System

Abstract

A system is provided.SOLUTION: A system includes image analysis means, reading history analysis means, market evaluation data acquisition means, recommended book selection means, recommendation sentence generation means, reading plan creation means, and user interface means.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] One of the problems that many book lovers face is missing the time or opportunity to read the books they have purchased, resulting in a "pile of books." This problem leads to an increase in unread books, and they are unable to fully enjoy the value of the books they have purchased. To resolve this situation, a system is needed that can efficiently manage books and appropriately select books that should be prioritized for reading and books that should be let go. [Means for solving the problem]

[0005] The present invention is a system that analyzes images of unread books and proposes an optimal reading strategy based on the user's reading habits and market evaluation. Specifically, image analysis means extracts book information, and reading history analysis means analyzes the user's reading habits. Market evaluation data acquisition means calculates the market evaluation of each book, and based on this data, recommended book selection means determines which books should be read and which should be discarded. Furthermore, recommendation generation means generates specific reasons for recommendations, and reading plan creation means presents a reading plan that matches the user's reading speed and lifestyle. A user interface means makes it easy for users to check this information. This efficiently solves the problem of unread books and provides a more fulfilling reading experience.

[0006] "Image analysis means" refers to technology for extracting information such as book title, author name, and ISBN from images of books uploaded by users.

[0007] "Reading history analysis means" refers to techniques and methods for analyzing a user's reading habits and preferences based on their past reading history.

[0008] "Market valuation data acquisition means" refers to techniques and methods for acquiring market valuation data for each book from the Internet or other sources and analyzing that information.

[0009] "Recommended book selection means" refers to techniques and methods for selecting books to read and books to discard based on users' reading habits and market evaluation data.

[0010] The "recommendation generation means" refers to a technique or method for generating a recommendation for a selected book that explains to the user why the book should be read.

[0011] "Reading plan creation means" refers to techniques and methods for creating realistic reading schedules and plans that take into account the user's reading speed and lifestyle.

[0012] "User interface means" means an interface technology or method by which a user can view and interact with recommended book lists, recommendations, reading plans, etc. [Brief explanation of the drawings]

[0013] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0014] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0016] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0017] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0018] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0019] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0021] [First embodiment]

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

[0023] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0024] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0026] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0030] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0033] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0034] The present invention is a system that efficiently manages the unread books that a user has accumulated (so-called "tsundoku") and appropriately selects books that should be read now and books that should be let go. The following describes an embodiment of the present invention.

[0035] Image upload and analysis

[0036] User: Take a photo of an unread book using a smartphone or digital camera.

[0037] On the device: The user takes a photo, saves it in the app, and then clicks the "Upload Image" button in the app to upload the photo to the server.

[0038] Server: Receives the uploaded images and uses an image analysis engine (e.g., a common image analysis API) to extract book information (title, author, ISBN, etc.) from the images.

[0039] Reading history analysis

[0040] Server: Refers to the database of the user's past reading history and analyzes the user's reading habits (favorite genres, book ratings, etc.). This information is passed to the user profile, and the latest trend data reflecting the user's reading preferences is accumulated.

[0041] Obtaining market evaluation

[0042] Server: Based on the extracted book information, the server obtains the latest market evaluation data for each book from the Internet (e.g., online bookstores and review sites), aggregates the obtained data, and assigns a market evaluation score to each book.

[0043] Selection of recommended books

[0044] Server: Evaluates the importance of each book based on the user's reading habits and market evaluation score. Books with high scores are classified as "recommended books" and "books to be discarded" and "books to be discarded" respectively.

[0045] Generating recommendation letters

[0046] Server: Uses generative AI models (e.g., natural language processing techniques) to generate recommendations for selected books, including specific reasons why the book should be read and information specific to the user's interests.

[0047] Creating a Reading Plan

[0048] Server: Creates a realistic reading plan based on the user's reading speed (estimated from past reading history) and daily routine (based on user-provided information). The reading plan includes a schedule for when each book should be completed.

[0049] User Interface

[0050] On-device: Through the app, users can check the "recommended books list" and "list of books to give up." They can also read the "recommendation" and understand the specific reasons for each book's recommendation.

[0051] Users: Start reading according to the in-app reading plan, and when they finish, record their progress in the app to provide feedback for future recommendations.

[0052] Specific examples

[0053] Here's a concrete example: A user takes photos of five unread books and uploads them to the app.

[0054] 1. Device: Upload a photo.

[0055] 2. Server: The image analysis engine extracts book information and obtains Book A (science fiction), Book B (business book), Book C (historical novel), Book D (self-help book), and Book E (fantasy).

[0056] 3. Server: Determine from past reading history that the user prefers science fiction and self-help books.

[0057] 4. Server: Books A and D have high market valuations, so they are recommended books.

[0058] 5. Server: Generate a recommendation: "Book A has an amazing story set against the backdrop of the latest technological trends, and is perfect for you." Similarly, generate a recommendation for Book D.

[0059] 6. Server: Taking into account the user's reading speed and lifestyle, propose a plan to read books A and D within one month.

[0060] 7. Device: The user checks this information through the app and begins reading according to the reading plan.

[0061] The above is a specific implementation of the "Unread Books Clearing Advisor." Through this system, users can efficiently manage their unread books and enjoy a meaningful reading experience.

[0062] The processing flow will be explained below.

[0063] Step 1:

[0064] User: Take a photo of an unread book with your smartphone.

[0065] Step 2:

[0066] On the device: The captured photo is saved in the app, and the user clicks the "Upload image" button within the app.

[0067] Step 3:

[0068] Terminal: Sends uploaded photo data to the server.

[0069] Step 4:

[0070] Server: Sends the received image data to the analysis engine.

[0071] Step 5:

[0072] Server: The image analysis engine extracts text information from the image and detects the book title, author name, ISBN, etc.

[0073] Step 6:

[0074] Server: Organizes the detected book information and stores it in a database.

[0075] Step 7:

[0076] Server: Accesses the database of users' past reading history and analyzes their reading habits.

[0077] Step 8:

[0078] Server: Updates user profiles and stores the latest reading habits data.

[0079] Step 9:

[0080] Server: Based on the extracted book information, obtains market evaluation data for each book from the Internet.

[0081] Step 10:

[0082] Server: Aggregates the acquired market evaluation data and assigns an evaluation score to each book.

[0083] Step 11:

[0084] Server: Based on the user's reading habits and market evaluation scores, selects books to read and books to discard.

[0085] Step 12:

[0086] Server: Generates recommendations for selected books using a generative AI model.

[0087] Step 13:

[0088] Server: Creates a realistic reading plan based on the user's reading speed and lifestyle information.

[0089] Step 14:

[0090] Server: Sends the created reading plan and recommended book information to the terminal.

[0091] Step 15:

[0092] On your device: Display recommended books and testimonials within the app for users to review.

[0093] Step 16:

[0094] On-device: The reading plan is displayed within the app, allowing users to track their progress.

[0095] Step 17:

[0096] User: Start reading the recommended book and track your progress within the app as you read.

[0097] This is the specific process flow of the "Tsundoku Kakuri Advisor." This system allows users to efficiently manage their unread books and have a meaningful reading experience.

[0098] Example 1

[0099] 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."

[0100] Currently, many users have piled up unread books, making it difficult to manage them and determine which books they should prioritize. Furthermore, there are no clear criteria for selecting books to let go, making it difficult to efficiently manage reading.

[0101] 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.

[0102] In this invention, the server includes image analysis means, reading history analysis means, market evaluation data acquisition means, recommended book selection means, recommendation generation means using a generative AI model, reading plan creation means that takes into account reading speed and daily rhythm, and user interface means, allowing users to efficiently manage unread books and appropriately select books to read now and books to let go.

[0103] "Image analysis means" refers to a technical device that analyzes photographs or image data and extracts specific book information (title, author name, ISBN, etc.) from it.

[0104] "Reading history analysis means" refers to a technical device that collects and analyzes a user's past reading history data and derives the user's reading tendencies and preferences.

[0105] The "market evaluation data acquisition means" is a technical device that acquires data on the market evaluation of books from the Internet and assigns an evaluation score to each book.

[0106] The "recommended book selection means" is a technical device that combines the user's reading habits with market evaluation data to select highly important books and classify them into a recommended book list.

[0107] A "means for generating recommendation sentences using a generative AI model" is a technical device that uses a generative AI model (e.g., natural language processing technology) to generate recommendation sentences for selected books.

[0108] The "means for creating a reading plan that takes into account reading speed and lifestyle rhythm" is a technical device that creates a realistic and effective reading plan based on the user's reading speed and lifestyle rhythm.

[0109] "User interface means" means an interface device through which a user interacts with a system and inputs and obtains information.

[0110] The present invention provides a system for efficiently managing a user's pile of unread books and appropriately selecting books that should be read now and books that should be let go. The following describes an embodiment of the present invention.

[0111] Image upload and analysis

[0112] User: Take a photo of an unread book with a smartphone or digital camera. For example, you can take a photo of five unread books at once.

[0113] Device: The user saves the photos they have taken in a dedicated app and clicks the "Upload Image" button in the app to upload the photos to the server.

[0114] Server: Receives uploaded images and uses an image analysis engine (e.g., Google Cloud Vision API) to extract book information (title, author, ISBN, etc.) from the images. The extracted information is stored in a database.

[0115] Reading history analysis

[0116] Server: Refers to the database of the user's past reading history and analyzes the user's reading habits (favorite genres, book ratings, etc.). This information is reflected in the user profile and stored as the latest trend data.

[0117] Obtaining market evaluation

[0118] Server: Based on the book information extracted through image analysis, market evaluation data for each book is obtained from the Internet (e.g., online bookstores and review sites). The obtained data is aggregated and a market evaluation score is assigned to each book.

[0119] Selection of recommended books

[0120] Server: Based on the user's reading habits and market evaluation score, each book is individually rated for importance. Books with high importance are classified into the "recommended books list," while books with low importance are classified into the "not recommended books list."

[0121] Generating recommendation letters

[0122] Server: Uses generative AI models (e.g., natural language processing techniques) to generate recommendations for selected books, including specific reasons why the book should be read and information specific to the user's interests.

[0123] Creating a Reading Plan

[0124] Server: Creates a realistic reading plan based on the user's reading speed (estimated from past reading history) and daily rhythm (based on information registered by the user). The reading plan includes a schedule for when each book should be completed.

[0125] User Interface

[0126] On the device: Through the app, users can check the "recommended books list" and the "letter of books to give up." They can also read the "recommendation" and understand the specific reasons for each book's recommendation.

[0127] Users: Start reading according to the in-app reading plan and record their progress within the app when they finish, providing feedback for future recommendations.

[0128] Specific examples

[0129] Here is a concrete example: If a user takes photos of five unread books and uploads them to the app, the process is as follows:

[0130] 1. User: Take a photo of an unread book with your smartphone and save it in a dedicated app.

[0131] 2. Device: Click the "Upload Image" button in the app to upload the photo to the server.

[0132] 3. Server: The image analysis engine extracts the book information and obtains information on Book A (science fiction), Book B (business book), Book C (historical novel), Book D (self-help book), and Book E (fantasy).

[0133] 4. Server: Determine from past reading history that the user likes science fiction and self-help books.

[0134] 5. Server: Books A and D have high market valuations, so they are recommended books.

[0135] 6. Server: Generates a recommendation using the generative AI model, such as "Book A has an amazing story unfolding against the backdrop of the latest technological trends, making it perfect for you." A recommendation for Book D is also generated in a similar manner.

[0136] 7. Server: Taking into account the user's reading speed and lifestyle, propose a plan to read books A and D within one month.

[0137] 8. Device: The user checks this information within the app and begins reading according to the reading plan.

[0138] Examples of prompts include:

[0139] "Generate the best recommendation based on this user's reading history and market evaluation."

[0140] The above is a specific embodiment of the "Unread Books Clearing Advisor." Through this system, users can efficiently manage their unread books and enjoy a meaningful reading experience.

[0141] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0142] Step 1: Capture and upload an image

[0143] A user takes photos of unread books using a smartphone or digital camera. For example, a user takes photos of five unread books at once.

[0144] Input: Photo data taken by a smartphone or digital camera.

[0145] Output: Photo data saved in the dedicated app.

[0146] Save the photos taken by the device in the app, and then click the "Upload Image" button in the app. This will upload the photo data to the server.

[0147] Input: Saved photo data.

[0148] Output: Photo data uploaded to the server.

[0149] Step 2: Image analysis

[0150] The server receives the uploaded images and sends the image data to an image analysis engine (e.g., Google Cloud Vision API).

[0151] Input: Uploaded photo data.

[0152] Output: Book information in an image (title, author, ISBN, etc.).

[0153] The server uses an image analysis engine to extract book information from the image, which is then stored in a database.

[0154] Input: Analysis results from the image analysis engine.

[0155] Output: Book information stored in a database.

[0156] Step 3: View and analyze your reading history

[0157] The server accesses the user's reading history database and retrieves data such as books read in the past, ratings, and reading frequency.

[0158] Input: A database of the user's past reading history.

[0159] Output: The retrieved reading history data.

[0160] The server analyzes the user's reading habits based on the reading history data it acquires. For example, it identifies the user's favorite genres and highly rated books.

[0161] Input: Reading history data.

[0162] Output: Analyzed reading trend data.

[0163] Step 4: Obtain market valuation data

[0164] Based on the book information extracted by image analysis, the server obtains market evaluation data for each book from the Internet, for example, by collecting data from online bookstores and review sites.

[0165] Input: Book information.

[0166] Output: Collected market valuation data.

[0167] The server aggregates the acquired market evaluation data and assigns a market evaluation score to each book.

[0168] Input: Market valuation data.

[0169] Output: A market rating score given to each book.

[0170] Step 5: Selecting recommended books

[0171] The server rates each book's importance based on the user's reading habits and market rating score.

[0172] Inputs: Reading trend data, market evaluation scores.

[0173] Output: The importance of the rated book.

[0174] The server classifies books with high scores into a "recommended book list" and books with low scores into a "not to be given up book list."

[0175] Input: Book importance.

[0176] Output: "Recommended books list" and "Let go books list".

[0177] Step 6: Generate testimonials

[0178] The server uses generative AI models (e.g., natural language processing techniques) to generate recommendations for the selected books.

[0179] Input: "Recommended book list", generative model.

[0180] Output: The generated recommendation.

[0181] For example, it generates a recommendation such as, "Book A has an amazing story set against the backdrop of the latest technological trends, and is perfect for you."

[0182] Step 7: Create a reading plan

[0183] The server creates a reading plan taking into account the user's reading speed (estimated from past reading history) and daily rhythm (based on information registered by the user).

[0184] Input: Reading speed, lifestyle data.

[0185] Output: A realistic reading plan.

[0186] For example, present a plan to read book A in three weeks and book D in four weeks.

[0187] Step 8: Providing a User Interface

[0188] The device allows the user to check the "recommended books list" and the "let go books list" through the app.

[0189] Input: "Recommended Book List", "Let Go Book List".

[0190] Output: The list displayed on the user's screen.

[0191] The device provides the user with a recommendation for each book within the app, including specific reasons for recommending the book.

[0192] Input: The generated testimonial.

[0193] Output: The testimonial provided to the user.

[0194] Users can start reading according to an in-app reading plan and track their progress as they finish.

[0195] Input: Reading progress information.

[0196] Output: Feedback to receive next recommendation.

[0197] The above is a detailed description of the processing steps in a specific embodiment of the "Unread Book Clearing Advisor."

[0198] (Application example 1)

[0199] 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."

[0200] There is a need for a system that can efficiently manage the unread books that users have accumulated (so-called "tsundoku") and properly select books that they should read now or let go of. It is also necessary to have a system that allows users to visually check these books in a virtual bookstore and understand the specific reasons for the recommendations before purchasing or letting go of them. In addition, users can receive detailed recommendations based on their own reading habits, which will enable them to effectively plan their reading.

[0201] 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.

[0202] In this invention, the server includes image analysis means, reading history analysis means, market evaluation data acquisition means, recommended book selection means, recommendation statement generation means, reading plan creation means, user interface means, virtual exhibition space generation means, and prompt statement generation means, which enable the user to efficiently manage unread books, visually check books in the virtual space, and select recommended books based on specific recommendation reasons and create a reading plan.

[0203] "Image analysis means" refers to a device or software that analyzes image data and extracts book information (title, author name, ISBN, etc.).

[0204] "Reading history analysis means" refers to a device or software that analyzes a user's reading habits based on the user's past reading history.

[0205] The "market evaluation data acquisition means" is a device or software that acquires market evaluation data of books from online bookstores, review sites, and the like on the Internet.

[0206] The "recommended book selection means" is a device or software that selects books that should be read now or that should be discarded based on the user's reading habits and market evaluation score.

[0207] The "recommendation generator" is a device or software that uses natural language processing technology to generate specific reasons for recommending a selected book.

[0208] A "reading plan creation tool" is a device or software that takes into account the user's reading speed and lifestyle and creates a realistic reading schedule.

[0209] "User interface means" means a device or software that provides a screen or method of operation through which a user can interact with the system and view recommended books, discarded books, recommendations, and reading plans.

[0210] A "virtual exhibition space generation means" is a device or software that uses virtual reality (VR) technology to generate an environment in which users can visually check unread books and recommended books in a virtual space.

[0211] A "prompt sentence generation means" is a device or software that generates an input sentence (prompt) for the generative AI model and obtains a specific reason for recommendation.

[0212] This invention is a system that allows users to efficiently manage their piles of unread books (so-called "tsundoku"), appropriately select books that should be read now or that should be let go, and purchase or let go of them while visually checking them in a virtual space. This system has the following main means.

[0213] The system consists of a server and a user's device (such as a smartphone or head-mounted display). Users take photos of unread books using their smartphone or digital camera and upload them through the application.

[0214] The server uses image analysis to extract book information (title, author, ISBN, etc.) from the uploaded image. This image analysis uses a common image analysis API (e.g., pytesseract).

[0215] Next, the server uses a reading history analysis means to refer to the user's past reading history database and analyze the user's reading habits (favorite genres, tendency of books rated, etc.). This information is stored in a user profile.

[0216] Using the market evaluation data acquisition means, the server acquires the latest market evaluation data (e.g., from online bookstores or review sites) for each book from the Internet based on the extracted book information. This data is analyzed, and a market evaluation score is assigned to each book.

[0217] Next, the recommendation book selection method evaluates the importance of each book based on the user's reading habits and market evaluation score. Highly rated books are classified into the "recommended books list," while low-rated books are classified into the "not recommended books list."

[0218] Using the recommendation generation means, the server uses a generative AI model (for example, OpenAI's text generation model) to generate a recommendation for the selected book. This recommendation includes specific reasons why the book should be read and information specific to the user's interests. For example, a prompt for the generative AI model might be, "The user's reading habits are 'science fiction' and 'self-help books.' Why do you recommend 'Book A'? Please explain the specific reasons."

[0219] The server creates a realistic reading plan based on the user's reading speed (estimated from past reading history) and daily rhythm (based on information registered by the user). This plan includes a schedule of when each book should be completed.

[0220] The virtual exhibition space generating means uses virtual reality (VR) technology to generate an environment in which the user can freely walk around the bookstore and visually check unread books and recommended books in the virtual space. The user interface means allows the user to check the "recommended book list" and the "let go book list" and to view detailed recommendations for each.

[0221] Users can start reading according to the in-app reading plan, and when they finish, they can record their progress in the app and provide feedback to receive the next recommendation. This feedback keeps the user's reading habits updated.

[0222] For example, if a user takes photos of five unread books and uploads them to the app, the server uses an image analysis engine to extract information about each book. Based on this book information, market evaluation data is obtained and a market evaluation score is assigned to each book. Based on the user's past reading history, the app determines that the user prefers science fiction and self-help books. Highly rated science fiction book A and self-help book D are added to the recommended books list. Using a generative AI model, a specific recommendation is generated, such as, "Book A has an amazing story unfolding against the backdrop of the latest technological trends, making it perfect for you." Taking into account the user's reading speed and lifestyle, the app then suggests a plan for reading books A and D within one month.

[0223] The above is a concrete implementation of the "Unread Books Clearing Advisor." Through this system, users can efficiently manage their unread books and enjoy a meaningful reading experience.

[0224] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0225] Step 1:

[0226] Users take a photo of an unread book with their smartphone or digital camera, save it in the app, and then click the "Upload Image" button to upload the photo to the server.

[0227] Input: Photo of an unread book

[0228] Output: Uploaded photo

[0229] Step 2:

[0230] The server uses image analysis to extract book information (title, author, ISBN, etc.) from the uploaded photo. For image analysis, it uses a common image analysis API (e.g., pytesseract).

[0231] Input: Uploaded photo

[0232] Output: Book information (title, author, ISBN, etc.)

[0233] Step 3:

[0234] The server uses a reading history analysis means to refer to the user's past reading history database and analyze the user's reading tendencies (favorite genres, tendency of books rated, etc.).

[0235] Input: User's past reading history

[0236] Output: User's reading habits

[0237] Step 4:

[0238] The server uses the market evaluation data acquisition means to acquire the latest market evaluation data for each book from the Internet based on the extracted book information, analyzes the acquired data, and assigns a market evaluation score to each book.

[0239] Input: Book information (title, author, ISBN, etc.)

[0240] Output: Market rating score for the book

[0241] Step 5:

[0242] The server uses a recommended book selection method to evaluate the importance of each book based on the user's reading habits and market evaluation score. Highly rated books are classified into a "recommended book list" and low-rated books are classified into a "not-recommended book list."

[0243] Input: User's reading habits, market evaluation score

[0244] Output: Recommended books list, To-be-given books list

[0245] Step 6:

[0246] The server uses the recommendation generator to generate a recommendation for the selected book using a generative AI model, the recommendation including specific reasons why the book should be read and information specific to the user's interests.

[0247] Input: Recommended book list, user's reading habits

[0248] Output: Recommendation (e.g., "Book A is perfect for you because it tells an amazing story set against the backdrop of the latest technological trends.")

[0249] Step 7:

[0250] The server uses a reading plan generator to create a realistic reading schedule that takes into account the user's reading speed and daily routine, including a timeline for when each book should be completed.

