; means for presenting the recommended information selected by the recommendation means to the user; and means for analyzing prompt sentences that receive recommendation requests from the user. This allows users to quickly find information that best suits their preferences and desired reading style, improving the user experience. It also enables the generation and management of highly accurate profiles that reflect the user's interests and psychological tendencies, and promotes the discovery of new information.

[0548] A "user profile" is data that compiles individual information including a user's preferred genres, preferred reading style, reading history, and so on.

[0549] "Reading history" is a record of the comics and books that a user has read, and is data that includes information on when the user started reading and when the user finished reading.

[0550] "Natural language processing" is a technology for analyzing text data entered by a user and understanding its meaning and intent.

[0551] A "machine learning algorithm" is an algorithm that learns patterns and relationships from large amounts of data and makes predictions and recommendations.

[0552] "Recommendation means" refers to methods and technologies for selecting and presenting optimal information to a user based on the user's profile and reading history.

[0553] A "prompt sentence" is a text sentence that describes a question or request that a user makes to the system.

[0554] A "parsing means" is a technique or method for parsing a prompt or other input data and understanding its meaning.

[0555] "Information" refers to data such as recommended manga and books provided to users.

[0556] This invention relates to a system that recommends the most suitable manga based on a user's preferred genre and desired reading atmosphere. This system generates an individual user profile based on information input by the user and manages their reading history. It also uses natural language processing and machine learning algorithms to recommend the most suitable manga for each user and presents the results to the user.

[0557] The system consists of the following main components:

[0558] 1. A terminal for receiving input from a user

[0559] 2. A server that processes input information and manages user profiles and reading histories

[0560] 3. A recommendation method that uses natural language processing and machine learning algorithms to select recommended manga.

[0561] Hardware and Software Environment

[0562] 1. Terminal - A device that receives user input, such as a smartphone or PC.

[0563] 2. Server - The server that processes and stores the data. Specifically, we use cloud-based servers (e.g., Amazon Web Services (AWS)).

[0564] 3. Natural language processing models - for example, BERT or GPT-3 - are used to analyze user input.

[0565] 4. Machine learning algorithms - for example, using Collaborative Filtering and Content-Based Filtering to recommend manga.

[0566] System Operation

[0567] User Registration

[0568] A user registers using a terminal and inputs their preferred genre and preferred reading atmosphere. This information is sent from the terminal to the server, and the server generates a user profile based on the received information and stores it in a database. For example, if a user likes the "fantasy" genre and prefers an "exciting" atmosphere, a profile can be generated by inputting this information.

[0569] Add reading history

[0570] When a user reads a manga, that information is sent to the server via the terminal. The server records the user's reading history in a database and adds the latest reading information to the user's profile. For example, when a user finishes reading a title called "Manga1," that reading history is sent to the server and added to the user's profile.

[0571] Manga Recommendations

[0572] When a user requests a recommendation for a new manga, the device sends the request to the server. The server analyzes the user's profile and reading history, and recommends the most suitable manga using natural language processing models and machine learning algorithms. The recommendation results are sent from the server to the device and displayed to the user. For example, if a user enters the prompt "I want to read a fantasy and exciting manga," the system will recommend "Manga2," "Manga3," and "Manga4."

[0573] Examples of prompt statements

[0574] When a user inputs a prompt such as "I want to read an exciting fantasy manga. Can you recommend some?", the system analyzes it using a natural language processing model and makes the best recommendations. This allows users to quickly find the manga that best suits their preferences and the atmosphere they want to read.

[0575] In this way, the present invention improves the user experience and provides an environment in which users can efficiently discover manga that suit their tastes.

[0576] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0577] Step 1:

[0578] The user registers using a terminal. The user enters their ID, password, preferred genre (e.g., "fantasy"), and desired reading atmosphere (e.g., "exciting") into the input form on the terminal. This information is registered on the terminal as input data.

[0579] Input: User ID, password, preferred genre, desired reading atmosphere

[0580] Specific operation: Fill in the information in the input form and press the "Register" button to complete the entry.

[0581] Output: The terminal organizes the input information and generates data in JSON format.

[0582] Step 2:

[0583] The device sends the information entered by the user to the server, where it is encrypted and securely transmitted using the HTTPS protocol.

[0584] Input: JSON formatted data entered by the user

[0585] Specific operation: The device formats the JSON data and sends it to the server via an HTTPS request.

[0586] Output: The server receives the JSON data.

[0587] Step 3:

[0588] The server analyzes the received information and generates a user profile, storing the data according to an internal database schema based on the genre and atmosphere information received.

[0589] Input: JSON format data received from the terminal

[0590] Specific operation: The server deserializes the received data, generates a user profile, and saves it in the database.

[0591] Output: The generated user profile is stored in a database.

[0592] Step 4:

[0593] The user starts reading a manga through the device. The user uses the search function in the system to select a manga (e.g., "Manga1") and clicks to read it.

[0594] Input: User's search keyword or manga selection status

[0595] Specific action: The user selects a manga from the search box or list and presses the "Read" button.

[0596] Output: Information about the selected manga will be displayed on the device.

[0597] Step 5:

[0598] The device sends information about the comic the user has started reading to the server, including the comic's ID and the user ID.

[0599] Input: User's selected manga ID and user ID

[0600] Specific operation: The device formats the selection information and sends it to the server via an HTTPS request.

[0601] Output: The server receives the selection information.

[0602] Step 6:

[0603] The server updates the user's reading history based on the received information. The server updates the database to add the new reading history to the user's profile.

[0604] Input: Received manga ID and user ID

[0605] Specific behavior: The server executes a database query to add a new reading history.

[0606] Output: The updated user's reading history is stored in the database.

[0607] Step 7:

[0608] The user requests a recommendation for a new manga. The user issues the request by clicking the "Recommend Manga" button.

[0609] Input: Recommendation request

[0610] What happens: The user presses a button to request a recommendation.

[0611] Output: A recommendation request is sent from the device to the server.

[0612] Step 8:

[0613] The device sends recommendation request information, including the user ID, to the server.

[0614] Input: Recommendation request with user ID

[0615] What it does: It formats the recommendation request and sends it to the server via an HTTPS request.

[0616] Output: The server receives the recommendation request.

[0617] Step 9:

[0618] The server analyzes user profiles and reading histories, uses natural language processing models to extract keywords related to the user's preferences and reading history, and uses machine learning algorithms to select the most suitable manga recommendations.

[0619] Input: User profile and reading history

[0620] How it works: Natural language processing models analyze profile data, and machine learning algorithms select the best recommendations.

[0621] Output: A list of recommended manga is generated.

[0622] Step 10:

[0623] The server transmits the selected recommendation results to the terminal.

[0624] Input: Recommended manga list

[0625] Specific operation: The recommendation list is formatted and sent to the device as an HTTPS response.

[0626] Output: The terminal receives the recommendation results.

[0627] Step 11:

[0628] The device displays the recommendation results to the user, who can then check the recommended manga (e.g., "Manga2," "Manga3," "Manga4").

[0629] Input: Recommended manga list received from the server

[0630] Specific operation: Display the recommendation results on the user interface.

[0631] Output: The recommended manga is displayed to the user.

[0632] (Application example 1)

[0633] 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."

[0634] Conventional manga recommendation systems have difficulty recommending appropriate manga because they do not fully consider users' preferences or reading history. Furthermore, they are insufficient as a means for users to discover new manga, limiting the improvement of the reading experience. Furthermore, due to the lack of use across a variety of devices and the lack of AI technology, optimal recommendations to users are delayed and accuracy is reduced.

[0635] 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.

[0636] In this invention, the server includes: a means for generating a user profile based on the user's preferred genres and desired reading style; a means for managing a reading history using the user profile; a recommendation means including natural language processing and machine learning algorithms for selecting optimal manga recommendations based on the user profile and reading history; a means for presenting the recommended manga selected by the recommendation means to the user; a means including an application to be installed on a smartphone; a means for processing and storing data using a cloud server; and a means for optimizing the recommendation results using a generative AI model. This allows users to quickly find the optimal manga based on their preferences and reading history, improving their reading experience. Furthermore, the use of the cloud server and generative AI model improves the accuracy and processing speed of recommendation results.

[0637] A "user profile" is a collection of information about an individual user that is generated based on the user's preferred genres and preferred reading atmosphere.

[0638] "Reading history" is a record of the manga that a user has read so far, and is data that is managed as part of a user profile.

[0639] The "recommendation method" is a system that uses natural language processing and machine learning algorithms to select the most suitable manga based on the user's profile and reading history, and presents it to the user.

[0640] "Natural language processing" is a technology that allows computers to understand, generate, and manipulate human language, and in this system it is used to analyze the genre and atmosphere of manga.

[0641] A "machine learning algorithm" is a computational method that learns from data, extracts patterns and rules, and makes predictions and classifications for new data.

[0642] The "application installed on a smartphone" is software that allows users to access the system using their smartphone to receive manga recommendations and manage their reading history.

[0643] A "cloud server" is a remote server utilized over the Internet, and is an infrastructure for processing and storing data.

[0644] A "generative AI model" is an artificial intelligence model that has been trained in advance using large amounts of data, and is a technology used to optimize manga recommendation results.

[0645] This invention is a system that recommends the most suitable manga based on the user's preferred genre and desired reading atmosphere.

[0646] System configuration

[0647] The system consists of the following main components:

[0648] 1. A device (smartphone) for receiving input from the user

[0649] 2. A server (cloud server) that processes input information and manages user profiles and reading histories

[0650] 3. A recommendation method (generative AI model) that uses natural language processing and machine learning algorithms to select recommended manga.

[0651] Hardware and Software Configuration

[0652] Hardware:

[0653] Smartphone

[0654] Cloud servers (e.g., Amazon Web Services, Microsoft Azure, Google Cloud Platform)

[0655] software:

[0656] Smartphone app development environment (iOS: Swift, Android: Kotlin)

[0657] Natural language processing libraries (e.g. TensorFlow, spaCy)

[0658] Machine learning algorithms (e.g., scikit-learn, PyTorch)

[0659] Database (e.g. MongoDB, MySQL)

[0660] Program processing overview

[0661] 1. User Registration:

[0662] Users register and input their preferred genres and the atmosphere they want to read. The smartphone organizes this information and sends it to the cloud server, which then creates a user profile based on the information it receives and stores it in a database.

[0663] 2. Add reading history:

[0664] When a user reads a manga, the information is sent to the cloud server via their smartphone. The server updates the user's reading history and adds the latest reading information to the user's profile.

[0665] 3. Manga Recommendations:

[0666] When a user requests a new manga recommendation, the smartphone device sends the request to a cloud server. The server analyzes the user's profile and reading history, and uses natural language processing and machine learning algorithms to select the most suitable manga. The server then optimizes the recommendation results using a generative AI model and sends the results to the smartphone device for display to the user.

[0667] Specific examples

[0668] For example, a user registers with the ID "user123" and enters "fantasy" as their preferred genre and "exciting" as the atmosphere they want to read. The smartphone organizes this information and sends it to the cloud server. The server creates a user profile based on the received information and saves it in the profile for "user123."

[0669] Next, when the user finishes reading "Manga1," the smartphone sends the information to the cloud server, which adds "Manga1" to the reading history of "user123."

[0670] Later, when the user requests a recommendation for a new manga, the cloud server analyzes the profile and reading history of user “user123” and selects the most suitable manga using natural language processing and machine learning algorithms.

[0671] Example prompts for generative AI models

[0672] Please recommend the best manga based on the following user profile.

[0673] User Profile:

[0674] ID: user123

[0675] Favorite genre: Fantasy

[0676] Reading mood: Exciting

[0677] Reading history: Manga1, Manga2, Manga3

[0678] Output the best manga recommendation results.

[0679] In this way, this system allows users to quickly find the manga that best suits their preferences and the atmosphere they want to read. Furthermore, by utilizing cloud servers and generative AI models, the accuracy and processing speed of recommendation results are improved, greatly improving the user's reading experience.

[0680] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0681] Step 1:

[0682] A user registers and inputs their preferred genre and preferred reading style. The device then organizes the input information and sends it to the cloud server. The input data includes the user ID, preferred genre, and preferred reading style. The cloud server receives this information, generates a user profile, and saves it in the database. As a result, individual user profiles are stored in the database.

[0683] Step 2:

[0684] When a user reads a manga, that information is sent to the cloud server via the device. The input data is the user ID and the title of the manga read. The cloud server receives this and adds the user's reading history to the user profile stored in the database. This updates the latest reading history information.

[0685] Step 3:

[0686] When a user requests a recommendation of a new manga, the device sends the request to the cloud server. The input data is the user ID. The cloud server extracts the user profile and reading history from the database and uses them for analysis. Specifically, it processes the data to recommend the most suitable manga to the user using a generative AI model. Here, natural language processing technology is used to analyze the user's profile information and reading history.

[0687] Step 4:

[0688] The cloud server inputs the prompt sentences into the generative AI model to obtain the optimal recommendation results. The input data is as follows:

[0689] Please recommend the best manga based on the following user profile.

[0690] User Profile:

[0691] ID: user123

[0692] Favorite genre: Fantasy

[0693] Reading mood: Exciting

[0694] Reading history: Manga1, Manga2, Manga3

[0695] Output the best manga recommendation results.

[0696] The generative AI model analyzes this prompt and generates the most suitable manga title. The generated result is a list of the most suitable manga titles.

[0697] Step 5:

[0698] The cloud server sends the generated recommendation results to the device, which receives them and displays them to the user. The output data is a list of recommended manga titles, allowing the user to view the best manga recommendation results based on their preferences.

[0699] Through the above processing steps, the system recommends the most suitable manga based on the user's preferences and reading history, improving the reading experience.

[0700] 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.

[0701] This invention relates to a system that combines a user's preferred genres and desired reading atmosphere with an emotion engine that recognizes the user's emotions. The system generates an individual user profile based on the user's input information and real-time emotion data, and manages their reading history. It also uses natural language processing and machine learning algorithms to recommend the most suitable manga for each user and presents the results to the user.

[0702] System Configuration

[0703] The system consists of the following main components:

[0704] 1. A terminal for receiving input from a user

[0705] 2. A server that processes input information and emotion data and manages user profiles and reading histories

[0706] 3. Emotion engine that recognizes and analyzes user emotion data

[0707] 4. A recommendation method that uses natural language processing and machine learning algorithms to select recommended manga.

[0708] Program processing overview

[0709] 1. User Registration

[0710] Users register and input their preferred genres and preferred reading atmosphere, which creates an individual user profile.

[0711] The terminal receives this input information, as well as the user's facial expression data, voice data, and other emotional data, and transmits them to the server.

[0712] The server generates a user profile based on the received information and emotion data and stores it in a database.

[0713] 2. Emotion Data Analysis

[0714] The emotion engine analyzes the user's emotion data in real time and provides the results to the server.

[0715] The server updates the user profile with the analysis results to reflect the user's psychological tendencies.

[0716] 3. Add reading history

[0717] When a user reads a manga, the information and emotional data are sent to the server via the device.

[0718] The server updates the user's reading history and adds the latest reading information and emotion data to the user profile.

