System

Abstract

A system is provided.SOLUTION: A system, comprising: means for generating a summary from a tokenized document using a generative AI model; means for organizing the summarized content into a catalog format; means for receiving a selection of a document from a user; means for presenting the summary and a checklist of the selected document; means for receiving a record of a practice by the user; means for analyzing the practice and generating feedback; and means for presenting the generated feedback to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Traditional self-improvement methods require users to purchase a self-improvement book, understand its contents, and decide what they should put into practice. This process takes a lot of time and effort, and users may not be able to fully understand all of the content, making it difficult to achieve efficient self-improvement. Another issue is that self-improvement books often do not provide specific action plans for applying the contents of the book to daily practice, making it difficult to continue practicing. [Means for solving the problem]

[0005] The present invention employs the following means to provide a system that summarizes self-help books and efficiently supports self-development. It provides a means for acquiring self-help book data and a means for tokenizing and cleaning the acquired data. It also provides a means for generating summaries from the tokenized data using a generative AI model and a means for organizing the summarized content in a catalog format. It also incorporates a means for a user to select a self-help book and a means for presenting summaries and checklists for the selected self-help book. By adding a means for receiving a record of the user's practice and a means for analyzing the practice status and generating feedback, a system is realized that includes a means for presenting the generated feedback to the user. This significantly improves the efficiency of self-development.

[0006] A "self-help book" is a book that provides advice and methodologies for personal growth and skill development.

[0007] "Self-help book data" refers to data that digitally represents the text information and content contained in a self-help book.

[0008] "Tokenization" is the process of dividing text data into the smallest meaningful units (tokens).

[0009] "Cleaning" is the process of removing or modifying unnecessary parts of data and preparing it in a form suitable for analysis and processing.

[0010] A "generative AI model" is an algorithm or system that uses artificial intelligence technology to generate new text from text data.

[0011] A "summary" is a sentence that extracts the main content of a text and expresses it concisely.

[0012] A "catalog format" is a format in which multiple items are organized and presented in the form of a list.

[0013] A "checklist" is a list of items to check off specific tasks or actions.

[0014] "Practical matters" are specific actions that users should take based on the contents of the self-help book.

[0015] The "diary format" is a format in which daily events and practical results are recorded in chronological order.

[0016] "Feedback" is a response that evaluates the current state of practice and indicates areas for improvement. [Brief explanation of the drawings]

[0017] [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

[0018] 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.

[0019] First, the terms used in the following description will be explained.

[0020] 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).

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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."

[0038] The present invention relates to a self-development efficiency improvement system using a generative AI model. This system is implemented as follows.

[0039] Overall system operation

[0040] 1. Acquisition and preprocessing of book data

[0041] The server retrieves data on self-help books from an e-book platform, which mainly contains text information.

[0042] The server tokenizes and cleans the data it receives, removing unnecessary tags and line breaks and splitting sentences into tokens using a natural language processing library.

[0043] 2. Summary generation using generative AI models

[0044] The server uses a generative AI model to summarize the content from the tokenized book data, such as a GPT-based natural language generation model.

[0045] The summarized text is saved in storage for later processing.

[0046] 3. Cataloging Abstracts

[0047] The server organizes the summarized self-help books into a catalog, where each summary is stored in JSON format, including the book's title, author, main points, etc.

[0048] 4. Extraction of practical matters and generation of checklists

[0049] The server extracts concrete actionable information from the summaries, which involves natural language processing to extract verbs and key actions from the book summaries.

[0050] Based on the extracted practices, the server generates a checklist that includes daily tasks and action items.

[0051] 5. User Interaction

[0052] Users can browse a catalog of self-help books through a dedicated application, check the summaries and effects of each book, and select the book that best suits them.

[0053] The terminal presents the user with a summary of the selected self-help book and a checklist, which the user can use for daily practice.

[0054] Users record their daily practices within the application, checking off action items such as whether they performed a self-assessment or made an independent decision.

[0055] The terminal sends the user's input to the server.

[0056] 6. Generating and Presenting Feedback

[0057] The server analyzes the user's practice records and generates feedback on their performance and areas for improvement.

[0058] The server then presents the generated feedback to the user via a dedicated application, including advice on next steps and further improvements.

[0059] Specific examples

[0060] For example, if you have a self-help book called "The 7 Habits":

[0061] The server retrieves the 7 Habits data, tokenizes it, and cleans it.

[0062] A generative AI model is used to generate summaries of "The 7 Habits" and add them to the catalog.

[0063] Users select "The 7 Habits" from the catalog and receive a summary and checklist.

[0064] Checklist example:

[0065] [ ] Did you self-assess daily?

[0066] [ ] Have you made one independent decision a day?

[0067] The user records their daily activities and sends the data from the terminal to the server.

[0068] The server analyzes the recorded data and generates feedback such as, "To further increase your independent decision-making, act consciously the next day," which is presented to the user via the device.

[0069] In this way, a system for improving the efficiency of self-development is constructed, allowing users to practice self-development continuously and efficiently.

[0070] The processing flow will be explained below.

[0071] Step 1:

[0072] The server accesses the API of the e-book platform to retrieve the text data of the self-help book, along with the book's metadata (title, author, publication year, etc.).

[0073] Step 2:

[0074] The server tokenizes the acquired book data. Specifically, it uses a natural language processing library to split the text into words and punctuation marks, and converts them into a data structure (e.g., an array).

[0075] Step 3:

[0076] The server cleans the tokenized data, removing unnecessary tags, line breaks, and whitespace, and formatting the text data to make it easier to parse.

[0077] Step 4:

[0078] The server generates summaries from the tokenized and cleaned data using a generative AI model, which is a pre-trained natural language generation model.

[0079] Step 5:

[0080] The server catalogs the generated summaries. It stores each self-help book summary in JSON format, creating a searchable and filterable catalog.

[0081] Step 6:

[0082] The server extracts actionable points from the summary, using natural language processing to pick out verbs and important guidelines from the summary and create a list.

[0083] Step 7:

[0084] The server generates a checklist based on the extracted practices, which includes specific action items that users should perform daily.

[0085] Step 8:

[0086] The terminal displays a list of cataloged self-help books to the user, and the user selects a self-help book from the catalog.

[0087] Step 9:

[0088] The device presents the user with a summary and checklist of the selected self-help book, which are displayed on a dedicated screen within the application.

[0089] Step 10:

[0090] The user records the daily activities based on the checklist, and fills in the status of the activities by checking the boxes.

[0091] Step 11:

[0092] The device sends the user's practice record to the server. The recorded data is sent in JSON format.

[0093] Step 12:

[0094] The server analyzes the user's practice records using machine learning models and statistical methods.

[0095] Step 13:

[0096] The server generates feedback based on the analysis results, including the user's progress and areas for improvement.

[0097] Step 14:

[0098] The device presents the generated feedback to the user, which is displayed in a message screen within the application.

[0099] Example 1

[0100] 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."

[0101] There is a need to efficiently understand the contents of self-help books and incorporate their practical tips into daily life. However, self-help books cover a wide range of topics, and it takes time and effort to read, understand, and practice each book. Furthermore, a lack of records and feedback on practical tips makes it difficult to improve the sustainability and effectiveness of self-help. The present invention aims to solve these problems by generating summaries of self-help books, suggesting practical ideas, and automatically recording and providing feedback, thereby providing a system that allows users to efficiently practice self-help.

[0102] 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.

[0103] In this invention, the server includes means for acquiring e-book data, means for tokenizing and cleaning the acquired data, means for generating summaries from the tokenized data using a generative model, means for organizing the summarized content in a catalog format, means for extracting practice points from the summaries and generating a checklist, means for accepting a user's book selection, means for presenting summaries and checklists for the selected books, means for receiving a record of the user's practice points, means for analyzing the practice points and generating feedback, and means for presenting the generated feedback to the user. This allows users to efficiently understand the contents of a wide range of self-help books in a summarized format and easily incorporate the practice points into their daily lives. Furthermore, the practice records and feedback can enable continuous self-help practice and improved effectiveness.

[0104] A "server" is a central processing unit that processes data and provides information upon receiving a request from a client.

[0105] "E-book data" refers to the content information of a book that is stored in digital format and can be displayed and viewed through electronic media.

[0106] "Tokenization" is the process of dividing text data into useful units (words and phrases) for natural language processing.

[0107] "Cleaning" is the process of removing unnecessary elements and errors from data and preparing it in a format suitable for analysis.

[0108] A "generative model" is an algorithm or system that uses artificial intelligence technology to process natural language and generate new text.

[0109] A "summary" is a concise summary of the main information in the original text data.

[0110] The "catalog format" is a format that allows a large number of items to be systematically organized and classified so that they can be displayed in a list.

[0111] "Practical matters" are specific actions or tasks that should actually be carried out based on the self-help book.

[0112] A "checklist" is a list organized by item to check and record practice matters.

[0113] A "user" is an individual who uses the system to refer to summaries and practical matters in self-help books and engage in self-improvement.

[0114] "Selection" is the act of choosing a particular item or option from a number of items or options.

[0115] "Recording" is the act of saving and retaining certain events or actions as data.

[0116] "Feedback" is information that provides evaluations and advice on a user's actions and results.

[0117] "Presenting" is the act of showing information to a user visually or audibly.

[0118] MODE FOR CARRYING OUT THE INVENTION

[0119] The present invention relates to a self-development efficiency improvement system using a generative AI model, and this system is implemented as follows.

[0120] Acquiring and preprocessing book data

[0121] The server first uses the API of the e-book platform to obtain data on self-help books. This data is mainly text information, and APIs such as Amazon Kindle and Google Books are used to obtain the data. The obtained text data is tokenized using a natural language processing library (e.g., NLTK or spaCy), and then cleaned by removing unnecessary tags and line breaks.

[0122] Summary Generation

[0123] The server uses a generative AI model (e.g., the GPT series) to generate a summary of the contents from the tokenized book data, which is then stored in storage for further processing.

[0124] Abstract Cataloging

[0125] The server organizes the summarized data of self-help books into a catalog. Each summary is saved in JSON format, including the book's title, author, main points, etc. This catalog serves as a reference for users when selecting a self-help book.

[0126] Extraction of practical matters and generation of checklists

[0127] The server uses natural language processing technology to extract specific actions from the summary, which then generates a checklist containing tasks and action items that the user should perform each day.

[0128] User Interaction

[0129] The user uses a dedicated application to browse a catalog of self-help books and select the book that best suits them. Based on this, the device presents the user with a summary of the selected book and a checklist. The user then uses this checklist as a reference for their daily practice.

[0130] Recording and feedback on practice matters

[0131] Users record their daily activities within the application and check off action items such as "Did I perform self-evaluation?" or "Did I make independent decisions?" The device sends the user's input data to the server. The server analyzes the recorded data and generates feedback on achievements and areas for improvement. The generated feedback is presented to the user via a dedicated application.

[0132] Specific examples

[0133] For example, taking the self-help book "The 7 Habits," the server first retrieves the data for "The 7 Habits" from the e-book platform, tokenizes it, and cleans it. The server then uses a generative AI model to generate a summary of "The 7 Habits" and adds it to the catalog. The user then selects "The 7 Habits" from the catalog in a dedicated application and receives the summary and checklist from the server.

[0134] Checklist example:

[0135] [ ] Did you self-assess daily?

[0136] [ ] Have you made one independent decision a day?

[0137] Users record their daily actions and send the data from their device to the server. The server analyzes the recorded data and generates specific feedback, such as "To further increase your independent decision-making, act consciously the next day," and presents it to the user via their device.

[0138] Prompt Sentence Examples

[0139] Summarize the 7 Habits, including a description of each habit and how it contributes to personal growth.

[0140] In this way, the system of the present invention provides users with an efficient means of self-improvement. The specific details of the process are realized by the cooperative operation of the server and the terminal.

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

[0142] Step 1:

[0143] The server uses the API of the e-book platform to obtain the text data of the self-help book.

[0144] Input: Your eBook platform API key and book identifier.

[0145] Output: Raw text data of the book.

[0146] Specific operation: The server sends an API request and receives the book's text data as a response.

[0147] Step 2:

[0148] The text data retrieved by the server is tokenized and cleaned.

[0149] Input: Raw text data.

[0150] Output: Tokenized and cleaned text data.

[0151] What it does: Uses a natural language processing library (e.g., NLTK or spaCy) to split text into words and phrases, and removes unnecessary tags and line breaks.

[0152] Step 3:

[0153] The server uses a generative AI model (e.g., GPT series) to generate summaries from the tokenized data.

[0154] Input: Tokenized and cleaned text data.

[0155] Output: A text summary of the book.

[0156] How it works: A prompt sentence is input into the generative AI model to generate a summary text. The prompt sentence contains the information that forms the basis of the summary.

[0157] Step 4:

[0158] The server organizes the generated summaries into a catalog and stores them in JSON format.

[0159] Input: Book summary text.

[0160] Output: JSON data in catalog format.

[0161] Specific operation: The summary text is converted into JSON format along with information such as the book title, author, and main points, and saved to storage.

[0162] Step 5:

[0163] The server extracts specific practice items from the summary and generates a checklist.

[0164] Input: Book summary text.

[0165] Output: A checklist with action points.

[0166] Specific actions: Using natural language processing technology, verbs and important guidelines for action are extracted from the summary text, and a checklist is created based on them.

[0167] Step 6:

[0168] A user uses a dedicated application to browse a catalog of self-help books and select a book.

[0169] Input: Catalog data.

[0170] Output: User's book selection information.

[0171] Specific operation: Display a catalog on the application screen and allow the user to select the book they want to read.

[0172] Step 7:

[0173] The terminal presents the user with summaries and checklists for the selected books.

[0174] Input: User's book selection information.

[0175] Output: Summary text and checklist.

[0176] Specific behavior: The summary and checklist are displayed on the application screen for the user to refer to.

[0177] Step 8:

[0178] Users record their daily practices and check off checklists within the application.

[0179] Input: User's practice record.

[0180] Output: Recorded practice data.

[0181] What it does: Record an action by tapping on a checklist item within the app.

[0182] Step 9:

[0183] The terminal transmits the user's input data to the server.

[0184] Input: Recorded practice data.

[0185] Output: Practice data sent to the server.

[0186] Specific behavior: The application sends data to the server as a POST request.

[0187] Step 10:

[0188] The server analyzes the recorded data and generates feedback on success and areas for improvement.

[0189] Input: Practice data sent to the server.

[0190] Output: Feedback text.

[0191] What it does: Performs statistical analysis and generates feedback based on user behavior patterns.

[0192] Step 11:

[0193] The server generates feedback and presents it to the user via a dedicated application.

[0194] Input: Feedback text.

[0195] Output: The feedback presented to the user.

[0196] Specific behavior: The feedback text is displayed on the application screen.

[0197] (Application example 1)

[0198] 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."

[0199] There is a need for a system that can streamline learning based on self-help books and enable users to continuously practice self-improvement based on their experiences and purchases in physical stores. Another issue is the lack of a means to effectively provide feedback based on the participation history of store events.

[0200] 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.

[0201] In this invention, the server includes means for acquiring self-improvement data, means for tokenizing and cleaning the acquired data, and means for generating summaries from the tokenized data using a generative AI model, thereby providing users with summaries and practice checklists based on their experiences and purchases in physical stores and providing feedback based on their participation in store events.

[0202] "Self-improvement data" is data that contains information to promote self-improvement and efficient learning.

[0203] A "generative AI model" is an artificial intelligence model that uses natural language processing to generatively create output from input data.

[0204] "Tokenization" is the process of dividing a sentence into certain linguistic units.

[0205] "Cleaning" is the process of removing unnecessary information and noise from data and organizing it.

[0206] A "summary" is information that briefly and condenses the essence of self-help data.

[0207] "Catalog format" is a method of organizing information by category and displaying it in a list format.

[0208] A "self-improvement guide" is a guide to promoting self-growth and goal achievement.

[0209] A "checklist" is a list of items to check the performance of a specific action or task.

[0210] "Practices" refer to the actions or tasks that users should actually undertake.

[0211] "Feedback" is information that provides evaluations and advice based on the user's actions.

[0212] A "physical store" is a commercial facility that a user can physically visit.

[0213] "Store Events" are activities or events held at physical stores with a specific theme or purpose.

[0214] "Participation history" is a record of events and activities that a user has participated in in the past.

[0215] This invention relates to a self-improvement efficiency system that uses a generative AI model to provide summaries and practice checklists based on experiences and purchases in physical stores, and provides feedback based on participation history in store events.

[0216] System configuration and operation

[0217] The server includes the following means:

[0218] 1. Obtaining self-development data:

[0219] The server acquires data on self-help books from the e-book platform, which mainly contains text information.

[0220] 2. Tokenize and clean the data:

[0221] The server tokenizes and cleans the data it receives, which includes using natural language processing libraries to tokenize sentences and remove unnecessary tags and line breaks.

[0222] 3. Summary generation using generative AI models:

[0223] The server uses a generative AI model (e.g., a GPT-based natural language generation model) to summarize the content from the tokenized book data, and the summarized text is stored in storage for later processing.

[0224] 4. Cataloging Abstracts:

[0225] The server organizes the summarized self-help books into a catalog, with each summary stored in a format that includes the book's title, author, main points, etc.

[0226] 5. Extraction of practice items and generation of checklists:

[0227] The server extracts specific actions from the summary, which involves natural language processing to extract verbs and key actions from the book summary, and then generates a checklist based on the extracted actions.

[0228] 6. User interaction:

[0229] The user browses a catalog of self-help books through a dedicated application (smartphone, smart glasses, head-mounted display, etc.). The user checks the summary and effects and selects a self-help guidebook. The device then presents the selected summary and checklist to the user.

[0230] 7. In-store experience and purchase assistance:

[0231] Based on in-store experiences and purchases, the presented summary and checklist are updated to guide the user through their actions.

[0232] 8. Providing feedback on in-store events:

[0233] Based on the user's history of participating in store events, the server generates feedback and provides it to the user via a dedicated application, including advice on next steps and further improvements.

[0234] Example

[0235] For example, if you have a self-help book called "The 7 Habits":

[0236] The server retrieves the 7 Habits data, tokenizes it, and cleans it.

[0237] Use a generative AI model (e.g., GPT series) to generate summaries of "The 7 Habits" and add them to the catalog.

[0238] Users select "The 7 Habits" from the catalog and receive a summary and checklist.

[0239] Checklist example:

[0240] [ ] Did you self-assess daily?

[0241] [ ] Have you made one independent decision a day?

[0242] As users purchase products based on the 7 Habits in physical stores, the summary and checklist are updated.

[0243] The user records their daily activities and sends the data from the terminal to the server.

[0244] The server analyzes the recorded data and generates feedback such as, "To make more independent decisions, act consciously the next day," which is presented to the user via the device.

[0245] Examples of prompt statements

[0246] A prompt to generate a summary of a self-help book might look like this:

[0247] "Summarize the following self-help books:"

[0248] The prompt to extract the practice items is as follows:

[0249] "Please create a checklist by extracting the practical points from the summary below:"

[0250] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0251] Step 1:

[0252] The server retrieves self-help data. This is the process of collecting text data from an e-book platform. This process uses the e-book API to request specific book data and retrieve it in text format. The input requires the e-book's book ID and API key, and the output is the book's text data.

[0253] Step 2:

[0254] The server tokenizes and cleans the acquired self-help data. This process uses a natural language processing library to remove unnecessary tags and line breaks from the text data and further divides it into tokens. The input is the book text data, and the output is the cleaned tokenized data.

[0255] Step 3:

[0256] The server generates a summary from the tokenized data using a generative AI model. This process involves providing a prompt sentence to a generative AI model (e.g., GPT) to create a summary. It requires cleaned tokenized data and a prompt sentence as input, and obtains the summarized text as output.

[0257] Step 4:

[0258] The server organizes the summarized content into a catalog, a process that formats the summarized text and stores it as a catalog entry, using the summarized text as input and obtaining catalog-formatted data as output.

[0259] Step 5:

[0260] The terminal accepts the user's selection of a self-help book. In this process, the user browses the catalog and makes a selection through a dedicated application. The input is catalog data, and the output is the user's selection information.

[0261] Step 6:

[0262] The terminal presents a summary and checklist for the selected self-help book. This process displays the summary data and checklist selected by the user on the screen. It uses the user's selection and associated summary data as input and obtains a screen display as output.

[0263] Step 7:

[0264] The terminal receives the record of the user's actions. In this process, the user records the actions based on the checklist. The user's input data is used as input, and the record data is obtained as output.

[0265] Step 8:

[0266] The server analyzes the user's practice and generates feedback. This process involves analyzing the user's recorded data and creating feedback using a generative AI model. The recorded data and prompt text are used as input, and the feedback text is obtained as output.

[0267] Step 9:

[0268] The terminal presents the generated feedback to the user. This process displays the generated feedback on the user's terminal screen, using the feedback text as input and obtaining a screen display as output.

[0269] Step 10:

[0270] The server includes means for providing a summary and a checklist of actions based on the experience and purchases at the physical store. The process utilizes the purchase history and experience information at the physical store to provide the summary and checklist optimized for the user. The process uses the purchase history and experience information as input and obtains the personalized summary and checklist as output.

