System

Abstract

A system is provided.SOLUTION: A system including means for performing an interview with a person having specialized knowledge or experience in a specific field by an automatic generation AI, and generating a result of the interview as an article, means for allowing a user to perform new registration or login, means for generating an interview form and transmitting the form to a target person, means for converting the result of the interview into an article by using a generation AI, means for disclosing the article, and means for collecting user feedback on the article and using the feedback for improving content.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In modern society, information from specialists with specialized knowledge and experience is a valuable resource, but it is difficult to share this information widely and make it understandable to many people. Furthermore, current information-sharing systems do not adequately facilitate direct interviews with specialists, effectively turn the content into articles, or accurately deliver this information to readers. This situation limits opportunities for average users to discover new hobbies. Therefore, there is a need to effectively collect and share information from specialists and provide users with new topics of interest. [Means for solving the problem]

[0005] The present invention provides a system that uses an automatic generation AI to conduct interviews with people with specialized knowledge and experience in a specific field and generate articles based on the interview results. Specifically, the system includes a means for a user to register or log in, generate an interview form, and send it to the target person. The system also includes a means for using the generation AI to write an article based on the interview results and publish the article, as well as a means for collecting user feedback on the article and using it to improve the content. Furthermore, the system includes a means for the generation AI to generate customized questions based on the target person's profile information, publish the generated article so that other users can view it, and store feedback on the article in a database. This allows for effective sharing of information about people with specialized knowledge and provides users with new hobbies and interests.

[0006] An "interview" is a question and answer process for gathering information from a person with specialized knowledge or experience.

[0007] "Generative AI" refers to systems or algorithms that use artificial intelligence techniques to automatically generate text or content.

[0008] An "article" is text content generated based on the results of an interview, and is intended for users to view.

[0009] "User registration" is the act of a new user providing their information to the system and creating an account.

[0010] "Logging in" is the act of an existing user accessing the system using their account information.

[0011] An "interview form" is a formatted document containing interview questions that is presented to a subject.

[0012] "Target person" refers to a person who has specific professional knowledge or experience.

[0013] "Profile Information" means basic information about a person, including details about their expertise and experience.

[0014] "Publishing" refers to the act of displaying the generated article on the system so that it can be widely viewed by users.

[0015] "Feedback" refers to information such as impressions, opinions, and suggestions for improvement provided by users after viewing an article.

[0016] A "database" is a system for efficiently storing and managing collected information and data. [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] This invention is a system that uses automatic generation AI to conduct interviews with people who have specialized knowledge and experience in a specific field (hereinafter referred to as specialists), generates the interview results as articles, and provides them to users. This system is composed of the following steps.

[0039] First, a user registers or logs in. When registering, the device provides a form for entering basic information such as username, password, and email address, which is then sent to the server. The server verifies the received information and stores it in a database if there are no problems. Similarly, if an existing user enters login information, the server authenticates them and, if successful, allows the user to access the system.

[0040] Next, an interview form for the specialist is generated. The server retrieves the specialist's profile information from the database and passes it to the generation AI to generate customized questions. The generated questions are reconstructed as an interview form and sent to the specialist's device.

[0041] Next, the specialist uses the terminal to enter answers into the interview form and send them to the server, which then stores the received answer data in a database.

[0042] The server then passes the saved response data back to the AI ​​generator to generate a detailed article, which is then stored in a database by the server and prepared for publication.

[0043] Once an article is published, the server displays it on the platform for all users to see, and users can provide feedback on the article, which is sent back to the server and stored in a database.

[0044] As a concrete example, suppose a specialist who is an expert in a particular field (e.g., craft making) logs into the system and updates his or her profile. Based on this profile information, the server generates customized questions such as, "Tell us about your most challenging project" and "What important lessons did you learn through that project?" These questions are provided to the specialist as an interview form, and the specialist answers them. After the response data is sent and stored on the server, the generation AI uses the content to create a detailed article. This article is finally published, allowing other users to view it and discover the appeal of crafts as a new hobby, as well as provide feedback.

[0045] In this way, the system allows for the effective sharing of specialized knowledge and experience, enabling many users to discover new hobbies and interests.

[0046] The processing flow will be explained below.

[0047] Step 1:

[0048] The user registers or logs in. The user clicks the "Register" button on the device and enters the user name, password, email address, etc. Once the registration information is complete, the device sends this information to the server.

[0049] Step 2:

[0050] The server verifies the received user information. It checks the email address format and password strength, and if there are no problems, it saves the user information in the database. It returns a message to the user that registration is complete.

[0051] Step 3:

[0052] The terminal displays a login screen, and the user enters a username and password. The terminal then sends the input data to the server.

[0053] Step 4:

[0054] The server verifies the login information it receives. If it is correct, it authenticates the user and allows access. If it is incorrect, it returns an error message.

[0055] Step 5:

[0056] The server retrieves the specialist's profile information from the database, including the specialist's area of ​​expertise and past experience.

[0057] Step 6:

[0058] The server passes the acquired profile information to the generation AI, which generates customized interview questions. The generated questions are then reconstructed into an interview form.

[0059] Step 7:

[0060] The server sends the generated interview form to the specialist's terminal, which displays it to the specialist.

[0061] Step 8:

[0062] The user (specialist) enters answers into the interview form. After entering the necessary answers, the user clicks the "Submit" button and the answer data is sent to the server.

[0063] Step 9:

[0064] The server saves the received response data in a database, and once saving is complete, returns a notification of transmission completion to the device.

[0065] Step 10:

[0066] The server then passes the saved response data back to the AI ​​generator, which then generates a detailed article based on that data.

[0067] Step 11:

[0068] The server saves the generated article to the database, and once saved, sets the status to "ready to publish".

[0069] Step 12:

[0070] The server publishes new articles on the platform, where they become available for all users to view.

[0071] Step 13:

[0072] The device displays a notification of the published article to the user, who can then view the article and post comments and impressions.

[0073] Step 14:

[0074] The user enters feedback on the article and clicks the "Submit" button. The device sends the feedback to the server.

[0075] Step 15:

[0076] The server saves the received feedback in the database, and once saving is complete, returns a feedback completion notification to the user.

[0077] Through these steps, this system can effectively compile interviews with specialists with specialized knowledge and experience into articles, and provide many users with new hobbies and interests.

[0078] Example 1

[0079] 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."

[0080] The present invention aims to provide a system that allows users to easily acquire new knowledge and interests by automatically conducting interviews with people who have specialized knowledge and experience in a specific field and generating and publishing the results of those interviews as articles.The objective of this system is to automate the process of effectively collecting specialized information and turning it into articles, thereby improving user convenience.

[0081] 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.

[0082] In this invention, the server includes a means for a user to register or log in, a means for transmitting user information to the server using a terminal, and a means for verifying the user information received by the server and storing it in a database, thereby enabling user information to be registered and managed reliably.

[0083] The server includes a means for acquiring profile information of the target person and generating customized questions using a generative AI model, a means for generating an interview form and sending it to the target person, and a means for the target person to answer the interview form and send it to the server using a terminal, thereby enabling individual interviews to be conducted efficiently and automatically.

[0084] Furthermore, the server includes means for creating articles based on the interview results using the generative AI model and storing the articles in a database, means for publishing the articles and making them available for other users to view, and means for collecting user feedback on the articles and storing the feedback in a database, thereby enabling the generated articles to be published quickly and for the articles to be improved based on user feedback.

[0085] A "user" is a person who accesses the system and provides information or views content.

[0086] A "terminal" is a device used by a user for operation, and includes, for example, a computer, a smartphone, a tablet, and the like.

[0087] The "Server" is the central computer system that receives, verifies, and stores user-submitted information and automates the interview using the generative AI model.

[0088] A "database" is a system that systematically stores user information, interview results, generated articles, feedback, etc.

[0089] "Profile information" is information about a person with specialized knowledge or experience in a particular field, and is used to generate customized questions.

[0090] A "generative AI model" is an artificial intelligence model that automatically generates new content based on generated text, and includes, for example, models that use natural language processing technology.

[0091] An "Interview Form" is an electronic form for presenting customized questions to a Specialist.

[0092] "Response data" refers to the response information entered by the subject in the interview form.

[0093] An "article" is text content generated using a generative AI model based on interview form response data.

[0094] "Feedback" refers to comment information such as impressions and suggestions for improvement provided by users regarding an article.

[0095] "Publishing" refers to the act of displaying the generated article on a web platform so that it can be viewed by general users.

[0096] This invention is a system that uses automatic generation AI to conduct interviews with people with specialized knowledge and experience (hereinafter referred to as specialists), generates articles based on the interview results, and provides them to users. This system is implemented using the following specific hardware and software.

[0097] First, a user accesses the system using a terminal. The terminal can be a computer, smartphone, tablet, etc. The user registers or logs in. The terminal provides a form for entering user information, and the information entered by the user is sent to the server. This information includes the user name, password, email address, etc.

[0098] The server verifies the received user information and stores it in the database if there are no problems. Validation can be performed using a web framework such as Django. For new users, the server verifies that the registration information does not overlap with existing data, and for valid logins, the server verifies that the entered information matches the information in the database.

[0099] Next, the server retrieves the specialist's profile information from the database. Based on the retrieved information, it generates customized questions. This process uses a generative AI model (e.g., OpenAI's GPT-3®). The prompt for the generative AI model is as follows:

[0100] Example prompt sentence:

[0101] "The specialist's name is ____. He is an expert in crafting. Generate questions for him such as:

[0102] 1. Tell us about your most challenging project.

[0103] 2. What are some important lessons you learned through the project?

[0104] 3. What crafts would you recommend for beginners?

[0105] The server reconstructs the generated questions as an interview form and sends it to the specialist's terminal. The specialist uses the terminal to enter answers into the interview form, and the terminal sends the entered answers to the server. The server stores the received answer data in a database.

[0106] The server then passes the saved response data back to the generation AI, which then generates a detailed article. For example, the generation AI might construct a sentence like, "Mr. / Ms. XX's most challenging project was XX." The generated article is then stored in a database by the server, ready for publication.

[0107] Once an article is published, the server displays it on the platform for all users to view, allowing them to gain new knowledge and interest. Furthermore, users can provide feedback on articles, which they send from their devices to the server. The server stores the received feedback in a database and uses it to improve the article.

[0108] This system automatically collects and systematically shares specialized knowledge and experience. Furthermore, by improving the content of articles based on user feedback, it becomes possible to provide more useful information. This is a specific embodiment of the present invention.

[0109] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0110] Step 1:

[0111] User registration or login

[0112] 1.1 A user accesses the system from a terminal through a web browser.

[0113] 1.2 The device displays a form for the user to sign up or log in.

[0114] Input: Personal information such as username, password, and email address

[0115] Output: User information to be sent

[0116] 1.3 The user enters the required information and clicks the "Submit" button.

[0117] 1.4 The terminal sends the entered information to the server.

[0118] Step 2:

[0119] Server verifies and stores user information

[0120] 2.1 The server verifies the received user information.

[0121] Input: Submitted user information

[0122] Output: Verification result (success / failure)

[0123] 2.2 In the case of new registration, the server checks whether the information is a duplicate of existing data in the database. In the case of login, the server checks whether the input information matches the information in the database.

[0124] 2.3 If the verification is successful, the server stores the user information in the database.

[0125] 2.4 The server then sends a message to the terminal indicating successful authentication.

[0126] Input: Validation result

[0127] Output: Authentication message

[0128] Step 3:

[0129] Obtaining specialist profile information and generating customized questions

[0130] 3.1 The server retrieves the specialist's profile information from the database.

[0131] Input: Specialist User ID

[0132] Output: Profile information

[0133] 3.2 Based on the profile information obtained by the server, a prompt sentence is input to the generative AI model (e.g., OpenAI GPT-3).

[0134] Input: Profile information, prompt text

[0135] Output: Customized question

[0136] 3.3 The server reconstructs the generated questions into an interview form and sends it to the specialist's terminal.

[0137] Input: Customized Question

[0138] Output: Interview form

[0139] Step 4:

[0140] Enter and submit answers to the interview form

[0141] 4.1 The specialist uses the terminal to enter responses into the interview form.

[0142] Input: Interview Form

[0143] Output: Response data

[0144] 4.2 The Specialist completes the response and clicks the "Submit" button.

[0145] 4.3 The terminal sends the entered response data to the server.

[0146] Step 5:

[0147] Response data saved on the server

[0148] 5.1 The server validates the response data received.

[0149] Input: Submitted response data

[0150] Output: Verification results

[0151] 5.2 If the verification is successful, the server stores the response data in the database.

[0152] Input: Validated response data

[0153] Output: Answer data stored in a database

[0154] Step 6:

[0155] Generating interview articles using generative AI models

[0156] 6.1 The server passes the saved answer data to a generative AI model (e.g., OpenAI GPT-3) to generate detailed articles.

[0157] Input: Response data

[0158] Output: The generated article

[0159] 6.2 The server stores the generated articles in a database.

[0160] Step 7:

[0161] Publish your article and gather feedback

[0162] 7.1 The server displays the ready-to-publish articles on the web platform.

[0163] Input: Generated article

[0164] Output: Published articles

[0165] 7.2 Users view articles and provide feedback.

[0166] Input: Feedback information

[0167] Output: Feedback to be sent

[0168] 7.3 The device sends the user-entered feedback to the server.