[0719] 4. Manga Recommendations

[0720] When a user requests a recommendation for a new manga, the device sends the request to the server.

[0721] The server analyzes user profiles, emotional data, and reading history, and uses natural language processing and machine learning algorithms to select recommended manga.

[0722] The recommendation results are sent from the server to the terminal, which then displays them to the user.

[0723] Specific examples

[0724] For example, a user registers with the ID "user123" and enters "fantasy" as their preferred genre and "exciting" as the atmosphere they want to read. The device organizes this information along with the user's facial expression and voice data, and sends it to the server. The server generates a user profile based on the received information and emotional data, and saves it in the profile for "user123."

[0725] The emotion engine then analyzes the facial expression and voice data of user "user123" in real time and provides the analysis results to the server, which then updates the profile based on this data to reflect the user's psychological tendencies.

[0726] After that, when the user finishes reading "Manga1," the information and emotional data from the reading session are sent from the device to the server. The server updates the reading history and emotional data of "user123."

[0727] When a user requests a recommendation for a new manga, the server analyzes the profile, emotional data, and reading history of user "user123," and uses natural language processing and machine learning algorithms to recommend "Manga2," "Manga3," and "Manga4." The recommendation results are sent to the device, which then displays them to the user.

[0728] ---

[0729] The above is an embodiment of the present invention. This system allows users to quickly find the manga that best suits their tastes and desired reading atmosphere, as well as real-time emotional data, providing a highly satisfying reading experience. It also allows publishers to accurately grasp readers' interests and emotions and effectively promote their works.

[0730] The processing flow will be explained below.

[0731] Step 1:

[0732] The user registers by entering their ID, preferred genre, and desired reading atmosphere.

[0733] Step 2:

[0734] The device receives the input information and organizes it according to a format, specifically creating a data packet containing the user's ID, preferred genre, and desired reading atmosphere.

[0735] Step 3:

[0736] The terminal transmits the organized data packets to the server.

[0737] Step 4:

[0738] The server analyzes the received data and generates a user profile, specifically storing the user ID, preferred genre, and preferred reading atmosphere in a database.

[0739] Step 5:

[0740] The device collects emotional data such as facial expressions and voice data from the user in real time and transmits it to the server.

[0741] Step 6:

[0742] The emotion engine analyzes the received emotion data and provides the results to the server. Specifically, it recognizes emotions from the user's facial expressions and voice and generates analysis results.

[0743] Step 7:

[0744] The server updates the user profile based on the analysis of the emotional data, specifically adding the emotional data to the profile to reflect the user's psychological tendencies.

[0745] Step 8:

[0746] The user selects a manga and reads it. Emotional data is collected while the user is reading.

[0747] Step 9:

[0748] The terminal transmits the user's reading history information and emotional data during reading to the server.

[0749] Step 10:

[0750] The server updates the user profile based on the reading history and emotion data. Specifically, it adds the ID and emotion data of the new manga to the user profile.

[0751] Step 11:

[0752] A user requests a recommendation for a new manga. The user sends a recommendation request through the terminal.

[0753] Step 12:

[0754] The device receives the recommendation request and sends it to the server. Specifically, it generates a recommendation request data packet including the user ID.

[0755] Step 13:

[0756] The server receives recommendation requests and analyzes user profiles, emotional data, and reading history, using natural language processing and machine learning algorithms to generate a list of recommendations based on the user's preferences.

[0757] Step 14:

[0758] The server sends the generated recommendation list to the device. Specifically, it generates a data packet containing the titles and IDs of the recommended manga.

[0759] Step 15:

[0760] The terminal receives the recommendation list and displays it to the user through a graphical user interface.

[0761] Step 16:

[0762] The user reviews the list of recommended manga and selects the manga they want to read next.

[0763] Example 2

[0764] 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."

[0765] Conventional recommendation systems make recommendations based on the user's preferences and desired reading atmosphere, but they do not fully consider the user's emotions or psychological tendencies, making it difficult to increase user satisfaction. In addition, there is a need for more accurate recommendations by utilizing real-time emotional data.

[0766] 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.

[0767] In this invention, the server includes: means for generating user information based on the user's preferred types and desired reading atmospheres received from the user; means for managing a reading history using the user information and emotion data; recommendation means including natural language processing and machine learning algorithms for selecting optimal recommended materials based on the user information and reading history; means for presenting the recommended materials selected by the recommendation means to the user; emotion analysis means for analyzing the user's current emotion data in real time; and update means for reflecting the analysis results of the emotion analysis means in the user information. This enables recommendations that take the user's emotions and psychological tendencies into consideration, providing a highly satisfying reading experience.

[0768] "User" refers to an individual who uses this system to receive manga recommendations.

[0769] "Favorite types" refers to the genres and categories of manga that users want to read, which they enter when registering.

[0770] "Desired reading atmosphere" refers to a specific emotion or tone of the manga that a user wants to read (e.g., exciting, relaxing).

[0771] "User information" refers to a profile generated based on the user's input preferences, desired reading atmosphere, and emotional data.

[0772] "Emotion data" refers to data that quantifies emotions derived from the user's facial expressions and voice.

[0773] "Reading history" refers to information including a record of the manga that the user has read in the past and emotional data at the time.

[0774] "Server" refers to the computer system that processes data and executes the recommendation algorithms of the System.

[0775] "Natural language processing" refers to algorithms and techniques for analyzing text information and understanding its meaning.

[0776] A "machine learning algorithm" refers to a computational method for automatically learning from data and finding patterns.

[0777] "Recommendation means" refers to the part of the system that uses user information, reading history, natural language processing, and machine learning algorithms to recommend the most suitable manga to users.

[0778] "Emotion analysis means" refers to the part of the system that analyzes the user's emotion data in real time and generates the results.

[0779] The "update means" refers to the part of the system that reflects the results of the emotion analysis means in the user information and keeps that information up to date.

[0780] "Recommended Materials" refers to manga recommended based on a user's profile and emotional data.

[0781] The present invention is a system that analyzes real-time emotional data in addition to the user's preferred types and desired reading atmosphere to recommend the most suitable manga to the user. The following describes the detailed procedure for specifically implementing the present invention.

[0782] System Configuration

[0783] The system consists of the following main components:

[0784] 1. A terminal for receiving input from a user

[0785] 2. A server that processes input information and emotion data and manages user profiles and reading histories

[0786] 3. Emotion analysis method for recognizing and analyzing user emotion data

[0787] 4. A recommendation method that uses natural language processing and machine learning algorithms to select recommended manga.

[0788] Specific hardware and software used

[0789] Device:

[0790] Use devices such as smartphones, tablets, and PCs to collect user input and emotional data.

[0791] Emotion analysis means:

[0792] Technologies such as Emotion API, Affectiva, and FaceReader are used to analyze emotional data.

[0793] server:

[0794] Data processing and management uses cloud services such as AWS EC2, Google Cloud, and Microsoft Azure.

[0795] Database:

[0796] Databases such as MySQL and PostgreSQL are used to store user profiles and reading history.

[0797] Natural Language Processing and Machine Learning:

[0798] The recommendation algorithm is implemented using Python libraries (NLTK, Scikit-learn, TensorFlow, PyTorch).

[0799] System Operation Overview

[0800] User Registration

[0801] The user uses a terminal to access a new registration form and inputs their preferred genre (e.g., "fantasy") and the atmosphere they want to read (e.g., "exciting"). The terminal collects this input information and sends it to the server along with the user's facial expression and voice data. The server generates user information based on the received data and stores it in a database.

[0802] Emotional Data Analysis

[0803] While a user is logged in to their device, real-time emotional data is collected via the camera and microphone. The device sends this data to a server, which then analyzes the received data using emotion analysis tools. The analysis results are reflected in the user information, and the user profile is updated to the latest version.

[0804] Add reading history

[0805] When a user finishes reading a manga, the terminal sends the information along with the emotional data from the reading session to the server. The server receives this data and updates the user's reading history and emotional data.

[0806] Manga Recommendations

[0807] When a user requests a new manga recommendation, the request is sent from the device to the server. The server analyzes the user's information, reading history, and emotional data, and uses natural language processing and machine learning algorithms to select the most suitable manga. The recommendation results are sent from the server to the device, which then displays them to the user.

[0808] Specific examples

[0809] For example, a user registers with the ID "user123" and enters "fantasy" as their preferred type of book and "exciting" as the desired reading atmosphere. The device organizes this information, along with facial expression and voice data, and sends it to the server. The server generates a user profile based on the received information and saves it in the profile for "user123."

[0810] The emotion analysis means analyzes the facial expression and voice data of user "user123" in real time and provides the analysis results to the server, which then updates the profile based on this data to reflect the user's psychological tendencies.

[0811] Next, when the user finishes reading "Manga1," that information and the emotional data during reading are sent from the terminal to the server, and the server updates the reading history and emotional data of "user123."

[0812] When a user requests a recommendation for a new manga, the server analyzes the profile, emotional data, and reading history of user "user123," and uses natural language processing and machine learning algorithms to recommend "Manga2," "Manga3," and "Manga4." The recommendation results are sent to the device, which then displays them to the user.

[0813] Prompt Sentence Examples

[0814] Example prompt 1:

[0815] "User123 is looking for manga in the fantasy genre with an exciting atmosphere. Please recommend three manga that fit his needs, taking into account his latest emotional data and reading history."

[0816] Example prompt 2:

[0817] "User ID: user321, Favorite genre: Horror, Recent emotional data: Calm. Based on this information, please recommend two manga."

[0818] The above is a detailed embodiment of the present invention. This system allows users to effectively find the most suitable manga based on their own feelings and preferences, providing a highly satisfying reading experience.

[0819] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0820] Step 1:

[0821] Entering user information and registering

[0822] Users use their device to access a new registration form and enter their preferred genre (e.g., "fantasy") and the atmosphere they want to read (e.g., "exciting").

[0823] Input: User's preferred type, desired reading atmosphere, facial expression data, voice data

[0824] Output: User information sent to the server

[0825] Specific operation: When a user clicks the "Register" button, the device collects form data using JavaScript, captures facial expressions with the camera, and records audio data with the microphone. The device converts the collected data into JSON format and sends it to the server using an HTTP POST request.

[0826] Step 2:

[0827] Saving user information

[0828] The server generates a user profile based on the received information and stores it in a database.

[0829] Input: JSON format user information sent from the terminal

[0830] Output: User profile stored in the database

[0831] What happens: The server receives the request using Python's Flask, parses the data, creates a profile for the user, and saves it in a MySQL database by executing an INSERT query.

[0832] Step 3:

[0833] Collecting Emotional Data

[0834] While the user is logged in to the device, real-time emotional data is collected via the camera and microphone.

[0835] Input: User's facial expression data, voice data

[0836] Output: Emotion data sent from the device to the server

[0837] How it works: When a user logs in to the system and loads a page, the device uses JavaScript to trigger the camera and microphone. Facial expression data and voice data are collected in real time using WebRTC. The device then sends this real-time data to the server using Python's Socket.IO.

[0838] Step 4:

[0839] Emotional Data Analysis

[0840] The server uses an emotion engine to analyze the received data.

[0841] Input: Real-time emotion data sent from the device

[0842] Output: Parsed emotion data, updated user profile

[0843] Specific operation: The server analyzes the received data using Emotion API (or Affectiva, FaceReader) and obtains the results. The server reflects the analysis results in the user profile and updates the database.

[0844] Step 5:

[0845] Add reading history

[0846] When the user finishes reading the manga, the information about the manga is sent from the terminal to the server along with the emotional data recorded during the reading.

[0847] Input: Information about the manga the user has read, emotional data while reading

[0848] Output: Updated reading history, sentiment data

[0849] Specific operation: When the user clicks the "Finished reading" button, the device collects information about the comic (title, ID, etc.). The device then sends the emotion data captured while reading to the server. The server adds the entry to the database and stores the emotion data.

[0850] Step 6:

[0851] Manga Recommendations

[0852] When a user requests a recommendation of a new manga, the request is sent from the terminal to the server.

[0853] Input: User request, user information, reading history, emotional data

[0854] Output: Recommended manga list

[0855] How it works: When a user clicks the "Recommend a new manga" button, the device generates a request in JSON format. The device then sends it to the server using an HTTP POST request. The server receives the request and analyzes it based on the user's profile, reading history, and sentiment data. It then runs natural language processing and machine learning algorithms using Python libraries (such as NLTK, Scikit-learn, and TensorFlow) to generate an optimal list of manga recommendations. The server then returns the recommendation results in JSON format to the device, which then displays them to the user as a web page.

[0856] (Application example 2)

[0857] 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."

[0858] In today's world, it is extremely difficult for users to select content that matches their preferences and current emotions from the vast amount of content available. Furthermore, conventional content recommendation systems are primarily based on a user's past behavioral history and preferences, making it difficult to provide recommendations that reflect real-time emotions and psychological states. This can prevent users from appropriately selecting content that matches their momentary emotions, potentially resulting in a decrease in user satisfaction. To address this issue, a content recommendation system that reflects a user's preferences and emotions in real time is needed.

[0859] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0860] In this invention, the server includes: means for generating a user profile based on the user's preferred genres and desired reading atmosphere received from the user; means including an emotion engine for analyzing emotion data collected via the terminal and reflecting the data in the user profile; means for managing a reading history using the user profile and emotion data; recommendation means including natural language processing and machine learning algorithms for selecting optimal recommended content based on the user profile and reading history; and means for presenting the recommended content selected by the recommendation means to the user. This allows the user to quickly find optimal content based on their preferences and real-time emotions, resulting in a highly satisfying experience.

[0861] A "user profile" refers to data containing individual user information that is generated by integrating information such as the user's preferred genres, the mood they want to read, and real-time emotional data.

[0862] "Emotion data" refers to data related to emotions acquired in real time, such as facial expression data and voice data of a user collected via a terminal.

[0863] An "emotion engine" refers to software or hardware that analyzes collected emotion data and reflects the results in a user profile.

[0864] "Reading history" refers to data that records and manages content that a user has read in the past and emotional data at the time.

[0865] "Natural language processing" refers to the technology that enables computers to understand, generate, and analyze human language.

[0866] "Machine learning algorithms" are algorithms that allow computers to learn from data, find patterns, and make predictions and decisions.

[0867] "Recommendation tool" refers to a system component that uses natural language processing and machine learning algorithms to select the most appropriate content based on user profile, emotional data, and reading history.

[0868] "Content" refers to the general term for information and entertainment consumed by users, such as manga, videos, and music.

[0869] "Terminal" refers to a device that collects emotional data and connects the user to the system.

[0870] A "server" refers to a computer system that performs a series of processes such as managing user profiles and reading history, analyzing emotional data, and recommending content.

[0871] The system embodying this invention creates an individual user profile based on the user's preferred genres and desired reading atmosphere, and recommends optimal content while reflecting the user's real-time psychological state through emotional data.

[0872] System Configuration

[0873] The system includes the following main components:

[0874] 1. Terminal

[0875] A device that receives input from users and collects emotional data. Examples include smartphones and tablets. The device uses a camera and microphone to capture the user's facial expression and voice data, and sends it to a server.