[0271] Step 11:

[0272] The terminal provides feedback based on the participation history of store events. In this process, the terminal refers to the participation history of store events and presents feedback to the user. The participation history is used as input and a feedback display is obtained as output.

[0273] 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.

[0274] The present invention relates to a self-development efficiency improvement system that uses a generative AI model and an emotion engine. This system is implemented as follows.

[0275] Overall system operation

[0276] 1. Acquisition and preprocessing of book data

[0277] The server accesses the API of the e-book platform to retrieve the text data of the self-help book, which mainly contains text information.

[0278] The server tokenizes the data it receives, specifically by using a natural language processing library to split the text into words and punctuation marks, and converts them into a data structure (e.g., an array).

[0279] The server cleans the tokenized data, removing unnecessary tags, line breaks, and whitespace, and formatting the text data to make it easier to parse.

[0280] 2. Summary generation using generative AI models

[0281] The server generates summaries from the tokenized and cleaned data using a generative AI model, such as a GPT-based natural language generation model.

[0282] The summarized text is saved in storage for later processing.

[0283] 3. Cataloging Abstracts

[0284] The server organizes the summarized self-help books into a catalog, where each summary is stored in JSON format, including the book's title, author, main points, etc.

[0285] 4. Extraction of practical matters and generation of checklists

[0286] The server extracts concrete actionable information from the summaries, which involves natural language processing to extract verbs and key actions from the book summaries.

[0287] Based on the extracted practices, the server generates a checklist, which includes specific action items that the user should perform daily.

[0288] 5. Emotion Recognition by Emotion Engine

[0289] The emotion engine analyzes the user's input, facial expressions, and voice to recognize emotions. Specifically, it uses a camera and microphone to analyze the user's facial expressions and voice in real time and evaluates their emotional state.

[0290] These emotional data are used to deepen understanding of the user's practice situation and improve the quality of feedback.

[0291] 6. User Interaction

[0292] Users can browse a catalog of self-help books through a dedicated application, check the summaries and effects of each book, and select the book that best suits them.

[0293] The device presents the user with a summary and checklist of the selected self-help book, which are displayed on a dedicated screen within the application.

[0294] Users record their daily actions based on a checklist, such as whether they performed a self-assessment or made an independent decision.

[0295] The terminal sends the user's input to the server.

[0296] 7. Generating and Presenting Feedback

[0297] The server analyzes the user's practice records using machine learning models and statistical methods.

[0298] The server then uses the emotion data from the emotion engine to generate feedback that takes into account the user's emotional state, including the user's progress and areas for improvement.

[0299] The device presents the generated feedback to the user, which is displayed in a message screen within the application.

[0300] Specific examples

[0301] For example, if you have a self-help book called "The 7 Habits":

[0302] The server retrieves the 7 Habits data, tokenizes it, and cleans it.

[0303] A generative AI model is used to generate summaries of "The 7 Habits" and add them to the catalog.

[0304] Users select "The 7 Habits" from the catalog and receive a summary and checklist.

[0305] Checklist example:

[0306] [ ] Did you self-assess daily?

[0307] [ ] Have you made one independent decision a day?

[0308] The user records their daily activities and sends the data from the terminal to the server.

[0309] The emotion engine recognizes the user's emotional state in real time and transmits the emotion data to the server.

[0310] The server analyzes the recorded data and emotional data, generates feedback such as, "Today's self-evaluation is good, but you lack independent decision-making. Try harder," and presents it to the user via the device.

[0311] In this way, a system for improving the efficiency of self-development is constructed, allowing users to continuously and efficiently practice self-development. By combining it with an emotion engine, feedback that takes into account the user's emotional state becomes possible, resulting in more personalized responses.

[0312] The processing flow will be explained below.

[0313] The present invention relates to a self-development efficiency improvement system that uses a generative AI model and an emotion engine. This system is implemented as follows.

[0314] Overall processing steps of the system

[0315] Step 1:

[0316] The server accesses the API of the e-book platform to obtain the text data of the self-help book. Specifically, it sends an API request specifying the book ID and extracts the text data from the JSON response.

[0317] Step 2:

[0318] The server tokenizes the text data it receives. Using a natural language processing library (e.g., NLTK or SpaCy), it splits the text into words and punctuation marks and converts them into a list.

[0319] Step 3:

[0320] The server cleans the tokenized data, removing unnecessary tags, line breaks, and whitespace, and using regular expressions to remove specific string patterns.

[0321] Step 4:

[0322] The server uses a generative AI model to generate a summary from the cleaned data. For example, it inputs text data into a GPT model and generates a summary that extracts key points.

[0323] Step 5:

[0324] The server catalogs the generated summaries, storing them in JSON format and indexing them using the self-help book metadata (title, author, publication year).

[0325] Step 6:

[0326] The server extracts actionable points from the summary, using natural language processing to pick out verbs and important guidelines from the book summary and create a list of specific action items.

[0327] Step 7:

[0328] The server generates a checklist based on the extracted practices. The checklist contains specific actions that users should take each day. The checklist is saved in JSON format.

[0329] Step 8:

[0330] The device displays a list of cataloged self-help books to the user, and the user interface also includes a search function to allow the user to easily find self-help books that interest them.

[0331] Step 9:

[0332] A user selects a self-help book, for example, "The 7 Habits," and then checks the summary and checklist on the book's details page.

[0333] Step 10:

[0334] The device presents the user with a summary and checklist of the selected self-help book, and the user reads the summary and checks the checklist within the application.

[0335] Step 11:

[0336] Users record their daily activities based on a checklist, tapping a checkbox to indicate whether a task is completed or not.

[0337] Step 12:

[0338] The device sends the user's practice record to the server, where the record data is sent in JSON format and stored.

[0339] Step 13:

[0340] The emotion engine analyzes user input, facial expressions, and vocal tones to recognize emotions. It uses cameras and microphones to collect data in real time and applies emotion analysis algorithms.

[0341] Step 14:

[0342] The server integrates and analyzes the user's practice records and emotional data, using a feedback algorithm that takes into account the user's emotional state.

[0343] Step 15:

[0344] The server generates feedback based on the analysis results, such as "Your self-evaluation today is good, but you lack proactive decision-making. Please act more consciously."

[0345] Step 16:

[0346] The device presents the generated feedback to the user, which is displayed in a message screen within the application.

[0347] The above processing steps create a system that can improve the efficiency of self-development and provide personalized feedback. Users can continuously and efficiently practice self-development, resulting in better results.

[0348] Example 2

[0349] 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."

[0350] In the past, it was difficult for users to efficiently extract the main points of each book and create an appropriate practice plan. In addition, there was a lack of feedback that took into account the user's emotional state, which resulted in a decrease in the effectiveness of the self-help book.

[0351] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring self-help book data, means for tokenizing and cleaning the acquired data, means for generating a summary from the tokenized data using a generative AI model, means for organizing the summarized content in a catalog format, means for extracting specific practice points from the summary and generating a checklist, means for analyzing a user's input, facial expressions, and voice to recognize emotions, means for analyzing the user's practice status and emotional data and generating feedback, and means for presenting the generated feedback to the user. This makes it possible to efficiently extract the key points of a self-help book and provide the user with feedback that takes into account their emotional state.

[0352] "Self-help book data" is data that includes text information of books related to self-help.

[0353] "Means for obtaining" refers to a function or device for obtaining necessary data from an external data source.

[0354] "Tokenization" is the process of dividing text data into its smallest units, such as words and punctuation marks.

[0355] "Cleaning means" refers to a process of arranging data by removing unnecessary tags, line breaks, and spaces from text data.

[0356] A "generative AI model" is an artificial intelligence model that uses natural language processing technology to summarize and generate text data.

[0357] The "means for generating summaries" is a function that uses a generative AI model to extract key points from text data and present them in a concise format.

[0358] The "means for organizing in a catalog format" is a means for storing summarized data in a specific structure and organizing it so that the user can easily access it.

[0359] The "means for extracting action items" is a function that identifies specific guidelines and verbs from summary data and extracts them as items to be put into practice.

[0360] The "means for generating a checklist" is a function that lists action items to be carried out based on the extracted practice items.

[0361] "User input" refers to information or data provided by a user, such as text entry or selection actions.

[0362] "Facial expression" refers to the user's facial movements and expressive state.

[0363] "Voice" refers to the state of a user's voice, including their tone and emotions.

[0364] The "means for recognizing emotions" is a function that analyzes the user's facial expressions and voice to identify their emotional state.

[0365] "Recording practice items" refers to the user recording the results of their daily practice.

[0366] The "means for generating feedback" is a function that creates feedback including areas for improvement and progress based on the user's practice data and emotional state.

[0367] The "means for presenting feedback" is a function for displaying the generated feedback to the user.

[0368] The present invention relates to a self-help efficiency improvement system that uses a generative AI model and an emotion engine. This system automates the process from acquiring self-help book data to providing feedback to users. Specific embodiments are described below.

[0369] Hardware and Software Use

[0370] The system mainly consists of a server, a terminal, and an emotion engine.

[0371] 1. Server Operation

[0372] Get book data:

[0373] The server accesses the API of the e-book platform to retrieve the text data of the self-help book. At this time, it sends a request using the Python requests library, and the data is saved in JSON format.

[0374] Tokenize and clean data:

[0375] The server tokenizes the retrieved data using a natural language processing library (e.g., NLTK or spaCy), and the cleaning process uses a regular expression library to remove unnecessary tags, line breaks, and whitespace.

[0376] Summary generation using generative AI models:

[0377] The server uses a generative AI model (e.g., OpenAI's GPT-3) to send the data along with the prompt and generate a summary, which is stored in a variable for later processing.

[0378] Abstract Cataloging:

[0379] The server organizes the summaries into a catalog, stored in JSON format, that includes the book title, author, and key points of the summary.

[0380] Extraction of practices and generation of checklists:

[0381] The server extracts action items (e.g., verbs and guidelines) from the summary text and lists them as a checklist.

[0382] 2. Operation of the Emotion Engine

[0383] The emotion engine uses a camera and microphone to capture the user's facial expressions and voice. This data is analyzed in real time to evaluate the user's emotional state. Specifically, it uses technologies such as OpenFace and TensorFlow.

[0384] 3. Device Operation

[0385] Browse the catalogue:

[0386] A user can browse a catalog of self-help books stored on a server through a dedicated application, select an appropriate book, and view its summary and checklist.

[0387] Present and record the checklist:

[0388] The terminal displays a summary of the selected book and a checklist to the user, who then records his or her daily activities based on the checklist and sends the data to the server.

[0389] 4. Generating and Presenting Feedback

[0390] Analysis of recorded data:

[0391] The server analyzes the practice records entered by the user using machine learning models and statistical methods, and also uses emotional data from the emotion engine to generate feedback that takes the user's emotional state into account.

[0392] Giving feedback:

[0393] The device presents the user with feedback sent from the server, including information about progress and areas for improvement.

[0394] Specific examples

[0395] For example, if a user chooses "The 7 Habits" as a self-help book, the server retrieves the book's data, tokenizes and cleans it, then uses GPT-3 to generate a summary and add it to the catalog. The user selects "The 7 Habits" from the catalog and receives the summary and checklist.

[0396] Checklist example:

[0397] [ ] Did you self-assess every day?

[0398] [ ] Did you make an independent decision?

[0399] Example of a generated AI prompt:

[0400] Please write a summary of "The 7 Habits" in the following format:

[0401] Key points of this book

[0402] Key Action Items

[0403] Practical Tips

[0404] Text: <insert text here>

[0405] In this way, a system for improving the efficiency of self-development is constructed, supporting users in practicing self-development continuously and effectively.By combining it with an emotion engine, it becomes possible to provide personalized feedback according to the user's emotional state.

[0406] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0407] Step 1:

[0408] The server accesses the API of the e-book platform and retrieves the text data of the self-help book. The API endpoint URL and access credentials are used as input, and the retrieved book data (JSON format) is output. Specifically, it sends a request to the API using the Python requests library (e.g., response = requests.get(API_URL, headers=headers)) and saves the retrieved data in JSON format (e.g., book_data = response.json()).

[0409] Step 2:

[0410] The server tokenizes and cleans the acquired book data. The acquired book data is used as input, and the output is the tokenized and cleaned data. Specifically, it uses a natural language processing library such as NLTK to split the text into words and punctuation marks (tokenization), and uses Python's regular expression library to remove unnecessary tags, line breaks, and spaces (e.g., clean_text = re.sub(r'\s+', ' ', book_data["text"])).

[0411] Step 3:

[0412] The server uses a generative AI model to generate a summary from the tokenized and cleaned data. It uses the cleaned text data and a prompt as input, and outputs the summary text. Specifically, it uses OpenAI's API to send the data along with the prompt (e.g., response = openai.Completion.create(engine="text-davinci-003", prompt=prompt, max_tokens=150)) and stores the generated summary in a variable (e.g., summary = response.choices[0].text.strip()).

[0413] Step 4:

[0414] The server organizes the summarized self-help books into a catalog. It takes the summary text and basic book information (title, author, etc.) as input, and outputs a catalog entry in JSON format. Specifically, it generates a data structure containing the summary text (e.g., catalog_entry = {"title": book_title, "author": book_author, "summary": summary}) and stores it in the database.

[0415] Step 5:

[0416] The server extracts specific actions from the summary and generates a checklist. The input is the summary text, and the output is a checklist. Specifically, it uses a text analysis algorithm to extract verbs and action points from the summary (e.g., actions = extract_actions_from_summary(summary)), and then creates a list of them (e.g., checklist = create_checklist(actions)).

[0417] Step 6:

[0418] The emotion engine analyzes user input, facial expressions, and vocal sounds to recognize emotions. It uses real-time facial and vocal data obtained from a camera and microphone as input, and outputs emotional data. Specifically, it uses OpenFace for facial recognition (e.g., emotion_face = analyze_facial_expression(image)) and TensorFlow for vocal analysis (e.g., emotion_voice = analyze_voice(voice_clip)).

[0419] Step 7:

[0420] The user browses a catalog of self-help books through a dedicated application, and selects and views the summary and checklist of a self-help book. The input is the catalog data stored on the server, and the output is the summary and checklist displayed to the user. Specifically, the mobile application displays the catalog screen, and retrieves and displays the self-help book data selected by the user.

[0421] Step 8:

[0422] The user records daily practice items based on the checklist, and the device sends the data to the server. The input is the practice data recorded by the user, and the output is the record data sent to the server. The specific operation is that the user enters data in the mobile application and sends the data to the server (e.g., send_to_server(record_data)).

[0423] Step 9:

[0424] The server analyzes the user's practice record and emotion data and generates feedback. It uses practice record data and emotion data as input, and outputs a feedback message. Specifically, it analyzes the data using machine learning models and statistical methods (e.g., feedback = generate_feedback(user_data, emotion_data)) and generates appropriate feedback.

[0425] Step 10:

[0426] The terminal presents the generated feedback to the user. The input is the feedback message sent from the server, and the output is the feedback displayed to the user. Specifically, the feedback is displayed on a message screen within the mobile application.

[0427] (Application example 2)

[0428] 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."

[0429] Conventional self-improvement support systems specialize in generating summaries and providing checklists to promote user growth, but lack the ability to generate feedback that takes into account the user's emotional state. As a result, they are unable to provide personalized feedback based on emotions that would help users maintain their self-improvement behavior. Furthermore, in the food delivery industry, there is a lack of systems that support self-improvement for delivery workers while they are working.

[0430] 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.

[0431] In this invention, the server includes means for acquiring self-help book data, means for tokenizing and cleaning the acquired data, means for generating summaries from the tokenized data using a generative AI model, means for organizing the summarized content in a catalog format, means for accepting a user's selection of a self-help book, means for presenting summaries and checklists of the selected self-help book, means for receiving a record of the user's practice, means for analyzing the practice status and generating feedback, means for presenting the generated feedback to the user, means for analyzing the user's emotional state, and means for adjusting the content of the feedback based on the user's emotional state. This makes it possible to provide personalized feedback based on the user's practice status and emotional state, allowing food delivery workers to efficiently engage in self-improvement while on the job.

[0432] "Self-help book data" is digital data of books and documents used as self-help books.

[0433] "Tokenization" is the process of dividing text data into smaller units such as words and punctuation marks.

[0434] "Cleaning" is the process of removing unnecessary tags, line breaks, and spaces from data to prepare it in a format that is easy to analyze.

[0435] A "generative AI model" is an algorithm or program that uses AI to generate natural language and summaries.

[0436] A "summary" is a short summary of the main points or content of a text or book.

[0437] "Catalog format" is a format in which information is organized and displayed by items such as title, author, and main points.

[0438] A "checklist" is a list of action items that a user should take.

[0439] "Feedback" is information such as suggestions for improvement or advice generated based on the practice situation and emotional state.

[0440] "Means for analyzing emotional state" refers to a method or system for analyzing emotions from the user's facial expressions, voice, etc.

[0441] The "means for adjusting the content of feedback based on emotional state" refers to a method or system that changes the feedback provided depending on the analyzed emotion.

[0442] This invention is a system for supporting users' self-development by efficiently utilizing the contents of self-help books, and is particularly targeted at delivery workers in the food delivery industry. This system is implemented using hardware and software including a server, a terminal, an emotion engine, a camera, and a microphone.

[0443] The server retrieves self-help book data from the e-book platform, tokenizes and cleans it, and then uses the tokenized data to generate summaries using a generative AI model. This generative AI model applies the GPT series of natural language generation models. The summaries are then organized into a catalog and saved in JSON format. This allows for efficient management of information and makes it easy for users to access.

[0444] Next, the device (e.g., a smartphone application) accepts user input. The user selects the desired book from a catalog of self-help books and receives a summary and a checklist. The checklist includes specific action items to be put into practice. The user records the actions they take each day and sends the data from the device to a server. For example, the checklist might include action items such as "Have you performed self-evaluation every day?" or "Have you made one independent decision per day?"

[0445] Furthermore, the emotion engine analyzes the user's emotional state using a camera and microphone. This analyzed emotional data is sent to a server, which generates feedback based on the user's progress and emotional state. The feedback includes personalized advice that takes the user's emotions into account, making it easier for the user to continue their self-improvement activities.

[0446] For example, if a delivery person opens the app and selects "The 7 Habits," the server retrieves the book's data, tokenizes it, and cleans it. A generative AI model then generates a summary and adds it to the catalog. The delivery person retrieves this summary from the catalog and records their actions based on a daily checklist. Meanwhile, an emotion engine recognizes the delivery person's emotional state from their facial expressions and tone of voice, and sends this data to the server. Based on the recorded data and emotion data, the server generates feedback such as, "Today's self-evaluation is good, but your independent decision-making skills are lacking. You need to work harder," and presents it to the delivery person via their device.

[0447] In this way, this invention is a system that supports users in continuing to work on self-improvement by streamlining the use of self-help books and providing personalized feedback that takes into account their emotional state. This system allows delivery workers, particularly in the food delivery industry, to efficiently engage in self-improvement while at work.

[0448] Examples of prompts:

[0449] "Set your goals for today as 'Perform daily self-evaluation' and 'Make independent decisions.' Judging from your emotional state, you seem a little tired today. Take a break and complete the practical tasks."

[0450] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0451] Step 1:

[0452] The server retrieves self-help book data using the API of the e-book platform. The input is the book ID, and the data retrieved from the API includes the book's text content. Specifically, the server sends an HTTP request and receives the e-book data. The output is the retrieved book data.

[0453] Step 2:

[0454] The server tokenizes and cleans the acquired book data. The input is the book data, and a natural language processing library is used to split the data into words and punctuation marks, and remove unnecessary characters and tags. Specifically, the server uses an NLP library to perform tokenization and regular expressions to perform cleaning. The output is the tokenized and cleaned data.

[0455] Step 3:

[0456] The server generates a summary using a generative AI model based on the tokenized and cleaned data. The input is the tokenized data, and the generative AI model (e.g., GPT sequence) extracts important content and generates a summary. Specifically, the server inputs the tokenized data into the generative AI model and receives the summary generated by the model. The output is the summarized text.

[0457] Step 4:

[0458] The server organizes the generated summary text into a catalog format. The input is the summary text, which is converted into JSON format for each item, such as title, author, and main points. Specifically, the server parses the summary text and creates a data structure corresponding to each item. The output is JSON data in catalog format.

[0459] Step 5:

[0460] The terminal accepts the user's selection of a self-help book. The input is the user's selection information, and based on that information, it presents a summary and checklist of the corresponding book from the catalog. In concrete terms, the terminal receives the user's input, retrieves the corresponding data, and displays it. The output is the summary and checklist presented to the user.

[0461] Step 6:

[0462] The user records the actions based on the checklist. The input is the user's recorded information, which is sent from the terminal to the server. In concrete terms, the user records an action item, and the terminal sends the information to the backend. The output is the action record stored on the server.

[0463] Step 7:

[0464] The emotion engine analyzes the user's emotional state using a camera and microphone. The input is the user's facial expression and vocal data, and the emotional state is evaluated through analysis. Specifically, the emotion engine acquires data from the camera and microphone and analyzes it using a machine learning algorithm. The output is evaluated emotional data.