[0169] 7.4 The server stores the received feedback in a database.

[0170] Input: Submitted feedback

[0171] Output: Feedback stored in a database

[0172] (Application example 1)

[0173] 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."

[0174] Conventional article generation systems using human interviews have faced challenges such as the high labor costs of conducting interviews and writing articles, as well as the difficulty of sharing specialized knowledge. Furthermore, the generated content needed to be provided in a format that was useful to a wide range of users, not limited to a specific category. However, previous technology did not provide a means to easily conduct interviews, generate articles, and publish them as a smartphone application.

[0175] 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.

[0176] In this invention, the server includes: means for conducting interviews with people with specialized knowledge and experience in a specific field using automatic generation AI and generating articles based on the interview results; means for users to register or log in; means for generating interview forms and sending them to the target individuals; means for using the generation AI to write articles about the interview results and publishing the articles; means for collecting user feedback on the articles and using it to improve content; means for making the generated articles available to other users in a content distribution service; and means for installing the articles as a smartphone application. This allows experts' knowledge and experience to be shared effectively, enabling users to discover new knowledge and interests. Furthermore, the smartphone application improves convenience and accessibility, potentially attracting a wide range of users.

[0177] A "person with specialized knowledge or experience in a particular field" is a person who has in-depth knowledge or practical experience in a particular specialized field that goes beyond general understanding.

[0178] An "interview" is a form of communication in which specific questions are answered by someone with specialized knowledge or experience.

[0179] "Automatic generation AI" refers to programs or systems that use artificial intelligence technology to automatically generate sentences, questions, articles, etc.

[0180] An "article" is written content that is based on interview results or other information.

[0181] "User registration" is the process by which a new user registers the personal information and authentication information required to use the system.

[0182] "Login" refers to the process by which an existing user enters the necessary authentication information to access a system and is authenticated.

[0183] An "interview form" is a written or electronic format that provides the questions and information needed to conduct an interview.

[0184] "Profile information" refers to personal information about the person being interviewed, such as their background, area of ​​expertise, and experience.

[0185] "Customized Questions" are individual questions created to drill down into specific topics based on a person's profile information.

[0186] "Feedback" refers to ratings and opinions provided by users regarding articles and content.

[0187] A "content distribution service" is a service that makes generated content available on the Internet so that users can view and access it.

[0188] A "smartphone application" is a software program that runs on a smartphone and through which services can be used.

[0189] A "database" is a system for efficiently and safely storing and managing collected data and information.

[0190] The system for implementing this invention uses an automatic generation AI to conduct interviews with people with specialized knowledge and experience in a specific field, and then generates an article based on the results of the interview and provides it to users. This system is primarily based on the interaction between a server, a terminal, and a user.

[0191] System configuration

[0192] 1. User Registration and Login:

[0193] Server: The user is presented with a form to register and enters basic information such as username, password, email address, etc. The information is sent to the server, which validates it and stores it in a database. Similarly, when an existing user logs in, the information is authenticated and, if successful, the user is granted system access.

[0194] 2. Generate the interview form:

[0195] Server: Retrieves specialist profile information from the database and passes it to the generation AI to generate customized questions. The generated questions are organized into an interview form and sent to the specialist's device.

[0196] 3. Collecting interview responses:

[0197] Terminal: The specialist enters answers into the interview form and sends the answers to the server via the terminal.

[0198] Server: Stores the received response data in a database.

[0199] 4. Article generation and publishing:

[0200] Server: The saved response data is passed to the AI ​​again to generate detailed articles. The generated articles are stored in a database and can be viewed by other users once they are ready to be published. They can also be provided in a format that can be installed as a smartphone application.

[0201] 5. Gathering Feedback:

[0202] Users: can provide feedback on articles, which will be sent to the server and stored in the database to improve the content.

[0203] Processing Details

[0204] 1. Hardware and Software:

[0205] Server: Runs the main program and manages the database. Builds an API server using the Flask framework and manages the database using SQLite.

[0206] Terminal: Devices used by specialists and general users, including smartphones, tablets, etc.

[0207] Generative AI models: Used for specific interview question generation and article generation. These include models like InterviewAI and ArticleGenerationAI.

[0208] Specific examples

[0209] Example of interview generation for experts

[0210] Profile Information:

[0211] Name: Yamada Taro

[0212] Specialty: Crafts

[0213] prompt:

[0214] Taro Yamada, tell us about your most challenging craft project and the lessons you learned.

[0215] Example questions generated:

[0216] 1. Tell us about your most challenging project.

[0217] 2. What are some important lessons you learned through the project?

[0218] The purpose of this system is to effectively share specialized knowledge and experience with many users through such concrete examples. Because it can be used through a smartphone application, it is convenient and accessible, and we expect it to be used by a wide range of users.

[0219] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0220] Step 1:

[0221] User Registration

[0222] User: To create a new account, a user enters basic information such as a username, password, and email address.

[0223] Server: The server receives this basic information, verifies the validity of the data, and if there are no problems, stores this information in a database (SQLite).

[0224] Input: Username, Password, Email Address.

[0225] Output: Validated user data is stored in the database.

[0226] Step 2:

[0227] Log in

[0228] User: An existing user logs into the system by entering their username and password.

[0229] Server: The server receives the entered authentication information, checks it against existing data in a database, and if successful, grants the user access to the system.

[0230] Input: Username, Password.

[0231] Output: If authentication is successful, grant access to the system. If authentication fails, return an error message.

[0232] Step 3:

[0233] Obtaining profile information and generating questions

[0234] Server: Retrieves specialist profile information from the database and passes it to the generation AI (InterviewAI).

[0235] Generative AI: Generates customized questions based on profile information.

[0236] Input: Specialist profile information.

[0237] Output: A customized interview form.

[0238] Server: Reconstructs the generated questions into an interview form and sends it to the specialist's terminal.

[0239] Step 4:

[0240] Enter and submit your interview answers

[0241] Specialist: Enter answers into the interview form and send them to the server via the terminal.

[0242] Server: Stores the received response data in a database.

[0243] Input: Specialist response data.

[0244] Output: Response data stored in a database.

[0245] Step 5:

[0246] Article Generation

[0247] Server: Pass the saved answer data to the generation AI (ArticleGenerationAI) to generate detailed articles.

[0248] Generative AI: Generates articles based on response data.

[0249] Input: Specialist response data.

[0250] Output: The generated article.

[0251] Server: Stores the generated articles in a database and prepares them for publication.

[0252] Step 6:

[0253] Article published

[0254] Server: The generated articles are published on the platform, allowing users to view them. They are also provided in a format that can be installed as a smartphone application.

[0255] Input: The generated article.

[0256] Output: The published article.

[0257] Step 7:

[0258] Feedback collection and storage

[0259] Users: Can view articles and provide feedback.

[0260] Server: Receives user feedback and stores it in a database.

[0261] Input: User feedback.

[0262] Output: Feedback stored in a database.

[0263] 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.

[0264] This invention is a system that uses an automatic generation AI to conduct interviews with people with specialized knowledge and experience in a specific field (hereinafter referred to as specialists), generates articles based on the results of the interviews, and then uses an emotion engine to analyze user feedback and emotions at the time of responses, thereby improving the quality of the content. This system is composed of the following steps.

[0265] First, a user registers or logs in. When registering, the device provides a form for entering basic information such as username, password, and email address. Once the information is entered, the device sends this information to the server. The server verifies the received information and stores it in the database if there are no problems. If an existing user enters login information, the server performs authentication, and if successful, the user can access the system.

[0266] Next, an interview form for the specialist is generated. The server retrieves the specialist's profile information from the database and passes it to the generation AI to generate customized questions. The generated questions are reconstructed as an interview form and sent to the specialist's device.

[0267] The specialist uses a terminal to enter answers into the interview form and send them to the server. The server stores the received answer data in a database. At this point, the server activates an emotion engine to analyze the answer data and recognize the emotional state of the specialist at the time of answering. The recognition results are stored along with the answer data and can be used to improve the quality of the interview content.

[0268] The server then passes the saved response data back to the AI ​​generator to generate a detailed article. The AI ​​uses this data to create a specific and detailed article. The generated article is then stored in the database by the server, ready for publication.

[0269] Once an article is published, the server displays it on the platform for all users to view. Users can also provide feedback on the article. When the feedback data is sent to the server, an emotion engine analyzes the content and recognizes the user's emotional state. Based on the recognition results, the server improves the content.

[0270] As a concrete example, consider a scenario in which a craftsman logs into the system and updates his or her profile. Based on this information, the server generates questions such as, "Tell us about your most challenging project" and "What important lessons did you learn from that project?" The specialist fills out an interview form, and the emotion engine analyzes the specialist's emotional state. The server stores the response data along with the specialist's emotional state, and then publishes a detailed article based on this information on the platform. When other users view the article and provide feedback, the emotion engine is also used, and future content is improved based on the obtained emotional data.

[0271] In this way, this system can effectively turn interviews with specialists with specialized knowledge and experience into articles, and by utilizing an emotion engine, it is possible to provide many users with new hobbies and interests.

[0272] The processing flow will be explained below.

[0273] Step 1:

[0274] A user registers or logs in. The user clicks the "Register" button on the device and enters information such as a username, password, and email address. Once the information is entered, the device sends it to the server.

[0275] Step 2:

[0276] The server verifies the user information it receives. It checks the email address format and password strength, and if there are no problems, it saves the user information in the database. It returns a message to the user that registration is complete to the terminal. If an existing user enters login information, the server performs authentication processing, and if successful, grants the user access rights.

[0277] Step 3:

[0278] The server retrieves the specialist's profile information from the database, including their area of ​​expertise, past projects, experience, etc.

[0279] Step 4:

[0280] The server passes the acquired profile information to the generation AI, which generates customized interview questions. The generation AI then creates the questions and reconstructs them into an interview form.

[0281] Step 5:

[0282] The server sends the generated interview form to the specialist's terminal, which displays the interview form and allows the specialist to enter answers.

[0283] Step 6:

[0284] The user (specialist) uses the terminal to enter answers into the interview form. Once the answers are complete, the user clicks the "Submit" button to send the answer data to the server.

[0285] Step 7:

[0286] The server stores the received answer data in a database. At this time, the server activates an emotion engine to analyze the data to recognize the emotional state of the specialist at the time of answering. The analysis results are stored together with the answer data.

[0287] Step 8:

[0288] The server then passes the saved response data back to the AI ​​generator, which then creates a detailed article based on the interview content.

[0289] Step 9:

[0290] The server saves the generated article to the database, and once done sets the status to indicate that the article is ready to be published.

[0291] Step 10:

[0292] The server publishes new articles on the platform, where they become available for all users to view.

[0293] Step 11:

[0294] The device displays a notification of the published article to the user, who can then view the article and post comments and impressions.

[0295] Step 12:

[0296] The user enters feedback on the article and clicks the "Submit" button. The device sends the feedback to the server.

[0297] Step 13:

[0298] The server stores the received feedback in a database. At this time, the server activates the emotion engine again to analyze the user's feedback and recognize their emotional state. The server then improves the content based on the analysis results.

[0299] Step 14:

[0300] The server sends a feedback completion notification to the terminal, which the terminal displays to the user, completing the feedback process.

[0301] Through these steps, this system can effectively turn interviews with specialists with specialized knowledge and experience into articles, and by using an emotion engine to analyze user feedback and the emotions expressed when answering, it can improve the quality of the content and provide many users with new hobbies and interests.

[0302] Example 2

[0303] 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."

[0304] In order to effectively turn interviews with specialists (people with specialized knowledge and experience in a specific field) into articles and improve the quality of those articles, it is important to improve the content by incorporating the depth and variety of the interview content and reader feedback. However, conventional systems have difficulty incorporating the emotions of specialists and readers, making it difficult to fully utilize feedback to improve the content. Furthermore, there is a lack of customization in the automatic generation of interview questions and the article-writing process, which means that the results of specialized interviews are not fully reflected in the articles.

[0305] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0306] In this invention, the server includes means for using an automatic generation AI to conduct interviews with people who have specialized knowledge and experience in a specific field and generate articles based on the interview results, means for a user to register or log in, means for generating an interview form and sending it to the person, means for using the generation AI to write an article about the interview results and publishing the article, means for collecting user feedback on the article and using the feedback to improve the content, means for using an emotion engine to analyze the person's emotional state at the time of their response, and means for using the emotion engine to analyze the emotional state of the user's feedback. This makes it possible to improve the quality of specialized interviews by taking the emotional state into consideration and to continuously improve the content based on the feedback.

[0307] "Automatic generation AI" is an artificial intelligence system that automatically generates text using natural language processing technology.

[0308] A "server" is a central processing unit that processes and manages data on a network.

[0309] A "terminal" is a device through which a user enters data or accesses information.

[0310] "User registration" is the process by which a user provides information about themselves and creates an account in order to use the system.

[0311] "Login" is the process by which an existing user is authenticated to access a system.

[0312] An "interview form" is a formal document containing specific questions that the interviewee uses to write their responses.

[0313] "Generative AI" is an artificial intelligence model that automatically generates new text based on given data or prompts.

[0314] "Articling" is the process of converting received data and information into an article format for readers.

[0315] "Publishing" is the process of making a generated article accessible to the public.

