System
The system uses a generative AI model to create tailored book summaries, addressing the challenge of time constraints and comprehension difficulties, improving reading efficiency and comprehension.
Patent Information
- Application Number
- JP2024133502
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2024-08-08
- Publication Date
- 2026-02-20
AI Technical Summary
Modern society faces challenges in finding time to read and understanding specialized or difficult books efficiently, with existing book summarization systems failing to provide summaries tailored to users' desired reading time and age.
A system utilizing a generative AI model to create summaries based on user input, including reading time, word count, and generation, with permission from authors and publishers, and optionally incorporating an emotion engine to adjust content.
Enables efficient understanding of book content within limited time, providing summaries that are easy to comprehend and tailored to individual needs, enhancing self-improvement and knowledge absorption.
Smart Images

Figure 2026030519000001_ABST
Abstract
Description
[Technical Field]
[0001] The technology of the present disclosure relates to a system. [Background technology]
[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]
[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]
[0004] In modern society, many people lead busy daily lives, making it difficult to find enough time to read. While reading is important for self-improvement and broadening knowledge, it is not easy to understand specialized or difficult books in a short amount of time. The purpose of this invention is to eliminate these time constraints and difficulties in comprehension, thereby enabling efficient reading and knowledge absorption. [Means for solving the problem]
[0005] The present invention is a system that includes the following means. First, a means for acquiring electronic data is provided, and book data is acquired with permission from the author and publisher. Next, a means is provided for the user to input the desired reading time, number of characters, and generation, and a means is provided for creating a summary using a generation AI based on the input information. This generation means adjusts words and expressions according to the user's generation, generating a summary that is easy to understand in a short amount of time. The system also includes a means for displaying the generated summary to the user, providing information efficiently. This configuration makes it easy for even busy modern people to understand the contents of a book in a short amount of time.
[0006] "Electronic data" refers to documents and content recorded in text format or a similar format, and primarily refers to book information licensed by authors and publishers.
[0007] "Means of acquisition" refers to the mechanisms and methods used to collect electronic data from databases and the Internet.
[0008] "User" refers to the end user who uses the summary service, and is the entity who inputs information such as reading time, desired number of characters, and generation.
[0009] "Input means" refers to an interface or device that allows the user to input necessary information such as reading time, number of characters, and generation.
[0010] "Means of generation" refers to the mechanism that processes input information to create a summary, and often refers specifically to generative AI.
[0011] A "summary" is a piece of writing that extracts the main parts or episodes from an original book or document and summarizes the main points concisely so that they can be understood in a short amount of time.
[0012] The "displaying means" refers to a method or device for visualizing the generated summary on a user's terminal so that it can be viewed. [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 uses a generative AI to provide a summary of a book with permission from the author and publisher. An embodiment of the system will be described below.
[0035] System configuration
[0036] This system is mainly composed of three elements: a server, a terminal, and a user.
[0037] server
[0038] The server plays a central role in this system and has the following functions:
[0039] 1. Electronic data acquisition: Electronic data with permission from the authors and publishers will be acquired from databases.
[0040] 2. Request processing: Receives the request sent from the terminal and analyzes its contents.
[0041] 3. Generative AI summary creation: Generate summaries based on user-specified reading time, word count, and generation.
[0042] 4. Send Abstract: Send the generated abstract to the terminal.
[0043] Terminal
[0044] The terminal is a device where users can enter requests through an interface and view the generated summaries. It has the following features:
[0045] 1. Providing an input interface: Provide a form for users to input reading time, word count, generation, book title, etc.
[0046] 2. Sending the request: Send the input request to the server.
[0047] 3. Display Abstract: The abstract received from the server is displayed to the user.
[0048] User
[0049] The user is the entity that uses this system and performs the following operations:
[0050] 1. Enter information: Enter reading time, word count, generation, and book title.
[0051] 2. Submit your request: Once you've completed the input, submit your request.
[0052] 3. Viewing the summary: The summary sent from the server is viewed on the terminal.
[0053] System operation example
[0054] A specific example of the operation of this system is shown below.
[0055] Example 1: Summary request for "young people" and "less than 10 minutes"
[0056] The user opens the device interface, enters the title of the book they want to read as "A Science Fiction," sets the desired reading time as "10 minutes or less," sets the desired word count as "1,000 characters," and sets the target age group as "Young people." Once they've completed the input, they press the send request button.
[0057] The terminal sends the input information to the server, which receives the request, retrieves the electronic data for "A Certain Science Fiction" from the database, and confirms that the book has been licensed.
[0058] The server passes the acquired digital data to a generation AI that creates a summary based on the user's wishes. The generation AI extracts key episodes and key points and generates a summary that can be read in under 10 minutes, using language appropriate for young people.
[0059] The server formats the generated summary and sends it to the terminal, which displays it on its user interface, allowing the user to read the summary within 10 minutes.
[0060] System convenience
[0061] This system allows users to efficiently understand the main content of a book within a limited time. It also makes difficult content easier to understand by appropriately summarizing it. Therefore, it can be said that this system greatly contributes to users' self-improvement and knowledge improvement.
[0062] The above is a concrete example of how the present invention can be implemented. This system provides flexible summaries tailored to the user's needs, improving reading efficiency and comprehension.
[0063] The processing flow will be explained below.
[0064] Step 1:
[0065] The user opens a summary request form in a device application or website.
[0066] Step 2:
[0067] The user fills out a form with the title of the book or books they want to read, the author's name, the desired reading time, the desired word count, and their generation.
[0068] Step 3:
[0069] The user presses the "Send Request" button to send the input information to the server.
[0070] Step 4:
[0071] The terminal converts the user's input information into an appropriate data format such as JSON and sends it to the server as an HTTP request (e.g., POST request).
[0072] Step 5:
[0073] The server receives the request data sent from the terminal.
[0074] Step 6:
[0075] The server checks the database to see if the specified book or publication has been licensed by the author and publisher.
[0076] Step 7:
[0077] If the permission is confirmed, the server retrieves the electronic data of the specified book from the database. If the permission is not confirmed, the server generates an error message and returns it to the terminal.
[0078] Step 8:
[0079] The server passes the acquired electronic data and the user's requests (desired reading time, number of characters, generation) to the generation AI.
[0080] Step 9:
[0081] The generative AI analyzes the provided electronic data and automatically extracts key points and episodes.
[0082] Step 10:
[0083] The AI then uses the extracted points to generate a summary that fits the specified time and number of characters, adjusting the words and expressions to suit the user's generation.
[0084] Step 11:
[0085] The server converts the summary received from the generation AI into an appropriate format, such as HTML or plain text.
[0086] Step 12:
[0087] The server sends the formatted summary to the terminal as an HTTP response.
[0088] Step 13:
[0089] The terminal receives the summary data sent from the server.
[0090] Step 14:
[0091] The terminal displays the received summary on a user interface.
[0092] Step 15:
[0093] The user views the generated summary on the terminal.
[0094] Example 1
[0095] 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."
[0096] In modern society, there is a huge amount of information and books available, and people are required to understand their content efficiently within a limited time. However, conventional book summarization systems have difficulty providing appropriate summaries that suit the user's desired reading time and age, and there is a lack of means to provide easy-to-understand summaries.
[0097] 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.
[0098] In this invention, the server includes a means for acquiring electronic data, a means for analyzing a request and acquiring electronic data from a database, a means for passing a prompt sentence to a generative AI model and generating a summary, and a means for formatting the generated summary and sending it to a terminal. This makes it possible to efficiently provide appropriate and easy-to-understand summaries according to the user's desired reading time, number of characters, and generation.
[0099] "Electronic data" refers to digital information handled by computers and electronic devices, including the contents of books and documents.
[0100] "User" refers to the primary user who uses the System to input information and receive book summaries.
[0101] A "request" refers to a request from a user to the system for specific processing or information provision.
[0102] "Server" refers to the computer system that plays a central role in this system and performs tasks such as analyzing requests, acquiring data, and running generative AI.
[0103] A "database" refers to a system that organizes and stores electronic data so that it can be efficiently searched when needed.
[0104] A "generative AI model" refers to an artificial intelligence system that generates and summarizes sentences using natural language processing techniques, such as large-scale language models.
[0105] A "prompt" refers to a text instruction entered into a generative AI model to instruct it on how to proceed.
[0106] A "summary" is a document that presents the main content of an original book or document in an abbreviated form.
[0107] "Terminal" refers to a device, such as a computer or smartphone, that a user uses to access the system, enter information, and view generated summaries.
[0108] "Formatting" refers to the process of adjusting the format and content of the generated summary to make it easier to read.
[0109] MODE FOR CARRYING OUT THE INVENTION
[0110] This invention is a system that uses a generative AI model to provide book summaries with permission from authors and publishers. This system mainly consists of three elements: a server, a terminal, and a user.
[0111] server
[0112] The server plays a central role in this system and has the following functions:
[0113] 1. Electronic Data Acquisition:
[0114] The server retrieves electronic data from the database with permission from the authors and publishers, specifically using a database management system such as SQL Server.
[0115] 2. Processing the request:
[0116] The server receives the request sent from the terminal and analyzes its contents. Web frameworks such as Flask and Django are used to process HTTP requests.
[0117] 3. Generative AI model for summarization:
[0118] The server uses a generative AI model (e.g., OpenAI's GPT model) to generate a summary based on the user's specified reading time, number of characters, and generation. In this process, it generates a prompt sentence and passes it to the AI.
[0119] 4. Submit your abstract:
[0120] The server formats the generated summary and sends it to the device. It uses a standard API endpoint to send it as JSON data.
[0121] Terminal
[0122] The terminal is a device where users can enter requests through an interface and view the generated summaries. It has the following features:
[0123] 1. Providing an input interface:
[0124] The terminal provides a form for users to input reading time, word count, generation, book title, etc. The interface is built using front-end frameworks such as React and Vue.js.
[0125] 2. Submit your request:
[0126] The device sends the input request to the server. It uses AJAX or Fetch API to send an HTTP request to the server.
[0127] 3. View Summary:
[0128] The device receives the summary from the server and displays it to the user in an easy-to-read format using style frameworks such as CSS and Bootstrap.
[0129] User
[0130] The user is the entity that uses this system and performs the following operations:
[0131] 1. Enter your information:
[0132] The user inputs the title, reading time, number of characters, and generation into a form on the terminal.
[0133] 2. Submit your request:
[0134] Once you have completed the input, click the Send Request button.
[0135] 3. View Abstract:
[0136] The summary sent from the server is viewed on the terminal.
[0137] Specific examples
[0138] A specific example of the operation of this system is shown below.
[0139] Example 1: Summary request for young people in under 10 minutes
[0140] The user opens the device interface, enters the title of the book they want to read as "A Science Fiction," sets the desired reading time as "10 minutes or less," sets the desired word count as "1,000 characters," and sets the target age group as "Young people." Once they've completed the input, they press the send request button.
[0141] The device converts the input information into JSON format and sends an HTTP POST request to the server.
[0142] The server receives the request, analyzes it, retrieves the digital copy of "A Certain Science Fiction Book" from the database, verifies that the book is licensed, and then passes the following prompt to the generative AI model:
[0143] "Please summarize the book "A Certain Science Fiction" in 1000 words or less for a young reader so that it can be read in under 10 minutes."
[0144] The generative AI model generates a summary and returns it to the server, which formats the summary and sends it to the device, which displays it on the user interface, allowing the user to read the summary in under 10 minutes.
[0145] The above is a specific embodiment of the present invention. This system provides flexible summaries tailored to the user's needs, improving reading efficiency and comprehension.
[0146] The flow of the identification process in the first embodiment will be described with reference to FIG.
[0147] Step 1:
[0148] The user uses the device interface to enter information such as reading time, desired word count, generation, book title, etc. The entered data is formatted in JSON format as shown in the example below.
[0149] json
[0150] {
[0151] "title": "A Science Fiction",
[0152] "reading_time": "within 10 minutes",
[0153] "character_count": "1000",
[0154] "generation": "young people"
[0155] }
[0156] (Input: Specified input from the user)
[0157] (Output: Request data in JSON format)
[0158] Step 2:
[0159] The device generates an HTTP POST request based on the input information and sends it to the server. This request includes all the information the user entered.
[0160] (Input: User input data)
[0161] (Output: HTTP POST request to server)
[0162] Step 3:
[0163] The server analyzes the received request and retrieves the digital data for "A Certain Science Fiction" from the database using an SQL query to verify that the data obtained is authorized.
[0164] (Input: HTTP POST request)
[0165] (Output: Electronic data retrieved from the database)
[0166] Step 4:
[0167] The server passes a prompt sentence to the generative AI model based on the acquired electronic data. This prompt sentence is formatted as follows:
[0168] "Please summarize the book "A Certain Science Fiction" in 1000 words or less for a young reader so that it can be read in under 10 minutes."
[0169] A generative AI model takes this prompt and generates a summary.
[0170] (Input: prompt text, electronic data)
[0171] (Output: Generated summary)
[0172] Step 5:
[0173] The server formats the generated summary and sends it to the device in JSON format, which is easy for the user to view.
[0174] (Input: Generated summary)
[0175] (Output: Summary data in JSON format to terminal)
[0176] Step 6:
[0177] The terminal analyzes the summary data received from the server and displays it on a user interface, which the user can view.
[0178] (Input: Summary data received from the server)
[0179] (Output: Summary displayed in the user interface)
[0180] (Application example 1)
[0181] 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."
[0182] In today's world, busy lifestyles mean limited time for reading, and people are required to efficiently understand the main content of a book in a short amount of time. There are also limited ways for individual users to enjoy books in a format appropriate for their generation and interests. Furthermore, there is a lack of platforms for discussing book summaries, making it difficult to share reading experiences.
[0183] 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.
[0184] In this invention, the server includes means for acquiring electronic data, means for users to input reading time, desired number of characters, and generation, means for generating summaries using a generative AI model, means for creating different summaries according to the reading time, number of characters, and generation specified by the user, and means for displaying the created summaries to users and providing a discussion function. This enables users to read efficiently according to their individual needs within a limited time, and also stimulates sharing of reading experiences and discussions.
[0185] "Electronic data" means information stored in digital form, including the entire text of a book or portions thereof.
[0186] A "generative AI model" is an algorithm that uses artificial intelligence technology to analyze input text and generate a summary.
[0187] "Reading time" is the amount of time a user plans to spend reading a particular book or summary thereof.
[0188] "Number of characters" means the total number of characters in the summary to be generated.
[0189] "Generation" refers to user groups based on geographic or cultural age, with different language and expressions being tailored to each generation.
[0190] A "user" is an entity that uses this system to obtain and view book summaries.
[0191] "Server" means a computing device that retrieves electronic data, receives requests, creates summaries using generative AI models, and transmits the summaries.
[0192] The "discussion function" is an interface that allows users to exchange opinions and discuss the contents of a book based on the generated summary.
[0193] An "input interface" is a user interface that provides a means for a user to input reading time, number of characters, generation, and book title.
[0194] This invention is a system that uses a generative AI model to provide authorized book summaries. The system is mainly composed of three elements: a server, a terminal, and a user.
[0195] server
[0196] The server plays a central role in this system and has the following functions:
[0197] 1. Acquisition of electronic data: Electronic data with permission from the copyright holder is acquired from the database.
[0198] 2. Request processing: Receives the request sent from the terminal and analyzes its contents.
[0199] 3. Generative AI model creates a summary: A summary is generated based on the user's specified reading time, word count, and generation. The generative AI model analyzes the text and creates a summary.
[0200] 4. Send Abstract: Send the generated abstract to the terminal.
[0201] 5. Providing a discussion function: Provide an interface for users to exchange opinions and hold discussions based on the summary content.
[0202] The hardware used is a general-purpose server computer, and the software used is Flask (a Python microframework) and the Requests library for HTTP requests.
[0203] Terminal
[0204] The terminal is a device through which a user can enter requests and view the generated summaries via an interface. This device includes the following features:
[0205] 1. Providing an input interface: Provide a form for users to input reading time, word count, generation, book title, etc.
[0206] 2. Sending the request: Send the input request to the server.
[0207] 3. Display Abstract: The abstract received from the server is displayed to the user.
[0208] 4. Providing a discussion function: A chat function is provided for users to exchange opinions about the summary content.
[0209] User
[0210] The user is the entity that uses this system and performs the following operations:
[0211] 1. Enter information: Enter reading time, word count, generation, and book title.
[0212] 2. Submit your request: Once you've completed the input, submit your request.
[0213] 3. Viewing the summary: The summary sent from the server is viewed on the terminal.
[0214] 4. Discussion of the summary: Exchange opinions and discuss the summary with other users.
[0215] System operation example
[0216] A specific example of the operation of this system is shown below.
[0217] Example 1: Summary request for "young people" and "under 15 minutes"
[0218] The user opens the device interface, inputs the title of the book they want to read, sets the desired reading time to "15 minutes or less," the desired number of characters to "1500 characters," and sets the target age group to "young people." Once they have completed the input, they press the send request button.
[0219] The terminal sends the input information to the server, which receives the request, retrieves the electronic data of the book from the database, and confirms that the book has been licensed.
[0220] The server passes the acquired digital data to a generative AI model, which then creates a summary based on the user's preferences. The generative AI model extracts key episodes and key points and generates a summary that can be read in under 15 minutes, using language appropriate for younger readers.
[0221] The generated summary is formatted on the server and sent to the terminal, which displays the received summary on the user interface and allows the user to read the summary within a specified time.
[0222] Furthermore, users can use the chat function to hold discussions with other users who are reading the same summary. Through the interface provided by the discussion function, users can exchange opinions and discuss the summarized content to deepen their understanding.
[0223] Example prompts for generative AI models
[0224] "Below is the full text of 'XXX (book title)' with permission from the copyright holder. Please generate a 1500-character summary of this book aimed at young people that can be read in under 15 minutes."
[0225] The above is an embodiment of the present invention. This system allows users to efficiently understand the main content of a book within a limited time, and also allows users to exchange opinions about the content of the summary with other users.
[0226] The flow of the specific processing in the application example 1 will be described with reference to FIG.
[0227] Step 1:
[0228] The user uses the device's interface to input the reading time, desired number of characters, generation, and book title. For example, the user might input "less than 15 minutes," "1500 characters," "for young people," and "XXX (book title)." The input data is temporarily saved on the device. At this point, the input is the reading time, desired number of characters, generation, and book title.
[0229] Step 2:
[0230] The device sends the input information to the server. At this stage, the request includes the previously input data (reading time, desired word count, generation, and book title). The server receives this request data and begins analyzing it.
[0231] Step 3:
[0232] The server retrieves the electronic data of the specified book from the database. When retrieving the electronic data, the server searches for and retrieves the electronic data of the relevant book based on the input book title. This electronic data is used in the next process.
[0233] Step 4:
[0234] The server verifies that the digital data retrieved from the database has been authorized by the copyright holder. If authorization is successful, the digital data is passed to the generative AI model. Authorization authorization includes checking license information.