[0251] Input: User's reading speed, daily routine, recommended book list

[0252] Output: Reading plan

[0253] Step 8:

[0254] The server uses a virtual exhibition space generating means and virtual reality (VR) technology to generate an environment in which the user can freely walk around the bookstore and visually check unread books and recommended books in the virtual space.

[0255] Input: Recommended books list, list of books to give up

[0256] Output: Virtual exhibition space

[0257] Step 9:

[0258] Through the user interface, the user can check the "recommended book list" and the "let go book list" and view detailed recommendations. Furthermore, the user can start reading according to the reading plan, and when they finish reading, the progress is recorded in the app, providing feedback for the next recommendation.

[0259] Input: Virtual exhibition space, recommendations, reading plan

[0260] Output: Reading progress feedback

[0261] 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.

[0262] The present invention is a system that effectively manages a user's unread books and proposes an optimal reading strategy taking into account reading habits and emotional state. Hereinafter, embodiments of the present invention will be described.

[0263] Image upload and analysis

[0264] User: Take a photo of an unread book with your smartphone.

[0265] On the device: The user takes a photo, saves it in the app, and then clicks the "Upload Image" button in the app to upload the photo to the server.

[0266] Server: Sends the received image data to the image analysis engine.

[0267] Server: The image analysis engine extracts text information from the image, detects the book title, author name, ISBN, etc., and stores this information in a database.

[0268] Reading history analysis

[0269] Server: Refers to the database of the user's past reading history and analyzes the user's reading habits (favorite genres, book ratings, etc.). It also updates the user profile and stores the latest reading habits data.

[0270] Obtaining market evaluation

[0271] Server: Based on the extracted book information, obtains market evaluation data for each book from the Internet.

[0272] Server: Aggregates the acquired market evaluation data, assigns an evaluation score to each book, and creates a list of recommended books and a list of books to be discarded based on that information.

[0273] Emotion recognition by emotion engine

[0274] On-device: Emotional data is collected using methods such as facial recognition and voice analysis to help the app understand the user's emotional state.

[0275] Server: Sends the collected emotion data to the emotion engine to analyze the user's current emotional state.

[0276] Selection of recommended books

[0277] Server: Based on the user's reading habits, emotional state, and market evaluation score, the server classifies books that should be read now into a recommended book list.

[0278] Server: By selecting recommended books based on emotional state, users can read books that suit their mood at the time.

[0279] Generating recommendation letters

[0280] Server: Uses a generative AI model to generate a recommendation for the selected book, taking into account the user's emotional state and providing specific reasons why the book should be read.

[0281] Creating a Reading Plan

[0282] Server: Creates a realistic reading plan based on the user's reading speed and lifestyle information. This plan includes a schedule for when each book should be completed.

[0283] User Interface

[0284] On your device: Through the app, users can view the "recommended books list" and "let go books list," as well as read the recommendations and understand the specific reasons for each book's recommendation.

[0285] Users: Start reading according to the in-app reading plan, and when they finish, record their progress in the app and receive next recommendations.

[0286] Specific examples

[0287] Here's a concrete example: If a user takes photos of five unread books and uploads them to the app, the following process will occur:

[0288] 1. Device: The user uploads five photos.

[0289] 2. Server: The image analysis engine extracts book information and obtains Book A (science fiction), Book B (business book), Book C (historical novel), Book D (self-help book), and Book E (fantasy).

[0290] 3. Server: Analyzes the user's past reading history and finds that they like science fiction and self-help books.

[0291] 4. Server: Books A and D have high market ratings, so they are classified into the recommended books list.

[0292] 5. Device: Recognizes the user's emotions and uses the emotion engine to analyze that the current emotion is fatigue.

[0293] 6. Server: Recommend book D, which has relaxing content that suits the tired state.

[0294] 7. Server: Generate a recommendation, such as, "This self-help book contains many specific relaxation techniques and is perfect for my current tired state."

[0295] 8. Server: Taking into account the user's reading speed and lifestyle, propose a plan to read books A and D within one month.

[0296] 9. Device: The user sees the recommended book list and reading plan and begins reading.

[0297] The above is a specific implementation of the "Unread Books Clearing Advisor" that combines an emotion engine. This system manages and recommends unread books taking into account the user's emotional state, providing a meaningful reading experience.

[0298] The processing flow will be explained below.

[0299] Step 1:

[0300] User: Take a photo of an unread book with your smartphone.

[0301] Step 2:

[0302] On your device: Save the photo you took in the app and click the "Upload image" button in the app.

[0303] Step 3:

[0304] Terminal: Sends uploaded photo data to the server.

[0305] Step 4:

[0306] Server: Sends the received image data to the image analysis engine.

[0307] Step 5:

[0308] Server: The image analysis engine extracts text information from the image and detects the book title, author name, ISBN, etc.

[0309] Step 6:

[0310] Server: Organizes the detected book information and stores it in a database.

[0311] Step 7:

[0312] Server: Accesses the database of users' past reading history and analyzes their reading habits.

[0313] Step 8:

[0314] Server: Updates user profiles and stores the latest reading habits data.

[0315] Step 9:

[0316] Server: Based on the extracted book information, obtains market evaluation data for each book from the Internet.

[0317] Step 10:

[0318] Server: Aggregates the acquired market evaluation data and assigns an evaluation score to each book.

[0319] Step 11:

[0320] On-device: The app uses facial recognition and voice analysis to collect emotional data to understand the user's emotional state.

[0321] Step 12:

[0322] Terminal: Sends collected emotion data to the server.

[0323] Step 13:

[0324] Server: The emotion engine analyzes the received emotion data and determines the user's current emotional state.

[0325] Step 14:

[0326] Server: Categorizes books to be read into a recommended book list based on the user's reading habits, emotional state, and rating scores.

[0327] Step 15:

[0328] Server: Uses a generative AI model to generate recommendations for selected books, including specific reasons that take into account the user's emotional state.

[0329] Step 16:

[0330] Server: Creates a realistic reading plan based on the user's reading speed and lifestyle information.

[0331] Step 17:

[0332] Server: Sends the created reading plan and recommended book information to the user's terminal.

[0333] Step 18:

[0334] On your device: Display recommended books and testimonials within the app for users to review.

[0335] Step 19:

[0336] On-device: The reading plan is displayed within the app, allowing users to track their progress.

[0337] Step 20:

[0338] User: Start reading the recommended book and track your progress within the app as you read.

[0339] Example 2

[0340] 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."

[0341] In modern society, many users have a large number of unread books, and find it difficult to manage them and progress in their reading. Furthermore, it is difficult to select appropriate books based on the user's emotional state, which can reduce the quality of the reading experience. There is a need to solve these problems and provide a more effective and efficient reading management and recommendation system.

[0342] 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.

[0343] In this invention, the server includes image analysis means, reading history analysis means, market evaluation data acquisition means, emotion data collection means, emotion state analysis means, recommended book selection means, recommendation statement generation means, reading plan creation means, and user interface means, which enable effective management of unread books for the user and further enable appropriate book recommendations taking into account the user's emotional state.

[0344] "Image analysis means" refers to a means of extracting text information from images uploaded by users and obtaining data such as book titles, author names, and ISBNs.

[0345] The "reading history analysis means" is a means for analyzing a user's past reading history data and identifying reading tendencies and preferred genres.

[0346] The "market evaluation data acquisition means" is a means for collecting market evaluation data of books from the Internet and assigning an evaluation score to each book.

[0347] "Emotional data collection means" refers to a means of collecting emotional data through facial recognition and voice analysis of the user.

[0348] The "emotional state analysis means" is a means for analyzing collected emotional data and identifying the user's current emotional state.

[0349] The "recommended book selection method" is a method for selecting appropriate books based on the user's reading habits, emotional state, and market evaluation score.

[0350] The "recommendation generation means" is a means for creating a recommendation for a selected book using a generative AI model.

[0351] The "reading plan creation tool" is a tool that creates a realistic reading plan based on the user's reading speed and lifestyle information.

[0352] "User interface means" means by which a user interacts with the system and views recommended book lists and reading plans.

[0353] The present invention provides a system that effectively manages a user's unread books and proposes an optimal reading strategy by taking into account their reading habits and emotional state. The system includes image analysis means, reading history analysis means, market evaluation data acquisition means, emotional data collection means, emotional state analysis means, recommended book selection means, recommendation message generation means, reading plan creation means, and user interface means. This allows for effective and efficient management of a user's unread books and the provision of recommended books.

[0354] Image upload and analysis

[0355] User:

[0356] Take a photo of an unread book with your smartphone. Specifically, open the camera app, center the book cover, and press the capture button.

[0357] Device:

[0358] Save the photos you take in the app, then click the "Upload Image" button in the app to upload the photos to the server. The device will then send the image data to the server.

[0359] server:

[0360] The received image data is sent to an image analysis engine, specifically using OCR technology, which extracts text information from the image (such as the book title, author name, ISBN, etc.) and stores that information in a database.

[0361] Reading history analysis

[0362] server:

[0363] Retrieve the user's past reading history from the database. Analyze past ratings, genres of books read, favorite authors, etc. Update the user profile if new trends are found.

[0364] Obtaining market evaluation

[0365] server:

[0366] Based on the extracted book information, market evaluation data is obtained from review sites and book databases (e.g., major bibliographic information sites, online bookstores) for each book. The obtained data is aggregated and an evaluation score is assigned to each book.

[0367] Emotion recognition by emotion engine

[0368] Device:

[0369] To recognize the user's emotional state, the system uses a smartphone camera for facial recognition and a voice assistant to collect voice data, which is then sent to a server.

[0370] server:

[0371] The received emotional data is analyzed by the emotion analysis engine to determine the current emotional state (e.g., tired, relaxed, stressed).

[0372] Selection of recommended books

[0373] server:

[0374] The system comprehensively assesses the user's reading habits, current emotional state, and market evaluation score to add the best books to the recommended book list, with a particular focus on books that match the user's current emotional state.

[0375] Generating recommendation letters

[0376] server:

[0377] Based on the selected book information, a prompt is input into a generative AI model (e.g., GPT-4) to generate a recommendation. Example prompt: "The user is currently feeling tired. This self-help book contains many specific relaxation techniques and is perfect for this tired state."

[0378] Creating a Reading Plan

[0379] server:

[0380] Based on the user's reading speed and lifestyle information, a realistic reading plan is created, including the estimated completion date for each book.

[0381] User Interface

[0382] Device:

[0383] The app displays a recommended book list and reading plan to users, and after checking the displayed content, users can start reading according to the plan.

[0384] Adding specific examples

[0385] For example, if a user takes photos of five unread books and uploads them to the app, the process would look like this:

[0386] 1. Device: The user uploads five photos.

[0387] 2. Server: The image analysis engine extracts book information and obtains Book A (science fiction), Book B (business book), Book C (historical novel), Book D (self-help book), and Book E (fantasy).

[0388] 3. Server: Analyzes the user's past reading history and finds that they like science fiction and self-help books.

[0389] 4. Server: Books A and D have high market ratings, so they are classified into the recommended books list.

[0390] 5. Device: Recognizes the user's emotions and uses the emotion engine to analyze that the current emotion is fatigue.

[0391] 6. Server: Recommend book D, which has relaxing content that suits the tired state.

[0392] 7. Server: Generate a recommendation, such as, "This self-help book contains many specific relaxation techniques and is perfect for my current tired state."

[0393] 8. Server: Taking into account the user's reading speed and lifestyle, propose a plan to read books A and D within one month.

[0394] 9. Device: The user sees the recommended book list and reading plan and begins reading.

[0395] The above is a specific implementation of the "Unread Books Clearing Advisor" that combines an emotion engine. This system manages and recommends unread books taking into account the user's emotional state, providing a meaningful reading experience.

[0396] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0397] Step 1:

[0398] User: Take a photo of an unread book with your smartphone.

[0399] Input: An image of a book taken with a smartphone camera.

[0400] Output: Book image files.

[0401] Specific actions: Launch the camera app, center the book cover, and press the capture button.

[0402] Step 2:

[0403] Device: Save the photo in the app and upload it to the server.

[0404] Input: Book image files.

[0405] Output: Sending image data to the server.

[0406] Specific operation: The captured photo is saved in the app, and the user clicks the "Upload image" button in the app. The device sends the image data to the server.

[0407] Step 3:

[0408] Server: Analyzes the image, extracts book information, and stores it in a database.

[0409] Input: Uploaded book image.

[0410] Output: Book information (title, author, ISBN) stored in a database.

[0411] Specific operation: The received image data is analyzed using OCR technology to extract text information from the image, detecting the book title, author name, and ISBN, and storing that information in a database.

[0412] Step 4:

[0413] Server: Refers to the user's reading history and analyzes reading trends.

[0414] Input: The user's reading history stored in a database.

[0415] Output: An updated profile of the user's reading habits as a result of the analysis.

[0416] What it does: It analyzes past reading history, attributes such as ratings, genres, and authors to identify users' reading habits, and updates their user profile if new habits are found.

[0417] Step 5:

[0418] Server: Collects book market evaluation data from the Internet.

[0419] Input: Extracted book information (title, author, ISBN).

[0420] Output: Book information with rating scores.

[0421] Specific operation: Based on book information, evaluation data is obtained from review sites and online bookstores, and evaluation scores are compiled and assigned to each book.

[0422] Step 6:

[0423] Terminal: Collects user emotional data.

[0424] Input: User's facial recognition image data and voice data.

[0425] Output: Sending emotion data to the server.

[0426] Specific operation: Facial recognition is performed using the smartphone camera, and voice recordings are collected using the voice assistant. The collected data is then sent to a server.

[0427] Step 7:

[0428] Server: Analyzes the emotional data to determine the current emotional state.

[0429] Input: Collected emotion data (face recognition images, audio data).

[0430] Output: Current emotional state judgment result.

[0431] What it does: The emotion analysis engine analyzes facial recognition data and voice data to determine the current emotional state.

[0432] Step 8:

[0433] Server: Selects recommended books based on reading habits, emotional state, and market evaluation.

[0434] Input: Reading habits profile, emotional state assessment results, market evaluation data.

[0435] Output: A list of recommended books.

[0436] Specific operation: Comprehensively evaluate the user's reading habits, current emotional state, and market evaluation score, select the most suitable books, and add them to the recommended book list.

[0437] Step 9:

[0438] Server: Generates recommendations for selected books using a generative AI model.

[0439] Input: Recommended book list.

[0440] Output: The generated recommendation.

[0441] Specific behavior: A prompt is input into a generative AI model (e.g., GPT-4) to generate a recommendation. Example prompt: "The user is currently feeling tired. This self-help book contains many specific relaxation techniques and is perfect for this tired state."

[0442] Step 10:

[0443] Server: Creates a reading plan for the user.

[0444] Input: User's reading speed, lifestyle information, recommended book list.

[0445] Output: Reading plan.

[0446] What it does: Create a realistic reading plan based on the user's reading speed and lifestyle information, including estimated completion dates for each book.

[0447] Step 11:

[0448] Device: Provides users with recommended book lists and reading plans.

[0449] Input: Recommended book list, reading plan.

[0450] Output: Information displayed by the user interface.

[0451] Specific operation: Display recommended book lists and reading plans to users through the app screen, allowing users to start reading based on them.

[0452] (Application example 2)

[0453] 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."

[0454] Conventional reading recommendation systems recommend books based solely on reading history and market evaluations, without taking into account the user's emotional state or usage environment, making it difficult for users to read the right book at the optimal time. In addition, users of smart devices need a system that can maximize their convenience.

[0455] 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.

[0456] In this invention, the server includes image analysis means, reading history analysis means, market evaluation data acquisition means, emotion recognition means, recommended book selection means, recommendation statement generation means, reading plan creation means, and smart device interface means, thereby enabling accurate book recommendations and the creation of reading plans that take into account the user's emotional state and usage environment.

[0457] 1. "Image analysis means" refers to a device or program that extracts text information from captured image data and detects book titles, author names, ISBNs, etc.

[0458] 2. "Reading history analysis means" refers to a device or program that refers to a user's past reading history and analyzes their reading habits.

[0459] 3. "Market evaluation data acquisition means" refers to a device or program that acquires and compiles market evaluation data for each book from the Internet.

[0460] 4. "Emotion recognition means" means a device or program that recognizes a user's emotional state using methods such as facial recognition or voice analysis.

[0461] 5. "Recommended book selection means" refers to a device or program that selects books to read based on a user's reading habits, emotional state, and market evaluation data.

[0462] 6. "Recommendation generation means" means a device or program consisting of a generative AI model that generates recommendations for selected books.

[0463] 7. "Reading plan creation means" means a device or program that creates a realistic reading plan based on the user's reading speed and lifestyle information.

[0464] 8. "Smart device interface means" means a device or program that provides information to a user through a device such as a smartphone or smart glasses.

[0465] This invention is a system that utilizes a smart device installed in an autonomous vehicle to effectively manage a user's unread books and propose an optimal reading strategy taking into account reading habits and emotional state. The following describes an embodiment of the invention.

[0466] Hardware and software used

[0467] Hardware:

[0468] Smart glasses and smartphones

[0469] Autonomous vehicle computer systems

[0470] software:

[0471] Python

[0472] OpenCV (image processing library)

[0473] FacialRecognition (emotion recognition library)

[0474] OCREngine (OCR analysis library)

[0475] BookRecommender (recommendation algorithm)

[0476] RecommendationModel (generative AI model)

[0477] System Operation

[0478] Image upload and analysis

[0479] Users take a photo of an unread book with their smartphone. The device's smart glasses store the photo and upload it to the autonomous vehicle's computer system. The server then uses image analysis tools to extract text information from the image, such as the book's title, author, and ISBN, and stores that information in a database.

[0480] Reading history analysis

[0481] The server uses the reading history analysis means to refer to the database of the user's past reading history and analyze the reading habits, and this information is also stored in the database.

[0482] Obtaining market evaluation

[0483] The server uses the market evaluation data acquisition means to acquire market evaluation data for each book from the Internet based on the extracted book information. The acquired market evaluation data is aggregated and an evaluation score is assigned to each book.

[0484] emotion recognition means

[0485] The smart glasses on the device collect the user's facial expression data and send it to a server, which then analyzes this data using emotion recognition means to determine the user's current emotional state.

[0486] Selection of recommended books

[0487] The server uses a recommended book selection means to select books to read now based on reading habits, emotional state, and market evaluation data, and the selected book information is stored in a database.

[0488] Generating recommendation letters

[0489] The server uses the generative AI model to generate recommendations for the selected books, which are then displayed on the smart glasses.

[0490] Creating a Reading Plan

[0491] The server uses the reading plan creation means to create a realistic reading plan that takes into account the user's reading speed and travel time.

[0492] Specific examples and prompts for generative AI models

[0493] Specific examples

[0494] For example, if a user takes photos of five unread books with their smartphone while riding in a self-driving vehicle and uploads them to the vehicle's system, the process will proceed as follows: If the smart glasses analyze the user's facial expression and determine that the user's emotional state is "tired," a recommendation will be generated and displayed, saying, "This self-help book contains many specific relaxation techniques and is perfect for your current tired state."

[0495] Prompt Sentence Examples

[0496] Prompt statement:

[0497] "Generate a recommendation for a self-help book that is ideal for when the user is in a tired emotional state. The book title is "A Relaxing Life" and the author is "Taro Yamada.""

[0498] This provides an environment where users can read self-help books, which is ideal when they are tired.

[0499] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0500] Step 1:

[0501] The user takes a photo of an unread book with their smartphone, and the image data is input into the device.

[0502] Step 2:

[0503] The device stores the captured images and uploads them to the autonomous vehicle's system via smart glasses.

[0504] Input: Image of unread book

[0505] Data processing: Image saving and uploading

[0506] Output: Image data to the server

[0507] Step 3:

[0508] The server uses image analysis to extract text information from the uploaded image, specifically detecting information such as the book title, author name, and ISBN.

[0509] Input: Image data

[0510] Data calculation: OCR analysis

[0511] Output: Book information (title, author, ISBN)

[0512] Step 4:

[0513] The server stores the extracted book information in a database, which is used for subsequent analysis and evaluation.

[0514] Input: Book information

[0515] Data processing: information storage

[0516] Output: Book information in the database

[0517] Step 5:

[0518] The server uses a reading history analysis means to refer to the user's past reading history data and analyze their reading habits, which is then used to recommend new books.

[0519] Input: Reading history database

[0520] Data Computing: Reading Trend Analysis

[0521] Output: Reading habits data

[0522] Step 6:

[0523] The server uses the market evaluation data acquisition means to acquire market evaluation data for each book from the Internet, specifically, to collect reviews and evaluation scores for the book.

[0524] Input: Book information

[0525] Data calculation: Data acquisition from the Internet

[0526] Output: Market valuation data

[0527] Step 7:

[0528] The server aggregates the acquired market evaluation data and assigns each book an evaluation score, which is used to select recommended books.

[0529] Input: Market valuation data

[0530] Data calculation: Score assignment

[0531] Output: Evaluation score

[0532] Step 8:

[0533] The smart glasses on the device collect and transmit facial expression data from the user to a server, which is used to analyze the user's emotional state.

[0534] Input: facial expression data

[0535] Data Processing: Data Collection and Transmission

[0536] Output: Facial expression data to the server

[0537] Step 9:

[0538] The server analyzes the collected facial expression data using emotion recognition means to determine the user's current emotional state.

[0539] Input: facial expression data

[0540] Data Computing: Emotion Recognition

[0541] Output: Emotional state

[0542] Step 10:

[0543] The server uses a recommended book selection means to select books to read now based on reading habits, emotional state, and market evaluation data.

[0544] Input: Reading habits data, emotional state, evaluation score

[0545] Data calculation: Book selection

[0546] Output: Recommended book list

[0547] Step 11:

[0548] The server uses a generative AI model to generate a recommendation for the selected book, for example, using prompts to provide specific reasons for the recommendation.

[0549] Input: Recommended book list, emotional state

[0550] Data calculation: recommendation generation

[0551] Output: Recommendation

[0552] Step 12:

[0553] The server uses the reading plan creation means to create a realistic reading plan that takes into account the user's reading speed and usage environment (such as travel time).