[0316] "Feedback" refers to the evaluations and opinions that users provide regarding articles and services.

[0317] An "emotion engine" is a software system for analyzing emotions in text and recognizing emotional states.

[0318] "Emotional state" refers to the emotional response of the person who generated the text and the user who provided the feedback.

[0319] A "database" is a system for storing and managing structured data.

[0320] "Profile information" refers to detailed information such as the background and qualifications of a user or expert.

[0321] This invention is a system that uses automatic generation AI to conduct interviews with people (specialists) who have specialized knowledge and experience in a specific field, generates the interview results as articles, and further improves the quality of content by using an emotion engine to analyze user feedback and emotions at the time of response.

[0322] The system includes the following major hardware and software components:

[0323] Server: The central unit that processes, manages, and stores data.

[0324] Terminal: A device that allows a user to input data or display information. Examples include personal computers and smartphones.

[0325] Generative AI: An artificial intelligence system that generates text based on interview results and prompts. OpenAI GPT-3 is used as an example.

[0326] Emotion engine: Software that analyzes the emotional state of text provided by a user or specialist. For example, IBM Watson® Tone Analyzer is used.

[0327] System Overview

[0328] First, a user registers or logs in. The device provides a form for entering basic information such as username, password, and email address, and then sends the information to the server. The server verifies the received information and stores it in a database if there are no problems. If the user is an existing user, the server authenticates the entered login information, and if successful, the user is allowed to access the system.

[0329] Next, an interview form for the specialist is generated. The server retrieves the specialist's profile information from the database and passes it to the generation AI to generate customized questions. For example, a question might be generated such as, "Tell us about your most challenging project." The generated questions are reconstructed as an interview form and sent to the specialist's device.

[0330] The specialist uses a terminal to enter answers into the interview form and send them to the server. The server stores the received answer data in a database. At this point, the server activates an emotion engine to analyze the emotional state of the specialist at the time of answering. The analysis results are stored along with the answer data and are used to improve the quality of the interview content.

[0331] The server then passes the saved response data back to the AI ​​generator to generate a detailed article. The generated article is specific and detailed. For example, a detailed article is generated based on the interview responses, such as "what the specialist described as the most challenging project." The generated article is then stored in a database by the server and prepared for publication.

[0332] Once an article is published, the server displays it on the platform for all users to view. Users can also provide feedback on the article. When the feedback data is sent to the server, the emotion engine analyzes its content and recognizes the user's emotional state. Based on the recognition results, the server improves the content.

[0333] Examples of concrete examples and prompts

[0334] Specific examples

[0335] Consider a scenario in which a craftsman logs into the system and updates his or her profile. During this process, the server generates questions based on the specialist's profile information, such as "Tell us about your most challenging project" and "What important lessons did you learn through this project?" The specialist fills out an interview form, and the emotion engine analyzes the specialist's emotional state. The server stores the emotional state along with the response data, and publishes a detailed article based on this information on the platform. Furthermore, the emotion engine is also used when other users view the article and provide feedback on their impressions and opinions. The obtained emotion data is used to improve future content.

[0336] Prompt Sentence Examples

[0337] "Consider questions that can be generated based on the specialist's profile information. For example, generate questions about their most challenging project and the key lessons learned through that project."

[0338] In this way, this system can effectively turn interviews with specialists with specialized knowledge and experience into articles, and by utilizing an emotion engine, it is possible to provide many users with new hobbies and interests.

[0339] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0340] Step 1: User registration and login

[0341] Input: A user accesses the new registration or login page using a terminal. If registering for the first time, they enter basic information such as their username, password, and email address. If they are an existing user, they enter their username and password.

[0342] Specific operation: The terminal displays a new registration form or login form. The user enters the required information and presses the submit button. The terminal then sends this information to the server.

[0343] Data processing and calculation: The server verifies the received information and stores it in the database in the case of new registration. In the case of login, it compares it with the information stored in the database.

[0344] Output: If new registration is successful, the message "Registration complete" is displayed, and if login is successful, access to the system is permitted. If authentication is unsuccessful, an "Error message" is displayed.

[0345] Step 2: Obtaining specialist profiles and generating interview forms

[0346] Input: The server retrieves the specialist's profile information from the database.

[0347] Specific operation: The server accesses the database to obtain the profile information of the target specialist, and passes the obtained information to the generation AI to generate customized questions.

[0348] Data processing and calculation: Generative AI (e.g., OpenAI GPT-3) generates customized questions based on the profile information obtained.

[0349] Output: The generated customized questions are output in text format, which the server reconstructs into an interview form and sends to the specialist's terminal.

[0350] Step 3: Fill in and submit the interview form

[0351] Input: The specialist uses the terminal to input answers into the interview form.

[0352] Specific operation: The terminal displays the interview form, and the specialist enters the necessary answers. Once the input is complete, the specialist presses the send button. The terminal then sends this to the server.

[0353] Data processing and calculation: The server stores the received response data in a database.

[0354] Output: The answer data is saved in the database. A success message is displayed on the specialist's terminal.

[0355] Step 4: Emotional state analysis by the emotion engine

[0356] Input: The answer data from the interview form is saved on the server.

[0357] Specific operation: The server launches an emotion engine (e.g., IBM Watson Tone Analyzer) to analyze the saved response data.

[0358] Data processing and calculation: The emotion engine analyzes the response data and recognizes the emotional state.

[0359] Output: The analysis results are saved in a database along with the response data.

[0360] Step 5: Article generation

[0361] Input: Answer data stored in the database and the analysis results of the emotional state.

[0362] Specific operation: The server passes the saved response data and the analysis results of the emotional state back to the generation AI, which then generates a detailed article.

[0363] Data processing and calculation: Generative AI generates specific and detailed articles based on this data.

[0364] Output: The generated articles are stored in the database.

[0365] Step 6: Publish your article

[0366] Input: Generated article data.

[0367] Specific operation: The server retrieves article data from the database and displays it on the platform.

[0368] Data processing and calculation: Article data is formatted and its layout is adjusted.

[0369] Output: The article is published and available for all users to see.

[0370] Step 7: Providing and collecting user feedback

[0371] Input: User-provided feedback.

[0372] Specific operation: The terminal displays the feedback form, the user enters the feedback, and when the user presses the send button, the terminal sends it to the server.

[0373] Data processing and calculation: The server stores the received feedback data in a database.

[0374] Output: Feedback data is saved in the database. A success message is displayed.

[0375] Step 8: Analyze the feedback emotional state with the Emotion Engine

[0376] Input: User feedback data.

[0377] Specific operation: The server starts the emotion engine and analyzes the stored feedback data.

[0378] Data processing and computation: The emotion engine analyzes the feedback data and recognizes the emotional state.

[0379] Output: The analysis results are stored in a database along with the feedback data.

[0380] Step 9: Improve your content

[0381] Input: Feedback data and the analysis results of its emotional state.

[0382] Specific operation: The server analyzes this data and generates suggestions for future content improvements.

[0383] Data processing and calculation: Statistical analysis and trend analysis are carried out, and specific improvement plans are created.

[0384] Output: An improvement plan is developed and reflected in future content creation.

[0385] (Application example 2)

[0386] 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."

[0387] Conventional interview article generation systems have had difficulty in fully utilizing user feedback to improve content quality. In particular, they lacked technology for analyzing the emotional aspects of feedback, making it difficult to individually optimize the user experience.

[0388] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for conducting interviews with people who have specialized knowledge and experience in a specific field using an automatic generation AI and generating an article based on the interview results, means for a user to register or log in, means for generating an interview form and sending it to the target person, means for writing an article based on the interview results using the generation AI and publishing the article, means for collecting user feedback on the article and using the feedback data to improve the content, and means for analyzing the feedback data using an emotion engine and improving the content based on user emotions. This makes it possible to analyze users' emotional feedback and generate individually optimized, high-quality content.

[0389] "Automatic generation AI" is a technology that uses artificial intelligence to automatically generate interviews and texts without the need for humans to do it manually.

[0390] An "interview form" is an electronic format for framing specific questions and soliciting responses from a person with specialized knowledge or experience.

[0391] "Generative AI" is an artificial intelligence system that automatically generates text, articles, and questions based on input data.

[0392] "Articling" is the process of compiling collected information and data into text and presenting it to readers.

[0393] "Feedback" refers to response information such as opinions, impressions, and evaluations provided by users.

[0394] The "emotion engine" is a system that analyzes the emotions contained in the answers and feedback of users and experts and determines whether they are positive or negative.

[0395] A "server" is a computer system that processes, stores, and communicates data.

[0396] "Content improvement" is the process of making changes and revisions to improve the quality of the information and articles we provide, based on recent user feedback and analysis.

[0397] This invention is a system that uses automatic generation AI to conduct interviews with people with specialized knowledge and experience in a specific field (hereinafter referred to as experts), generates and publishes the results as articles, and further improves the quality of content by analyzing user feedback with an emotion engine.

[0398] 1. User Registration / Login

[0399] Hardware: Smartphones, tablets

[0400] Software: Frontend (React Native), Backend (Node.js), Database (MongoDB)

[0401] process:

[0402] A user signs up or logs in.

[0403] The front end provides user input information as a form.

[0404] The user's input information (username, password, email address) is sent to the server.

[0405] The server receives the information and stores it in a database or performs authentication.

[0406] 2. Generate an interview form

[0407] Hardware: Server

[0408] Software: Generative AI model (OpenAI GPT-4 (registered trademark)), database (MongoDB)

[0409] process:

[0410] The server retrieves the expert's profile information from the database.

[0411] Enter your profile information into the generative AI to generate customized questions.

[0412] The generated questions are reconstructed as an interview form and sent to the expert.

[0413] 3. Receiving and analyzing interview responses

[0414] Hardware: Server

[0415] Software: Frontend (React Native), Backend (Node.js), Sentiment Engine (Sentiment Analysis API)

[0416] process:

[0417] Experts will answer the interview form.

[0418] The response data is sent to the server.

[0419] The server stores the received response data in a database.

[0420] Activate the emotion engine to recognize the emotional state of the person at the time of answering.

[0421] The response data is saved along with the recognition results.

[0422] 4. Article creation and preparation for publication

[0423] Hardware: Server

[0424] Software: Generative AI model (OpenAI GPT-4), database (MongoDB)

[0425] process:

[0426] The server passes the saved response data to the generative AI model.

[0427] Generative AI models create detailed articles.

[0428] Store the article in a database and prepare it for publication.

[0429] 5. Publish the article and analyze the feedback

[0430] Hardware: smartphones, tablets, servers

[0431] Software: Frontend (React Native), Backend (Node.js), Sentiment Engine (Sentiment Analysis API)

[0432] process:

[0433] The server displays the generated articles on the platform.

[0434] Users view articles and provide feedback.

[0435] The feedback data is sent to the server and analyzed by the emotion engine.

[0436] Content improvements are made based on the recognition results.

[0437] Examples:

[0438] Example of system operation

[0439] The server generates interviews with famous chefs in the culinary field.

[0440] Sample questions: "What was the most challenging aspect of developing your latest recipe?", "What was the most important lesson you learned during the cooking process?"

[0441] A user reads an article and provides feedback saying, "This article was very helpful. I'd like to learn more about it."

[0442] Example prompt sentence:

[0443] Prompt to be input to the generated AI:

[0444] “Based on the chef’s profile provided, generate customized questions about his / her recent projects and learnings.”

[0445] Example of generated question:

[0446] "Tell me about your most recent recipe development. What made it particularly challenging?"

[0447] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0448] Step 1:

[0449] A user registers or logs in. Using a smartphone or tablet, the user enters their name, password, and email address. The information is compiled into a form and sent from the device to the server. The server receives it and stores it in a database, or authenticates it in the case of a login. The input data is the username, password, and email address, and the output is approval of the registration or authentication result for the login.

[0450] Step 2:

[0451] The server retrieves the expert's profile information from the database. This profile information is basic data about the expert (such as name, career history, and area of ​​expertise). Input data for the generation AI is constructed based on the retrieved profile information. The generation AI generates customized interview questions based on the given profile information. The input to the generation AI is the profile information, and the output is customized questions.

[0452] Step 3:

[0453] The generated questions are reconstructed as an interview form, which the server sends to the expert. The expert receives the interview form on his / her terminal and enters answers to each question. At this time, the terminal sends the expert's input data to the server, and the sent answer data is temporarily stored in the terminal's memory. The input data are the generated questions and the expert's answers, and the output is the data sent to the server.

[0454] Step 4:

[0455] The server stores the received response data in a database. During this process, the server activates an emotion engine to perform emotion analysis on the response data. The input data to the server is the response data, to which emotion labels are assigned by the emotion engine. The output is the analyzed emotion data and its corresponding label.

[0456] Step 5:

[0457] The server passes the saved response data and emotion labels to the generation AI, which then generates a detailed article. The generation AI uses this information to create specific and detailed article text. The input data to the generation AI are the response data and emotion labels, and the output is the generated article text.

[0458] Step 6:

[0459] The generated article text is stored in a database by the server and displayed on the platform when it is ready to be published. Other users can view the article and provide feedback. Viewers can enter feedback using their smartphones or tablets and send it to the server. The input data is the user feedback, and the output is the feedback data.