[0235] Step 5:
[0236] The server generates and passes a prompt to the generative AI model based on the user-specified reading time, desired number of characters, and generation. An example of a prompt is, "Below is the full text of 'XXX (book title)' with permission from the copyright holder. Please generate a 1500-character summary of this book aimed at young people that can be read in 15 minutes or less."
[0237] Step 6:
[0238] The server uses a generative AI model, such as GPT-3, to generate a summary based on the prompt. The generated summary is optimized to meet the user-specified criteria (less than 15 minutes, 1500 characters, and aimed at young people). The generated summary is in text format.
[0239] Step 7:
[0240] The server then formats the generated summary to make it easier for the user to read, for example by dividing it into paragraphs and highlighting important points, and the formatted summary is then ready to be sent to the device as text data.
[0241] Step 8:
[0242] The server sends the formatted summary to the terminal, which displays the received summary on its user interface.
[0243] Step 9:
[0244] The device displays the received summary to the user, who has 15 minutes to finish reading it. The device also has a discussion function that allows users to exchange opinions and discuss the summary with other users.
[0245] The above is a description of the process flow of the program of the system that realizes the application example, broken down into specific steps.
[0246] 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.
[0247] The present invention is a system that uses generative AI to provide book summaries with permission from authors and publishers, and further combines it with an emotion engine that recognizes user emotions. An embodiment of the system will be described below.
[0248] System configuration
[0249] This system is mainly composed of three elements: a server, a terminal, and a user. In addition, it has the function of recognizing the user's emotions using an emotion engine and adjusting the summary content based on those emotions.
[0250] server
[0251] The server plays a central role in this system and has the following functions:
[0252] 1. Electronic data acquisition: Electronic data with permission from the authors and publishers will be acquired from databases.
[0253] 2. Request processing: Receives the request sent from the terminal and analyzes its contents.
[0254] 3. Generative AI summary creation: Generate summaries based on user-specified reading time, word count, and generation.
[0255] 4. Emotion analysis using an emotion engine: Recognizes the user's emotions and adjusts the content and expression of the summary based on the analysis results.
[0256] 5. Send Abstract: Send the generated abstract to the terminal.
[0257] Terminal
[0258] The terminal is a device where users can enter requests through an interface and view the generated summaries. It has the following features:
[0259] 1. Providing an input interface: Provide a form for users to input reading time, word count, generation, book title, etc.
[0260] 2. Sending the request: Send the input request to the server.
[0261] 3. Acquiring emotional data: Acquire emotional data using the user's facial expressions and tone of voice.
[0262] 4. Display Abstract: The abstract received from the server is displayed to the user.
[0263] User
[0264] The user is the entity that uses this system and performs the following operations:
[0265] 1. Enter information: Enter reading time, word count, generation, and book title.
[0266] 2. Submit your request: Once you've completed the input, submit your request.
[0267] 3. Providing emotional data: Emotional data is provided using the device's camera or microphone.
[0268] 4. Viewing the summary: The summary sent from the server is viewed on the terminal.
[0269] System operation example
[0270] A specific example of the operation of this system is shown below.
[0271] Example 1: Summary request based on "young people", "under 10 minutes", and "positive sentiment"
[0272] The user opens the device's interface, enters the title of the book they want to read as "A Science Fiction," sets the desired reading time as "10 minutes or less," the desired number of characters as "1,000 characters," and sets the target age group as "Young people." In addition, the device's camera and microphone are used to provide facial expressions and tone of voice to the emotion engine.
[0273] The device sends the input information and emotion data to the server. The server receives the request, retrieves the digital data for "A Certain Science Fiction" from the database, and confirms that the book has been licensed.
[0274] The server passes the acquired digital data to a generation AI that creates a summary based on the user's wishes. The generation AI extracts key episodes and key points and generates a summary that can be read in under 10 minutes, using language appropriate for young people.
[0275] Furthermore, the emotion engine analyzes the user's emotional data and adjusts the content and expressions of the summary to match positive emotions, for example by using more energetic and positive expressions.
[0276] The server formats the generated summary and sends it to the terminal, which displays it on its user interface, allowing the user to read the summary within 10 minutes.
[0277] System convenience
[0278] This system allows users to efficiently understand the main content of a book within a limited time frame. Furthermore, by adjusting the summary based on the user's emotions, it provides a more personalized and easy-to-read summary. This improves the user's reading experience and contributes greatly to self-improvement and knowledge growth.
[0279] The above is a concrete example of how the present invention can be implemented. This system provides flexible summaries tailored to the user's needs and emotions, improving reading efficiency and comprehension.
[0280] The processing flow will be explained below.
[0281] Step 1:
[0282] The user opens a summary request form in a device application or website.
[0283] Step 2:
[0284] The user fills out a form with the title of the book or books they want to read, the author's name, the desired reading time, the desired word count, and their generation.
[0285] Step 3:
[0286] The user presses the "Send Request" button to send the input information to the server.
[0287] Step 4:
[0288] The terminal converts the user's input information into an appropriate data format, such as JSON, and sends it to the server as an HTTP request.
[0289] Step 5:
[0290] The device captures emotional data by detecting the user's facial expressions and tone of voice, and this information is collected in real time via a camera and microphone.
[0291] Step 6:
[0292] The device analyzes the emotion data and sends the results to the server.
[0293] Step 7:
[0294] The server receives the request data and emotion data sent from the terminal.
[0295] Step 8:
[0296] The server checks the database to see if the specified book or publication has been licensed by the author and publisher.
[0297] Step 9:
[0298] If the permission is confirmed, the server retrieves the electronic data of the specified book from the database. If the permission is not confirmed, the server generates an error message and returns it to the terminal.
[0299] Step 10:
[0300] The server passes the acquired electronic data and the user's requests (desired reading time, number of characters, generation) to the generation AI.
[0301] Step 11:
[0302] The generative AI analyzes the provided electronic data and automatically extracts key points and episodes.
[0303] Step 12:
[0304] The AI then uses the extracted points to generate a summary that fits the specified time and number of characters, adjusting the words and expressions to suit the user's generation.
[0305] Step 13:
[0306] The emotion engine analyzes the received emotion data and adjusts the content and expression of the summary based on the user's emotion. For example, if the user is expressing positive emotions, it will use more energetic expressions that reflect that emotion.
[0307] Step 14:
[0308] The server converts the summaries received from the generative AI and emotion engine into an appropriate format, such as HTML or plain text.
[0309] Step 15:
[0310] The server sends the formatted summary to the terminal as an HTTP response.
[0311] Step 16:
[0312] The terminal receives the summary data sent from the server.
[0313] Step 17:
[0314] The terminal displays the received summary on a user interface.
[0315] Step 18:
[0316] The user views the generated summary on the terminal.
[0317] Example 2
[0318] 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."
[0319] Conventional book summarization services can generate summaries based on given conditions, but they have difficulty providing flexible summaries that match the user's emotions. Furthermore, they are limited in their ability to adjust the optimal reading time and word count for each user, or the expression to suit the target generation. This makes it difficult to provide personalized summaries, and has led to problems in improving user satisfaction.
[0320] 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.
[0321] In this invention, the server includes means for acquiring electronic data, means for the user to input the reading time, desired number of characters, and generation, means for analyzing the input information, means for creating a summary based on the acquired electronic data and a generation AI model, means for analyzing the user's emotion data after generating the summary and adjusting the summary content based on the emotion, and means for displaying the created summary to the user. This makes it possible to provide a personalized summary based on the user's reading conditions and emotions, thereby improving the user's reading experience.
[0322] "Electronic data" refers to information such as books and documents expressed in digital form.
[0323] "User" means a person who operates and uses this system.
[0324] "Reading time" refers to the time required to read and understand a book summary designated by the user.
[0325] "Desired word count" refers to the number of words the user specifies the book summary should contain.
[0326] "Generation" refers to a particular age group or social group to which a user belongs.
[0327] "Input means" refers to an interface that allows users to input conditions and data into the system.
[0328] "Means of analysis" refers to the function of interpreting input data and conditions and performing the processing necessary for the system to operate properly.
[0329] A "generative AI model" is an algorithm that uses artificial intelligence and is a technology that automatically generates summaries of sentences or documents based on specific conditions.
[0330] A "summary" is a concise summary of the main information or points of a book or document.
[0331] "Emotional data" refers to information about emotions obtained from the user's facial expressions, tone of voice, etc.
[0332] "Adjustment means" refers to the function of changing the content and expression to the optimum based on the analysis results.
[0333] The "display means" refers to an interface for visually conveying the generated summary to the user.
[0334] This invention is a system that uses generative AI to provide book summaries with permission from authors and publishers, and also combines it with an emotion engine that recognizes the user's emotions. The system is mainly composed of three elements: a server, a terminal, and a user. The roles and operations of each are described in detail below.
[0335] server
[0336] The server is a hardware and software component that is responsible for the central operation of the entire system. Specifically, it has the following functions:
[0337] 1. Acquisition of electronic data
[0338] The server retrieves electronic data of books licensed by authors and publishers from a database, for example, by using a database management system (DBMS) to quickly search and retrieve the electronic data.
[0339] 2. Processing the Request
[0340] It receives user requests sent from the device and analyzes their contents, including input parameters (book title, reading time, number of characters, generation, etc.).
[0341] 3. Generative AI-powered summaries
[0342] The acquired digital data is input into a generative AI model, which generates a summary based on the user's specified conditions (reading time, number of characters, generation, etc.). For example, a generative AI that applies natural language processing (NLP) technology is used.
[0343] 4. Emotion analysis using an emotion engine
[0344] The technology analyzes the user's emotional data (facial expressions and tone of voice) and adjusts the summary content based on the results. Emotion recognition technology uses machine learning algorithms.
[0345] 5. Submit your summary
[0346] The generated and adjusted summary is sent to the terminal.
[0347] For example, to generate a summary of a science fiction novel for "younger adults" that can be read in under 10 minutes, the prompt would be:
[0348] Generate a summary of a science fiction novel, aimed at young people, that can be read in under 10 minutes, and is up to 1000 characters long.
[0349] Terminal
[0350] A terminal is a device that provides an interface for users to use the system. Its specific functions are as follows:
[0351] 1. Providing an input interface
[0352] Provide a form for users to enter their reading criteria (reading time, word count, generation, book title), for example, using a web browser or mobile application.
[0353] 2. Submitting a Request
[0354] The entered conditions are sent to the server using HTTP or another data communication protocol.
[0355] 3. Acquiring Emotion Data
[0356] The user's facial expressions and tone of voice are captured through a camera and microphone and sent to the emotion engine.
[0357] 4. Viewing the Summary
[0358] The summary received from the server is displayed on the screen, using HTML and mobile app UI as the interface.
[0359] User
[0360] The user is the entity that uses this system to obtain a book summary, and performs the following operations:
[0361] 1. Enter your information
[0362] Enter your reading criteria into the device interface, for example, "Science fiction," "Less than 10 minutes," "1,000 characters," and "For young people."
[0363] 2. Submitting a Request
[0364] Click the request button to send the input information to the server.
[0365] 3. Providing Emotion Data
[0366] It uses the device's camera and microphone to provide emotional data, such as a smile or a calm tone of voice.
[0367] 4. Viewing the Abstract
[0368] The summary sent from the server is viewed on the terminal screen and the content is understood based on the specified conditions.
[0369] As described above, the present invention is a system that provides an efficient reading experience by providing flexible and personalized book summaries based on the user's reading conditions and emotions.
[0370] The flow of the identification process in the second embodiment will be described with reference to FIG.
[0371] System program processing flow
[0372] Step 1: Entering the User Interface
[0373] The terminal is the main player. Here's what it does:
[0374] Input: The user enters information into an input form, including the book title, reading time, desired word count, and generation.
[0375] Data processing: The terminal converts the input information into request data.
[0376] Output: The request data is prepared.
[0377] Step 2: Submitting the request
[0378] The terminal is the main player. Here's what it does:
[0379] Input: The request data prepared in step 1.
[0380] Data operation: Converts the request data into an HTTP request format.
[0381] Output: Sends the request data to the server.
[0382] Step 3: Receiving and Parsing the Request
[0383] The server is the main player. Here's what it does:
[0384] Input: The request data sent from the device.
[0385] Data calculation: Analyze the request data and extract the title, reading time, desired number of characters, and generation.
[0386] Output: Parsed condition data.
[0387] Step 4: Get the data
[0388] The server is the main player. Here's what it does:
[0389] Input: The condition data extracted in step 3.
[0390] Data processing: Search and retrieve the corresponding electronic data from the database.
[0391] Output: The electronic data obtained.
[0392] Step 5: Generative AI creates a summary
[0393] The server is the main player. Here's what it does:
[0394] Input: The electronic data obtained and the user's conditions.
[0395] Data Computation: Input data into a generative AI model to generate summaries based on reading time, desired word count, and generation.
[0396] Output: The generated summary data.
[0397] Specific prompt examples:
[0398] Generate a summary of a science fiction novel, aimed at young people, that can be read in under 10 minutes, and is up to 1000 characters long.
[0399] Step 6: Sentiment analysis and summary adjustment
[0400] The server is the main player. Here's what it does:
[0401] Input: Generated summary data and user emotion data.
[0402] Data calculation: Emotional data is input into the emotion engine, and the summary content is adjusted based on the analysis results.
[0403] Output: Adjusted summary data.
[0404] Step 7: Send and view the summary
[0405] The server and the device are the main players in the collaboration. The specific operations are as follows:
[0406] Input: Adjusted summary data.
[0407] Data calculation: The server formats the summary data for transmission to the terminal.
[0408] Output: Summary data sent to the terminal.
[0409] Next, the terminal takes center stage. Here's what it does:
[0410] Input: Abstract data sent by the server.
[0411] Data processing: Converts the received summary data into a format that is displayed on the user interface.
[0412] Output: The summary data is displayed on the terminal screen and provided to the user.
[0413] This is the specific program processing flow of this system. At each processing step, the necessary data processing and calculations are performed based on the input data, and the results are passed on to the next processing step to provide a flexible and personalized book summary.
[0414] (Application example 2)
[0415] 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."
[0416] Conventional summary systems are unable to consider the user's emotions and state, making it difficult to provide a personalized reading experience. Furthermore, the summaries generated are uniform, making it impossible to provide content optimized for the user's emotions. Therefore, in order to improve the user's reading experience, it is necessary to provide summaries tailored to each individual's emotional state.
[0417] 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.
[0418] In this invention, the server includes means for acquiring electronic data, means for the user to input reading time, desired number of characters, and generation, means for generating, means for creating a summary, means for acquiring emotional data, means for adjusting the summary based on emotional analysis, and means for displaying the created summary to the user, thereby making it possible to provide a summary optimized for the emotional state of the user.
[0419] "Electronic data" refers to information that expresses the contents of a book in digital form and is available on a server.
[0420] "Means of acquisition" refers to the server's ability to download electronic data from authors and publishers.
[0421] "Means for input" refers to a system in which the user inputs parameters such as the desired reading time, number of characters, and generation into the terminal.
[0422] "Means of generation" refers to the function of using generative AI to create a book summary based on information entered by the user.
[0423] "Means for creating summaries" refers to the function of summarizing the main contents of a book so that they can be understood in a short amount of time.
[0424] "Means for acquiring emotional data" refers to a system that analyzes the user's facial expressions and tone of voice to detect emotions.
[0425] "Means for adjusting the summary based on emotion analysis" refers to a function for changing the content and expression of the summary based on the acquired emotion data of the user.
[0426] "Displaying means" refers to a system that displays the created summary on the user's terminal.
[0427] This invention is a system for providing a book summary optimized for a user's emotional state, and specifically consists of three elements: a server, a terminal, and a user. Specific embodiments of this system are described below.
[0428] server
[0429] The server plays a central role in this system and has the following functions:
[0430] Acquisition of electronic data: A function to acquire electronic data of books with permission from authors and publishers. Specifically, the server downloads electronic book data from the database.
[0431] Request processing: Analyzes the user's request sent from the device and uses a generative AI model to create a book summary based on the user's specified reading time, word count, and generation.
[0432] Sentiment Analysis: Analyzes the user's emotional data and adjusts the summary content. This function uses an emotion engine to analyze the user's facial expressions, tone of voice, etc.
[0433] Terminal
[0434] A terminal is a device that provides an interface for users to operate the system. Specifically, it has the following functions:
[0435] Providing an input interface: Provide a form for users to input reading time, word count, generation, book title, etc.
[0436] Acquiring emotional data: Acquires the user's emotional data using the device's camera and microphone. Detects the user's emotional state by analyzing facial expressions and voice using OpenCV.
[0437] Displaying the summary: The summary sent from the server is displayed to the user. The generated summary is adjusted based on sentiment analysis, so it is the most appropriate content for the user.
[0438] User
[0439] The user is the entity that uses this system and performs the following operations:
[0440] Enter information: Enter reading time, word count, generation, book title, etc. using the device interface.
[0441] Submit your request: Once you have completed the entry, submit your request to request an electronic summary of your data.
[0442] Providing emotional data: Emotional data is provided from facial expressions and tone of voice using the device's camera and microphone.
[0443] Viewing the summary: The summary sent from the server is received on the terminal and viewed.
[0444] Specific examples
[0445] For example, consider a case where a user requests a summary of a "science novel" and sets the reading time to "less than 10 minutes," the desired word count to "1,000 characters," and the target demographic to "young people." When the user provides emotional data (e.g., joy) using the device's camera and microphone, the server acquires the electronic data and generates a summary using a generative AI model. Next, the emotion engine performs emotional analysis and adjusts the summary's expression to be more positive. As a result, the server sends a summary that uses a lot of positive language and can be read in less than 10 minutes to the device, and the user can view it.
[0446] Prompt Sentence Examples
[0447] "Generate a summary of the book in 150 characters or less: "Harry Potter and the Philosopher's Stone, this book is...""
[0448] In this way, the system provides summaries tailored to the user's emotional state, enabling an efficient and personalized reading experience.
[0449] The flow of the specific processing in the application example 2 will be described with reference to FIG.
[0450] Step 1:
[0451] The user uses the terminal interface to input the book title, desired reading time, number of characters, generation, etc. The input information is collected by the terminal and sent to the server in the next step.
[0452] Input: Book title, desired reading time, desired number of characters, generation
[0453] Output: Request data sent to the next step
[0454] Step 2:
[0455] The terminal sends the collected user input information to the server, which receives and analyzes this request data.
[0456] Input: User request data
[0457] Output: Analysis result of request data
[0458] Step 3:
[0459] The device's camera and microphone are used to acquire the user's emotional data, which is collected by the device and sent to the server in the next step.
[0460] Input: User's facial expression, tone of voice
[0461] Output: Parsed emotion data
[0462] Step 4:
[0463] The device sends emotional data to the server, which receives and analyzes the data.
[0464] Input: Parsed emotion data
[0465] Output: Analysis results of emotion data
[0466] Step 5:
[0467] The server retrieves the e-book data from the database and sends a prompt to the AI model based on the user's request to generate a summary. The prompt is: "Please generate a summary of the book's contents in 150 characters or less: 'Harry Potter and the Philosopher's Stone, this book is...'"