[0465] Step 8:

[0466] The server generates feedback based on practice status data and emotion data and presents it to the user. The input is practice record data and emotion data, which are analyzed using machine learning models and statistical methods to generate personalized feedback. Specifically, the server summarizes the analysis results, generates a feedback message, and sends it to the terminal. The output is the feedback message presented to the user.

[0467] 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.

[0468] 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.

[0469] 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.

[0470] [Second embodiment]

[0471] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0472] 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.

[0473] 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).

[0474] 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.

[0475] 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.

[0476] 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).

[0477] 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.

[0478] 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.

[0479] 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.

[0480] 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.

[0481] 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.

[0482] 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."

[0483] The present invention relates to a self-development efficiency improvement system using a generative AI model. This system is implemented as follows.

[0484] Overall system operation

[0485] 1. Acquisition and preprocessing of book data

[0486] The server retrieves data on self-help books from an e-book platform, which mainly contains text information.

[0487] The server tokenizes and cleans the data it receives, removing unnecessary tags and line breaks and splitting sentences into tokens using a natural language processing library.

[0488] 2. Summary generation using generative AI models

[0489] The server uses a generative AI model to summarize the content from the tokenized book data, such as a GPT-based natural language generation model.

[0490] The summarized text is saved in storage for later processing.

[0491] 3. Cataloging Abstracts

[0492] The server organizes the summarized self-help books into a catalog, where each summary is stored in JSON format, including the book's title, author, main points, etc.

[0493] 4. Extraction of practical matters and generation of checklists

[0494] The server extracts concrete actionable information from the summaries, which involves natural language processing to extract verbs and key actions from the book summaries.

[0495] Based on the extracted practices, the server generates a checklist that includes daily tasks and action items.

[0496] 5. User Interaction

[0497] Users can browse a catalog of self-help books through a dedicated application, check the summaries and effects of each book, and select the book that best suits them.

[0498] The terminal presents the user with a summary of the selected self-help book and a checklist, which the user can use for daily practice.

[0499] Users record their daily practices within the application, checking off action items such as whether they performed a self-assessment or made an independent decision.

[0500] The terminal sends the user's input to the server.

[0501] 6. Generating and Presenting Feedback

[0502] The server analyzes the user's practice records and generates feedback on their performance and areas for improvement.

[0503] The server then presents the generated feedback to the user via a dedicated application, including advice on next steps and further improvements.

[0504] Specific examples

[0505] For example, if you have a self-help book called "The 7 Habits":

[0506] The server retrieves the 7 Habits data, tokenizes it, and cleans it.

[0507] A generative AI model is used to generate summaries of "The 7 Habits" and add them to the catalog.

[0508] Users select "The 7 Habits" from the catalog and receive a summary and checklist.

[0509] Checklist example:

[0510] [ ] Did you self-assess daily?

[0511] [ ] Have you made one independent decision a day?

[0512] The user records their daily activities and sends the data from the terminal to the server.

[0513] The server analyzes the recorded data and generates feedback such as, "To further increase your independent decision-making, act consciously the next day," which is presented to the user via the device.

[0514] In this way, a system for improving the efficiency of self-development is constructed, allowing users to practice self-development continuously and efficiently.

[0515] The processing flow will be explained below.

[0516] Step 1:

[0517] The server accesses the API of the e-book platform to retrieve the text data of the self-help book, along with the book's metadata (title, author, publication year, etc.).

[0518] Step 2:

[0519] The server tokenizes the acquired book data. Specifically, it uses a natural language processing library to split the text into words and punctuation marks, and converts them into a data structure (e.g., an array).

[0520] Step 3:

[0521] The server cleans the tokenized data, removing unnecessary tags, line breaks, and whitespace, and formatting the text data to make it easier to parse.

[0522] Step 4:

[0523] The server generates summaries from the tokenized and cleaned data using a generative AI model, which is a pre-trained natural language generation model.

[0524] Step 5:

[0525] The server catalogs the generated summaries. It stores each self-help book summary in JSON format, creating a searchable and filterable catalog.

[0526] Step 6:

[0527] The server extracts actionable points from the summary, using natural language processing to pick out verbs and important guidelines from the summary and create a list.

[0528] Step 7:

[0529] The server generates a checklist based on the extracted practices, which includes specific action items that users should perform daily.

[0530] Step 8:

[0531] The terminal displays a list of cataloged self-help books to the user, and the user selects a self-help book from the catalog.

[0532] Step 9:

[0533] The device presents the user with a summary and checklist of the selected self-help book, which are displayed on a dedicated screen within the application.

[0534] Step 10:

[0535] The user records the daily activities based on the checklist, and fills in the status of the activities by checking the boxes.

[0536] Step 11:

[0537] The device sends the user's practice record to the server. The recorded data is sent in JSON format.

[0538] Step 12:

[0539] The server analyzes the user's practice records using machine learning models and statistical methods.

[0540] Step 13:

[0541] The server generates feedback based on the analysis results, including the user's progress and areas for improvement.

[0542] Step 14:

[0543] The device presents the generated feedback to the user, which is displayed in a message screen within the application.

[0544] Example 1

[0545] 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."

[0546] There is a need to efficiently understand the contents of self-help books and incorporate their practical tips into daily life. However, self-help books cover a wide range of topics, and it takes time and effort to read, understand, and practice each book. Furthermore, a lack of records and feedback on practical tips makes it difficult to improve the sustainability and effectiveness of self-help. The present invention aims to solve these problems by generating summaries of self-help books, suggesting practical ideas, and automatically recording and providing feedback, thereby providing a system that allows users to efficiently practice self-help.

[0547] 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.

[0548] In this invention, the server includes means for acquiring e-book data, means for tokenizing and cleaning the acquired data, means for generating summaries from the tokenized data using a generative model, means for organizing the summarized content in a catalog format, means for extracting practice points from the summaries and generating a checklist, means for accepting a user's book selection, means for presenting summaries and checklists for the selected books, means for receiving a record of the user's practice points, means for analyzing the practice points and generating feedback, and means for presenting the generated feedback to the user. This allows users to efficiently understand the contents of a wide range of self-help books in a summarized format and easily incorporate the practice points into their daily lives. Furthermore, the practice records and feedback can enable continuous self-help practice and improved effectiveness.

[0549] A "server" is a central processing unit that processes data and provides information upon receiving a request from a client.

[0550] "E-book data" refers to the content information of a book that is stored in digital format and can be displayed and viewed through electronic media.

[0551] "Tokenization" is the process of dividing text data into useful units (words and phrases) for natural language processing.

[0552] "Cleaning" is the process of removing unnecessary elements and errors from data and preparing it in a format suitable for analysis.

[0553] A "generative model" is an algorithm or system that uses artificial intelligence technology to process natural language and generate new text.

[0554] A "summary" is a concise summary of the main information in the original text data.

[0555] The "catalog format" is a format that allows a large number of items to be systematically organized and classified so that they can be displayed in a list.

[0556] "Practical matters" are specific actions or tasks that should actually be carried out based on the self-help book.

[0557] A "checklist" is a list organized by item to check and record practice matters.

[0558] A "user" is an individual who uses the system to refer to summaries and practical matters in self-help books and engage in self-improvement.

[0559] "Selection" is the act of choosing a particular item or option from a number of items or options.

[0560] "Recording" is the act of saving and retaining certain events or actions as data.

[0561] "Feedback" is information that provides evaluations and advice on a user's actions and results.

[0562] "Presenting" is the act of showing information to a user visually or audibly.

[0563] MODE FOR CARRYING OUT THE INVENTION

[0564] The present invention relates to a self-development efficiency improvement system using a generative AI model, and this system is implemented as follows.

[0565] Acquiring and preprocessing book data

[0566] The server first uses the API of the e-book platform to obtain data on self-help books. This data is mainly text information, and APIs such as Amazon Kindle and Google Books are used to obtain the data. The obtained text data is tokenized using a natural language processing library (e.g., NLTK or spaCy), and then cleaned by removing unnecessary tags and line breaks.

[0567] Summary Generation

[0568] The server uses a generative AI model (e.g., the GPT series) to generate a summary of the contents from the tokenized book data, which is then stored in storage for further processing.

[0569] Abstract Cataloging

[0570] The server organizes the summarized data of self-help books into a catalog. Each summary is saved in JSON format, including the book's title, author, main points, etc. This catalog serves as a reference for users when selecting a self-help book.

[0571] Extraction of practical matters and generation of checklists

[0572] The server uses natural language processing technology to extract specific actions from the summary, which then generates a checklist containing tasks and action items that the user should perform each day.

[0573] User Interaction

[0574] The user uses a dedicated application to browse a catalog of self-help books and select the book that best suits them. Based on this, the device presents the user with a summary of the selected book and a checklist. The user then uses this checklist as a reference for their daily practice.

[0575] Recording and feedback on practice matters

[0576] Users record their daily activities within the application and check off action items such as "Did I perform self-evaluation?" or "Did I make independent decisions?" The device sends the user's input data to the server. The server analyzes the recorded data and generates feedback on achievements and areas for improvement. The generated feedback is presented to the user via a dedicated application.

[0577] Specific examples

[0578] For example, taking the self-help book "The 7 Habits," the server first retrieves the data for "The 7 Habits" from the e-book platform, tokenizes it, and cleans it. The server then uses a generative AI model to generate a summary of "The 7 Habits" and adds it to the catalog. The user then selects "The 7 Habits" from the catalog in a dedicated application and receives the summary and checklist from the server.

[0579] Checklist example:

[0580] [ ] Did you self-assess daily?

[0581] [ ] Have you made one independent decision a day?

[0582] Users record their daily actions and send the data from their device to the server. The server analyzes the recorded data and generates specific feedback, such as "To further increase your independent decision-making, act consciously the next day," and presents it to the user via their device.

[0583] Prompt Sentence Examples

[0584] Summarize the 7 Habits, including a description of each habit and how it contributes to personal growth.

[0585] In this way, the system of the present invention provides users with an efficient means of self-improvement. The specific details of the process are realized by the cooperative operation of the server and the terminal.

[0586] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0587] Step 1:

[0588] The server uses the API of the e-book platform to obtain the text data of the self-help book.

[0589] Input: Your eBook platform API key and book identifier.

[0590] Output: Raw text data of the book.

[0591] Specific operation: The server sends an API request and receives the book's text data as a response.

[0592] Step 2:

[0593] The text data retrieved by the server is tokenized and cleaned.

[0594] Input: Raw text data.

[0595] Output: Tokenized and cleaned text data.

[0596] What it does: Uses a natural language processing library (e.g., NLTK or spaCy) to split text into words and phrases, and removes unnecessary tags and line breaks.

[0597] Step 3:

[0598] The server uses a generative AI model (e.g., GPT series) to generate summaries from the tokenized data.

[0599] Input: Tokenized and cleaned text data.

[0600] Output: A text summary of the book.

[0601] How it works: A prompt sentence is input into the generative AI model to generate a summary text. The prompt sentence contains the information that forms the basis of the summary.

[0602] Step 4:

[0603] The server organizes the generated summaries into a catalog and stores them in JSON format.

[0604] Input: Book summary text.

[0605] Output: JSON data in catalog format.

[0606] Specific operation: The summary text is converted into JSON format along with information such as the book title, author, and main points, and saved to storage.

[0607] Step 5:

[0608] The server extracts specific practice items from the summary and generates a checklist.

[0609] Input: Book summary text.

[0610] Output: A checklist with action points.

[0611] Specific actions: Using natural language processing technology, verbs and important guidelines for action are extracted from the summary text, and a checklist is created based on them.

[0612] Step 6:

[0613] A user uses a dedicated application to browse a catalog of self-help books and select a book.

[0614] Input: Catalog data.

[0615] Output: User's book selection information.

[0616] Specific operation: Display a catalog on the application screen and allow the user to select the book they want to read.

[0617] Step 7:

[0618] The terminal presents the user with summaries and checklists for the selected books.

[0619] Input: User's book selection information.

[0620] Output: Summary text and checklist.

[0621] Specific behavior: The summary and checklist are displayed on the application screen for the user to refer to.

[0622] Step 8:

[0623] Users record their daily practices and check off checklists within the application.

[0624] Input: User's practice record.

[0625] Output: Recorded practice data.

[0626] What it does: Record an action by tapping on a checklist item within the app.

[0627] Step 9:

[0628] The terminal transmits the user's input data to the server.

[0629] Input: Recorded practice data.

[0630] Output: Practice data sent to the server.

[0631] Specific behavior: The application sends data to the server as a POST request.

[0632] Step 10:

[0633] The server analyzes the recorded data and generates feedback on success and areas for improvement.

[0634] Input: Practice data sent to the server.

[0635] Output: Feedback text.

[0636] What it does: Performs statistical analysis and generates feedback based on user behavior patterns.

[0637] Step 11:

[0638] The server generates feedback and presents it to the user via a dedicated application.

[0639] Input: Feedback text.

[0640] Output: The feedback presented to the user.

[0641] Specific behavior: The feedback text is displayed on the application screen.

[0642] (Application example 1)

[0643] 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."

[0644] There is a need for a system that can streamline learning based on self-help books and enable users to continuously practice self-improvement based on their experiences and purchases in physical stores. Another issue is the lack of a means to effectively provide feedback based on the participation history of store events.

[0645] 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.

[0646] In this invention, the server includes means for acquiring self-improvement data, means for tokenizing and cleaning the acquired data, and means for generating summaries from the tokenized data using a generative AI model, thereby providing users with summaries and practice checklists based on their experiences and purchases in physical stores and providing feedback based on their participation in store events.

[0647] "Self-improvement data" is data that contains information to promote self-improvement and efficient learning.

[0648] A "generative AI model" is an artificial intelligence model that uses natural language processing to generatively create output from input data.

[0649] "Tokenization" is the process of dividing a sentence into certain linguistic units.

[0650] "Cleaning" is the process of removing unnecessary information and noise from data and organizing it.

[0651] A "summary" is information that briefly and condenses the essence of self-help data.

[0652] "Catalog format" is a method of organizing information by category and displaying it in a list format.

[0653] A "self-improvement guide" is a guide to promoting self-growth and goal achievement.

[0654] A "checklist" is a list of items to check the performance of a specific action or task.

[0655] "Practices" refer to the actions or tasks that users should actually undertake.

[0656] "Feedback" is information that provides evaluations and advice based on the user's actions.

[0657] A "physical store" is a commercial facility that a user can physically visit.

[0658] "Store Events" are activities or events held at physical stores with a specific theme or purpose.

[0659] "Participation history" is a record of events and activities that a user has participated in in the past.

[0660] This invention relates to a self-improvement efficiency system that uses a generative AI model to provide summaries and practice checklists based on experiences and purchases in physical stores, and provides feedback based on participation history in store events.

[0661] System configuration and operation

[0662] The server includes the following means:

[0663] 1. Obtaining self-development data:

[0664] The server acquires data on self-help books from the e-book platform, which mainly contains text information.

[0665] 2. Tokenize and clean the data:

[0666] The server tokenizes and cleans the data it receives, which includes using natural language processing libraries to tokenize sentences and remove unnecessary tags and line breaks.

[0667] 3. Summary generation using generative AI models:

[0668] The server uses a generative AI model (e.g., a GPT-based natural language generation model) to summarize the content from the tokenized book data, and the summarized text is stored in storage for later processing.

[0669] 4. Cataloging Abstracts:

[0670] The server organizes the summarized self-help books into a catalog, with each summary stored in a format that includes the book's title, author, main points, etc.

[0671] 5. Extraction of practice items and generation of checklists:

[0672] The server extracts specific actions from the summary, which involves natural language processing to extract verbs and key actions from the book summary, and then generates a checklist based on the extracted actions.

[0673] 6. User interaction:

[0674] The user browses a catalog of self-help books through a dedicated application (smartphone, smart glasses, head-mounted display, etc.). The user checks the summary and effects and selects a self-help guidebook. The device then presents the selected summary and checklist to the user.

[0675] 7. In-store experience and purchase assistance:

[0676] Based on in-store experiences and purchases, the presented summary and checklist are updated to guide the user through their actions.

[0677] 8. Providing feedback on in-store events:

[0678] Based on the user's history of participating in store events, the server generates feedback and provides it to the user via a dedicated application, including advice on next steps and further improvements.

[0679] Example

[0680] For example, if you have a self-help book called "The 7 Habits":

[0681] The server retrieves the 7 Habits data, tokenizes it, and cleans it.

[0682] Use a generative AI model (e.g., GPT series) to generate summaries of "The 7 Habits" and add them to the catalog.

[0683] Users select "The 7 Habits" from the catalog and receive a summary and checklist.

[0684] Checklist example:

[0685] [ ] Did you self-assess daily?

[0686] [ ] Have you made one independent decision a day?

[0687] As users purchase products based on the 7 Habits in physical stores, the summary and checklist are updated.

[0688] The user records their daily activities and sends the data from the terminal to the server.

[0689] The server analyzes the recorded data and generates feedback such as, "To make more independent decisions, act consciously the next day," which is presented to the user via the device.

[0690] Examples of prompt statements

[0691] A prompt to generate a summary of a self-help book might look like this:

[0692] "Summarize the following self-help books:"

[0693] The prompt to extract the practice items is as follows:

[0694] "Please create a checklist by extracting the practical points from the summary below:"

[0695] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0696] Step 1:

[0697] The server retrieves self-help data. This is the process of collecting text data from an e-book platform. This process uses the e-book API to request specific book data and retrieve it in text format. The input requires the e-book's book ID and API key, and the output is the book's text data.

[0698] Step 2:

[0699] The server tokenizes and cleans the acquired self-help data. This process uses a natural language processing library to remove unnecessary tags and line breaks from the text data and further divides it into tokens. The input is the book text data, and the output is the cleaned tokenized data.

[0700] Step 3:

[0701] The server generates a summary from the tokenized data using a generative AI model. This process involves providing a prompt sentence to a generative AI model (e.g., GPT) to create a summary. It requires cleaned tokenized data and a prompt sentence as input, and obtains the summarized text as output.

[0702] Step 4:

[0703] The server organizes the summarized content into a catalog, a process that formats the summarized text and stores it as a catalog entry, using the summarized text as input and obtaining catalog-formatted data as output.

[0704] Step 5:

[0705] The terminal accepts the user's selection of a self-help book. In this process, the user browses the catalog and makes a selection through a dedicated application. The input is catalog data, and the output is the user's selection information.

[0706] Step 6:

[0707] The terminal presents a summary and checklist for the selected self-help book. This process displays the summary data and checklist selected by the user on the screen. It uses the user's selection and associated summary data as input and obtains a screen display as output.

[0708] Step 7:

[0709] The terminal receives the record of the user's actions. In this process, the user records the actions based on the checklist. The user's input data is used as input, and the record data is obtained as output.

[0710] Step 8:

[0711] The server analyzes the user's practice and generates feedback. This process involves analyzing the user's recorded data and creating feedback using a generative AI model. The recorded data and prompt text are used as input, and the feedback text is obtained as output.

[0712] Step 9:

[0713] The terminal presents the generated feedback to the user. This process displays the generated feedback on the user's terminal screen, using the feedback text as input and obtaining a screen display as output.

[0714] Step 10:

[0715] The server includes means for providing a summary and a checklist of actions based on the experience and purchases at the physical store. The process utilizes the purchase history and experience information at the physical store to provide the summary and checklist optimized for the user. The process uses the purchase history and experience information as input and obtains the personalized summary and checklist as output.

[0716] Step 11:

[0717] The terminal provides feedback based on the participation history of store events. In this process, the terminal refers to the participation history of store events and presents feedback to the user. The participation history is used as input and a feedback display is obtained as output.

[0718] 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.

[0719] The present invention relates to a self-development efficiency improvement system that uses a generative AI model and an emotion engine. This system is implemented as follows.

[0720] Overall system operation

[0721] 1. Acquisition and preprocessing of book data

[0722] The server accesses the API of the e-book platform to retrieve the text data of the self-help book, which mainly contains text information.

[0723] The server tokenizes the data it receives, specifically by using a natural language processing library to split the text into words and punctuation marks, and converts them into a data structure (e.g., an array).

[0724] The server cleans the tokenized data, removing unnecessary tags, line breaks, and whitespace, and formatting the text data to make it easier to parse.

[0725] 2. Summary generation using generative AI models

[0726] The server generates summaries from the tokenized and cleaned data using a generative AI model, such as a GPT-based natural language generation model.

[0727] The summarized text is saved in storage for later processing.

[0728] 3. Cataloging Abstracts

[0729] The server organizes the summarized self-help books into a catalog, where each summary is stored in JSON format, including the book's title, author, main points, etc.

[0730] 4. Extraction of practical matters and generation of checklists

[0731] The server extracts concrete actionable information from the summaries, which involves natural language processing to extract verbs and key actions from the book summaries.

[0732] Based on the extracted practices, the server generates a checklist, which includes specific action items that the user should perform daily.

[0733] 5. Emotion Recognition by Emotion Engine

[0734] The emotion engine analyzes the user's input, facial expressions, and voice to recognize emotions. Specifically, it uses a camera and microphone to analyze the user's facial expressions and voice in real time and evaluates their emotional state.

[0735] These emotional data are used to deepen understanding of the user's practice situation and improve the quality of feedback.

[0736] 6. User Interaction

[0737] Users can browse a catalog of self-help books through a dedicated application, check the summaries and effects of each book, and select the book that best suits them.