[0460] Step 7:

[0461] The server receives the feedback data and analyzes it using an emotion engine. Based on the analysis results, the server improves the content. The input data for feedback is the user's impressions and evaluations, and the output is feedback data with emotion labels. This data is used as a reference for future content generation and improvements.

[0462] 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.

[0463] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0464] 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.

[0465] [Second embodiment]

[0466] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0467] 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.

[0468] 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).

[0469] 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.

[0470] 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.

[0471] 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).

[0472] 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.

[0473] 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.

[0474] 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.

[0475] 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.

[0476] 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.

[0477] 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."

[0478] This invention is a system that uses automatic generation AI to conduct interviews with people who have specialized knowledge and experience in a specific field (hereinafter referred to as specialists), generates the interview results as articles, and provides them to users. This system is composed of the following steps.

[0479] First, a user registers or logs in. When registering, the device provides a form for entering basic information such as username, password, and email address, which is then sent to the server. The server verifies the received information and stores it in a database if there are no problems. Similarly, if an existing user enters login information, the server authenticates them and, if successful, allows the user to access the system.

[0480] Next, an interview form for the specialist is generated. The server retrieves the specialist's profile information from the database and passes it to the generation AI to generate customized questions. The generated questions are reconstructed as an interview form and sent to the specialist's device.

[0481] Next, the specialist uses the terminal to enter answers into the interview form and send them to the server, which then stores the received answer data in a database.

[0482] The server then passes the saved response data back to the AI ​​generator to generate a detailed article, which is then stored in a database by the server and prepared for publication.

[0483] Once an article is published, the server displays it on the platform for all users to see, and users can provide feedback on the article, which is sent back to the server and stored in a database.

[0484] As a concrete example, suppose a specialist who is an expert in a particular field (e.g., craft making) logs into the system and updates his or her profile. Based on this profile information, the server generates customized questions such as, "Tell us about your most challenging project" and "What important lessons did you learn through that project?" These questions are provided to the specialist as an interview form, and the specialist answers them. After the response data is sent and stored on the server, the generation AI uses the content to create a detailed article. This article is finally published, allowing other users to view it and discover the appeal of crafts as a new hobby, as well as provide feedback.

[0485] In this way, the system allows for the effective sharing of specialized knowledge and experience, enabling many users to discover new hobbies and interests.

[0486] The processing flow will be explained below.

[0487] Step 1:

[0488] The user registers or logs in. The user clicks the "Register" button on the device and enters the user name, password, email address, etc. Once the registration information is complete, the device sends this information to the server.

[0489] Step 2:

[0490] The server verifies the received user information. It checks the email address format and password strength, and if there are no problems, it saves the user information in the database. It returns a message to the user that registration is complete.

[0491] Step 3:

[0492] The terminal displays a login screen, and the user enters a username and password. The terminal then sends the input data to the server.

[0493] Step 4:

[0494] The server verifies the login information it receives. If it is correct, it authenticates the user and allows access. If it is incorrect, it returns an error message.

[0495] Step 5:

[0496] The server retrieves the specialist's profile information from the database, including the specialist's area of ​​expertise and past experience.

[0497] Step 6:

[0498] The server passes the acquired profile information to the generation AI, which generates customized interview questions. The generated questions are then reconstructed into an interview form.

[0499] Step 7:

[0500] The server sends the generated interview form to the specialist's terminal, which displays it to the specialist.

[0501] Step 8:

[0502] The user (specialist) enters answers into the interview form. After entering the necessary answers, the user clicks the "Submit" button and the answer data is sent to the server.

[0503] Step 9:

[0504] The server saves the received response data in a database, and once saving is complete, returns a notification of transmission completion to the device.

[0505] Step 10:

[0506] The server then passes the saved response data back to the AI ​​generator, which then generates a detailed article based on that data.

[0507] Step 11:

[0508] The server saves the generated article to the database, and once saved, sets the status to "ready to publish".

[0509] Step 12:

[0510] The server publishes new articles on the platform, where they become available for all users to view.

[0511] Step 13:

[0512] The device displays a notification of the published article to the user, who can then view the article and post comments and impressions.

[0513] Step 14:

[0514] The user enters feedback on the article and clicks the "Submit" button. The device sends the feedback to the server.

[0515] Step 15:

[0516] The server saves the received feedback in the database, and once saving is complete, returns a feedback completion notification to the user.

[0517] Through these steps, this system can effectively compile interviews with specialists with specialized knowledge and experience into articles, and provide many users with new hobbies and interests.

[0518] Example 1

[0519] 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."

[0520] The present invention aims to provide a system that allows users to easily acquire new knowledge and interests by automatically conducting interviews with people who have specialized knowledge and experience in a specific field and generating and publishing the results of those interviews as articles.The objective of this system is to automate the process of effectively collecting specialized information and turning it into articles, thereby improving user convenience.

[0521] 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.

[0522] In this invention, the server includes a means for a user to register or log in, a means for transmitting user information to the server using a terminal, and a means for verifying the user information received by the server and storing it in a database, thereby enabling user information to be registered and managed reliably.

[0523] The server includes a means for acquiring profile information of the target person and generating customized questions using a generative AI model, a means for generating an interview form and sending it to the target person, and a means for the target person to answer the interview form and send it to the server using a terminal, thereby enabling individual interviews to be conducted efficiently and automatically.

[0524] Furthermore, the server includes means for creating articles based on the interview results using the generative AI model and storing the articles in a database, means for publishing the articles and making them available for other users to view, and means for collecting user feedback on the articles and storing the feedback in a database, thereby enabling the generated articles to be published quickly and for the articles to be improved based on user feedback.

[0525] A "user" is a person who accesses the system and provides information or views content.

[0526] A "terminal" is a device used by a user for operation, and includes, for example, a computer, a smartphone, a tablet, and the like.

[0527] The "Server" is the central computer system that receives, verifies, and stores user-submitted information and automates the interview using the generative AI model.

[0528] A "database" is a system that systematically stores user information, interview results, generated articles, feedback, etc.

[0529] "Profile information" is information about a person with specialized knowledge or experience in a particular field, and is used to generate customized questions.

[0530] A "generative AI model" is an artificial intelligence model that automatically generates new content based on generated text, and includes, for example, models that use natural language processing technology.

[0531] An "Interview Form" is an electronic form for presenting customized questions to a Specialist.

[0532] "Response data" refers to the response information entered by the subject in the interview form.

[0533] An "article" is text content generated using a generative AI model based on interview form response data.

[0534] "Feedback" refers to comment information such as impressions and suggestions for improvement provided by users regarding an article.

[0535] "Publishing" refers to the act of displaying the generated article on a web platform so that it can be viewed by general users.

[0536] This invention is a system that uses automatic generation AI to conduct interviews with people with specialized knowledge and experience (hereinafter referred to as specialists), generates articles based on the interview results, and provides them to users. This system is implemented using the following specific hardware and software.

[0537] First, a user accesses the system using a terminal. The terminal can be a computer, smartphone, tablet, etc. The user registers or logs in. The terminal provides a form for entering user information, and the information entered by the user is sent to the server. This information includes the user name, password, email address, etc.

[0538] The server verifies the received user information and stores it in the database if there are no problems. Validation can be performed using a web framework such as Django. For new users, the server verifies that the registration information does not overlap with existing data, and for valid logins, the server verifies that the entered information matches the information in the database.

[0539] Next, the server retrieves the specialist's profile information from the database. Based on the retrieved information, it generates customized questions. This process uses a generative AI model (e.g., OpenAI's GPT-3). The prompt for the generative AI model is as follows:

[0540] Example prompt sentence:

[0541] "The specialist's name is ____. He is an expert in crafting. Generate questions for him such as:

[0542] 1. Tell us about your most challenging project.

[0543] 2. What are some important lessons you learned through the project?

[0544] 3. What crafts would you recommend for beginners?

[0545] The server reconstructs the generated questions as an interview form and sends it to the specialist's terminal. The specialist uses the terminal to enter answers into the interview form, and the terminal sends the entered answers to the server. The server stores the received answer data in a database.

[0546] The server then passes the saved response data back to the generation AI, which then generates a detailed article. For example, the generation AI might construct a sentence like, "Mr. / Ms. XX's most challenging project was XX." The generated article is then stored in a database by the server, ready for publication.

[0547] Once an article is published, the server displays it on the platform for all users to view, allowing them to gain new knowledge and interest. Furthermore, users can provide feedback on articles, which they send from their devices to the server. The server stores the received feedback in a database and uses it to improve the article.

[0548] This system automatically collects and systematically shares specialized knowledge and experience. Furthermore, by improving the content of articles based on user feedback, it becomes possible to provide more useful information. This is a specific embodiment of the present invention.

[0549] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0550] Step 1:

[0551] User registration or login

[0552] 1.1 A user accesses the system from a terminal through a web browser.

[0553] 1.2 The device displays a form for the user to sign up or log in.

[0554] Input: Personal information such as username, password, and email address

[0555] Output: User information to be sent

[0556] 1.3 The user enters the required information and clicks the "Submit" button.

[0557] 1.4 The terminal sends the entered information to the server.

[0558] Step 2:

[0559] Server verifies and stores user information

[0560] 2.1 The server verifies the received user information.

[0561] Input: Submitted user information

[0562] Output: Verification result (success / failure)

[0563] 2.2 In the case of new registration, the server checks whether the information is a duplicate of existing data in the database. In the case of login, the server checks whether the input information matches the information in the database.

[0564] 2.3 If the verification is successful, the server stores the user information in the database.

[0565] 2.4 The server then sends a message to the terminal indicating successful authentication.

[0566] Input: Validation result

[0567] Output: Authentication message

[0568] Step 3:

[0569] Obtaining specialist profile information and generating customized questions

[0570] 3.1 The server retrieves the specialist's profile information from the database.

[0571] Input: Specialist User ID

[0572] Output: Profile information

[0573] 3.2 Based on the profile information obtained by the server, a prompt sentence is input to the generative AI model (e.g., OpenAI GPT-3).

[0574] Input: Profile information, prompt text

[0575] Output: Customized question

[0576] 3.3 The server reconstructs the generated questions into an interview form and sends it to the specialist's terminal.

[0577] Input: Customized Question

[0578] Output: Interview form

[0579] Step 4:

[0580] Enter and submit answers to the interview form

[0581] 4.1 The specialist uses the terminal to enter responses into the interview form.

[0582] Input: Interview Form

[0583] Output: Response data

[0584] 4.2 The Specialist completes the response and clicks the "Submit" button.

[0585] 4.3 The terminal sends the entered response data to the server.

[0586] Step 5:

[0587] Response data saved on the server

[0588] 5.1 The server validates the response data received.

[0589] Input: Submitted response data

[0590] Output: Verification results

[0591] 5.2 If the verification is successful, the server stores the response data in the database.

[0592] Input: Validated response data

[0593] Output: Answer data stored in a database

[0594] Step 6:

[0595] Generating interview articles using generative AI models

[0596] 6.1 The server passes the saved answer data to a generative AI model (e.g., OpenAI GPT-3) to generate detailed articles.

[0597] Input: Response data

[0598] Output: The generated article

[0599] 6.2 The server stores the generated articles in a database.

[0600] Step 7:

[0601] Publish your article and gather feedback

[0602] 7.1 The server displays the ready-to-publish articles on the web platform.

[0603] Input: Generated article

[0604] Output: Published articles

[0605] 7.2 Users view articles and provide feedback.

[0606] Input: Feedback information

[0607] Output: Feedback to be sent

[0608] 7.3 The device sends the user-entered feedback to the server.

[0609] 7.4 The server stores the received feedback in a database.

[0610] Input: Submitted feedback

[0611] Output: Feedback stored in a database

[0612] (Application example 1)

[0613] 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."

[0614] Conventional article generation systems using human interviews have faced challenges such as the high labor costs of conducting interviews and writing articles, as well as the difficulty of sharing specialized knowledge. Furthermore, the generated content needed to be provided in a format that was useful to a wide range of users, not limited to a specific category. However, previous technology did not provide a means to easily conduct interviews, generate articles, and publish them as a smartphone application.

[0615] 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.

[0616] In this invention, the server includes: means for conducting interviews with people with specialized knowledge and experience in a specific field using automatic generation AI and generating articles based on the interview results; means for users to register or log in; means for generating interview forms and sending them to the target individuals; means for using the generation AI to write articles about the interview results and publishing the articles; means for collecting user feedback on the articles and using it to improve content; means for making the generated articles available to other users in a content distribution service; and means for installing the articles as a smartphone application. This allows experts' knowledge and experience to be shared effectively, enabling users to discover new knowledge and interests. Furthermore, the smartphone application improves convenience and accessibility, potentially attracting a wide range of users.

[0617] A "person with specialized knowledge or experience in a particular field" is a person who has in-depth knowledge or practical experience in a particular specialized field that goes beyond general understanding.

[0618] An "interview" is a form of communication in which specific questions are answered by someone with specialized knowledge or experience.

[0619] "Automatic generation AI" refers to programs or systems that use artificial intelligence technology to automatically generate sentences, questions, articles, etc.

[0620] An "article" is written content that is based on interview results or other information.

[0621] "User registration" is the process by which a new user registers the personal information and authentication information required to use the system.

[0622] "Login" refers to the process by which an existing user enters the necessary authentication information to access a system and is authenticated.

[0623] An "interview form" is a written or electronic format that provides the questions and information needed to conduct an interview.