[0468] Input: e-book data, request data, prompt text
[0469] Output: Generated book summary
[0470] Step 6:
[0471] The server adjusts the generated summary based on sentiment analysis. For example, if the sentiment is positive, it will use more positive expressions.
[0472] Input: Generated summary, analysis results of emotion data
[0473] Output: A sentiment-adjusted summary
[0474] Step 7:
[0475] The server sends the adjusted summary content to the terminal, which displays the received summary to the user.
[0476] Input: Adjusted summary
[0477] Output: A summary that is displayed to the user
[0478] This allows users to receive summaries optimized for their emotional state, resulting in an efficient and personalized reading experience.
[0479] 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.
[0480] 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.
[0481] 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.
[0482] [Second embodiment]
[0483] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.
[0484] 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.
[0485] 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).
[0486] 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.
[0487] 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.
[0488] 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).
[0489] 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.
[0490] 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.
[0491] 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.
[0492] 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.
[0493] 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.
[0494] 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."
[0495] The present invention is a system that uses a generative AI to provide a summary of a book with permission from the author and publisher. An embodiment of the system will be described below.
[0496] System configuration
[0497] This system is mainly composed of three elements: a server, a terminal, and a user.
[0498] server
[0499] The server plays a central role in this system and has the following functions:
[0500] 1. Electronic data acquisition: Electronic data with permission from the authors and publishers will be acquired from databases.
[0501] 2. Request processing: Receives the request sent from the terminal and analyzes its contents.
[0502] 3. Generative AI summary creation: Generate summaries based on user-specified reading time, word count, and generation.
[0503] 4. Send Abstract: Send the generated abstract to the terminal.
[0504] Terminal
[0505] The terminal is a device where users can enter requests through an interface and view the generated summaries. It has the following features:
[0506] 1. Providing an input interface: Provide a form for users to input reading time, word count, generation, book title, etc.
[0507] 2. Sending the request: Send the input request to the server.
[0508] 3. Display Abstract: The abstract received from the server is displayed to the user.
[0509] User
[0510] The user is the entity that uses this system and performs the following operations:
[0511] 1. Enter information: Enter reading time, word count, generation, and book title.
[0512] 2. Submit your request: Once you've completed the input, submit your request.
[0513] 3. Viewing the summary: The summary sent from the server is viewed on the terminal.
[0514] System operation example
[0515] A specific example of the operation of this system is shown below.
[0516] Example 1: Summary request for "young people" and "less than 10 minutes"
[0517] The user opens the device interface, enters the title of the book they want to read as "A Science Fiction," sets the desired reading time as "10 minutes or less," sets the desired word count as "1,000 characters," and sets the target age group as "Young people." Once they've completed the input, they press the send request button.
[0518] The terminal sends the input information to the server, which receives the request, retrieves the electronic data for "A Certain Science Fiction" from the database, and confirms that the book has been licensed.
[0519] The server passes the acquired digital data to a generation AI that creates a summary based on the user's wishes. The generation AI extracts key episodes and key points and generates a summary that can be read in under 10 minutes, using language appropriate for young people.
[0520] The server formats the generated summary and sends it to the terminal, which displays it on its user interface, allowing the user to read the summary within 10 minutes.
[0521] System convenience
[0522] This system allows users to efficiently understand the main content of a book within a limited time. It also makes difficult content easier to understand by appropriately summarizing it. Therefore, it can be said that this system greatly contributes to users' self-improvement and knowledge improvement.
[0523] The above is a concrete example of how the present invention can be implemented. This system provides flexible summaries tailored to the user's needs, improving reading efficiency and comprehension.
[0524] The processing flow will be explained below.
[0525] Step 1:
[0526] The user opens a summary request form in a device application or website.
[0527] Step 2:
[0528] The user fills out a form with the title of the book or books they want to read, the author's name, the desired reading time, the desired word count, and their generation.
[0529] Step 3:
[0530] The user presses the "Send Request" button to send the input information to the server.
[0531] Step 4:
[0532] The terminal converts the user's input information into an appropriate data format such as JSON and sends it to the server as an HTTP request (e.g., POST request).
[0533] Step 5:
[0534] The server receives the request data sent from the terminal.
[0535] Step 6:
[0536] The server checks the database to see if the specified book or publication has been licensed by the author and publisher.
[0537] Step 7:
[0538] If the permission is confirmed, the server retrieves the electronic data of the specified book from the database. If the permission is not confirmed, the server generates an error message and returns it to the terminal.
[0539] Step 8:
[0540] The server passes the acquired electronic data and the user's requests (desired reading time, number of characters, generation) to the generation AI.
[0541] Step 9:
[0542] The generative AI analyzes the provided electronic data and automatically extracts key points and episodes.
[0543] Step 10:
[0544] The AI then uses the extracted points to generate a summary that fits the specified time and number of characters, adjusting the words and expressions to suit the user's generation.
[0545] Step 11:
[0546] The server converts the summary received from the generation AI into an appropriate format, such as HTML or plain text.
[0547] Step 12:
[0548] The server sends the formatted summary to the terminal as an HTTP response.
[0549] Step 13:
[0550] The terminal receives the summary data sent from the server.
[0551] Step 14:
[0552] The terminal displays the received summary on a user interface.
[0553] Step 15:
[0554] The user views the generated summary on the terminal.
[0555] Example 1
[0556] 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."
[0557] In modern society, there is a huge amount of information and books available, and people are required to understand their content efficiently within a limited time. However, conventional book summarization systems have difficulty providing appropriate summaries that suit the user's desired reading time and age, and there is a lack of means to provide easy-to-understand summaries.
[0558] 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.
[0559] In this invention, the server includes a means for acquiring electronic data, a means for analyzing a request and acquiring electronic data from a database, a means for passing a prompt sentence to a generative AI model and generating a summary, and a means for formatting the generated summary and sending it to a terminal. This makes it possible to efficiently provide appropriate and easy-to-understand summaries according to the user's desired reading time, number of characters, and generation.
[0560] "Electronic data" refers to digital information handled by computers and electronic devices, including the contents of books and documents.
[0561] "User" refers to the primary user who uses the System to input information and receive book summaries.
[0562] A "request" refers to a request from a user to the system for specific processing or information provision.
[0563] "Server" refers to the computer system that plays a central role in this system and performs tasks such as analyzing requests, acquiring data, and running generative AI.
[0564] A "database" refers to a system that organizes and stores electronic data so that it can be efficiently searched when needed.
[0565] A "generative AI model" refers to an artificial intelligence system that generates and summarizes sentences using natural language processing techniques, such as large-scale language models.
[0566] A "prompt" refers to a text instruction entered into a generative AI model to instruct it on how to proceed.
[0567] A "summary" is a document that presents the main content of an original book or document in an abbreviated form.
[0568] "Terminal" refers to a device, such as a computer or smartphone, that a user uses to access the system, enter information, and view generated summaries.
[0569] "Formatting" refers to the process of adjusting the format and content of the generated summary to make it easier to read.
[0570] MODE FOR CARRYING OUT THE INVENTION
[0571] This invention is a system that uses a generative AI model to provide book summaries with permission from authors and publishers. This system mainly consists of three elements: a server, a terminal, and a user.
[0572] server
[0573] The server plays a central role in this system and has the following functions:
[0574] 1. Electronic Data Acquisition:
[0575] The server retrieves electronic data from the database with permission from the authors and publishers, specifically using a database management system such as SQL Server.
[0576] 2. Processing the request:
[0577] The server receives the request sent from the terminal and analyzes its contents. Web frameworks such as Flask and Django are used to process HTTP requests.
[0578] 3. Generative AI model for summarization:
[0579] The server uses a generative AI model (e.g., OpenAI's GPT model) to generate a summary based on the user's specified reading time, number of characters, and generation. In this process, it generates a prompt sentence and passes it to the AI.
[0580] 4. Submit your abstract:
[0581] The server formats the generated summary and sends it to the device. It uses a standard API endpoint to send it as JSON data.
[0582] Terminal
[0583] The terminal is a device where users can enter requests through an interface and view the generated summaries. It has the following features:
[0584] 1. Providing an input interface:
[0585] The terminal provides a form for users to input reading time, word count, generation, book title, etc. The interface is built using front-end frameworks such as React and Vue.js.
[0586] 2. Submit your request:
[0587] The device sends the input request to the server. It uses AJAX or Fetch API to send an HTTP request to the server.
[0588] 3. View Summary:
[0589] The device receives the summary from the server and displays it to the user in an easy-to-read format using style frameworks such as CSS and Bootstrap.
[0590] User
[0591] The user is the entity that uses this system and performs the following operations:
[0592] 1. Enter your information:
[0593] The user inputs the title, reading time, number of characters, and generation into a form on the terminal.
[0594] 2. Submit your request:
[0595] Once you have completed the input, click the Send Request button.
[0596] 3. View Abstract:
[0597] The summary sent from the server is viewed on the terminal.
[0598] Specific examples
[0599] A specific example of the operation of this system is shown below.
[0600] Example 1: Summary request for young people in under 10 minutes
[0601] The user opens the device interface, enters the title of the book they want to read as "A Science Fiction," sets the desired reading time as "10 minutes or less," sets the desired word count as "1,000 characters," and sets the target age group as "Young people." Once they've completed the input, they press the send request button.
[0602] The device converts the input information into JSON format and sends an HTTP POST request to the server.
[0603] The server receives the request, analyzes it, retrieves the digital copy of "A Certain Science Fiction Book" from the database, verifies that the book is licensed, and then passes the following prompt to the generative AI model:
[0604] "Please summarize the book "A Certain Science Fiction" in 1000 words or less for a young reader so that it can be read in under 10 minutes."
[0605] The generative AI model generates a summary and returns it to the server, which formats the summary and sends it to the device, which displays it on the user interface, allowing the user to read the summary in under 10 minutes.
[0606] The above is a specific embodiment of the present invention. This system provides flexible summaries tailored to the user's needs, improving reading efficiency and comprehension.
[0607] The flow of the identification process in the first embodiment will be described with reference to FIG.
[0608] Step 1:
[0609] The user uses the device interface to enter information such as reading time, desired word count, generation, book title, etc. The entered data is formatted in JSON format as shown in the example below.
[0610] json
[0611] {
[0612] "title": "A Science Fiction",
[0613] "reading_time": "within 10 minutes",
[0614] "character_count": "1000",
[0615] "generation": "young people"
[0616] }
[0617] (Input: Specified input from the user)
[0618] (Output: Request data in JSON format)
[0619] Step 2:
[0620] The device generates an HTTP POST request based on the input information and sends it to the server. This request includes all the information the user entered.
[0621] (Input: User input data)
[0622] (Output: HTTP POST request to server)
[0623] Step 3:
[0624] The server analyzes the received request and retrieves the digital data for "A Certain Science Fiction" from the database using an SQL query to verify that the data obtained is authorized.
[0625] (Input: HTTP POST request)
[0626] (Output: Electronic data retrieved from the database)
[0627] Step 4:
[0628] The server passes a prompt sentence to the generative AI model based on the acquired electronic data. This prompt sentence is formatted as follows:
[0629] "Please summarize the book "A Certain Science Fiction" in 1000 words or less for a young reader so that it can be read in under 10 minutes."
[0630] A generative AI model takes this prompt and generates a summary.
[0631] (Input: prompt text, electronic data)
[0632] (Output: Generated summary)
[0633] Step 5:
[0634] The server formats the generated summary and sends it to the device in JSON format, which is easy for the user to view.
[0635] (Input: Generated summary)
[0636] (Output: Summary data in JSON format to terminal)
[0637] Step 6:
[0638] The terminal analyzes the summary data received from the server and displays it on a user interface, which the user can view.
[0639] (Input: Summary data received from the server)
[0640] (Output: Summary displayed in the user interface)
[0641] (Application example 1)
[0642] 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."
[0643] In today's world, busy lifestyles mean limited time for reading, and people are required to efficiently understand the main content of a book in a short amount of time. There are also limited ways for individual users to enjoy books in a format appropriate for their generation and interests. Furthermore, there is a lack of platforms for discussing book summaries, making it difficult to share reading experiences.
[0644] 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.
[0645] In this invention, the server includes means for acquiring electronic data, means for users to input reading time, desired number of characters, and generation, means for generating summaries using a generative AI model, means for creating different summaries according to the reading time, number of characters, and generation specified by the user, and means for displaying the created summaries to users and providing a discussion function. This enables users to read efficiently according to their individual needs within a limited time, and also stimulates sharing of reading experiences and discussions.
[0646] "Electronic data" means information stored in digital form, including the entire text of a book or portions thereof.
[0647] A "generative AI model" is an algorithm that uses artificial intelligence technology to analyze input text and generate a summary.
[0648] "Reading time" is the amount of time a user plans to spend reading a particular book or summary thereof.
[0649] "Number of characters" means the total number of characters in the summary to be generated.
[0650] "Generation" refers to user groups based on geographic or cultural age, with different language and expressions being tailored to each generation.
[0651] A "user" is an entity that uses this system to obtain and view book summaries.
[0652] "Server" means a computing device that retrieves electronic data, receives requests, creates summaries using generative AI models, and transmits the summaries.
[0653] The "discussion function" is an interface that allows users to exchange opinions and discuss the contents of a book based on the generated summary.
[0654] An "input interface" is a user interface that provides a means for a user to input reading time, number of characters, generation, and book title.
[0655] This invention is a system that uses a generative AI model to provide authorized book summaries. The system is mainly composed of three elements: a server, a terminal, and a user.
[0656] server
[0657] The server plays a central role in this system and has the following functions:
[0658] 1. Acquisition of electronic data: Electronic data with permission from the copyright holder is acquired from the database.
[0659] 2. Request processing: Receives the request sent from the terminal and analyzes its contents.
[0660] 3. Generative AI model creates a summary: A summary is generated based on the user's specified reading time, word count, and generation. The generative AI model analyzes the text and creates a summary.
[0661] 4. Send Abstract: Send the generated abstract to the terminal.
[0662] 5. Providing a discussion function: Provide an interface for users to exchange opinions and hold discussions based on the summary content.
[0663] The hardware used is a general-purpose server computer, and the software used is Flask (a Python microframework) and the Requests library for HTTP requests.
[0664] Terminal
[0665] The terminal is a device through which a user can enter requests and view the generated summaries via an interface. This device includes the following features:
[0666] 1. Providing an input interface: Provide a form for users to input reading time, word count, generation, book title, etc.
[0667] 2. Sending the request: Send the input request to the server.
[0668] 3. Display Abstract: The abstract received from the server is displayed to the user.
[0669] 4. Providing a discussion function: A chat function is provided for users to exchange opinions about the summary content.
[0670] User
[0671] The user is the entity that uses this system and performs the following operations:
[0672] 1. Enter information: Enter reading time, word count, generation, and book title.
[0673] 2. Submit your request: Once you've completed the input, submit your request.
[0674] 3. Viewing the summary: The summary sent from the server is viewed on the terminal.
[0675] 4. Discussion of the summary: Exchange opinions and discuss the summary with other users.
[0676] System operation example
[0677] A specific example of the operation of this system is shown below.
[0678] Example 1: Summary request for "young people" and "under 15 minutes"
[0679] The user opens the device interface, inputs the title of the book they want to read, sets the desired reading time to "15 minutes or less," the desired number of characters to "1500 characters," and sets the target age group to "young people." Once they have completed the input, they press the send request button.
[0680] The terminal sends the input information to the server, which receives the request, retrieves the electronic data of the book from the database, and confirms that the book has been licensed.
[0681] The server passes the acquired digital data to a generative AI model, which then creates a summary based on the user's preferences. The generative AI model extracts key episodes and key points and generates a summary that can be read in under 15 minutes, using language appropriate for younger readers.
[0682] The generated summary is formatted on the server and sent to the terminal, which displays the received summary on the user interface and allows the user to read the summary within a specified time.
[0683] Furthermore, users can use the chat function to hold discussions with other users who are reading the same summary. Through the interface provided by the discussion function, users can exchange opinions and discuss the summarized content to deepen their understanding.
[0684] Example prompts for generative AI models
[0685] "Below is the full text of 'XXX (book title)' with permission from the copyright holder. Please generate a 1500-character summary of this book aimed at young people that can be read in under 15 minutes."
[0686] The above is an embodiment of the present invention. This system allows users to efficiently understand the main content of a book within a limited time, and also allows users to exchange opinions about the content of the summary with other users.
[0687] The flow of the specific processing in the application example 1 will be described with reference to FIG.
[0688] Step 1:
[0689] The user uses the device's interface to input the reading time, desired number of characters, generation, and book title. For example, the user might input "less than 15 minutes," "1500 characters," "for young people," and "XXX (book title)." The input data is temporarily saved on the device. At this point, the input is the reading time, desired number of characters, generation, and book title.
[0690] Step 2:
[0691] The device sends the input information to the server. At this stage, the request includes the previously input data (reading time, desired word count, generation, and book title). The server receives this request data and begins analyzing it.
[0692] Step 3:
[0693] The server retrieves the electronic data of the specified book from the database. When retrieving the electronic data, the server searches for and retrieves the electronic data of the relevant book based on the input book title. This electronic data is used in the next process.
[0694] Step 4:
[0695] The server verifies that the digital data retrieved from the database has been authorized by the copyright holder. If authorization is successful, the digital data is passed to the generative AI model. Authorization authorization includes checking license information.
[0696] Step 5:
[0697] The server generates and passes a prompt to the generative AI model based on the user-specified reading time, desired number of characters, and generation. An example of a prompt is, "Below is the full text of 'XXX (book title)' with permission from the copyright holder. Please generate a 1500-character summary of this book aimed at young people that can be read in 15 minutes or less."
[0698] Step 6:
[0699] The server uses a generative AI model, such as GPT-3, to generate a summary based on the prompt. The generated summary is optimized to meet the user-specified criteria (less than 15 minutes, 1500 characters, and aimed at young people). The generated summary is in text format.
[0700] Step 7:
[0701] The server then formats the generated summary to make it easier for the user to read, for example by dividing it into paragraphs and highlighting important points, and the formatted summary is then ready to be sent to the device as text data.
[0702] Step 8:
[0703] The server sends the formatted summary to the terminal, which displays the received summary on its user interface.
[0704] Step 9:
[0705] The device displays the received summary to the user, who has 15 minutes to finish reading it. The device also has a discussion function that allows users to exchange opinions and discuss the summary with other users.
[0706] The above is a description of the process flow of the program of the system that realizes the application example, broken down into specific steps.
[0707] 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.
[0708] The present invention is a system that uses generative AI to provide book summaries with permission from authors and publishers, and further combines it with an emotion engine that recognizes user emotions. An embodiment of the system will be described below.
[0709] System configuration
[0710] This system is mainly composed of three elements: a server, a terminal, and a user. In addition, it has the function of recognizing the user's emotions using an emotion engine and adjusting the summary content based on those emotions.
[0711] server
[0712] The server plays a central role in this system and has the following functions:
[0713] 1. Electronic data acquisition: Electronic data with permission from the authors and publishers will be acquired from databases.
[0714] 2. Request processing: Receives the request sent from the terminal and analyzes its contents.