[0554] Input: Reading speed, usage environment

[0555] Data calculation: Reading plan creation

[0556] Output: Reading plan

[0557] Step 13:

[0558] Users can view the recommended book list, recommendations, and reading plan through a smart device interface, such as smart glasses or a smartphone.

[0559] Input: Recommended book list, recommendation, reading plan

[0560] Data processing: Information display

[0561] Output: User confirmation and execution

[0562] 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.

[0563] 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.

[0564] 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.

[0565] [Second embodiment]

[0566] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0567] 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.

[0568] 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).

[0569] 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.

[0570] 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.

[0571] 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).

[0572] 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.

[0573] 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.

[0574] 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.

[0575] 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.

[0576] 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.

[0577] 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."

[0578] The present invention is a system that efficiently manages the unread books that a user has accumulated (so-called "tsundoku") and appropriately selects books that should be read now and books that should be let go. The following describes an embodiment of the present invention.

[0579] Image upload and analysis

[0580] User: Take a photo of an unread book using a smartphone or digital camera.

[0581] On the device: The user takes a photo, saves it in the app, and then clicks the "Upload Image" button in the app to upload the photo to the server.

[0582] Server: Receives the uploaded images and uses an image analysis engine (e.g., a common image analysis API) to extract book information (title, author, ISBN, etc.) from the images.

[0583] Reading history analysis

[0584] Server: Refers to the database of the user's past reading history and analyzes the user's reading habits (favorite genres, book ratings, etc.). This information is passed to the user profile, and the latest trend data reflecting the user's reading preferences is accumulated.

[0585] Obtaining market evaluation

[0586] Server: Based on the extracted book information, the server obtains the latest market evaluation data for each book from the Internet (e.g., online bookstores and review sites), aggregates the obtained data, and assigns a market evaluation score to each book.

[0587] Selection of recommended books

[0588] Server: Evaluates the importance of each book based on the user's reading habits and market evaluation score. Books with high scores are classified as "recommended books" and "books to be discarded" and "books to be discarded" respectively.

[0589] Generating recommendation letters

[0590] Server: Uses generative AI models (e.g., natural language processing techniques) to generate recommendations for selected books, including specific reasons why the book should be read and information specific to the user's interests.

[0591] Creating a Reading Plan

[0592] Server: Creates a realistic reading plan based on the user's reading speed (estimated from past reading history) and daily routine (based on user-provided information). The reading plan includes a schedule for when each book should be completed.

[0593] User Interface

[0594] On-device: Through the app, users can check the "recommended books list" and "list of books to give up." They can also read the "recommendation" and understand the specific reasons for each book's recommendation.

[0595] Users: Start reading according to the in-app reading plan, and when they finish, record their progress in the app to provide feedback for future recommendations.

[0596] Specific examples

[0597] Here's a concrete example: A user takes photos of five unread books and uploads them to the app.

[0598] 1. Device: Upload a photo.

[0599] 2. Server: The image analysis engine extracts book information and obtains Book A (science fiction), Book B (business book), Book C (historical novel), Book D (self-help book), and Book E (fantasy).

[0600] 3. Server: Determine from past reading history that the user prefers science fiction and self-help books.

[0601] 4. Server: Books A and D have high market valuations, so they are recommended books.

[0602] 5. Server: Generate a recommendation: "Book A has an amazing story set against the backdrop of the latest technological trends, and is perfect for you." Similarly, generate a recommendation for Book D.

[0603] 6. Server: Taking into account the user's reading speed and lifestyle, propose a plan to read books A and D within one month.

[0604] 7. Device: The user checks this information through the app and begins reading according to the reading plan.

[0605] The above is a specific implementation of the "Unread Books Clearing Advisor." Through this system, users can efficiently manage their unread books and enjoy a meaningful reading experience.

[0606] The processing flow will be explained below.

[0607] Step 1:

[0608] User: Take a photo of an unread book with your smartphone.

[0609] Step 2:

[0610] On the device: The captured photo is saved in the app, and the user clicks the "Upload image" button within the app.

[0611] Step 3:

[0612] Terminal: Sends uploaded photo data to the server.

[0613] Step 4:

[0614] Server: Sends the received image data to the analysis engine.

[0615] Step 5:

[0616] Server: The image analysis engine extracts text information from the image and detects the book title, author name, ISBN, etc.

[0617] Step 6:

[0618] Server: Organizes the detected book information and stores it in a database.

[0619] Step 7:

[0620] Server: Accesses the database of users' past reading history and analyzes their reading habits.

[0621] Step 8:

[0622] Server: Updates user profiles and stores the latest reading habits data.

[0623] Step 9:

[0624] Server: Based on the extracted book information, obtains market evaluation data for each book from the Internet.

[0625] Step 10:

[0626] Server: Aggregates the acquired market evaluation data and assigns an evaluation score to each book.

[0627] Step 11:

[0628] Server: Based on the user's reading habits and market evaluation scores, selects books to read and books to discard.

[0629] Step 12:

[0630] Server: Generates recommendations for selected books using a generative AI model.

[0631] Step 13:

[0632] Server: Creates a realistic reading plan based on the user's reading speed and lifestyle information.

[0633] Step 14:

[0634] Server: Sends the created reading plan and recommended book information to the terminal.

[0635] Step 15:

[0636] On your device: Display recommended books and testimonials within the app for users to review.

[0637] Step 16:

[0638] On-device: The reading plan is displayed within the app, allowing users to track their progress.

[0639] Step 17:

[0640] User: Start reading the recommended book and track your progress within the app as you read.

[0641] This is the specific process flow of the "Tsundoku Kakuri Advisor." This system allows users to efficiently manage their unread books and have a meaningful reading experience.

[0642] Example 1

[0643] 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."

[0644] Currently, many users have piled up unread books, making it difficult to manage them and determine which books they should prioritize. Furthermore, there are no clear criteria for selecting books to let go, making it difficult to efficiently manage reading.

[0645] 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.

[0646] In this invention, the server includes image analysis means, reading history analysis means, market evaluation data acquisition means, recommended book selection means, recommendation generation means using a generative AI model, reading plan creation means that takes into account reading speed and daily rhythm, and user interface means, allowing users to efficiently manage unread books and appropriately select books to read now and books to let go.

[0647] "Image analysis means" refers to a technical device that analyzes photographs or image data and extracts specific book information (title, author name, ISBN, etc.) from it.

[0648] "Reading history analysis means" refers to a technical device that collects and analyzes a user's past reading history data and derives the user's reading tendencies and preferences.

[0649] The "market evaluation data acquisition means" is a technical device that acquires data on the market evaluation of books from the Internet and assigns an evaluation score to each book.

[0650] The "recommended book selection means" is a technical device that combines the user's reading habits with market evaluation data to select highly important books and classify them into a recommended book list.

[0651] A "means for generating recommendation sentences using a generative AI model" is a technical device that uses a generative AI model (e.g., natural language processing technology) to generate recommendation sentences for selected books.

[0652] The "means for creating a reading plan that takes into account reading speed and lifestyle rhythm" is a technical device that creates a realistic and effective reading plan based on the user's reading speed and lifestyle rhythm.

[0653] "User interface means" means an interface device through which a user interacts with a system and inputs and obtains information.

[0654] The present invention provides a system for efficiently managing a user's pile of unread books and appropriately selecting books that should be read now and books that should be let go. The following describes an embodiment of the present invention.

[0655] Image upload and analysis

[0656] User: Take a photo of an unread book with a smartphone or digital camera. For example, you can take a photo of five unread books at once.

[0657] Device: The user saves the photos they have taken in a dedicated app and clicks the "Upload Image" button in the app to upload the photos to the server.

[0658] Server: Receives uploaded images and uses an image analysis engine (e.g., Google Cloud Vision API) to extract book information (title, author, ISBN, etc.) from the images. The extracted information is stored in a database.

[0659] Reading history analysis

[0660] Server: Refers to the database of the user's past reading history and analyzes the user's reading habits (favorite genres, book ratings, etc.). This information is reflected in the user profile and stored as the latest trend data.

[0661] Obtaining market evaluation

[0662] Server: Based on the book information extracted through image analysis, market evaluation data for each book is obtained from the Internet (e.g., online bookstores and review sites). The obtained data is aggregated and a market evaluation score is assigned to each book.

[0663] Selection of recommended books

[0664] Server: Based on the user's reading habits and market evaluation score, each book is individually rated for importance. Books with high importance are classified into the "recommended books list," while books with low importance are classified into the "not recommended books list."

[0665] Generating recommendation letters

[0666] Server: Uses generative AI models (e.g., natural language processing techniques) to generate recommendations for selected books, including specific reasons why the book should be read and information specific to the user's interests.

[0667] Creating a Reading Plan

[0668] Server: Creates a realistic reading plan based on the user's reading speed (estimated from past reading history) and daily rhythm (based on information registered by the user). The reading plan includes a schedule for when each book should be completed.

[0669] User Interface

[0670] On the device: Through the app, users can check the "recommended books list" and the "letter of books to give up." They can also read the "recommendation" and understand the specific reasons for each book's recommendation.

[0671] Users: Start reading according to the in-app reading plan and record their progress within the app when they finish, providing feedback for future recommendations.

[0672] Specific examples

[0673] Here is a concrete example: If a user takes photos of five unread books and uploads them to the app, the process is as follows:

[0674] 1. User: Take a photo of an unread book with your smartphone and save it in a dedicated app.

[0675] 2. Device: Click the "Upload Image" button in the app to upload the photo to the server.

[0676] 3. Server: The image analysis engine extracts the book information and obtains information on Book A (science fiction), Book B (business book), Book C (historical novel), Book D (self-help book), and Book E (fantasy).

[0677] 4. Server: Determine from past reading history that the user likes science fiction and self-help books.

[0678] 5. Server: Books A and D have high market valuations, so they are recommended books.

[0679] 6. Server: Generates a recommendation using the generative AI model, such as "Book A has an amazing story unfolding against the backdrop of the latest technological trends, making it perfect for you." A recommendation for Book D is also generated in a similar manner.

[0680] 7. Server: Taking into account the user's reading speed and lifestyle, propose a plan to read books A and D within one month.

[0681] 8. Device: The user checks this information within the app and begins reading according to the reading plan.

[0682] Examples of prompts include:

[0683] "Generate the best recommendation based on this user's reading history and market evaluation."

[0684] The above is a specific embodiment of the "Unread Books Clearing Advisor." Through this system, users can efficiently manage their unread books and enjoy a meaningful reading experience.

[0685] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0686] Step 1: Capture and upload an image

[0687] A user takes photos of unread books using a smartphone or digital camera. For example, a user takes photos of five unread books at once.

[0688] Input: Photo data taken by a smartphone or digital camera.

[0689] Output: Photo data saved in the dedicated app.

[0690] Save the photos taken by the device in the app, and then click the "Upload Image" button in the app. This will upload the photo data to the server.

[0691] Input: Saved photo data.

[0692] Output: Photo data uploaded to the server.

[0693] Step 2: Image analysis

[0694] The server receives the uploaded images and sends the image data to an image analysis engine (e.g., Google Cloud Vision API).

[0695] Input: Uploaded photo data.

[0696] Output: Book information in an image (title, author, ISBN, etc.).

[0697] The server uses an image analysis engine to extract book information from the image, which is then stored in a database.

[0698] Input: Analysis results from the image analysis engine.

[0699] Output: Book information stored in a database.

[0700] Step 3: View and analyze your reading history

[0701] The server accesses the user's reading history database and retrieves data such as books read in the past, ratings, and reading frequency.

[0702] Input: A database of the user's past reading history.

[0703] Output: The retrieved reading history data.

[0704] The server analyzes the user's reading habits based on the reading history data it acquires. For example, it identifies the user's favorite genres and highly rated books.

[0705] Input: Reading history data.

[0706] Output: Analyzed reading trend data.

[0707] Step 4: Obtain market valuation data

[0708] Based on the book information extracted by image analysis, the server obtains market evaluation data for each book from the Internet, for example, by collecting data from online bookstores and review sites.

[0709] Input: Book information.

[0710] Output: Collected market valuation data.

[0711] The server aggregates the acquired market evaluation data and assigns a market evaluation score to each book.

[0712] Input: Market valuation data.

[0713] Output: A market rating score given to each book.

[0714] Step 5: Selecting recommended books

[0715] The server rates each book's importance based on the user's reading habits and market rating score.

[0716] Inputs: Reading trend data, market evaluation scores.

[0717] Output: The importance of the rated book.

[0718] The server classifies books with high scores into a "recommended book list" and books with low scores into a "not to be given up book list."

[0719] Input: Book importance.

[0720] Output: "Recommended books list" and "Let go books list".

[0721] Step 6: Generate testimonials

[0722] The server uses generative AI models (e.g., natural language processing techniques) to generate recommendations for the selected books.

[0723] Input: "Recommended book list", generative model.

[0724] Output: The generated recommendation.

[0725] For example, it generates a recommendation such as, "Book A has an amazing story set against the backdrop of the latest technological trends, and is perfect for you."

[0726] Step 7: Create a reading plan

[0727] The server creates a reading plan taking into account the user's reading speed (estimated from past reading history) and daily rhythm (based on information registered by the user).

[0728] Input: Reading speed, lifestyle data.

[0729] Output: A realistic reading plan.

[0730] For example, present a plan to read book A in three weeks and book D in four weeks.

[0731] Step 8: Providing a User Interface

[0732] The device allows the user to check the "recommended books list" and the "let go books list" through the app.

[0733] Input: "Recommended Book List", "Let Go Book List".

[0734] Output: The list displayed on the user's screen.

[0735] The device provides the user with a recommendation for each book within the app, including specific reasons for recommending the book.

[0736] Input: The generated testimonial.

[0737] Output: The testimonial provided to the user.

[0738] Users can start reading according to an in-app reading plan and track their progress as they finish.

[0739] Input: Reading progress information.

[0740] Output: Feedback to receive next recommendation.

[0741] The above is a detailed description of the processing steps in a specific embodiment of the "Unread Book Clearing Advisor."

[0742] (Application example 1)

[0743] 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."

[0744] There is a need for a system that can efficiently manage the unread books that users have accumulated (so-called "tsundoku") and properly select books that they should read now or let go of. It is also necessary to have a system that allows users to visually check these books in a virtual bookstore and understand the specific reasons for the recommendations before purchasing or letting go of them. In addition, users can receive detailed recommendations based on their own reading habits, which will enable them to effectively plan their reading.

[0745] 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.

[0746] In this invention, the server includes image analysis means, reading history analysis means, market evaluation data acquisition means, recommended book selection means, recommendation statement generation means, reading plan creation means, user interface means, virtual exhibition space generation means, and prompt statement generation means, which enable the user to efficiently manage unread books, visually check books in the virtual space, and select recommended books based on specific recommendation reasons and create a reading plan.

[0747] "Image analysis means" refers to a device or software that analyzes image data and extracts book information (title, author name, ISBN, etc.).

[0748] "Reading history analysis means" refers to a device or software that analyzes a user's reading habits based on the user's past reading history.

[0749] The "market evaluation data acquisition means" is a device or software that acquires market evaluation data of books from online bookstores, review sites, and the like on the Internet.

[0750] The "recommended book selection means" is a device or software that selects books that should be read now or that should be discarded based on the user's reading habits and market evaluation score.

[0751] The "recommendation generator" is a device or software that uses natural language processing technology to generate specific reasons for recommending a selected book.

[0752] A "reading plan creation tool" is a device or software that takes into account the user's reading speed and lifestyle and creates a realistic reading schedule.

[0753] "User interface means" means a device or software that provides a screen or method of operation through which a user can interact with the system and view recommended books, discarded books, recommendations, and reading plans.

[0754] A "virtual exhibition space generation means" is a device or software that uses virtual reality (VR) technology to generate an environment in which users can visually check unread books and recommended books in a virtual space.

[0755] A "prompt sentence generation means" is a device or software that generates an input sentence (prompt) for the generative AI model and obtains a specific reason for recommendation.

[0756] This invention is a system that allows users to efficiently manage their piles of unread books (so-called "tsundoku"), appropriately select books that should be read now or that should be let go, and purchase or let go of them while visually checking them in a virtual space. This system has the following main means.

[0757] The system consists of a server and a user's device (such as a smartphone or head-mounted display). Users take photos of unread books using their smartphone or digital camera and upload them through the application.

[0758] The server uses image analysis to extract book information (title, author, ISBN, etc.) from the uploaded image. This image analysis uses a common image analysis API (e.g., pytesseract).

[0759] Next, the server uses a reading history analysis means to refer to the user's past reading history database and analyze the user's reading habits (favorite genres, tendency of books rated, etc.). This information is stored in a user profile.

[0760] Using the market evaluation data acquisition means, the server acquires the latest market evaluation data (e.g., from online bookstores or review sites) for each book from the Internet based on the extracted book information. This data is analyzed, and a market evaluation score is assigned to each book.

[0761] Next, the recommendation book selection method evaluates the importance of each book based on the user's reading habits and market evaluation score. Highly rated books are classified into the "recommended books list," while low-rated books are classified into the "not recommended books list."

[0762] Using the recommendation generation means, the server uses a generative AI model (for example, OpenAI's text generation model) to generate a recommendation for the selected book. This recommendation includes specific reasons why the book should be read and information specific to the user's interests. For example, a prompt for the generative AI model might be, "The user's reading habits are 'science fiction' and 'self-help books.' Why do you recommend 'Book A'? Please explain the specific reasons."

[0763] The server creates a realistic reading plan based on the user's reading speed (estimated from past reading history) and daily rhythm (based on information registered by the user). This plan includes a schedule of when each book should be completed.

[0764] The virtual exhibition space generating means uses virtual reality (VR) technology to generate an environment in which the user can freely walk around the bookstore and visually check unread books and recommended books in the virtual space. The user interface means allows the user to check the "recommended book list" and the "let go book list" and to view detailed recommendations for each.

[0765] Users can start reading according to the in-app reading plan, and when they finish, they can record their progress in the app and provide feedback to receive the next recommendation. This feedback keeps the user's reading habits updated.

[0766] For example, if a user takes photos of five unread books and uploads them to the app, the server uses an image analysis engine to extract information about each book. Based on this book information, market evaluation data is obtained and a market evaluation score is assigned to each book. Based on the user's past reading history, the app determines that the user prefers science fiction and self-help books. Highly rated science fiction book A and self-help book D are added to the recommended books list. Using a generative AI model, a specific recommendation is generated, such as, "Book A has an amazing story unfolding against the backdrop of the latest technological trends, making it perfect for you." Taking into account the user's reading speed and lifestyle, the app then suggests a plan for reading books A and D within one month.

[0767] The above is a concrete implementation of the "Unread Books Clearing Advisor." Through this system, users can efficiently manage their unread books and enjoy a meaningful reading experience.

[0768] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0769] Step 1:

[0770] Users take a photo of an unread book with their smartphone or digital camera, save it in the app, and then click the "Upload Image" button to upload the photo to the server.

[0771] Input: Photo of an unread book

[0772] Output: Uploaded photo

[0773] Step 2:

[0774] The server uses image analysis to extract book information (title, author, ISBN, etc.) from the uploaded photo. For image analysis, it uses a common image analysis API (e.g., pytesseract).

[0775] Input: Uploaded photo

[0776] Output: Book information (title, author, ISBN, etc.)

[0777] Step 3:

[0778] The server uses a reading history analysis means to refer to the user's past reading history database and analyze the user's reading tendencies (favorite genres, tendency of books rated, etc.).

[0779] Input: User's past reading history

[0780] Output: User's reading habits

[0781] Step 4:

[0782] The server uses the market evaluation data acquisition means to acquire the latest market evaluation data for each book from the Internet based on the extracted book information, analyzes the acquired data, and assigns a market evaluation score to each book.

[0783] Input: Book information (title, author, ISBN, etc.)

[0784] Output: Market rating score for the book

[0785] Step 5:

[0786] The server uses a recommended book selection method to evaluate the importance of each book based on the user's reading habits and market evaluation score. Highly rated books are classified into a "recommended book list" and low-rated books are classified into a "not-recommended book list."

[0787] Input: User's reading habits, market evaluation score

[0788] Output: Recommended books list, To-be-given books list

[0789] Step 6:

[0790] The server uses the recommendation generator to generate a recommendation for the selected book using a generative AI model, the recommendation including specific reasons why the book should be read and information specific to the user's interests.

[0791] Input: Recommended book list, user's reading habits

[0792] Output: Recommendation (e.g., "Book A is perfect for you because it tells an amazing story set against the backdrop of the latest technological trends.")

[0793] Step 7:

[0794] The server uses a reading plan generator to create a realistic reading schedule that takes into account the user's reading speed and daily routine, including a timeline for when each book should be completed.

[0795] Input: User's reading speed, daily routine, recommended book list

[0796] Output: Reading plan

[0797] Step 8:

[0798] The server uses a virtual exhibition space generating means and virtual reality (VR) technology to generate an environment in which the user can freely walk around the bookstore and visually check unread books and recommended books in the virtual space.

[0799] Input: Recommended books list, list of books to give up

[0800] Output: Virtual exhibition space

[0801] Step 9:

[0802] Through the user interface, the user can check the "recommended book list" and the "let go book list" and view detailed recommendations. Furthermore, the user can start reading according to the reading plan, and when they finish reading, the progress is recorded in the app, providing feedback for the next recommendation.

[0803] Input: Virtual exhibition space, recommendations, reading plan

[0804] Output: Reading progress feedback

[0805] 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.

[0806] The present invention is a system that effectively manages a user's unread books and proposes an optimal reading strategy taking into account reading habits and emotional state. Hereinafter, embodiments of the present invention will be described.

[0807] Image upload and analysis

[0808] User: Take a photo of an unread book with your smartphone.

[0809] On the device: The user takes a photo, saves it in the app, and then clicks the "Upload Image" button in the app to upload the photo to the server.

[0810] Server: Sends the received image data to the image analysis engine.

[0811] Server: The image analysis engine extracts text information from the image, detects the book title, author name, ISBN, etc., and stores this information in a database.