[0876] 2. Server

[0877] It processes input information and emotion data, and manages user profiles and reading histories. Its role is to generate user profiles, manage reading histories, and provide content selected by recommendation means to the device.

[0878] 3. Emotion Engine

[0879] The emotion engine analyzes the user's emotion data in real time and updates the user profile by providing the results to the server. The emotion engine consists of software and hardware that analyzes the user's facial expressions and voice data.

[0880] 4. Recommendation method

[0881] It uses natural language processing (NLP) and machine learning algorithms to select the most suitable content based on the user's profile and reading history. It runs on the server and sends the selected content to the device.

[0882] Program processing

[0883] 1. User Registration

[0884] Users register and input their preferred genres and preferred reading atmospheres. This creates an individual user profile. The device then sends this input information, along with the user's facial expression and voice data, to the server.

[0885] 2. Data analysis and profile generation

[0886] The server generates a user profile based on the received information and emotion data and stores it in a database. The emotion engine analyzes the emotion data in real time and provides the analysis results to the server.

[0887] 3. Reflecting Emotional Data

[0888] Based on the analysis results of the emotion engine, the server updates the user profile to reflect psychological trends. Specifically, it analyzes information obtained from facial expressions and voice to detect and record the user's current emotions.

[0889] 4. Add reading history

[0890] Each time a user consumes content, the device sends the content along with emotional data to the server, which then updates the user's reading history and adds the latest reading information and emotional data to the user profile.

[0891] 5. Content Recommendations

[0892] When a user requests new content recommendations, the server analyzes the user's profile, emotional data, and reading history, and uses natural language processing (NLP) and machine learning algorithms to select the most suitable content. The selected recommendations are then sent to the device, which then displays them to the user.

[0893] Specific examples

[0894] For example, suppose a user registers with the ID "user456" and selects "SF" as their preferred genre and "relaxing" as their preferred reading atmosphere. The device collects this information along with the user's facial expression and voice data and sends it to the server. The server creates a profile for "user456" based on the received information and emotional data.

[0895] The emotion engine then analyzes the facial and voice data of "user456" in real time and provides the results to the server, which then updates the profile based on this data to reflect the user's psychological tendencies.

[0896] After that, when the user finishes reading "MangaX," the device sends the information along with the emotional data from the reading session to the server. The server then updates the reading history and emotional data of "user456."

[0897] Finally, when the user requests a recommendation for a new manga, the server analyzes it and recommends the most suitable "MangaY" and "MangaZ." The recommendation results are sent to the device of "user456," which then displays them to the user.

[0898] Prompt Sentence Examples

[0899] "Recommend MangaY and MangaZ based on the user's preferred genre of SF and the relaxing atmosphere they want to experience while reading."

[0900] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0901] Step 1:

[0902] User Registration

[0903] The user registers and inputs their preferred genre and desired reading atmosphere, which creates an initial profile for the user. The device collects this input information along with the user's facial expression and voice data, and sends it to the server.

[0904] Input: User information (preferred genre, desired reading atmosphere), facial expression data, voice data

[0905] Data processing: An initial user profile is generated based on the input information. Facial expression data and voice data are analyzed by the emotion engine and registered as initial emotion data.

[0906] Output: Generated initial user profile

[0907] Step 2:

[0908] Data analysis and profile generation

[0909] The server generates an initial user profile based on the received information and emotion data and stores it in a database. At this time, the emotion engine analyzes the emotion data in real time and provides the results to the server.

[0910] Input: Initial user profile, emotion data

[0911] Data processing: Data is analyzed using the emotion engine to evaluate the user's emotional state and update the user profile accordingly.

[0912] Output: Updated user profile

[0913] Step 3:

[0914] Emotion data reflection

[0915] The emotion engine analyzes the emotion data acquired in real time, and the server updates the user profile based on the results. The user's current emotional state is reflected in the profile.

[0916] Input: Real-time emotion data

[0917] Data processing: The emotion engine analyzes facial expression and voice data, converts the user's emotions into numerical values, and evaluates them. The evaluation results are sent to the server and reflected in the user profile.

[0918] Output: User profile reflecting emotional data

[0919] Step 4:

[0920] Add reading history

[0921] Every time a user consumes content, that information and emotional data is sent from the device to the server, which then uses this information to update the user's reading history and reflect it in their profile.

[0922] Input: Reading information, emotional data during consumption

[0923] Data processing: Reading information and emotion data are combined and added to the database as a series of historical data. User profiles are updated based on reading history.

[0924] Output: Updated reading history, user profile

[0925] Step 5:

[0926] Content Recommendations

[0927] When a user requests new content recommendations, the server analyzes the user's profile, emotional data, and reading history to recommend the most appropriate content. This is done using natural language processing and machine learning algorithms. The recommended content is then sent to the device and displayed to the user.

[0928] Input: User profile, reading history, real-time emotional data

[0929] Data processing: Analyze data using natural language processing and machine learning algorithms to select the most suitable content. The results are then verified using a generative AI model.

[0930] Output: Recommended content

[0931] Specific prompt examples:

[0932] "Recommend MangaY and MangaZ based on the user's preferred genre of SF and the relaxing atmosphere they want to experience while reading."

[0933] 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.

[0934] 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.

[0935] 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.

[0936] [Third embodiment]

[0937] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0938] 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.

[0939] 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).

[0940] 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.

[0941] 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.

[0942] 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).

[0943] 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.

[0944] 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.

[0945] 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.

[0946] 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.

[0947] 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.

[0948] 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."

[0949] This invention relates to a system that recommends the most suitable manga based on a user's preferred genre and desired reading atmosphere. The system generates an individual user profile based on information input by the user and manages their reading history. It also uses natural language processing and machine learning algorithms to recommend the most suitable manga for each user and presents the results to the user.

[0950] System Configuration

[0951] The system consists of the following main components:

[0952] 1. A terminal for receiving input from a user

[0953] 2. A server that processes input information and manages user profiles and reading histories

[0954] 3. A recommendation method that uses natural language processing and machine learning algorithms to select recommended manga.

[0955] Program processing overview

[0956] 1. User Registration

[0957] Users register and input their preferred genres and preferred reading atmosphere, which creates a personalized profile for the user.

[0958] The terminal organizes this input information and sends it to the server.

[0959] The server generates a user profile based on the received information and stores it in a database.

[0960] 2. Add reading history

[0961] When a user reads a manga, the information is sent to the server via the terminal.

[0962] The server updates the user's reading history and adds the latest reading information to the user's profile.

[0963] 3. Manga Recommendations

[0964] When a user requests a recommendation for a new manga, the device sends the request to the server.

[0965] The server analyzes user profiles and reading histories and uses natural language processing and machine learning algorithms to select recommended manga.

[0966] The recommendation results are sent from the server to the terminal, which then displays them to the user.

[0967] Specific examples

[0968] For example, a user registers with the ID "user123" and enters "fantasy" as their preferred genre and "exciting" as the desired reading atmosphere. The device organizes this information and sends it to the server. The server creates a user profile based on the received information and saves it in the profile of "user123."

[0969] Next, when the user finishes reading "Manga1," the information is sent from the terminal to the server, which adds "Manga1" to the reading history of "user123."

[0970] When the user subsequently requests a recommendation for a new manga, the server analyzes the profile and reading history of user "user123" and uses natural language processing and machine learning algorithms to recommend "Manga2," "Manga3," and "Manga4." The recommendation results are then sent to the device, which displays them to the user.

[0971] ---

[0972] The above is an embodiment of the present invention. This system allows users to quickly find manga that best suits their preferences and the atmosphere they want to read, improving their reading experience. It also allows publishers to accurately grasp readers' interests and promote their works more effectively.

[0973] The processing flow will be explained below.

[0974] Step 1:

[0975] The user registers by entering their ID, preferred genre, and desired reading atmosphere.

[0976] Step 2:

[0977] The device receives the input information and sends it to the server in a format that creates a data packet containing the user's ID, preferred genre, and desired reading atmosphere.

[0978] Step 3:

[0979] The server analyzes the received data and generates a user profile, including the user ID, preferred genre, and preferred reading atmosphere, which is then stored in a database.

[0980] Step 4:

[0981] The user selects a manga and begins reading.

[0982] Step 5:

[0983] When a user finishes reading a manga, the device acquires that information. Specifically, it records the title and ID of the manga that the user has finished reading.

[0984] Step 6:

[0985] The device sends the reading history information to the server, generating a data packet containing the user ID and the ID of the manga that has been read.

[0986] Step 7:

[0987] The server analyzes the received reading history data and updates the user profile. Specifically, it adds the new manga ID to the user's reading history list.

[0988] Step 8:

[0989] A user requests a recommendation for a new manga. The user sends a recommendation request through the terminal.

[0990] Step 9:

[0991] The device receives the recommendation request and sends it to the server. Specifically, it generates a recommendation request data packet including the user ID.

[0992] Step 10:

[0993] The server receives recommendation requests, analyzes the user's profile and reading history, and generates a list of recommendations based on the user's preferences using natural language processing and machine learning algorithms.

[0994] Step 11:

[0995] The server sends the generated recommendation list to the device. Specifically, it generates a data packet containing the titles and IDs of the recommended manga.

[0996] Step 12:

[0997] The terminal receives the recommendation list and displays it to the user through a graphical user interface.

[0998] Step 13:

[0999] The user reviews the list of recommended manga and selects the manga they want to read next.

[1000] Example 1

[1001] 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."

[1002] Currently, users face challenges in quickly finding the most appropriate information based on their preferences and desired reading atmosphere. Furthermore, it is difficult to generate and manage profiles that accurately reflect users' interests and psychological tendencies, which reduces the accuracy of recommendations. Furthermore, there is a need for an efficient recommendation method to promote the discovery of new information.

[1003] 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.

[1004] In this invention, the server includes: means for generating a user profile based on the user's preferred genres and desired reading style received from the user; means for managing a reading history using the user profile; means for managing reading start information and reading completion information based on the reading history information; recommendation means including natural language processing and machine learning algorithms for selecting optimal recommended information based on the user profile and reading history; means for presenting the recommended information selected by the recommendation means to the user; and means for analyzing prompt sentences that receive recommendation requests from the user. This allows users to quickly find information that best suits their preferences and desired reading style, improving the user experience. It also enables the generation and management of highly accurate profiles that reflect the user's interests and psychological tendencies, and promotes the discovery of new information.

[1005] A "user profile" is data that compiles individual information including a user's preferred genres, preferred reading style, reading history, and so on.

[1006] "Reading history" is a record of the comics and books that a user has read, and is data that includes information on when the user started reading and when the user finished reading.

[1007] "Natural language processing" is a technology for analyzing text data entered by a user and understanding its meaning and intent.

[1008] A "machine learning algorithm" is an algorithm that learns patterns and relationships from large amounts of data and makes predictions and recommendations.

[1009] "Recommendation means" refers to methods and technologies for selecting and presenting optimal information to a user based on the user's profile and reading history.

[1010] A "prompt sentence" is a text sentence that describes a question or request that a user makes to the system.

[1011] A "parsing means" is a technique or method for parsing a prompt or other input data and understanding its meaning.

[1012] "Information" refers to data such as recommended manga and books provided to users.

[1013] This invention relates to a system that recommends the most suitable manga based on a user's preferred genre and desired reading atmosphere. This system generates an individual user profile based on information input by the user and manages their reading history. It also uses natural language processing and machine learning algorithms to recommend the most suitable manga for each user and presents the results to the user.

[1014] The system consists of the following main components:

[1015] 1. A terminal for receiving input from a user

[1016] 2. A server that processes input information and manages user profiles and reading histories

[1017] 3. A recommendation method that uses natural language processing and machine learning algorithms to select recommended manga.

[1018] Hardware and Software Environment

[1019] 1. Terminal - A device that receives user input, such as a smartphone or PC.

[1020] 2. Server - The server that processes and stores the data. Specifically, we use cloud-based servers (e.g., Amazon Web Services (AWS)).

[1021] 3. Natural language processing models - for example, BERT or GPT-3 - are used to analyze user input.

[1022] 4. Machine learning algorithms - for example, using Collaborative Filtering and Content-Based Filtering to recommend manga.

[1023] System Operation

[1024] User Registration

[1025] A user registers using a terminal and inputs their preferred genre and preferred reading atmosphere. This information is sent from the terminal to the server, and the server generates a user profile based on the received information and stores it in a database. For example, if a user likes the "fantasy" genre and prefers an "exciting" atmosphere, a profile can be generated by inputting this information.

[1026] Add reading history

[1027] When a user reads a manga, that information is sent to the server via the terminal. The server records the user's reading history in a database and adds the latest reading information to the user's profile. For example, when a user finishes reading a title called "Manga1," that reading history is sent to the server and added to the user's profile.

[1028] Manga Recommendations

[1029] When a user requests a recommendation for a new manga, the device sends the request to the server. The server analyzes the user's profile and reading history, and recommends the most suitable manga using natural language processing models and machine learning algorithms. The recommendation results are sent from the server to the device and displayed to the user. For example, if a user enters the prompt "I want to read a fantasy and exciting manga," the system will recommend "Manga2," "Manga3," and "Manga4."

[1030] Examples of prompt statements

[1031] When a user inputs a prompt such as "I want to read an exciting fantasy manga. Can you recommend some?", the system analyzes it using a natural language processing model and makes the best recommendations. This allows users to quickly find the manga that best suits their preferences and the atmosphere they want to read.

[1032] In this way, the present invention improves the user experience and provides an environment in which users can efficiently discover manga that suit their tastes.

[1033] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1034] Step 1:

[1035] The user registers using a terminal. The user enters their ID, password, preferred genre (e.g., "fantasy"), and desired reading atmosphere (e.g., "exciting") into the input form on the terminal. This information is registered on the terminal as input data.

[1036] Input: User ID, password, preferred genre, desired reading atmosphere

[1037] Specific operation: Fill in the information in the input form and press the "Register" button to complete the entry.

[1038] Output: The terminal organizes the input information and generates data in JSON format.

[1039] Step 2:

[1040] The device sends the information entered by the user to the server, where it is encrypted and securely transmitted using the HTTPS protocol.

[1041] Input: JSON formatted data entered by the user

[1042] Specific operation: The device formats the JSON data and sends it to the server via an HTTPS request.

[1043] Output: The server receives the JSON data.

[1044] Step 3:

[1045] The server analyzes the received information and generates a user profile, storing the data according to an internal database schema based on the genre and atmosphere information received.

[1046] Input: JSON format data received from the terminal

[1047] Specific operation: The server deserializes the received data, generates a user profile, and saves it in the database.

[1048] Output: The generated user profile is stored in a database.

[1049] Step 4:

[1050] The user starts reading a manga through the device. The user uses the search function in the system to select a manga (e.g., "Manga1") and clicks to read it.

[1051] Input: User's search keyword or manga selection status

[1052] Specific action: The user selects a manga from the search box or list and presses the "Read" button.

[1053] Output: Information about the selected manga will be displayed on the device.

[1054] Step 5:

[1055] The device sends information about the comic the user has started reading to the server, including the comic's ID and the user ID.