[0624] "Profile information" refers to personal information about the person being interviewed, such as their background, area of ​​expertise, and experience.

[0625] "Customized Questions" are individual questions created to drill down into specific topics based on a person's profile information.

[0626] "Feedback" refers to ratings and opinions provided by users regarding articles and content.

[0627] A "content distribution service" is a service that makes generated content available on the Internet so that users can view and access it.

[0628] A "smartphone application" is a software program that runs on a smartphone and through which services can be used.

[0629] A "database" is a system for efficiently and safely storing and managing collected data and information.

[0630] The system for implementing this invention uses an automatic generation AI to conduct interviews with people with specialized knowledge and experience in a specific field, and then generates an article based on the results of the interview and provides it to users. This system is primarily based on the interaction between a server, a terminal, and a user.

[0631] System configuration

[0632] 1. User Registration and Login:

[0633] Server: The user is presented with a form to register and enters basic information such as username, password, email address, etc. The information is sent to the server, which validates it and stores it in a database. Similarly, when an existing user logs in, the information is authenticated and, if successful, the user is granted system access.

[0634] 2. Generate the interview form:

[0635] Server: Retrieves specialist profile information from the database and passes it to the generation AI to generate customized questions. The generated questions are organized into an interview form and sent to the specialist's device.

[0636] 3. Collecting interview responses:

[0637] Terminal: The specialist enters answers into the interview form and sends the answers to the server via the terminal.

[0638] Server: Stores the received response data in a database.

[0639] 4. Article generation and publishing:

[0640] Server: The saved response data is passed to the AI ​​again to generate detailed articles. The generated articles are stored in a database and can be viewed by other users once they are ready to be published. They can also be provided in a format that can be installed as a smartphone application.

[0641] 5. Gathering Feedback:

[0642] Users: can provide feedback on articles, which will be sent to the server and stored in the database to improve the content.

[0643] Processing Details

[0644] 1. Hardware and Software:

[0645] Server: Runs the main program and manages the database. Builds an API server using the Flask framework and manages the database using SQLite.

[0646] Terminal: Devices used by specialists and general users, including smartphones, tablets, etc.

[0647] Generative AI models: Used for specific interview question generation and article generation. These include models like InterviewAI and ArticleGenerationAI.

[0648] Specific examples

[0649] Example of interview generation for experts

[0650] Profile Information:

[0651] Name: Yamada Taro

[0652] Specialty: Crafts

[0653] prompt:

[0654] Taro Yamada, tell us about your most challenging craft project and the lessons you learned.

[0655] Example questions generated:

[0656] 1. Tell us about your most challenging project.

[0657] 2. What are some important lessons you learned through the project?

[0658] The purpose of this system is to effectively share specialized knowledge and experience with many users through such concrete examples. Because it can be used through a smartphone application, it is convenient and accessible, and we expect it to be used by a wide range of users.

[0659] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0660] Step 1:

[0661] User Registration

[0662] User: To create a new account, a user enters basic information such as a username, password, and email address.

[0663] Server: The server receives this basic information, verifies the validity of the data, and if there are no problems, stores this information in a database (SQLite).

[0664] Input: Username, Password, Email Address.

[0665] Output: Validated user data is stored in the database.

[0666] Step 2:

[0667] Log in

[0668] User: An existing user logs into the system by entering their username and password.

[0669] Server: The server receives the entered authentication information, checks it against existing data in a database, and if successful, grants the user access to the system.

[0670] Input: Username, Password.

[0671] Output: If authentication is successful, grant access to the system. If authentication fails, return an error message.

[0672] Step 3:

[0673] Obtaining profile information and generating questions

[0674] Server: Retrieves specialist profile information from the database and passes it to the generation AI (InterviewAI).

[0675] Generative AI: Generates customized questions based on profile information.

[0676] Input: Specialist profile information.

[0677] Output: A customized interview form.

[0678] Server: Reconstructs the generated questions into an interview form and sends it to the specialist's terminal.

[0679] Step 4:

[0680] Enter and submit your interview answers

[0681] Specialist: Enter answers into the interview form and send them to the server via the terminal.

[0682] Server: Stores the received response data in a database.

[0683] Input: Specialist response data.

[0684] Output: Response data stored in a database.

[0685] Step 5:

[0686] Article Generation

[0687] Server: Pass the saved answer data to the generation AI (ArticleGenerationAI) to generate detailed articles.

[0688] Generative AI: Generates articles based on response data.

[0689] Input: Specialist response data.

[0690] Output: The generated article.

[0691] Server: Stores the generated articles in a database and prepares them for publication.

[0692] Step 6:

[0693] Article published

[0694] Server: The generated articles are published on the platform, allowing users to view them. They are also provided in a format that can be installed as a smartphone application.

[0695] Input: The generated article.

[0696] Output: The published article.

[0697] Step 7:

[0698] Feedback collection and storage

[0699] Users: Can view articles and provide feedback.

[0700] Server: Receives user feedback and stores it in a database.

[0701] Input: User feedback.

[0702] Output: Feedback stored in a database.

[0703] 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.

[0704] This invention is a system that uses an automatic generation AI to conduct interviews with people with specialized knowledge and experience in a specific field (hereinafter referred to as specialists), generates articles based on the results of the interviews, and then uses an emotion engine to analyze user feedback and emotions at the time of responses, thereby improving the quality of the content. This system is composed of the following steps.

[0705] First, a user registers or logs in. When registering, the device provides a form for entering basic information such as username, password, and email address. Once the information is entered, the device sends this information to the server. The server verifies the received information and stores it in the database if there are no problems. If an existing user enters login information, the server performs authentication, and if successful, the user can access the system.

[0706] Next, an interview form for the specialist is generated. The server retrieves the specialist's profile information from the database and passes it to the generation AI to generate customized questions. The generated questions are reconstructed as an interview form and sent to the specialist's device.

[0707] The specialist uses a terminal to enter answers into the interview form and send them to the server. The server stores the received answer data in a database. At this point, the server activates an emotion engine to analyze the answer data and recognize the emotional state of the specialist at the time of answering. The recognition results are stored along with the answer data and can be used to improve the quality of the interview content.

[0708] The server then passes the saved response data back to the AI ​​generator to generate a detailed article. The AI ​​uses this data to create a specific and detailed article. The generated article is then stored in the database by the server, ready for publication.

[0709] Once an article is published, the server displays it on the platform for all users to view. Users can also provide feedback on the article. When the feedback data is sent to the server, an emotion engine analyzes the content and recognizes the user's emotional state. Based on the recognition results, the server improves the content.

[0710] As a concrete example, consider a scenario in which a craftsman logs into the system and updates his or her profile. Based on this information, the server generates questions such as, "Tell us about your most challenging project" and "What important lessons did you learn from that project?" The specialist fills out an interview form, and the emotion engine analyzes the specialist's emotional state. The server stores the response data along with the specialist's emotional state, and then publishes a detailed article based on this information on the platform. When other users view the article and provide feedback, the emotion engine is also used, and future content is improved based on the obtained emotional data.

[0711] In this way, this system can effectively turn interviews with specialists with specialized knowledge and experience into articles, and by utilizing an emotion engine, it is possible to provide many users with new hobbies and interests.

[0712] The processing flow will be explained below.

[0713] Step 1:

[0714] A user registers or logs in. The user clicks the "Register" button on the device and enters information such as a username, password, and email address. Once the information is entered, the device sends it to the server.

[0715] Step 2:

[0716] The server verifies the user information it receives. It checks the email address format and password strength, and if there are no problems, it saves the user information in the database. It returns a message to the user that registration is complete to the terminal. If an existing user enters login information, the server performs authentication processing, and if successful, grants the user access rights.

[0717] Step 3:

[0718] The server retrieves the specialist's profile information from the database, including their area of ​​expertise, past projects, experience, etc.

[0719] Step 4:

[0720] The server passes the acquired profile information to the generation AI, which generates customized interview questions. The generation AI then creates the questions and reconstructs them into an interview form.

[0721] Step 5:

[0722] The server sends the generated interview form to the specialist's terminal, which displays the interview form and allows the specialist to enter answers.

[0723] Step 6:

[0724] The user (specialist) uses the terminal to enter answers into the interview form. Once the answers are complete, the user clicks the "Submit" button to send the answer data to the server.

[0725] Step 7:

[0726] The server stores the received answer data in a database. At this time, the server activates an emotion engine to analyze the data to recognize the emotional state of the specialist at the time of answering. The analysis results are stored together with the answer data.

[0727] Step 8:

[0728] The server then passes the saved response data back to the AI ​​generator, which then creates a detailed article based on the interview content.

[0729] Step 9:

[0730] The server saves the generated article to the database, and once done sets the status to indicate that the article is ready to be published.

[0731] Step 10:

[0732] The server publishes new articles on the platform, where they become available for all users to view.

[0733] Step 11:

[0734] The device displays a notification of the published article to the user, who can then view the article and post comments and impressions.

[0735] Step 12:

[0736] The user enters feedback on the article and clicks the "Submit" button. The device sends the feedback to the server.

[0737] Step 13:

[0738] The server stores the received feedback in a database. At this time, the server activates the emotion engine again to analyze the user's feedback and recognize their emotional state. The server then improves the content based on the analysis results.

[0739] Step 14:

[0740] The server sends a feedback completion notification to the terminal, which the terminal displays to the user, completing the feedback process.

[0741] Through these steps, this system can effectively turn interviews with specialists with specialized knowledge and experience into articles, and by using an emotion engine to analyze user feedback and the emotions expressed when answering, it can improve the quality of the content and provide many users with new hobbies and interests.

[0742] Example 2

[0743] 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."

[0744] In order to effectively turn interviews with specialists (people with specialized knowledge and experience in a specific field) into articles and improve the quality of those articles, it is important to improve the content by incorporating the depth and variety of the interview content and reader feedback. However, conventional systems have difficulty incorporating the emotions of specialists and readers, making it difficult to fully utilize feedback to improve the content. Furthermore, there is a lack of customization in the automatic generation of interview questions and the article-writing process, which means that the results of specialized interviews are not fully reflected in the articles.

[0745] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0746] In this invention, the server includes means for using an automatic generation AI to conduct interviews with people who have specialized knowledge and experience in a specific field and generate articles based on the interview results, means for a user to register or log in, means for generating an interview form and sending it to the person, means for using the generation AI to write an article about the interview results and publishing the article, means for collecting user feedback on the article and using the feedback to improve the content, means for using an emotion engine to analyze the person's emotional state at the time of their response, and means for using the emotion engine to analyze the emotional state of the user's feedback. This makes it possible to improve the quality of specialized interviews by taking the emotional state into consideration and to continuously improve the content based on the feedback.

[0747] "Automatic generation AI" is an artificial intelligence system that automatically generates text using natural language processing technology.

[0748] A "server" is a central processing unit that processes and manages data on a network.

[0749] A "terminal" is a device through which a user enters data or accesses information.

[0750] "User registration" is the process by which a user provides information about themselves and creates an account in order to use the system.

[0751] "Login" is the process by which an existing user is authenticated to access a system.

[0752] An "interview form" is a formal document containing specific questions that the interviewee uses to write their responses.

[0753] "Generative AI" is an artificial intelligence model that automatically generates new text based on given data or prompts.

[0754] "Articling" is the process of converting received data and information into an article format for readers.

[0755] "Publishing" is the process of making a generated article accessible to the public.

[0756] "Feedback" refers to the evaluations and opinions that users provide regarding articles and services.

[0757] An "emotion engine" is a software system for analyzing emotions in text and recognizing emotional states.

[0758] "Emotional state" refers to the emotional response of the person who generated the text and the user who provided the feedback.

[0759] A "database" is a system for storing and managing structured data.

[0760] "Profile information" refers to detailed information such as the background and qualifications of a user or expert.

[0761] This invention is a system that uses automatic generation AI to conduct interviews with people (specialists) who have specialized knowledge and experience in a specific field, generates the interview results as articles, and further improves the quality of content by using an emotion engine to analyze user feedback and emotions at the time of response.

[0762] The system includes the following major hardware and software components:

[0763] Server: The central unit that processes, manages, and stores data.

[0764] Terminal: A device that allows a user to input data or display information. Examples include personal computers and smartphones.

[0765] Generative AI: An artificial intelligence system that generates text based on interview results and prompts. OpenAI GPT-3 is used as an example.

[0766] Emotion engine: Software that analyzes the emotional state of text provided by a user or specialist. For example, IBM Watson Tone Analyzer is used.

[0767] System Overview

[0768] First, a user registers or logs in. The device provides a form for entering basic information such as username, password, and email address, and then sends the information to the server. The server verifies the received information and stores it in a database if there are no problems. If the user is an existing user, the server authenticates the entered login information, and if successful, the user is allowed to access the system.

[0769] Next, an interview form for the specialist is generated. The server retrieves the specialist's profile information from the database and passes it to the generation AI to generate customized questions. For example, a question might be generated such as, "Tell us about your most challenging project." The generated questions are reconstructed as an interview form and sent to the specialist's device.

[0770] The specialist uses a terminal to enter answers into the interview form and send them to the server. The server stores the received answer data in a database. At this point, the server activates an emotion engine to analyze the emotional state of the specialist at the time of answering. The analysis results are stored along with the answer data and are used to improve the quality of the interview content.