[0812] Reading history analysis

[0813] Server: Refers to the database of the user's past reading history and analyzes the user's reading habits (favorite genres, book ratings, etc.). It also updates the user profile and stores the latest reading habits data.

[0814] Obtaining market evaluation

[0815] Server: Based on the extracted book information, obtains market evaluation data for each book from the Internet.

[0816] Server: Aggregates the acquired market evaluation data, assigns an evaluation score to each book, and creates a list of recommended books and a list of books to be discarded based on that information.

[0817] Emotion recognition by emotion engine

[0818] On-device: Emotional data is collected using methods such as facial recognition and voice analysis to help the app understand the user's emotional state.

[0819] Server: Sends the collected emotion data to the emotion engine to analyze the user's current emotional state.

[0820] Selection of recommended books

[0821] Server: Based on the user's reading habits, emotional state, and market evaluation score, the server classifies books that should be read now into a recommended book list.

[0822] Server: By selecting recommended books based on emotional state, users can read books that suit their mood at the time.

[0823] Generating recommendation letters

[0824] Server: Uses a generative AI model to generate a recommendation for the selected book, taking into account the user's emotional state and providing specific reasons why the book should be read.

[0825] Creating a Reading Plan

[0826] Server: Creates a realistic reading plan based on the user's reading speed and lifestyle information. This plan includes a schedule for when each book should be completed.

[0827] User Interface

[0828] On your device: Through the app, users can view the "recommended books list" and "let go books list," as well as read the recommendations and understand the specific reasons for each book's recommendation.

[0829] Users: Start reading according to the in-app reading plan, and when they finish, record their progress in the app and receive next recommendations.

[0830] Specific examples

[0831] Here's a concrete example: If a user takes photos of five unread books and uploads them to the app, the following process will occur:

[0832] 1. Device: The user uploads five photos.

[0833] 2. Server: The image analysis engine extracts book information and obtains Book A (science fiction), Book B (business book), Book C (historical novel), Book D (self-help book), and Book E (fantasy).

[0834] 3. Server: Analyzes the user's past reading history and finds that they like science fiction and self-help books.

[0835] 4. Server: Books A and D have high market ratings, so they are classified into the recommended books list.

[0836] 5. Device: Recognizes the user's emotions and uses the emotion engine to analyze that the current emotion is fatigue.

[0837] 6. Server: Recommend book D, which has relaxing content that suits the tired state.

[0838] 7. Server: Generate a recommendation, such as, "This self-help book contains many specific relaxation techniques and is perfect for my current tired state."

[0839] 8. Server: Taking into account the user's reading speed and lifestyle, propose a plan to read books A and D within one month.

[0840] 9. Device: The user sees the recommended book list and reading plan and begins reading.

[0841] The above is a specific implementation of the "Unread Books Clearing Advisor" that combines an emotion engine. This system manages and recommends unread books taking into account the user's emotional state, providing a meaningful reading experience.

[0842] The processing flow will be explained below.

[0843] Step 1:

[0844] User: Take a photo of an unread book with your smartphone.

[0845] Step 2:

[0846] On your device: Save the photo you took in the app and click the "Upload image" button in the app.

[0847] Step 3:

[0848] Terminal: Sends uploaded photo data to the server.

[0849] Step 4:

[0850] Server: Sends the received image data to the image analysis engine.

[0851] Step 5:

[0852] Server: The image analysis engine extracts text information from the image and detects the book title, author name, ISBN, etc.

[0853] Step 6:

[0854] Server: Organizes the detected book information and stores it in a database.

[0855] Step 7:

[0856] Server: Accesses the database of users' past reading history and analyzes their reading habits.

[0857] Step 8:

[0858] Server: Updates user profiles and stores the latest reading habits data.

[0859] Step 9:

[0860] Server: Based on the extracted book information, obtains market evaluation data for each book from the Internet.

[0861] Step 10:

[0862] Server: Aggregates the acquired market evaluation data and assigns an evaluation score to each book.

[0863] Step 11:

[0864] On-device: The app uses facial recognition and voice analysis to collect emotional data to understand the user's emotional state.

[0865] Step 12:

[0866] Terminal: Sends collected emotion data to the server.

[0867] Step 13:

[0868] Server: The emotion engine analyzes the received emotion data and determines the user's current emotional state.

[0869] Step 14:

[0870] Server: Categorizes books to be read into a recommended book list based on the user's reading habits, emotional state, and rating scores.

[0871] Step 15:

[0872] Server: Uses a generative AI model to generate recommendations for selected books, including specific reasons that take into account the user's emotional state.

[0873] Step 16:

[0874] Server: Creates a realistic reading plan based on the user's reading speed and lifestyle information.

[0875] Step 17:

[0876] Server: Sends the created reading plan and recommended book information to the user's terminal.

[0877] Step 18:

[0878] On your device: Display recommended books and testimonials within the app for users to review.

[0879] Step 19:

[0880] On-device: The reading plan is displayed within the app, allowing users to track their progress.

[0881] Step 20:

[0882] User: Start reading the recommended book and track your progress within the app as you read.

[0883] Example 2

[0884] 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."

[0885] In modern society, many users have a large number of unread books, and find it difficult to manage them and progress in their reading. Furthermore, it is difficult to select appropriate books based on the user's emotional state, which can reduce the quality of the reading experience. There is a need to solve these problems and provide a more effective and efficient reading management and recommendation system.

[0886] 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.

[0887] In this invention, the server includes image analysis means, reading history analysis means, market evaluation data acquisition means, emotion data collection means, emotion state analysis means, recommended book selection means, recommendation statement generation means, reading plan creation means, and user interface means, which enable effective management of unread books for the user and further enable appropriate book recommendations taking into account the user's emotional state.

[0888] "Image analysis means" refers to a means of extracting text information from images uploaded by users and obtaining data such as book titles, author names, and ISBNs.

[0889] The "reading history analysis means" is a means for analyzing a user's past reading history data and identifying reading tendencies and preferred genres.

[0890] The "market evaluation data acquisition means" is a means for collecting market evaluation data of books from the Internet and assigning an evaluation score to each book.

[0891] "Emotional data collection means" refers to a means of collecting emotional data through facial recognition and voice analysis of the user.

[0892] The "emotional state analysis means" is a means for analyzing collected emotional data and identifying the user's current emotional state.

[0893] The "recommended book selection method" is a method for selecting appropriate books based on the user's reading habits, emotional state, and market evaluation score.

[0894] The "recommendation generation means" is a means for creating a recommendation for a selected book using a generative AI model.

[0895] The "reading plan creation tool" is a tool that creates a realistic reading plan based on the user's reading speed and lifestyle information.

[0896] "User interface means" means by which a user interacts with the system and views recommended book lists and reading plans.

[0897] The present invention provides a system that effectively manages a user's unread books and proposes an optimal reading strategy by taking into account their reading habits and emotional state. The system includes image analysis means, reading history analysis means, market evaluation data acquisition means, emotional data collection means, emotional state analysis means, recommended book selection means, recommendation message generation means, reading plan creation means, and user interface means. This allows for effective and efficient management of a user's unread books and the provision of recommended books.

[0898] Image upload and analysis

[0899] User:

[0900] Take a photo of an unread book with your smartphone. Specifically, open the camera app, center the book cover, and press the capture button.

[0901] Device:

[0902] Save the photos you take in the app, then click the "Upload Image" button in the app to upload the photos to the server. The device will then send the image data to the server.

[0903] server:

[0904] The received image data is sent to an image analysis engine, specifically using OCR technology, which extracts text information from the image (such as the book title, author name, ISBN, etc.) and stores that information in a database.

[0905] Reading history analysis

[0906] server:

[0907] Retrieve the user's past reading history from the database. Analyze past ratings, genres of books read, favorite authors, etc. Update the user profile if new trends are found.

[0908] Obtaining market evaluation

[0909] server:

[0910] Based on the extracted book information, market evaluation data is obtained from review sites and book databases (e.g., major bibliographic information sites, online bookstores) for each book. The obtained data is aggregated and an evaluation score is assigned to each book.

[0911] Emotion recognition by emotion engine

[0912] Device:

[0913] To recognize the user's emotional state, the system uses a smartphone camera for facial recognition and a voice assistant to collect voice data, which is then sent to a server.

[0914] server:

[0915] The received emotional data is analyzed by the emotion analysis engine to determine the current emotional state (e.g., tired, relaxed, stressed).

[0916] Selection of recommended books

[0917] server:

[0918] The system comprehensively assesses the user's reading habits, current emotional state, and market evaluation score to add the best books to the recommended book list, with a particular focus on books that match the user's current emotional state.

[0919] Generating recommendation letters

[0920] server:

[0921] Based on the selected book information, a prompt is input into a generative AI model (e.g., GPT-4) to generate a recommendation. Example prompt: "The user is currently feeling tired. This self-help book contains many specific relaxation techniques and is perfect for this tired state."

[0922] Creating a Reading Plan

[0923] server:

[0924] Based on the user's reading speed and lifestyle information, a realistic reading plan is created, including the estimated completion date for each book.

[0925] User Interface

[0926] Device:

[0927] The app displays a recommended book list and reading plan to users, and after checking the displayed content, users can start reading according to the plan.

[0928] Adding specific examples

[0929] For example, if a user takes photos of five unread books and uploads them to the app, the process would look like this:

[0930] 1. Device: The user uploads five photos.

[0931] 2. Server: The image analysis engine extracts book information and obtains Book A (science fiction), Book B (business book), Book C (historical novel), Book D (self-help book), and Book E (fantasy).

[0932] 3. Server: Analyzes the user's past reading history and finds that they like science fiction and self-help books.

[0933] 4. Server: Books A and D have high market ratings, so they are classified into the recommended books list.

[0934] 5. Device: Recognizes the user's emotions and uses the emotion engine to analyze that the current emotion is fatigue.

[0935] 6. Server: Recommend book D, which has relaxing content that suits the tired state.

[0936] 7. Server: Generate a recommendation, such as, "This self-help book contains many specific relaxation techniques and is perfect for my current tired state."

[0937] 8. Server: Taking into account the user's reading speed and lifestyle, propose a plan to read books A and D within one month.

[0938] 9. Device: The user sees the recommended book list and reading plan and begins reading.

[0939] The above is a specific implementation of the "Unread Books Clearing Advisor" that combines an emotion engine. This system manages and recommends unread books taking into account the user's emotional state, providing a meaningful reading experience.

[0940] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0941] Step 1:

[0942] User: Take a photo of an unread book with your smartphone.

[0943] Input: An image of a book taken with a smartphone camera.

[0944] Output: Book image files.

[0945] Specific actions: Launch the camera app, center the book cover, and press the capture button.

[0946] Step 2:

[0947] Device: Save the photo in the app and upload it to the server.

[0948] Input: Book image files.

[0949] Output: Sending image data to the server.

[0950] Specific operation: The captured photo is saved in the app, and the user clicks the "Upload image" button in the app. The device sends the image data to the server.

[0951] Step 3:

[0952] Server: Analyzes the image, extracts book information, and stores it in a database.

[0953] Input: Uploaded book image.

[0954] Output: Book information (title, author, ISBN) stored in a database.

[0955] Specific operation: The received image data is analyzed using OCR technology to extract text information from the image, detecting the book title, author name, and ISBN, and storing that information in a database.

[0956] Step 4:

[0957] Server: Refers to the user's reading history and analyzes reading trends.

[0958] Input: The user's reading history stored in a database.

[0959] Output: An updated profile of the user's reading habits as a result of the analysis.

[0960] What it does: It analyzes past reading history, attributes such as ratings, genres, and authors to identify users' reading habits, and updates their user profile if new habits are found.

[0961] Step 5:

[0962] Server: Collects book market evaluation data from the Internet.

[0963] Input: Extracted book information (title, author, ISBN).

[0964] Output: Book information with rating scores.

[0965] Specific operation: Based on book information, evaluation data is obtained from review sites and online bookstores, and evaluation scores are compiled and assigned to each book.

[0966] Step 6:

[0967] Terminal: Collects user emotional data.

[0968] Input: User's facial recognition image data and voice data.

[0969] Output: Sending emotion data to the server.

[0970] Specific operation: Facial recognition is performed using the smartphone camera, and voice recordings are collected using the voice assistant. The collected data is then sent to a server.

[0971] Step 7:

[0972] Server: Analyzes the emotional data to determine the current emotional state.

[0973] Input: Collected emotion data (face recognition images, audio data).

[0974] Output: Current emotional state judgment result.

[0975] What it does: The emotion analysis engine analyzes facial recognition data and voice data to determine the current emotional state.

[0976] Step 8:

[0977] Server: Selects recommended books based on reading habits, emotional state, and market evaluation.

[0978] Input: Reading habits profile, emotional state assessment results, market evaluation data.

[0979] Output: A list of recommended books.

[0980] Specific operation: Comprehensively evaluate the user's reading habits, current emotional state, and market evaluation score, select the most suitable books, and add them to the recommended book list.

[0981] Step 9:

[0982] Server: Generates recommendations for selected books using a generative AI model.

[0983] Input: Recommended book list.

[0984] Output: The generated recommendation.

[0985] Specific behavior: A prompt is input into a generative AI model (e.g., GPT-4) to generate a recommendation. Example prompt: "The user is currently feeling tired. This self-help book contains many specific relaxation techniques and is perfect for this tired state."

[0986] Step 10:

[0987] Server: Creates a reading plan for the user.

[0988] Input: User's reading speed, lifestyle information, recommended book list.

[0989] Output: Reading plan.

[0990] What it does: Create a realistic reading plan based on the user's reading speed and lifestyle information, including estimated completion dates for each book.

[0991] Step 11:

[0992] Device: Provides users with recommended book lists and reading plans.

[0993] Input: Recommended book list, reading plan.

[0994] Output: Information displayed by the user interface.

[0995] Specific operation: Display recommended book lists and reading plans to users through the app screen, allowing users to start reading based on them.

[0996] (Application example 2)

[0997] 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."

[0998] Conventional reading recommendation systems recommend books based solely on reading history and market evaluations, without taking into account the user's emotional state or usage environment, making it difficult for users to read the right book at the optimal time. In addition, users of smart devices need a system that can maximize their convenience.

[0999] 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.

[1000] In this invention, the server includes image analysis means, reading history analysis means, market evaluation data acquisition means, emotion recognition means, recommended book selection means, recommendation statement generation means, reading plan creation means, and smart device interface means, thereby enabling accurate book recommendations and the creation of reading plans that take into account the user's emotional state and usage environment.

[1001] 1. "Image analysis means" refers to a device or program that extracts text information from captured image data and detects book titles, author names, ISBNs, etc.

[1002] 2. "Reading history analysis means" refers to a device or program that refers to a user's past reading history and analyzes their reading habits.

[1003] 3. "Market evaluation data acquisition means" refers to a device or program that acquires and compiles market evaluation data for each book from the Internet.

[1004] 4. "Emotion recognition means" means a device or program that recognizes a user's emotional state using methods such as facial recognition or voice analysis.

[1005] 5. "Recommended book selection means" refers to a device or program that selects books to read based on a user's reading habits, emotional state, and market evaluation data.

[1006] 6. "Recommendation generation means" means a device or program consisting of a generative AI model that generates recommendations for selected books.

[1007] 7. "Reading plan creation means" means a device or program that creates a realistic reading plan based on the user's reading speed and lifestyle information.

[1008] 8. "Smart device interface means" means a device or program that provides information to a user through a device such as a smartphone or smart glasses.

[1009] This invention is a system that utilizes a smart device installed in an autonomous vehicle to effectively manage a user's unread books and propose an optimal reading strategy taking into account reading habits and emotional state. The following describes an embodiment of the invention.

[1010] Hardware and software used

[1011] Hardware:

[1012] Smart glasses and smartphones

[1013] Autonomous vehicle computer systems

[1014] software:

[1015] Python

[1016] OpenCV (image processing library)

[1017] FacialRecognition (emotion recognition library)

[1018] OCREngine (OCR analysis library)

[1019] BookRecommender (recommendation algorithm)

[1020] RecommendationModel (generative AI model)

[1021] System Operation

[1022] Image upload and analysis

[1023] Users take a photo of an unread book with their smartphone. The device's smart glasses store the photo and upload it to the autonomous vehicle's computer system. The server then uses image analysis tools to extract text information from the image, such as the book's title, author, and ISBN, and stores that information in a database.

[1024] Reading history analysis

[1025] The server uses the reading history analysis means to refer to the database of the user's past reading history and analyze the reading habits, and this information is also stored in the database.

[1026] Obtaining market evaluation

[1027] The server uses the market evaluation data acquisition means to acquire market evaluation data for each book from the Internet based on the extracted book information. The acquired market evaluation data is aggregated and an evaluation score is assigned to each book.

[1028] emotion recognition means

[1029] The smart glasses on the device collect the user's facial expression data and send it to a server, which then analyzes this data using emotion recognition means to determine the user's current emotional state.

[1030] Selection of recommended books

[1031] The server uses a recommended book selection means to select books to read now based on reading habits, emotional state, and market evaluation data, and the selected book information is stored in a database.

[1032] Generating recommendation letters

[1033] The server uses the generative AI model to generate recommendations for the selected books, which are then displayed on the smart glasses.

[1034] Creating a Reading Plan

[1035] The server uses the reading plan creation means to create a realistic reading plan that takes into account the user's reading speed and travel time.

[1036] Specific examples and prompts for generative AI models

[1037] Specific examples

[1038] For example, if a user takes photos of five unread books with their smartphone while riding in a self-driving vehicle and uploads them to the vehicle's system, the process will proceed as follows: If the smart glasses analyze the user's facial expression and determine that the user's emotional state is "tired," a recommendation will be generated and displayed, saying, "This self-help book contains many specific relaxation techniques and is perfect for your current tired state."

[1039] Prompt Sentence Examples

[1040] Prompt statement:

[1041] "Generate a recommendation for a self-help book that is ideal for when the user is in a tired emotional state. The book title is "A Relaxing Life" and the author is "Taro Yamada.""

[1042] This provides an environment where users can read self-help books, which is ideal when they are tired.

[1043] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1044] Step 1:

[1045] The user takes a photo of an unread book with their smartphone, and the image data is input into the device.

[1046] Step 2:

[1047] The device stores the captured images and uploads them to the autonomous vehicle's system via smart glasses.

[1048] Input: Image of unread book

[1049] Data processing: Image saving and uploading

[1050] Output: Image data to the server

[1051] Step 3:

[1052] The server uses image analysis to extract text information from the uploaded image, specifically detecting information such as the book title, author name, and ISBN.

[1053] Input: Image data

[1054] Data calculation: OCR analysis

[1055] Output: Book information (title, author, ISBN)

[1056] Step 4:

[1057] The server stores the extracted book information in a database, which is used for subsequent analysis and evaluation.

[1058] Input: Book information

[1059] Data processing: information storage

[1060] Output: Book information in the database

[1061] Step 5:

[1062] The server uses a reading history analysis means to refer to the user's past reading history data and analyze their reading habits, which is then used to recommend new books.

[1063] Input: Reading history database

[1064] Data Computing: Reading Trend Analysis

[1065] Output: Reading habits data

[1066] Step 6:

[1067] The server uses the market evaluation data acquisition means to acquire market evaluation data for each book from the Internet, specifically, to collect reviews and evaluation scores for the book.

[1068] Input: Book information

[1069] Data calculation: Data acquisition from the Internet

[1070] Output: Market valuation data

[1071] Step 7:

[1072] The server aggregates the acquired market evaluation data and assigns each book an evaluation score, which is used to select recommended books.

[1073] Input: Market valuation data

[1074] Data calculation: Score assignment

[1075] Output: Evaluation score

[1076] Step 8:

[1077] The smart glasses on the device collect and transmit facial expression data from the user to a server, which is used to analyze the user's emotional state.

[1078] Input: facial expression data

[1079] Data Processing: Data Collection and Transmission

[1080] Output: Facial expression data to the server

[1081] Step 9:

[1082] The server analyzes the collected facial expression data using emotion recognition means to determine the user's current emotional state.

[1083] Input: facial expression data

[1084] Data Computing: Emotion Recognition

[1085] Output: Emotional state

[1086] Step 10:

[1087] The server uses a recommended book selection means to select books to read now based on reading habits, emotional state, and market evaluation data.

[1088] Input: Reading habits data, emotional state, evaluation score

[1089] Data calculation: Book selection

[1090] Output: Recommended book list

[1091] Step 11:

[1092] The server uses a generative AI model to generate a recommendation for the selected book, for example, using prompts to provide specific reasons for the recommendation.

[1093] Input: Recommended book list, emotional state

[1094] Data calculation: recommendation generation

[1095] Output: Recommendation

[1096] Step 12:

[1097] The server uses the reading plan creation means to create a realistic reading plan that takes into account the user's reading speed and usage environment (such as travel time).

[1098] Input: Reading speed, usage environment

[1099] Data calculation: Reading plan creation

[1100] Output: Reading plan

[1101] Step 13:

[1102] Users can view the recommended book list, recommendations, and reading plan through a smart device interface, such as smart glasses or a smartphone.

[1103] Input: Recommended book list, recommendation, reading plan

[1104] Data processing: Information display

[1105] Output: User confirmation and execution

[1106] 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.

[1107] 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.

[1108] 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.

[1109] [Third embodiment]

[1110] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1111] 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.

[1112] 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).

[1113] 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.

[1114] 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.

[1115] 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).

[1116] 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.

[1117] 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.

[1118] 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.

[1119] 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.

[1120] 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.

[1121] 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."

[1122] The present invention is a system that efficiently manages the unread books that a user has accumulated (so-called "tsundoku") and appropriately selects books that should be read now and books that should be let go. The following describes an embodiment of the present invention.

[1123] Image upload and analysis

[1124] User: Take a photo of an unread book using a smartphone or digital camera.

[1125] On the device: The user takes a photo, saves it in the app, and then clicks the "Upload Image" button in the app to upload the photo to the server.

[1126] Server: Receives the uploaded images and uses an image analysis engine (e.g., a common image analysis API) to extract book information (title, author, ISBN, etc.) from the images.

[1127] Reading history analysis

[1128] Server: Refers to the database of the user's past reading history and analyzes the user's reading habits (favorite genres, book ratings, etc.). This information is passed to the user profile, and the latest trend data reflecting the user's reading preferences is accumulated.