[1056] Input: User's selected manga ID and user ID

[1057] Specific operation: The device formats the selection information and sends it to the server via an HTTPS request.

[1058] Output: The server receives the selection information.

[1059] Step 6:

[1060] The server updates the user's reading history based on the received information. The server updates the database to add the new reading history to the user's profile.

[1061] Input: Received manga ID and user ID

[1062] Specific behavior: The server executes a database query to add a new reading history.

[1063] Output: The updated user's reading history is stored in the database.

[1064] Step 7:

[1065] The user requests a recommendation for a new manga. The user issues the request by clicking the "Recommend Manga" button.

[1066] Input: Recommendation request

[1067] What happens: The user presses a button to request a recommendation.

[1068] Output: A recommendation request is sent from the device to the server.

[1069] Step 8:

[1070] The device sends recommendation request information, including the user ID, to the server.

[1071] Input: Recommendation request with user ID

[1072] What it does: It formats the recommendation request and sends it to the server via an HTTPS request.

[1073] Output: The server receives the recommendation request.

[1074] Step 9:

[1075] The server analyzes user profiles and reading histories, uses natural language processing models to extract keywords related to the user's preferences and reading history, and uses machine learning algorithms to select the most suitable manga recommendations.

[1076] Input: User profile and reading history

[1077] How it works: Natural language processing models analyze profile data, and machine learning algorithms select the best recommendations.

[1078] Output: A list of recommended manga is generated.

[1079] Step 10:

[1080] The server transmits the selected recommendation results to the terminal.

[1081] Input: Recommended manga list

[1082] Specific operation: The recommendation list is formatted and sent to the device as an HTTPS response.

[1083] Output: The terminal receives the recommendation results.

[1084] Step 11:

[1085] The device displays the recommendation results to the user, who can then check the recommended manga (e.g., "Manga2," "Manga3," "Manga4").

[1086] Input: Recommended manga list received from the server

[1087] Specific operation: Display the recommendation results on the user interface.

[1088] Output: The recommended manga is displayed to the user.

[1089] (Application example 1)

[1090] 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."

[1091] Conventional manga recommendation systems have difficulty recommending appropriate manga because they do not fully consider users' preferences or reading history. Furthermore, they are insufficient as a means for users to discover new manga, limiting the improvement of the reading experience. Furthermore, due to the lack of use across a variety of devices and the lack of AI technology, optimal recommendations to users are delayed and accuracy is reduced.

[1092] 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.

[1093] In this invention, the server includes: a means for generating a user profile based on the user's preferred genres and desired reading style; a means for managing a reading history using the user profile; a recommendation means including natural language processing and machine learning algorithms for selecting optimal manga recommendations based on the user profile and reading history; a means for presenting the recommended manga selected by the recommendation means to the user; a means including an application to be installed on a smartphone; a means for processing and storing data using a cloud server; and a means for optimizing the recommendation results using a generative AI model. This allows users to quickly find the optimal manga based on their preferences and reading history, improving their reading experience. Furthermore, the use of the cloud server and generative AI model improves the accuracy and processing speed of recommendation results.

[1094] A "user profile" is a collection of information about an individual user that is generated based on the user's preferred genres and preferred reading atmosphere.

[1095] "Reading history" is a record of the manga that a user has read so far, and is data that is managed as part of a user profile.

[1096] The "recommendation method" is a system that uses natural language processing and machine learning algorithms to select the most suitable manga based on the user's profile and reading history, and presents it to the user.

[1097] "Natural language processing" is a technology that allows computers to understand, generate, and manipulate human language, and in this system it is used to analyze the genre and atmosphere of manga.

[1098] A "machine learning algorithm" is a computational method that learns from data, extracts patterns and rules, and makes predictions and classifications for new data.

[1099] The "application installed on a smartphone" is software that allows users to access the system using their smartphone to receive manga recommendations and manage their reading history.

[1100] A "cloud server" is a remote server utilized over the Internet, and is an infrastructure for processing and storing data.

[1101] A "generative AI model" is an artificial intelligence model that has been trained in advance using large amounts of data, and is a technology used to optimize manga recommendation results.

[1102] This invention is a system that recommends the most suitable manga based on the user's preferred genre and desired reading atmosphere.

[1103] System configuration

[1104] The system consists of the following main components:

[1105] 1. A device (smartphone) for receiving input from the user

[1106] 2. A server (cloud server) that processes input information and manages user profiles and reading histories

[1107] 3. A recommendation method (generative AI model) that uses natural language processing and machine learning algorithms to select recommended manga.

[1108] Hardware and Software Configuration

[1109] Hardware:

[1110] Smartphone

[1111] Cloud servers (e.g., Amazon Web Services, Microsoft Azure, Google Cloud Platform)

[1112] software:

[1113] Smartphone app development environment (iOS: Swift, Android: Kotlin)

[1114] Natural language processing libraries (e.g. TensorFlow, spaCy)

[1115] Machine learning algorithms (e.g., scikit-learn, PyTorch)

[1116] Database (e.g. MongoDB, MySQL)

[1117] Program processing overview

[1118] 1. User Registration:

[1119] Users register and input their preferred genres and the atmosphere they want to read. The smartphone organizes this information and sends it to the cloud server, which then creates a user profile based on the information it receives and stores it in a database.

[1120] 2. Add reading history:

[1121] When a user reads a manga, the information is sent to the cloud server via their smartphone. The server updates the user's reading history and adds the latest reading information to the user's profile.

[1122] 3. Manga Recommendations:

[1123] When a user requests a new manga recommendation, the smartphone device sends the request to a cloud server. The server analyzes the user's profile and reading history, and uses natural language processing and machine learning algorithms to select the most suitable manga. The server then optimizes the recommendation results using a generative AI model and sends the results to the smartphone device for display to the user.

[1124] Specific examples

[1125] For example, a user registers with the ID "user123" and enters "fantasy" as their preferred genre and "exciting" as the atmosphere they want to read. The smartphone organizes this information and sends it to the cloud server. The server creates a user profile based on the received information and saves it in the profile for "user123."

[1126] Next, when the user finishes reading "Manga1," the smartphone sends the information to the cloud server, which adds "Manga1" to the reading history of "user123."

[1127] Later, when the user requests a recommendation for a new manga, the cloud server analyzes the profile and reading history of user “user123” and selects the most suitable manga using natural language processing and machine learning algorithms.

[1128] Example prompts for generative AI models

[1129] Please recommend the best manga based on the following user profile.

[1130] User Profile:

[1131] ID: user123

[1132] Favorite genre: Fantasy

[1133] Reading mood: Exciting

[1134] Reading history: Manga1, Manga2, Manga3

[1135] Output the best manga recommendation results.

[1136] In this way, this system allows users to quickly find the manga that best suits their preferences and the atmosphere they want to read. Furthermore, by utilizing cloud servers and generative AI models, the accuracy and processing speed of recommendation results are improved, greatly improving the user's reading experience.

[1137] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1138] Step 1:

[1139] A user registers and inputs their preferred genre and preferred reading style. The device then organizes the input information and sends it to the cloud server. The input data includes the user ID, preferred genre, and preferred reading style. The cloud server receives this information, generates a user profile, and saves it in the database. As a result, individual user profiles are stored in the database.

[1140] Step 2:

[1141] When a user reads a manga, that information is sent to the cloud server via the device. The input data is the user ID and the title of the manga read. The cloud server receives this and adds the user's reading history to the user profile stored in the database. This updates the latest reading history information.

[1142] Step 3:

[1143] When a user requests a recommendation of a new manga, the device sends the request to the cloud server. The input data is the user ID. The cloud server extracts the user profile and reading history from the database and uses them for analysis. Specifically, it processes the data to recommend the most suitable manga to the user using a generative AI model. Here, natural language processing technology is used to analyze the user's profile information and reading history.

[1144] Step 4:

[1145] The cloud server inputs the prompt sentences into the generative AI model to obtain the optimal recommendation results. The input data is as follows:

[1146] Please recommend the best manga based on the following user profile.

[1147] User Profile:

[1148] ID: user123

[1149] Favorite genre: Fantasy

[1150] Reading mood: Exciting

[1151] Reading history: Manga1, Manga2, Manga3

[1152] Output the best manga recommendation results.

[1153] The generative AI model analyzes this prompt and generates the most suitable manga title. The generated result is a list of the most suitable manga titles.

[1154] Step 5:

[1155] The cloud server sends the generated recommendation results to the device, which receives them and displays them to the user. The output data is a list of recommended manga titles, allowing the user to view the best manga recommendation results based on their preferences.

[1156] Through the above processing steps, the system recommends the most suitable manga based on the user's preferences and reading history, improving the reading experience.

[1157] 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.

[1158] This invention relates to a system that combines a user's preferred genres and desired reading atmosphere with an emotion engine that recognizes the user's emotions. The system generates an individual user profile based on the user's input information and real-time emotion data, and manages their reading history. It also uses natural language processing and machine learning algorithms to recommend the most suitable manga for each user and presents the results to the user.

[1159] System Configuration

[1160] The system consists of the following main components:

[1161] 1. A terminal for receiving input from a user

[1162] 2. A server that processes input information and emotion data and manages user profiles and reading histories

[1163] 3. Emotion engine that recognizes and analyzes user emotion data

[1164] 4. A recommendation method that uses natural language processing and machine learning algorithms to select recommended manga.

[1165] Program processing overview

[1166] 1. User Registration

[1167] Users register and input their preferred genres and preferred reading atmosphere, which creates an individual user profile.

[1168] The terminal receives this input information, as well as the user's facial expression data, voice data, and other emotional data, and transmits them to the server.

[1169] The server generates a user profile based on the received information and emotion data and stores it in a database.

[1170] 2. Emotion Data Analysis

[1171] The emotion engine analyzes the user's emotion data in real time and provides the results to the server.

[1172] The server updates the user profile with the analysis results to reflect the user's psychological tendencies.

[1173] 3. Add reading history

[1174] When a user reads a manga, the information and emotional data are sent to the server via the device.

[1175] The server updates the user's reading history and adds the latest reading information and emotion data to the user profile.

[1176] 4. Manga Recommendations

[1177] When a user requests a recommendation for a new manga, the device sends the request to the server.

[1178] The server analyzes user profiles, emotional data, and reading history, and uses natural language processing and machine learning algorithms to select recommended manga.

[1179] The recommendation results are sent from the server to the terminal, which then displays them to the user.

[1180] Specific examples

[1181] For example, a user registers with the ID "user123" and enters "fantasy" as their preferred genre and "exciting" as the atmosphere they want to read. The device organizes this information along with the user's facial expression and voice data, and sends it to the server. The server generates a user profile based on the received information and emotional data, and saves it in the profile for "user123."

[1182] The emotion engine then analyzes the facial expression and voice data of user "user123" in real time and provides the analysis results to the server, which then updates the profile based on this data to reflect the user's psychological tendencies.

[1183] After that, when the user finishes reading "Manga1," the information and emotional data from the reading session are sent from the device to the server. The server updates the reading history and emotional data of "user123."

[1184] When a user requests a recommendation for a new manga, the server analyzes the profile, emotional data, and reading history of user "user123," and uses natural language processing and machine learning algorithms to recommend "Manga2," "Manga3," and "Manga4." The recommendation results are sent to the device, which then displays them to the user.

[1185] ---

[1186] The above is an embodiment of the present invention. This system allows users to quickly find the manga that best suits their tastes and desired reading atmosphere, as well as real-time emotional data, providing a highly satisfying reading experience. It also allows publishers to accurately grasp readers' interests and emotions and effectively promote their works.

[1187] The processing flow will be explained below.

[1188] Step 1:

[1189] The user registers by entering their ID, preferred genre, and desired reading atmosphere.

[1190] Step 2:

[1191] The device receives the input information and organizes it according to a format, specifically creating a data packet containing the user's ID, preferred genre, and desired reading atmosphere.

[1192] Step 3:

[1193] The terminal transmits the organized data packets to the server.

[1194] Step 4:

[1195] The server analyzes the received data and generates a user profile, specifically storing the user ID, preferred genre, and preferred reading atmosphere in a database.

[1196] Step 5:

[1197] The device collects emotional data such as facial expressions and voice data from the user in real time and transmits it to the server.

[1198] Step 6:

[1199] The emotion engine analyzes the received emotion data and provides the results to the server. Specifically, it recognizes emotions from the user's facial expressions and voice and generates analysis results.

[1200] Step 7:

[1201] The server updates the user profile based on the analysis of the emotional data, specifically adding the emotional data to the profile to reflect the user's psychological tendencies.

[1202] Step 8:

[1203] The user selects a manga and reads it. Emotional data is collected while the user is reading.

[1204] Step 9:

[1205] The terminal transmits the user's reading history information and emotional data during reading to the server.

[1206] Step 10:

[1207] The server updates the user profile based on the reading history and emotion data. Specifically, it adds the ID and emotion data of the new manga to the user profile.

[1208] Step 11:

[1209] A user requests a recommendation for a new manga. The user sends a recommendation request through the terminal.

[1210] Step 12:

[1211] The device receives the recommendation request and sends it to the server. Specifically, it generates a recommendation request data packet including the user ID.

[1212] Step 13:

[1213] The server receives recommendation requests and analyzes user profiles, emotional data, and reading history, using natural language processing and machine learning algorithms to generate a list of recommendations based on the user's preferences.

[1214] Step 14:

[1215] The server sends the generated recommendation list to the device. Specifically, it generates a data packet containing the titles and IDs of the recommended manga.

[1216] Step 15:

[1217] The terminal receives the recommendation list and displays it to the user through a graphical user interface.

[1218] Step 16:

[1219] The user reviews the list of recommended manga and selects the manga they want to read next.

[1220] Example 2

[1221] 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."

[1222] Conventional recommendation systems make recommendations based on the user's preferences and desired reading atmosphere, but they do not fully consider the user's emotions or psychological tendencies, making it difficult to increase user satisfaction. In addition, there is a need for more accurate recommendations by utilizing real-time emotional data.

[1223] 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.

[1224] In this invention, the server includes: means for generating user information based on the user's preferred types and desired reading atmospheres received from the user; means for managing a reading history using the user information and emotion data; recommendation means including natural language processing and machine learning algorithms for selecting optimal recommended materials based on the user information and reading history; means for presenting the recommended materials selected by the recommendation means to the user; emotion analysis means for analyzing the user's current emotion data in real time; and update means for reflecting the analysis results of the emotion analysis means in the user information. This enables recommendations that take the user's emotions and psychological tendencies into consideration, providing a highly satisfying reading experience.

[1225] "User" refers to an individual who uses this system to receive manga recommendations.

[1226] "Favorite types" refers to the genres and categories of manga that users want to read, which they enter when registering.

[1227] "Desired reading atmosphere" refers to a specific emotion or tone of the manga that a user wants to read (e.g., exciting, relaxing).

[1228] "User information" refers to a profile generated based on the user's input preferences, desired reading atmosphere, and emotional data.

[1229] "Emotion data" refers to data that quantifies emotions derived from the user's facial expressions and voice.

[1230] "Reading history" refers to information including a record of the manga that the user has read in the past and emotional data at the time.