[0715] 3. Generative AI summary creation: Generate summaries based on user-specified reading time, word count, and generation.
[0716] 4. Emotion analysis using an emotion engine: Recognizes the user's emotions and adjusts the content and expression of the summary based on the analysis results.
[0717] 5. Send Abstract: Send the generated abstract to the terminal.
[0718] Terminal
[0719] The terminal is a device where users can enter requests through an interface and view the generated summaries. It has the following features:
[0720] 1. Providing an input interface: Provide a form for users to input reading time, word count, generation, book title, etc.
[0721] 2. Sending the request: Send the input request to the server.
[0722] 3. Acquiring emotional data: Acquire emotional data using the user's facial expressions and tone of voice.
[0723] 4. Display Abstract: The abstract received from the server is displayed to the user.
[0724] User
[0725] The user is the entity that uses this system and performs the following operations:
[0726] 1. Enter information: Enter reading time, word count, generation, and book title.
[0727] 2. Submit your request: Once you've completed the input, submit your request.
[0728] 3. Providing emotional data: Emotional data is provided using the device's camera or microphone.
[0729] 4. Viewing the summary: The summary sent from the server is viewed on the terminal.
[0730] System operation example
[0731] A specific example of the operation of this system is shown below.
[0732] Example 1: Summary request based on "young people", "under 10 minutes", and "positive sentiment"
[0733] The user opens the device's interface, enters the title of the book they want to read as "A Science Fiction," sets the desired reading time as "10 minutes or less," the desired number of characters as "1,000 characters," and sets the target age group as "Young people." In addition, the device's camera and microphone are used to provide facial expressions and tone of voice to the emotion engine.
[0734] The device sends the input information and emotion data to the server. The server receives the request, retrieves the digital data for "A Certain Science Fiction" from the database, and confirms that the book has been licensed.
[0735] The server passes the acquired digital data to a generation AI that creates a summary based on the user's wishes. The generation AI extracts key episodes and key points and generates a summary that can be read in under 10 minutes, using language appropriate for young people.
[0736] Furthermore, the emotion engine analyzes the user's emotional data and adjusts the content and expressions of the summary to match positive emotions, for example by using more energetic and positive expressions.
[0737] The server formats the generated summary and sends it to the terminal, which displays it on its user interface, allowing the user to read the summary within 10 minutes.
[0738] System convenience
[0739] This system allows users to efficiently understand the main content of a book within a limited time frame. Furthermore, by adjusting the summary based on the user's emotions, it provides a more personalized and easy-to-read summary. This improves the user's reading experience and contributes greatly to self-improvement and knowledge growth.
[0740] The above is a concrete example of how the present invention can be implemented. This system provides flexible summaries tailored to the user's needs and emotions, improving reading efficiency and comprehension.
[0741] The processing flow will be explained below.
[0742] Step 1:
[0743] The user opens a summary request form in a device application or website.
[0744] Step 2:
[0745] The user fills out a form with the title of the book or books they want to read, the author's name, the desired reading time, the desired word count, and their generation.
[0746] Step 3:
[0747] The user presses the "Send Request" button to send the input information to the server.
[0748] Step 4:
[0749] The terminal converts the user's input information into an appropriate data format, such as JSON, and sends it to the server as an HTTP request.
[0750] Step 5:
[0751] The device captures emotional data by detecting the user's facial expressions and tone of voice, and this information is collected in real time via a camera and microphone.
[0752] Step 6:
[0753] The device analyzes the emotion data and sends the results to the server.
[0754] Step 7:
[0755] The server receives the request data and emotion data sent from the terminal.
[0756] Step 8:
[0757] The server checks the database to see if the specified book or publication has been licensed by the author and publisher.
[0758] Step 9:
[0759] If the permission is confirmed, the server retrieves the electronic data of the specified book from the database. If the permission is not confirmed, the server generates an error message and returns it to the terminal.
[0760] Step 10:
[0761] The server passes the acquired electronic data and the user's requests (desired reading time, number of characters, generation) to the generation AI.
[0762] Step 11:
[0763] The generative AI analyzes the provided electronic data and automatically extracts key points and episodes.
[0764] Step 12:
[0765] The AI then uses the extracted points to generate a summary that fits the specified time and number of characters, adjusting the words and expressions to suit the user's generation.
[0766] Step 13:
[0767] The emotion engine analyzes the received emotion data and adjusts the content and expression of the summary based on the user's emotion. For example, if the user is expressing positive emotions, it will use more energetic expressions that reflect that emotion.
[0768] Step 14:
[0769] The server converts the summaries received from the generative AI and emotion engine into an appropriate format, such as HTML or plain text.
[0770] Step 15:
[0771] The server sends the formatted summary to the terminal as an HTTP response.
[0772] Step 16:
[0773] The terminal receives the summary data sent from the server.
[0774] Step 17:
[0775] The terminal displays the received summary on a user interface.
[0776] Step 18:
[0777] The user views the generated summary on the terminal.
[0778] Example 2
[0779] 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."
[0780] Conventional book summarization services can generate summaries based on given conditions, but they have difficulty providing flexible summaries that match the user's emotions. Furthermore, they are limited in their ability to adjust the optimal reading time and word count for each user, or the expression to suit the target generation. This makes it difficult to provide personalized summaries, and has led to problems in improving user satisfaction.
[0781] 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.
[0782] In this invention, the server includes means for acquiring electronic data, means for the user to input the reading time, desired number of characters, and generation, means for analyzing the input information, means for creating a summary based on the acquired electronic data and a generation AI model, means for analyzing the user's emotion data after generating the summary and adjusting the summary content based on the emotion, and means for displaying the created summary to the user. This makes it possible to provide a personalized summary based on the user's reading conditions and emotions, thereby improving the user's reading experience.
[0783] "Electronic data" refers to information such as books and documents expressed in digital form.
[0784] "User" means a person who operates and uses this system.
[0785] "Reading time" refers to the time required to read and understand a book summary designated by the user.
[0786] "Desired word count" refers to the number of words the user specifies the book summary should contain.
[0787] "Generation" refers to a particular age group or social group to which a user belongs.
[0788] "Input means" refers to an interface that allows users to input conditions and data into the system.
[0789] "Means of analysis" refers to the function of interpreting input data and conditions and performing the processing necessary for the system to operate properly.
[0790] A "generative AI model" is an algorithm that uses artificial intelligence and is a technology that automatically generates summaries of sentences or documents based on specific conditions.
[0791] A "summary" is a concise summary of the main information or points of a book or document.
[0792] "Emotional data" refers to information about emotions obtained from the user's facial expressions, tone of voice, etc.
[0793] "Adjustment means" refers to the function of changing the content and expression to the optimum based on the analysis results.
[0794] The "display means" refers to an interface for visually conveying the generated summary to the user.
[0795] This invention is a system that uses generative AI to provide book summaries with permission from authors and publishers, and also combines it with an emotion engine that recognizes the user's emotions. The system is mainly composed of three elements: a server, a terminal, and a user. The roles and operations of each are described in detail below.
[0796] server
[0797] The server is a hardware and software component that is responsible for the central operation of the entire system. Specifically, it has the following functions:
[0798] 1. Acquisition of electronic data
[0799] The server retrieves electronic data of books licensed by authors and publishers from a database, for example, by using a database management system (DBMS) to quickly search and retrieve the electronic data.
[0800] 2. Processing the Request
[0801] It receives user requests sent from the device and analyzes their contents, including input parameters (book title, reading time, number of characters, generation, etc.).
[0802] 3. Generative AI-powered summaries
[0803] The acquired digital data is input into a generative AI model, which generates a summary based on the user's specified conditions (reading time, number of characters, generation, etc.). For example, a generative AI that applies natural language processing (NLP) technology is used.
[0804] 4. Emotion analysis using an emotion engine
[0805] The technology analyzes the user's emotional data (facial expressions and tone of voice) and adjusts the summary content based on the results. Emotion recognition technology uses machine learning algorithms.
[0806] 5. Submit your summary
[0807] The generated and adjusted summary is sent to the terminal.
[0808] For example, to generate a summary of a science fiction novel for "younger adults" that can be read in under 10 minutes, the prompt would be:
[0809] Generate a summary of a science fiction novel, aimed at young people, that can be read in under 10 minutes, and is up to 1000 characters long.
[0810] Terminal
[0811] A terminal is a device that provides an interface for users to use the system. Its specific functions are as follows:
[0812] 1. Providing an input interface
[0813] Provide a form for users to enter their reading criteria (reading time, word count, generation, book title), for example, using a web browser or mobile application.
[0814] 2. Submitting a Request
[0815] The entered conditions are sent to the server using HTTP or another data communication protocol.
[0816] 3. Acquiring Emotion Data
[0817] The user's facial expressions and tone of voice are captured through a camera and microphone and sent to the emotion engine.
[0818] 4. Viewing the Summary
[0819] The summary received from the server is displayed on the screen, using HTML and mobile app UI as the interface.
[0820] User
[0821] The user is the entity that uses this system to obtain a book summary, and performs the following operations:
[0822] 1. Enter your information
[0823] Enter your reading criteria into the device interface, for example, "Science fiction," "Less than 10 minutes," "1,000 characters," and "For young people."
[0824] 2. Submitting a Request
[0825] Click the request button to send the input information to the server.
[0826] 3. Providing Emotion Data
[0827] It uses the device's camera and microphone to provide emotional data, such as a smile or a calm tone of voice.
[0828] 4. Viewing the Abstract
[0829] The summary sent from the server is viewed on the terminal screen and the content is understood based on the specified conditions.
[0830] As described above, the present invention is a system that provides an efficient reading experience by providing flexible and personalized book summaries based on the user's reading conditions and emotions.
[0831] The flow of the identification process in the second embodiment will be described with reference to FIG.
[0832] System program processing flow
[0833] Step 1: Entering the User Interface
[0834] The terminal is the main player. Here's what it does:
[0835] Input: The user enters information into an input form, including the book title, reading time, desired word count, and generation.
[0836] Data processing: The terminal converts the input information into request data.
[0837] Output: The request data is prepared.
[0838] Step 2: Submitting the request
[0839] The terminal is the main player. Here's what it does:
[0840] Input: The request data prepared in step 1.
[0841] Data operation: Converts the request data into an HTTP request format.
[0842] Output: Sends the request data to the server.
[0843] Step 3: Receiving and Parsing the Request
[0844] The server is the main player. Here's what it does:
[0845] Input: The request data sent from the device.
[0846] Data calculation: Analyze the request data and extract the title, reading time, desired number of characters, and generation.
[0847] Output: Parsed condition data.
[0848] Step 4: Get the data
[0849] The server is the main player. Here's what it does:
[0850] Input: The condition data extracted in step 3.
[0851] Data processing: Search and retrieve the corresponding electronic data from the database.
[0852] Output: The electronic data obtained.
[0853] Step 5: Generative AI creates a summary
[0854] The server is the main player. Here's what it does:
[0855] Input: The electronic data obtained and the user's conditions.
[0856] Data Computation: Input data into a generative AI model to generate summaries based on reading time, desired word count, and generation.
[0857] Output: The generated summary data.
[0858] Specific prompt examples:
[0859] Generate a summary of a science fiction novel, aimed at young people, that can be read in under 10 minutes, and is up to 1000 characters long.
[0860] Step 6: Sentiment analysis and summary adjustment
[0861] The server is the main player. Here's what it does:
[0862] Input: Generated summary data and user emotion data.
[0863] Data calculation: Emotional data is input into the emotion engine, and the summary content is adjusted based on the analysis results.
[0864] Output: Adjusted summary data.
[0865] Step 7: Send and view the summary
[0866] The server and the device are the main players in the collaboration. The specific operations are as follows:
[0867] Input: Adjusted summary data.
[0868] Data calculation: The server formats the summary data for transmission to the terminal.
[0869] Output: Summary data sent to the terminal.
[0870] Next, the terminal takes center stage. Here's what it does:
[0871] Input: Abstract data sent by the server.
[0872] Data processing: Converts the received summary data into a format that is displayed on the user interface.
[0873] Output: The summary data is displayed on the terminal screen and provided to the user.
[0874] This is the specific program processing flow of this system. At each processing step, the necessary data processing and calculations are performed based on the input data, and the results are passed on to the next processing step to provide a flexible and personalized book summary.
[0875] (Application example 2)
[0876] 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."
[0877] Conventional summary systems are unable to consider the user's emotions and state, making it difficult to provide a personalized reading experience. Furthermore, the summaries generated are uniform, making it impossible to provide content optimized for the user's emotions. Therefore, in order to improve the user's reading experience, it is necessary to provide summaries tailored to each individual's emotional state.
[0878] 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.
[0879] In this invention, the server includes means for acquiring electronic data, means for the user to input reading time, desired number of characters, and generation, means for generating, means for creating a summary, means for acquiring emotional data, means for adjusting the summary based on emotional analysis, and means for displaying the created summary to the user, thereby making it possible to provide a summary optimized for the emotional state of the user.
[0880] "Electronic data" refers to information that expresses the contents of a book in digital form and is available on a server.
[0881] "Means of acquisition" refers to the server's ability to download electronic data from authors and publishers.
[0882] "Means for input" refers to a system in which the user inputs parameters such as the desired reading time, number of characters, and generation into the terminal.
[0883] "Means of generation" refers to the function of using generative AI to create a book summary based on information entered by the user.
[0884] "Means for creating summaries" refers to the function of summarizing the main contents of a book so that they can be understood in a short amount of time.
[0885] "Means for acquiring emotional data" refers to a system that analyzes the user's facial expressions and tone of voice to detect emotions.
[0886] "Means for adjusting the summary based on emotion analysis" refers to a function for changing the content and expression of the summary based on the acquired emotion data of the user.
[0887] "Displaying means" refers to a system that displays the created summary on the user's terminal.
[0888] This invention is a system for providing a book summary optimized for a user's emotional state, and specifically consists of three elements: a server, a terminal, and a user. Specific embodiments of this system are described below.
[0889] server
[0890] The server plays a central role in this system and has the following functions:
[0891] Acquisition of electronic data: A function to acquire electronic data of books with permission from authors and publishers. Specifically, the server downloads electronic book data from the database.
[0892] Request processing: Analyzes the user's request sent from the device and uses a generative AI model to create a book summary based on the user's specified reading time, word count, and generation.
[0893] Sentiment Analysis: Analyzes the user's emotional data and adjusts the summary content. This function uses an emotion engine to analyze the user's facial expressions, tone of voice, etc.
[0894] Terminal
[0895] A terminal is a device that provides an interface for users to operate the system. Specifically, it has the following functions:
[0896] Providing an input interface: Provide a form for users to input reading time, word count, generation, book title, etc.
[0897] Acquiring emotional data: Acquires the user's emotional data using the device's camera and microphone. Detects the user's emotional state by analyzing facial expressions and voice using OpenCV.
[0898] Displaying the summary: The summary sent from the server is displayed to the user. The generated summary is adjusted based on sentiment analysis, so it is the most appropriate content for the user.
[0899] User
[0900] The user is the entity that uses this system and performs the following operations:
[0901] Enter information: Enter reading time, word count, generation, book title, etc. using the device interface.
[0902] Submit your request: Once you have completed the entry, submit your request to request an electronic summary of your data.
[0903] Providing emotional data: Emotional data is provided from facial expressions and tone of voice using the device's camera and microphone.
[0904] Viewing the summary: The summary sent from the server is received on the terminal and viewed.
[0905] Specific examples
[0906] For example, consider a case where a user requests a summary of a "science novel" and sets the reading time to "less than 10 minutes," the desired word count to "1,000 characters," and the target demographic to "young people." When the user provides emotional data (e.g., joy) using the device's camera and microphone, the server acquires the electronic data and generates a summary using a generative AI model. Next, the emotion engine performs emotional analysis and adjusts the summary's expression to be more positive. As a result, the server sends a summary that uses a lot of positive language and can be read in less than 10 minutes to the device, and the user can view it.
[0907] Prompt Sentence Examples
[0908] "Generate a summary of the book in 150 characters or less: "Harry Potter and the Philosopher's Stone, this book is...""
[0909] In this way, the system provides summaries tailored to the user's emotional state, enabling an efficient and personalized reading experience.
[0910] The flow of the specific processing in the application example 2 will be described with reference to FIG.
[0911] Step 1:
[0912] The user uses the terminal interface to input the book title, desired reading time, number of characters, generation, etc. The input information is collected by the terminal and sent to the server in the next step.
[0913] Input: Book title, desired reading time, desired number of characters, generation
[0914] Output: Request data sent to the next step
[0915] Step 2:
[0916] The terminal sends the collected user input information to the server, which receives and analyzes this request data.
[0917] Input: User request data
[0918] Output: Analysis result of request data
[0919] Step 3:
[0920] The device's camera and microphone are used to acquire the user's emotional data, which is collected by the device and sent to the server in the next step.
[0921] Input: User's facial expression, tone of voice
[0922] Output: Parsed emotion data
[0923] Step 4:
[0924] The device sends emotional data to the server, which receives and analyzes the data.
[0925] Input: Parsed emotion data
[0926] Output: Analysis results of emotion data
[0927] Step 5:
[0928] The server retrieves the e-book data from the database and sends a prompt to the AI model based on the user's request to generate a summary. The prompt is: "Please generate a summary of the book's contents in 150 characters or less: 'Harry Potter and the Philosopher's Stone, this book is...'"
[0929] Input: e-book data, request data, prompt text
[0930] Output: Generated book summary
[0931] Step 6:
[0932] The server adjusts the generated summary based on sentiment analysis. For example, if the sentiment is positive, it will use more positive expressions.
[0933] Input: Generated summary, analysis results of emotion data
[0934] Output: A sentiment-adjusted summary
[0935] Step 7:
[0936] The server sends the adjusted summary content to the terminal, which displays the received summary to the user.
[0937] Input: Adjusted summary
[0938] Output: A summary that is displayed to the user
[0939] This allows users to receive summaries optimized for their emotional state, resulting in an efficient and personalized reading experience.
[0940] 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.
[0941] 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.
[0942] 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.
[0943] [Third embodiment]
[0944] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.
[0945] 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.
[0946] 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).
[0947] 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.
[0948] 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.
[0949] 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).
[0950] 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.
[0951] 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.
[0952] 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.
[0953] 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.
[0954] 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.
[0955] 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."
[0956] The present invention is a system that uses a generative AI to provide a summary of a book with permission from the author and publisher. An embodiment of the system will be described below.
[0957] System configuration
[0958] This system is mainly composed of three elements: a server, a terminal, and a user.
[0959] server
[0960] The server plays a central role in this system and has the following functions:
[0961] 1. Electronic data acquisition: Electronic data with permission from the authors and publishers will be acquired from databases.
[0962] 2. Request processing: Receives the request sent from the terminal and analyzes its contents.
[0963] 3. Generative AI summary creation: Generate summaries based on user-specified reading time, word count, and generation.
[0964] 4. Send Abstract: Send the generated abstract to the terminal.
[0965] Terminal
[0966] The terminal is a device where users can enter requests through an interface and view the generated summaries. It has the following features:
[0967] 1. Providing an input interface: Provide a form for users to input reading time, word count, generation, book title, etc.