[1129] Obtaining market evaluation

[1130] Server: Based on the extracted book information, the server obtains the latest market evaluation data for each book from the Internet (e.g., online bookstores and review sites), aggregates the obtained data, and assigns a market evaluation score to each book.

[1131] Selection of recommended books

[1132] Server: Evaluates the importance of each book based on the user's reading habits and market evaluation score. Books with high scores are classified as "recommended books" and "books to be discarded" and "books to be discarded" respectively.

[1133] Generating recommendation letters

[1134] Server: Uses generative AI models (e.g., natural language processing techniques) to generate recommendations for selected books, including specific reasons why the book should be read and information specific to the user's interests.

[1135] Creating a Reading Plan

[1136] Server: Creates a realistic reading plan based on the user's reading speed (estimated from past reading history) and daily routine (based on user-provided information). The reading plan includes a schedule for when each book should be completed.

[1137] User Interface

[1138] On-device: Through the app, users can check the "recommended books list" and "list of books to give up." They can also read the "recommendation" and understand the specific reasons for each book's recommendation.

[1139] Users: Start reading according to the in-app reading plan, and when they finish, record their progress in the app to provide feedback for future recommendations.

[1140] Specific examples

[1141] Here's a concrete example: A user takes photos of five unread books and uploads them to the app.

[1142] 1. Device: Upload a photo.

[1143] 2. Server: The image analysis engine extracts book information and obtains Book A (science fiction), Book B (business book), Book C (historical novel), Book D (self-help book), and Book E (fantasy).

[1144] 3. Server: Determine from past reading history that the user prefers science fiction and self-help books.

[1145] 4. Server: Books A and D have high market valuations, so they are recommended books.

[1146] 5. Server: Generate a recommendation: "Book A has an amazing story set against the backdrop of the latest technological trends, and is perfect for you." Similarly, generate a recommendation for Book D.

[1147] 6. Server: Taking into account the user's reading speed and lifestyle, propose a plan to read books A and D within one month.

[1148] 7. Device: The user checks this information through the app and begins reading according to the reading plan.

[1149] The above is a specific implementation of the "Unread Books Clearing Advisor." Through this system, users can efficiently manage their unread books and enjoy a meaningful reading experience.

[1150] The processing flow will be explained below.

[1151] Step 1:

[1152] User: Take a photo of an unread book with your smartphone.

[1153] Step 2:

[1154] On the device: The captured photo is saved in the app, and the user clicks the "Upload image" button within the app.

[1155] Step 3:

[1156] Terminal: Sends uploaded photo data to the server.

[1157] Step 4:

[1158] Server: Sends the received image data to the analysis engine.

[1159] Step 5:

[1160] Server: The image analysis engine extracts text information from the image and detects the book title, author name, ISBN, etc.

[1161] Step 6:

[1162] Server: Organizes the detected book information and stores it in a database.

[1163] Step 7:

[1164] Server: Accesses the database of users' past reading history and analyzes their reading habits.

[1165] Step 8:

[1166] Server: Updates user profiles and stores the latest reading habits data.

[1167] Step 9:

[1168] Server: Based on the extracted book information, obtains market evaluation data for each book from the Internet.

[1169] Step 10:

[1170] Server: Aggregates the acquired market evaluation data and assigns an evaluation score to each book.

[1171] Step 11:

[1172] Server: Based on the user's reading habits and market evaluation scores, selects books to read and books to discard.

[1173] Step 12:

[1174] Server: Generates recommendations for selected books using a generative AI model.

[1175] Step 13:

[1176] Server: Creates a realistic reading plan based on the user's reading speed and lifestyle information.

[1177] Step 14:

[1178] Server: Sends the created reading plan and recommended book information to the terminal.

[1179] Step 15:

[1180] On your device: Display recommended books and testimonials within the app for users to review.

[1181] Step 16:

[1182] On-device: The reading plan is displayed within the app, allowing users to track their progress.

[1183] Step 17:

[1184] User: Start reading the recommended book and track your progress within the app as you read.

[1185] This is the specific process flow of the "Tsundoku Kakuri Advisor." This system allows users to efficiently manage their unread books and have a meaningful reading experience.

[1186] Example 1

[1187] 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."

[1188] Currently, many users have piled up unread books, making it difficult to manage them and determine which books they should prioritize. Furthermore, there are no clear criteria for selecting books to let go, making it difficult to efficiently manage reading.

[1189] 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.

[1190] In this invention, the server includes image analysis means, reading history analysis means, market evaluation data acquisition means, recommended book selection means, recommendation generation means using a generative AI model, reading plan creation means that takes into account reading speed and daily rhythm, and user interface means, allowing users to efficiently manage unread books and appropriately select books to read now and books to let go.

[1191] "Image analysis means" refers to a technical device that analyzes photographs or image data and extracts specific book information (title, author name, ISBN, etc.) from it.

[1192] "Reading history analysis means" refers to a technical device that collects and analyzes a user's past reading history data and derives the user's reading tendencies and preferences.

[1193] The "market evaluation data acquisition means" is a technical device that acquires data on the market evaluation of books from the Internet and assigns an evaluation score to each book.

[1194] The "recommended book selection means" is a technical device that combines the user's reading habits with market evaluation data to select highly important books and classify them into a recommended book list.

[1195] A "means for generating recommendation sentences using a generative AI model" is a technical device that uses a generative AI model (e.g., natural language processing technology) to generate recommendation sentences for selected books.

[1196] The "means for creating a reading plan that takes into account reading speed and lifestyle rhythm" is a technical device that creates a realistic and effective reading plan based on the user's reading speed and lifestyle rhythm.

[1197] "User interface means" means an interface device through which a user interacts with a system and inputs and obtains information.

[1198] The present invention provides a system for efficiently managing a user's pile of unread books and appropriately selecting books that should be read now and books that should be let go. The following describes an embodiment of the present invention.

[1199] Image upload and analysis

[1200] User: Take a photo of an unread book with a smartphone or digital camera. For example, you can take a photo of five unread books at once.

[1201] Device: The user saves the photos they have taken in a dedicated app and clicks the "Upload Image" button in the app to upload the photos to the server.

[1202] Server: Receives uploaded images and uses an image analysis engine (e.g., Google Cloud Vision API) to extract book information (title, author, ISBN, etc.) from the images. The extracted information is stored in a database.

[1203] Reading history analysis

[1204] Server: Refers to the database of the user's past reading history and analyzes the user's reading habits (favorite genres, book ratings, etc.). This information is reflected in the user profile and stored as the latest trend data.

[1205] Obtaining market evaluation

[1206] Server: Based on the book information extracted through image analysis, market evaluation data for each book is obtained from the Internet (e.g., online bookstores and review sites). The obtained data is aggregated and a market evaluation score is assigned to each book.

[1207] Selection of recommended books

[1208] Server: Based on the user's reading habits and market evaluation score, each book is individually rated for importance. Books with high importance are classified into the "recommended books list," while books with low importance are classified into the "not recommended books list."

[1209] Generating recommendation letters

[1210] Server: Uses generative AI models (e.g., natural language processing techniques) to generate recommendations for selected books, including specific reasons why the book should be read and information specific to the user's interests.

[1211] Creating a Reading Plan

[1212] Server: Creates a realistic reading plan based on the user's reading speed (estimated from past reading history) and daily rhythm (based on information registered by the user). The reading plan includes a schedule for when each book should be completed.

[1213] User Interface

[1214] On the device: Through the app, users can check the "recommended books list" and the "letter of books to give up." They can also read the "recommendation" and understand the specific reasons for each book's recommendation.

[1215] Users: Start reading according to the in-app reading plan and record their progress within the app when they finish, providing feedback for future recommendations.

[1216] Specific examples

[1217] Here is a concrete example: If a user takes photos of five unread books and uploads them to the app, the process is as follows:

[1218] 1. User: Take a photo of an unread book with your smartphone and save it in a dedicated app.

[1219] 2. Device: Click the "Upload Image" button in the app to upload the photo to the server.

[1220] 3. Server: The image analysis engine extracts the book information and obtains information on Book A (science fiction), Book B (business book), Book C (historical novel), Book D (self-help book), and Book E (fantasy).

[1221] 4. Server: Determine from past reading history that the user likes science fiction and self-help books.

[1222] 5. Server: Books A and D have high market valuations, so they are recommended books.

[1223] 6. Server: Generates a recommendation using the generative AI model, such as "Book A has an amazing story unfolding against the backdrop of the latest technological trends, making it perfect for you." A recommendation for Book D is also generated in a similar manner.

[1224] 7. Server: Taking into account the user's reading speed and lifestyle, propose a plan to read books A and D within one month.

[1225] 8. Device: The user checks this information within the app and begins reading according to the reading plan.

[1226] Examples of prompts include:

[1227] "Generate the best recommendation based on this user's reading history and market evaluation."

[1228] The above is a specific embodiment of the "Unread Books Clearing Advisor." Through this system, users can efficiently manage their unread books and enjoy a meaningful reading experience.

[1229] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1230] Step 1: Capture and upload an image

[1231] A user takes photos of unread books using a smartphone or digital camera. For example, a user takes photos of five unread books at once.

[1232] Input: Photo data taken by a smartphone or digital camera.

[1233] Output: Photo data saved in the dedicated app.

[1234] Save the photos taken by the device in the app, and then click the "Upload Image" button in the app. This will upload the photo data to the server.

[1235] Input: Saved photo data.

[1236] Output: Photo data uploaded to the server.

[1237] Step 2: Image analysis

[1238] The server receives the uploaded images and sends the image data to an image analysis engine (e.g., Google Cloud Vision API).

[1239] Input: Uploaded photo data.

[1240] Output: Book information in an image (title, author, ISBN, etc.).

[1241] The server uses an image analysis engine to extract book information from the image, which is then stored in a database.

[1242] Input: Analysis results from the image analysis engine.

[1243] Output: Book information stored in a database.

[1244] Step 3: View and analyze your reading history

[1245] The server accesses the user's reading history database and retrieves data such as books read in the past, ratings, and reading frequency.

[1246] Input: A database of the user's past reading history.

[1247] Output: The retrieved reading history data.

[1248] The server analyzes the user's reading habits based on the reading history data it acquires. For example, it identifies the user's favorite genres and highly rated books.

[1249] Input: Reading history data.

[1250] Output: Analyzed reading trend data.

[1251] Step 4: Obtain market valuation data

[1252] Based on the book information extracted by image analysis, the server obtains market evaluation data for each book from the Internet, for example, by collecting data from online bookstores and review sites.

[1253] Input: Book information.

[1254] Output: Collected market valuation data.

[1255] The server aggregates the acquired market evaluation data and assigns a market evaluation score to each book.

[1256] Input: Market valuation data.

[1257] Output: A market rating score given to each book.

[1258] Step 5: Selecting recommended books

[1259] The server rates each book's importance based on the user's reading habits and market rating score.

[1260] Inputs: Reading trend data, market evaluation scores.

[1261] Output: The importance of the rated book.

[1262] The server classifies books with high scores into a "recommended book list" and books with low scores into a "not to be given up book list."

[1263] Input: Book importance.

[1264] Output: "Recommended books list" and "Let go books list".

[1265] Step 6: Generate testimonials

[1266] The server uses generative AI models (e.g., natural language processing techniques) to generate recommendations for the selected books.

[1267] Input: "Recommended book list", generative model.

[1268] Output: The generated recommendation.

[1269] For example, it generates a recommendation such as, "Book A has an amazing story set against the backdrop of the latest technological trends, and is perfect for you."

[1270] Step 7: Create a reading plan

[1271] The server creates a reading plan taking into account the user's reading speed (estimated from past reading history) and daily rhythm (based on information registered by the user).

[1272] Input: Reading speed, lifestyle data.

[1273] Output: A realistic reading plan.

[1274] For example, present a plan to read book A in three weeks and book D in four weeks.

[1275] Step 8: Providing a User Interface

[1276] The device allows the user to check the "recommended books list" and the "let go books list" through the app.

[1277] Input: "Recommended Book List", "Let Go Book List".

[1278] Output: The list displayed on the user's screen.

[1279] The device provides the user with a recommendation for each book within the app, including specific reasons for recommending the book.

[1280] Input: The generated testimonial.

[1281] Output: The testimonial provided to the user.

[1282] Users can start reading according to an in-app reading plan and track their progress as they finish.

[1283] Input: Reading progress information.

[1284] Output: Feedback to receive next recommendation.

[1285] The above is a detailed description of the processing steps in a specific embodiment of the "Unread Book Clearing Advisor."

[1286] (Application example 1)

[1287] 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."

[1288] There is a need for a system that can efficiently manage the unread books that users have accumulated (so-called "tsundoku") and properly select books that they should read now or let go of. It is also necessary to have a system that allows users to visually check these books in a virtual bookstore and understand the specific reasons for the recommendations before purchasing or letting go of them. In addition, users can receive detailed recommendations based on their own reading habits, which will enable them to effectively plan their reading.

[1289] 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.

[1290] In this invention, the server includes image analysis means, reading history analysis means, market evaluation data acquisition means, recommended book selection means, recommendation statement generation means, reading plan creation means, user interface means, virtual exhibition space generation means, and prompt statement generation means, which enable the user to efficiently manage unread books, visually check books in the virtual space, and select recommended books based on specific recommendation reasons and create a reading plan.

[1291] "Image analysis means" refers to a device or software that analyzes image data and extracts book information (title, author name, ISBN, etc.).

[1292] "Reading history analysis means" refers to a device or software that analyzes a user's reading habits based on the user's past reading history.

[1293] The "market evaluation data acquisition means" is a device or software that acquires market evaluation data of books from online bookstores, review sites, and the like on the Internet.

[1294] The "recommended book selection means" is a device or software that selects books that should be read now or that should be discarded based on the user's reading habits and market evaluation score.

[1295] The "recommendation generator" is a device or software that uses natural language processing technology to generate specific reasons for recommending a selected book.

[1296] A "reading plan creation tool" is a device or software that takes into account the user's reading speed and lifestyle and creates a realistic reading schedule.

[1297] "User interface means" means a device or software that provides a screen or method of operation through which a user can interact with the system and view recommended books, discarded books, recommendations, and reading plans.

[1298] A "virtual exhibition space generation means" is a device or software that uses virtual reality (VR) technology to generate an environment in which users can visually check unread books and recommended books in a virtual space.

[1299] A "prompt sentence generation means" is a device or software that generates an input sentence (prompt) for the generative AI model and obtains a specific reason for recommendation.

[1300] This invention is a system that allows users to efficiently manage their piles of unread books (so-called "tsundoku"), appropriately select books that should be read now or that should be let go, and purchase or let go of them while visually checking them in a virtual space. This system has the following main means.

[1301] The system consists of a server and a user's device (such as a smartphone or head-mounted display). Users take photos of unread books using their smartphone or digital camera and upload them through the application.

[1302] The server uses image analysis to extract book information (title, author, ISBN, etc.) from the uploaded image. This image analysis uses a common image analysis API (e.g., pytesseract).

[1303] Next, the server uses a reading history analysis means to refer to the user's past reading history database and analyze the user's reading habits (favorite genres, tendency of books rated, etc.). This information is stored in a user profile.

[1304] Using the market evaluation data acquisition means, the server acquires the latest market evaluation data (e.g., from online bookstores or review sites) for each book from the Internet based on the extracted book information. This data is analyzed, and a market evaluation score is assigned to each book.

[1305] Next, the recommendation book selection method evaluates the importance of each book based on the user's reading habits and market evaluation score. Highly rated books are classified into the "recommended books list," while low-rated books are classified into the "not recommended books list."

[1306] Using the recommendation generation means, the server uses a generative AI model (for example, OpenAI's text generation model) to generate a recommendation for the selected book. This recommendation includes specific reasons why the book should be read and information specific to the user's interests. For example, a prompt for the generative AI model might be, "The user's reading habits are 'science fiction' and 'self-help books.' Why do you recommend 'Book A'? Please explain the specific reasons."

[1307] The server creates a realistic reading plan based on the user's reading speed (estimated from past reading history) and daily rhythm (based on information registered by the user). This plan includes a schedule of when each book should be completed.

[1308] The virtual exhibition space generating means uses virtual reality (VR) technology to generate an environment in which the user can freely walk around the bookstore and visually check unread books and recommended books in the virtual space. The user interface means allows the user to check the "recommended book list" and the "let go book list" and to view detailed recommendations for each.

[1309] Users can start reading according to the in-app reading plan, and when they finish, they can record their progress in the app and provide feedback to receive the next recommendation. This feedback keeps the user's reading habits updated.

[1310] For example, if a user takes photos of five unread books and uploads them to the app, the server uses an image analysis engine to extract information about each book. Based on this book information, market evaluation data is obtained and a market evaluation score is assigned to each book. Based on the user's past reading history, the app determines that the user prefers science fiction and self-help books. Highly rated science fiction book A and self-help book D are added to the recommended books list. Using a generative AI model, a specific recommendation is generated, such as, "Book A has an amazing story unfolding against the backdrop of the latest technological trends, making it perfect for you." Taking into account the user's reading speed and lifestyle, the app then suggests a plan for reading books A and D within one month.

[1311] The above is a concrete implementation of the "Unread Books Clearing Advisor." Through this system, users can efficiently manage their unread books and enjoy a meaningful reading experience.

[1312] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1313] Step 1:

[1314] Users take a photo of an unread book with their smartphone or digital camera, save it in the app, and then click the "Upload Image" button to upload the photo to the server.

[1315] Input: Photo of an unread book

[1316] Output: Uploaded photo

[1317] Step 2:

[1318] The server uses image analysis to extract book information (title, author, ISBN, etc.) from the uploaded photo. For image analysis, it uses a common image analysis API (e.g., pytesseract).

[1319] Input: Uploaded photo

[1320] Output: Book information (title, author, ISBN, etc.)

[1321] Step 3:

[1322] The server uses a reading history analysis means to refer to the user's past reading history database and analyze the user's reading tendencies (favorite genres, tendency of books rated, etc.).

[1323] Input: User's past reading history

[1324] Output: User's reading habits

[1325] Step 4:

[1326] The server uses the market evaluation data acquisition means to acquire the latest market evaluation data for each book from the Internet based on the extracted book information, analyzes the acquired data, and assigns a market evaluation score to each book.

[1327] Input: Book information (title, author, ISBN, etc.)

[1328] Output: Market rating score for the book

[1329] Step 5:

[1330] The server uses a recommended book selection method to evaluate the importance of each book based on the user's reading habits and market evaluation score. Highly rated books are classified into a "recommended book list" and low-rated books are classified into a "not-recommended book list."

[1331] Input: User's reading habits, market evaluation score

[1332] Output: Recommended books list, To-be-given books list

[1333] Step 6:

[1334] The server uses the recommendation generator to generate a recommendation for the selected book using a generative AI model, the recommendation including specific reasons why the book should be read and information specific to the user's interests.

[1335] Input: Recommended book list, user's reading habits

[1336] Output: Recommendation (e.g., "Book A is perfect for you because it tells an amazing story set against the backdrop of the latest technological trends.")

[1337] Step 7:

[1338] The server uses a reading plan generator to create a realistic reading schedule that takes into account the user's reading speed and daily routine, including a timeline for when each book should be completed.

[1339] Input: User's reading speed, daily routine, recommended book list

[1340] Output: Reading plan

[1341] Step 8:

[1342] The server uses a virtual exhibition space generating means and virtual reality (VR) technology to generate an environment in which the user can freely walk around the bookstore and visually check unread books and recommended books in the virtual space.

[1343] Input: Recommended books list, list of books to give up

[1344] Output: Virtual exhibition space

[1345] Step 9:

[1346] Through the user interface, the user can check the "recommended book list" and the "let go book list" and view detailed recommendations. Furthermore, the user can start reading according to the reading plan, and when they finish reading, the progress is recorded in the app, providing feedback for the next recommendation.

[1347] Input: Virtual exhibition space, recommendations, reading plan

[1348] Output: Reading progress feedback

[1349] 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.

[1350] The present invention is a system that effectively manages a user's unread books and proposes an optimal reading strategy taking into account reading habits and emotional state. Hereinafter, embodiments of the present invention will be described.

[1351] Image upload and analysis

[1352] User: Take a photo of an unread book with your smartphone.

[1353] On the device: The user takes a photo, saves it in the app, and then clicks the "Upload Image" button in the app to upload the photo to the server.

[1354] Server: Sends the received image data to the image analysis engine.

[1355] Server: The image analysis engine extracts text information from the image, detects the book title, author name, ISBN, etc., and stores this information in a database.

[1356] Reading history analysis

[1357] Server: Refers to the database of the user's past reading history and analyzes the user's reading habits (favorite genres, book ratings, etc.). It also updates the user profile and stores the latest reading habits data.

[1358] Obtaining market evaluation

[1359] Server: Based on the extracted book information, obtains market evaluation data for each book from the Internet.

[1360] Server: Aggregates the acquired market evaluation data, assigns an evaluation score to each book, and creates a list of recommended books and a list of books to be discarded based on that information.

[1361] Emotion recognition by emotion engine

[1362] On-device: Emotional data is collected using methods such as facial recognition and voice analysis to help the app understand the user's emotional state.

[1363] Server: Sends the collected emotion data to the emotion engine to analyze the user's current emotional state.

[1364] Selection of recommended books

[1365] Server: Based on the user's reading habits, emotional state, and market evaluation score, the server classifies books that should be read now into a recommended book list.

[1366] Server: By selecting recommended books based on emotional state, users can read books that suit their mood at the time.

[1367] Generating recommendation letters

[1368] Server: Uses a generative AI model to generate a recommendation for the selected book, taking into account the user's emotional state and providing specific reasons why the book should be read.

[1369] Creating a Reading Plan

[1370] Server: Creates a realistic reading plan based on the user's reading speed and lifestyle information. This plan includes a schedule for when each book should be completed.

[1371] User Interface

[1372] On your device: Through the app, users can view the "recommended books list" and "let go books list," as well as read the recommendations and understand the specific reasons for each book's recommendation.

[1373] Users: Start reading according to the in-app reading plan, and when they finish, record their progress in the app and receive next recommendations.