[1231] "Server" refers to the computer system that processes data and executes the recommendation algorithms of the System.

[1232] "Natural language processing" refers to algorithms and techniques for analyzing text information and understanding its meaning.

[1233] A "machine learning algorithm" refers to a computational method for automatically learning from data and finding patterns.

[1234] "Recommendation means" refers to the part of the system that uses user information, reading history, natural language processing, and machine learning algorithms to recommend the most suitable manga to users.

[1235] "Emotion analysis means" refers to the part of the system that analyzes the user's emotion data in real time and generates the results.

[1236] The "update means" refers to the part of the system that reflects the results of the emotion analysis means in the user information and keeps that information up to date.

[1237] "Recommended Materials" refers to manga recommended based on a user's profile and emotional data.

[1238] The present invention is a system that analyzes real-time emotional data in addition to the user's preferred types and desired reading atmosphere to recommend the most suitable manga to the user. The following describes the detailed procedure for specifically implementing the present invention.

[1239] System Configuration

[1240] The system consists of the following main components:

[1241] 1. A terminal for receiving input from a user

[1242] 2. A server that processes input information and emotion data and manages user profiles and reading histories

[1243] 3. Emotion analysis method for recognizing and analyzing user emotion data

[1244] 4. A recommendation method that uses natural language processing and machine learning algorithms to select recommended manga.

[1245] Specific hardware and software used

[1246] Device:

[1247] Use devices such as smartphones, tablets, and PCs to collect user input and emotional data.

[1248] Emotion analysis means:

[1249] Technologies such as Emotion API, Affectiva, and FaceReader are used to analyze emotional data.

[1250] server:

[1251] Data processing and management uses cloud services such as AWS EC2, Google Cloud, and Microsoft Azure.

[1252] Database:

[1253] Databases such as MySQL and PostgreSQL are used to store user profiles and reading history.

[1254] Natural Language Processing and Machine Learning:

[1255] The recommendation algorithm is implemented using Python libraries (NLTK, Scikit-learn, TensorFlow, PyTorch).

[1256] System Operation Overview

[1257] User Registration

[1258] The user uses a terminal to access a new registration form and inputs their preferred genre (e.g., "fantasy") and the atmosphere they want to read (e.g., "exciting"). The terminal collects this input information and sends it to the server along with the user's facial expression and voice data. The server generates user information based on the received data and stores it in a database.

[1259] Emotional Data Analysis

[1260] While a user is logged in to their device, real-time emotional data is collected via the camera and microphone. The device sends this data to a server, which then analyzes the received data using emotion analysis tools. The analysis results are reflected in the user information, and the user profile is updated to the latest version.

[1261] Add reading history

[1262] When a user finishes reading a manga, the terminal sends the information along with the emotional data from the reading session to the server. The server receives this data and updates the user's reading history and emotional data.

[1263] Manga Recommendations

[1264] When a user requests a new manga recommendation, the request is sent from the device to the server. The server analyzes the user's information, reading history, and emotional data, and uses natural language processing and machine learning algorithms to select the most suitable manga. The recommendation results are sent from the server to the device, which then displays them to the user.

[1265] Specific examples

[1266] For example, a user registers with the ID "user123" and enters "fantasy" as their preferred type of book and "exciting" as the desired reading atmosphere. The device organizes this information, along with facial expression and voice data, and sends it to the server. The server generates a user profile based on the received information and saves it in the profile for "user123."

[1267] The emotion analysis means analyzes the facial expression and voice data of user "user123" in real time and provides the analysis results to the server, which then updates the profile based on this data to reflect the user's psychological tendencies.

[1268] Next, when the user finishes reading "Manga1," that information and the emotional data during reading are sent from the terminal to the server, and the server updates the reading history and emotional data of "user123."

[1269] When a user requests a recommendation for a new manga, the server analyzes the profile, emotional data, and reading history of user "user123," and uses natural language processing and machine learning algorithms to recommend "Manga2," "Manga3," and "Manga4." The recommendation results are sent to the device, which then displays them to the user.

[1270] Prompt Sentence Examples

[1271] Example prompt 1:

[1272] "User123 is looking for manga in the fantasy genre with an exciting atmosphere. Please recommend three manga that fit his needs, taking into account his latest emotional data and reading history."

[1273] Example prompt 2:

[1274] "User ID: user321, Favorite genre: Horror, Recent emotional data: Calm. Based on this information, please recommend two manga."

[1275] The above is a detailed embodiment of the present invention. This system allows users to effectively find the most suitable manga based on their own feelings and preferences, providing a highly satisfying reading experience.

[1276] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1277] Step 1:

[1278] Entering user information and registering

[1279] Users use their device to access a new registration form and enter their preferred genre (e.g., "fantasy") and the atmosphere they want to read (e.g., "exciting").

[1280] Input: User's preferred type, desired reading atmosphere, facial expression data, voice data

[1281] Output: User information sent to the server

[1282] Specific operation: When a user clicks the "Register" button, the device collects form data using JavaScript, captures facial expressions with the camera, and records audio data with the microphone. The device converts the collected data into JSON format and sends it to the server using an HTTP POST request.

[1283] Step 2:

[1284] Saving user information

[1285] The server generates a user profile based on the received information and stores it in a database.

[1286] Input: JSON format user information sent from the terminal

[1287] Output: User profile stored in the database

[1288] What happens: The server receives the request using Python's Flask, parses the data, creates a profile for the user, and saves it in a MySQL database by executing an INSERT query.

[1289] Step 3:

[1290] Collecting Emotional Data

[1291] While the user is logged in to the device, real-time emotional data is collected via the camera and microphone.

[1292] Input: User's facial expression data, voice data

[1293] Output: Emotion data sent from the device to the server

[1294] How it works: When a user logs in to the system and loads a page, the device uses JavaScript to trigger the camera and microphone. Facial expression data and voice data are collected in real time using WebRTC. The device then sends this real-time data to the server using Python's Socket.IO.

[1295] Step 4:

[1296] Emotional Data Analysis

[1297] The server uses an emotion engine to analyze the received data.

[1298] Input: Real-time emotion data sent from the device

[1299] Output: Parsed emotion data, updated user profile

[1300] Specific operation: The server analyzes the received data using Emotion API (or Affectiva, FaceReader) and obtains the results. The server reflects the analysis results in the user profile and updates the database.

[1301] Step 5:

[1302] Add reading history

[1303] When the user finishes reading the manga, the information about the manga is sent from the terminal to the server along with the emotional data recorded during the reading.

[1304] Input: Information about the manga the user has read, emotional data while reading

[1305] Output: Updated reading history, sentiment data

[1306] Specific operation: When the user clicks the "Finished reading" button, the device collects information about the comic (title, ID, etc.). The device then sends the emotion data captured while reading to the server. The server adds the entry to the database and stores the emotion data.

[1307] Step 6:

[1308] Manga Recommendations

[1309] When a user requests a recommendation of a new manga, the request is sent from the terminal to the server.

[1310] Input: User request, user information, reading history, emotional data

[1311] Output: Recommended manga list

[1312] How it works: When a user clicks the "Recommend a new manga" button, the device generates a request in JSON format. The device then sends it to the server using an HTTP POST request. The server receives the request and analyzes it based on the user's profile, reading history, and sentiment data. It then runs natural language processing and machine learning algorithms using Python libraries (such as NLTK, Scikit-learn, and TensorFlow) to generate an optimal list of manga recommendations. The server then returns the recommendation results in JSON format to the device, which then displays them to the user as a web page.

[1313] (Application example 2)

[1314] 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."

[1315] In today's world, it is extremely difficult for users to select content that matches their preferences and current emotions from the vast amount of content available. Furthermore, conventional content recommendation systems are primarily based on a user's past behavioral history and preferences, making it difficult to provide recommendations that reflect real-time emotions and psychological states. This can prevent users from appropriately selecting content that matches their momentary emotions, potentially resulting in a decrease in user satisfaction. To address this issue, a content recommendation system that reflects a user's preferences and emotions in real time is needed.

[1316] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1317] In this invention, the server includes: means for generating a user profile based on the user's preferred genres and desired reading atmosphere received from the user; means including an emotion engine for analyzing emotion data collected via the terminal and reflecting the data in the user profile; means for managing a reading history using the user profile and emotion data; recommendation means including natural language processing and machine learning algorithms for selecting optimal recommended content based on the user profile and reading history; and means for presenting the recommended content selected by the recommendation means to the user. This allows the user to quickly find optimal content based on their preferences and real-time emotions, resulting in a highly satisfying experience.

[1318] A "user profile" refers to data containing individual user information that is generated by integrating information such as the user's preferred genres, the mood they want to read, and real-time emotional data.

[1319] "Emotion data" refers to data related to emotions acquired in real time, such as facial expression data and voice data of a user collected via a terminal.

[1320] An "emotion engine" refers to software or hardware that analyzes collected emotion data and reflects the results in a user profile.

[1321] "Reading history" refers to data that records and manages content that a user has read in the past and emotional data at the time.

[1322] "Natural language processing" refers to the technology that enables computers to understand, generate, and analyze human language.

[1323] "Machine learning algorithms" are algorithms that allow computers to learn from data, find patterns, and make predictions and decisions.

[1324] "Recommendation tool" refers to a system component that uses natural language processing and machine learning algorithms to select the most appropriate content based on user profile, emotional data, and reading history.

[1325] "Content" refers to the general term for information and entertainment consumed by users, such as manga, videos, and music.

[1326] "Terminal" refers to a device that collects emotional data and connects the user to the system.

[1327] A "server" refers to a computer system that performs a series of processes such as managing user profiles and reading history, analyzing emotional data, and recommending content.

[1328] The system embodying this invention creates an individual user profile based on the user's preferred genres and desired reading atmosphere, and recommends optimal content while reflecting the user's real-time psychological state through emotional data.

[1329] System Configuration

[1330] The system includes the following main components:

[1331] 1. Terminal

[1332] A device that receives input from users and collects emotional data. Examples include smartphones and tablets. The device uses a camera and microphone to capture the user's facial expression and voice data, and sends it to a server.

[1333] 2. Server

[1334] It processes input information and emotion data, and manages user profiles and reading histories. Its role is to generate user profiles, manage reading histories, and provide content selected by recommendation means to the device.

[1335] 3. Emotion Engine

[1336] The emotion engine analyzes the user's emotion data in real time and updates the user profile by providing the results to the server. The emotion engine consists of software and hardware that analyzes the user's facial expressions and voice data.

[1337] 4. Recommendation method

[1338] It uses natural language processing (NLP) and machine learning algorithms to select the most suitable content based on the user's profile and reading history. It runs on the server and sends the selected content to the device.

[1339] Program processing

[1340] 1. User Registration

[1341] Users register and input their preferred genres and preferred reading atmospheres. This creates an individual user profile. The device then sends this input information, along with the user's facial expression and voice data, to the server.

[1342] 2. Data analysis and profile generation

[1343] The server generates a user profile based on the received information and emotion data and stores it in a database. The emotion engine analyzes the emotion data in real time and provides the analysis results to the server.

[1344] 3. Reflecting Emotional Data

[1345] Based on the analysis results of the emotion engine, the server updates the user profile to reflect psychological trends. Specifically, it analyzes information obtained from facial expressions and voice to detect and record the user's current emotions.

[1346] 4. Add reading history

[1347] Each time a user consumes content, the device sends the content along with emotional data to the server, which then updates the user's reading history and adds the latest reading information and emotional data to the user profile.

[1348] 5. Content Recommendations

[1349] When a user requests new content recommendations, the server analyzes the user's profile, emotional data, and reading history, and uses natural language processing (NLP) and machine learning algorithms to select the most suitable content. The selected recommendations are then sent to the device, which then displays them to the user.

[1350] Specific examples

[1351] For example, suppose a user registers with the ID "user456" and selects "SF" as their preferred genre and "relaxing" as their preferred reading atmosphere. The device collects this information along with the user's facial expression and voice data and sends it to the server. The server creates a profile for "user456" based on the received information and emotional data.

[1352] The emotion engine then analyzes the facial and voice data of "user456" in real time and provides the results to the server, which then updates the profile based on this data to reflect the user's psychological tendencies.

[1353] After that, when the user finishes reading "MangaX," the device sends the information along with the emotional data from the reading session to the server. The server then updates the reading history and emotional data of "user456."

[1354] Finally, when the user requests a recommendation for a new manga, the server analyzes it and recommends the most suitable "MangaY" and "MangaZ." The recommendation results are sent to the device of "user456," which then displays them to the user.

[1355] Prompt Sentence Examples

[1356] "Recommend MangaY and MangaZ based on the user's preferred genre of SF and the relaxing atmosphere they want to experience while reading."

[1357] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1358] Step 1:

[1359] User Registration

[1360] The user registers and inputs their preferred genre and desired reading atmosphere, which creates an initial profile for the user. The device collects this input information along with the user's facial expression and voice data, and sends it to the server.

[1361] Input: User information (preferred genre, desired reading atmosphere), facial expression data, voice data

[1362] Data processing: An initial user profile is generated based on the input information. Facial expression data and voice data are analyzed by the emotion engine and registered as initial emotion data.

[1363] Output: Generated initial user profile

[1364] Step 2:

[1365] Data analysis and profile generation

[1366] The server generates an initial user profile based on the received information and emotion data and stores it in a database. At this time, the emotion engine analyzes the emotion data in real time and provides the results to the server.

[1367] Input: Initial user profile, emotion data

[1368] Data processing: Data is analyzed using the emotion engine to evaluate the user's emotional state and update the user profile accordingly.

[1369] Output: Updated user profile

[1370] Step 3:

[1371] Emotion data reflection

[1372] The emotion engine analyzes the emotion data acquired in real time, and the server updates the user profile based on the results. The user's current emotional state is reflected in the profile.

[1373] Input: Real-time emotion data

[1374] Data processing: The emotion engine analyzes facial expression and voice data, converts the user's emotions into numerical values, and evaluates them. The evaluation results are sent to the server and reflected in the user profile.

[1375] Output: User profile reflecting emotional data

[1376] Step 4:

[1377] Add reading history

[1378] Every time a user consumes content, that information and emotional data is sent from the device to the server, which then uses this information to update the user's reading history and reflect it in their profile.

[1379] Input: Reading information, emotional data during consumption

[1380] Data processing: Reading information and emotion data are combined and added to the database as a series of historical data. User profiles are updated based on reading history.

[1381] Output: Updated reading history, user profile

[1382] Step 5:

[1383] Content Recommendations

[1384] When a user requests new content recommendations, the server analyzes the user's profile, emotional data, and reading history to recommend the most appropriate content. This is done using natural language processing and machine learning algorithms. The recommended content is then sent to the device and displayed to the user.

[1385] Input: User profile, reading history, real-time emotional data

[1386] Data processing: Analyze data using natural language processing and machine learning algorithms to select the most suitable content. The results are then verified using a generative AI model.

[1387] Output: Recommended content

[1388] Specific prompt examples:

[1389] "Recommend MangaY and MangaZ based on the user's preferred genre of SF and the relaxing atmosphere they want to experience while reading."