[0738] The device presents the user with a summary and checklist of the selected self-help book, which are displayed on a dedicated screen within the application.

[0739] Users record their daily actions based on a checklist, such as whether they performed a self-assessment or made an independent decision.

[0740] The terminal sends the user's input to the server.

[0741] 7. Generating and Presenting Feedback

[0742] The server analyzes the user's practice records using machine learning models and statistical methods.

[0743] The server then uses the emotion data from the emotion engine to generate feedback that takes into account the user's emotional state, including the user's progress and areas for improvement.

[0744] The device presents the generated feedback to the user, which is displayed in a message screen within the application.

[0745] Specific examples

[0746] For example, if you have a self-help book called "The 7 Habits":

[0747] The server retrieves the 7 Habits data, tokenizes it, and cleans it.

[0748] A generative AI model is used to generate summaries of "The 7 Habits" and add them to the catalog.

[0749] Users select "The 7 Habits" from the catalog and receive a summary and checklist.

[0750] Checklist example:

[0751] [ ] Did you self-assess daily?

[0752] [ ] Have you made one independent decision a day?

[0753] The user records their daily activities and sends the data from the terminal to the server.

[0754] The emotion engine recognizes the user's emotional state in real time and transmits the emotion data to the server.

[0755] The server analyzes the recorded data and emotional data, generates feedback such as, "Today's self-evaluation is good, but you lack independent decision-making. Try harder," and presents it to the user via the device.

[0756] In this way, a system for improving the efficiency of self-development is constructed, allowing users to continuously and efficiently practice self-development. By combining it with an emotion engine, feedback that takes into account the user's emotional state becomes possible, resulting in more personalized responses.

[0757] The processing flow will be explained below.

[0758] The present invention relates to a self-development efficiency improvement system that uses a generative AI model and an emotion engine. This system is implemented as follows.

[0759] Overall processing steps of the system

[0760] Step 1:

[0761] The server accesses the API of the e-book platform to obtain the text data of the self-help book. Specifically, it sends an API request specifying the book ID and extracts the text data from the JSON response.

[0762] Step 2:

[0763] The server tokenizes the text data it receives. Using a natural language processing library (e.g., NLTK or SpaCy), it splits the text into words and punctuation marks and converts them into a list.

[0764] Step 3:

[0765] The server cleans the tokenized data, removing unnecessary tags, line breaks, and whitespace, and using regular expressions to remove specific string patterns.

[0766] Step 4:

[0767] The server uses a generative AI model to generate a summary from the cleaned data. For example, it inputs text data into a GPT model and generates a summary that extracts key points.

[0768] Step 5:

[0769] The server catalogs the generated summaries, storing them in JSON format and indexing them using the self-help book metadata (title, author, publication year).

[0770] Step 6:

[0771] The server extracts actionable points from the summary, using natural language processing to pick out verbs and important guidelines from the book summary and create a list of specific action items.

[0772] Step 7:

[0773] The server generates a checklist based on the extracted practices. The checklist contains specific actions that users should take each day. The checklist is saved in JSON format.

[0774] Step 8:

[0775] The device displays a list of cataloged self-help books to the user, and the user interface also includes a search function to allow the user to easily find self-help books that interest them.

[0776] Step 9:

[0777] A user selects a self-help book, for example, "The 7 Habits," and then checks the summary and checklist on the book's details page.

[0778] Step 10:

[0779] The device presents the user with a summary and checklist of the selected self-help book, and the user reads the summary and checks the checklist within the application.

[0780] Step 11:

[0781] Users record their daily activities based on a checklist, tapping a checkbox to indicate whether a task is completed or not.

[0782] Step 12:

[0783] The device sends the user's practice record to the server, where the record data is sent in JSON format and stored.

[0784] Step 13:

[0785] The emotion engine analyzes user input, facial expressions, and vocal tones to recognize emotions. It uses cameras and microphones to collect data in real time and applies emotion analysis algorithms.

[0786] Step 14:

[0787] The server integrates and analyzes the user's practice records and emotional data, using a feedback algorithm that takes into account the user's emotional state.

[0788] Step 15:

[0789] The server generates feedback based on the analysis results, such as "Your self-evaluation today is good, but you lack proactive decision-making. Please act more consciously."

[0790] Step 16:

[0791] The device presents the generated feedback to the user, which is displayed in a message screen within the application.

[0792] The above processing steps create a system that can improve the efficiency of self-development and provide personalized feedback. Users can continuously and efficiently practice self-development, resulting in better results.

[0793] Example 2

[0794] 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."

[0795] In the past, it was difficult for users to efficiently extract the main points of each book and create an appropriate practice plan. In addition, there was a lack of feedback that took into account the user's emotional state, which resulted in a decrease in the effectiveness of the self-help book.

[0796] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring self-help book data, means for tokenizing and cleaning the acquired data, means for generating a summary from the tokenized data using a generative AI model, means for organizing the summarized content in a catalog format, means for extracting specific practice points from the summary and generating a checklist, means for analyzing a user's input, facial expressions, and voice to recognize emotions, means for analyzing the user's practice status and emotional data and generating feedback, and means for presenting the generated feedback to the user. This makes it possible to efficiently extract the key points of a self-help book and provide the user with feedback that takes into account their emotional state.

[0797] "Self-help book data" is data that includes text information of books related to self-help.

[0798] "Means for obtaining" refers to a function or device for obtaining necessary data from an external data source.

[0799] "Tokenization" is the process of dividing text data into its smallest units, such as words and punctuation marks.

[0800] "Cleaning means" refers to a process of arranging data by removing unnecessary tags, line breaks, and spaces from text data.

[0801] A "generative AI model" is an artificial intelligence model that uses natural language processing technology to summarize and generate text data.

[0802] The "means for generating summaries" is a function that uses a generative AI model to extract key points from text data and present them in a concise format.

[0803] The "means for organizing in a catalog format" is a means for storing summarized data in a specific structure and organizing it so that the user can easily access it.

[0804] The "means for extracting action items" is a function that identifies specific guidelines and verbs from summary data and extracts them as items to be put into practice.

[0805] The "means for generating a checklist" is a function that lists action items to be carried out based on the extracted practice items.

[0806] "User input" refers to information or data provided by a user, such as text entry or selection actions.

[0807] "Facial expression" refers to the user's facial movements and expressive state.

[0808] "Voice" refers to the state of a user's voice, including their tone and emotions.

[0809] The "means for recognizing emotions" is a function that analyzes the user's facial expressions and voice to identify their emotional state.

[0810] "Recording practice items" refers to the user recording the results of their daily practice.

[0811] The "means for generating feedback" is a function that creates feedback including areas for improvement and progress based on the user's practice data and emotional state.

[0812] The "means for presenting feedback" is a function for displaying the generated feedback to the user.

[0813] The present invention relates to a self-help efficiency improvement system that uses a generative AI model and an emotion engine. This system automates the process from acquiring self-help book data to providing feedback to users. Specific embodiments are described below.

[0814] Hardware and Software Use

[0815] The system mainly consists of a server, a terminal, and an emotion engine.

[0816] 1. Server Operation

[0817] Get book data:

[0818] The server accesses the API of the e-book platform to retrieve the text data of the self-help book. At this time, it sends a request using the Python requests library, and the data is saved in JSON format.

[0819] Tokenize and clean data:

[0820] The server tokenizes the retrieved data using a natural language processing library (e.g., NLTK or spaCy), and the cleaning process uses a regular expression library to remove unnecessary tags, line breaks, and whitespace.

[0821] Summary generation using generative AI models:

[0822] The server uses a generative AI model (e.g., OpenAI's GPT-3) to send the data along with the prompt and generate a summary, which is stored in a variable for later processing.

[0823] Abstract Cataloging:

[0824] The server organizes the summaries into a catalog, stored in JSON format, that includes the book title, author, and key points of the summary.

[0825] Extraction of practices and generation of checklists:

[0826] The server extracts action items (e.g., verbs and guidelines) from the summary text and lists them as a checklist.

[0827] 2. Operation of the Emotion Engine

[0828] The emotion engine uses a camera and microphone to capture the user's facial expressions and voice. This data is analyzed in real time to evaluate the user's emotional state. Specifically, it uses technologies such as OpenFace and TensorFlow.

[0829] 3. Device Operation

[0830] Browse the catalogue:

[0831] A user can browse a catalog of self-help books stored on a server through a dedicated application, select an appropriate book, and view its summary and checklist.

[0832] Present and record the checklist:

[0833] The terminal displays a summary of the selected book and a checklist to the user, who then records his or her daily activities based on the checklist and sends the data to the server.

[0834] 4. Generating and Presenting Feedback

[0835] Analysis of recorded data:

[0836] The server analyzes the practice records entered by the user using machine learning models and statistical methods, and also uses emotional data from the emotion engine to generate feedback that takes the user's emotional state into account.

[0837] Giving feedback:

[0838] The device presents the user with feedback sent from the server, including information about progress and areas for improvement.

[0839] Specific examples

[0840] For example, if a user chooses "The 7 Habits" as a self-help book, the server retrieves the book's data, tokenizes and cleans it, then uses GPT-3 to generate a summary and add it to the catalog. The user selects "The 7 Habits" from the catalog and receives the summary and checklist.

[0841] Checklist example:

[0842] [ ] Did you self-assess every day?

[0843] [ ] Did you make an independent decision?

[0844] Example of a generated AI prompt:

[0845] Please write a summary of "The 7 Habits" in the following format:

[0846] Key points of this book

[0847] Key Action Items

[0848] Practical Tips

[0849] Text: <insert text here>

[0850] In this way, a system for improving the efficiency of self-development is constructed, supporting users in practicing self-development continuously and effectively.By combining it with an emotion engine, it becomes possible to provide personalized feedback according to the user's emotional state.

[0851] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0852] Step 1:

[0853] The server accesses the API of the e-book platform and retrieves the text data of the self-help book. The API endpoint URL and access credentials are used as input, and the retrieved book data (JSON format) is output. Specifically, it sends a request to the API using the Python requests library (e.g., response = requests.get(API_URL, headers=headers)) and saves the retrieved data in JSON format (e.g., book_data = response.json()).

[0854] Step 2:

[0855] The server tokenizes and cleans the acquired book data. The acquired book data is used as input, and the output is the tokenized and cleaned data. Specifically, it uses a natural language processing library such as NLTK to split the text into words and punctuation marks (tokenization), and uses Python's regular expression library to remove unnecessary tags, line breaks, and spaces (e.g., clean_text = re.sub(r'\s+', ' ', book_data["text"])).

[0856] Step 3:

[0857] The server uses a generative AI model to generate a summary from the tokenized and cleaned data. It uses the cleaned text data and a prompt as input, and outputs the summary text. Specifically, it uses OpenAI's API to send the data along with the prompt (e.g., response = openai.Completion.create(engine="text-davinci-003", prompt=prompt, max_tokens=150)) and stores the generated summary in a variable (e.g., summary = response.choices[0].text.strip()).

[0858] Step 4:

[0859] The server organizes the summarized self-help books into a catalog. It takes the summary text and basic book information (title, author, etc.) as input, and outputs a catalog entry in JSON format. Specifically, it generates a data structure containing the summary text (e.g., catalog_entry = {"title": book_title, "author": book_author, "summary": summary}) and stores it in the database.

[0860] Step 5:

[0861] The server extracts specific actions from the summary and generates a checklist. The input is the summary text, and the output is a checklist. Specifically, it uses a text analysis algorithm to extract verbs and action points from the summary (e.g., actions = extract_actions_from_summary(summary)), and then creates a list of them (e.g., checklist = create_checklist(actions)).

[0862] Step 6:

[0863] The emotion engine analyzes user input, facial expressions, and vocal sounds to recognize emotions. It uses real-time facial and vocal data obtained from a camera and microphone as input, and outputs emotional data. Specifically, it uses OpenFace for facial recognition (e.g., emotion_face = analyze_facial_expression(image)) and TensorFlow for vocal analysis (e.g., emotion_voice = analyze_voice(voice_clip)).

[0864] Step 7:

[0865] The user browses a catalog of self-help books through a dedicated application, and selects and views the summary and checklist of a self-help book. The input is the catalog data stored on the server, and the output is the summary and checklist displayed to the user. Specifically, the mobile application displays the catalog screen, and retrieves and displays the self-help book data selected by the user.

[0866] Step 8:

[0867] The user records daily practice items based on the checklist, and the device sends the data to the server. The input is the practice data recorded by the user, and the output is the record data sent to the server. The specific operation is that the user enters data in the mobile application and sends the data to the server (e.g., send_to_server(record_data)).

[0868] Step 9:

[0869] The server analyzes the user's practice record and emotion data and generates feedback. It uses practice record data and emotion data as input, and outputs a feedback message. Specifically, it analyzes the data using machine learning models and statistical methods (e.g., feedback = generate_feedback(user_data, emotion_data)) and generates appropriate feedback.

[0870] Step 10:

[0871] The terminal presents the generated feedback to the user. The input is the feedback message sent from the server, and the output is the feedback displayed to the user. Specifically, the feedback is displayed on a message screen within the mobile application.

[0872] (Application example 2)

[0873] 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."

[0874] Conventional self-improvement support systems specialize in generating summaries and providing checklists to promote user growth, but lack the ability to generate feedback that takes into account the user's emotional state. As a result, they are unable to provide personalized feedback based on emotions that would help users maintain their self-improvement behavior. Furthermore, in the food delivery industry, there is a lack of systems that support self-improvement for delivery workers while they are working.

[0875] 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.

[0876] In this invention, the server includes means for acquiring self-help book data, means for tokenizing and cleaning the acquired data, means for generating summaries from the tokenized data using a generative AI model, means for organizing the summarized content in a catalog format, means for accepting a user's selection of a self-help book, means for presenting summaries and checklists of the selected self-help book, means for receiving a record of the user's practice, means for analyzing the practice status and generating feedback, means for presenting the generated feedback to the user, means for analyzing the user's emotional state, and means for adjusting the content of the feedback based on the user's emotional state. This makes it possible to provide personalized feedback based on the user's practice status and emotional state, allowing food delivery workers to efficiently engage in self-improvement while on the job.

[0877] "Self-help book data" is digital data of books and documents used as self-help books.

[0878] "Tokenization" is the process of dividing text data into smaller units such as words and punctuation marks.

[0879] "Cleaning" is the process of removing unnecessary tags, line breaks, and spaces from data to prepare it in a format that is easy to analyze.

[0880] A "generative AI model" is an algorithm or program that uses AI to generate natural language and summaries.

[0881] A "summary" is a short summary of the main points or content of a text or book.

[0882] "Catalog format" is a format in which information is organized and displayed by items such as title, author, and main points.

[0883] A "checklist" is a list of action items that a user should take.

[0884] "Feedback" is information such as suggestions for improvement or advice generated based on the practice situation and emotional state.

[0885] "Means for analyzing emotional state" refers to a method or system for analyzing emotions from the user's facial expressions, voice, etc.

[0886] The "means for adjusting the content of feedback based on emotional state" refers to a method or system that changes the feedback provided depending on the analyzed emotion.

[0887] This invention is a system for supporting users' self-development by efficiently utilizing the contents of self-help books, and is particularly targeted at delivery workers in the food delivery industry. This system is implemented using hardware and software including a server, a terminal, an emotion engine, a camera, and a microphone.

[0888] The server retrieves self-help book data from the e-book platform, tokenizes and cleans it, and then uses the tokenized data to generate summaries using a generative AI model. This generative AI model applies the GPT series of natural language generation models. The summaries are then organized into a catalog and saved in JSON format. This allows for efficient management of information and makes it easy for users to access.

[0889] Next, the device (e.g., a smartphone application) accepts user input. The user selects the desired book from a catalog of self-help books and receives a summary and a checklist. The checklist includes specific action items to be put into practice. The user records the actions they take each day and sends the data from the device to a server. For example, the checklist might include action items such as "Have you performed self-evaluation every day?" or "Have you made one independent decision per day?"

[0890] Furthermore, the emotion engine analyzes the user's emotional state using a camera and microphone. This analyzed emotional data is sent to a server, which generates feedback based on the user's progress and emotional state. The feedback includes personalized advice that takes the user's emotions into account, making it easier for the user to continue their self-improvement activities.

[0891] For example, if a delivery person opens the app and selects "The 7 Habits," the server retrieves the book's data, tokenizes it, and cleans it. A generative AI model then generates a summary and adds it to the catalog. The delivery person retrieves this summary from the catalog and records their actions based on a daily checklist. Meanwhile, an emotion engine recognizes the delivery person's emotional state from their facial expressions and tone of voice, and sends this data to the server. Based on the recorded data and emotion data, the server generates feedback such as, "Today's self-evaluation is good, but your independent decision-making skills are lacking. You need to work harder," and presents it to the delivery person via their device.

[0892] In this way, this invention is a system that supports users in continuing to work on self-improvement by streamlining the use of self-help books and providing personalized feedback that takes into account their emotional state. This system allows delivery workers, particularly in the food delivery industry, to efficiently engage in self-improvement while at work.

[0893] Examples of prompts:

[0894] "Set your goals for today as 'Perform daily self-evaluation' and 'Make independent decisions.' Judging from your emotional state, you seem a little tired today. Take a break and complete the practical tasks."

[0895] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0896] Step 1:

[0897] The server retrieves self-help book data using the API of the e-book platform. The input is the book ID, and the data retrieved from the API includes the book's text content. Specifically, the server sends an HTTP request and receives the e-book data. The output is the retrieved book data.

[0898] Step 2:

[0899] The server tokenizes and cleans the acquired book data. The input is the book data, and a natural language processing library is used to split the data into words and punctuation marks, and remove unnecessary characters and tags. Specifically, the server uses an NLP library to perform tokenization and regular expressions to perform cleaning. The output is the tokenized and cleaned data.

[0900] Step 3:

[0901] The server generates a summary using a generative AI model based on the tokenized and cleaned data. The input is the tokenized data, and the generative AI model (e.g., GPT sequence) extracts important content and generates a summary. Specifically, the server inputs the tokenized data into the generative AI model and receives the summary generated by the model. The output is the summarized text.

[0902] Step 4:

[0903] The server organizes the generated summary text into a catalog format. The input is the summary text, which is converted into JSON format for each item, such as title, author, and main points. Specifically, the server parses the summary text and creates a data structure corresponding to each item. The output is JSON data in catalog format.

[0904] Step 5:

[0905] The terminal accepts the user's selection of a self-help book. The input is the user's selection information, and based on that information, it presents a summary and checklist of the corresponding book from the catalog. In concrete terms, the terminal receives the user's input, retrieves the corresponding data, and displays it. The output is the summary and checklist presented to the user.

[0906] Step 6:

[0907] The user records the actions based on the checklist. The input is the user's recorded information, which is sent from the terminal to the server. In concrete terms, the user records an action item, and the terminal sends the information to the backend. The output is the action record stored on the server.

[0908] Step 7:

[0909] The emotion engine analyzes the user's emotional state using a camera and microphone. The input is the user's facial expression and vocal data, and the emotional state is evaluated through analysis. Specifically, the emotion engine acquires data from the camera and microphone and analyzes it using a machine learning algorithm. The output is evaluated emotional data.

[0910] Step 8:

[0911] The server generates feedback based on practice status data and emotion data and presents it to the user. The input is practice record data and emotion data, which are analyzed using machine learning models and statistical methods to generate personalized feedback. Specifically, the server summarizes the analysis results, generates a feedback message, and sends it to the terminal. The output is the feedback message presented to the user.

[0912] 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.

[0913] 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.

[0914] 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.

[0915] [Third embodiment]

[0916] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0917] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0918] 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).

[0919] 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.

[0920] 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.

[0921] 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).

[0922] 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.

[0923] 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.

[0924] 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.

[0925] 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.

[0926] 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.

[0927] 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."

[0928] The present invention relates to a self-development efficiency improvement system using a generative AI model. This system is implemented as follows.

[0929] Overall system operation

[0930] 1. Acquisition and preprocessing of book data

[0931] The server retrieves data on self-help books from an e-book platform, which mainly contains text information.

[0932] The server tokenizes and cleans the data it receives, removing unnecessary tags and line breaks and splitting sentences into tokens using a natural language processing library.

[0933] 2. Summary generation using generative AI models

[0934] The server uses a generative AI model to summarize the content from the tokenized book data, such as a GPT-based natural language generation model.

[0935] The summarized text is saved in storage for later processing.

[0936] 3. Cataloging Abstracts

[0937] The server organizes the summarized self-help books into a catalog, where each summary is stored in JSON format, including the book's title, author, main points, etc.

[0938] 4. Extraction of practical matters and generation of checklists

[0939] The server extracts concrete actionable information from the summaries, which involves natural language processing to extract verbs and key actions from the book summaries.

[0940] Based on the extracted practices, the server generates a checklist that includes daily tasks and action items.

[0941] 5. User Interaction

[0942] Users can browse a catalog of self-help books through a dedicated application, check the summaries and effects of each book, and select the book that best suits them.

[0943] The terminal presents the user with a summary of the selected self-help book and a checklist, which the user can use for daily practice.

[0944] Users record their daily practices within the application, checking off action items such as whether they performed a self-assessment or made an independent decision.

[0945] The terminal sends the user's input to the server.