[1374] Specific examples

[1375] Here's a concrete example: If a user takes photos of five unread books and uploads them to the app, the following process will occur:

[1376] 1. Device: The user uploads five photos.

[1377] 2. Server: The image analysis engine extracts book information and obtains Book A (science fiction), Book B (business book), Book C (historical novel), Book D (self-help book), and Book E (fantasy).

[1378] 3. Server: Analyzes the user's past reading history and finds that they like science fiction and self-help books.

[1379] 4. Server: Books A and D have high market ratings, so they are classified into the recommended books list.

[1380] 5. Device: Recognizes the user's emotions and uses the emotion engine to analyze that the current emotion is fatigue.

[1381] 6. Server: Recommend book D, which has relaxing content that suits the tired state.

[1382] 7. Server: Generate a recommendation, such as, "This self-help book contains many specific relaxation techniques and is perfect for my current tired state."

[1383] 8. Server: Taking into account the user's reading speed and lifestyle, propose a plan to read books A and D within one month.

[1384] 9. Device: The user sees the recommended book list and reading plan and begins reading.

[1385] The above is a specific implementation of the "Unread Books Clearing Advisor" that combines an emotion engine. This system manages and recommends unread books taking into account the user's emotional state, providing a meaningful reading experience.

[1386] The processing flow will be explained below.

[1387] Step 1:

[1388] User: Take a photo of an unread book with your smartphone.

[1389] Step 2:

[1390] On your device: Save the photo you took in the app and click the "Upload image" button in the app.

[1391] Step 3:

[1392] Terminal: Sends uploaded photo data to the server.

[1393] Step 4:

[1394] Server: Sends the received image data to the image analysis engine.

[1395] Step 5:

[1396] Server: The image analysis engine extracts text information from the image and detects the book title, author name, ISBN, etc.

[1397] Step 6:

[1398] Server: Organizes the detected book information and stores it in a database.

[1399] Step 7:

[1400] Server: Accesses the database of users' past reading history and analyzes their reading habits.

[1401] Step 8:

[1402] Server: Updates user profiles and stores the latest reading habits data.

[1403] Step 9:

[1404] Server: Based on the extracted book information, obtains market evaluation data for each book from the Internet.

[1405] Step 10:

[1406] Server: Aggregates the acquired market evaluation data and assigns an evaluation score to each book.

[1407] Step 11:

[1408] On-device: The app uses facial recognition and voice analysis to collect emotional data to understand the user's emotional state.

[1409] Step 12:

[1410] Terminal: Sends collected emotion data to the server.

[1411] Step 13:

[1412] Server: The emotion engine analyzes the received emotion data and determines the user's current emotional state.

[1413] Step 14:

[1414] Server: Categorizes books to be read into a recommended book list based on the user's reading habits, emotional state, and rating scores.

[1415] Step 15:

[1416] Server: Uses a generative AI model to generate recommendations for selected books, including specific reasons that take into account the user's emotional state.

[1417] Step 16:

[1418] Server: Creates a realistic reading plan based on the user's reading speed and lifestyle information.

[1419] Step 17:

[1420] Server: Sends the created reading plan and recommended book information to the user's terminal.

[1421] Step 18:

[1422] On your device: Display recommended books and testimonials within the app for users to review.

[1423] Step 19:

[1424] On-device: The reading plan is displayed within the app, allowing users to track their progress.

[1425] Step 20:

[1426] User: Start reading the recommended book and track your progress within the app as you read.

[1427] Example 2

[1428] 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."

[1429] In modern society, many users have a large number of unread books, and find it difficult to manage them and progress in their reading. Furthermore, it is difficult to select appropriate books based on the user's emotional state, which can reduce the quality of the reading experience. There is a need to solve these problems and provide a more effective and efficient reading management and recommendation system.

[1430] 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.

[1431] In this invention, the server includes image analysis means, reading history analysis means, market evaluation data acquisition means, emotion data collection means, emotion state analysis means, recommended book selection means, recommendation statement generation means, reading plan creation means, and user interface means, which enable effective management of unread books for the user and further enable appropriate book recommendations taking into account the user's emotional state.

[1432] "Image analysis means" refers to a means of extracting text information from images uploaded by users and obtaining data such as book titles, author names, and ISBNs.

[1433] The "reading history analysis means" is a means for analyzing a user's past reading history data and identifying reading tendencies and preferred genres.

[1434] The "market evaluation data acquisition means" is a means for collecting market evaluation data of books from the Internet and assigning an evaluation score to each book.

[1435] "Emotional data collection means" refers to a means of collecting emotional data through facial recognition and voice analysis of the user.

[1436] The "emotional state analysis means" is a means for analyzing collected emotional data and identifying the user's current emotional state.

[1437] The "recommended book selection method" is a method for selecting appropriate books based on the user's reading habits, emotional state, and market evaluation score.

[1438] The "recommendation generation means" is a means for creating a recommendation for a selected book using a generative AI model.

[1439] The "reading plan creation tool" is a tool that creates a realistic reading plan based on the user's reading speed and lifestyle information.

[1440] "User interface means" means by which a user interacts with the system and views recommended book lists and reading plans.

[1441] The present invention provides a system that effectively manages a user's unread books and proposes an optimal reading strategy by taking into account their reading habits and emotional state. The system includes image analysis means, reading history analysis means, market evaluation data acquisition means, emotional data collection means, emotional state analysis means, recommended book selection means, recommendation message generation means, reading plan creation means, and user interface means. This allows for effective and efficient management of a user's unread books and the provision of recommended books.

[1442] Image upload and analysis

[1443] User:

[1444] Take a photo of an unread book with your smartphone. Specifically, open the camera app, center the book cover, and press the capture button.

[1445] Device:

[1446] Save the photos you take in the app, then click the "Upload Image" button in the app to upload the photos to the server. The device will then send the image data to the server.

[1447] server:

[1448] The received image data is sent to an image analysis engine, specifically using OCR technology, which extracts text information from the image (such as the book title, author name, ISBN, etc.) and stores that information in a database.

[1449] Reading history analysis

[1450] server:

[1451] Retrieve the user's past reading history from the database. Analyze past ratings, genres of books read, favorite authors, etc. Update the user profile if new trends are found.

[1452] Obtaining market evaluation

[1453] server:

[1454] Based on the extracted book information, market evaluation data is obtained from review sites and book databases (e.g., major bibliographic information sites, online bookstores) for each book. The obtained data is aggregated and an evaluation score is assigned to each book.

[1455] Emotion recognition by emotion engine

[1456] Device:

[1457] To recognize the user's emotional state, the system uses a smartphone camera for facial recognition and a voice assistant to collect voice data, which is then sent to a server.

[1458] server:

[1459] The received emotional data is analyzed by the emotion analysis engine to determine the current emotional state (e.g., tired, relaxed, stressed).

[1460] Selection of recommended books

[1461] server:

[1462] The system comprehensively assesses the user's reading habits, current emotional state, and market evaluation score to add the best books to the recommended book list, with a particular focus on books that match the user's current emotional state.

[1463] Generating recommendation letters

[1464] server:

[1465] Based on the selected book information, a prompt is input into a generative AI model (e.g., GPT-4) to generate a recommendation. Example prompt: "The user is currently feeling tired. This self-help book contains many specific relaxation techniques and is perfect for this tired state."

[1466] Creating a Reading Plan

[1467] server:

[1468] Based on the user's reading speed and lifestyle information, a realistic reading plan is created, including the estimated completion date for each book.

[1469] User Interface

[1470] Device:

[1471] The app displays a recommended book list and reading plan to users, and after checking the displayed content, users can start reading according to the plan.

[1472] Adding specific examples

[1473] For example, if a user takes photos of five unread books and uploads them to the app, the process would look like this:

[1474] 1. Device: The user uploads five photos.

[1475] 2. Server: The image analysis engine extracts book information and obtains Book A (science fiction), Book B (business book), Book C (historical novel), Book D (self-help book), and Book E (fantasy).

[1476] 3. Server: Analyzes the user's past reading history and finds that they like science fiction and self-help books.

[1477] 4. Server: Books A and D have high market ratings, so they are classified into the recommended books list.

[1478] 5. Device: Recognizes the user's emotions and uses the emotion engine to analyze that the current emotion is fatigue.

[1479] 6. Server: Recommend book D, which has relaxing content that suits the tired state.

[1480] 7. Server: Generate a recommendation, such as, "This self-help book contains many specific relaxation techniques and is perfect for my current tired state."

[1481] 8. Server: Taking into account the user's reading speed and lifestyle, propose a plan to read books A and D within one month.

[1482] 9. Device: The user sees the recommended book list and reading plan and begins reading.

[1483] The above is a specific implementation of the "Unread Books Clearing Advisor" that combines an emotion engine. This system manages and recommends unread books taking into account the user's emotional state, providing a meaningful reading experience.

[1484] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1485] Step 1:

[1486] User: Take a photo of an unread book with your smartphone.

[1487] Input: An image of a book taken with a smartphone camera.

[1488] Output: Book image files.

[1489] Specific actions: Launch the camera app, center the book cover, and press the capture button.

[1490] Step 2:

[1491] Device: Save the photo in the app and upload it to the server.

[1492] Input: Book image files.

[1493] Output: Sending image data to the server.

[1494] Specific operation: The captured photo is saved in the app, and the user clicks the "Upload image" button in the app. The device sends the image data to the server.

[1495] Step 3:

[1496] Server: Analyzes the image, extracts book information, and stores it in a database.

[1497] Input: Uploaded book image.

[1498] Output: Book information (title, author, ISBN) stored in a database.

[1499] Specific operation: The received image data is analyzed using OCR technology to extract text information from the image, detecting the book title, author name, and ISBN, and storing that information in a database.

[1500] Step 4:

[1501] Server: Refers to the user's reading history and analyzes reading trends.

[1502] Input: The user's reading history stored in a database.

[1503] Output: An updated profile of the user's reading habits as a result of the analysis.

[1504] What it does: It analyzes past reading history, attributes such as ratings, genres, and authors to identify users' reading habits, and updates their user profile if new habits are found.

[1505] Step 5:

[1506] Server: Collects book market evaluation data from the Internet.

[1507] Input: Extracted book information (title, author, ISBN).

[1508] Output: Book information with rating scores.

[1509] Specific operation: Based on book information, evaluation data is obtained from review sites and online bookstores, and evaluation scores are compiled and assigned to each book.

[1510] Step 6:

[1511] Terminal: Collects user emotional data.

[1512] Input: User's facial recognition image data and voice data.

[1513] Output: Sending emotion data to the server.

[1514] Specific operation: Facial recognition is performed using the smartphone camera, and voice recordings are collected using the voice assistant. The collected data is then sent to a server.

[1515] Step 7:

[1516] Server: Analyzes the emotional data to determine the current emotional state.

[1517] Input: Collected emotion data (face recognition images, audio data).

[1518] Output: Current emotional state judgment result.

[1519] What it does: The emotion analysis engine analyzes facial recognition data and voice data to determine the current emotional state.

[1520] Step 8:

[1521] Server: Selects recommended books based on reading habits, emotional state, and market evaluation.

[1522] Input: Reading habits profile, emotional state assessment results, market evaluation data.

[1523] Output: A list of recommended books.

[1524] Specific operation: Comprehensively evaluate the user's reading habits, current emotional state, and market evaluation score, select the most suitable books, and add them to the recommended book list.

[1525] Step 9:

[1526] Server: Generates recommendations for selected books using a generative AI model.

[1527] Input: Recommended book list.

[1528] Output: The generated recommendation.

[1529] Specific behavior: A prompt is input into a generative AI model (e.g., GPT-4) to generate a recommendation. Example prompt: "The user is currently feeling tired. This self-help book contains many specific relaxation techniques and is perfect for this tired state."

[1530] Step 10:

[1531] Server: Creates a reading plan for the user.

[1532] Input: User's reading speed, lifestyle information, recommended book list.

[1533] Output: Reading plan.

[1534] What it does: Create a realistic reading plan based on the user's reading speed and lifestyle information, including estimated completion dates for each book.

[1535] Step 11:

[1536] Device: Provides users with recommended book lists and reading plans.

[1537] Input: Recommended book list, reading plan.

[1538] Output: Information displayed by the user interface.

[1539] Specific operation: Display recommended book lists and reading plans to users through the app screen, allowing users to start reading based on them.

[1540] (Application example 2)

[1541] 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."

[1542] Conventional reading recommendation systems recommend books based solely on reading history and market evaluations, without taking into account the user's emotional state or usage environment, making it difficult for users to read the right book at the optimal time. In addition, users of smart devices need a system that can maximize their convenience.

[1543] 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.

[1544] In this invention, the server includes image analysis means, reading history analysis means, market evaluation data acquisition means, emotion recognition means, recommended book selection means, recommendation statement generation means, reading plan creation means, and smart device interface means, thereby enabling accurate book recommendations and the creation of reading plans that take into account the user's emotional state and usage environment.

[1545] 1. "Image analysis means" refers to a device or program that extracts text information from captured image data and detects book titles, author names, ISBNs, etc.

[1546] 2. "Reading history analysis means" refers to a device or program that refers to a user's past reading history and analyzes their reading habits.

[1547] 3. "Market evaluation data acquisition means" refers to a device or program that acquires and compiles market evaluation data for each book from the Internet.

[1548] 4. "Emotion recognition means" means a device or program that recognizes a user's emotional state using methods such as facial recognition or voice analysis.

[1549] 5. "Recommended book selection means" refers to a device or program that selects books to read based on a user's reading habits, emotional state, and market evaluation data.

[1550] 6. "Recommendation generation means" means a device or program consisting of a generative AI model that generates recommendations for selected books.

[1551] 7. "Reading plan creation means" means a device or program that creates a realistic reading plan based on the user's reading speed and lifestyle information.

[1552] 8. "Smart device interface means" means a device or program that provides information to a user through a device such as a smartphone or smart glasses.

[1553] This invention is a system that utilizes a smart device installed in an autonomous vehicle to effectively manage a user's unread books and propose an optimal reading strategy taking into account reading habits and emotional state. The following describes an embodiment of the invention.

[1554] Hardware and software used

[1555] Hardware:

[1556] Smart glasses and smartphones

[1557] Autonomous vehicle computer systems

[1558] software:

[1559] Python

[1560] OpenCV (image processing library)

[1561] FacialRecognition (emotion recognition library)

[1562] OCREngine (OCR analysis library)

[1563] BookRecommender (recommendation algorithm)

[1564] RecommendationModel (generative AI model)

[1565] System Operation

[1566] Image upload and analysis

[1567] Users take a photo of an unread book with their smartphone. The device's smart glasses store the photo and upload it to the autonomous vehicle's computer system. The server then uses image analysis tools to extract text information from the image, such as the book's title, author, and ISBN, and stores that information in a database.

[1568] Reading history analysis

[1569] The server uses the reading history analysis means to refer to the database of the user's past reading history and analyze the reading habits, and this information is also stored in the database.

[1570] Obtaining market evaluation

[1571] The server uses the market evaluation data acquisition means to acquire market evaluation data for each book from the Internet based on the extracted book information. The acquired market evaluation data is aggregated and an evaluation score is assigned to each book.

[1572] emotion recognition means

[1573] The smart glasses on the device collect the user's facial expression data and send it to a server, which then analyzes this data using emotion recognition means to determine the user's current emotional state.

[1574] Selection of recommended books

[1575] The server uses a recommended book selection means to select books to read now based on reading habits, emotional state, and market evaluation data, and the selected book information is stored in a database.

[1576] Generating recommendation letters

[1577] The server uses the generative AI model to generate recommendations for the selected books, which are then displayed on the smart glasses.

[1578] Creating a Reading Plan

[1579] The server uses the reading plan creation means to create a realistic reading plan that takes into account the user's reading speed and travel time.

[1580] Specific examples and prompts for generative AI models

[1581] Specific examples

[1582] For example, if a user takes photos of five unread books with their smartphone while riding in a self-driving vehicle and uploads them to the vehicle's system, the process will proceed as follows: If the smart glasses analyze the user's facial expression and determine that the user's emotional state is "tired," a recommendation will be generated and displayed, saying, "This self-help book contains many specific relaxation techniques and is perfect for your current tired state."

[1583] Prompt Sentence Examples

[1584] Prompt statement:

[1585] "Generate a recommendation for a self-help book that is ideal for when the user is in a tired emotional state. The book title is "A Relaxing Life" and the author is "Taro Yamada.""

[1586] This provides an environment where users can read self-help books, which is ideal when they are tired.

[1587] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1588] Step 1:

[1589] The user takes a photo of an unread book with their smartphone, and the image data is input into the device.

[1590] Step 2:

[1591] The device stores the captured images and uploads them to the autonomous vehicle's system via smart glasses.

[1592] Input: Image of unread book

[1593] Data processing: Image saving and uploading

[1594] Output: Image data to the server

[1595] Step 3:

[1596] The server uses image analysis to extract text information from the uploaded image, specifically detecting information such as the book title, author name, and ISBN.

[1597] Input: Image data

[1598] Data calculation: OCR analysis

[1599] Output: Book information (title, author, ISBN)

[1600] Step 4:

[1601] The server stores the extracted book information in a database, which is used for subsequent analysis and evaluation.

[1602] Input: Book information

[1603] Data processing: information storage

[1604] Output: Book information in the database

[1605] Step 5:

[1606] The server uses a reading history analysis means to refer to the user's past reading history data and analyze their reading habits, which is then used to recommend new books.

[1607] Input: Reading history database

[1608] Data Computing: Reading Trend Analysis

[1609] Output: Reading habits data

[1610] Step 6:

[1611] The server uses the market evaluation data acquisition means to acquire market evaluation data for each book from the Internet, specifically, to collect reviews and evaluation scores for the book.

[1612] Input: Book information

[1613] Data calculation: Data acquisition from the Internet

[1614] Output: Market valuation data

[1615] Step 7:

[1616] The server aggregates the acquired market evaluation data and assigns each book an evaluation score, which is used to select recommended books.

[1617] Input: Market valuation data

[1618] Data calculation: Score assignment

[1619] Output: Evaluation score

[1620] Step 8:

[1621] The smart glasses on the device collect and transmit facial expression data from the user to a server, which is used to analyze the user's emotional state.

[1622] Input: facial expression data

[1623] Data Processing: Data Collection and Transmission

[1624] Output: Facial expression data to the server

[1625] Step 9:

[1626] The server analyzes the collected facial expression data using emotion recognition means to determine the user's current emotional state.

[1627] Input: facial expression data

[1628] Data Computing: Emotion Recognition

[1629] Output: Emotional state

[1630] Step 10:

[1631] The server uses a recommended book selection means to select books to read now based on reading habits, emotional state, and market evaluation data.

[1632] Input: Reading habits data, emotional state, evaluation score

[1633] Data calculation: Book selection

[1634] Output: Recommended book list

[1635] Step 11:

[1636] The server uses a generative AI model to generate a recommendation for the selected book, for example, using prompts to provide specific reasons for the recommendation.

[1637] Input: Recommended book list, emotional state

[1638] Data calculation: recommendation generation

[1639] Output: Recommendation

[1640] Step 12:

[1641] The server uses the reading plan creation means to create a realistic reading plan that takes into account the user's reading speed and usage environment (such as travel time).

[1642] Input: Reading speed, usage environment

[1643] Data calculation: Reading plan creation

[1644] Output: Reading plan

[1645] Step 13:

[1646] Users can view the recommended book list, recommendations, and reading plan through a smart device interface, such as smart glasses or a smartphone.

[1647] Input: Recommended book list, recommendation, reading plan

[1648] Data processing: Information display

[1649] Output: User confirmation and execution

[1650] 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.

[1651] 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.

[1652] 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.

[1653] [Fourth embodiment]

[1654] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1655] 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.

[1656] 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).

[1657] 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.

[1658] 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.

[1659] 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).

[1660] 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.

[1661] 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.

[1662] 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.

[1663] 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.

[1664] 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.

[1665] 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.

[1666] 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."

[1667] The present invention is a system that efficiently manages the unread books that a user has accumulated (so-called "tsundoku") and appropriately selects books that should be read now and books that should be let go. The following describes an embodiment of the present invention.

[1668] Image upload and analysis

[1669] User: Take a photo of an unread book using a smartphone or digital camera.

[1670] On the device: The user takes a photo, saves it in the app, and then clicks the "Upload Image" button in the app to upload the photo to the server.

[1671] Server: Receives the uploaded images and uses an image analysis engine (e.g., a common image analysis API) to extract book information (title, author, ISBN, etc.) from the images.

[1672] Reading history analysis

[1673] Server: Refers to the database of the user's past reading history and analyzes the user's reading habits (favorite genres, book ratings, etc.). This information is passed to the user profile, and the latest trend data reflecting the user's reading preferences is accumulated.

[1674] Obtaining market evaluation

[1675] Server: Based on the extracted book information, the server obtains the latest market evaluation data for each book from the Internet (e.g., online bookstores and review sites), aggregates the obtained data, and assigns a market evaluation score to each book.

[1676] Selection of recommended books

[1677] Server: Evaluates the importance of each book based on the user's reading habits and market evaluation score. Books with high scores are classified as "recommended books" and "books to be discarded" and "books to be discarded" respectively.

[1678] Generating recommendation letters

[1679] Server: Uses generative AI models (e.g., natural language processing techniques) to generate recommendations for selected books, including specific reasons why the book should be read and information specific to the user's interests.

[1680] Creating a Reading Plan

[1681] Server: Creates a realistic reading plan based on the user's reading speed (estimated from past reading history) and daily routine (based on user-provided information). The reading plan includes a schedule for when each book should be completed.

[1682] User Interface

[1683] On-device: Through the app, users can check the "recommended books list" and "list of books to give up." They can also read the "recommendation" and understand the specific reasons for each book's recommendation.

[1684] Users: Start reading according to the in-app reading plan, and when they finish, record their progress in the app to provide feedback for future recommendations.

[1685] Specific examples

[1686] Here's a concrete example: A user takes photos of five unread books and uploads them to the app.

[1687] 1. Device: Upload a photo.