[1390] 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.

[1391] 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.

[1392] 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.

[1393] [Fourth embodiment]

[1394] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1395] 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.

[1396] 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).

[1397] 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.

[1398] 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.

[1399] 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).

[1400] 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.

[1401] 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.

[1402] 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.

[1403] 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.

[1404] 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.

[1405] 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.

[1406] 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."

[1407] This invention relates to a system that recommends the most suitable manga based on a user's preferred genre and desired reading atmosphere. The system generates an individual user profile based on information input by the user and manages their reading history. It also uses natural language processing and machine learning algorithms to recommend the most suitable manga for each user and presents the results to the user.

[1408] System Configuration

[1409] The system consists of the following main components:

[1410] 1. A terminal for receiving input from a user

[1411] 2. A server that processes input information and manages user profiles and reading histories

[1412] 3. A recommendation method that uses natural language processing and machine learning algorithms to select recommended manga.

[1413] Program processing overview

[1414] 1. User Registration

[1415] Users register and input their preferred genres and preferred reading atmosphere, which creates a personalized profile for the user.

[1416] The terminal organizes this input information and sends it to the server.

[1417] The server generates a user profile based on the received information and stores it in a database.

[1418] 2. Add reading history

[1419] When a user reads a manga, the information is sent to the server via the terminal.

[1420] The server updates the user's reading history and adds the latest reading information to the user's profile.

[1421] 3. Manga Recommendations

[1422] When a user requests a recommendation for a new manga, the device sends the request to the server.

[1423] The server analyzes user profiles and reading histories and uses natural language processing and machine learning algorithms to select recommended manga.

[1424] The recommendation results are sent from the server to the terminal, which then displays them to the user.

[1425] Specific examples

[1426] For example, a user registers with the ID "user123" and enters "fantasy" as their preferred genre and "exciting" as the desired reading atmosphere. The device organizes this information and sends it to the server. The server creates a user profile based on the received information and saves it in the profile of "user123."

[1427] Next, when the user finishes reading "Manga1," the information is sent from the terminal to the server, which adds "Manga1" to the reading history of "user123."

[1428] When the user subsequently requests a recommendation for a new manga, the server analyzes the profile and reading history of user "user123" and uses natural language processing and machine learning algorithms to recommend "Manga2," "Manga3," and "Manga4." The recommendation results are then sent to the device, which displays them to the user.

[1429] ---

[1430] The above is an embodiment of the present invention. This system allows users to quickly find manga that best suits their preferences and the atmosphere they want to read, improving their reading experience. It also allows publishers to accurately grasp readers' interests and promote their works more effectively.

[1431] The processing flow will be explained below.

[1432] Step 1:

[1433] The user registers by entering their ID, preferred genre, and desired reading atmosphere.

[1434] Step 2:

[1435] The device receives the input information and sends it to the server in a format that creates a data packet containing the user's ID, preferred genre, and desired reading atmosphere.

[1436] Step 3:

[1437] The server analyzes the received data and generates a user profile, including the user ID, preferred genre, and preferred reading atmosphere, which is then stored in a database.

[1438] Step 4:

[1439] The user selects a manga and begins reading.

[1440] Step 5:

[1441] When a user finishes reading a manga, the device acquires that information. Specifically, it records the title and ID of the manga that the user has finished reading.

[1442] Step 6:

[1443] The device sends the reading history information to the server, generating a data packet containing the user ID and the ID of the manga that has been read.

[1444] Step 7:

[1445] The server analyzes the received reading history data and updates the user profile. Specifically, it adds the new manga ID to the user's reading history list.

[1446] Step 8:

[1447] A user requests a recommendation for a new manga. The user sends a recommendation request through the terminal.

[1448] Step 9:

[1449] The device receives the recommendation request and sends it to the server. Specifically, it generates a recommendation request data packet including the user ID.

[1450] Step 10:

[1451] The server receives recommendation requests, analyzes the user's profile and reading history, and generates a list of recommendations based on the user's preferences using natural language processing and machine learning algorithms.

[1452] Step 11:

[1453] The server sends the generated recommendation list to the device. Specifically, it generates a data packet containing the titles and IDs of the recommended manga.

[1454] Step 12:

[1455] The terminal receives the recommendation list and displays it to the user through a graphical user interface.

[1456] Step 13:

[1457] The user reviews the list of recommended manga and selects the manga they want to read next.

[1458] Example 1

[1459] 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."

[1460] Currently, users face challenges in quickly finding the most appropriate information based on their preferences and desired reading atmosphere. Furthermore, it is difficult to generate and manage profiles that accurately reflect users' interests and psychological tendencies, which reduces the accuracy of recommendations. Furthermore, there is a need for an efficient recommendation method to promote the discovery of new information.

[1461] 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.

[1462] In this invention, the server includes: means for generating a user profile based on the user's preferred genres and desired reading style received from the user; means for managing a reading history using the user profile; means for managing reading start information and reading completion information based on the reading history information; recommendation means including natural language processing and machine learning algorithms for selecting optimal recommended information based on the user profile and reading history; means for presenting the recommended information selected by the recommendation means to the user; and means for analyzing prompt sentences that receive recommendation requests from the user. This allows users to quickly find information that best suits their preferences and desired reading style, improving the user experience. It also enables the generation and management of highly accurate profiles that reflect the user's interests and psychological tendencies, and promotes the discovery of new information.

[1463] A "user profile" is data that compiles individual information including a user's preferred genres, preferred reading style, reading history, and so on.

[1464] "Reading history" is a record of the comics and books that a user has read, and is data that includes information on when the user started reading and when the user finished reading.

[1465] "Natural language processing" is a technology for analyzing text data entered by a user and understanding its meaning and intent.

[1466] A "machine learning algorithm" is an algorithm that learns patterns and relationships from large amounts of data and makes predictions and recommendations.

[1467] "Recommendation means" refers to methods and technologies for selecting and presenting optimal information to a user based on the user's profile and reading history.

[1468] A "prompt sentence" is a text sentence that describes a question or request that a user makes to the system.

[1469] A "parsing means" is a technique or method for parsing a prompt or other input data and understanding its meaning.

[1470] "Information" refers to data such as recommended manga and books provided to users.

[1471] This invention relates to a system that recommends the most suitable manga based on a user's preferred genre and desired reading atmosphere. This system generates an individual user profile based on information input by the user and manages their reading history. It also uses natural language processing and machine learning algorithms to recommend the most suitable manga for each user and presents the results to the user.

[1472] The system consists of the following main components:

[1473] 1. A terminal for receiving input from a user

[1474] 2. A server that processes input information and manages user profiles and reading histories

[1475] 3. A recommendation method that uses natural language processing and machine learning algorithms to select recommended manga.

[1476] Hardware and Software Environment

[1477] 1. Terminal - A device that receives user input, such as a smartphone or PC.

[1478] 2. Server - The server that processes and stores the data. Specifically, we use cloud-based servers (e.g., Amazon Web Services (AWS)).

[1479] 3. Natural language processing models - for example, BERT or GPT-3 - are used to analyze user input.

[1480] 4. Machine learning algorithms - for example, using Collaborative Filtering and Content-Based Filtering to recommend manga.

[1481] System Operation

[1482] User Registration

[1483] A user registers using a terminal and inputs their preferred genre and preferred reading atmosphere. This information is sent from the terminal to the server, and the server generates a user profile based on the received information and stores it in a database. For example, if a user likes the "fantasy" genre and prefers an "exciting" atmosphere, a profile can be generated by inputting this information.

[1484] Add reading history

[1485] When a user reads a manga, that information is sent to the server via the terminal. The server records the user's reading history in a database and adds the latest reading information to the user's profile. For example, when a user finishes reading a title called "Manga1," that reading history is sent to the server and added to the user's profile.

[1486] Manga Recommendations

[1487] When a user requests a recommendation for a new manga, the device sends the request to the server. The server analyzes the user's profile and reading history, and recommends the most suitable manga using natural language processing models and machine learning algorithms. The recommendation results are sent from the server to the device and displayed to the user. For example, if a user enters the prompt "I want to read a fantasy and exciting manga," the system will recommend "Manga2," "Manga3," and "Manga4."

[1488] Examples of prompt statements

[1489] When a user inputs a prompt such as "I want to read an exciting fantasy manga. Can you recommend some?", the system analyzes it using a natural language processing model and makes the best recommendations. This allows users to quickly find the manga that best suits their preferences and the atmosphere they want to read.

[1490] In this way, the present invention improves the user experience and provides an environment in which users can efficiently discover manga that suit their tastes.

[1491] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1492] Step 1:

[1493] The user registers using a terminal. The user enters their ID, password, preferred genre (e.g., "fantasy"), and desired reading atmosphere (e.g., "exciting") into the input form on the terminal. This information is registered on the terminal as input data.

[1494] Input: User ID, password, preferred genre, desired reading atmosphere

[1495] Specific operation: Fill in the information in the input form and press the "Register" button to complete the entry.

[1496] Output: The terminal organizes the input information and generates data in JSON format.

[1497] Step 2:

[1498] The device sends the information entered by the user to the server, where it is encrypted and securely transmitted using the HTTPS protocol.

[1499] Input: JSON formatted data entered by the user

[1500] Specific operation: The device formats the JSON data and sends it to the server via an HTTPS request.

[1501] Output: The server receives the JSON data.

[1502] Step 3:

[1503] The server analyzes the received information and generates a user profile, storing the data according to an internal database schema based on the genre and atmosphere information received.

[1504] Input: JSON format data received from the terminal

[1505] Specific operation: The server deserializes the received data, generates a user profile, and saves it in the database.

[1506] Output: The generated user profile is stored in a database.

[1507] Step 4:

[1508] The user starts reading a manga through the device. The user uses the search function in the system to select a manga (e.g., "Manga1") and clicks to read it.

[1509] Input: User's search keyword or manga selection status

[1510] Specific action: The user selects a manga from the search box or list and presses the "Read" button.

[1511] Output: Information about the selected manga will be displayed on the device.

[1512] Step 5:

[1513] The device sends information about the comic the user has started reading to the server, including the comic's ID and the user ID.

[1514] Input: User's selected manga ID and user ID

[1515] Specific operation: The device formats the selection information and sends it to the server via an HTTPS request.

[1516] Output: The server receives the selection information.

[1517] Step 6:

[1518] The server updates the user's reading history based on the received information. The server updates the database to add the new reading history to the user's profile.

[1519] Input: Received manga ID and user ID

[1520] Specific behavior: The server executes a database query to add a new reading history.

[1521] Output: The updated user's reading history is stored in the database.

[1522] Step 7:

[1523] The user requests a recommendation for a new manga. The user issues the request by clicking the "Recommend Manga" button.

[1524] Input: Recommendation request

[1525] What happens: The user presses a button to request a recommendation.

[1526] Output: A recommendation request is sent from the device to the server.

[1527] Step 8:

[1528] The device sends recommendation request information, including the user ID, to the server.

[1529] Input: Recommendation request with user ID

[1530] What it does: It formats the recommendation request and sends it to the server via an HTTPS request.

[1531] Output: The server receives the recommendation request.

[1532] Step 9:

[1533] The server analyzes user profiles and reading histories, uses natural language processing models to extract keywords related to the user's preferences and reading history, and uses machine learning algorithms to select the most suitable manga recommendations.

[1534] Input: User profile and reading history

[1535] How it works: Natural language processing models analyze profile data, and machine learning algorithms select the best recommendations.

[1536] Output: A list of recommended manga is generated.

[1537] Step 10:

[1538] The server transmits the selected recommendation results to the terminal.

[1539] Input: Recommended manga list

[1540] Specific operation: The recommendation list is formatted and sent to the device as an HTTPS response.

[1541] Output: The terminal receives the recommendation results.

[1542] Step 11:

[1543] The device displays the recommendation results to the user, who can then check the recommended manga (e.g., "Manga2," "Manga3," "Manga4").

[1544] Input: Recommended manga list received from the server

[1545] Specific operation: Display the recommendation results on the user interface.

[1546] Output: The recommended manga is displayed to the user.

[1547] (Application example 1)

[1548] 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."

[1549] Conventional manga recommendation systems have difficulty recommending appropriate manga because they do not fully consider users' preferences or reading history. Furthermore, they are insufficient as a means for users to discover new manga, limiting the improvement of the reading experience. Furthermore, due to the lack of use across a variety of devices and the lack of AI technology, optimal recommendations to users are delayed and accuracy is reduced.

[1550] 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.

[1551] In this invention, the server includes: a means for generating a user profile based on the user's preferred genres and desired reading style; a means for managing a reading history using the user profile; a recommendation means including natural language processing and machine learning algorithms for selecting optimal manga recommendations based on the user profile and reading history; a means for presenting the recommended manga selected by the recommendation means to the user; a means including an application to be installed on a smartphone; a means for processing and storing data using a cloud server; and a means for optimizing the recommendation results using a generative AI model. This allows users to quickly find the optimal manga based on their preferences and reading history, improving their reading experience. Furthermore, the use of the cloud server and generative AI model improves the accuracy and processing speed of recommendation results.

[1552] A "user profile" is a collection of information about an individual user that is generated based on the user's preferred genres and preferred reading atmosphere.

[1553] "Reading history" is a record of the manga that a user has read so far, and is data that is managed as part of a user profile.

[1554] The "recommendation method" is a system that uses natural language processing and machine learning algorithms to select the most suitable manga based on the user's profile and reading history, and presents it to the user.

[1555] "Natural language processing" is a technology that allows computers to understand, generate, and manipulate human language, and in this system it is used to analyze the genre and atmosphere of manga.

[1556] A "machine learning algorithm" is a computational method that learns from data, extracts patterns and rules, and makes predictions and classifications for new data.

[1557] The "application installed on a smartphone" is software that allows users to access the system using their smartphone to receive manga recommendations and manage their reading history.

[1558] A "cloud server" is a remote server utilized over the Internet, and is an infrastructure for processing and storing data.

[1559] A "generative AI model" is an artificial intelligence model that has been trained in advance using large amounts of data, and is a technology used to optimize manga recommendation results.

[1560] This invention is a system that recommends the most suitable manga based on the user's preferred genre and desired reading atmosphere.

[1561] System configuration

[1562] The system consists of the following main components:

[1563] 1. A device (smartphone) for receiving input from the user

[1564] 2. A server (cloud server) that processes input information and manages user profiles and reading histories

[1565] 3. A recommendation method (generative AI model) that uses natural language processing and machine learning algorithms to select recommended manga.

[1566] Hardware and Software Configuration

[1567] Hardware:

[1568] Smartphone

[1569] Cloud servers (e.g., Amazon Web Services, Microsoft Azure, Google Cloud Platform)

[1570] software:

[1571] Smartphone app development environment (iOS: Swift, Android: Kotlin)

[1572] Natural language processing libraries (e.g. TensorFlow, spaCy)

[1573] Machine learning algorithms (e.g., scikit-learn, PyTorch)

[1574] Database (e.g. MongoDB, MySQL)

[1575] Program processing overview

[1576] 1. User Registration:

[1577] Users register and input their preferred genres and the atmosphere they want to read. The smartphone organizes this information and sends it to the cloud server, which then creates a user profile based on the information it receives and stores it in a database.