[0946] 6. Generating and Presenting Feedback

[0947] The server analyzes the user's practice records and generates feedback on their performance and areas for improvement.

[0948] The server then presents the generated feedback to the user via a dedicated application, including advice on next steps and further improvements.

[0949] Specific examples

[0950] For example, if you have a self-help book called "The 7 Habits":

[0951] The server retrieves the 7 Habits data, tokenizes it, and cleans it.

[0952] A generative AI model is used to generate summaries of "The 7 Habits" and add them to the catalog.

[0953] Users select "The 7 Habits" from the catalog and receive a summary and checklist.

[0954] Checklist example:

[0955] [ ] Did you self-assess daily?

[0956] [ ] Have you made one independent decision a day?

[0957] The user records their daily activities and sends the data from the terminal to the server.

[0958] The server analyzes the recorded data and generates feedback such as, "To further increase your independent decision-making, act consciously the next day," which is presented to the user via the device.

[0959] In this way, a system for improving the efficiency of self-development is constructed, allowing users to practice self-development continuously and efficiently.

[0960] The processing flow will be explained below.

[0961] Step 1:

[0962] The server accesses the API of the e-book platform to retrieve the text data of the self-help book, along with the book's metadata (title, author, publication year, etc.).

[0963] Step 2:

[0964] The server tokenizes the acquired book data. Specifically, it uses a natural language processing library to split the text into words and punctuation marks, and converts them into a data structure (e.g., an array).

[0965] Step 3:

[0966] The server cleans the tokenized data, removing unnecessary tags, line breaks, and whitespace, and formatting the text data to make it easier to parse.

[0967] Step 4:

[0968] The server generates summaries from the tokenized and cleaned data using a generative AI model, which is a pre-trained natural language generation model.

[0969] Step 5:

[0970] The server catalogs the generated summaries. It stores each self-help book summary in JSON format, creating a searchable and filterable catalog.

[0971] Step 6:

[0972] The server extracts actionable points from the summary, using natural language processing to pick out verbs and important guidelines from the summary and create a list.

[0973] Step 7:

[0974] The server generates a checklist based on the extracted practices, which includes specific action items that users should perform daily.

[0975] Step 8:

[0976] The terminal displays a list of cataloged self-help books to the user, and the user selects a self-help book from the catalog.

[0977] Step 9:

[0978] The device presents the user with a summary and checklist of the selected self-help book, which are displayed on a dedicated screen within the application.

[0979] Step 10:

[0980] The user records the daily activities based on the checklist, and fills in the status of the activities by checking the boxes.

[0981] Step 11:

[0982] The device sends the user's practice record to the server. The recorded data is sent in JSON format.

[0983] Step 12:

[0984] The server analyzes the user's practice records using machine learning models and statistical methods.

[0985] Step 13:

[0986] The server generates feedback based on the analysis results, including the user's progress and areas for improvement.

[0987] Step 14:

[0988] The device presents the generated feedback to the user, which is displayed in a message screen within the application.

[0989] Example 1

[0990] 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."

[0991] There is a need to efficiently understand the contents of self-help books and incorporate their practical tips into daily life. However, self-help books cover a wide range of topics, and it takes time and effort to read, understand, and practice each book. Furthermore, a lack of records and feedback on practical tips makes it difficult to improve the sustainability and effectiveness of self-help. The present invention aims to solve these problems by generating summaries of self-help books, suggesting practical ideas, and automatically recording and providing feedback, thereby providing a system that allows users to efficiently practice self-help.

[0992] 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.

[0993] In this invention, the server includes means for acquiring e-book data, means for tokenizing and cleaning the acquired data, means for generating summaries from the tokenized data using a generative model, means for organizing the summarized content in a catalog format, means for extracting practice points from the summaries and generating a checklist, means for accepting a user's book selection, means for presenting summaries and checklists for the selected books, means for receiving a record of the user's practice points, means for analyzing the practice points and generating feedback, and means for presenting the generated feedback to the user. This allows users to efficiently understand the contents of a wide range of self-help books in a summarized format and easily incorporate the practice points into their daily lives. Furthermore, the practice records and feedback can enable continuous self-help practice and improved effectiveness.

[0994] A "server" is a central processing unit that processes data and provides information upon receiving a request from a client.

[0995] "E-book data" refers to the content information of a book that is stored in digital format and can be displayed and viewed through electronic media.

[0996] "Tokenization" is the process of dividing text data into useful units (words and phrases) for natural language processing.

[0997] "Cleaning" is the process of removing unnecessary elements and errors from data and preparing it in a format suitable for analysis.

[0998] A "generative model" is an algorithm or system that uses artificial intelligence technology to process natural language and generate new text.

[0999] A "summary" is a concise summary of the main information in the original text data.

[1000] The "catalog format" is a format that allows a large number of items to be systematically organized and classified so that they can be displayed in a list.

[1001] "Practical matters" are specific actions or tasks that should actually be carried out based on the self-help book.

[1002] A "checklist" is a list organized by item to check and record practice matters.

[1003] A "user" is an individual who uses the system to refer to summaries and practical matters in self-help books and engage in self-improvement.

[1004] "Selection" is the act of choosing a particular item or option from a number of items or options.

[1005] "Recording" is the act of saving and retaining certain events or actions as data.

[1006] "Feedback" is information that provides evaluations and advice on a user's actions and results.

[1007] "Presenting" is the act of showing information to a user visually or audibly.

[1008] MODE FOR CARRYING OUT THE INVENTION

[1009] The present invention relates to a self-development efficiency improvement system using a generative AI model, and this system is implemented as follows.

[1010] Acquiring and preprocessing book data

[1011] The server first uses the API of the e-book platform to obtain data on self-help books. This data is mainly text information, and APIs such as Amazon Kindle and Google Books are used to obtain the data. The obtained text data is tokenized using a natural language processing library (e.g., NLTK or spaCy), and then cleaned by removing unnecessary tags and line breaks.

[1012] Summary Generation

[1013] The server uses a generative AI model (e.g., the GPT series) to generate a summary of the contents from the tokenized book data, which is then stored in storage for further processing.

[1014] Abstract Cataloging

[1015] The server organizes the summarized data of self-help books into a catalog. Each summary is saved in JSON format, including the book's title, author, main points, etc. This catalog serves as a reference for users when selecting a self-help book.

[1016] Extraction of practical matters and generation of checklists

[1017] The server uses natural language processing technology to extract specific actions from the summary, which then generates a checklist containing tasks and action items that the user should perform each day.

[1018] User Interaction

[1019] The user uses a dedicated application to browse a catalog of self-help books and select the book that best suits them. Based on this, the device presents the user with a summary of the selected book and a checklist. The user then uses this checklist as a reference for their daily practice.

[1020] Recording and feedback on practice matters

[1021] Users record their daily activities within the application and check off action items such as "Did I perform self-evaluation?" or "Did I make independent decisions?" The device sends the user's input data to the server. The server analyzes the recorded data and generates feedback on achievements and areas for improvement. The generated feedback is presented to the user via a dedicated application.

[1022] Specific examples

[1023] For example, taking the self-help book "The 7 Habits," the server first retrieves the data for "The 7 Habits" from the e-book platform, tokenizes it, and cleans it. The server then uses a generative AI model to generate a summary of "The 7 Habits" and adds it to the catalog. The user then selects "The 7 Habits" from the catalog in a dedicated application and receives the summary and checklist from the server.

[1024] Checklist example:

[1025] [ ] Did you self-assess daily?

[1026] [ ] Have you made one independent decision a day?

[1027] Users record their daily actions and send the data from their device to the server. The server analyzes the recorded data and generates specific feedback, such as "To further increase your independent decision-making, act consciously the next day," and presents it to the user via their device.

[1028] Prompt Sentence Examples

[1029] Summarize the 7 Habits, including a description of each habit and how it contributes to personal growth.

[1030] In this way, the system of the present invention provides users with an efficient means of self-improvement. The specific details of the process are realized by the cooperative operation of the server and the terminal.

[1031] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1032] Step 1:

[1033] The server uses the API of the e-book platform to obtain the text data of the self-help book.

[1034] Input: Your eBook platform API key and book identifier.

[1035] Output: Raw text data of the book.

[1036] Specific operation: The server sends an API request and receives the book's text data as a response.

[1037] Step 2:

[1038] The text data retrieved by the server is tokenized and cleaned.

[1039] Input: Raw text data.

[1040] Output: Tokenized and cleaned text data.

[1041] What it does: Uses a natural language processing library (e.g., NLTK or spaCy) to split text into words and phrases, and removes unnecessary tags and line breaks.

[1042] Step 3:

[1043] The server uses a generative AI model (e.g., GPT series) to generate summaries from the tokenized data.

[1044] Input: Tokenized and cleaned text data.

[1045] Output: A text summary of the book.

[1046] How it works: A prompt sentence is input into the generative AI model to generate a summary text. The prompt sentence contains the information that forms the basis of the summary.

[1047] Step 4:

[1048] The server organizes the generated summaries into a catalog and stores them in JSON format.

[1049] Input: Book summary text.

[1050] Output: JSON data in catalog format.

[1051] Specific operation: The summary text is converted into JSON format along with information such as the book title, author, and main points, and saved to storage.

[1052] Step 5:

[1053] The server extracts specific practice items from the summary and generates a checklist.

[1054] Input: Book summary text.

[1055] Output: A checklist with action points.

[1056] Specific actions: Using natural language processing technology, verbs and important guidelines for action are extracted from the summary text, and a checklist is created based on them.

[1057] Step 6:

[1058] A user uses a dedicated application to browse a catalog of self-help books and select a book.

[1059] Input: Catalog data.

[1060] Output: User's book selection information.

[1061] Specific operation: Display a catalog on the application screen and allow the user to select the book they want to read.

[1062] Step 7:

[1063] The terminal presents the user with summaries and checklists for the selected books.

[1064] Input: User's book selection information.

[1065] Output: Summary text and checklist.

[1066] Specific behavior: The summary and checklist are displayed on the application screen for the user to refer to.

[1067] Step 8:

[1068] Users record their daily practices and check off checklists within the application.

[1069] Input: User's practice record.

[1070] Output: Recorded practice data.

[1071] What it does: Record an action by tapping on a checklist item within the app.

[1072] Step 9:

[1073] The terminal transmits the user's input data to the server.

[1074] Input: Recorded practice data.

[1075] Output: Practice data sent to the server.

[1076] Specific behavior: The application sends data to the server as a POST request.

[1077] Step 10:

[1078] The server analyzes the recorded data and generates feedback on success and areas for improvement.

[1079] Input: Practice data sent to the server.

[1080] Output: Feedback text.

[1081] What it does: Performs statistical analysis and generates feedback based on user behavior patterns.

[1082] Step 11:

[1083] The server generates feedback and presents it to the user via a dedicated application.

[1084] Input: Feedback text.

[1085] Output: The feedback presented to the user.

[1086] Specific behavior: The feedback text is displayed on the application screen.

[1087] (Application example 1)

[1088] 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."

[1089] There is a need for a system that can streamline learning based on self-help books and enable users to continuously practice self-improvement based on their experiences and purchases in physical stores. Another issue is the lack of a means to effectively provide feedback based on the participation history of store events.

[1090] 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.

[1091] In this invention, the server includes means for acquiring self-improvement data, means for tokenizing and cleaning the acquired data, and means for generating summaries from the tokenized data using a generative AI model, thereby providing users with summaries and practice checklists based on their experiences and purchases in physical stores and providing feedback based on their participation in store events.

[1092] "Self-improvement data" is data that contains information to promote self-improvement and efficient learning.

[1093] A "generative AI model" is an artificial intelligence model that uses natural language processing to generatively create output from input data.

[1094] "Tokenization" is the process of dividing a sentence into certain linguistic units.

[1095] "Cleaning" is the process of removing unnecessary information and noise from data and organizing it.

[1096] A "summary" is information that briefly and condenses the essence of self-help data.

[1097] "Catalog format" is a method of organizing information by category and displaying it in a list format.

[1098] A "self-improvement guide" is a guide to promoting self-growth and goal achievement.

[1099] A "checklist" is a list of items to check the performance of a specific action or task.

[1100] "Practices" refer to the actions or tasks that users should actually undertake.

[1101] "Feedback" is information that provides evaluations and advice based on the user's actions.

[1102] A "physical store" is a commercial facility that a user can physically visit.

[1103] "Store Events" are activities or events held at physical stores with a specific theme or purpose.

[1104] "Participation history" is a record of events and activities that a user has participated in in the past.

[1105] This invention relates to a self-improvement efficiency system that uses a generative AI model to provide summaries and practice checklists based on experiences and purchases in physical stores, and provides feedback based on participation history in store events.

[1106] System configuration and operation

[1107] The server includes the following means:

[1108] 1. Obtaining self-development data:

[1109] The server acquires data on self-help books from the e-book platform, which mainly contains text information.

[1110] 2. Tokenize and clean the data:

[1111] The server tokenizes and cleans the data it receives, which includes using natural language processing libraries to tokenize sentences and remove unnecessary tags and line breaks.

[1112] 3. Summary generation using generative AI models:

[1113] The server uses a generative AI model (e.g., a GPT-based natural language generation model) to summarize the content from the tokenized book data, and the summarized text is stored in storage for later processing.

[1114] 4. Cataloging Abstracts:

[1115] The server organizes the summarized self-help books into a catalog, with each summary stored in a format that includes the book's title, author, main points, etc.

[1116] 5. Extraction of practice items and generation of checklists:

[1117] The server extracts specific actions from the summary, which involves natural language processing to extract verbs and key actions from the book summary, and then generates a checklist based on the extracted actions.

[1118] 6. User interaction:

[1119] The user browses a catalog of self-help books through a dedicated application (smartphone, smart glasses, head-mounted display, etc.). The user checks the summary and effects and selects a self-help guidebook. The device then presents the selected summary and checklist to the user.

[1120] 7. In-store experience and purchase assistance:

[1121] Based on in-store experiences and purchases, the presented summary and checklist are updated to guide the user through their actions.

[1122] 8. Providing feedback on in-store events:

[1123] Based on the user's history of participating in store events, the server generates feedback and provides it to the user via a dedicated application, including advice on next steps and further improvements.

[1124] Example

[1125] For example, if you have a self-help book called "The 7 Habits":

[1126] The server retrieves the 7 Habits data, tokenizes it, and cleans it.

[1127] Use a generative AI model (e.g., GPT series) to generate summaries of "The 7 Habits" and add them to the catalog.

[1128] Users select "The 7 Habits" from the catalog and receive a summary and checklist.

[1129] Checklist example:

[1130] [ ] Did you self-assess daily?

[1131] [ ] Have you made one independent decision a day?

[1132] As users purchase products based on the 7 Habits in physical stores, the summary and checklist are updated.

[1133] The user records their daily activities and sends the data from the terminal to the server.

[1134] The server analyzes the recorded data and generates feedback such as, "To make more independent decisions, act consciously the next day," which is presented to the user via the device.

[1135] Examples of prompt statements

[1136] A prompt to generate a summary of a self-help book might look like this:

[1137] "Summarize the following self-help books:"

[1138] The prompt to extract the practice items is as follows:

[1139] "Please create a checklist by extracting the practical points from the summary below:"

[1140] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1141] Step 1:

[1142] The server retrieves self-help data. This is the process of collecting text data from an e-book platform. This process uses the e-book API to request specific book data and retrieve it in text format. The input requires the e-book's book ID and API key, and the output is the book's text data.

[1143] Step 2:

[1144] The server tokenizes and cleans the acquired self-help data. This process uses a natural language processing library to remove unnecessary tags and line breaks from the text data and further divides it into tokens. The input is the book text data, and the output is the cleaned tokenized data.

[1145] Step 3:

[1146] The server generates a summary from the tokenized data using a generative AI model. This process involves providing a prompt sentence to a generative AI model (e.g., GPT) to create a summary. It requires cleaned tokenized data and a prompt sentence as input, and obtains the summarized text as output.

[1147] Step 4:

[1148] The server organizes the summarized content into a catalog, a process that formats the summarized text and stores it as a catalog entry, using the summarized text as input and obtaining catalog-formatted data as output.

[1149] Step 5:

[1150] The terminal accepts the user's selection of a self-help book. In this process, the user browses the catalog and makes a selection through a dedicated application. The input is catalog data, and the output is the user's selection information.

[1151] Step 6:

[1152] The terminal presents a summary and checklist for the selected self-help book. This process displays the summary data and checklist selected by the user on the screen. It uses the user's selection and associated summary data as input and obtains a screen display as output.

[1153] Step 7:

[1154] The terminal receives the record of the user's actions. In this process, the user records the actions based on the checklist. The user's input data is used as input, and the record data is obtained as output.

[1155] Step 8:

[1156] The server analyzes the user's practice and generates feedback. This process involves analyzing the user's recorded data and creating feedback using a generative AI model. The recorded data and prompt text are used as input, and the feedback text is obtained as output.

[1157] Step 9:

[1158] The terminal presents the generated feedback to the user. This process displays the generated feedback on the user's terminal screen, using the feedback text as input and obtaining a screen display as output.

[1159] Step 10:

[1160] The server includes means for providing a summary and a checklist of actions based on the experience and purchases at the physical store. The process utilizes the purchase history and experience information at the physical store to provide the summary and checklist optimized for the user. The process uses the purchase history and experience information as input and obtains the personalized summary and checklist as output.

[1161] Step 11:

[1162] The terminal provides feedback based on the participation history of store events. In this process, the terminal refers to the participation history of store events and presents feedback to the user. The participation history is used as input and a feedback display is obtained as output.

[1163] 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.

[1164] The present invention relates to a self-development efficiency improvement system that uses a generative AI model and an emotion engine. This system is implemented as follows.

[1165] Overall system operation

[1166] 1. Acquisition and preprocessing of book data

[1167] The server accesses the API of the e-book platform to retrieve the text data of the self-help book, which mainly contains text information.

[1168] The server tokenizes the data it receives, specifically by using a natural language processing library to split the text into words and punctuation marks, and converts them into a data structure (e.g., an array).

[1169] The server cleans the tokenized data, removing unnecessary tags, line breaks, and whitespace, and formatting the text data to make it easier to parse.

[1170] 2. Summary generation using generative AI models

[1171] The server generates summaries from the tokenized and cleaned data using a generative AI model, such as a GPT-based natural language generation model.

[1172] The summarized text is saved in storage for later processing.

[1173] 3. Cataloging Abstracts

[1174] The server organizes the summarized self-help books into a catalog, where each summary is stored in JSON format, including the book's title, author, main points, etc.

[1175] 4. Extraction of practical matters and generation of checklists

[1176] The server extracts concrete actionable information from the summaries, which involves natural language processing to extract verbs and key actions from the book summaries.

[1177] Based on the extracted practices, the server generates a checklist, which includes specific action items that the user should perform daily.

[1178] 5. Emotion Recognition by Emotion Engine

[1179] The emotion engine analyzes the user's input, facial expressions, and voice to recognize emotions. Specifically, it uses a camera and microphone to analyze the user's facial expressions and voice in real time and evaluates their emotional state.

[1180] These emotional data are used to deepen understanding of the user's practice situation and improve the quality of feedback.

[1181] 6. User Interaction

[1182] Users can browse a catalog of self-help books through a dedicated application, check the summaries and effects of each book, and select the book that best suits them.

[1183] The device presents the user with a summary and checklist of the selected self-help book, which are displayed on a dedicated screen within the application.

[1184] Users record their daily actions based on a checklist, such as whether they performed a self-assessment or made an independent decision.

[1185] The terminal sends the user's input to the server.

[1186] 7. Generating and Presenting Feedback

[1187] The server analyzes the user's practice records using machine learning models and statistical methods.

[1188] The server then uses the emotion data from the emotion engine to generate feedback that takes into account the user's emotional state, including the user's progress and areas for improvement.

[1189] The device presents the generated feedback to the user, which is displayed in a message screen within the application.

[1190] Specific examples

[1191] For example, if you have a self-help book called "The 7 Habits":

[1192] The server retrieves the 7 Habits data, tokenizes it, and cleans it.

[1193] A generative AI model is used to generate summaries of "The 7 Habits" and add them to the catalog.

[1194] Users select "The 7 Habits" from the catalog and receive a summary and checklist.

[1195] Checklist example:

[1196] [ ] Did you self-assess daily?

[1197] [ ] Have you made one independent decision a day?

[1198] The user records their daily activities and sends the data from the terminal to the server.

[1199] The emotion engine recognizes the user's emotional state in real time and transmits the emotion data to the server.

[1200] The server analyzes the recorded data and emotional data, generates feedback such as, "Today's self-evaluation is good, but you lack independent decision-making. Try harder," and presents it to the user via the device.

[1201] In this way, a system for improving the efficiency of self-development is constructed, allowing users to continuously and efficiently practice self-development. By combining it with an emotion engine, feedback that takes into account the user's emotional state becomes possible, resulting in more personalized responses.

[1202] The processing flow will be explained below.

[1203] The present invention relates to a self-development efficiency improvement system that uses a generative AI model and an emotion engine. This system is implemented as follows.

[1204] Overall processing steps of the system

[1205] Step 1:

[1206] The server accesses the API of the e-book platform to obtain the text data of the self-help book. Specifically, it sends an API request specifying the book ID and extracts the text data from the JSON response.