[1688] 2. Server: The image analysis engine extracts book information and obtains Book A (science fiction), Book B (business book), Book C (historical novel), Book D (self-help book), and Book E (fantasy).

[1689] 3. Server: Determine from past reading history that the user prefers science fiction and self-help books.

[1690] 4. Server: Books A and D have high market valuations, so they are recommended books.

[1691] 5. Server: Generate a recommendation: "Book A has an amazing story set against the backdrop of the latest technological trends, and is perfect for you." Similarly, generate a recommendation for Book D.

[1692] 6. Server: Taking into account the user's reading speed and lifestyle, propose a plan to read books A and D within one month.

[1693] 7. Device: The user checks this information through the app and begins reading according to the reading plan.

[1694] The above is a specific implementation of the "Unread Books Clearing Advisor." Through this system, users can efficiently manage their unread books and enjoy a meaningful reading experience.

[1695] The processing flow will be explained below.

[1696] Step 1:

[1697] User: Take a photo of an unread book with your smartphone.

[1698] Step 2:

[1699] On the device: The captured photo is saved in the app, and the user clicks the "Upload image" button within the app.

[1700] Step 3:

[1701] Terminal: Sends uploaded photo data to the server.

[1702] Step 4:

[1703] Server: Sends the received image data to the analysis engine.

[1704] Step 5:

[1705] Server: The image analysis engine extracts text information from the image and detects the book title, author name, ISBN, etc.

[1706] Step 6:

[1707] Server: Organizes the detected book information and stores it in a database.

[1708] Step 7:

[1709] Server: Accesses the database of users' past reading history and analyzes their reading habits.

[1710] Step 8:

[1711] Server: Updates user profiles and stores the latest reading habits data.

[1712] Step 9:

[1713] Server: Based on the extracted book information, obtains market evaluation data for each book from the Internet.

[1714] Step 10:

[1715] Server: Aggregates the acquired market evaluation data and assigns an evaluation score to each book.

[1716] Step 11:

[1717] Server: Based on the user's reading habits and market evaluation scores, selects books to read and books to discard.

[1718] Step 12:

[1719] Server: Generates recommendations for selected books using a generative AI model.

[1720] Step 13:

[1721] Server: Creates a realistic reading plan based on the user's reading speed and lifestyle information.

[1722] Step 14:

[1723] Server: Sends the created reading plan and recommended book information to the terminal.

[1724] Step 15:

[1725] On your device: Display recommended books and testimonials within the app for users to review.

[1726] Step 16:

[1727] On-device: The reading plan is displayed within the app, allowing users to track their progress.

[1728] Step 17:

[1729] User: Start reading the recommended book and track your progress within the app as you read.

[1730] This is the specific process flow of the "Tsundoku Kakuri Advisor." This system allows users to efficiently manage their unread books and have a meaningful reading experience.

[1731] Example 1

[1732] 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."

[1733] Currently, many users have piled up unread books, making it difficult to manage them and determine which books they should prioritize. Furthermore, there are no clear criteria for selecting books to let go, making it difficult to efficiently manage reading.

[1734] 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.

[1735] In this invention, the server includes image analysis means, reading history analysis means, market evaluation data acquisition means, recommended book selection means, recommendation generation means using a generative AI model, reading plan creation means that takes into account reading speed and daily rhythm, and user interface means, allowing users to efficiently manage unread books and appropriately select books to read now and books to let go.

[1736] "Image analysis means" refers to a technical device that analyzes photographs or image data and extracts specific book information (title, author name, ISBN, etc.) from it.

[1737] "Reading history analysis means" refers to a technical device that collects and analyzes a user's past reading history data and derives the user's reading tendencies and preferences.

[1738] The "market evaluation data acquisition means" is a technical device that acquires data on the market evaluation of books from the Internet and assigns an evaluation score to each book.

[1739] The "recommended book selection means" is a technical device that combines the user's reading habits with market evaluation data to select highly important books and classify them into a recommended book list.

[1740] A "means for generating recommendation sentences using a generative AI model" is a technical device that uses a generative AI model (e.g., natural language processing technology) to generate recommendation sentences for selected books.

[1741] The "means for creating a reading plan that takes into account reading speed and lifestyle rhythm" is a technical device that creates a realistic and effective reading plan based on the user's reading speed and lifestyle rhythm.

[1742] "User interface means" means an interface device through which a user interacts with a system and inputs and obtains information.

[1743] The present invention provides a system for efficiently managing a user's pile of unread books and appropriately selecting books that should be read now and books that should be let go. The following describes an embodiment of the present invention.

[1744] Image upload and analysis

[1745] User: Take a photo of an unread book with a smartphone or digital camera. For example, you can take a photo of five unread books at once.

[1746] Device: The user saves the photos they have taken in a dedicated app and clicks the "Upload Image" button in the app to upload the photos to the server.

[1747] Server: Receives uploaded images and uses an image analysis engine (e.g., Google Cloud Vision API) to extract book information (title, author, ISBN, etc.) from the images. The extracted information is stored in a database.

[1748] Reading history analysis

[1749] Server: Refers to the database of the user's past reading history and analyzes the user's reading habits (favorite genres, book ratings, etc.). This information is reflected in the user profile and stored as the latest trend data.

[1750] Obtaining market evaluation

[1751] Server: Based on the book information extracted through image analysis, market evaluation data for each book is obtained from the Internet (e.g., online bookstores and review sites). The obtained data is aggregated and a market evaluation score is assigned to each book.

[1752] Selection of recommended books

[1753] Server: Based on the user's reading habits and market evaluation score, each book is individually rated for importance. Books with high importance are classified into the "recommended books list," while books with low importance are classified into the "not recommended books list."

[1754] Generating recommendation letters

[1755] Server: Uses generative AI models (e.g., natural language processing techniques) to generate recommendations for selected books, including specific reasons why the book should be read and information specific to the user's interests.

[1756] Creating a Reading Plan

[1757] Server: Creates a realistic reading plan based on the user's reading speed (estimated from past reading history) and daily rhythm (based on information registered by the user). The reading plan includes a schedule for when each book should be completed.

[1758] User Interface

[1759] On the device: Through the app, users can check the "recommended books list" and the "letter of books to give up." They can also read the "recommendation" and understand the specific reasons for each book's recommendation.

[1760] Users: Start reading according to the in-app reading plan and record their progress within the app when they finish, providing feedback for future recommendations.

[1761] Specific examples

[1762] Here is a concrete example: If a user takes photos of five unread books and uploads them to the app, the process is as follows:

[1763] 1. User: Take a photo of an unread book with your smartphone and save it in a dedicated app.

[1764] 2. Device: Click the "Upload Image" button in the app to upload the photo to the server.

[1765] 3. Server: The image analysis engine extracts the book information and obtains information on Book A (science fiction), Book B (business book), Book C (historical novel), Book D (self-help book), and Book E (fantasy).

[1766] 4. Server: Determine from past reading history that the user likes science fiction and self-help books.

[1767] 5. Server: Books A and D have high market valuations, so they are recommended books.

[1768] 6. Server: Generates a recommendation using the generative AI model, such as "Book A has an amazing story unfolding against the backdrop of the latest technological trends, making it perfect for you." A recommendation for Book D is also generated in a similar manner.

[1769] 7. Server: Taking into account the user's reading speed and lifestyle, propose a plan to read books A and D within one month.

[1770] 8. Device: The user checks this information within the app and begins reading according to the reading plan.

[1771] Examples of prompts include:

[1772] "Generate the best recommendation based on this user's reading history and market evaluation."

[1773] The above is a specific embodiment of the "Unread Books Clearing Advisor." Through this system, users can efficiently manage their unread books and enjoy a meaningful reading experience.

[1774] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1775] Step 1: Capture and upload an image

[1776] A user takes photos of unread books using a smartphone or digital camera. For example, a user takes photos of five unread books at once.

[1777] Input: Photo data taken by a smartphone or digital camera.

[1778] Output: Photo data saved in the dedicated app.

[1779] Save the photos taken by the device in the app, and then click the "Upload Image" button in the app. This will upload the photo data to the server.

[1780] Input: Saved photo data.

[1781] Output: Photo data uploaded to the server.

[1782] Step 2: Image analysis

[1783] The server receives the uploaded images and sends the image data to an image analysis engine (e.g., Google Cloud Vision API).

[1784] Input: Uploaded photo data.

[1785] Output: Book information in an image (title, author, ISBN, etc.).

[1786] The server uses an image analysis engine to extract book information from the image, which is then stored in a database.

[1787] Input: Analysis results from the image analysis engine.

[1788] Output: Book information stored in a database.

[1789] Step 3: View and analyze your reading history

[1790] The server accesses the user's reading history database and retrieves data such as books read in the past, ratings, and reading frequency.

[1791] Input: A database of the user's past reading history.

[1792] Output: The retrieved reading history data.

[1793] The server analyzes the user's reading habits based on the reading history data it acquires. For example, it identifies the user's favorite genres and highly rated books.

[1794] Input: Reading history data.

[1795] Output: Analyzed reading trend data.

[1796] Step 4: Obtain market valuation data

[1797] Based on the book information extracted by image analysis, the server obtains market evaluation data for each book from the Internet, for example, by collecting data from online bookstores and review sites.

[1798] Input: Book information.

[1799] Output: Collected market valuation data.

[1800] The server aggregates the acquired market evaluation data and assigns a market evaluation score to each book.

[1801] Input: Market valuation data.

[1802] Output: A market rating score given to each book.

[1803] Step 5: Selecting recommended books

[1804] The server rates each book's importance based on the user's reading habits and market rating score.

[1805] Inputs: Reading trend data, market evaluation scores.

[1806] Output: The importance of the rated book.

[1807] The server classifies books with high scores into a "recommended book list" and books with low scores into a "not to be given up book list."

[1808] Input: Book importance.

[1809] Output: "Recommended books list" and "Let go books list".

[1810] Step 6: Generate testimonials

[1811] The server uses generative AI models (e.g., natural language processing techniques) to generate recommendations for the selected books.

[1812] Input: "Recommended book list", generative model.

[1813] Output: The generated recommendation.

[1814] For example, it generates a recommendation such as, "Book A has an amazing story set against the backdrop of the latest technological trends, and is perfect for you."

[1815] Step 7: Create a reading plan

[1816] The server creates a reading plan taking into account the user's reading speed (estimated from past reading history) and daily rhythm (based on information registered by the user).

[1817] Input: Reading speed, lifestyle data.

[1818] Output: A realistic reading plan.

[1819] For example, present a plan to read book A in three weeks and book D in four weeks.

[1820] Step 8: Providing a User Interface

[1821] The device allows the user to check the "recommended books list" and the "let go books list" through the app.

[1822] Input: "Recommended Book List", "Let Go Book List".

[1823] Output: The list displayed on the user's screen.

[1824] The device provides the user with a recommendation for each book within the app, including specific reasons for recommending the book.

[1825] Input: The generated testimonial.

[1826] Output: The testimonial provided to the user.

[1827] Users can start reading according to an in-app reading plan and track their progress as they finish.

[1828] Input: Reading progress information.

[1829] Output: Feedback to receive next recommendation.

[1830] The above is a detailed description of the processing steps in a specific embodiment of the "Unread Book Clearing Advisor."

[1831] (Application example 1)

[1832] 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."

[1833] There is a need for a system that can efficiently manage the unread books that users have accumulated (so-called "tsundoku") and properly select books that they should read now or let go of. It is also necessary to have a system that allows users to visually check these books in a virtual bookstore and understand the specific reasons for the recommendations before purchasing or letting go of them. In addition, users can receive detailed recommendations based on their own reading habits, which will enable them to effectively plan their reading.

[1834] 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.

[1835] In this invention, the server includes image analysis means, reading history analysis means, market evaluation data acquisition means, recommended book selection means, recommendation statement generation means, reading plan creation means, user interface means, virtual exhibition space generation means, and prompt statement generation means, which enable the user to efficiently manage unread books, visually check books in the virtual space, and select recommended books based on specific recommendation reasons and create a reading plan.

[1836] "Image analysis means" refers to a device or software that analyzes image data and extracts book information (title, author name, ISBN, etc.).

[1837] "Reading history analysis means" refers to a device or software that analyzes a user's reading habits based on the user's past reading history.

[1838] The "market evaluation data acquisition means" is a device or software that acquires market evaluation data of books from online bookstores, review sites, and the like on the Internet.

[1839] The "recommended book selection means" is a device or software that selects books that should be read now or that should be discarded based on the user's reading habits and market evaluation score.

[1840] The "recommendation generator" is a device or software that uses natural language processing technology to generate specific reasons for recommending a selected book.

[1841] A "reading plan creation tool" is a device or software that takes into account the user's reading speed and lifestyle and creates a realistic reading schedule.

[1842] "User interface means" means a device or software that provides a screen or method of operation through which a user can interact with the system and view recommended books, discarded books, recommendations, and reading plans.

[1843] A "virtual exhibition space generation means" is a device or software that uses virtual reality (VR) technology to generate an environment in which users can visually check unread books and recommended books in a virtual space.

[1844] A "prompt sentence generation means" is a device or software that generates an input sentence (prompt) for the generative AI model and obtains a specific reason for recommendation.

[1845] This invention is a system that allows users to efficiently manage their piles of unread books (so-called "tsundoku"), appropriately select books that should be read now or that should be let go, and purchase or let go of them while visually checking them in a virtual space. This system has the following main means.

[1846] The system consists of a server and a user's device (such as a smartphone or head-mounted display). Users take photos of unread books using their smartphone or digital camera and upload them through the application.

[1847] The server uses image analysis to extract book information (title, author, ISBN, etc.) from the uploaded image. This image analysis uses a common image analysis API (e.g., pytesseract).

[1848] Next, the server uses a reading history analysis means to refer to the user's past reading history database and analyze the user's reading habits (favorite genres, tendency of books rated, etc.). This information is stored in a user profile.

[1849] Using the market evaluation data acquisition means, the server acquires the latest market evaluation data (e.g., from online bookstores or review sites) for each book from the Internet based on the extracted book information. This data is analyzed, and a market evaluation score is assigned to each book.

[1850] Next, the recommendation book selection method evaluates the importance of each book based on the user's reading habits and market evaluation score. Highly rated books are classified into the "recommended books list," while low-rated books are classified into the "not recommended books list."

[1851] Using the recommendation generation means, the server uses a generative AI model (for example, OpenAI's text generation model) to generate a recommendation for the selected book. This recommendation includes specific reasons why the book should be read and information specific to the user's interests. For example, a prompt for the generative AI model might be, "The user's reading habits are 'science fiction' and 'self-help books.' Why do you recommend 'Book A'? Please explain the specific reasons."

[1852] The server creates a realistic reading plan based on the user's reading speed (estimated from past reading history) and daily rhythm (based on information registered by the user). This plan includes a schedule of when each book should be completed.

[1853] The virtual exhibition space generating means uses virtual reality (VR) technology to generate an environment in which the user can freely walk around the bookstore and visually check unread books and recommended books in the virtual space. The user interface means allows the user to check the "recommended book list" and the "let go book list" and to view detailed recommendations for each.

[1854] Users can start reading according to the in-app reading plan, and when they finish, they can record their progress in the app and provide feedback to receive the next recommendation. This feedback keeps the user's reading habits updated.

[1855] For example, if a user takes photos of five unread books and uploads them to the app, the server uses an image analysis engine to extract information about each book. Based on this book information, market evaluation data is obtained and a market evaluation score is assigned to each book. Based on the user's past reading history, the app determines that the user prefers science fiction and self-help books. Highly rated science fiction book A and self-help book D are added to the recommended books list. Using a generative AI model, a specific recommendation is generated, such as, "Book A has an amazing story unfolding against the backdrop of the latest technological trends, making it perfect for you." Taking into account the user's reading speed and lifestyle, the app then suggests a plan for reading books A and D within one month.

[1856] The above is a concrete implementation of the "Unread Books Clearing Advisor." Through this system, users can efficiently manage their unread books and enjoy a meaningful reading experience.

[1857] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1858] Step 1:

[1859] Users take a photo of an unread book with their smartphone or digital camera, save it in the app, and then click the "Upload Image" button to upload the photo to the server.

[1860] Input: Photo of an unread book

[1861] Output: Uploaded photo

[1862] Step 2:

[1863] The server uses image analysis to extract book information (title, author, ISBN, etc.) from the uploaded photo. For image analysis, it uses a common image analysis API (e.g., pytesseract).

[1864] Input: Uploaded photo

[1865] Output: Book information (title, author, ISBN, etc.)

[1866] Step 3:

[1867] The server uses a reading history analysis means to refer to the user's past reading history database and analyze the user's reading tendencies (favorite genres, tendency of books rated, etc.).

[1868] Input: User's past reading history

[1869] Output: User's reading habits

[1870] Step 4:

[1871] The server uses the market evaluation data acquisition means to acquire the latest market evaluation data for each book from the Internet based on the extracted book information, analyzes the acquired data, and assigns a market evaluation score to each book.

[1872] Input: Book information (title, author, ISBN, etc.)

[1873] Output: Market rating score for the book

[1874] Step 5:

[1875] The server uses a recommended book selection method to evaluate the importance of each book based on the user's reading habits and market evaluation score. Highly rated books are classified into a "recommended book list" and low-rated books are classified into a "not-recommended book list."

[1876] Input: User's reading habits, market evaluation score

[1877] Output: Recommended books list, To-be-given books list

[1878] Step 6:

[1879] The server uses the recommendation generator to generate a recommendation for the selected book using a generative AI model, the recommendation including specific reasons why the book should be read and information specific to the user's interests.

[1880] Input: Recommended book list, user's reading habits

[1881] Output: Recommendation (e.g., "Book A is perfect for you because it tells an amazing story set against the backdrop of the latest technological trends.")

[1882] Step 7:

[1883] The server uses a reading plan generator to create a realistic reading schedule that takes into account the user's reading speed and daily routine, including a timeline for when each book should be completed.

[1884] Input: User's reading speed, daily routine, recommended book list

[1885] Output: Reading plan

[1886] Step 8:

[1887] The server uses a virtual exhibition space generating means and virtual reality (VR) technology to generate an environment in which the user can freely walk around the bookstore and visually check unread books and recommended books in the virtual space.

[1888] Input: Recommended books list, list of books to give up

[1889] Output: Virtual exhibition space

[1890] Step 9:

[1891] Through the user interface, the user can check the "recommended book list" and the "let go book list" and view detailed recommendations. Furthermore, the user can start reading according to the reading plan, and when they finish reading, the progress is recorded in the app, providing feedback for the next recommendation.

[1892] Input: Virtual exhibition space, recommendations, reading plan

[1893] Output: Reading progress feedback

[1894] 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.

[1895] The present invention is a system that effectively manages a user's unread books and proposes an optimal reading strategy taking into account reading habits and emotional state. Hereinafter, embodiments of the present invention will be described.

[1896] Image upload and analysis

[1897] User: Take a photo of an unread book with your smartphone.

[1898] On the device: The user takes a photo, saves it in the app, and then clicks the "Upload Image" button in the app to upload the photo to the server.

[1899] Server: Sends the received image data to the image analysis engine.

[1900] Server: The image analysis engine extracts text information from the image, detects the book title, author name, ISBN, etc., and stores this information in a database.

[1901] Reading history analysis

[1902] Server: Refers to the database of the user's past reading history and analyzes the user's reading habits (favorite genres, book ratings, etc.). It also updates the user profile and stores the latest reading habits data.

[1903] Obtaining market evaluation

[1904] Server: Based on the extracted book information, obtains market evaluation data for each book from the Internet.

[1905] Server: Aggregates the acquired market evaluation data, assigns an evaluation score to each book, and creates a list of recommended books and a list of books to be discarded based on that information.

[1906] Emotion recognition by emotion engine

[1907] On-device: Emotional data is collected using methods such as facial recognition and voice analysis to help the app understand the user's emotional state.

[1908] Server: Sends the collected emotion data to the emotion engine to analyze the user's current emotional state.

[1909] Selection of recommended books

[1910] Server: Based on the user's reading habits, emotional state, and market evaluation score, the server classifies books that should be read now into a recommended book list.

[1911] Server: By selecting recommended books based on emotional state, users can read books that suit their mood at the time.

[1912] Generating recommendation letters

[1913] Server: Uses a generative AI model to generate a recommendation for the selected book, taking into account the user's emotional state and providing specific reasons why the book should be read.

[1914] Creating a Reading Plan

[1915] Server: Creates a realistic reading plan based on the user's reading speed and lifestyle information. This plan includes a schedule for when each book should be completed.

[1916] User Interface

[1917] On your device: Through the app, users can view the "recommended books list" and "let go books list," as well as read the recommendations and understand the specific reasons for each book's recommendation.

[1918] Users: Start reading according to the in-app reading plan, and when they finish, record their progress in the app and receive next recommendations.

[1919] Specific examples

[1920] Here's a concrete example: If a user takes photos of five unread books and uploads them to the app, the following process will occur:

[1921] 1. Device: The user uploads five photos.

[1922] 2. Server: The image analysis engine extracts book information and obtains Book A (science fiction), Book B (business book), Book C (historical novel), Book D (self-help book), and Book E (fantasy).

[1923] 3. Server: Analyzes the user's past reading history and finds that they like science fiction and self-help books.

[1924] 4. Server: Books A and D have high market ratings, so they are classified into the recommended books list.

[1925] 5. Device: Recognizes the user's emotions and uses the emotion engine to analyze that the current emotion is fatigue.

[1926] 6. Server: Recommend book D, which has relaxing content that suits the tired state.

[1927] 7. Server: Generate a recommendation, such as, "This self-help book contains many specific relaxation techniques and is perfect for my current tired state."

[1928] 8. Server: Taking into account the user's reading speed and lifestyle, propose a plan to read books A and D within one month.

[1929] 9. Device: The user sees the recommended book list and reading plan and begins reading.

[1930] The above is a specific implementation of the "Unread Books Clearing Advisor" that combines an emotion engine. This system manages and recommends unread books taking into account the user's emotional state, providing a meaningful reading experience.

[1931] The processing flow will be explained below.

[1932] Step 1:

[1933] User: Take a photo of an unread book with your smartphone.