[0968] 2. Sending the request: Send the input request to the server.
[0969] 3. Display Abstract: The abstract received from the server is displayed to the user.
[0970] User
[0971] The user is the entity that uses this system and performs the following operations:
[0972] 1. Enter information: Enter reading time, word count, generation, and book title.
[0973] 2. Submit your request: Once you've completed the input, submit your request.
[0974] 3. Viewing the summary: The summary sent from the server is viewed on the terminal.
[0975] System operation example
[0976] A specific example of the operation of this system is shown below.
[0977] Example 1: Summary request for "young people" and "less than 10 minutes"
[0978] The user opens the device interface, enters the title of the book they want to read as "A Science Fiction," sets the desired reading time as "10 minutes or less," sets the desired word count as "1,000 characters," and sets the target age group as "Young people." Once they've completed the input, they press the send request button.
[0979] The terminal sends the input information to the server, which receives the request, retrieves the electronic data for "A Certain Science Fiction" from the database, and confirms that the book has been licensed.
[0980] The server passes the acquired digital data to a generation AI that creates a summary based on the user's wishes. The generation AI extracts key episodes and key points and generates a summary that can be read in under 10 minutes, using language appropriate for young people.
[0981] The server formats the generated summary and sends it to the terminal, which displays it on its user interface, allowing the user to read the summary within 10 minutes.
[0982] System convenience
[0983] This system allows users to efficiently understand the main content of a book within a limited time. It also makes difficult content easier to understand by appropriately summarizing it. Therefore, it can be said that this system greatly contributes to users' self-improvement and knowledge improvement.
[0984] The above is a concrete example of how the present invention can be implemented. This system provides flexible summaries tailored to the user's needs, improving reading efficiency and comprehension.
[0985] The processing flow will be explained below.
[0986] Step 1:
[0987] The user opens a summary request form in a device application or website.
[0988] Step 2:
[0989] The user fills out a form with the title of the book or books they want to read, the author's name, the desired reading time, the desired word count, and their generation.
[0990] Step 3:
[0991] The user presses the "Send Request" button to send the input information to the server.
[0992] Step 4:
[0993] The terminal converts the user's input information into an appropriate data format such as JSON and sends it to the server as an HTTP request (e.g., POST request).
[0994] Step 5:
[0995] The server receives the request data sent from the terminal.
[0996] Step 6:
[0997] The server checks the database to see if the specified book or publication has been licensed by the author and publisher.
[0998] Step 7:
[0999] If the permission is confirmed, the server retrieves the electronic data of the specified book from the database. If the permission is not confirmed, the server generates an error message and returns it to the terminal.
[1000] Step 8:
[1001] The server passes the acquired electronic data and the user's requests (desired reading time, number of characters, generation) to the generation AI.
[1002] Step 9:
[1003] The generative AI analyzes the provided electronic data and automatically extracts key points and episodes.
[1004] Step 10:
[1005] The AI then uses the extracted points to generate a summary that fits the specified time and number of characters, adjusting the words and expressions to suit the user's generation.
[1006] Step 11:
[1007] The server converts the summary received from the generation AI into an appropriate format, such as HTML or plain text.
[1008] Step 12:
[1009] The server sends the formatted summary to the terminal as an HTTP response.
[1010] Step 13:
[1011] The terminal receives the summary data sent from the server.
[1012] Step 14:
[1013] The terminal displays the received summary on a user interface.
[1014] Step 15:
[1015] The user views the generated summary on the terminal.
[1016] Example 1
[1017] 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."
[1018] In modern society, there is a huge amount of information and books available, and people are required to understand their content efficiently within a limited time. However, conventional book summarization systems have difficulty providing appropriate summaries that suit the user's desired reading time and age, and there is a lack of means to provide easy-to-understand summaries.
[1019] 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.
[1020] In this invention, the server includes a means for acquiring electronic data, a means for analyzing a request and acquiring electronic data from a database, a means for passing a prompt sentence to a generative AI model and generating a summary, and a means for formatting the generated summary and sending it to a terminal. This makes it possible to efficiently provide appropriate and easy-to-understand summaries according to the user's desired reading time, number of characters, and generation.
[1021] "Electronic data" refers to digital information handled by computers and electronic devices, including the contents of books and documents.
[1022] "User" refers to the primary user who uses the System to input information and receive book summaries.
[1023] A "request" refers to a request from a user to the system for specific processing or information provision.
[1024] "Server" refers to the computer system that plays a central role in this system and performs tasks such as analyzing requests, acquiring data, and running generative AI.
[1025] A "database" refers to a system that organizes and stores electronic data so that it can be efficiently searched when needed.
[1026] A "generative AI model" refers to an artificial intelligence system that generates and summarizes sentences using natural language processing techniques, such as large-scale language models.
[1027] A "prompt" refers to a text instruction entered into a generative AI model to instruct it on how to proceed.
[1028] A "summary" is a document that presents the main content of an original book or document in an abbreviated form.
[1029] "Terminal" refers to a device, such as a computer or smartphone, that a user uses to access the system, enter information, and view generated summaries.
[1030] "Formatting" refers to the process of adjusting the format and content of the generated summary to make it easier to read.
[1031] MODE FOR CARRYING OUT THE INVENTION
[1032] This invention is a system that uses a generative AI model to provide book summaries with permission from authors and publishers. This system mainly consists of three elements: a server, a terminal, and a user.
[1033] server
[1034] The server plays a central role in this system and has the following functions:
[1035] 1. Electronic Data Acquisition:
[1036] The server retrieves electronic data from the database with permission from the authors and publishers, specifically using a database management system such as SQL Server.
[1037] 2. Processing the request:
[1038] The server receives the request sent from the terminal and analyzes its contents. Web frameworks such as Flask and Django are used to process HTTP requests.
[1039] 3. Generative AI model for summarization:
[1040] The server uses a generative AI model (e.g., OpenAI's GPT model) to generate a summary based on the user's specified reading time, number of characters, and generation. In this process, it generates a prompt sentence and passes it to the AI.
[1041] 4. Submit your abstract:
[1042] The server formats the generated summary and sends it to the device. It uses a standard API endpoint to send it as JSON data.
[1043] Terminal
[1044] The terminal is a device where users can enter requests through an interface and view the generated summaries. It has the following features:
[1045] 1. Providing an input interface:
[1046] The terminal provides a form for users to input reading time, word count, generation, book title, etc. The interface is built using front-end frameworks such as React and Vue.js.
[1047] 2. Submit your request:
[1048] The device sends the input request to the server. It uses AJAX or Fetch API to send an HTTP request to the server.
[1049] 3. View Summary:
[1050] The device receives the summary from the server and displays it to the user in an easy-to-read format using style frameworks such as CSS and Bootstrap.
[1051] User
[1052] The user is the entity that uses this system and performs the following operations:
[1053] 1. Enter your information:
[1054] The user inputs the title, reading time, number of characters, and generation into a form on the terminal.
[1055] 2. Submit your request:
[1056] Once you have completed the input, click the Send Request button.
[1057] 3. View Abstract:
[1058] The summary sent from the server is viewed on the terminal.
[1059] Specific examples
[1060] A specific example of the operation of this system is shown below.
[1061] Example 1: Summary request for young people in under 10 minutes
[1062] The user opens the device interface, enters the title of the book they want to read as "A Science Fiction," sets the desired reading time as "10 minutes or less," sets the desired word count as "1,000 characters," and sets the target age group as "Young people." Once they've completed the input, they press the send request button.
[1063] The device converts the input information into JSON format and sends an HTTP POST request to the server.
[1064] The server receives the request, analyzes it, retrieves the digital copy of "A Certain Science Fiction Book" from the database, verifies that the book is licensed, and then passes the following prompt to the generative AI model:
[1065] "Please summarize the book "A Certain Science Fiction" in 1000 words or less for a young reader so that it can be read in under 10 minutes."
[1066] The generative AI model generates a summary and returns it to the server, which formats the summary and sends it to the device, which displays it on the user interface, allowing the user to read the summary in under 10 minutes.
[1067] The above is a specific embodiment of the present invention. This system provides flexible summaries tailored to the user's needs, improving reading efficiency and comprehension.
[1068] The flow of the identification process in the first embodiment will be described with reference to FIG.
[1069] Step 1:
[1070] The user uses the device interface to enter information such as reading time, desired word count, generation, book title, etc. The entered data is formatted in JSON format as shown in the example below.
[1071] json
[1072] {
[1073] "title": "A Science Fiction",
[1074] "reading_time": "within 10 minutes",
[1075] "character_count": "1000",
[1076] "generation": "young people"
[1077] }
[1078] (Input: Specified input from the user)
[1079] (Output: Request data in JSON format)
[1080] Step 2:
[1081] The device generates an HTTP POST request based on the input information and sends it to the server. This request includes all the information the user entered.
[1082] (Input: User input data)
[1083] (Output: HTTP POST request to server)
[1084] Step 3:
[1085] The server analyzes the received request and retrieves the digital data for "A Certain Science Fiction" from the database using an SQL query to verify that the data obtained is authorized.
[1086] (Input: HTTP POST request)
[1087] (Output: Electronic data retrieved from the database)
[1088] Step 4:
[1089] The server passes a prompt sentence to the generative AI model based on the acquired electronic data. This prompt sentence is formatted as follows:
[1090] "Please summarize the book "A Certain Science Fiction" in 1000 words or less for a young reader so that it can be read in under 10 minutes."
[1091] A generative AI model takes this prompt and generates a summary.
[1092] (Input: prompt text, electronic data)
[1093] (Output: Generated summary)
[1094] Step 5:
[1095] The server formats the generated summary and sends it to the device in JSON format, which is easy for the user to view.
[1096] (Input: Generated summary)
[1097] (Output: Summary data in JSON format to terminal)
[1098] Step 6:
[1099] The terminal analyzes the summary data received from the server and displays it on a user interface, which the user can view.
[1100] (Input: Summary data received from the server)
[1101] (Output: Summary displayed in the user interface)
[1102] (Application example 1)
[1103] 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."
[1104] In today's world, busy lifestyles mean limited time for reading, and people are required to efficiently understand the main content of a book in a short amount of time. There are also limited ways for individual users to enjoy books in a format appropriate for their generation and interests. Furthermore, there is a lack of platforms for discussing book summaries, making it difficult to share reading experiences.
[1105] 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.
[1106] In this invention, the server includes means for acquiring electronic data, means for users to input reading time, desired number of characters, and generation, means for generating summaries using a generative AI model, means for creating different summaries according to the reading time, number of characters, and generation specified by the user, and means for displaying the created summaries to users and providing a discussion function. This enables users to read efficiently according to their individual needs within a limited time, and also stimulates sharing of reading experiences and discussions.
[1107] "Electronic data" means information stored in digital form, including the entire text of a book or portions thereof.
[1108] A "generative AI model" is an algorithm that uses artificial intelligence technology to analyze input text and generate a summary.
[1109] "Reading time" is the amount of time a user plans to spend reading a particular book or summary thereof.
[1110] "Number of characters" means the total number of characters in the summary to be generated.
[1111] "Generation" refers to user groups based on geographic or cultural age, with different language and expressions being tailored to each generation.
[1112] A "user" is an entity that uses this system to obtain and view book summaries.
[1113] "Server" means a computing device that retrieves electronic data, receives requests, creates summaries using generative AI models, and transmits the summaries.
[1114] The "discussion function" is an interface that allows users to exchange opinions and discuss the contents of a book based on the generated summary.
[1115] An "input interface" is a user interface that provides a means for a user to input reading time, number of characters, generation, and book title.
[1116] This invention is a system that uses a generative AI model to provide authorized book summaries. The system is mainly composed of three elements: a server, a terminal, and a user.
[1117] server
[1118] The server plays a central role in this system and has the following functions:
[1119] 1. Acquisition of electronic data: Electronic data with permission from the copyright holder is acquired from the database.
[1120] 2. Request processing: Receives the request sent from the terminal and analyzes its contents.
[1121] 3. Generative AI model creates a summary: A summary is generated based on the user's specified reading time, word count, and generation. The generative AI model analyzes the text and creates a summary.
[1122] 4. Send Abstract: Send the generated abstract to the terminal.
[1123] 5. Providing a discussion function: Provide an interface for users to exchange opinions and hold discussions based on the summary content.
[1124] The hardware used is a general-purpose server computer, and the software used is Flask (a Python microframework) and the Requests library for HTTP requests.
[1125] Terminal
[1126] The terminal is a device through which a user can enter requests and view the generated summaries via an interface. This device includes the following features:
[1127] 1. Providing an input interface: Provide a form for users to input reading time, word count, generation, book title, etc.
[1128] 2. Sending the request: Send the input request to the server.
[1129] 3. Display Abstract: The abstract received from the server is displayed to the user.
[1130] 4. Providing a discussion function: A chat function is provided for users to exchange opinions about the summary content.
[1131] User
[1132] The user is the entity that uses this system and performs the following operations:
[1133] 1. Enter information: Enter reading time, word count, generation, and book title.
[1134] 2. Submit your request: Once you've completed the input, submit your request.
[1135] 3. Viewing the summary: The summary sent from the server is viewed on the terminal.
[1136] 4. Discussion of the summary: Exchange opinions and discuss the summary with other users.
[1137] System operation example
[1138] A specific example of the operation of this system is shown below.
[1139] Example 1: Summary request for "young people" and "under 15 minutes"
[1140] The user opens the device interface, inputs the title of the book they want to read, sets the desired reading time to "15 minutes or less," the desired number of characters to "1500 characters," and sets the target age group to "young people." Once they have completed the input, they press the send request button.
[1141] The terminal sends the input information to the server, which receives the request, retrieves the electronic data of the book from the database, and confirms that the book has been licensed.
[1142] The server passes the acquired digital data to a generative AI model, which then creates a summary based on the user's preferences. The generative AI model extracts key episodes and key points and generates a summary that can be read in under 15 minutes, using language appropriate for younger readers.
[1143] The generated summary is formatted on the server and sent to the terminal, which displays the received summary on the user interface and allows the user to read the summary within a specified time.
[1144] Furthermore, users can use the chat function to hold discussions with other users who are reading the same summary. Through the interface provided by the discussion function, users can exchange opinions and discuss the summarized content to deepen their understanding.
[1145] Example prompts for generative AI models
[1146] "Below is the full text of 'XXX (book title)' with permission from the copyright holder. Please generate a 1500-character summary of this book aimed at young people that can be read in under 15 minutes."
[1147] The above is an embodiment of the present invention. This system allows users to efficiently understand the main content of a book within a limited time, and also allows users to exchange opinions about the content of the summary with other users.
[1148] The flow of the specific processing in the application example 1 will be described with reference to FIG.
[1149] Step 1:
[1150] The user uses the device's interface to input the reading time, desired number of characters, generation, and book title. For example, the user might input "less than 15 minutes," "1500 characters," "for young people," and "XXX (book title)." The input data is temporarily saved on the device. At this point, the input is the reading time, desired number of characters, generation, and book title.
[1151] Step 2:
[1152] The device sends the input information to the server. At this stage, the request includes the previously input data (reading time, desired word count, generation, and book title). The server receives this request data and begins analyzing it.
[1153] Step 3:
[1154] The server retrieves the electronic data of the specified book from the database. When retrieving the electronic data, the server searches for and retrieves the electronic data of the relevant book based on the input book title. This electronic data is used in the next process.
[1155] Step 4:
[1156] The server verifies that the digital data retrieved from the database has been authorized by the copyright holder. If authorization is successful, the digital data is passed to the generative AI model. Authorization authorization includes checking license information.
[1157] Step 5:
[1158] The server generates and passes a prompt to the generative AI model based on the user-specified reading time, desired number of characters, and generation. An example of a prompt is, "Below is the full text of 'XXX (book title)' with permission from the copyright holder. Please generate a 1500-character summary of this book aimed at young people that can be read in 15 minutes or less."
[1159] Step 6:
[1160] The server uses a generative AI model, such as GPT-3, to generate a summary based on the prompt. The generated summary is optimized to meet the user-specified criteria (less than 15 minutes, 1500 characters, and aimed at young people). The generated summary is in text format.
[1161] Step 7:
[1162] The server then formats the generated summary to make it easier for the user to read, for example by dividing it into paragraphs and highlighting important points, and the formatted summary is then ready to be sent to the device as text data.
[1163] Step 8:
[1164] The server sends the formatted summary to the terminal, which displays the received summary on its user interface.
[1165] Step 9:
[1166] The device displays the received summary to the user, who has 15 minutes to finish reading it. The device also has a discussion function that allows users to exchange opinions and discuss the summary with other users.
[1167] The above is a description of the process flow of the program of the system that realizes the application example, broken down into specific steps.
[1168] 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.
[1169] The present invention is a system that uses generative AI to provide book summaries with permission from authors and publishers, and further combines it with an emotion engine that recognizes user emotions. An embodiment of the system will be described below.
[1170] System configuration
[1171] This system is mainly composed of three elements: a server, a terminal, and a user. In addition, it has the function of recognizing the user's emotions using an emotion engine and adjusting the summary content based on those emotions.
[1172] server
[1173] The server plays a central role in this system and has the following functions:
[1174] 1. Electronic data acquisition: Electronic data with permission from the authors and publishers will be acquired from databases.
[1175] 2. Request processing: Receives the request sent from the terminal and analyzes its contents.
[1176] 3. Generative AI summary creation: Generate summaries based on user-specified reading time, word count, and generation.
[1177] 4. Emotion analysis using an emotion engine: Recognizes the user's emotions and adjusts the content and expression of the summary based on the analysis results.
[1178] 5. Send Abstract: Send the generated abstract to the terminal.
[1179] Terminal
[1180] The terminal is a device where users can enter requests through an interface and view the generated summaries. It has the following features:
[1181] 1. Providing an input interface: Provide a form for users to input reading time, word count, generation, book title, etc.
[1182] 2. Sending the request: Send the input request to the server.
[1183] 3. Acquiring emotional data: Acquire emotional data using the user's facial expressions and tone of voice.
[1184] 4. Display Abstract: The abstract received from the server is displayed to the user.
[1185] User
[1186] The user is the entity that uses this system and performs the following operations:
[1187] 1. Enter information: Enter reading time, word count, generation, and book title.
[1188] 2. Submit your request: Once you've completed the input, submit your request.
[1189] 3. Providing emotional data: Emotional data is provided using the device's camera or microphone.
[1190] 4. Viewing the summary: The summary sent from the server is viewed on the terminal.
[1191] System operation example
[1192] A specific example of the operation of this system is shown below.
[1193] Example 1: Summary request based on "young people", "under 10 minutes", and "positive sentiment"
[1194] The user opens the device's interface, enters the title of the book they want to read as "A Science Fiction," sets the desired reading time as "10 minutes or less," the desired number of characters as "1,000 characters," and sets the target age group as "Young people." In addition, the device's camera and microphone are used to provide facial expressions and tone of voice to the emotion engine.
[1195] The device sends the input information and emotion data to the server. The server receives the request, retrieves the digital data for "A Certain Science Fiction" from the database, and confirms that the book has been licensed.