[1207] Step 2:

[1208] The server tokenizes the text data it receives. Using a natural language processing library (e.g., NLTK or SpaCy), it splits the text into words and punctuation marks and converts them into a list.

[1209] Step 3:

[1210] The server cleans the tokenized data, removing unnecessary tags, line breaks, and whitespace, and using regular expressions to remove specific string patterns.

[1211] Step 4:

[1212] The server uses a generative AI model to generate a summary from the cleaned data. For example, it inputs text data into a GPT model and generates a summary that extracts key points.

[1213] Step 5:

[1214] The server catalogs the generated summaries, storing them in JSON format and indexing them using the self-help book metadata (title, author, publication year).

[1215] Step 6:

[1216] The server extracts actionable points from the summary, using natural language processing to pick out verbs and important guidelines from the book summary and create a list of specific action items.

[1217] Step 7:

[1218] The server generates a checklist based on the extracted practices. The checklist contains specific actions that users should take each day. The checklist is saved in JSON format.

[1219] Step 8:

[1220] The device displays a list of cataloged self-help books to the user, and the user interface also includes a search function to allow the user to easily find self-help books that interest them.

[1221] Step 9:

[1222] A user selects a self-help book, for example, "The 7 Habits," and then checks the summary and checklist on the book's details page.

[1223] Step 10:

[1224] The device presents the user with a summary and checklist of the selected self-help book, and the user reads the summary and checks the checklist within the application.

[1225] Step 11:

[1226] Users record their daily activities based on a checklist, tapping a checkbox to indicate whether a task is completed or not.

[1227] Step 12:

[1228] The device sends the user's practice record to the server, where the record data is sent in JSON format and stored.

[1229] Step 13:

[1230] The emotion engine analyzes user input, facial expressions, and vocal tones to recognize emotions. It uses cameras and microphones to collect data in real time and applies emotion analysis algorithms.

[1231] Step 14:

[1232] The server integrates and analyzes the user's practice records and emotional data, using a feedback algorithm that takes into account the user's emotional state.

[1233] Step 15:

[1234] The server generates feedback based on the analysis results, such as "Your self-evaluation today is good, but you lack proactive decision-making. Please act more consciously."

[1235] Step 16:

[1236] The device presents the generated feedback to the user, which is displayed in a message screen within the application.

[1237] The above processing steps create a system that can improve the efficiency of self-development and provide personalized feedback. Users can continuously and efficiently practice self-development, resulting in better results.

[1238] Example 2

[1239] 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."

[1240] In the past, it was difficult for users to efficiently extract the main points of each book and create an appropriate practice plan. In addition, there was a lack of feedback that took into account the user's emotional state, which resulted in a decrease in the effectiveness of the self-help book.

[1241] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring self-help book data, means for tokenizing and cleaning the acquired data, means for generating a summary from the tokenized data using a generative AI model, means for organizing the summarized content in a catalog format, means for extracting specific practice points from the summary and generating a checklist, means for analyzing a user's input, facial expressions, and voice to recognize emotions, means for analyzing the user's practice status and emotional data and generating feedback, and means for presenting the generated feedback to the user. This makes it possible to efficiently extract the key points of a self-help book and provide the user with feedback that takes into account their emotional state.

[1242] "Self-help book data" is data that includes text information of books related to self-help.

[1243] "Means for obtaining" refers to a function or device for obtaining necessary data from an external data source.

[1244] "Tokenization" is the process of dividing text data into its smallest units, such as words and punctuation marks.

[1245] "Cleaning means" refers to a process of arranging data by removing unnecessary tags, line breaks, and spaces from text data.

[1246] A "generative AI model" is an artificial intelligence model that uses natural language processing technology to summarize and generate text data.

[1247] The "means for generating summaries" is a function that uses a generative AI model to extract key points from text data and present them in a concise format.

[1248] The "means for organizing in a catalog format" is a means for storing summarized data in a specific structure and organizing it so that the user can easily access it.

[1249] The "means for extracting action items" is a function that identifies specific guidelines and verbs from summary data and extracts them as items to be put into practice.

[1250] The "means for generating a checklist" is a function that lists action items to be carried out based on the extracted practice items.

[1251] "User input" refers to information or data provided by a user, such as text entry or selection actions.

[1252] "Facial expression" refers to the user's facial movements and expressive state.

[1253] "Voice" refers to the state of a user's voice, including their tone and emotions.

[1254] The "means for recognizing emotions" is a function that analyzes the user's facial expressions and voice to identify their emotional state.

[1255] "Recording practice items" refers to the user recording the results of their daily practice.

[1256] The "means for generating feedback" is a function that creates feedback including areas for improvement and progress based on the user's practice data and emotional state.

[1257] The "means for presenting feedback" is a function for displaying the generated feedback to the user.

[1258] The present invention relates to a self-help efficiency improvement system that uses a generative AI model and an emotion engine. This system automates the process from acquiring self-help book data to providing feedback to users. Specific embodiments are described below.

[1259] Hardware and Software Use

[1260] The system mainly consists of a server, a terminal, and an emotion engine.

[1261] 1. Server Operation

[1262] Get book data:

[1263] The server accesses the API of the e-book platform to retrieve the text data of the self-help book. At this time, it sends a request using the Python requests library, and the data is saved in JSON format.

[1264] Tokenize and clean data:

[1265] The server tokenizes the retrieved data using a natural language processing library (e.g., NLTK or spaCy), and the cleaning process uses a regular expression library to remove unnecessary tags, line breaks, and whitespace.

[1266] Summary generation using generative AI models:

[1267] The server uses a generative AI model (e.g., OpenAI's GPT-3) to send the data along with the prompt and generate a summary, which is stored in a variable for later processing.

[1268] Abstract Cataloging:

[1269] The server organizes the summaries into a catalog, stored in JSON format, that includes the book title, author, and key points of the summary.

[1270] Extraction of practices and generation of checklists:

[1271] The server extracts action items (e.g., verbs and guidelines) from the summary text and lists them as a checklist.

[1272] 2. Operation of the Emotion Engine

[1273] The emotion engine uses a camera and microphone to capture the user's facial expressions and voice. This data is analyzed in real time to evaluate the user's emotional state. Specifically, it uses technologies such as OpenFace and TensorFlow.

[1274] 3. Device Operation

[1275] Browse the catalogue:

[1276] A user can browse a catalog of self-help books stored on a server through a dedicated application, select an appropriate book, and view its summary and checklist.

[1277] Present and record the checklist:

[1278] The terminal displays a summary of the selected book and a checklist to the user, who then records his or her daily activities based on the checklist and sends the data to the server.

[1279] 4. Generating and Presenting Feedback

[1280] Analysis of recorded data:

[1281] The server analyzes the practice records entered by the user using machine learning models and statistical methods, and also uses emotional data from the emotion engine to generate feedback that takes the user's emotional state into account.

[1282] Giving feedback:

[1283] The device presents the user with feedback sent from the server, including information about progress and areas for improvement.

[1284] Specific examples

[1285] For example, if a user chooses "The 7 Habits" as a self-help book, the server retrieves the book's data, tokenizes and cleans it, then uses GPT-3 to generate a summary and add it to the catalog. The user selects "The 7 Habits" from the catalog and receives the summary and checklist.

[1286] Checklist example:

[1287] [ ] Did you self-assess every day?

[1288] [ ] Did you make an independent decision?

[1289] Example of a generated AI prompt:

[1290] Please write a summary of "The 7 Habits" in the following format:

[1291] Key points of this book

[1292] Key Action Items

[1293] Practical Tips

[1294] Text: <insert text here>

[1295] In this way, a system for improving the efficiency of self-development is constructed, supporting users in practicing self-development continuously and effectively.By combining it with an emotion engine, it becomes possible to provide personalized feedback according to the user's emotional state.

[1296] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1297] Step 1:

[1298] The server accesses the API of the e-book platform and retrieves the text data of the self-help book. The API endpoint URL and access credentials are used as input, and the retrieved book data (JSON format) is output. Specifically, it sends a request to the API using the Python requests library (e.g., response = requests.get(API_URL, headers=headers)) and saves the retrieved data in JSON format (e.g., book_data = response.json()).

[1299] Step 2:

[1300] The server tokenizes and cleans the acquired book data. The acquired book data is used as input, and the output is the tokenized and cleaned data. Specifically, it uses a natural language processing library such as NLTK to split the text into words and punctuation marks (tokenization), and uses Python's regular expression library to remove unnecessary tags, line breaks, and spaces (e.g., clean_text = re.sub(r'\s+', ' ', book_data["text"])).

[1301] Step 3:

[1302] The server uses a generative AI model to generate a summary from the tokenized and cleaned data. It uses the cleaned text data and a prompt as input, and outputs the summary text. Specifically, it uses OpenAI's API to send the data along with the prompt (e.g., response = openai.Completion.create(engine="text-davinci-003", prompt=prompt, max_tokens=150)) and stores the generated summary in a variable (e.g., summary = response.choices[0].text.strip()).

[1303] Step 4:

[1304] The server organizes the summarized self-help books into a catalog. It takes the summary text and basic book information (title, author, etc.) as input, and outputs a catalog entry in JSON format. Specifically, it generates a data structure containing the summary text (e.g., catalog_entry = {"title": book_title, "author": book_author, "summary": summary}) and stores it in the database.

[1305] Step 5:

[1306] The server extracts specific actions from the summary and generates a checklist. The input is the summary text, and the output is a checklist. Specifically, it uses a text analysis algorithm to extract verbs and action points from the summary (e.g., actions = extract_actions_from_summary(summary)), and then creates a list of them (e.g., checklist = create_checklist(actions)).

[1307] Step 6:

[1308] The emotion engine analyzes user input, facial expressions, and vocal sounds to recognize emotions. It uses real-time facial and vocal data obtained from a camera and microphone as input, and outputs emotional data. Specifically, it uses OpenFace for facial recognition (e.g., emotion_face = analyze_facial_expression(image)) and TensorFlow for vocal analysis (e.g., emotion_voice = analyze_voice(voice_clip)).

[1309] Step 7:

[1310] The user browses a catalog of self-help books through a dedicated application, and selects and views the summary and checklist of a self-help book. The input is the catalog data stored on the server, and the output is the summary and checklist displayed to the user. Specifically, the mobile application displays the catalog screen, and retrieves and displays the self-help book data selected by the user.

[1311] Step 8:

[1312] The user records daily practice items based on the checklist, and the device sends the data to the server. The input is the practice data recorded by the user, and the output is the record data sent to the server. The specific operation is that the user enters data in the mobile application and sends the data to the server (e.g., send_to_server(record_data)).

[1313] Step 9:

[1314] The server analyzes the user's practice record and emotion data and generates feedback. It uses practice record data and emotion data as input, and outputs a feedback message. Specifically, it analyzes the data using machine learning models and statistical methods (e.g., feedback = generate_feedback(user_data, emotion_data)) and generates appropriate feedback.

[1315] Step 10:

[1316] The terminal presents the generated feedback to the user. The input is the feedback message sent from the server, and the output is the feedback displayed to the user. Specifically, the feedback is displayed on a message screen within the mobile application.

[1317] (Application example 2)

[1318] 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."

[1319] Conventional self-improvement support systems specialize in generating summaries and providing checklists to promote user growth, but lack the ability to generate feedback that takes into account the user's emotional state. As a result, they are unable to provide personalized feedback based on emotions that would help users maintain their self-improvement behavior. Furthermore, in the food delivery industry, there is a lack of systems that support self-improvement for delivery workers while they are working.

[1320] 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.

[1321] In this invention, the server includes means for acquiring self-help book data, means for tokenizing and cleaning the acquired data, means for generating summaries from the tokenized data using a generative AI model, means for organizing the summarized content in a catalog format, means for accepting a user's selection of a self-help book, means for presenting summaries and checklists of the selected self-help book, means for receiving a record of the user's practice, means for analyzing the practice status and generating feedback, means for presenting the generated feedback to the user, means for analyzing the user's emotional state, and means for adjusting the content of the feedback based on the user's emotional state. This makes it possible to provide personalized feedback based on the user's practice status and emotional state, allowing food delivery workers to efficiently engage in self-improvement while on the job.

[1322] "Self-help book data" is digital data of books and documents used as self-help books.

[1323] "Tokenization" is the process of dividing text data into smaller units such as words and punctuation marks.

[1324] "Cleaning" is the process of removing unnecessary tags, line breaks, and spaces from data to prepare it in a format that is easy to analyze.

[1325] A "generative AI model" is an algorithm or program that uses AI to generate natural language and summaries.

[1326] A "summary" is a short summary of the main points or content of a text or book.

[1327] "Catalog format" is a format in which information is organized and displayed by items such as title, author, and main points.

[1328] A "checklist" is a list of action items that a user should take.

[1329] "Feedback" is information such as suggestions for improvement or advice generated based on the practice situation and emotional state.

[1330] "Means for analyzing emotional state" refers to a method or system for analyzing emotions from the user's facial expressions, voice, etc.

[1331] The "means for adjusting the content of feedback based on emotional state" refers to a method or system that changes the feedback provided depending on the analyzed emotion.

[1332] This invention is a system for supporting users' self-development by efficiently utilizing the contents of self-help books, and is particularly targeted at delivery workers in the food delivery industry. This system is implemented using hardware and software including a server, a terminal, an emotion engine, a camera, and a microphone.

[1333] The server retrieves self-help book data from the e-book platform, tokenizes and cleans it, and then uses the tokenized data to generate summaries using a generative AI model. This generative AI model applies the GPT series of natural language generation models. The summaries are then organized into a catalog and saved in JSON format. This allows for efficient management of information and makes it easy for users to access.

[1334] Next, the device (e.g., a smartphone application) accepts user input. The user selects the desired book from a catalog of self-help books and receives a summary and a checklist. The checklist includes specific action items to be put into practice. The user records the actions they take each day and sends the data from the device to a server. For example, the checklist might include action items such as "Have you performed self-evaluation every day?" or "Have you made one independent decision per day?"

[1335] Furthermore, the emotion engine analyzes the user's emotional state using a camera and microphone. This analyzed emotional data is sent to a server, which generates feedback based on the user's progress and emotional state. The feedback includes personalized advice that takes the user's emotions into account, making it easier for the user to continue their self-improvement activities.

[1336] For example, if a delivery person opens the app and selects "The 7 Habits," the server retrieves the book's data, tokenizes it, and cleans it. A generative AI model then generates a summary and adds it to the catalog. The delivery person retrieves this summary from the catalog and records their actions based on a daily checklist. Meanwhile, an emotion engine recognizes the delivery person's emotional state from their facial expressions and tone of voice, and sends this data to the server. Based on the recorded data and emotion data, the server generates feedback such as, "Today's self-evaluation is good, but your independent decision-making skills are lacking. You need to work harder," and presents it to the delivery person via their device.

[1337] In this way, this invention is a system that supports users in continuing to work on self-improvement by streamlining the use of self-help books and providing personalized feedback that takes into account their emotional state. This system allows delivery workers, particularly in the food delivery industry, to efficiently engage in self-improvement while at work.

[1338] Examples of prompts:

[1339] "Set your goals for today as 'Perform daily self-evaluation' and 'Make independent decisions.' Judging from your emotional state, you seem a little tired today. Take a break and complete the practical tasks."

[1340] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1341] Step 1:

[1342] The server retrieves self-help book data using the API of the e-book platform. The input is the book ID, and the data retrieved from the API includes the book's text content. Specifically, the server sends an HTTP request and receives the e-book data. The output is the retrieved book data.

[1343] Step 2:

[1344] The server tokenizes and cleans the acquired book data. The input is the book data, and a natural language processing library is used to split the data into words and punctuation marks, and remove unnecessary characters and tags. Specifically, the server uses an NLP library to perform tokenization and regular expressions to perform cleaning. The output is the tokenized and cleaned data.

[1345] Step 3:

[1346] The server generates a summary using a generative AI model based on the tokenized and cleaned data. The input is the tokenized data, and the generative AI model (e.g., GPT sequence) extracts important content and generates a summary. Specifically, the server inputs the tokenized data into the generative AI model and receives the summary generated by the model. The output is the summarized text.

[1347] Step 4:

[1348] The server organizes the generated summary text into a catalog format. The input is the summary text, which is converted into JSON format for each item, such as title, author, and main points. Specifically, the server parses the summary text and creates a data structure corresponding to each item. The output is JSON data in catalog format.

[1349] Step 5:

[1350] The terminal accepts the user's selection of a self-help book. The input is the user's selection information, and based on that information, it presents a summary and checklist of the corresponding book from the catalog. In concrete terms, the terminal receives the user's input, retrieves the corresponding data, and displays it. The output is the summary and checklist presented to the user.

[1351] Step 6:

[1352] The user records the actions based on the checklist. The input is the user's recorded information, which is sent from the terminal to the server. In concrete terms, the user records an action item, and the terminal sends the information to the backend. The output is the action record stored on the server.

[1353] Step 7:

[1354] The emotion engine analyzes the user's emotional state using a camera and microphone. The input is the user's facial expression and vocal data, and the emotional state is evaluated through analysis. Specifically, the emotion engine acquires data from the camera and microphone and analyzes it using a machine learning algorithm. The output is evaluated emotional data.

[1355] Step 8:

[1356] The server generates feedback based on practice status data and emotion data and presents it to the user. The input is practice record data and emotion data, which are analyzed using machine learning models and statistical methods to generate personalized feedback. Specifically, the server summarizes the analysis results, generates a feedback message, and sends it to the terminal. The output is the feedback message presented to the user.

[1357] 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.

[1358] 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.

[1359] 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.

[1360] [Fourth embodiment]

[1361] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1362] 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.

[1363] 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).

[1364] 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.

[1365] 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.

[1366] 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).

[1367] 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.

[1368] 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.

[1369] 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.

[1370] 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.

[1371] 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.

[1372] 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.

[1373] 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."

[1374] The present invention relates to a self-development efficiency improvement system using a generative AI model. This system is implemented as follows.

[1375] Overall system operation

[1376] 1. Acquisition and preprocessing of book data

[1377] The server retrieves data on self-help books from an e-book platform, which mainly contains text information.

[1378] The server tokenizes and cleans the data it receives, removing unnecessary tags and line breaks and splitting sentences into tokens using a natural language processing library.

[1379] 2. Summary generation using generative AI models

[1380] The server uses a generative AI model to summarize the content from the tokenized book data, such as a GPT-based natural language generation model.

[1381] The summarized text is saved in storage for later processing.

[1382] 3. Cataloging Abstracts

[1383] The server organizes the summarized self-help books into a catalog, where each summary is stored in JSON format, including the book's title, author, main points, etc.

[1384] 4. Extraction of practical matters and generation of checklists

[1385] The server extracts concrete actionable information from the summaries, which involves natural language processing to extract verbs and key actions from the book summaries.

[1386] Based on the extracted practices, the server generates a checklist that includes daily tasks and action items.

[1387] 5. User Interaction

[1388] Users can browse a catalog of self-help books through a dedicated application, check the summaries and effects of each book, and select the book that best suits them.

[1389] The terminal presents the user with a summary of the selected self-help book and a checklist, which the user can use for daily practice.

[1390] Users record their daily practices within the application, checking off action items such as whether they performed a self-assessment or made an independent decision.

[1391] The terminal sends the user's input to the server.

[1392] 6. Generating and Presenting Feedback

[1393] The server analyzes the user's practice records and generates feedback on their performance and areas for improvement.

[1394] The server then presents the generated feedback to the user via a dedicated application, including advice on next steps and further improvements.

[1395] Specific examples

[1396] For example, if you have a self-help book called "The 7 Habits":

[1397] The server retrieves the 7 Habits data, tokenizes it, and cleans it.

[1398] A generative AI model is used to generate summaries of "The 7 Habits" and add them to the catalog.

[1399] Users select "The 7 Habits" from the catalog and receive a summary and checklist.

[1400] Checklist example:

[1401] [ ] Did you self-assess daily?

[1402] [ ] Have you made one independent decision a day?

[1403] The user records their daily activities and sends the data from the terminal to the server.

[1404] The server analyzes the recorded data and generates feedback such as, "To further increase your independent decision-making, act consciously the next day," which is presented to the user via the device.

[1405] In this way, a system for improving the efficiency of self-development is constructed, allowing users to practice self-development continuously and efficiently.

[1406] The processing flow will be explained below.

[1407] Step 1:

[1408] The server accesses the API of the e-book platform to retrieve the text data of the self-help book, along with the book's metadata (title, author, publication year, etc.).

[1409] Step 2:

[1410] The server tokenizes the acquired book data. Specifically, it uses a natural language processing library to split the text into words and punctuation marks, and converts them into a data structure (e.g., an array).

[1411] Step 3:

[1412] The server cleans the tokenized data, removing unnecessary tags, line breaks, and whitespace, and formatting the text data to make it easier to parse.

[1413] Step 4:

[1414] The server generates summaries from the tokenized and cleaned data using a generative AI model, which is a pre-trained natural language generation model.

[1415] Step 5:

[1416] The server catalogs the generated summaries. It stores each self-help book summary in JSON format, creating a searchable and filterable catalog.

[1417] Step 6:

[1418] The server extracts actionable points from the summary, using natural language processing to pick out verbs and important guidelines from the summary and create a list.