[1934] Step 2:

[1935] On your device: Save the photo you took in the app and click the "Upload image" button in the app.

[1936] Step 3:

[1937] Terminal: Sends uploaded photo data to the server.

[1938] Step 4:

[1939] Server: Sends the received image data to the image analysis engine.

[1940] Step 5:

[1941] Server: The image analysis engine extracts text information from the image and detects the book title, author name, ISBN, etc.

[1942] Step 6:

[1943] Server: Organizes the detected book information and stores it in a database.

[1944] Step 7:

[1945] Server: Accesses the database of users' past reading history and analyzes their reading habits.

[1946] Step 8:

[1947] Server: Updates user profiles and stores the latest reading habits data.

[1948] Step 9:

[1949] Server: Based on the extracted book information, obtains market evaluation data for each book from the Internet.

[1950] Step 10:

[1951] Server: Aggregates the acquired market evaluation data and assigns an evaluation score to each book.

[1952] Step 11:

[1953] On-device: The app uses facial recognition and voice analysis to collect emotional data to understand the user's emotional state.

[1954] Step 12:

[1955] Terminal: Sends collected emotion data to the server.

[1956] Step 13:

[1957] Server: The emotion engine analyzes the received emotion data and determines the user's current emotional state.

[1958] Step 14:

[1959] Server: Categorizes books to be read into a recommended book list based on the user's reading habits, emotional state, and rating scores.

[1960] Step 15:

[1961] Server: Uses a generative AI model to generate recommendations for selected books, including specific reasons that take into account the user's emotional state.

[1962] Step 16:

[1963] Server: Creates a realistic reading plan based on the user's reading speed and lifestyle information.

[1964] Step 17:

[1965] Server: Sends the created reading plan and recommended book information to the user's terminal.

[1966] Step 18:

[1967] On your device: Display recommended books and testimonials within the app for users to review.

[1968] Step 19:

[1969] On-device: The reading plan is displayed within the app, allowing users to track their progress.

[1970] Step 20:

[1971] User: Start reading the recommended book and track your progress within the app as you read.

[1972] Example 2

[1973] 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."

[1974] In modern society, many users have a large number of unread books, and find it difficult to manage them and progress in their reading. Furthermore, it is difficult to select appropriate books based on the user's emotional state, which can reduce the quality of the reading experience. There is a need to solve these problems and provide a more effective and efficient reading management and recommendation system.

[1975] 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.

[1976] In this invention, the server includes image analysis means, reading history analysis means, market evaluation data acquisition means, emotion data collection means, emotion state analysis means, recommended book selection means, recommendation statement generation means, reading plan creation means, and user interface means, which enable effective management of unread books for the user and further enable appropriate book recommendations taking into account the user's emotional state.

[1977] "Image analysis means" refers to a means of extracting text information from images uploaded by users and obtaining data such as book titles, author names, and ISBNs.

[1978] The "reading history analysis means" is a means for analyzing a user's past reading history data and identifying reading tendencies and preferred genres.

[1979] The "market evaluation data acquisition means" is a means for collecting market evaluation data of books from the Internet and assigning an evaluation score to each book.

[1980] "Emotional data collection means" refers to a means of collecting emotional data through facial recognition and voice analysis of the user.

[1981] The "emotional state analysis means" is a means for analyzing collected emotional data and identifying the user's current emotional state.

[1982] The "recommended book selection method" is a method for selecting appropriate books based on the user's reading habits, emotional state, and market evaluation score.

[1983] The "recommendation generation means" is a means for creating a recommendation for a selected book using a generative AI model.

[1984] The "reading plan creation tool" is a tool that creates a realistic reading plan based on the user's reading speed and lifestyle information.

[1985] "User interface means" means by which a user interacts with the system and views recommended book lists and reading plans.

[1986] The present invention provides a system that effectively manages a user's unread books and proposes an optimal reading strategy by taking into account their reading habits and emotional state. The system includes image analysis means, reading history analysis means, market evaluation data acquisition means, emotional data collection means, emotional state analysis means, recommended book selection means, recommendation message generation means, reading plan creation means, and user interface means. This allows for effective and efficient management of a user's unread books and the provision of recommended books.

[1987] Image upload and analysis

[1988] User:

[1989] Take a photo of an unread book with your smartphone. Specifically, open the camera app, center the book cover, and press the capture button.

[1990] Device:

[1991] Save the photos you take in the app, then click the "Upload Image" button in the app to upload the photos to the server. The device will then send the image data to the server.

[1992] server:

[1993] The received image data is sent to an image analysis engine, specifically using OCR technology, which extracts text information from the image (such as the book title, author name, ISBN, etc.) and stores that information in a database.

[1994] Reading history analysis

[1995] server:

[1996] Retrieve the user's past reading history from the database. Analyze past ratings, genres of books read, favorite authors, etc. Update the user profile if new trends are found.

[1997] Obtaining market evaluation

[1998] server:

[1999] Based on the extracted book information, market evaluation data is obtained from review sites and book databases (e.g., major bibliographic information sites, online bookstores) for each book. The obtained data is aggregated and an evaluation score is assigned to each book.

[2000] Emotion recognition by emotion engine

[2001] Device:

[2002] To recognize the user's emotional state, the system uses a smartphone camera for facial recognition and a voice assistant to collect voice data, which is then sent to a server.

[2003] server:

[2004] The received emotional data is analyzed by the emotion analysis engine to determine the current emotional state (e.g., tired, relaxed, stressed).

[2005] Selection of recommended books

[2006] server:

[2007] The system comprehensively assesses the user's reading habits, current emotional state, and market evaluation score to add the best books to the recommended book list, with a particular focus on books that match the user's current emotional state.

[2008] Generating recommendation letters

[2009] server:

[2010] Based on the selected book information, a prompt is input into a generative AI model (e.g., GPT-4) to generate a recommendation. Example prompt: "The user is currently feeling tired. This self-help book contains many specific relaxation techniques and is perfect for this tired state."

[2011] Creating a Reading Plan

[2012] server:

[2013] Based on the user's reading speed and lifestyle information, a realistic reading plan is created, including the estimated completion date for each book.

[2014] User Interface

[2015] Device:

[2016] The app displays a recommended book list and reading plan to users, and after checking the displayed content, users can start reading according to the plan.

[2017] Adding specific examples

[2018] For example, if a user takes photos of five unread books and uploads them to the app, the process would look like this:

[2019] 1. Device: The user uploads five photos.

[2020] 2. Server: The image analysis engine extracts book information and obtains Book A (science fiction), Book B (business book), Book C (historical novel), Book D (self-help book), and Book E (fantasy).

[2021] 3. Server: Analyzes the user's past reading history and finds that they like science fiction and self-help books.

[2022] 4. Server: Books A and D have high market ratings, so they are classified into the recommended books list.

[2023] 5. Device: Recognizes the user's emotions and uses the emotion engine to analyze that the current emotion is fatigue.

[2024] 6. Server: Recommend book D, which has relaxing content that suits the tired state.

[2025] 7. Server: Generate a recommendation, such as, "This self-help book contains many specific relaxation techniques and is perfect for my current tired state."

[2026] 8. Server: Taking into account the user's reading speed and lifestyle, propose a plan to read books A and D within one month.

[2027] 9. Device: The user sees the recommended book list and reading plan and begins reading.

[2028] The above is a specific implementation of the "Unread Books Clearing Advisor" that combines an emotion engine. This system manages and recommends unread books taking into account the user's emotional state, providing a meaningful reading experience.

[2029] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2030] Step 1:

[2031] User: Take a photo of an unread book with your smartphone.

[2032] Input: An image of a book taken with a smartphone camera.

[2033] Output: Book image files.

[2034] Specific actions: Launch the camera app, center the book cover, and press the capture button.

[2035] Step 2:

[2036] Device: Save the photo in the app and upload it to the server.

[2037] Input: Book image files.

[2038] Output: Sending image data to the server.

[2039] Specific operation: The captured photo is saved in the app, and the user clicks the "Upload image" button in the app. The device sends the image data to the server.

[2040] Step 3:

[2041] Server: Analyzes the image, extracts book information, and stores it in a database.

[2042] Input: Uploaded book image.

[2043] Output: Book information (title, author, ISBN) stored in a database.

[2044] Specific operation: The received image data is analyzed using OCR technology to extract text information from the image, detecting the book title, author name, and ISBN, and storing that information in a database.

[2045] Step 4:

[2046] Server: Refers to the user's reading history and analyzes reading trends.

[2047] Input: The user's reading history stored in a database.

[2048] Output: An updated profile of the user's reading habits as a result of the analysis.

[2049] What it does: It analyzes past reading history, attributes such as ratings, genres, and authors to identify users' reading habits, and updates their user profile if new habits are found.

[2050] Step 5:

[2051] Server: Collects book market evaluation data from the Internet.

[2052] Input: Extracted book information (title, author, ISBN).

[2053] Output: Book information with rating scores.

[2054] Specific operation: Based on book information, evaluation data is obtained from review sites and online bookstores, and evaluation scores are compiled and assigned to each book.

[2055] Step 6:

[2056] Terminal: Collects user emotional data.

[2057] Input: User's facial recognition image data and voice data.

[2058] Output: Sending emotion data to the server.

[2059] Specific operation: Facial recognition is performed using the smartphone camera, and voice recordings are collected using the voice assistant. The collected data is then sent to a server.

[2060] Step 7:

[2061] Server: Analyzes the emotional data to determine the current emotional state.

[2062] Input: Collected emotion data (face recognition images, audio data).

[2063] Output: Current emotional state judgment result.

[2064] What it does: The emotion analysis engine analyzes facial recognition data and voice data to determine the current emotional state.

[2065] Step 8:

[2066] Server: Selects recommended books based on reading habits, emotional state, and market evaluation.

[2067] Input: Reading habits profile, emotional state assessment results, market evaluation data.

[2068] Output: A list of recommended books.

[2069] Specific operation: Comprehensively evaluate the user's reading habits, current emotional state, and market evaluation score, select the most suitable books, and add them to the recommended book list.

[2070] Step 9:

[2071] Server: Generates recommendations for selected books using a generative AI model.

[2072] Input: Recommended book list.

[2073] Output: The generated recommendation.

[2074] Specific behavior: A prompt is input into a generative AI model (e.g., GPT-4) to generate a recommendation. Example prompt: "The user is currently feeling tired. This self-help book contains many specific relaxation techniques and is perfect for this tired state."

[2075] Step 10:

[2076] Server: Creates a reading plan for the user.

[2077] Input: User's reading speed, lifestyle information, recommended book list.

[2078] Output: Reading plan.

[2079] What it does: Create a realistic reading plan based on the user's reading speed and lifestyle information, including estimated completion dates for each book.

[2080] Step 11:

[2081] Device: Provides users with recommended book lists and reading plans.

[2082] Input: Recommended book list, reading plan.

[2083] Output: Information displayed by the user interface.

[2084] Specific operation: Display recommended book lists and reading plans to users through the app screen, allowing users to start reading based on them.

[2085] (Application example 2)

[2086] 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."

[2087] Conventional reading recommendation systems recommend books based solely on reading history and market evaluations, without taking into account the user's emotional state or usage environment, making it difficult for users to read the right book at the optimal time. In addition, users of smart devices need a system that can maximize their convenience.

[2088] 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.

[2089] In this invention, the server includes image analysis means, reading history analysis means, market evaluation data acquisition means, emotion recognition means, recommended book selection means, recommendation statement generation means, reading plan creation means, and smart device interface means, thereby enabling accurate book recommendations and the creation of reading plans that take into account the user's emotional state and usage environment.

[2090] 1. "Image analysis means" refers to a device or program that extracts text information from captured image data and detects book titles, author names, ISBNs, etc.

[2091] 2. "Reading history analysis means" refers to a device or program that refers to a user's past reading history and analyzes their reading habits.

[2092] 3. "Market evaluation data acquisition means" refers to a device or program that acquires and compiles market evaluation data for each book from the Internet.

[2093] 4. "Emotion recognition means" means a device or program that recognizes a user's emotional state using methods such as facial recognition or voice analysis.

[2094] 5. "Recommended book selection means" refers to a device or program that selects books to read based on a user's reading habits, emotional state, and market evaluation data.

[2095] 6. "Recommendation generation means" means a device or program consisting of a generative AI model that generates recommendations for selected books.

[2096] 7. "Reading plan creation means" means a device or program that creates a realistic reading plan based on the user's reading speed and lifestyle information.

[2097] 8. "Smart device interface means" means a device or program that provides information to a user through a device such as a smartphone or smart glasses.

[2098] This invention is a system that utilizes a smart device installed in an autonomous vehicle to effectively manage a user's unread books and propose an optimal reading strategy taking into account reading habits and emotional state. The following describes an embodiment of the invention.

[2099] Hardware and software used

[2100] Hardware:

[2101] Smart glasses and smartphones

[2102] Autonomous vehicle computer systems

[2103] software:

[2104] Python

[2105] OpenCV (image processing library)

[2106] FacialRecognition (emotion recognition library)

[2107] OCREngine (OCR analysis library)

[2108] BookRecommender (recommendation algorithm)

[2109] RecommendationModel (generative AI model)

[2110] System Operation

[2111] Image upload and analysis

[2112] Users take a photo of an unread book with their smartphone. The device's smart glasses store the photo and upload it to the autonomous vehicle's computer system. The server then uses image analysis tools to extract text information from the image, such as the book's title, author, and ISBN, and stores that information in a database.

[2113] Reading history analysis

[2114] The server uses the reading history analysis means to refer to the database of the user's past reading history and analyze the reading habits, and this information is also stored in the database.

[2115] Obtaining market evaluation

[2116] The server uses the market evaluation data acquisition means to acquire market evaluation data for each book from the Internet based on the extracted book information. The acquired market evaluation data is aggregated and an evaluation score is assigned to each book.

[2117] emotion recognition means

[2118] The smart glasses on the device collect the user's facial expression data and send it to a server, which then analyzes this data using emotion recognition means to determine the user's current emotional state.

[2119] Selection of recommended books

[2120] The server uses a recommended book selection means to select books to read now based on reading habits, emotional state, and market evaluation data, and the selected book information is stored in a database.

[2121] Generating recommendation letters

[2122] The server uses the generative AI model to generate recommendations for the selected books, which are then displayed on the smart glasses.

[2123] Creating a Reading Plan

[2124] The server uses the reading plan creation means to create a realistic reading plan that takes into account the user's reading speed and travel time.

[2125] Specific examples and prompts for generative AI models

[2126] Specific examples

[2127] For example, if a user takes photos of five unread books with their smartphone while riding in a self-driving vehicle and uploads them to the vehicle's system, the process will proceed as follows: If the smart glasses analyze the user's facial expression and determine that the user's emotional state is "tired," a recommendation will be generated and displayed, saying, "This self-help book contains many specific relaxation techniques and is perfect for your current tired state."

[2128] Prompt Sentence Examples

[2129] Prompt statement:

[2130] "Generate a recommendation for a self-help book that is ideal for when the user is in a tired emotional state. The book title is "A Relaxing Life" and the author is "Taro Yamada.""

[2131] This provides an environment where users can read self-help books, which is ideal when they are tired.

[2132] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2133] Step 1:

[2134] The user takes a photo of an unread book with their smartphone, and the image data is input into the device.

[2135] Step 2:

[2136] The device stores the captured images and uploads them to the autonomous vehicle's system via smart glasses.

[2137] Input: Image of unread book

[2138] Data processing: Image saving and uploading

[2139] Output: Image data to the server

[2140] Step 3:

[2141] The server uses image analysis to extract text information from the uploaded image, specifically detecting information such as the book title, author name, and ISBN.

[2142] Input: Image data

[2143] Data calculation: OCR analysis

[2144] Output: Book information (title, author, ISBN)

[2145] Step 4:

[2146] The server stores the extracted book information in a database, which is used for subsequent analysis and evaluation.

[2147] Input: Book information

[2148] Data processing: information storage

[2149] Output: Book information in the database

[2150] Step 5:

[2151] The server uses a reading history analysis means to refer to the user's past reading history data and analyze their reading habits, which is then used to recommend new books.

[2152] Input: Reading history database

[2153] Data Computing: Reading Trend Analysis

[2154] Output: Reading habits data

[2155] Step 6:

[2156] The server uses the market evaluation data acquisition means to acquire market evaluation data for each book from the Internet, specifically, to collect reviews and evaluation scores for the book.

[2157] Input: Book information

[2158] Data calculation: Data acquisition from the Internet

[2159] Output: Market valuation data

[2160] Step 7:

[2161] The server aggregates the acquired market evaluation data and assigns each book an evaluation score, which is used to select recommended books.

[2162] Input: Market valuation data

[2163] Data calculation: Score assignment

[2164] Output: Evaluation score

[2165] Step 8:

[2166] The smart glasses on the device collect and transmit facial expression data from the user to a server, which is used to analyze the user's emotional state.

[2167] Input: facial expression data

[2168] Data Processing: Data Collection and Transmission

[2169] Output: Facial expression data to the server

[2170] Step 9:

[2171] The server analyzes the collected facial expression data using emotion recognition means to determine the user's current emotional state.

[2172] Input: facial expression data

[2173] Data Computing: Emotion Recognition

[2174] Output: Emotional state

[2175] Step 10:

[2176] The server uses a recommended book selection means to select books to read now based on reading habits, emotional state, and market evaluation data.

[2177] Input: Reading habits data, emotional state, evaluation score

[2178] Data calculation: Book selection

[2179] Output: Recommended book list

[2180] Step 11:

[2181] The server uses a generative AI model to generate a recommendation for the selected book, for example, using prompts to provide specific reasons for the recommendation.

[2182] Input: Recommended book list, emotional state

[2183] Data calculation: recommendation generation

[2184] Output: Recommendation

[2185] Step 12:

[2186] The server uses the reading plan creation means to create a realistic reading plan that takes into account the user's reading speed and usage environment (such as travel time).

[2187] Input: Reading speed, usage environment

[2188] Data calculation: Reading plan creation

[2189] Output: Reading plan

[2190] Step 13:

[2191] Users can view the recommended book list, recommendations, and reading plan through a smart device interface, such as smart glasses or a smartphone.

[2192] Input: Recommended book list, recommendation, reading plan

[2193] Data processing: Information display

[2194] Output: User confirmation and execution

[2195] 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.

[2196] 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.

[2197] 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.

[2198] 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.

[2199] 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.

[2200] 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.

[2201] 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).

[2202] 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.

[2203] 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."

[2204] 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.

[2205] 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).

[2206] 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.

[2207] 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.

[2208] 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.

[2209] 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.

[2210] 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.

[2211] 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.

[2212] 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.

[2213] 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.

[2214] 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.

[2215] 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.

[2216] The following is further disclosed regarding the above embodiment.

[2217] (Claim 1)

[2218] Image analysis means;

[2219] A reading history analysis tool;

[2220] A means for obtaining market valuation data;

[2221] A means for selecting recommended books;

[2222] A recommendation generation means;

[2223] a reading planning tool;

[2224] User interface means;

[2225] A system including:

[2226] (Claim 2)

[2227] The system of claim 1, wherein the system analyzes a user's reading habits based on past reading history.

[2228] (Claim 3)

[2229] 10. The system of claim 1, wherein the market evaluation data for the book is obtained from the Internet.

[2230] "Example 1"

[2231] (Claim 1)

[2232] Image analysis means;

[2233] A reading history analysis tool;

[2234] A means for obtaining market valuation data;

[2235] A means for selecting recommended books;

[2236] A means for generating recommendation sentences using a generative AI model;

[2237] A reading plan creation tool that takes into account reading speed and daily rhythm;

[2238] User interface means;

[2239] A system including:

[2240] (Claim 2)

[2241] The system of claim 1, wherein the system analyzes a user's reading habits based on past reading history.

[2242] (Claim 3)

[2243] 10. The system of claim 1, wherein the market evaluation data for the book is obtained from the Internet.

[2244] "Application Example 1"

[2245] (Claim 1)

[2246] Image analysis means;

[2247] A reading history analysis tool;

[2248] A means for obtaining market valuation data;

[2249] A means for selecting recommended books;

[2250] A recommendation generation means;

[2251] a reading planning tool;

[2252] User interface means;

[2253] A virtual exhibition space generating means;

[2254] prompt sentence generation means;

[2255] A system including:

[2256] (Claim 2)

[2257] The system of claim 1, wherein the system analyzes a user's reading habits based on past reading history.

[2258] (Claim 3)

[2259] 10. The system of claim 1, wherein the market evaluation data for the book is obtained from the Internet.

[2260] "Example 2: Combining Emotion Engines"

[2261] (Claim 1)

[2262] Image analysis means;

[2263] A reading history analysis tool;

[2264] A means for obtaining market valuation data;

[2265] An emotion data collection means;

[2266] emotional state analysis means;

[2267] A means for selecting recommended books;

[2268] A recommendation generation means;

[2269] a reading planning tool;

[2270] User interface means;

[2271] A system including:

[2272] (Claim 2)

[2273] The system of claim 1, further comprising: analyzing a user's reading habits based on past reading history and current emotional state.

[2274] (Claim 3)

[2275] 10. The system of claim 1, wherein the market evaluation information for the book is obtained from a communication network.

[2276] "Application example 2 when combining emotion engines"

[2277] (Claim 1)

[2278] Image analysis means;

[2279] A reading history analysis tool;

[2280] A means for obtaining market valuation data;

[2281] An emotion recognition means;

[2282] A means for selecting recommended books;

[2283] A recommendation generation means;

[2284] a reading planning tool;

[2285] and a smart device interface means.

[2286] (Claim 2)

[2287] The system according to claim 1, wherein the system analyzes a user's reading habits based on past reading history.

[2288] (Claim 3)

[2289] 10. The system of claim 1, wherein the market evaluation data for the book is obtained from a network. [Explanation of symbols]

[2290] 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. Image analysis means; A reading history analysis tool; A means for obtaining market valuation data; A means for selecting recommended books; A recommendation generation means; a reading planning tool; User interface means; A system including:

2. The system according to claim 1, wherein the system analyzes the user's reading habits based on past reading history.

3. 10. The system of claim 1, wherein the market evaluation data for the book is obtained from the Internet.

Images