[1196] The server passes the acquired digital data to a generation AI that creates a summary based on the user's wishes. The generation AI extracts key episodes and key points and generates a summary that can be read in under 10 minutes, using language appropriate for young people.
[1197] Furthermore, the emotion engine analyzes the user's emotional data and adjusts the content and expressions of the summary to match positive emotions, for example by using more energetic and positive expressions.
[1198] The server formats the generated summary and sends it to the terminal, which displays it on its user interface, allowing the user to read the summary within 10 minutes.
[1199] System convenience
[1200] This system allows users to efficiently understand the main content of a book within a limited time frame. Furthermore, by adjusting the summary based on the user's emotions, it provides a more personalized and easy-to-read summary. This improves the user's reading experience and contributes greatly to self-improvement and knowledge growth.
[1201] The above is a concrete example of how the present invention can be implemented. This system provides flexible summaries tailored to the user's needs and emotions, improving reading efficiency and comprehension.
[1202] The processing flow will be explained below.
[1203] Step 1:
[1204] The user opens a summary request form in a device application or website.
[1205] Step 2:
[1206] The user fills out a form with the title of the book or books they want to read, the author's name, the desired reading time, the desired word count, and their generation.
[1207] Step 3:
[1208] The user presses the "Send Request" button to send the input information to the server.
[1209] Step 4:
[1210] The terminal converts the user's input information into an appropriate data format, such as JSON, and sends it to the server as an HTTP request.
[1211] Step 5:
[1212] The device captures emotional data by detecting the user's facial expressions and tone of voice, and this information is collected in real time via a camera and microphone.
[1213] Step 6:
[1214] The device analyzes the emotion data and sends the results to the server.
[1215] Step 7:
[1216] The server receives the request data and emotion data sent from the terminal.
[1217] Step 8:
[1218] The server checks the database to see if the specified book or publication has been licensed by the author and publisher.
[1219] Step 9:
[1220] If the permission is confirmed, the server retrieves the electronic data of the specified book from the database. If the permission is not confirmed, the server generates an error message and returns it to the terminal.
[1221] Step 10:
[1222] The server passes the acquired electronic data and the user's requests (desired reading time, number of characters, generation) to the generation AI.
[1223] Step 11:
[1224] The generative AI analyzes the provided electronic data and automatically extracts key points and episodes.
[1225] Step 12:
[1226] The AI then uses the extracted points to generate a summary that fits the specified time and number of characters, adjusting the words and expressions to suit the user's generation.
[1227] Step 13:
[1228] The emotion engine analyzes the received emotion data and adjusts the content and expression of the summary based on the user's emotion. For example, if the user is expressing positive emotions, it will use more energetic expressions that reflect that emotion.
[1229] Step 14:
[1230] The server converts the summaries received from the generative AI and emotion engine into an appropriate format, such as HTML or plain text.
[1231] Step 15:
[1232] The server sends the formatted summary to the terminal as an HTTP response.
[1233] Step 16:
[1234] The terminal receives the summary data sent from the server.
[1235] Step 17:
[1236] The terminal displays the received summary on a user interface.
[1237] Step 18:
[1238] The user views the generated summary on the terminal.
[1239] Example 2
[1240] 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."
[1241] Conventional book summarization services can generate summaries based on given conditions, but they have difficulty providing flexible summaries that match the user's emotions. Furthermore, they are limited in their ability to adjust the optimal reading time and word count for each user, or the expression to suit the target generation. This makes it difficult to provide personalized summaries, and has led to problems in improving user satisfaction.
[1242] 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.
[1243] In this invention, the server includes means for acquiring electronic data, means for the user to input the reading time, desired number of characters, and generation, means for analyzing the input information, means for creating a summary based on the acquired electronic data and a generation AI model, means for analyzing the user's emotion data after generating the summary and adjusting the summary content based on the emotion, and means for displaying the created summary to the user. This makes it possible to provide a personalized summary based on the user's reading conditions and emotions, thereby improving the user's reading experience.
[1244] "Electronic data" refers to information such as books and documents expressed in digital form.
[1245] "User" means a person who operates and uses this system.
[1246] "Reading time" refers to the time required to read and understand a book summary designated by the user.
[1247] "Desired word count" refers to the number of words the user specifies the book summary should contain.
[1248] "Generation" refers to a particular age group or social group to which a user belongs.
[1249] "Input means" refers to an interface that allows users to input conditions and data into the system.
[1250] "Means of analysis" refers to the function of interpreting input data and conditions and performing the processing necessary for the system to operate properly.
[1251] A "generative AI model" is an algorithm that uses artificial intelligence and is a technology that automatically generates summaries of sentences or documents based on specific conditions.
[1252] A "summary" is a concise summary of the main information or points of a book or document.
[1253] "Emotional data" refers to information about emotions obtained from the user's facial expressions, tone of voice, etc.
[1254] "Adjustment means" refers to the function of changing the content and expression to the optimum based on the analysis results.
[1255] The "display means" refers to an interface for visually conveying the generated summary to the user.
[1256] This invention is a system that uses generative AI to provide book summaries with permission from authors and publishers, and also combines it with an emotion engine that recognizes the user's emotions. The system is mainly composed of three elements: a server, a terminal, and a user. The roles and operations of each are described in detail below.
[1257] server
[1258] The server is a hardware and software component that is responsible for the central operation of the entire system. Specifically, it has the following functions:
[1259] 1. Acquisition of electronic data
[1260] The server retrieves electronic data of books licensed by authors and publishers from a database, for example, by using a database management system (DBMS) to quickly search and retrieve the electronic data.
[1261] 2. Processing the Request
[1262] It receives user requests sent from the device and analyzes their contents, including input parameters (book title, reading time, number of characters, generation, etc.).
[1263] 3. Generative AI-powered summaries
[1264] The acquired digital data is input into a generative AI model, which generates a summary based on the user's specified conditions (reading time, number of characters, generation, etc.). For example, a generative AI that applies natural language processing (NLP) technology is used.
[1265] 4. Emotion analysis using an emotion engine
[1266] The technology analyzes the user's emotional data (facial expressions and tone of voice) and adjusts the summary content based on the results. Emotion recognition technology uses machine learning algorithms.
[1267] 5. Submit your summary
[1268] The generated and adjusted summary is sent to the terminal.
[1269] For example, to generate a summary of a science fiction novel for "younger adults" that can be read in under 10 minutes, the prompt would be:
[1270] Generate a summary of a science fiction novel, aimed at young people, that can be read in under 10 minutes, and is up to 1000 characters long.
[1271] Terminal
[1272] A terminal is a device that provides an interface for users to use the system. Its specific functions are as follows:
[1273] 1. Providing an input interface
[1274] Provide a form for users to enter their reading criteria (reading time, word count, generation, book title), for example, using a web browser or mobile application.
[1275] 2. Submitting a Request
[1276] The entered conditions are sent to the server using HTTP or another data communication protocol.
[1277] 3. Acquiring Emotion Data
[1278] The user's facial expressions and tone of voice are captured through a camera and microphone and sent to the emotion engine.
[1279] 4. Viewing the Summary
[1280] The summary received from the server is displayed on the screen, using HTML and mobile app UI as the interface.
[1281] User
[1282] The user is the entity that uses this system to obtain a book summary, and performs the following operations:
[1283] 1. Enter your information
[1284] Enter your reading criteria into the device interface, for example, "Science fiction," "Less than 10 minutes," "1,000 characters," and "For young people."
[1285] 2. Submitting a Request
[1286] Click the request button to send the input information to the server.
[1287] 3. Providing Emotion Data
[1288] It uses the device's camera and microphone to provide emotional data, such as a smile or a calm tone of voice.
[1289] 4. Viewing the Abstract
[1290] The summary sent from the server is viewed on the terminal screen and the content is understood based on the specified conditions.
[1291] As described above, the present invention is a system that provides an efficient reading experience by providing flexible and personalized book summaries based on the user's reading conditions and emotions.
[1292] The flow of the identification process in the second embodiment will be described with reference to FIG.
[1293] System program processing flow
[1294] Step 1: Entering the User Interface
[1295] The terminal is the main player. Here's what it does:
[1296] Input: The user enters information into an input form, including the book title, reading time, desired word count, and generation.
[1297] Data processing: The terminal converts the input information into request data.
[1298] Output: The request data is prepared.
[1299] Step 2: Submitting the request
[1300] The terminal is the main player. Here's what it does:
[1301] Input: The request data prepared in step 1.
[1302] Data operation: Converts the request data into an HTTP request format.
[1303] Output: Sends the request data to the server.
[1304] Step 3: Receiving and Parsing the Request
[1305] The server is the main player. Here's what it does:
[1306] Input: The request data sent from the device.
[1307] Data calculation: Analyze the request data and extract the title, reading time, desired number of characters, and generation.
[1308] Output: Parsed condition data.
[1309] Step 4: Get the data
[1310] The server is the main player. Here's what it does:
[1311] Input: The condition data extracted in step 3.
[1312] Data processing: Search and retrieve the corresponding electronic data from the database.
[1313] Output: The electronic data obtained.
[1314] Step 5: Generative AI creates a summary
[1315] The server is the main player. Here's what it does:
[1316] Input: The electronic data obtained and the user's conditions.
[1317] Data Computation: Input data into a generative AI model to generate summaries based on reading time, desired word count, and generation.
[1318] Output: The generated summary data.
[1319] Specific prompt examples:
[1320] Generate a summary of a science fiction novel, aimed at young people, that can be read in under 10 minutes, and is up to 1000 characters long.
[1321] Step 6: Sentiment analysis and summary adjustment
[1322] The server is the main player. Here's what it does:
[1323] Input: Generated summary data and user emotion data.
[1324] Data calculation: Emotional data is input into the emotion engine, and the summary content is adjusted based on the analysis results.
[1325] Output: Adjusted summary data.
[1326] Step 7: Send and view the summary
[1327] The server and the device are the main players in the collaboration. The specific operations are as follows:
[1328] Input: Adjusted summary data.
[1329] Data calculation: The server formats the summary data for transmission to the terminal.
[1330] Output: Summary data sent to the terminal.
[1331] Next, the terminal takes center stage. Here's what it does:
[1332] Input: Abstract data sent by the server.
[1333] Data processing: Converts the received summary data into a format that is displayed on the user interface.
[1334] Output: The summary data is displayed on the terminal screen and provided to the user.
[1335] This is the specific program processing flow of this system. At each processing step, the necessary data processing and calculations are performed based on the input data, and the results are passed on to the next processing step to provide a flexible and personalized book summary.
[1336] (Application example 2)
[1337] 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."
[1338] Conventional summary systems are unable to consider the user's emotions and state, making it difficult to provide a personalized reading experience. Furthermore, the summaries generated are uniform, making it impossible to provide content optimized for the user's emotions. Therefore, in order to improve the user's reading experience, it is necessary to provide summaries tailored to each individual's emotional state.
[1339] 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.
[1340] In this invention, the server includes means for acquiring electronic data, means for the user to input reading time, desired number of characters, and generation, means for generating, means for creating a summary, means for acquiring emotional data, means for adjusting the summary based on emotional analysis, and means for displaying the created summary to the user, thereby making it possible to provide a summary optimized for the emotional state of the user.
[1341] "Electronic data" refers to information that expresses the contents of a book in digital form and is available on a server.
[1342] "Means of acquisition" refers to the server's ability to download electronic data from authors and publishers.
[1343] "Means for input" refers to a system in which the user inputs parameters such as the desired reading time, number of characters, and generation into the terminal.
[1344] "Means of generation" refers to the function of using generative AI to create a book summary based on information entered by the user.
[1345] "Means for creating summaries" refers to the function of summarizing the main contents of a book so that they can be understood in a short amount of time.
[1346] "Means for acquiring emotional data" refers to a system that analyzes the user's facial expressions and tone of voice to detect emotions.
[1347] "Means for adjusting the summary based on emotion analysis" refers to a function for changing the content and expression of the summary based on the acquired emotion data of the user.
[1348] "Displaying means" refers to a system that displays the created summary on the user's terminal.
[1349] This invention is a system for providing a book summary optimized for a user's emotional state, and specifically consists of three elements: a server, a terminal, and a user. Specific embodiments of this system are described below.
[1350] server
[1351] The server plays a central role in this system and has the following functions:
[1352] Acquisition of electronic data: A function to acquire electronic data of books with permission from authors and publishers. Specifically, the server downloads electronic book data from the database.
[1353] Request processing: Analyzes the user's request sent from the device and uses a generative AI model to create a book summary based on the user's specified reading time, word count, and generation.
[1354] Sentiment Analysis: Analyzes the user's emotional data and adjusts the summary content. This function uses an emotion engine to analyze the user's facial expressions, tone of voice, etc.
[1355] Terminal
[1356] A terminal is a device that provides an interface for users to operate the system. Specifically, it has the following functions:
[1357] Providing an input interface: Provide a form for users to input reading time, word count, generation, book title, etc.
[1358] Acquiring emotional data: Acquires the user's emotional data using the device's camera and microphone. Detects the user's emotional state by analyzing facial expressions and voice using OpenCV.
[1359] Displaying the summary: The summary sent from the server is displayed to the user. The generated summary is adjusted based on sentiment analysis, so it is the most appropriate content for the user.
[1360] User
[1361] The user is the entity that uses this system and performs the following operations:
[1362] Enter information: Enter reading time, word count, generation, book title, etc. using the device interface.
[1363] Submit your request: Once you have completed the entry, submit your request to request an electronic summary of your data.
[1364] Providing emotional data: Emotional data is provided from facial expressions and tone of voice using the device's camera and microphone.
[1365] Viewing the summary: The summary sent from the server is received on the terminal and viewed.
[1366] Specific examples
[1367] For example, consider a case where a user requests a summary of a "science novel" and sets the reading time to "less than 10 minutes," the desired word count to "1,000 characters," and the target demographic to "young people." When the user provides emotional data (e.g., joy) using the device's camera and microphone, the server acquires the electronic data and generates a summary using a generative AI model. Next, the emotion engine performs emotional analysis and adjusts the summary's expression to be more positive. As a result, the server sends a summary that uses a lot of positive language and can be read in less than 10 minutes to the device, and the user can view it.
[1368] Prompt Sentence Examples
[1369] "Generate a summary of the book in 150 characters or less: "Harry Potter and the Philosopher's Stone, this book is...""
[1370] In this way, the system provides summaries tailored to the user's emotional state, enabling an efficient and personalized reading experience.
[1371] The flow of the specific processing in the application example 2 will be described with reference to FIG.
[1372] Step 1:
[1373] The user uses the terminal interface to input the book title, desired reading time, number of characters, generation, etc. The input information is collected by the terminal and sent to the server in the next step.
[1374] Input: Book title, desired reading time, desired number of characters, generation
[1375] Output: Request data sent to the next step
[1376] Step 2:
[1377] The terminal sends the collected user input information to the server, which receives and analyzes this request data.
[1378] Input: User request data
[1379] Output: Analysis result of request data
[1380] Step 3:
[1381] The device's camera and microphone are used to acquire the user's emotional data, which is collected by the device and sent to the server in the next step.
[1382] Input: User's facial expression, tone of voice
[1383] Output: Parsed emotion data
[1384] Step 4:
[1385] The device sends emotional data to the server, which receives and analyzes the data.
[1386] Input: Parsed emotion data
[1387] Output: Analysis results of emotion data
[1388] Step 5:
[1389] The server retrieves the e-book data from the database and sends a prompt to the AI model based on the user's request to generate a summary. The prompt is: "Please generate a summary of the book's contents in 150 characters or less: 'Harry Potter and the Philosopher's Stone, this book is...'"
[1390] Input: e-book data, request data, prompt text
[1391] Output: Generated book summary
[1392] Step 6:
[1393] The server adjusts the generated summary based on sentiment analysis. For example, if the sentiment is positive, it will use more positive expressions.
[1394] Input: Generated summary, analysis results of emotion data
[1395] Output: A sentiment-adjusted summary
[1396] Step 7:
[1397] The server sends the adjusted summary content to the terminal, which displays the received summary to the user.
[1398] Input: Adjusted summary
[1399] Output: A summary that is displayed to the user
[1400] This allows users to receive summaries optimized for their emotional state, resulting in an efficient and personalized reading experience.
[1401] 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.
[1402] 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.
[1403] 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.
[1404] [Fourth embodiment]
[1405] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.
[1406] 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.
[1407] 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).
[1408] 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.
[1409] 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.
[1410] 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).
[1411] 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.
[1412] 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.
[1413] 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.
[1414] 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.
[1415] 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.
[1416] 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.
[1417] 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."
[1418] The present invention is a system that uses a generative AI to provide a summary of a book with permission from the author and publisher. An embodiment of the system will be described below.
[1419] System configuration
[1420] This system is mainly composed of three elements: a server, a terminal, and a user.
[1421] server
[1422] The server plays a central role in this system and has the following functions:
[1423] 1. Electronic data acquisition: Electronic data with permission from the authors and publishers will be acquired from databases.
[1424] 2. Request processing: Receives the request sent from the terminal and analyzes its contents.
[1425] 3. Generative AI summary creation: Generate summaries based on user-specified reading time, word count, and generation.
[1426] 4. Send Abstract: Send the generated abstract to the terminal.
[1427] Terminal
[1428] The terminal is a device where users can enter requests through an interface and view the generated summaries. It has the following features:
[1429] 1. Providing an input interface: Provide a form for users to input reading time, word count, generation, book title, etc.
[1430] 2. Sending the request: Send the input request to the server.
[1431] 3. Display Abstract: The abstract received from the server is displayed to the user.
[1432] User
[1433] The user is the entity that uses this system and performs the following operations:
[1434] 1. Enter information: Enter reading time, word count, generation, and book title.
[1435] 2. Submit your request: Once you've completed the input, submit your request.
[1436] 3. Viewing the summary: The summary sent from the server is viewed on the terminal.
[1437] System operation example
[1438] A specific example of the operation of this system is shown below.
[1439] Example 1: Summary request for "young people" and "less than 10 minutes"
[1440] The user opens the device interface, enters the title of the book they want to read as "A Science Fiction," sets the desired reading time as "10 minutes or less," sets the desired word count as "1,000 characters," and sets the target age group as "Young people." Once they've completed the input, they press the send request button.
[1441] The terminal sends the input information to the server, which receives the request, retrieves the electronic data for "A Certain Science Fiction" from the database, and confirms that the book has been licensed.
[1442] The server passes the acquired digital data to a generation AI that creates a summary based on the user's wishes. The generation AI extracts key episodes and key points and generates a summary that can be read in under 10 minutes, using language appropriate for young people.
[1443] The server formats the generated summary and sends it to the terminal, which displays it on its user interface, allowing the user to read the summary within 10 minutes.
[1444] System convenience
[1445] This system allows users to efficiently understand the main content of a book within a limited time. It also makes difficult content easier to understand by appropriately summarizing it. Therefore, it can be said that this system greatly contributes to users' self-improvement and knowledge improvement.