[1419] Step 7:

[1420] The server generates a checklist based on the extracted practices, which includes specific action items that users should perform daily.

[1421] Step 8:

[1422] The terminal displays a list of cataloged self-help books to the user, and the user selects a self-help book from the catalog.

[1423] Step 9:

[1424] The device presents the user with a summary and checklist of the selected self-help book, which are displayed on a dedicated screen within the application.

[1425] Step 10:

[1426] The user records the daily activities based on the checklist, and fills in the status of the activities by checking the boxes.

[1427] Step 11:

[1428] The device sends the user's practice record to the server. The recorded data is sent in JSON format.

[1429] Step 12:

[1430] The server analyzes the user's practice records using machine learning models and statistical methods.

[1431] Step 13:

[1432] The server generates feedback based on the analysis results, including the user's progress and areas for improvement.

[1433] Step 14:

[1434] The device presents the generated feedback to the user, which is displayed in a message screen within the application.

[1435] Example 1

[1436] 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."

[1437] There is a need to efficiently understand the contents of self-help books and incorporate their practical tips into daily life. However, self-help books cover a wide range of topics, and it takes time and effort to read, understand, and practice each book. Furthermore, a lack of records and feedback on practical tips makes it difficult to improve the sustainability and effectiveness of self-help. The present invention aims to solve these problems by generating summaries of self-help books, suggesting practical ideas, and automatically recording and providing feedback, thereby providing a system that allows users to efficiently practice self-help.

[1438] 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.

[1439] In this invention, the server includes means for acquiring e-book data, means for tokenizing and cleaning the acquired data, means for generating summaries from the tokenized data using a generative model, means for organizing the summarized content in a catalog format, means for extracting practice points from the summaries and generating a checklist, means for accepting a user's book selection, means for presenting summaries and checklists for the selected books, means for receiving a record of the user's practice points, means for analyzing the practice points and generating feedback, and means for presenting the generated feedback to the user. This allows users to efficiently understand the contents of a wide range of self-help books in a summarized format and easily incorporate the practice points into their daily lives. Furthermore, the practice records and feedback can enable continuous self-help practice and improved effectiveness.

[1440] A "server" is a central processing unit that processes data and provides information upon receiving a request from a client.

[1441] "E-book data" refers to the content information of a book that is stored in digital format and can be displayed and viewed through electronic media.

[1442] "Tokenization" is the process of dividing text data into useful units (words and phrases) for natural language processing.

[1443] "Cleaning" is the process of removing unnecessary elements and errors from data and preparing it in a format suitable for analysis.

[1444] A "generative model" is an algorithm or system that uses artificial intelligence technology to process natural language and generate new text.

[1445] A "summary" is a concise summary of the main information in the original text data.

[1446] The "catalog format" is a format that allows a large number of items to be systematically organized and classified so that they can be displayed in a list.

[1447] "Practical matters" are specific actions or tasks that should actually be carried out based on the self-help book.

[1448] A "checklist" is a list organized by item to check and record practice matters.

[1449] A "user" is an individual who uses the system to refer to summaries and practical matters in self-help books and engage in self-improvement.

[1450] "Selection" is the act of choosing a particular item or option from a number of items or options.

[1451] "Recording" is the act of saving and retaining certain events or actions as data.

[1452] "Feedback" is information that provides evaluations and advice on a user's actions and results.

[1453] "Presenting" is the act of showing information to a user visually or audibly.

[1454] MODE FOR CARRYING OUT THE INVENTION

[1455] The present invention relates to a self-development efficiency improvement system using a generative AI model, and this system is implemented as follows.

[1456] Acquiring and preprocessing book data

[1457] The server first uses the API of the e-book platform to obtain data on self-help books. This data is mainly text information, and APIs such as Amazon Kindle and Google Books are used to obtain the data. The obtained text data is tokenized using a natural language processing library (e.g., NLTK or spaCy), and then cleaned by removing unnecessary tags and line breaks.

[1458] Summary Generation

[1459] The server uses a generative AI model (e.g., the GPT series) to generate a summary of the contents from the tokenized book data, which is then stored in storage for further processing.

[1460] Abstract Cataloging

[1461] The server organizes the summarized data of self-help books into a catalog. Each summary is saved in JSON format, including the book's title, author, main points, etc. This catalog serves as a reference for users when selecting a self-help book.

[1462] Extraction of practical matters and generation of checklists

[1463] The server uses natural language processing technology to extract specific actions from the summary, which then generates a checklist containing tasks and action items that the user should perform each day.

[1464] User Interaction

[1465] The user uses a dedicated application to browse a catalog of self-help books and select the book that best suits them. Based on this, the device presents the user with a summary of the selected book and a checklist. The user then uses this checklist as a reference for their daily practice.

[1466] Recording and feedback on practice matters

[1467] Users record their daily activities within the application and check off action items such as "Did I perform self-evaluation?" or "Did I make independent decisions?" The device sends the user's input data to the server. The server analyzes the recorded data and generates feedback on achievements and areas for improvement. The generated feedback is presented to the user via a dedicated application.

[1468] Specific examples

[1469] For example, taking the self-help book "The 7 Habits," the server first retrieves the data for "The 7 Habits" from the e-book platform, tokenizes it, and cleans it. The server then uses a generative AI model to generate a summary of "The 7 Habits" and adds it to the catalog. The user then selects "The 7 Habits" from the catalog in a dedicated application and receives the summary and checklist from the server.

[1470] Checklist example:

[1471] [ ] Did you self-assess daily?

[1472] [ ] Have you made one independent decision a day?

[1473] Users record their daily actions and send the data from their device to the server. The server analyzes the recorded data and generates specific feedback, such as "To further increase your independent decision-making, act consciously the next day," and presents it to the user via their device.

[1474] Prompt Sentence Examples

[1475] Summarize the 7 Habits, including a description of each habit and how it contributes to personal growth.

[1476] In this way, the system of the present invention provides users with an efficient means of self-improvement. The specific details of the process are realized by the cooperative operation of the server and the terminal.

[1477] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1478] Step 1:

[1479] The server uses the API of the e-book platform to obtain the text data of the self-help book.

[1480] Input: Your eBook platform API key and book identifier.

[1481] Output: Raw text data of the book.

[1482] Specific operation: The server sends an API request and receives the book's text data as a response.

[1483] Step 2:

[1484] The text data retrieved by the server is tokenized and cleaned.

[1485] Input: Raw text data.

[1486] Output: Tokenized and cleaned text data.

[1487] What it does: Uses a natural language processing library (e.g., NLTK or spaCy) to split text into words and phrases, and removes unnecessary tags and line breaks.

[1488] Step 3:

[1489] The server uses a generative AI model (e.g., GPT series) to generate summaries from the tokenized data.

[1490] Input: Tokenized and cleaned text data.

[1491] Output: A text summary of the book.

[1492] How it works: A prompt sentence is input into the generative AI model to generate a summary text. The prompt sentence contains the information that forms the basis of the summary.

[1493] Step 4:

[1494] The server organizes the generated summaries into a catalog and stores them in JSON format.

[1495] Input: Book summary text.

[1496] Output: JSON data in catalog format.

[1497] Specific operation: The summary text is converted into JSON format along with information such as the book title, author, and main points, and saved to storage.

[1498] Step 5:

[1499] The server extracts specific practice items from the summary and generates a checklist.

[1500] Input: Book summary text.

[1501] Output: A checklist with action points.

[1502] Specific actions: Using natural language processing technology, verbs and important guidelines for action are extracted from the summary text, and a checklist is created based on them.

[1503] Step 6:

[1504] A user uses a dedicated application to browse a catalog of self-help books and select a book.

[1505] Input: Catalog data.

[1506] Output: User's book selection information.

[1507] Specific operation: Display a catalog on the application screen and allow the user to select the book they want to read.

[1508] Step 7:

[1509] The terminal presents the user with summaries and checklists for the selected books.

[1510] Input: User's book selection information.

[1511] Output: Summary text and checklist.

[1512] Specific behavior: The summary and checklist are displayed on the application screen for the user to refer to.

[1513] Step 8:

[1514] Users record their daily practices and check off checklists within the application.

[1515] Input: User's practice record.

[1516] Output: Recorded practice data.

[1517] What it does: Record an action by tapping on a checklist item within the app.

[1518] Step 9:

[1519] The terminal transmits the user's input data to the server.

[1520] Input: Recorded practice data.

[1521] Output: Practice data sent to the server.

[1522] Specific behavior: The application sends data to the server as a POST request.

[1523] Step 10:

[1524] The server analyzes the recorded data and generates feedback on success and areas for improvement.

[1525] Input: Practice data sent to the server.

[1526] Output: Feedback text.

[1527] What it does: Performs statistical analysis and generates feedback based on user behavior patterns.

[1528] Step 11:

[1529] The server generates feedback and presents it to the user via a dedicated application.

[1530] Input: Feedback text.

[1531] Output: The feedback presented to the user.

[1532] Specific behavior: The feedback text is displayed on the application screen.

[1533] (Application example 1)

[1534] 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."

[1535] There is a need for a system that can streamline learning based on self-help books and enable users to continuously practice self-improvement based on their experiences and purchases in physical stores. Another issue is the lack of a means to effectively provide feedback based on the participation history of store events.

[1536] 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.

[1537] In this invention, the server includes means for acquiring self-improvement data, means for tokenizing and cleaning the acquired data, and means for generating summaries from the tokenized data using a generative AI model, thereby providing users with summaries and practice checklists based on their experiences and purchases in physical stores and providing feedback based on their participation in store events.

[1538] "Self-improvement data" is data that contains information to promote self-improvement and efficient learning.

[1539] A "generative AI model" is an artificial intelligence model that uses natural language processing to generatively create output from input data.

[1540] "Tokenization" is the process of dividing a sentence into certain linguistic units.

[1541] "Cleaning" is the process of removing unnecessary information and noise from data and organizing it.

[1542] A "summary" is information that briefly and condenses the essence of self-help data.

[1543] "Catalog format" is a method of organizing information by category and displaying it in a list format.

[1544] A "self-improvement guide" is a guide to promoting self-growth and goal achievement.

[1545] A "checklist" is a list of items to check the performance of a specific action or task.

[1546] "Practices" refer to the actions or tasks that users should actually undertake.

[1547] "Feedback" is information that provides evaluations and advice based on the user's actions.

[1548] A "physical store" is a commercial facility that a user can physically visit.

[1549] "Store Events" are activities or events held at physical stores with a specific theme or purpose.

[1550] "Participation history" is a record of events and activities that a user has participated in in the past.

[1551] This invention relates to a self-improvement efficiency system that uses a generative AI model to provide summaries and practice checklists based on experiences and purchases in physical stores, and provides feedback based on participation history in store events.

[1552] System configuration and operation

[1553] The server includes the following means:

[1554] 1. Obtaining self-development data:

[1555] The server acquires data on self-help books from the e-book platform, which mainly contains text information.

[1556] 2. Tokenize and clean the data:

[1557] The server tokenizes and cleans the data it receives, which includes using natural language processing libraries to tokenize sentences and remove unnecessary tags and line breaks.

[1558] 3. Summary generation using generative AI models:

[1559] The server uses a generative AI model (e.g., a GPT-based natural language generation model) to summarize the content from the tokenized book data, and the summarized text is stored in storage for later processing.

[1560] 4. Cataloging Abstracts:

[1561] The server organizes the summarized self-help books into a catalog, with each summary stored in a format that includes the book's title, author, main points, etc.

[1562] 5. Extraction of practice items and generation of checklists:

[1563] The server extracts specific actions from the summary, which involves natural language processing to extract verbs and key actions from the book summary, and then generates a checklist based on the extracted actions.

[1564] 6. User interaction:

[1565] The user browses a catalog of self-help books through a dedicated application (smartphone, smart glasses, head-mounted display, etc.). The user checks the summary and effects and selects a self-help guidebook. The device then presents the selected summary and checklist to the user.

[1566] 7. In-store experience and purchase assistance:

[1567] Based on in-store experiences and purchases, the presented summary and checklist are updated to guide the user through their actions.

[1568] 8. Providing feedback on in-store events:

[1569] Based on the user's history of participating in store events, the server generates feedback and provides it to the user via a dedicated application, including advice on next steps and further improvements.

[1570] Example

[1571] For example, if you have a self-help book called "The 7 Habits":

[1572] The server retrieves the 7 Habits data, tokenizes it, and cleans it.

[1573] Use a generative AI model (e.g., GPT series) to generate summaries of "The 7 Habits" and add them to the catalog.

[1574] Users select "The 7 Habits" from the catalog and receive a summary and checklist.

[1575] Checklist example:

[1576] [ ] Did you self-assess daily?

[1577] [ ] Have you made one independent decision a day?

[1578] As users purchase products based on the 7 Habits in physical stores, the summary and checklist are updated.

[1579] The user records their daily activities and sends the data from the terminal to the server.

[1580] The server analyzes the recorded data and generates feedback such as, "To make more independent decisions, act consciously the next day," which is presented to the user via the device.

[1581] Examples of prompt statements

[1582] A prompt to generate a summary of a self-help book might look like this:

[1583] "Summarize the following self-help books:"

[1584] The prompt to extract the practice items is as follows:

[1585] "Please create a checklist by extracting the practical points from the summary below:"

[1586] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1587] Step 1:

[1588] The server retrieves self-help data. This is the process of collecting text data from an e-book platform. This process uses the e-book API to request specific book data and retrieve it in text format. The input requires the e-book's book ID and API key, and the output is the book's text data.

[1589] Step 2:

[1590] The server tokenizes and cleans the acquired self-help data. This process uses a natural language processing library to remove unnecessary tags and line breaks from the text data and further divides it into tokens. The input is the book text data, and the output is the cleaned tokenized data.

[1591] Step 3:

[1592] The server generates a summary from the tokenized data using a generative AI model. This process involves providing a prompt sentence to a generative AI model (e.g., GPT) to create a summary. It requires cleaned tokenized data and a prompt sentence as input, and obtains the summarized text as output.

[1593] Step 4:

[1594] The server organizes the summarized content into a catalog, a process that formats the summarized text and stores it as a catalog entry, using the summarized text as input and obtaining catalog-formatted data as output.

[1595] Step 5:

[1596] The terminal accepts the user's selection of a self-help book. In this process, the user browses the catalog and makes a selection through a dedicated application. The input is catalog data, and the output is the user's selection information.

[1597] Step 6:

[1598] The terminal presents a summary and checklist for the selected self-help book. This process displays the summary data and checklist selected by the user on the screen. It uses the user's selection and associated summary data as input and obtains a screen display as output.

[1599] Step 7:

[1600] The terminal receives the record of the user's actions. In this process, the user records the actions based on the checklist. The user's input data is used as input, and the record data is obtained as output.

[1601] Step 8:

[1602] The server analyzes the user's practice and generates feedback. This process involves analyzing the user's recorded data and creating feedback using a generative AI model. The recorded data and prompt text are used as input, and the feedback text is obtained as output.

[1603] Step 9:

[1604] The terminal presents the generated feedback to the user. This process displays the generated feedback on the user's terminal screen, using the feedback text as input and obtaining a screen display as output.

[1605] Step 10:

[1606] The server includes means for providing a summary and a checklist of actions based on the experience and purchases at the physical store. The process utilizes the purchase history and experience information at the physical store to provide the summary and checklist optimized for the user. The process uses the purchase history and experience information as input and obtains the personalized summary and checklist as output.

[1607] Step 11:

[1608] The terminal provides feedback based on the participation history of store events. In this process, the terminal refers to the participation history of store events and presents feedback to the user. The participation history is used as input and a feedback display is obtained as output.

[1609] 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.

[1610] The present invention relates to a self-development efficiency improvement system that uses a generative AI model and an emotion engine. This system is implemented as follows.

[1611] Overall system operation

[1612] 1. Acquisition and preprocessing of book data

[1613] The server accesses the API of the e-book platform to retrieve the text data of the self-help book, which mainly contains text information.

[1614] The server tokenizes the data it receives, specifically by using a natural language processing library to split the text into words and punctuation marks, and converts them into a data structure (e.g., an array).

[1615] The server cleans the tokenized data, removing unnecessary tags, line breaks, and whitespace, and formatting the text data to make it easier to parse.

[1616] 2. Summary generation using generative AI models

[1617] The server generates summaries from the tokenized and cleaned data using a generative AI model, such as a GPT-based natural language generation model.

[1618] The summarized text is saved in storage for later processing.

[1619] 3. Cataloging Abstracts

[1620] The server organizes the summarized self-help books into a catalog, where each summary is stored in JSON format, including the book's title, author, main points, etc.

[1621] 4. Extraction of practical matters and generation of checklists

[1622] The server extracts concrete actionable information from the summaries, which involves natural language processing to extract verbs and key actions from the book summaries.

[1623] Based on the extracted practices, the server generates a checklist, which includes specific action items that the user should perform daily.

[1624] 5. Emotion Recognition by Emotion Engine

[1625] The emotion engine analyzes the user's input, facial expressions, and voice to recognize emotions. Specifically, it uses a camera and microphone to analyze the user's facial expressions and voice in real time and evaluates their emotional state.

[1626] These emotional data are used to deepen understanding of the user's practice situation and improve the quality of feedback.

[1627] 6. User Interaction

[1628] Users can browse a catalog of self-help books through a dedicated application, check the summaries and effects of each book, and select the book that best suits them.

[1629] The device presents the user with a summary and checklist of the selected self-help book, which are displayed on a dedicated screen within the application.

[1630] Users record their daily actions based on a checklist, such as whether they performed a self-assessment or made an independent decision.

[1631] The terminal sends the user's input to the server.

[1632] 7. Generating and Presenting Feedback

[1633] The server analyzes the user's practice records using machine learning models and statistical methods.

[1634] The server then uses the emotion data from the emotion engine to generate feedback that takes into account the user's emotional state, including the user's progress and areas for improvement.

[1635] The device presents the generated feedback to the user, which is displayed in a message screen within the application.

[1636] Specific examples

[1637] For example, if you have a self-help book called "The 7 Habits":

[1638] The server retrieves the 7 Habits data, tokenizes it, and cleans it.

[1639] A generative AI model is used to generate summaries of "The 7 Habits" and add them to the catalog.

[1640] Users select "The 7 Habits" from the catalog and receive a summary and checklist.

[1641] Checklist example:

[1642] [ ] Did you self-assess daily?

[1643] [ ] Have you made one independent decision a day?

[1644] The user records their daily activities and sends the data from the terminal to the server.

[1645] The emotion engine recognizes the user's emotional state in real time and transmits the emotion data to the server.

[1646] The server analyzes the recorded data and emotional data, generates feedback such as, "Today's self-evaluation is good, but you lack independent decision-making. Try harder," and presents it to the user via the device.

[1647] In this way, a system for improving the efficiency of self-development is constructed, allowing users to continuously and efficiently practice self-development. By combining it with an emotion engine, feedback that takes into account the user's emotional state becomes possible, resulting in more personalized responses.

[1648] The processing flow will be explained below.

[1649] The present invention relates to a self-development efficiency improvement system that uses a generative AI model and an emotion engine. This system is implemented as follows.

[1650] Overall processing steps of the system

[1651] Step 1:

[1652] The server accesses the API of the e-book platform to obtain the text data of the self-help book. Specifically, it sends an API request specifying the book ID and extracts the text data from the JSON response.

[1653] Step 2:

[1654] The server tokenizes the text data it receives. Using a natural language processing library (e.g., NLTK or SpaCy), it splits the text into words and punctuation marks and converts them into a list.

[1655] Step 3:

[1656] The server cleans the tokenized data, removing unnecessary tags, line breaks, and whitespace, and using regular expressions to remove specific string patterns.

[1657] Step 4:

[1658] The server uses a generative AI model to generate a summary from the cleaned data. For example, it inputs text data into a GPT model and generates a summary that extracts key points.

[1659] Step 5:

[1660] The server catalogs the generated summaries, storing them in JSON format and indexing them using the self-help book metadata (title, author, publication year).

[1661] Step 6:

[1662] The server extracts actionable points from the summary, using natural language processing to pick out verbs and important guidelines from the book summary and create a list of specific action items.

[1663] Step 7:

[1664] The server generates a checklist based on the extracted practices. The checklist contains specific actions that users should take each day. The checklist is saved in JSON format.

[1665] Step 8:

[1666] The device displays a list of cataloged self-help books to the user, and the user interface also includes a search function to allow the user to easily find self-help books that interest them.

[1667] Step 9:

[1668] A user selects a self-help book, for example, "The 7 Habits," and then checks the summary and checklist on the book's details page.

[1669] Step 10:

[1670] The device presents the user with a summary and checklist of the selected self-help book, and the user reads the summary and checks the checklist within the application.

[1671] Step 11:

[1672] Users record their daily activities based on a checklist, tapping a checkbox to indicate whether a task is completed or not.

[1673] Step 12:

[1674] The device sends the user's practice record to the server, where the record data is sent in JSON format and stored.

[1675] Step 13:

[1676] The emotion engine analyzes user input, facial expressions, and vocal tones to recognize emotions. It uses cameras and microphones to collect data in real time and applies emotion analysis algorithms.