[1578] 2. Add reading history:

[1579] When a user reads a manga, the information is sent to the cloud server via their smartphone. The server updates the user's reading history and adds the latest reading information to the user's profile.

[1580] 3. Manga Recommendations:

[1581] When a user requests a new manga recommendation, the smartphone device sends the request to a cloud server. The server analyzes the user's profile and reading history, and uses natural language processing and machine learning algorithms to select the most suitable manga. The server then optimizes the recommendation results using a generative AI model and sends the results to the smartphone device for display to the user.

[1582] Specific examples

[1583] For example, a user registers with the ID "user123" and enters "fantasy" as their preferred genre and "exciting" as the atmosphere they want to read. The smartphone organizes this information and sends it to the cloud server. The server creates a user profile based on the received information and saves it in the profile for "user123."

[1584] Next, when the user finishes reading "Manga1," the smartphone sends the information to the cloud server, which adds "Manga1" to the reading history of "user123."

[1585] Later, when the user requests a recommendation for a new manga, the cloud server analyzes the profile and reading history of user “user123” and selects the most suitable manga using natural language processing and machine learning algorithms.

[1586] Example prompts for generative AI models

[1587] Please recommend the best manga based on the following user profile.

[1588] User Profile:

[1589] ID: user123

[1590] Favorite genre: Fantasy

[1591] Reading mood: Exciting

[1592] Reading history: Manga1, Manga2, Manga3

[1593] Output the best manga recommendation results.

[1594] In this way, this system allows users to quickly find the manga that best suits their preferences and the atmosphere they want to read. Furthermore, by utilizing cloud servers and generative AI models, the accuracy and processing speed of recommendation results are improved, greatly improving the user's reading experience.

[1595] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1596] Step 1:

[1597] A user registers and inputs their preferred genre and preferred reading style. The device then organizes the input information and sends it to the cloud server. The input data includes the user ID, preferred genre, and preferred reading style. The cloud server receives this information, generates a user profile, and saves it in the database. As a result, individual user profiles are stored in the database.

[1598] Step 2:

[1599] When a user reads a manga, that information is sent to the cloud server via the device. The input data is the user ID and the title of the manga read. The cloud server receives this and adds the user's reading history to the user profile stored in the database. This updates the latest reading history information.

[1600] Step 3:

[1601] When a user requests a recommendation of a new manga, the device sends the request to the cloud server. The input data is the user ID. The cloud server extracts the user profile and reading history from the database and uses them for analysis. Specifically, it processes the data to recommend the most suitable manga to the user using a generative AI model. Here, natural language processing technology is used to analyze the user's profile information and reading history.

[1602] Step 4:

[1603] The cloud server inputs the prompt sentences into the generative AI model to obtain the optimal recommendation results. The input data is as follows:

[1604] Please recommend the best manga based on the following user profile.

[1605] User Profile:

[1606] ID: user123

[1607] Favorite genre: Fantasy

[1608] Reading mood: Exciting

[1609] Reading history: Manga1, Manga2, Manga3

[1610] Output the best manga recommendation results.

[1611] The generative AI model analyzes this prompt and generates the most suitable manga title. The generated result is a list of the most suitable manga titles.

[1612] Step 5:

[1613] The cloud server sends the generated recommendation results to the device, which receives them and displays them to the user. The output data is a list of recommended manga titles, allowing the user to view the best manga recommendation results based on their preferences.

[1614] Through the above processing steps, the system recommends the most suitable manga based on the user's preferences and reading history, improving the reading experience.

[1615] 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.

[1616] This invention relates to a system that combines a user's preferred genres and desired reading atmosphere with an emotion engine that recognizes the user's emotions. The system generates an individual user profile based on the user's input information and real-time emotion data, and manages their reading history. It also uses natural language processing and machine learning algorithms to recommend the most suitable manga for each user and presents the results to the user.

[1617] System Configuration

[1618] The system consists of the following main components:

[1619] 1. A terminal for receiving input from a user

[1620] 2. A server that processes input information and emotion data and manages user profiles and reading histories

[1621] 3. Emotion engine that recognizes and analyzes user emotion data

[1622] 4. A recommendation method that uses natural language processing and machine learning algorithms to select recommended manga.

[1623] Program processing overview

[1624] 1. User Registration

[1625] Users register and input their preferred genres and preferred reading atmosphere, which creates an individual user profile.

[1626] The terminal receives this input information, as well as the user's facial expression data, voice data, and other emotional data, and transmits them to the server.

[1627] The server generates a user profile based on the received information and emotion data and stores it in a database.

[1628] 2. Emotion Data Analysis

[1629] The emotion engine analyzes the user's emotion data in real time and provides the results to the server.

[1630] The server updates the user profile with the analysis results to reflect the user's psychological tendencies.

[1631] 3. Add reading history

[1632] When a user reads a manga, the information and emotional data are sent to the server via the device.

[1633] The server updates the user's reading history and adds the latest reading information and emotion data to the user profile.

[1634] 4. Manga Recommendations

[1635] When a user requests a recommendation for a new manga, the device sends the request to the server.

[1636] The server analyzes user profiles, emotional data, and reading history, and uses natural language processing and machine learning algorithms to select recommended manga.

[1637] The recommendation results are sent from the server to the terminal, which then displays them to the user.

[1638] Specific examples

[1639] For example, a user registers with the ID "user123" and enters "fantasy" as their preferred genre and "exciting" as the atmosphere they want to read. The device organizes this information along with the user's facial expression and voice data, and sends it to the server. The server generates a user profile based on the received information and emotional data, and saves it in the profile for "user123."

[1640] The emotion engine then analyzes the facial expression and voice data of user "user123" in real time and provides the analysis results to the server, which then updates the profile based on this data to reflect the user's psychological tendencies.

[1641] After that, when the user finishes reading "Manga1," the information and emotional data from the reading session are sent from the device to the server. The server updates the reading history and emotional data of "user123."

[1642] When a user requests a recommendation for a new manga, the server analyzes the profile, emotional data, and reading history of user "user123," and uses natural language processing and machine learning algorithms to recommend "Manga2," "Manga3," and "Manga4." The recommendation results are sent to the device, which then displays them to the user.

[1643] ---

[1644] The above is an embodiment of the present invention. This system allows users to quickly find the manga that best suits their tastes and desired reading atmosphere, as well as real-time emotional data, providing a highly satisfying reading experience. It also allows publishers to accurately grasp readers' interests and emotions and effectively promote their works.

[1645] The processing flow will be explained below.

[1646] Step 1:

[1647] The user registers by entering their ID, preferred genre, and desired reading atmosphere.

[1648] Step 2:

[1649] The device receives the input information and organizes it according to a format, specifically creating a data packet containing the user's ID, preferred genre, and desired reading atmosphere.

[1650] Step 3:

[1651] The terminal transmits the organized data packets to the server.

[1652] Step 4:

[1653] The server analyzes the received data and generates a user profile, specifically storing the user ID, preferred genre, and preferred reading atmosphere in a database.

[1654] Step 5:

[1655] The device collects emotional data such as facial expressions and voice data from the user in real time and transmits it to the server.

[1656] Step 6:

[1657] The emotion engine analyzes the received emotion data and provides the results to the server. Specifically, it recognizes emotions from the user's facial expressions and voice and generates analysis results.

[1658] Step 7:

[1659] The server updates the user profile based on the analysis of the emotional data, specifically adding the emotional data to the profile to reflect the user's psychological tendencies.

[1660] Step 8:

[1661] The user selects a manga and reads it. Emotional data is collected while the user is reading.

[1662] Step 9:

[1663] The terminal transmits the user's reading history information and emotional data during reading to the server.

[1664] Step 10:

[1665] The server updates the user profile based on the reading history and emotion data. Specifically, it adds the ID and emotion data of the new manga to the user profile.

[1666] Step 11:

[1667] A user requests a recommendation for a new manga. The user sends a recommendation request through the terminal.

[1668] Step 12:

[1669] The device receives the recommendation request and sends it to the server. Specifically, it generates a recommendation request data packet including the user ID.

[1670] Step 13:

[1671] The server receives recommendation requests and analyzes user profiles, emotional data, and reading history, using natural language processing and machine learning algorithms to generate a list of recommendations based on the user's preferences.

[1672] Step 14:

[1673] The server sends the generated recommendation list to the device. Specifically, it generates a data packet containing the titles and IDs of the recommended manga.

[1674] Step 15:

[1675] The terminal receives the recommendation list and displays it to the user through a graphical user interface.

[1676] Step 16:

[1677] The user reviews the list of recommended manga and selects the manga they want to read next.

[1678] Example 2

[1679] 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."

[1680] Conventional recommendation systems make recommendations based on the user's preferences and desired reading atmosphere, but they do not fully consider the user's emotions or psychological tendencies, making it difficult to increase user satisfaction. In addition, there is a need for more accurate recommendations by utilizing real-time emotional data.

[1681] 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.

[1682] In this invention, the server includes: means for generating user information based on the user's preferred types and desired reading atmospheres received from the user; means for managing a reading history using the user information and emotion data; recommendation means including natural language processing and machine learning algorithms for selecting optimal recommended materials based on the user information and reading history; means for presenting the recommended materials selected by the recommendation means to the user; emotion analysis means for analyzing the user's current emotion data in real time; and update means for reflecting the analysis results of the emotion analysis means in the user information. This enables recommendations that take the user's emotions and psychological tendencies into consideration, providing a highly satisfying reading experience.

[1683] "User" refers to an individual who uses this system to receive manga recommendations.

[1684] "Favorite types" refers to the genres and categories of manga that users want to read, which they enter when registering.

[1685] "Desired reading atmosphere" refers to a specific emotion or tone of the manga that a user wants to read (e.g., exciting, relaxing).

[1686] "User information" refers to a profile generated based on the user's input preferences, desired reading atmosphere, and emotional data.

[1687] "Emotion data" refers to data that quantifies emotions derived from the user's facial expressions and voice.

[1688] "Reading history" refers to information including a record of the manga that the user has read in the past and emotional data at the time.

[1689] "Server" refers to the computer system that processes data and executes the recommendation algorithms of the System.

[1690] "Natural language processing" refers to algorithms and techniques for analyzing text information and understanding its meaning.

[1691] A "machine learning algorithm" refers to a computational method for automatically learning from data and finding patterns.

[1692] "Recommendation means" refers to the part of the system that uses user information, reading history, natural language processing, and machine learning algorithms to recommend the most suitable manga to users.

[1693] "Emotion analysis means" refers to the part of the system that analyzes the user's emotion data in real time and generates the results.

[1694] The "update means" refers to the part of the system that reflects the results of the emotion analysis means in the user information and keeps that information up to date.

[1695] "Recommended Materials" refers to manga recommended based on a user's profile and emotional data.

[1696] The present invention is a system that analyzes real-time emotional data in addition to the user's preferred types and desired reading atmosphere to recommend the most suitable manga to the user. The following describes the detailed procedure for specifically implementing the present invention.

[1697] System Configuration

[1698] The system consists of the following main components:

[1699] 1. A terminal for receiving input from a user

[1700] 2. A server that processes input information and emotion data and manages user profiles and reading histories

[1701] 3. Emotion analysis method for recognizing and analyzing user emotion data

[1702] 4. A recommendation method that uses natural language processing and machine learning algorithms to select recommended manga.

[1703] Specific hardware and software used

[1704] Device:

[1705] Use devices such as smartphones, tablets, and PCs to collect user input and emotional data.

[1706] Emotion analysis means:

[1707] Technologies such as Emotion API, Affectiva, and FaceReader are used to analyze emotional data.

[1708] server:

[1709] Data processing and management uses cloud services such as AWS EC2, Google Cloud, and Microsoft Azure.

[1710] Database:

[1711] Databases such as MySQL and PostgreSQL are used to store user profiles and reading history.

[1712] Natural Language Processing and Machine Learning:

[1713] The recommendation algorithm is implemented using Python libraries (NLTK, Scikit-learn, TensorFlow, PyTorch).

[1714] System Operation Overview

[1715] User Registration

[1716] The user uses a terminal to access a new registration form and inputs their preferred genre (e.g., "fantasy") and the atmosphere they want to read (e.g., "exciting"). The terminal collects this input information and sends it to the server along with the user's facial expression and voice data. The server generates user information based on the received data and stores it in a database.

[1717] Emotional Data Analysis

[1718] While a user is logged in to their device, real-time emotional data is collected via the camera and microphone. The device sends this data to a server, which then analyzes the received data using emotion analysis tools. The analysis results are reflected in the user information, and the user profile is updated to the latest version.

[1719] Add reading history

[1720] When a user finishes reading a manga, the terminal sends the information along with the emotional data from the reading session to the server. The server receives this data and updates the user's reading history and emotional data.

[1721] Manga Recommendations

[1722] When a user requests a new manga recommendation, the request is sent from the device to the server. The server analyzes the user's information, reading history, and emotional data, and uses natural language processing and machine learning algorithms to select the most suitable manga. The recommendation results are sent from the server to the device, which then displays them to the user.

[1723] Specific examples

[1724] For example, a user registers with the ID "user123" and enters "fantasy" as their preferred type of book and "exciting" as the desired reading atmosphere. The device organizes this information, along with facial expression and voice data, and sends it to the server. The server generates a user profile based on the received information and saves it in the profile for "user123."

[1725] The emotion analysis means analyzes the facial expression and voice data of user "user123" in real time and provides the analysis results to the server, which then updates the profile based on this data to reflect the user's psychological tendencies.

[1726] Next, when the user finishes reading "Manga1," that information and the emotional data during reading are sent from the terminal to the server, and the server updates the reading history and emotional data of "user123."

[1727] When a user requests a recommendation for a new manga, the server analyzes the profile, emotional data, and reading history of user "user123," and uses natural language processing and machine learning algorithms to recommend "Manga2," "Manga3," and "Manga4." The recommendation results are sent to the device, which then displays them to the user.

[1728] Prompt Sentence Examples

[1729] Example prompt 1:

[1730] "User123 is looking for manga in the fantasy genre with an exciting atmosphere. Please recommend three manga that fit his needs, taking into account his latest emotional data and reading history."

[1731] Example prompt 2:

[1732] "User ID: user321, Favorite genre: Horror, Recent emotional data: Calm. Based on this information, please recommend two manga."

[1733] The above is a detailed embodiment of the present invention. This system allows users to effectively find the most suitable manga based on their own feelings and preferences, providing a highly satisfying reading experience.

[1734] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1735] Step 1:

[1736] Entering user information and registering

[1737] Users use their device to access a new registration form and enter their preferred genre (e.g., "fantasy") and the atmosphere they want to read (e.g., "exciting").

[1738] Input: User's preferred type, desired reading atmosphere, facial expression data, voice data

[1739] Output: User information sent to the server

[1740] Specific operation: When a user clicks the "Register" button, the device collects form data using JavaScript, captures facial expressions with the camera, and records audio data with the microphone. The device converts the collected data into JSON format and sends it to the server using an HTTP POST request.