[1446] The above is a concrete example of how the present invention can be implemented. This system provides flexible summaries tailored to the user's needs, improving reading efficiency and comprehension.
[1447] The processing flow will be explained below.
[1448] Step 1:
[1449] The user opens a summary request form in a device application or website.
[1450] Step 2:
[1451] The user fills out a form with the title of the book or books they want to read, the author's name, the desired reading time, the desired word count, and their generation.
[1452] Step 3:
[1453] The user presses the "Send Request" button to send the input information to the server.
[1454] Step 4:
[1455] The terminal converts the user's input information into an appropriate data format such as JSON and sends it to the server as an HTTP request (e.g., POST request).
[1456] Step 5:
[1457] The server receives the request data sent from the terminal.
[1458] Step 6:
[1459] The server checks the database to see if the specified book or publication has been licensed by the author and publisher.
[1460] Step 7:
[1461] If the permission is confirmed, the server retrieves the electronic data of the specified book from the database. If the permission is not confirmed, the server generates an error message and returns it to the terminal.
[1462] Step 8:
[1463] The server passes the acquired electronic data and the user's requests (desired reading time, number of characters, generation) to the generation AI.
[1464] Step 9:
[1465] The generative AI analyzes the provided electronic data and automatically extracts key points and episodes.
[1466] Step 10:
[1467] The AI then uses the extracted points to generate a summary that fits the specified time and number of characters, adjusting the words and expressions to suit the user's generation.
[1468] Step 11:
[1469] The server converts the summary received from the generation AI into an appropriate format, such as HTML or plain text.
[1470] Step 12:
[1471] The server sends the formatted summary to the terminal as an HTTP response.
[1472] Step 13:
[1473] The terminal receives the summary data sent from the server.
[1474] Step 14:
[1475] The terminal displays the received summary on a user interface.
[1476] Step 15:
[1477] The user views the generated summary on the terminal.
[1478] Example 1
[1479] 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."
[1480] In modern society, there is a huge amount of information and books available, and people are required to understand their content efficiently within a limited time. However, conventional book summarization systems have difficulty providing appropriate summaries that suit the user's desired reading time and age, and there is a lack of means to provide easy-to-understand summaries.
[1481] 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.
[1482] In this invention, the server includes a means for acquiring electronic data, a means for analyzing a request and acquiring electronic data from a database, a means for passing a prompt sentence to a generative AI model and generating a summary, and a means for formatting the generated summary and sending it to a terminal. This makes it possible to efficiently provide appropriate and easy-to-understand summaries according to the user's desired reading time, number of characters, and generation.
[1483] "Electronic data" refers to digital information handled by computers and electronic devices, including the contents of books and documents.
[1484] "User" refers to the primary user who uses the System to input information and receive book summaries.
[1485] A "request" refers to a request from a user to the system for specific processing or information provision.
[1486] "Server" refers to the computer system that plays a central role in this system and performs tasks such as analyzing requests, acquiring data, and running generative AI.
[1487] A "database" refers to a system that organizes and stores electronic data so that it can be efficiently searched when needed.
[1488] A "generative AI model" refers to an artificial intelligence system that generates and summarizes sentences using natural language processing techniques, such as large-scale language models.
[1489] A "prompt" refers to a text instruction entered into a generative AI model to instruct it on how to proceed.
[1490] A "summary" is a document that presents the main content of an original book or document in an abbreviated form.
[1491] "Terminal" refers to a device, such as a computer or smartphone, that a user uses to access the system, enter information, and view generated summaries.
[1492] "Formatting" refers to the process of adjusting the format and content of the generated summary to make it easier to read.
[1493] MODE FOR CARRYING OUT THE INVENTION
[1494] This invention is a system that uses a generative AI model to provide book summaries with permission from authors and publishers. This system mainly consists of three elements: a server, a terminal, and a user.
[1495] server
[1496] The server plays a central role in this system and has the following functions:
[1497] 1. Electronic Data Acquisition:
[1498] The server retrieves electronic data from the database with permission from the authors and publishers, specifically using a database management system such as SQL Server.
[1499] 2. Processing the request:
[1500] The server receives the request sent from the terminal and analyzes its contents. Web frameworks such as Flask and Django are used to process HTTP requests.
[1501] 3. Generative AI model for summarization:
[1502] The server uses a generative AI model (e.g., OpenAI's GPT model) to generate a summary based on the user's specified reading time, number of characters, and generation. In this process, it generates a prompt sentence and passes it to the AI.
[1503] 4. Submit your abstract:
[1504] The server formats the generated summary and sends it to the device. It uses a standard API endpoint to send it as JSON data.
[1505] Terminal
[1506] The terminal is a device where users can enter requests through an interface and view the generated summaries. It has the following features:
[1507] 1. Providing an input interface:
[1508] The terminal provides a form for users to input reading time, word count, generation, book title, etc. The interface is built using front-end frameworks such as React and Vue.js.
[1509] 2. Submit your request:
[1510] The device sends the input request to the server. It uses AJAX or Fetch API to send an HTTP request to the server.
[1511] 3. View Summary:
[1512] The device receives the summary from the server and displays it to the user in an easy-to-read format using style frameworks such as CSS and Bootstrap.
[1513] User
[1514] The user is the entity that uses this system and performs the following operations:
[1515] 1. Enter your information:
[1516] The user inputs the title, reading time, number of characters, and generation into a form on the terminal.
[1517] 2. Submit your request:
[1518] Once you have completed the input, click the Send Request button.
[1519] 3. View Abstract:
[1520] The summary sent from the server is viewed on the terminal.
[1521] Specific examples
[1522] A specific example of the operation of this system is shown below.
[1523] Example 1: Summary request for young people in under 10 minutes
[1524] The user opens the device interface, enters the title of the book they want to read as "A Science Fiction," sets the desired reading time as "10 minutes or less," sets the desired word count as "1,000 characters," and sets the target age group as "Young people." Once they've completed the input, they press the send request button.
[1525] The device converts the input information into JSON format and sends an HTTP POST request to the server.
[1526] The server receives the request, analyzes it, retrieves the digital copy of "A Certain Science Fiction Book" from the database, verifies that the book is licensed, and then passes the following prompt to the generative AI model:
[1527] "Please summarize the book "A Certain Science Fiction" in 1000 words or less for a young reader so that it can be read in under 10 minutes."
[1528] The generative AI model generates a summary and returns it to the server, which formats the summary and sends it to the device, which displays it on the user interface, allowing the user to read the summary in under 10 minutes.
[1529] The above is a specific embodiment of the present invention. This system provides flexible summaries tailored to the user's needs, improving reading efficiency and comprehension.
[1530] The flow of the identification process in the first embodiment will be described with reference to FIG.
[1531] Step 1:
[1532] The user uses the device interface to enter information such as reading time, desired word count, generation, book title, etc. The entered data is formatted in JSON format as shown in the example below.
[1533] json
[1534] {
[1535] "title": "A Science Fiction",
[1536] "reading_time": "within 10 minutes",
[1537] "character_count": "1000",
[1538] "generation": "young people"
[1539] }
[1540] (Input: Specified input from the user)
[1541] (Output: Request data in JSON format)
[1542] Step 2:
[1543] The device generates an HTTP POST request based on the input information and sends it to the server. This request includes all the information the user entered.
[1544] (Input: User input data)
[1545] (Output: HTTP POST request to server)
[1546] Step 3:
[1547] The server analyzes the received request and retrieves the digital data for "A Certain Science Fiction" from the database using an SQL query to verify that the data obtained is authorized.
[1548] (Input: HTTP POST request)
[1549] (Output: Electronic data retrieved from the database)
[1550] Step 4:
[1551] The server passes a prompt sentence to the generative AI model based on the acquired electronic data. This prompt sentence is formatted as follows:
[1552] "Please summarize the book "A Certain Science Fiction" in 1000 words or less for a young reader so that it can be read in under 10 minutes."
[1553] A generative AI model takes this prompt and generates a summary.
[1554] (Input: prompt text, electronic data)
[1555] (Output: Generated summary)
[1556] Step 5:
[1557] The server formats the generated summary and sends it to the device in JSON format, which is easy for the user to view.
[1558] (Input: Generated summary)
[1559] (Output: Summary data in JSON format to terminal)
[1560] Step 6:
[1561] The terminal analyzes the summary data received from the server and displays it on a user interface, which the user can view.
[1562] (Input: Summary data received from the server)
[1563] (Output: Summary displayed in the user interface)
[1564] (Application example 1)
[1565] 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."
[1566] In today's world, busy lifestyles mean limited time for reading, and people are required to efficiently understand the main content of a book in a short amount of time. There are also limited ways for individual users to enjoy books in a format appropriate for their generation and interests. Furthermore, there is a lack of platforms for discussing book summaries, making it difficult to share reading experiences.
[1567] 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.
[1568] In this invention, the server includes means for acquiring electronic data, means for users to input reading time, desired number of characters, and generation, means for generating summaries using a generative AI model, means for creating different summaries according to the reading time, number of characters, and generation specified by the user, and means for displaying the created summaries to users and providing a discussion function. This enables users to read efficiently according to their individual needs within a limited time, and also stimulates sharing of reading experiences and discussions.
[1569] "Electronic data" means information stored in digital form, including the entire text of a book or portions thereof.
[1570] A "generative AI model" is an algorithm that uses artificial intelligence technology to analyze input text and generate a summary.
[1571] "Reading time" is the amount of time a user plans to spend reading a particular book or summary thereof.
[1572] "Number of characters" means the total number of characters in the summary to be generated.
[1573] "Generation" refers to user groups based on geographic or cultural age, with different language and expressions being tailored to each generation.
[1574] A "user" is an entity that uses this system to obtain and view book summaries.
[1575] "Server" means a computing device that retrieves electronic data, receives requests, creates summaries using generative AI models, and transmits the summaries.
[1576] The "discussion function" is an interface that allows users to exchange opinions and discuss the contents of a book based on the generated summary.
[1577] An "input interface" is a user interface that provides a means for a user to input reading time, number of characters, generation, and book title.
[1578] This invention is a system that uses a generative AI model to provide authorized book summaries. The system is mainly composed of three elements: a server, a terminal, and a user.
[1579] server
[1580] The server plays a central role in this system and has the following functions:
[1581] 1. Acquisition of electronic data: Electronic data with permission from the copyright holder is acquired from the database.
[1582] 2. Request processing: Receives the request sent from the terminal and analyzes its contents.
[1583] 3. Generative AI model creates a summary: A summary is generated based on the user's specified reading time, word count, and generation. The generative AI model analyzes the text and creates a summary.
[1584] 4. Send Abstract: Send the generated abstract to the terminal.
[1585] 5. Providing a discussion function: Provide an interface for users to exchange opinions and hold discussions based on the summary content.
[1586] The hardware used is a general-purpose server computer, and the software used is Flask (a Python microframework) and the Requests library for HTTP requests.
[1587] Terminal
[1588] The terminal is a device through which a user can enter requests and view the generated summaries via an interface. This device includes the following features:
[1589] 1. Providing an input interface: Provide a form for users to input reading time, word count, generation, book title, etc.
[1590] 2. Sending the request: Send the input request to the server.
[1591] 3. Display Abstract: The abstract received from the server is displayed to the user.
[1592] 4. Providing a discussion function: A chat function is provided for users to exchange opinions about the summary content.
[1593] User
[1594] The user is the entity that uses this system and performs the following operations:
[1595] 1. Enter information: Enter reading time, word count, generation, and book title.
[1596] 2. Submit your request: Once you've completed the input, submit your request.
[1597] 3. Viewing the summary: The summary sent from the server is viewed on the terminal.
[1598] 4. Discussion of the summary: Exchange opinions and discuss the summary with other users.
[1599] System operation example
[1600] A specific example of the operation of this system is shown below.
[1601] Example 1: Summary request for "young people" and "under 15 minutes"
[1602] The user opens the device interface, inputs the title of the book they want to read, sets the desired reading time to "15 minutes or less," the desired number of characters to "1500 characters," and sets the target age group to "young people." Once they have completed the input, they press the send request button.
[1603] The terminal sends the input information to the server, which receives the request, retrieves the electronic data of the book from the database, and confirms that the book has been licensed.
[1604] The server passes the acquired digital data to a generative AI model, which then creates a summary based on the user's preferences. The generative AI model extracts key episodes and key points and generates a summary that can be read in under 15 minutes, using language appropriate for younger readers.
[1605] The generated summary is formatted on the server and sent to the terminal, which displays the received summary on the user interface and allows the user to read the summary within a specified time.
[1606] Furthermore, users can use the chat function to hold discussions with other users who are reading the same summary. Through the interface provided by the discussion function, users can exchange opinions and discuss the summarized content to deepen their understanding.
[1607] Example prompts for generative AI models
[1608] "Below is the full text of 'XXX (book title)' with permission from the copyright holder. Please generate a 1500-character summary of this book aimed at young people that can be read in under 15 minutes."
[1609] The above is an embodiment of the present invention. This system allows users to efficiently understand the main content of a book within a limited time, and also allows users to exchange opinions about the content of the summary with other users.
[1610] The flow of the specific processing in the application example 1 will be described with reference to FIG.
[1611] Step 1:
[1612] The user uses the device's interface to input the reading time, desired number of characters, generation, and book title. For example, the user might input "less than 15 minutes," "1500 characters," "for young people," and "XXX (book title)." The input data is temporarily saved on the device. At this point, the input is the reading time, desired number of characters, generation, and book title.
[1613] Step 2:
[1614] The device sends the input information to the server. At this stage, the request includes the previously input data (reading time, desired word count, generation, and book title). The server receives this request data and begins analyzing it.
[1615] Step 3:
[1616] The server retrieves the electronic data of the specified book from the database. When retrieving the electronic data, the server searches for and retrieves the electronic data of the relevant book based on the input book title. This electronic data is used in the next process.
[1617] Step 4:
[1618] The server verifies that the digital data retrieved from the database has been authorized by the copyright holder. If authorization is successful, the digital data is passed to the generative AI model. Authorization authorization includes checking license information.
[1619] Step 5:
[1620] The server generates and passes a prompt to the generative AI model based on the user-specified reading time, desired number of characters, and generation. An example of a prompt is, "Below is the full text of 'XXX (book title)' with permission from the copyright holder. Please generate a 1500-character summary of this book aimed at young people that can be read in 15 minutes or less."
[1621] Step 6:
[1622] The server uses a generative AI model, such as GPT-3, to generate a summary based on the prompt. The generated summary is optimized to meet the user-specified criteria (less than 15 minutes, 1500 characters, and aimed at young people). The generated summary is in text format.
[1623] Step 7:
[1624] The server then formats the generated summary to make it easier for the user to read, for example by dividing it into paragraphs and highlighting important points, and the formatted summary is then ready to be sent to the device as text data.
[1625] Step 8:
[1626] The server sends the formatted summary to the terminal, which displays the received summary on its user interface.
[1627] Step 9:
[1628] The device displays the received summary to the user, who has 15 minutes to finish reading it. The device also has a discussion function that allows users to exchange opinions and discuss the summary with other users.
[1629] The above is a description of the process flow of the program of the system that realizes the application example, broken down into specific steps.
[1630] 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.
[1631] The present invention is a system that uses generative AI to provide book summaries with permission from authors and publishers, and further combines it with an emotion engine that recognizes user emotions. An embodiment of the system will be described below.
[1632] System configuration
[1633] This system is mainly composed of three elements: a server, a terminal, and a user. In addition, it has the function of recognizing the user's emotions using an emotion engine and adjusting the summary content based on those emotions.
[1634] server
[1635] The server plays a central role in this system and has the following functions:
[1636] 1. Electronic data acquisition: Electronic data with permission from the authors and publishers will be acquired from databases.
[1637] 2. Request processing: Receives the request sent from the terminal and analyzes its contents.
[1638] 3. Generative AI summary creation: Generate summaries based on user-specified reading time, word count, and generation.
[1639] 4. Emotion analysis using an emotion engine: Recognizes the user's emotions and adjusts the content and expression of the summary based on the analysis results.
[1640] 5. Send Abstract: Send the generated abstract to the terminal.
[1641] Terminal
[1642] The terminal is a device where users can enter requests through an interface and view the generated summaries. It has the following features:
[1643] 1. Providing an input interface: Provide a form for users to input reading time, word count, generation, book title, etc.
[1644] 2. Sending the request: Send the input request to the server.
[1645] 3. Acquiring emotional data: Acquire emotional data using the user's facial expressions and tone of voice.
[1646] 4. Display Abstract: The abstract received from the server is displayed to the user.
[1647] User
[1648] The user is the entity that uses this system and performs the following operations:
[1649] 1. Enter information: Enter reading time, word count, generation, and book title.
[1650] 2. Submit your request: Once you've completed the input, submit your request.
[1651] 3. Providing emotional data: Emotional data is provided using the device's camera or microphone.
[1652] 4. Viewing the summary: The summary sent from the server is viewed on the terminal.
[1653] System operation example
[1654] A specific example of the operation of this system is shown below.
[1655] Example 1: Summary request based on "young people", "under 10 minutes", and "positive sentiment"
[1656] The user opens the device's interface, enters the title of the book they want to read as "A Science Fiction," sets the desired reading time as "10 minutes or less," the desired number of characters as "1,000 characters," and sets the target age group as "Young people." In addition, the device's camera and microphone are used to provide facial expressions and tone of voice to the emotion engine.
[1657] The device sends the input information and emotion data to the server. The server receives the request, retrieves the digital data for "A Certain Science Fiction" from the database, and confirms that the book has been licensed.
[1658] The server passes the acquired digital data to a generation AI that creates a summary based on the user's wishes. The generation AI extracts key episodes and key points and generates a summary that can be read in under 10 minutes, using language appropriate for young people.
[1659] Furthermore, the emotion engine analyzes the user's emotional data and adjusts the content and expressions of the summary to match positive emotions, for example by using more energetic and positive expressions.
[1660] The server formats the generated summary and sends it to the terminal, which displays it on its user interface, allowing the user to read the summary within 10 minutes.
[1661] System convenience
[1662] This system allows users to efficiently understand the main content of a book within a limited time frame. Furthermore, by adjusting the summary based on the user's emotions, it provides a more personalized and easy-to-read summary. This improves the user's reading experience and contributes greatly to self-improvement and knowledge growth.
[1663] The above is a concrete example of how the present invention can be implemented. This system provides flexible summaries tailored to the user's needs and emotions, improving reading efficiency and comprehension.
[1664] The processing flow will be explained below.
[1665] Step 1:
[1666] The user opens a summary request form in a device application or website.
[1667] Step 2:
[1668] The user fills out a form with the title of the book or books they want to read, the author's name, the desired reading time, the desired word count, and their generation.
[1669] Step 3:
[1670] The user presses the "Send Request" button to send the input information to the server.
[1671] Step 4:
[1672] The terminal converts the user's input information into an appropriate data format, such as JSON, and sends it to the server as an HTTP request.
[1673] Step 5:
[1674] The device captures emotional data by detecting the user's facial expressions and tone of voice, and this information is collected in real time via a camera and microphone.