[1677] Step 14:

[1678] The server integrates and analyzes the user's practice records and emotional data, using a feedback algorithm that takes into account the user's emotional state.

[1679] Step 15:

[1680] The server generates feedback based on the analysis results, such as "Your self-evaluation today is good, but you lack proactive decision-making. Please act more consciously."

[1681] Step 16:

[1682] The device presents the generated feedback to the user, which is displayed in a message screen within the application.

[1683] The above processing steps create a system that can improve the efficiency of self-development and provide personalized feedback. Users can continuously and efficiently practice self-development, resulting in better results.

[1684] Example 2

[1685] 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."

[1686] In the past, it was difficult for users to efficiently extract the main points of each book and create an appropriate practice plan. In addition, there was a lack of feedback that took into account the user's emotional state, which resulted in a decrease in the effectiveness of the self-help book.

[1687] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring self-help book data, means for tokenizing and cleaning the acquired data, means for generating a summary from the tokenized data using a generative AI model, means for organizing the summarized content in a catalog format, means for extracting specific practice points from the summary and generating a checklist, means for analyzing a user's input, facial expressions, and voice to recognize emotions, means for analyzing the user's practice status and emotional data and generating feedback, and means for presenting the generated feedback to the user. This makes it possible to efficiently extract the key points of a self-help book and provide the user with feedback that takes into account their emotional state.

[1688] "Self-help book data" is data that includes text information of books related to self-help.

[1689] "Means for obtaining" refers to a function or device for obtaining necessary data from an external data source.

[1690] "Tokenization" is the process of dividing text data into its smallest units, such as words and punctuation marks.

[1691] "Cleaning means" refers to a process of arranging data by removing unnecessary tags, line breaks, and spaces from text data.

[1692] A "generative AI model" is an artificial intelligence model that uses natural language processing technology to summarize and generate text data.

[1693] The "means for generating summaries" is a function that uses a generative AI model to extract key points from text data and present them in a concise format.

[1694] The "means for organizing in a catalog format" is a means for storing summarized data in a specific structure and organizing it so that the user can easily access it.

[1695] The "means for extracting action items" is a function that identifies specific guidelines and verbs from summary data and extracts them as items to be put into practice.

[1696] The "means for generating a checklist" is a function that lists action items to be carried out based on the extracted practice items.

[1697] "User input" refers to information or data provided by a user, such as text entry or selection actions.

[1698] "Facial expression" refers to the user's facial movements and expressive state.

[1699] "Voice" refers to the state of a user's voice, including their tone and emotions.

[1700] The "means for recognizing emotions" is a function that analyzes the user's facial expressions and voice to identify their emotional state.

[1701] "Recording practice items" refers to the user recording the results of their daily practice.

[1702] The "means for generating feedback" is a function that creates feedback including areas for improvement and progress based on the user's practice data and emotional state.

[1703] The "means for presenting feedback" is a function for displaying the generated feedback to the user.

[1704] The present invention relates to a self-help efficiency improvement system that uses a generative AI model and an emotion engine. This system automates the process from acquiring self-help book data to providing feedback to users. Specific embodiments are described below.

[1705] Hardware and Software Use

[1706] The system mainly consists of a server, a terminal, and an emotion engine.

[1707] 1. Server Operation

[1708] Get book data:

[1709] The server accesses the API of the e-book platform to retrieve the text data of the self-help book. At this time, it sends a request using the Python requests library, and the data is saved in JSON format.

[1710] Tokenize and clean data:

[1711] The server tokenizes the retrieved data using a natural language processing library (e.g., NLTK or spaCy), and the cleaning process uses a regular expression library to remove unnecessary tags, line breaks, and whitespace.

[1712] Summary generation using generative AI models:

[1713] The server uses a generative AI model (e.g., OpenAI's GPT-3) to send the data along with the prompt and generate a summary, which is stored in a variable for later processing.

[1714] Abstract Cataloging:

[1715] The server organizes the summaries into a catalog, stored in JSON format, that includes the book title, author, and key points of the summary.

[1716] Extraction of practices and generation of checklists:

[1717] The server extracts action items (e.g., verbs and guidelines) from the summary text and lists them as a checklist.

[1718] 2. Operation of the Emotion Engine

[1719] The emotion engine uses a camera and microphone to capture the user's facial expressions and voice. This data is analyzed in real time to evaluate the user's emotional state. Specifically, it uses technologies such as OpenFace and TensorFlow.

[1720] 3. Device Operation

[1721] Browse the catalogue:

[1722] A user can browse a catalog of self-help books stored on a server through a dedicated application, select an appropriate book, and view its summary and checklist.

[1723] Present and record the checklist:

[1724] The terminal displays a summary of the selected book and a checklist to the user, who then records his or her daily activities based on the checklist and sends the data to the server.

[1725] 4. Generating and Presenting Feedback

[1726] Analysis of recorded data:

[1727] The server analyzes the practice records entered by the user using machine learning models and statistical methods, and also uses emotional data from the emotion engine to generate feedback that takes the user's emotional state into account.

[1728] Giving feedback:

[1729] The device presents the user with feedback sent from the server, including information about progress and areas for improvement.

[1730] Specific examples

[1731] For example, if a user chooses "The 7 Habits" as a self-help book, the server retrieves the book's data, tokenizes and cleans it, then uses GPT-3 to generate a summary and add it to the catalog. The user selects "The 7 Habits" from the catalog and receives the summary and checklist.

[1732] Checklist example:

[1733] [ ] Did you self-assess every day?

[1734] [ ] Did you make an independent decision?

[1735] Example of a generated AI prompt:

[1736] Please write a summary of "The 7 Habits" in the following format:

[1737] Key points of this book

[1738] Key Action Items

[1739] Practical Tips

[1740] Text: <insert text here>

[1741] In this way, a system for improving the efficiency of self-development is constructed, supporting users in practicing self-development continuously and effectively.By combining it with an emotion engine, it becomes possible to provide personalized feedback according to the user's emotional state.

[1742] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1743] Step 1:

[1744] The server accesses the API of the e-book platform and retrieves the text data of the self-help book. The API endpoint URL and access credentials are used as input, and the retrieved book data (JSON format) is output. Specifically, it sends a request to the API using the Python requests library (e.g., response = requests.get(API_URL, headers=headers)) and saves the retrieved data in JSON format (e.g., book_data = response.json()).

[1745] Step 2:

[1746] The server tokenizes and cleans the acquired book data. The acquired book data is used as input, and the output is the tokenized and cleaned data. Specifically, it uses a natural language processing library such as NLTK to split the text into words and punctuation marks (tokenization), and uses Python's regular expression library to remove unnecessary tags, line breaks, and spaces (e.g., clean_text = re.sub(r'\s+', ' ', book_data["text"])).

[1747] Step 3:

[1748] The server uses a generative AI model to generate a summary from the tokenized and cleaned data. It uses the cleaned text data and a prompt as input, and outputs the summary text. Specifically, it uses OpenAI's API to send the data along with the prompt (e.g., response = openai.Completion.create(engine="text-davinci-003", prompt=prompt, max_tokens=150)) and stores the generated summary in a variable (e.g., summary = response.choices[0].text.strip()).

[1749] Step 4:

[1750] The server organizes the summarized self-help books into a catalog. It takes the summary text and basic book information (title, author, etc.) as input, and outputs a catalog entry in JSON format. Specifically, it generates a data structure containing the summary text (e.g., catalog_entry = {"title": book_title, "author": book_author, "summary": summary}) and stores it in the database.

[1751] Step 5:

[1752] The server extracts specific actions from the summary and generates a checklist. The input is the summary text, and the output is a checklist. Specifically, it uses a text analysis algorithm to extract verbs and action points from the summary (e.g., actions = extract_actions_from_summary(summary)), and then creates a list of them (e.g., checklist = create_checklist(actions)).

[1753] Step 6:

[1754] The emotion engine analyzes user input, facial expressions, and vocal sounds to recognize emotions. It uses real-time facial and vocal data obtained from a camera and microphone as input, and outputs emotional data. Specifically, it uses OpenFace for facial recognition (e.g., emotion_face = analyze_facial_expression(image)) and TensorFlow for vocal analysis (e.g., emotion_voice = analyze_voice(voice_clip)).

[1755] Step 7:

[1756] The user browses a catalog of self-help books through a dedicated application, and selects and views the summary and checklist of a self-help book. The input is the catalog data stored on the server, and the output is the summary and checklist displayed to the user. Specifically, the mobile application displays the catalog screen, and retrieves and displays the self-help book data selected by the user.

[1757] Step 8:

[1758] The user records daily practice items based on the checklist, and the device sends the data to the server. The input is the practice data recorded by the user, and the output is the record data sent to the server. The specific operation is that the user enters data in the mobile application and sends the data to the server (e.g., send_to_server(record_data)).

[1759] Step 9:

[1760] The server analyzes the user's practice record and emotion data and generates feedback. It uses practice record data and emotion data as input, and outputs a feedback message. Specifically, it analyzes the data using machine learning models and statistical methods (e.g., feedback = generate_feedback(user_data, emotion_data)) and generates appropriate feedback.

[1761] Step 10:

[1762] The terminal presents the generated feedback to the user. The input is the feedback message sent from the server, and the output is the feedback displayed to the user. Specifically, the feedback is displayed on a message screen within the mobile application.

[1763] (Application example 2)

[1764] 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."

[1765] Conventional self-improvement support systems specialize in generating summaries and providing checklists to promote user growth, but lack the ability to generate feedback that takes into account the user's emotional state. As a result, they are unable to provide personalized feedback based on emotions that would help users maintain their self-improvement behavior. Furthermore, in the food delivery industry, there is a lack of systems that support self-improvement for delivery workers while they are working.

[1766] 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.

[1767] In this invention, the server includes means for acquiring self-help book data, means for tokenizing and cleaning the acquired data, means for generating summaries from the tokenized data using a generative AI model, means for organizing the summarized content in a catalog format, means for accepting a user's selection of a self-help book, means for presenting summaries and checklists of the selected self-help book, means for receiving a record of the user's practice, means for analyzing the practice status and generating feedback, means for presenting the generated feedback to the user, means for analyzing the user's emotional state, and means for adjusting the content of the feedback based on the user's emotional state. This makes it possible to provide personalized feedback based on the user's practice status and emotional state, allowing food delivery workers to efficiently engage in self-improvement while on the job.

[1768] "Self-help book data" is digital data of books and documents used as self-help books.

[1769] "Tokenization" is the process of dividing text data into smaller units such as words and punctuation marks.

[1770] "Cleaning" is the process of removing unnecessary tags, line breaks, and spaces from data to prepare it in a format that is easy to analyze.

[1771] A "generative AI model" is an algorithm or program that uses AI to generate natural language and summaries.

[1772] A "summary" is a short summary of the main points or content of a text or book.

[1773] "Catalog format" is a format in which information is organized and displayed by items such as title, author, and main points.

[1774] A "checklist" is a list of action items that a user should take.

[1775] "Feedback" is information such as suggestions for improvement or advice generated based on the practice situation and emotional state.

[1776] "Means for analyzing emotional state" refers to a method or system for analyzing emotions from the user's facial expressions, voice, etc.

[1777] The "means for adjusting the content of feedback based on emotional state" refers to a method or system that changes the feedback provided depending on the analyzed emotion.

[1778] This invention is a system for supporting users' self-development by efficiently utilizing the contents of self-help books, and is particularly targeted at delivery workers in the food delivery industry. This system is implemented using hardware and software including a server, a terminal, an emotion engine, a camera, and a microphone.

[1779] The server retrieves self-help book data from the e-book platform, tokenizes and cleans it, and then uses the tokenized data to generate summaries using a generative AI model. This generative AI model applies the GPT series of natural language generation models. The summaries are then organized into a catalog and saved in JSON format. This allows for efficient management of information and makes it easy for users to access.

[1780] Next, the device (e.g., a smartphone application) accepts user input. The user selects the desired book from a catalog of self-help books and receives a summary and a checklist. The checklist includes specific action items to be put into practice. The user records the actions they take each day and sends the data from the device to a server. For example, the checklist might include action items such as "Have you performed self-evaluation every day?" or "Have you made one independent decision per day?"

[1781] Furthermore, the emotion engine analyzes the user's emotional state using a camera and microphone. This analyzed emotional data is sent to a server, which generates feedback based on the user's progress and emotional state. The feedback includes personalized advice that takes the user's emotions into account, making it easier for the user to continue their self-improvement activities.

[1782] For example, if a delivery person opens the app and selects "The 7 Habits," the server retrieves the book's data, tokenizes it, and cleans it. A generative AI model then generates a summary and adds it to the catalog. The delivery person retrieves this summary from the catalog and records their actions based on a daily checklist. Meanwhile, an emotion engine recognizes the delivery person's emotional state from their facial expressions and tone of voice, and sends this data to the server. Based on the recorded data and emotion data, the server generates feedback such as, "Today's self-evaluation is good, but your independent decision-making skills are lacking. You need to work harder," and presents it to the delivery person via their device.

[1783] In this way, this invention is a system that supports users in continuing to work on self-improvement by streamlining the use of self-help books and providing personalized feedback that takes into account their emotional state. This system allows delivery workers, particularly in the food delivery industry, to efficiently engage in self-improvement while at work.

[1784] Examples of prompts:

[1785] "Set your goals for today as 'Perform daily self-evaluation' and 'Make independent decisions.' Judging from your emotional state, you seem a little tired today. Take a break and complete the practical tasks."

[1786] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1787] Step 1:

[1788] The server retrieves self-help book data using the API of the e-book platform. The input is the book ID, and the data retrieved from the API includes the book's text content. Specifically, the server sends an HTTP request and receives the e-book data. The output is the retrieved book data.

[1789] Step 2:

[1790] The server tokenizes and cleans the acquired book data. The input is the book data, and a natural language processing library is used to split the data into words and punctuation marks, and remove unnecessary characters and tags. Specifically, the server uses an NLP library to perform tokenization and regular expressions to perform cleaning. The output is the tokenized and cleaned data.

[1791] Step 3:

[1792] The server generates a summary using a generative AI model based on the tokenized and cleaned data. The input is the tokenized data, and the generative AI model (e.g., GPT sequence) extracts important content and generates a summary. Specifically, the server inputs the tokenized data into the generative AI model and receives the summary generated by the model. The output is the summarized text.

[1793] Step 4:

[1794] The server organizes the generated summary text into a catalog format. The input is the summary text, which is converted into JSON format for each item, such as title, author, and main points. Specifically, the server parses the summary text and creates a data structure corresponding to each item. The output is JSON data in catalog format.

[1795] Step 5:

[1796] The terminal accepts the user's selection of a self-help book. The input is the user's selection information, and based on that information, it presents a summary and checklist of the corresponding book from the catalog. In concrete terms, the terminal receives the user's input, retrieves the corresponding data, and displays it. The output is the summary and checklist presented to the user.

[1797] Step 6:

[1798] The user records the actions based on the checklist. The input is the user's recorded information, which is sent from the terminal to the server. In concrete terms, the user records an action item, and the terminal sends the information to the backend. The output is the action record stored on the server.

[1799] Step 7:

[1800] The emotion engine analyzes the user's emotional state using a camera and microphone. The input is the user's facial expression and vocal data, and the emotional state is evaluated through analysis. Specifically, the emotion engine acquires data from the camera and microphone and analyzes it using a machine learning algorithm. The output is evaluated emotional data.

[1801] Step 8:

[1802] The server generates feedback based on practice status data and emotion data and presents it to the user. The input is practice record data and emotion data, which are analyzed using machine learning models and statistical methods to generate personalized feedback. Specifically, the server summarizes the analysis results, generates a feedback message, and sends it to the terminal. The output is the feedback message presented to the user.

[1803] 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.

[1804] 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.

[1805] 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.

[1806] 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.

[1807] 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.

[1808] 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.

[1809] 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).

[1810] 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.

[1811] 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."

[1812] 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.

[1813] 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).

[1814] 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.

[1815] 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.

[1816] 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.

[1817] 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.

[1818] 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.

[1819] 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.

[1820] 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.

[1821] 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.

[1822] 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.

[1823] 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.

[1824] The following is further disclosed regarding the above embodiment.

[1825] (Claim 1)

[1826] A means of obtaining self-help book data;

[1827] A means of tokenizing and cleaning the acquired data;

[1828] a means for generating a summary from the tokenized data using a generative AI model; and

[1829] A means of organizing the summarized content in catalog form;

[1830] means for accepting a selection of a self-help book by a user;

[1831] A means of presenting summaries and checklists of selected self-help books;

[1832] means for receiving a record of user actions;

[1833] a means of analyzing practice and generating feedback;

[1834] The system includes a means for presenting the generated feedback to a user.

[1835] (Claim 2)

[1836] 10. The system of claim 1, wherein the generative AI model includes means for generating summaries using natural language processing.

[1837] (Claim 3)

[1838] 10. The system of claim 1, wherein the checklist includes a means for recording the user's practices in a diary format.

[1839] "Example 1"

[1840] (Claim 1)

[1841] A means for acquiring electronic book data;

[1842] A means of tokenizing and cleaning the acquired data;

[1843] means for generating a summary from the tokenized data using a generative model;

[1844] A means of organizing the summarized content in catalog form;

[1845] A means of extracting practice items from the summary and generating a checklist;

[1846] means for accepting a book selection by a user;

[1847] a means of presenting summaries and checklists of selected books;

[1848] means for receiving a record of user actions;

[1849] a means of analyzing practice records and generating feedback;

[1850] The system includes a means for presenting the generated feedback to a user.

[1851] (Claim 2)

[1852] The system of claim 1 , wherein the generative model generates the summary using natural language processing.

[1853] (Claim 3)

[1854] 10. The system of claim 1, wherein the checklist records the user's practices in a diary format.

[1855] "Application Example 1"

[1856] (Claim 1)

[1857] a means for obtaining personal development data;

[1858] A means of tokenizing and cleaning the acquired data;

[1859] a means for generating a summary from the tokenized data using a generative AI model; and

[1860] A means of organizing the summarized content in catalog form;

[1861] means for accepting a selection of a self-help guidebook by a user;

[1862] A means of presenting summaries and checklists of selected self-help instructional materials;

[1863] means for receiving a record of user actions;

[1864] a means of analyzing practice and generating feedback;

[1865] means for presenting the generated feedback to the user;

[1866] A means to provide summaries and practice checklists based on in-store experiences and purchases;

[1867] A system including a means for providing feedback based on a history of participation in store events.

[1868] (Claim 2)

[1869] 10. The system of claim 1, wherein the generative AI model includes means for generating summaries using natural language processing.

[1870] (Claim 3)

[1871] 10. The system of claim 1, wherein the checklist includes a means for recording the user's practices in a diary format.

[1872] "Example 2: Combining Emotion Engines"

[1873] (Claim 1)

[1874] A means of obtaining self-help book data;

[1875] A means of tokenizing and cleaning the acquired data;

[1876] a means for generating a summary from the tokenized data using a generative AI model; and

[1877] A means of organizing the summarized content in catalog form;

[1878] A means of extracting specific practice items from the summary and generating a checklist;

[1879] means for accepting a selection of a self-help book by a user;

[1880] A means of presenting summaries and checklists of selected self-help books;

[1881] A means of recognizing emotions by analyzing user input, facial expressions, and voice;

[1882] means for receiving a record of user actions;

[1883] a means of analyzing practice situations and emotional data and generating feedback;

[1884] The system includes a means for presenting the generated feedback to a user.

[1885] (Claim 2)

[1886] 10. The system of claim 1, wherein the generative AI model includes means for generating summaries using natural language processing.

[1887] (Claim 3)

[1888] 10. The system of claim 1, wherein the checklist includes a means for recording the user's practices in a diary format.

[1889] "Application example 2 when combining emotion engines"

[1890] (Claim 1)

[1891] A means of obtaining self-help book data;

[1892] A means of tokenizing and cleaning the acquired data;

[1893] a means for generating a summary from the tokenized data using a generative AI model; and

[1894] A means of organizing the summarized content in catalog form;

[1895] means for accepting a selection of a self-help book by a user;

[1896] A means of presenting summaries and checklists of selected self-help books;

[1897] means for receiving a record of user actions;

[1898] a means of analyzing practice and generating feedback;

[1899] means for presenting the generated feedback to the user;

[1900] means for analyzing the emotional state of a user;

[1901] The system includes a means for adjusting the content of the feedback based on the emotional state.

[1902] (Claim 2)

[1903] 10. The system of claim 1, wherein the generative AI model includes means for generating summaries using natural language processing.

[1904] (Claim 3)

[1905] 10. The system of claim 1, wherein the checklist includes a means for recording the user's practices in a diary format. [Explanation of symbols]

[1906] 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 of obtaining self-help book data; A means of tokenizing and cleaning the acquired data; a means for generating a summary from the tokenized data using a generative AI model; and A means of organizing the summarized content in catalog form; means for accepting a selection of a self-help book by a user; A means of presenting summaries and checklists of selected self-help books; means for receiving a record of user actions; a means of analyzing practice and generating feedback; The system includes a means for presenting the generated feedback to a user.

2. The system of claim 1 , wherein the generative AI model includes means for generating summaries using natural language processing.

3. 2. The system of claim 1, wherein the checklist includes a means for recording the user's practices in a diary format.

Images