[1741] Step 2:

[1742] Saving user information

[1743] The server generates a user profile based on the received information and stores it in a database.

[1744] Input: JSON format user information sent from the terminal

[1745] Output: User profile stored in the database

[1746] What happens: The server receives the request using Python's Flask, parses the data, creates a profile for the user, and saves it in a MySQL database by executing an INSERT query.

[1747] Step 3:

[1748] Collecting Emotional Data

[1749] While the user is logged in to the device, real-time emotional data is collected via the camera and microphone.

[1750] Input: User's facial expression data, voice data

[1751] Output: Emotion data sent from the device to the server

[1752] How it works: When a user logs in to the system and loads a page, the device uses JavaScript to trigger the camera and microphone. Facial expression data and voice data are collected in real time using WebRTC. The device then sends this real-time data to the server using Python's Socket.IO.

[1753] Step 4:

[1754] Emotional Data Analysis

[1755] The server uses an emotion engine to analyze the received data.

[1756] Input: Real-time emotion data sent from the device

[1757] Output: Parsed emotion data, updated user profile

[1758] Specific operation: The server analyzes the received data using Emotion API (or Affectiva, FaceReader) and obtains the results. The server reflects the analysis results in the user profile and updates the database.

[1759] Step 5:

[1760] Add reading history

[1761] When the user finishes reading the manga, the information about the manga is sent from the terminal to the server along with the emotional data recorded during the reading.

[1762] Input: Information about the manga the user has read, emotional data while reading

[1763] Output: Updated reading history, sentiment data

[1764] Specific operation: When the user clicks the "Finished reading" button, the device collects information about the comic (title, ID, etc.). The device then sends the emotion data captured while reading to the server. The server adds the entry to the database and stores the emotion data.

[1765] Step 6:

[1766] Manga Recommendations

[1767] When a user requests a recommendation of a new manga, the request is sent from the terminal to the server.

[1768] Input: User request, user information, reading history, emotional data

[1769] Output: Recommended manga list

[1770] How it works: When a user clicks the "Recommend a new manga" button, the device generates a request in JSON format. The device then sends it to the server using an HTTP POST request. The server receives the request and analyzes it based on the user's profile, reading history, and sentiment data. It then runs natural language processing and machine learning algorithms using Python libraries (such as NLTK, Scikit-learn, and TensorFlow) to generate an optimal list of manga recommendations. The server then returns the recommendation results in JSON format to the device, which then displays them to the user as a web page.

[1771] (Application example 2)

[1772] 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."

[1773] In today's world, it is extremely difficult for users to select content that matches their preferences and current emotions from the vast amount of content available. Furthermore, conventional content recommendation systems are primarily based on a user's past behavioral history and preferences, making it difficult to provide recommendations that reflect real-time emotions and psychological states. This can prevent users from appropriately selecting content that matches their momentary emotions, potentially resulting in a decrease in user satisfaction. To address this issue, a content recommendation system that reflects a user's preferences and emotions in real time is needed.

[1774] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1775] In this invention, the server includes: means for generating a user profile based on the user's preferred genres and desired reading atmosphere received from the user; means including an emotion engine for analyzing emotion data collected via the terminal and reflecting the data in the user profile; means for managing a reading history using the user profile and emotion data; recommendation means including natural language processing and machine learning algorithms for selecting optimal recommended content based on the user profile and reading history; and means for presenting the recommended content selected by the recommendation means to the user. This allows the user to quickly find optimal content based on their preferences and real-time emotions, resulting in a highly satisfying experience.

[1776] A "user profile" refers to data containing individual user information that is generated by integrating information such as the user's preferred genres, the mood they want to read, and real-time emotional data.

[1777] "Emotion data" refers to data related to emotions acquired in real time, such as facial expression data and voice data of a user collected via a terminal.

[1778] An "emotion engine" refers to software or hardware that analyzes collected emotion data and reflects the results in a user profile.

[1779] "Reading history" refers to data that records and manages content that a user has read in the past and emotional data at the time.

[1780] "Natural language processing" refers to the technology that enables computers to understand, generate, and analyze human language.

[1781] "Machine learning algorithms" are algorithms that allow computers to learn from data, find patterns, and make predictions and decisions.

[1782] "Recommendation tool" refers to a system component that uses natural language processing and machine learning algorithms to select the most appropriate content based on user profile, emotional data, and reading history.

[1783] "Content" refers to the general term for information and entertainment consumed by users, such as manga, videos, and music.

[1784] "Terminal" refers to a device that collects emotional data and connects the user to the system.

[1785] A "server" refers to a computer system that performs a series of processes such as managing user profiles and reading history, analyzing emotional data, and recommending content.

[1786] The system embodying this invention creates an individual user profile based on the user's preferred genres and desired reading atmosphere, and recommends optimal content while reflecting the user's real-time psychological state through emotional data.

[1787] System Configuration

[1788] The system includes the following main components:

[1789] 1. Terminal

[1790] A device that receives input from users and collects emotional data. Examples include smartphones and tablets. The device uses a camera and microphone to capture the user's facial expression and voice data, and sends it to a server.

[1791] 2. Server

[1792] It processes input information and emotion data, and manages user profiles and reading histories. Its role is to generate user profiles, manage reading histories, and provide content selected by recommendation means to the device.

[1793] 3. Emotion Engine

[1794] The emotion engine analyzes the user's emotion data in real time and updates the user profile by providing the results to the server. The emotion engine consists of software and hardware that analyzes the user's facial expressions and voice data.

[1795] 4. Recommendation method

[1796] It uses natural language processing (NLP) and machine learning algorithms to select the most suitable content based on the user's profile and reading history. It runs on the server and sends the selected content to the device.

[1797] Program processing

[1798] 1. User Registration

[1799] Users register and input their preferred genres and preferred reading atmospheres. This creates an individual user profile. The device then sends this input information, along with the user's facial expression and voice data, to the server.

[1800] 2. Data analysis and profile generation

[1801] The server generates a user profile based on the received information and emotion data and stores it in a database. The emotion engine analyzes the emotion data in real time and provides the analysis results to the server.

[1802] 3. Reflecting Emotional Data

[1803] Based on the analysis results of the emotion engine, the server updates the user profile to reflect psychological trends. Specifically, it analyzes information obtained from facial expressions and voice to detect and record the user's current emotions.

[1804] 4. Add reading history

[1805] Each time a user consumes content, the device sends the content along with emotional data to the server, which then updates the user's reading history and adds the latest reading information and emotional data to the user profile.

[1806] 5. Content Recommendations

[1807] When a user requests new content recommendations, the server analyzes the user's profile, emotional data, and reading history, and uses natural language processing (NLP) and machine learning algorithms to select the most suitable content. The selected recommendations are then sent to the device, which then displays them to the user.

[1808] Specific examples

[1809] For example, suppose a user registers with the ID "user456" and selects "SF" as their preferred genre and "relaxing" as their preferred reading atmosphere. The device collects this information along with the user's facial expression and voice data and sends it to the server. The server creates a profile for "user456" based on the received information and emotional data.

[1810] The emotion engine then analyzes the facial and voice data of "user456" in real time and provides the results to the server, which then updates the profile based on this data to reflect the user's psychological tendencies.

[1811] After that, when the user finishes reading "MangaX," the device sends the information along with the emotional data from the reading session to the server. The server then updates the reading history and emotional data of "user456."

[1812] Finally, when the user requests a recommendation for a new manga, the server analyzes it and recommends the most suitable "MangaY" and "MangaZ." The recommendation results are sent to the device of "user456," which then displays them to the user.

[1813] Prompt Sentence Examples

[1814] "Recommend MangaY and MangaZ based on the user's preferred genre of SF and the relaxing atmosphere they want to experience while reading."

[1815] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1816] Step 1:

[1817] User Registration

[1818] The user registers and inputs their preferred genre and desired reading atmosphere, which creates an initial profile for the user. The device collects this input information along with the user's facial expression and voice data, and sends it to the server.

[1819] Input: User information (preferred genre, desired reading atmosphere), facial expression data, voice data

[1820] Data processing: An initial user profile is generated based on the input information. Facial expression data and voice data are analyzed by the emotion engine and registered as initial emotion data.

[1821] Output: Generated initial user profile

[1822] Step 2:

[1823] Data analysis and profile generation

[1824] The server generates an initial user profile based on the received information and emotion data and stores it in a database. At this time, the emotion engine analyzes the emotion data in real time and provides the results to the server.

[1825] Input: Initial user profile, emotion data

[1826] Data processing: Data is analyzed using the emotion engine to evaluate the user's emotional state and update the user profile accordingly.

[1827] Output: Updated user profile

[1828] Step 3:

[1829] Emotion data reflection

[1830] The emotion engine analyzes the emotion data acquired in real time, and the server updates the user profile based on the results. The user's current emotional state is reflected in the profile.

[1831] Input: Real-time emotion data

[1832] Data processing: The emotion engine analyzes facial expression and voice data, converts the user's emotions into numerical values, and evaluates them. The evaluation results are sent to the server and reflected in the user profile.

[1833] Output: User profile reflecting emotional data

[1834] Step 4:

[1835] Add reading history

[1836] Every time a user consumes content, that information and emotional data is sent from the device to the server, which then uses this information to update the user's reading history and reflect it in their profile.

[1837] Input: Reading information, emotional data during consumption

[1838] Data processing: Reading information and emotion data are combined and added to the database as a series of historical data. User profiles are updated based on reading history.

[1839] Output: Updated reading history, user profile

[1840] Step 5:

[1841] Content Recommendations

[1842] When a user requests new content recommendations, the server analyzes the user's profile, emotional data, and reading history to recommend the most appropriate content. This is done using natural language processing and machine learning algorithms. The recommended content is then sent to the device and displayed to the user.

[1843] Input: User profile, reading history, real-time emotional data

[1844] Data processing: Analyze data using natural language processing and machine learning algorithms to select the most suitable content. The results are then verified using a generative AI model.

[1845] Output: Recommended content

[1846] Specific prompt examples:

[1847] "Recommend MangaY and MangaZ based on the user's preferred genre of SF and the relaxing atmosphere they want to experience while reading."

[1848] 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.

[1849] 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.

[1850] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1851] 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.

[1852] FIG. 9 is a diagram illustrating 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 actions 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.

[1853] 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.

[1854] 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).

[1855] 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.

[1856] 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."

[1857] 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.

[1858] 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).

[1859] 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.

[1860] 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.

[1861] 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.

[1862] 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.

[1863] 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.

[1864] 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.

[1865] 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.

[1866] 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.

[1867] 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.

[1868] 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.

[1869] The following is further disclosed regarding the above embodiment.

[1870] (Claim 1)

[1871] A means for generating a user profile based on the user's preferred genre and preferred reading atmosphere received from the user;

[1872] means for managing a reading history using said user profile;

[1873] A recommendation means including natural language processing and machine learning algorithms that selects optimal manga recommendations based on the user profile and reading history;

[1874] The system includes a means for presenting the recommended manga selected by the recommendation means to the user.

[1875] (Claim 2)

[1876] 10. The system of claim 1,

[1877] The system wherein the user profile is configured to reflect the user's individual interests and psychological tendencies.

[1878] (Claim 3)

[1879] 10. The system of claim 1,

[1880] A system in which the recommendation means operates to promote discovery of new manga.

[1881] "Example 1"

[1882] (Claim 1)

[1883] A means for generating a user profile based on the user's preferred genre and preferred reading atmosphere received from the user;

[1884] means for managing a reading history using said user profile;

[1885] a means for managing reading start information and reading completion information based on the reading history information;

[1886] a recommendation means including natural language processing and machine learning algorithms for selecting optimal recommendation information based on the user profile and reading history;

[1887] a means for presenting the recommended information selected by the recommendation means to a user;

[1888] prompt sentence analysis means for receiving a recommendation request from the user;

[1889] A system including:

[1890] (Claim 2)

[1891] 10. The system of claim 1, wherein the user profile is configured to reflect the user's individual interests and psychological tendencies.

[1892] (Claim 3)

[1893] 10. The system of claim 1, wherein the recommendation means operates to facilitate discovery of new information.

[1894] "Application Example 1"

[1895] (Claim 1)

[1896] A means for generating a user profile based on the user's preferred genre and preferred reading atmosphere received from the user;

[1897] means for managing a reading history using said user profile;

[1898] A recommendation means including natural language processing and machine learning algorithms that selects optimal manga recommendations based on the user profile and reading history;

[1899] a means for presenting the recommended manga selected by the recommendation means to a user;

[1900] means including an application installed on a smartphone;

[1901] a means for processing and storing data using a cloud server;

[1902] A means of optimizing recommendation results using a generative AI model; and

[1903] A system including:

[1904] (Claim 2)

[1905] 10. The system of claim 1, wherein the user profile is configured to reflect the user's individual interests and psychological tendencies.

[1906] (Claim 3)

[1907] 10. The system of claim 1, wherein the recommendation means operates to promote discovery of new manga.

[1908] "Example 2: Combining Emotion Engines"

[1909] (Claim 1)

[1910] A means for generating user information based on the type of preference and desired reading atmosphere received from the user;

[1911] a means for managing a reading history using the user information and emotion data;

[1912] a recommendation means including natural language processing and machine learning algorithms for selecting optimal recommended materials based on the user information and reading history;

[1913] a means for presenting the recommended materials selected by the recommendation means to a user;

[1914] emotion analysis means for analyzing the user's current emotion data in real time;

[1915] updating means for reflecting the analysis result of the emotion analysis means in the user information;

[1916] A system including:

[1917] (Claim 2)

[1918] 10. The system of claim 1, wherein the user information is configured to reflect the user's individual interests and psychological tendencies.

[1919] (Claim 3)

[1920] 10. The system of claim 1, wherein the recommendation means operates to facilitate discovery of new material.

[1921] "Application example 2 when combining emotion engines"

[1922] (Claim 1)

[1923] A means for generating a user profile based on the user's preferred genre and preferred reading atmosphere received from the user;

[1924] means for analyzing emotion data collected via the terminal and including an emotion engine for reflecting the data in a user profile;

[1925] means for managing a reading history using the user profile and emotion data;

[1926] a recommendation means including natural language processing and machine learning algorithms for selecting optimal recommended content based on the user profile and reading history;

[1927] The system includes a means for presenting the recommended content selected by the recommendation means to a user.

[1928] (Claim 2)

[1929] 10. The system of claim 1, wherein the user profile is configured to reflect the user's individual interests and psychological tendencies.

[1930] (Claim 3)

[1931] 10. The system of claim 1, wherein the recommender operates to facilitate discovery of new content. [Explanation of symbols]

[1932] 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 generating a user profile based on the user's preferred genre and preferred reading atmosphere received from the user; means for managing a reading history using said user profile; A recommendation means including natural language processing and machine learning algorithms that selects optimal manga recommendations based on the user profile and reading history; The system includes a means for presenting the recommended manga selected by the recommendation means to the user.

2. 10. The system of claim 1, The system wherein the user profile is configured to reflect the user's individual interests and psychological tendencies.

3. 10. The system of claim 1, A system in which the recommendation means operates to promote discovery of new manga.

Images