[1675] Step 6:
[1676] The device analyzes the emotion data and sends the results to the server.
[1677] Step 7:
[1678] The server receives the request data and emotion data sent from the terminal.
[1679] Step 8:
[1680] The server checks the database to see if the specified book or publication has been licensed by the author and publisher.
[1681] Step 9:
[1682] If the permission is confirmed, the server retrieves the electronic data of the specified book from the database. If the permission is not confirmed, the server generates an error message and returns it to the terminal.
[1683] Step 10:
[1684] The server passes the acquired electronic data and the user's requests (desired reading time, number of characters, generation) to the generation AI.
[1685] Step 11:
[1686] The generative AI analyzes the provided electronic data and automatically extracts key points and episodes.
[1687] Step 12:
[1688] The AI then uses the extracted points to generate a summary that fits the specified time and number of characters, adjusting the words and expressions to suit the user's generation.
[1689] Step 13:
[1690] The emotion engine analyzes the received emotion data and adjusts the content and expression of the summary based on the user's emotion. For example, if the user is expressing positive emotions, it will use more energetic expressions that reflect that emotion.
[1691] Step 14:
[1692] The server converts the summaries received from the generative AI and emotion engine into an appropriate format, such as HTML or plain text.
[1693] Step 15:
[1694] The server sends the formatted summary to the terminal as an HTTP response.
[1695] Step 16:
[1696] The terminal receives the summary data sent from the server.
[1697] Step 17:
[1698] The terminal displays the received summary on a user interface.
[1699] Step 18:
[1700] The user views the generated summary on the terminal.
[1701] Example 2
[1702] 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."
[1703] Conventional book summarization services can generate summaries based on given conditions, but they have difficulty providing flexible summaries that match the user's emotions. Furthermore, they are limited in their ability to adjust the optimal reading time and word count for each user, or the expression to suit the target generation. This makes it difficult to provide personalized summaries, and has led to problems in improving user satisfaction.
[1704] 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.
[1705] In this invention, the server includes means for acquiring electronic data, means for the user to input the reading time, desired number of characters, and generation, means for analyzing the input information, means for creating a summary based on the acquired electronic data and a generation AI model, means for analyzing the user's emotion data after generating the summary and adjusting the summary content based on the emotion, and means for displaying the created summary to the user. This makes it possible to provide a personalized summary based on the user's reading conditions and emotions, thereby improving the user's reading experience.
[1706] "Electronic data" refers to information such as books and documents expressed in digital form.
[1707] "User" means a person who operates and uses this system.
[1708] "Reading time" refers to the time required to read and understand a book summary designated by the user.
[1709] "Desired word count" refers to the number of words the user specifies the book summary should contain.
[1710] "Generation" refers to a particular age group or social group to which a user belongs.
[1711] "Input means" refers to an interface that allows users to input conditions and data into the system.
[1712] "Means of analysis" refers to the function of interpreting input data and conditions and performing the processing necessary for the system to operate properly.
[1713] A "generative AI model" is an algorithm that uses artificial intelligence and is a technology that automatically generates summaries of sentences or documents based on specific conditions.
[1714] A "summary" is a concise summary of the main information or points of a book or document.
[1715] "Emotional data" refers to information about emotions obtained from the user's facial expressions, tone of voice, etc.
[1716] "Adjustment means" refers to the function of changing the content and expression to the optimum based on the analysis results.
[1717] The "display means" refers to an interface for visually conveying the generated summary to the user.
[1718] This invention is a system that uses generative AI to provide book summaries with permission from authors and publishers, and also combines it with an emotion engine that recognizes the user's emotions. The system is mainly composed of three elements: a server, a terminal, and a user. The roles and operations of each are described in detail below.
[1719] server
[1720] The server is a hardware and software component that is responsible for the central operation of the entire system. Specifically, it has the following functions:
[1721] 1. Acquisition of electronic data
[1722] The server retrieves electronic data of books licensed by authors and publishers from a database, for example, by using a database management system (DBMS) to quickly search and retrieve the electronic data.
[1723] 2. Processing the Request
[1724] It receives user requests sent from the device and analyzes their contents, including input parameters (book title, reading time, number of characters, generation, etc.).
[1725] 3. Generative AI-powered summaries
[1726] The acquired digital data is input into a generative AI model, which generates a summary based on the user's specified conditions (reading time, number of characters, generation, etc.). For example, a generative AI that applies natural language processing (NLP) technology is used.
[1727] 4. Emotion analysis using an emotion engine
[1728] The technology analyzes the user's emotional data (facial expressions and tone of voice) and adjusts the summary content based on the results. Emotion recognition technology uses machine learning algorithms.
[1729] 5. Submit your summary
[1730] The generated and adjusted summary is sent to the terminal.
[1731] For example, to generate a summary of a science fiction novel for "younger adults" that can be read in under 10 minutes, the prompt would be:
[1732] Generate a summary of a science fiction novel, aimed at young people, that can be read in under 10 minutes, and is up to 1000 characters long.
[1733] Terminal
[1734] A terminal is a device that provides an interface for users to use the system. Its specific functions are as follows:
[1735] 1. Providing an input interface
[1736] Provide a form for users to enter their reading criteria (reading time, word count, generation, book title), for example, using a web browser or mobile application.
[1737] 2. Submitting a Request
[1738] The entered conditions are sent to the server using HTTP or another data communication protocol.
[1739] 3. Acquiring Emotion Data
[1740] The user's facial expressions and tone of voice are captured through a camera and microphone and sent to the emotion engine.
[1741] 4. Viewing the Summary
[1742] The summary received from the server is displayed on the screen, using HTML and mobile app UI as the interface.
[1743] User
[1744] The user is the entity that uses this system to obtain a book summary, and performs the following operations:
[1745] 1. Enter your information
[1746] Enter your reading criteria into the device interface, for example, "Science fiction," "Less than 10 minutes," "1,000 characters," and "For young people."
[1747] 2. Submitting a Request
[1748] Click the request button to send the input information to the server.
[1749] 3. Providing Emotion Data
[1750] It uses the device's camera and microphone to provide emotional data, such as a smile or a calm tone of voice.
[1751] 4. Viewing the Abstract
[1752] The summary sent from the server is viewed on the terminal screen and the content is understood based on the specified conditions.
[1753] As described above, the present invention is a system that provides an efficient reading experience by providing flexible and personalized book summaries based on the user's reading conditions and emotions.
[1754] The flow of the identification process in the second embodiment will be described with reference to FIG.
[1755] System program processing flow
[1756] Step 1: Entering the User Interface
[1757] The terminal is the main player. Here's what it does:
[1758] Input: The user enters information into an input form, including the book title, reading time, desired word count, and generation.
[1759] Data processing: The terminal converts the input information into request data.
[1760] Output: The request data is prepared.
[1761] Step 2: Submitting the request
[1762] The terminal is the main player. Here's what it does:
[1763] Input: The request data prepared in step 1.
[1764] Data operation: Converts the request data into an HTTP request format.
[1765] Output: Sends the request data to the server.
[1766] Step 3: Receiving and Parsing the Request
[1767] The server is the main player. Here's what it does:
[1768] Input: The request data sent from the device.
[1769] Data calculation: Analyze the request data and extract the title, reading time, desired number of characters, and generation.
[1770] Output: Parsed condition data.
[1771] Step 4: Get the data
[1772] The server is the main player. Here's what it does:
[1773] Input: The condition data extracted in step 3.
[1774] Data processing: Search and retrieve the corresponding electronic data from the database.
[1775] Output: The electronic data obtained.
[1776] Step 5: Generative AI creates a summary
[1777] The server is the main player. Here's what it does:
[1778] Input: The electronic data obtained and the user's conditions.
[1779] Data Computation: Input data into a generative AI model to generate summaries based on reading time, desired word count, and generation.
[1780] Output: The generated summary data.
[1781] Specific prompt examples:
[1782] Generate a summary of a science fiction novel, aimed at young people, that can be read in under 10 minutes, and is up to 1000 characters long.
[1783] Step 6: Sentiment analysis and summary adjustment
[1784] The server is the main player. Here's what it does:
[1785] Input: Generated summary data and user emotion data.
[1786] Data calculation: Emotional data is input into the emotion engine, and the summary content is adjusted based on the analysis results.
[1787] Output: Adjusted summary data.
[1788] Step 7: Send and view the summary
[1789] The server and the device are the main players in the collaboration. The specific operations are as follows:
[1790] Input: Adjusted summary data.
[1791] Data calculation: The server formats the summary data for transmission to the terminal.
[1792] Output: Summary data sent to the terminal.
[1793] Next, the terminal takes center stage. Here's what it does:
[1794] Input: Abstract data sent by the server.
[1795] Data processing: Converts the received summary data into a format that is displayed on the user interface.
[1796] Output: The summary data is displayed on the terminal screen and provided to the user.
[1797] This is the specific program processing flow of this system. At each processing step, the necessary data processing and calculations are performed based on the input data, and the results are passed on to the next processing step to provide a flexible and personalized book summary.
[1798] (Application example 2)
[1799] 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."
[1800] Conventional summary systems are unable to consider the user's emotions and state, making it difficult to provide a personalized reading experience. Furthermore, the summaries generated are uniform, making it impossible to provide content optimized for the user's emotions. Therefore, in order to improve the user's reading experience, it is necessary to provide summaries tailored to each individual's emotional state.
[1801] 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.
[1802] In this invention, the server includes means for acquiring electronic data, means for the user to input reading time, desired number of characters, and generation, means for generating, means for creating a summary, means for acquiring emotional data, means for adjusting the summary based on emotional analysis, and means for displaying the created summary to the user, thereby making it possible to provide a summary optimized for the emotional state of the user.
[1803] "Electronic data" refers to information that expresses the contents of a book in digital form and is available on a server.
[1804] "Means of acquisition" refers to the server's ability to download electronic data from authors and publishers.
[1805] "Means for input" refers to a system in which the user inputs parameters such as the desired reading time, number of characters, and generation into the terminal.
[1806] "Means of generation" refers to the function of using generative AI to create a book summary based on information entered by the user.
[1807] "Means for creating summaries" refers to the function of summarizing the main contents of a book so that they can be understood in a short amount of time.
[1808] "Means for acquiring emotional data" refers to a system that analyzes the user's facial expressions and tone of voice to detect emotions.
[1809] "Means for adjusting the summary based on emotion analysis" refers to a function for changing the content and expression of the summary based on the acquired emotion data of the user.
[1810] "Displaying means" refers to a system that displays the created summary on the user's terminal.
[1811] This invention is a system for providing a book summary optimized for a user's emotional state, and specifically consists of three elements: a server, a terminal, and a user. Specific embodiments of this system are described below.
[1812] server
[1813] The server plays a central role in this system and has the following functions:
[1814] Acquisition of electronic data: A function to acquire electronic data of books with permission from authors and publishers. Specifically, the server downloads electronic book data from the database.
[1815] Request processing: Analyzes the user's request sent from the device and uses a generative AI model to create a book summary based on the user's specified reading time, word count, and generation.
[1816] Sentiment Analysis: Analyzes the user's emotional data and adjusts the summary content. This function uses an emotion engine to analyze the user's facial expressions, tone of voice, etc.
[1817] Terminal
[1818] A terminal is a device that provides an interface for users to operate the system. Specifically, it has the following functions:
[1819] Providing an input interface: Provide a form for users to input reading time, word count, generation, book title, etc.
[1820] Acquiring emotional data: Acquires the user's emotional data using the device's camera and microphone. Detects the user's emotional state by analyzing facial expressions and voice using OpenCV.
[1821] Displaying the summary: The summary sent from the server is displayed to the user. The generated summary is adjusted based on sentiment analysis, so it is the most appropriate content for the user.
[1822] User
[1823] The user is the entity that uses this system and performs the following operations:
[1824] Enter information: Enter reading time, word count, generation, book title, etc. using the device interface.
[1825] Submit your request: Once you have completed the entry, submit your request to request an electronic summary of your data.
[1826] Providing emotional data: Emotional data is provided from facial expressions and tone of voice using the device's camera and microphone.
[1827] Viewing the summary: The summary sent from the server is received on the terminal and viewed.
[1828] Specific examples
[1829] For example, consider a case where a user requests a summary of a "science novel" and sets the reading time to "less than 10 minutes," the desired word count to "1,000 characters," and the target demographic to "young people." When the user provides emotional data (e.g., joy) using the device's camera and microphone, the server acquires the electronic data and generates a summary using a generative AI model. Next, the emotion engine performs emotional analysis and adjusts the summary's expression to be more positive. As a result, the server sends a summary that uses a lot of positive language and can be read in less than 10 minutes to the device, and the user can view it.
[1830] Prompt Sentence Examples
[1831] "Generate a summary of the book in 150 characters or less: "Harry Potter and the Philosopher's Stone, this book is...""
[1832] In this way, the system provides summaries tailored to the user's emotional state, enabling an efficient and personalized reading experience.
[1833] The flow of the specific processing in the application example 2 will be described with reference to FIG.
[1834] Step 1:
[1835] The user uses the terminal interface to input the book title, desired reading time, number of characters, generation, etc. The input information is collected by the terminal and sent to the server in the next step.
[1836] Input: Book title, desired reading time, desired number of characters, generation
[1837] Output: Request data sent to the next step
[1838] Step 2:
[1839] The terminal sends the collected user input information to the server, which receives and analyzes this request data.
[1840] Input: User request data
[1841] Output: Analysis result of request data
[1842] Step 3:
[1843] The device's camera and microphone are used to acquire the user's emotional data, which is collected by the device and sent to the server in the next step.
[1844] Input: User's facial expression, tone of voice
[1845] Output: Parsed emotion data
[1846] Step 4:
[1847] The device sends emotional data to the server, which receives and analyzes the data.
[1848] Input: Parsed emotion data
[1849] Output: Analysis results of emotion data
[1850] Step 5:
[1851] The server retrieves the e-book data from the database and sends a prompt to the AI model based on the user's request to generate a summary. The prompt is: "Please generate a summary of the book's contents in 150 characters or less: 'Harry Potter and the Philosopher's Stone, this book is...'"
[1852] Input: e-book data, request data, prompt text
[1853] Output: Generated book summary
[1854] Step 6:
[1855] The server adjusts the generated summary based on sentiment analysis. For example, if the sentiment is positive, it will use more positive expressions.
[1856] Input: Generated summary, analysis results of emotion data
[1857] Output: A sentiment-adjusted summary
[1858] Step 7:
[1859] The server sends the adjusted summary content to the terminal, which displays the received summary to the user.
[1860] Input: Adjusted summary
[1861] Output: A summary that is displayed to the user
[1862] This allows users to receive summaries optimized for their emotional state, resulting in an efficient and personalized reading experience.
[1863] 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.
[1864] 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.
[1865] 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.
[1866] 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.
[1867] 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.
[1868] 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.
[1869] 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).
[1870] 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.
[1871] 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."
[1872] 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.
[1873] 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).
[1874] 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.
[1875] 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.
[1876] 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.
[1877] 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.
[1878] 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.
[1879] 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.
[1880] 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.
[1881] 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.
[1882] 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.
[1883] 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.
[1884] The following is further disclosed regarding the above embodiment.
[1885] (Claim 1)
[1886] a means for obtaining electronic data;
[1887] A means for users to input reading time, desired number of characters, and generation;
[1888] a generating means;
[1889] a means for generating a summary;
[1890] means for displaying the generated summary to a user;
[1891] A system including:
[1892] (Claim 2)
[1893] 10. The system of claim 1, further comprising means for verifying that the electronic data has been licensed by the author and publisher.
[1894] (Claim 3)
[1895] 2. The system according to claim 1, wherein the generating means has means for adjusting words and expressions according to the generation of the user.
[1896] "Example 1"
[1897] (Claim 1)
[1898] a means for obtaining electronic data;
[1899] A means for users to input reading time, desired number of characters, and generation;
[1900] a means for sending a request to a server;
[1901] means for parsing the request at the server and retrieving the electronic data from the database;
[1902] A means for passing prompts to a generative AI model to generate summaries; and
[1903] means for formatting the generated summary and transmitting it to a terminal;
[1904] means for displaying the received summary;
[1905] A system including:
[1906] (Claim 2)
[1907] 10. The system of claim 1, further comprising means for verifying that the electronic data has been licensed by the author and publisher.
[1908] (Claim 3)
[1909] 2. The system according to claim 1, wherein the generating means has means for adjusting words and expressions according to the generation of the user.
[1910] "Application Example 1"
[1911] (Claim 1)
[1912] a means for obtaining electronic data;
[1913] A means for users to input reading time, desired number of characters, and generation;
[1914] a means for generating a summary using a generative AI model;
[1915] A means to create different summaries depending on the user's specified reading time, number of characters, and generation, and
[1916] a means for displaying the generated summary to the user and providing further discussion capabilities;
[1917] A system including:
[1918] (Claim 2)
[1919] 10. The system of claim 1, further comprising means for verifying that the electronic data is licensed by the copyright holder.
[1920] (Claim 3)
[1921] The system of claim 1, further comprising means for adjusting words and expressions according to the user's generation using a generative AI model.
[1922] "Example 2: Combining Emotion Engines"
[1923] (Claim 1)
[1924] a means for obtaining electronic data;
[1925] A means for users to input reading time, desired number of characters, and generation;
[1926] means for analyzing input information;
[1927] a means for generating a summary of the acquired electronic data based on a generative AI model;
[1928] means for analyzing the user's emotion data after generating the summary and adjusting the summary content based on the emotion;
[1929] means for displaying the generated summary to a user;
[1930] A system including:
[1931] (Claim 2)
[1932] 10. The system of claim 1, further comprising means for verifying that the electronic data has been licensed by the author and publisher.
[1933] (Claim 3)
[1934] The system of claim 1, further comprising means for generating a summary based on conditions (such as reading time, number of characters, generation, etc.) input to the generative AI model.
[1935] "Application example 2 when combining emotion engines"
[1936] (Claim 1)
[1937] a means for obtaining electronic data;
[1938] A means for users to input reading time, desired number of characters, and generation;
[1939] a generating means;
[1940] a means for generating a summary;
[1941] A means for acquiring emotion data;
[1942] means for tailoring the summary based on sentiment analysis;
[1943] means for displaying the generated summary to a user;
[1944] A system including:
[1945] (Claim 2)
[1946] 10. The system of claim 1, further comprising means for verifying that the electronic data has been licensed by the author and publisher.
[1947] (Claim 3)
[1948] 2. The system according to claim 1, wherein the generating means comprises means for adjusting words and expressions according to the generation of the user, and further means for adjusting the summary content based on sentiment analysis. [Explanation of symbols]
[1949] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>
Claims
1. a means for obtaining electronic data; A means for users to input reading time, desired number of characters, and generation; a generating means; a means for generating a summary; means for displaying the generated summary to a user; A system including:
2. 10. The system of claim 1, further comprising means for verifying that the electronic data has been licensed by the author and publisher.
3. 2. The system according to claim 1, wherein the generating means has means for adjusting words and expressions according to the generation of the user.
Citation Information
Patent Citations
Persona chatbot control method and system
JP2022180282A