[0771] The server then passes the saved response data back to the AI ​​generator to generate a detailed article. The generated article is specific and detailed. For example, a detailed article is generated based on the interview responses, such as "what the specialist described as the most challenging project." The generated article is then stored in a database by the server and prepared for publication.

[0772] Once an article is published, the server displays it on the platform for all users to view. Users can also provide feedback on the article. When the feedback data is sent to the server, the emotion engine analyzes its content and recognizes the user's emotional state. Based on the recognition results, the server improves the content.

[0773] Examples of concrete examples and prompts

[0774] Specific examples

[0775] Consider a scenario in which a craftsman logs into the system and updates his or her profile. During this process, the server generates questions based on the specialist's profile information, such as "Tell us about your most challenging project" and "What important lessons did you learn through this project?" The specialist fills out an interview form, and the emotion engine analyzes the specialist's emotional state. The server stores the emotional state along with the response data, and publishes a detailed article based on this information on the platform. Furthermore, the emotion engine is also used when other users view the article and provide feedback on their impressions and opinions. The obtained emotion data is used to improve future content.

[0776] Prompt Sentence Examples

[0777] "Consider questions that can be generated based on the specialist's profile information. For example, generate questions about their most challenging project and the key lessons learned through that project."

[0778] In this way, this system can effectively turn interviews with specialists with specialized knowledge and experience into articles, and by utilizing an emotion engine, it is possible to provide many users with new hobbies and interests.

[0779] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0780] Step 1: User registration and login

[0781] Input: A user accesses the new registration or login page using a terminal. If registering for the first time, they enter basic information such as their username, password, and email address. If they are an existing user, they enter their username and password.

[0782] Specific operation: The terminal displays a new registration form or login form. The user enters the required information and presses the submit button. The terminal then sends this information to the server.

[0783] Data processing and calculation: The server verifies the received information and stores it in the database in the case of new registration. In the case of login, it compares it with the information stored in the database.

[0784] Output: If new registration is successful, the message "Registration complete" is displayed, and if login is successful, access to the system is permitted. If authentication is unsuccessful, an "Error message" is displayed.

[0785] Step 2: Obtaining specialist profiles and generating interview forms

[0786] Input: The server retrieves the specialist's profile information from the database.

[0787] Specific operation: The server accesses the database to obtain the profile information of the target specialist, and passes the obtained information to the generation AI to generate customized questions.

[0788] Data processing and calculation: Generative AI (e.g., OpenAI GPT-3) generates customized questions based on the profile information obtained.

[0789] Output: The generated customized questions are output in text format, which the server reconstructs into an interview form and sends to the specialist's terminal.

[0790] Step 3: Fill in and submit the interview form

[0791] Input: The specialist uses the terminal to input answers into the interview form.

[0792] Specific operation: The terminal displays the interview form, and the specialist enters the necessary answers. Once the input is complete, the specialist presses the send button. The terminal then sends this to the server.

[0793] Data processing and calculation: The server stores the received response data in a database.

[0794] Output: The answer data is saved in the database. A success message is displayed on the specialist's terminal.

[0795] Step 4: Emotional state analysis by the emotion engine

[0796] Input: The answer data from the interview form is saved on the server.

[0797] Specific operation: The server launches an emotion engine (e.g., IBM Watson Tone Analyzer) to analyze the saved response data.

[0798] Data processing and calculation: The emotion engine analyzes the response data and recognizes the emotional state.

[0799] Output: The analysis results are saved in a database along with the response data.

[0800] Step 5: Article generation

[0801] Input: Answer data stored in the database and the analysis results of the emotional state.

[0802] Specific operation: The server passes the saved response data and the analysis results of the emotional state back to the generation AI, which then generates a detailed article.

[0803] Data processing and calculation: Generative AI generates specific and detailed articles based on this data.

[0804] Output: The generated articles are stored in the database.

[0805] Step 6: Publish your article

[0806] Input: Generated article data.

[0807] Specific operation: The server retrieves article data from the database and displays it on the platform.

[0808] Data processing and calculation: Article data is formatted and its layout is adjusted.

[0809] Output: The article is published and available for all users to see.

[0810] Step 7: Providing and collecting user feedback

[0811] Input: User-provided feedback.

[0812] Specific operation: The terminal displays the feedback form, the user enters the feedback, and when the user presses the send button, the terminal sends it to the server.

[0813] Data processing and calculation: The server stores the received feedback data in a database.

[0814] Output: Feedback data is saved in the database. A success message is displayed.

[0815] Step 8: Analyze the feedback emotional state with the Emotion Engine

[0816] Input: User feedback data.

[0817] Specific operation: The server starts the emotion engine and analyzes the stored feedback data.

[0818] Data processing and computation: The emotion engine analyzes the feedback data and recognizes the emotional state.

[0819] Output: The analysis results are stored in a database along with the feedback data.

[0820] Step 9: Improve your content

[0821] Input: Feedback data and the analysis results of its emotional state.

[0822] Specific operation: The server analyzes this data and generates suggestions for future content improvements.

[0823] Data processing and calculation: Statistical analysis and trend analysis are carried out, and specific improvement plans are created.

[0824] Output: An improvement plan is developed and reflected in future content creation.

[0825] (Application example 2)

[0826] 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."

[0827] Conventional interview article generation systems have had difficulty in fully utilizing user feedback to improve content quality. In particular, they lacked technology for analyzing the emotional aspects of feedback, making it difficult to individually optimize the user experience.

[0828] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for conducting interviews with people who have specialized knowledge and experience in a specific field using an automatic generation AI and generating an article based on the interview results, means for a user to register or log in, means for generating an interview form and sending it to the target person, means for writing an article based on the interview results using the generation AI and publishing the article, means for collecting user feedback on the article and using the feedback data to improve the content, and means for analyzing the feedback data using an emotion engine and improving the content based on user emotions. This makes it possible to analyze users' emotional feedback and generate individually optimized, high-quality content.

[0829] "Automatic generation AI" is a technology that uses artificial intelligence to automatically generate interviews and texts without the need for humans to do it manually.

[0830] An "interview form" is an electronic format for framing specific questions and soliciting responses from a person with specialized knowledge or experience.

[0831] "Generative AI" is an artificial intelligence system that automatically generates text, articles, and questions based on input data.

[0832] "Articling" is the process of compiling collected information and data into text and presenting it to readers.

[0833] "Feedback" refers to response information such as opinions, impressions, and evaluations provided by users.

[0834] The "emotion engine" is a system that analyzes the emotions contained in the answers and feedback of users and experts and determines whether they are positive or negative.

[0835] A "server" is a computer system that processes, stores, and communicates data.

[0836] "Content improvement" is the process of making changes and revisions to improve the quality of the information and articles we provide, based on recent user feedback and analysis.

[0837] This invention is a system that uses automatic generation AI to conduct interviews with people with specialized knowledge and experience in a specific field (hereinafter referred to as experts), generates and publishes the results as articles, and further improves the quality of content by analyzing user feedback with an emotion engine.

[0838] 1. User Registration / Login

[0839] Hardware: Smartphones, tablets

[0840] Software: Frontend (React Native), Backend (Node.js), Database (MongoDB)

[0841] process:

[0842] A user signs up or logs in.

[0843] The front end provides user input information as a form.

[0844] The user's input information (username, password, email address) is sent to the server.

[0845] The server receives the information and stores it in a database or performs authentication.

[0846] 2. Generate an interview form

[0847] Hardware: Server

[0848] Software: Generative AI model (OpenAI GPT-4), database (MongoDB)

[0849] process:

[0850] The server retrieves the expert's profile information from the database.

[0851] Enter your profile information into the generative AI to generate customized questions.

[0852] The generated questions are reconstructed as an interview form and sent to the expert.

[0853] 3. Receiving and analyzing interview responses

[0854] Hardware: Server

[0855] Software: Frontend (React Native), Backend (Node.js), Sentiment Engine (Sentiment Analysis API)

[0856] process:

[0857] Experts will answer the interview form.

[0858] The response data is sent to the server.

[0859] The server stores the received response data in a database.

[0860] Activate the emotion engine to recognize the emotional state of the person at the time of answering.

[0861] The response data is saved along with the recognition results.

[0862] 4. Article creation and preparation for publication

[0863] Hardware: Server

[0864] Software: Generative AI model (OpenAI GPT-4), database (MongoDB)

[0865] process:

[0866] The server passes the saved response data to the generative AI model.

[0867] Generative AI models create detailed articles.

[0868] Store the article in a database and prepare it for publication.

[0869] 5. Publish the article and analyze the feedback

[0870] Hardware: smartphones, tablets, servers

[0871] Software: Frontend (React Native), Backend (Node.js), Sentiment Engine (Sentiment Analysis API)

[0872] process:

[0873] The server displays the generated articles on the platform.

[0874] Users view articles and provide feedback.

[0875] The feedback data is sent to the server and analyzed by the emotion engine.

[0876] Content improvements are made based on the recognition results.

[0877] Examples:

[0878] Example of system operation

[0879] The server generates interviews with famous chefs in the culinary field.

[0880] Sample questions: "What was the most challenging aspect of developing your latest recipe?", "What was the most important lesson you learned during the cooking process?"

[0881] A user reads an article and provides feedback saying, "This article was very helpful. I'd like to learn more about it."

[0882] Example prompt sentence:

[0883] Prompt to be input to the generated AI:

[0884] “Based on the chef’s profile provided, generate customized questions about his / her recent projects and learnings.”

[0885] Example of generated question:

[0886] "Tell me about your most recent recipe development. What made it particularly challenging?"

[0887] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0888] Step 1:

[0889] A user registers or logs in. Using a smartphone or tablet, the user enters their name, password, and email address. The information is compiled into a form and sent from the device to the server. The server receives it and stores it in a database, or authenticates it in the case of a login. The input data is the username, password, and email address, and the output is approval of the registration or authentication result for the login.

[0890] Step 2:

[0891] The server retrieves the expert's profile information from the database. This profile information is basic data about the expert (such as name, career history, and area of ​​expertise). Input data for the generation AI is constructed based on the retrieved profile information. The generation AI generates customized interview questions based on the given profile information. The input to the generation AI is the profile information, and the output is customized questions.

[0892] Step 3:

[0893] The generated questions are reconstructed as an interview form, which the server sends to the expert. The expert receives the interview form on his / her terminal and enters answers to each question. At this time, the terminal sends the expert's input data to the server, and the sent answer data is temporarily stored in the terminal's memory. The input data are the generated questions and the expert's answers, and the output is the data sent to the server.

[0894] Step 4:

[0895] The server stores the received response data in a database. During this process, the server activates an emotion engine to perform emotion analysis on the response data. The input data to the server is the response data, to which emotion labels are assigned by the emotion engine. The output is the analyzed emotion data and its corresponding label.

[0896] Step 5:

[0897] The server passes the saved response data and emotion labels to the generation AI, which then generates a detailed article. The generation AI uses this information to create specific and detailed article text. The input data to the generation AI are the response data and emotion labels, and the output is the generated article text.

[0898] Step 6:

[0899] The generated article text is stored in a database by the server and displayed on the platform when it is ready to be published. Other users can view the article and provide feedback. Viewers can enter feedback using their smartphones or tablets and send it to the server. The input data is the user feedback, and the output is the feedback data.

[0900] Step 7:

[0901] The server receives the feedback data and analyzes it using an emotion engine. Based on the analysis results, the server improves the content. The input data for feedback is the user's impressions and evaluations, and the output is feedback data with emotion labels. This data is used as a reference for future content generation and improvements.

[0902] 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.

[0903] 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.

[0904] 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.

[0905] [Third embodiment]

[0906] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0907] 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.

[0908] 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).

[0909] 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.

[0910] 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.

[0911] 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).

[0912] 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.

[0913] 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.

[0914] 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.

[0915] 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.

[0916] 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.

[0917] 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."

[0918] This invention is a system that uses automatic generation AI to conduct interviews with people who have specialized knowledge and experience in a specific field (hereinafter referred to as specialists), generates the interview results as articles, and provides them to users. This system is composed of the following steps.

[0919] First, a user registers or logs in. When registering, the device provides a form for entering basic information such as username, password, and email address, which is then sent to the server. The server verifies the received information and stores it in a database if there are no problems. Similarly, if an existing user enters login information, the server authenticates them and, if successful, allows the user to access the system.

[0920] Next, an interview form for the specialist is generated. The server retrieves the specialist's profile information from the database and passes it to the generation AI to generate customized questions. The generated questions are reconstructed as an interview form and sent to the specialist's device.

[0921] Next, the specialist uses the terminal to enter answers into the interview form and send them to the server, which then stores the received answer data in a database.

[0922] The server then passes the saved response data back to the AI ​​generator to generate a detailed article, which is then stored in a database by the server and prepared for publication.

[0923] Once an article is published, the server displays it on the platform for all users to see, and users can provide feedback on the article, which is sent back to the server and stored in a database.

[0924] As a concrete example, suppose a specialist who is an expert in a particular field (e.g., craft making) logs into the system and updates his or her profile. Based on this profile information, the server generates customized questions such as, "Tell us about your most challenging project" and "What important lessons did you learn through that project?" These questions are provided to the specialist as an interview form, and the specialist answers them. After the response data is sent and stored on the server, the generation AI uses the content to create a detailed article. This article is finally published, allowing other users to view it and discover the appeal of crafts as a new hobby, as well as provide feedback.

[0925] In this way, the system allows for the effective sharing of specialized knowledge and experience, enabling many users to discover new hobbies and interests.

[0926] The processing flow will be explained below.

[0927] Step 1:

[0928] The user registers or logs in. The user clicks the "Register" button on the device and enters the user name, password, email address, etc. Once the registration information is complete, the device sends this information to the server.

[0929] Step 2:

[0930] The server verifies the received user information. It checks the email address format and password strength, and if there are no problems, it saves the user information in the database. It returns a message to the user that registration is complete.

[0931] Step 3:

[0932] The terminal displays a login screen, and the user enters a username and password. The terminal then sends the input data to the server.

[0933] Step 4:

[0934] The server verifies the login information it receives. If it is correct, it authenticates the user and allows access. If it is incorrect, it returns an error message.

[0935] Step 5:

[0936] The server retrieves the specialist's profile information from the database, including the specialist's area of ​​expertise and past experience.

[0937] Step 6:

[0938] The server passes the acquired profile information to the generation AI, which generates customized interview questions. The generated questions are then reconstructed into an interview form.

[0939] Step 7:

[0940] The server sends the generated interview form to the specialist's terminal, which displays it to the specialist.

[0941] Step 8:

[0942] The user (specialist) enters answers into the interview form. After entering the necessary answers, the user clicks the "Submit" button and the answer data is sent to the server.

[0943] Step 9:

[0944] The server saves the received response data in a database, and once saving is complete, returns a notification of transmission completion to the device.

[0945] Step 10:

[0946] The server then passes the saved response data back to the AI ​​generator, which then generates a detailed article based on that data.

[0947] Step 11:

[0948] The server saves the generated article to the database, and once saved, sets the status to "ready to publish".

[0949] Step 12:

[0950] The server publishes new articles on the platform, where they become available for all users to view.

[0951] Step 13:

[0952] The device displays a notification of the published article to the user, who can then view the article and post comments and impressions.

[0953] Step 14:

[0954] The user enters feedback on the article and clicks the "Submit" button. The device sends the feedback to the server.

[0955] Step 15:

[0956] The server saves the received feedback in the database, and once saving is complete, returns a feedback completion notification to the user.

[0957] Through these steps, this system can effectively compile interviews with specialists with specialized knowledge and experience into articles, and provide many users with new hobbies and interests.

[0958] Example 1

[0959] 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."

[0960] The present invention aims to provide a system that allows users to easily acquire new knowledge and interests by automatically conducting interviews with people who have specialized knowledge and experience in a specific field and generating and publishing the results of those interviews as articles.The objective of this system is to automate the process of effectively collecting specialized information and turning it into articles, thereby improving user convenience.

[0961] 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.

[0962] In this invention, the server includes a means for a user to register or log in, a means for transmitting user information to the server using a terminal, and a means for verifying the user information received by the server and storing it in a database, thereby enabling user information to be registered and managed reliably.

[0963] The server includes a means for acquiring profile information of the target person and generating customized questions using a generative AI model, a means for generating an interview form and sending it to the target person, and a means for the target person to answer the interview form and send it to the server using a terminal, thereby enabling individual interviews to be conducted efficiently and automatically.

[0964] Furthermore, the server includes means for creating articles based on the interview results using the generative AI model and storing the articles in a database, means for publishing the articles and making them available for other users to view, and means for collecting user feedback on the articles and storing the feedback in a database, thereby enabling the generated articles to be published quickly and for the articles to be improved based on user feedback.

[0965] A "user" is a person who accesses the system and provides information or views content.

[0966] A "terminal" is a device used by a user for operation, and includes, for example, a computer, a smartphone, a tablet, and the like.

[0967] The "Server" is the central computer system that receives, verifies, and stores user-submitted information and automates the interview using the generative AI model.

[0968] A "database" is a system that systematically stores user information, interview results, generated articles, feedback, etc.

[0969] "Profile information" is information about a person with specialized knowledge or experience in a particular field, and is used to generate customized questions.

[0970] A "generative AI model" is an artificial intelligence model that automatically generates new content based on generated text, and includes, for example, models that use natural language processing technology.

[0971] An "Interview Form" is an electronic form for presenting customized questions to a Specialist.

[0972] "Response data" refers to the response information entered by the subject in the interview form.

[0973] An "article" is text content generated using a generative AI model based on interview form response data.

[0974] "Feedback" refers to comment information such as impressions and suggestions for improvement provided by users regarding an article.

[0975] "Publishing" refers to the act of displaying the generated article on a web platform so that it can be viewed by general users.

[0976] This invention is a system that uses automatic generation AI to conduct interviews with people with specialized knowledge and experience (hereinafter referred to as specialists), generates articles based on the interview results, and provides them to users. This system is implemented using the following specific hardware and software.

[0977] First, a user accesses the system using a terminal. The terminal can be a computer, smartphone, tablet, etc. The user registers or logs in. The terminal provides a form for entering user information, and the information entered by the user is sent to the server. This information includes the user name, password, email address, etc.

[0978] The server verifies the received user information and stores it in the database if there are no problems. Validation can be performed using a web framework such as Django. For new users, the server verifies that the registration information does not overlap with existing data, and for valid logins, the server verifies that the entered information matches the information in the database.

[0979] Next, the server retrieves the specialist's profile information from the database. Based on the retrieved information, it generates customized questions. This process uses a generative AI model (e.g., OpenAI's GPT-3). The prompt for the generative AI model is as follows:

[0980] Example prompt sentence:

[0981] "The specialist's name is ____. He is an expert in crafting. Generate questions for him such as:

[0982] 1. Tell us about your most challenging project.

[0983] 2. What are some important lessons you learned through the project?

[0984] 3. What crafts would you recommend for beginners?

[0985] The server reconstructs the generated questions as an interview form and sends it to the specialist's terminal. The specialist uses the terminal to enter answers into the interview form, and the terminal sends the entered answers to the server. The server stores the received answer data in a database.

[0986] The server then passes the saved response data back to the generation AI, which then generates a detailed article. For example, the generation AI might construct a sentence like, "Mr. / Ms. XX's most challenging project was XX." The generated article is then stored in a database by the server, ready for publication.

[0987] Once an article is published, the server displays it on the platform for all users to view, allowing them to gain new knowledge and interest. Furthermore, users can provide feedback on articles, which they send from their devices to the server. The server stores the received feedback in a database and uses it to improve the article.

[0988] This system automatically collects and systematically shares specialized knowledge and experience. Furthermore, by improving the content of articles based on user feedback, it becomes possible to provide more useful information. This is a specific embodiment of the present invention.

[0989] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0990] Step 1:

[0991] User registration or login

[0992] 1.1 A user accesses the system from a terminal through a web browser.

[0993] 1.2 The device displays a form for the user to sign up or log in.

[0994] Input: Personal information such as username, password, and email address

[0995] Output: User information to be sent

[0996] 1.3 The user enters the required information and clicks the "Submit" button.

[0997] 1.4 The terminal sends the entered information to the server.

[0998] Step 2:

[0999] Server verifies and stores user information

[1000] 2.1 The server verifies the received user information.

[1001] Input: Submitted user information

[1002] Output: Verification result (success / failure)

[1003] 2.2 In the case of new registration, the server checks whether the information is a duplicate of existing data in the database. In the case of login, the server checks whether the input information matches the information in the database.

[1004] 2.3 If the verification is successful, the server stores the user information in the database.

[1005] 2.4 The server then sends a message to the terminal indicating successful authentication.

[1006] Input: Validation result

[1007] Output: Authentication message

[1008] Step 3:

[1009] Obtaining specialist profile information and generating customized questions

[1010] 3.1 The server retrieves the specialist's profile information from the database.

[1011] Input: Specialist User ID

[1012] Output: Profile information

[1013] 3.2 Based on the profile information obtained by the server, a prompt sentence is input to the generative AI model (e.g., OpenAI GPT-3).

[1014] Input: Profile information, prompt text

[1015] Output: Customized question

[1016] 3.3 The server reconstructs the generated questions into an interview form and sends it to the specialist's terminal.

[1017] Input: Customized Question

[1018] Output: Interview form

[1019] Step 4:

[1020] Enter and submit answers to the interview form

[1021] 4.1 The specialist uses the terminal to enter responses into the interview form.

[1022] Input: Interview Form

[1023] Output: Response data

[1024] 4.2 The Specialist completes the response and clicks the "Submit" button.

[1025] 4.3 The terminal sends the entered response data to the server.

[1026] Step 5:

[1027] Response data saved on the server

[1028] 5.1 The server validates the response data received.

[1029] Input: Submitted response data

[1030] Output: Verification results

[1031] 5.2 If the verification is successful, the server stores the response data in the database.

[1032] Input: Validated response data

[1033] Output: Answer data stored in a database

[1034] Step 6:

[1035] Generating interview articles using generative AI models

[1036] 6.1 The server passes the saved answer data to a generative AI model (e.g., OpenAI GPT-3) to generate detailed articles.

[1037] Input: Response data

[1038] Output: The generated article

[1039] 6.2 The server stores the generated articles in a database.

[1040] Step 7:

[1041] Publish your article and gather feedback

[1042] 7.1 The server displays the ready-to-publish articles on the web platform.

[1043] Input: Generated article

[1044] Output: Published articles

[1045] 7.2 Users view articles and provide feedback.

[1046] Input: Feedback information

[1047] Output: Feedback to be sent

[1048] 7.3 The device sends the user-entered feedback to the server.

[1049] 7.4 The server stores the received feedback in a database.

[1050] Input: Submitted feedback

[1051] Output: Feedback stored in a database

[1052] (Application example 1)

[1053] 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."

[1054] Conventional article generation systems using human interviews have faced challenges such as the high labor costs of conducting interviews and writing articles, as well as the difficulty of sharing specialized knowledge. Furthermore, the generated content needed to be provided in a format that was useful to a wide range of users, not limited to a specific category. However, previous technology did not provide a means to easily conduct interviews, generate articles, and publish them as a smartphone application.

[1055] 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.

[1056] In this invention, the server includes: means for conducting interviews with people with specialized knowledge and experience in a specific field using automatic generation AI and generating articles based on the interview results; means for users to register or log in; means for generating interview forms and sending them to the target individuals; means for using the generation AI to write articles about the interview results and publishing the articles; means for collecting user feedback on the articles and using it to improve content; means for making the generated articles available to other users in a content distribution service; and means for installing the articles as a smartphone application. This allows experts' knowledge and experience to be shared effectively, enabling users to discover new knowledge and interests. Furthermore, the smartphone application improves convenience and accessibility, potentially attracting a wide range of users.

[1057] A "person with specialized knowledge or experience in a particular field" is a person who has in-depth knowledge or practical experience in a particular specialized field that goes beyond general understanding.

[1058] An "interview" is a form of communication in which specific questions are answered by someone with specialized knowledge or experience.

[1059] "Automatic generation AI" refers to programs or systems that use artificial intelligence technology to automatically generate sentences, questions, articles, etc.

[1060] An "article" is written content that is based on interview results or other information.

[1061] "User registration" is the process by which a new user registers the personal information and authentication information required to use the system.

[1062] "Login" refers to the process by which an existing user enters the necessary authentication information to access a system and is authenticated.

[1063] An "interview form" is a written or electronic format that provides the questions and information needed to conduct an interview.

[1064] "Profile information" refers to personal information about the person being interviewed, such as their background, area of ​​expertise, and experience.

[1065] "Customized Questions" are individual questions created to drill down into specific topics based on a person's profile information.

[1066] "Feedback" refers to ratings and opinions provided by users regarding articles and content.

[1067] A "content distribution service" is a service that makes generated content available on the Internet so that users can view and access it.

[1068] A "smartphone application" is a software program that runs on a smartphone and through which services can be used.

[1069] A "database" is a system for efficiently and safely storing and managing collected data and information.

[1070] The system for implementing this invention uses an automatic generation AI to conduct interviews with people with specialized knowledge and experience in a specific field, and then generates an article based on the results of the interview and provides it to users. This system is primarily based on the interaction between a server, a terminal, and a user.

[1071] System configuration

[1072] 1. User Registration and Login:

[1073] Server: The user is presented with a form to register and enters basic information such as username, password, email address, etc. The information is sent to the server, which validates it and stores it in a database. Similarly, when an existing user logs in, the information is authenticated and, if successful, the user is granted system access.

[1074] 2. Generate the interview form:

[1075] Server: Retrieves specialist profile information from the database and passes it to the generation AI to generate customized questions. The generated questions are organized into an interview form and sent to the specialist's device.

[1076] 3. Collecting interview responses:

[1077] Terminal: The specialist enters answers into the interview form and sends the answers to the server via the terminal.

[1078] Server: Stores the received response data in a database.

[1079] 4. Article generation and publishing:

[1080] Server: The saved response data is passed to the AI ​​again to generate detailed articles. The generated articles are stored in a database and can be viewed by other users once they are ready to be published. They can also be provided in a format that can be installed as a smartphone application.

[1081] 5. Gathering Feedback:

[1082] Users: can provide feedback on articles, which will be sent to the server and stored in the database to improve the content.

[1083] Processing Details

[1084] 1. Hardware and Software:

[1085] Server: Runs the main program and manages the database. Builds an API server using the Flask framework and manages the database using SQLite.

[1086] Terminal: Devices used by specialists and general users, including smartphones, tablets, etc.

[1087] Generative AI models: Used for specific interview question generation and article generation. These include models like InterviewAI and ArticleGenerationAI.

[1088] Specific examples

[1089] Example of interview generation for experts

[1090] Profile Information:

[1091] Name: Yamada Taro

[1092] Specialty: Crafts

[1093] prompt:

[1094] Taro Yamada, tell us about your most challenging craft project and the lessons you learned.

[1095] Example questions generated:

[1096] 1. Tell us about your most challenging project.

[1097] 2. What are some important lessons you learned through the project?

[1098] The purpose of this system is to effectively share specialized knowledge and experience with many users through such concrete examples. Because it can be used through a smartphone application, it is convenient and accessible, and we expect it to be used by a wide range of users.

[1099] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1100] Step 1:

[1101] User Registration

[1102] User: To create a new account, a user enters basic information such as a username, password, and email address.

[1103] Server: The server receives this basic information, verifies the validity of the data, and if there are no problems, stores this information in a database (SQLite).

[1104] Input: Username, Password, Email Address.

[1105] Output: Validated user data is stored in the database.

[1106] Step 2:

[1107] Log in

[1108] User: An existing user logs into the system by entering their username and password.

[1109] Server: The server receives the entered authentication information, checks it against existing data in a database, and if successful, grants the user access to the system.

[1110] Input: Username, Password.

[1111] Output: If authentication is successful, grant access to the system. If authentication fails, return an error message.

[1112] Step 3:

[1113] Obtaining profile information and generating questions

[1114] Server: Retrieves specialist profile information from the database and passes it to the generation AI (InterviewAI).

[1115] Generative AI: Generates customized questions based on profile information.

[1116] Input: Specialist profile information.

[1117] Output: A customized interview form.

[1118] Server: Reconstructs the generated questions into an interview form and sends it to the specialist's terminal.

[1119] Step 4:

[1120] Enter and submit your interview answers

[1121] Specialist: Enter answers into the interview form and send them to the server via the terminal.

[1122] Server: Stores the received response data in a database.

[1123] Input: Specialist response data.

[1124] Output: Response data stored in a database.

[1125] Step 5:

[1126] Article Generation

[1127] Server: Pass the saved answer data to the generation AI (ArticleGenerationAI) to generate detailed articles.

[1128] Generative AI: Generates articles based on response data.

[1129] Input: Specialist response data.

[1130] Output: The generated article.

[1131] Server: Stores the generated articles in a database and prepares them for publication.

[1132] Step 6:

[1133] Article published

[1134] Server: The generated articles are published on the platform, allowing users to view them. They are also provided in a format that can be installed as a smartphone application.

[1135] Input: The generated article.

[1136] Output: The published article.

[1137] Step 7:

[1138] Feedback collection and storage

[1139] Users: Can view articles and provide feedback.

[1140] Server: Receives user feedback and stores it in a database.

[1141] Input: User feedback.

[1142] Output: Feedback stored in a database.

[1143] 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.

[1144] This invention is a system that uses an automatic generation AI to conduct interviews with people with specialized knowledge and experience in a specific field (hereinafter referred to as specialists), generates articles based on the results of the interviews, and then uses an emotion engine to analyze user feedback and emotions at the time of responses, thereby improving the quality of the content. This system is composed of the following steps.

[1145] First, a user registers or logs in. When registering, the device provides a form for entering basic information such as username, password, and email address. Once the information is entered, the device sends this information to the server. The server verifies the received information and stores it in the database if there are no problems. If an existing user enters login information, the server performs authentication, and if successful, the user can access the system.

[1146] Next, an interview form for the specialist is generated. The server retrieves the specialist's profile information from the database and passes it to the generation AI to generate customized questions. The generated questions are reconstructed as an interview form and sent to the specialist's device.

[1147] The specialist uses a terminal to enter answers into the interview form and send them to the server. The server stores the received answer data in a database. At this point, the server activates an emotion engine to analyze the answer data and recognize the emotional state of the specialist at the time of answering. The recognition results are stored along with the answer data and can be used to improve the quality of the interview content.

[1148] The server then passes the saved response data back to the AI ​​generator to generate a detailed article. The AI ​​uses this data to create a specific and detailed article. The generated article is then stored in the database by the server, ready for publication.

[1149] Once an article is published, the server displays it on the platform for all users to view. Users can also provide feedback on the article. When the feedback data is sent to the server, an emotion engine analyzes the content and recognizes the user's emotional state. Based on the recognition results, the server improves the content.

[1150] As a concrete example, consider a scenario in which a craftsman logs into the system and updates his or her profile. Based on this information, the server generates questions such as, "Tell us about your most challenging project" and "What important lessons did you learn from that project?" The specialist fills out an interview form, and the emotion engine analyzes the specialist's emotional state. The server stores the response data along with the specialist's emotional state, and then publishes a detailed article based on this information on the platform. When other users view the article and provide feedback, the emotion engine is also used, and future content is improved based on the obtained emotional data.

[1151] In this way, this system can effectively turn interviews with specialists with specialized knowledge and experience into articles, and by utilizing an emotion engine, it is possible to provide many users with new hobbies and interests.

[1152] The processing flow will be explained below.

[1153] Step 1:

[1154] A user registers or logs in. The user clicks the "Register" button on the device and enters information such as a username, password, and email address. Once the information is entered, the device sends it to the server.

[1155] Step 2:

[1156] The server verifies the user information it receives. It checks the email address format and password strength, and if there are no problems, it saves the user information in the database. It returns a message to the user that registration is complete to the terminal. If an existing user enters login information, the server performs authentication processing, and if successful, grants the user access rights.

[1157] Step 3:

[1158] The server retrieves the specialist's profile information from the database, including their area of ​​expertise, past projects, experience, etc.

[1159] Step 4:

[1160] The server passes the acquired profile information to the generation AI, which generates customized interview questions. The generation AI then creates the questions and reconstructs them into an interview form.

[1161] Step 5:

[1162] The server sends the generated interview form to the specialist's terminal, which displays the interview form and allows the specialist to enter answers.

[1163] Step 6:

[1164] The user (specialist) uses the terminal to enter answers into the interview form. Once the answers are complete, the user clicks the "Submit" button to send the answer data to the server.

[1165] Step 7:

[1166] The server stores the received answer data in a database. At this time, the server activates an emotion engine to analyze the data to recognize the emotional state of the specialist at the time of answering. The analysis results are stored together with the answer data.

[1167] Step 8:

[1168] The server then passes the saved response data back to the AI ​​generator, which then creates a detailed article based on the interview content.

[1169] Step 9:

[1170] The server saves the generated article to the database, and once done sets the status to indicate that the article is ready to be published.

[1171] Step 10:

[1172] The server publishes new articles on the platform, where they become available for all users to view.

[1173] Step 11:

[1174] The device displays a notification of the published article to the user, who can then view the article and post comments and impressions.

[1175] Step 12:

[1176] The user enters feedback on the article and clicks the "Submit" button. The device sends the feedback to the server.

[1177] Step 13:

[1178] The server stores the received feedback in a database. At this time, the server activates the emotion engine again to analyze the user's feedback and recognize their emotional state. The server then improves the content based on the analysis results.

[1179] Step 14:

[1180] The server sends a feedback completion notification to the terminal, which the terminal displays to the user, completing the feedback process.

[1181] Through these steps, this system can effectively turn interviews with specialists with specialized knowledge and experience into articles, and by using an emotion engine to analyze user feedback and the emotions expressed when answering, it can improve the quality of the content and provide many users with new hobbies and interests.

[1182] Example 2

[1183] 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."

[1184] In order to effectively turn interviews with specialists (people with specialized knowledge and experience in a specific field) into articles and improve the quality of those articles, it is important to improve the content by incorporating the depth and variety of the interview content and reader feedback. However, conventional systems have difficulty incorporating the emotions of specialists and readers, making it difficult to fully utilize feedback to improve the content. Furthermore, there is a lack of customization in the automatic generation of interview questions and the article-writing process, which means that the results of specialized interviews are not fully reflected in the articles.

[1185] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1186] In this invention, the server includes means for using an automatic generation AI to conduct interviews with people who have specialized knowledge and experience in a specific field and generate articles based on the interview results, means for a user to register or log in, means for generating an interview form and sending it to the person, means for using the generation AI to write an article about the interview results and publishing the article, means for collecting user feedback on the article and using the feedback to improve the content, means for using an emotion engine to analyze the person's emotional state at the time of their response, and means for using the emotion engine to analyze the emotional state of the user's feedback. This makes it possible to improve the quality of specialized interviews by taking the emotional state into consideration and to continuously improve the content based on the feedback.

[1187] "Automatic generation AI" is an artificial intelligence system that automatically generates text using natural language processing technology.

[1188] A "server" is a central processing unit that processes and manages data on a network.

[1189] A "terminal" is a device through which a user enters data or accesses information.

[1190] "User registration" is the process by which a user provides information about themselves and creates an account in order to use the system.

[1191] "Login" is the process by which an existing user is authenticated to access a system.

[1192] An "interview form" is a formal document containing specific questions that the interviewee uses to write their responses.

[1193] "Generative AI" is an artificial intelligence model that automatically generates new text based on given data or prompts.

[1194] "Articling" is the process of converting received data and information into an article format for readers.

[1195] "Publishing" is the process of making a generated article accessible to the public.

[1196] "Feedback" refers to the evaluations and opinions that users provide regarding articles and services.

[1197] An "emotion engine" is a software system for analyzing emotions in text and recognizing emotional states.

[1198] "Emotional state" refers to the emotional response of the person who generated the text and the user who provided the feedback.

[1199] A "database" is a system for storing and managing structured data.

[1200] "Profile information" refers to detailed information such as the background and qualifications of a user or expert.

[1201] This invention is a system that uses automatic generation AI to conduct interviews with people (specialists) who have specialized knowledge and experience in a specific field, generates the interview results as articles, and further improves the quality of content by using an emotion engine to analyze user feedback and emotions at the time of response.

[1202] The system includes the following major hardware and software components:

[1203] Server: The central unit that processes, manages, and stores data.

[1204] Terminal: A device that allows a user to input data or display information. Examples include personal computers and smartphones.

[1205] Generative AI: An artificial intelligence system that generates text based on interview results and prompts. OpenAI GPT-3 is used as an example.

[1206] Emotion engine: Software that analyzes the emotional state of text provided by a user or specialist. For example, IBM Watson Tone Analyzer is used.

[1207] System Overview

[1208] First, a user registers or logs in. The device provides a form for entering basic information such as username, password, and email address, and then sends the information to the server. The server verifies the received information and stores it in a database if there are no problems. If the user is an existing user, the server authenticates the entered login information, and if successful, the user is allowed to access the system.

[1209] Next, an interview form for the specialist is generated. The server retrieves the specialist's profile information from the database and passes it to the generation AI to generate customized questions. For example, a question might be generated such as, "Tell us about your most challenging project." The generated questions are reconstructed as an interview form and sent to the specialist's device.

[1210] The specialist uses a terminal to enter answers into the interview form and send them to the server. The server stores the received answer data in a database. At this point, the server activates an emotion engine to analyze the emotional state of the specialist at the time of answering. The analysis results are stored along with the answer data and are used to improve the quality of the interview content.

[1211] The server then passes the saved response data back to the AI ​​generator to generate a detailed article. The generated article is specific and detailed. For example, a detailed article is generated based on the interview responses, such as "what the specialist described as the most challenging project." The generated article is then stored in a database by the server and prepared for publication.

[1212] Once an article is published, the server displays it on the platform for all users to view. Users can also provide feedback on the article. When the feedback data is sent to the server, the emotion engine analyzes its content and recognizes the user's emotional state. Based on the recognition results, the server improves the content.

[1213] Examples of concrete examples and prompts

[1214] Specific examples

[1215] Consider a scenario in which a craftsman logs into the system and updates his or her profile. During this process, the server generates questions based on the specialist's profile information, such as "Tell us about your most challenging project" and "What important lessons did you learn through this project?" The specialist fills out an interview form, and the emotion engine analyzes the specialist's emotional state. The server stores the emotional state along with the response data, and publishes a detailed article based on this information on the platform. Furthermore, the emotion engine is also used when other users view the article and provide feedback on their impressions and opinions. The obtained emotion data is used to improve future content.

[1216] Prompt Sentence Examples

[1217] "Consider questions that can be generated based on the specialist's profile information. For example, generate questions about their most challenging project and the key lessons learned through that project."

[1218] In this way, this system can effectively turn interviews with specialists with specialized knowledge and experience into articles, and by utilizing an emotion engine, it is possible to provide many users with new hobbies and interests.

[1219] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1220] Step 1: User registration and login

[1221] Input: A user accesses the new registration or login page using a terminal. If registering for the first time, they enter basic information such as their username, password, and email address. If they are an existing user, they enter their username and password.

[1222] Specific operation: The terminal displays a new registration form or login form. The user enters the required information and presses the submit button. The terminal then sends this information to the server.

[1223] Data processing and calculation: The server verifies the received information and stores it in the database in the case of new registration. In the case of login, it compares it with the information stored in the database.

[1224] Output: If new registration is successful, the message "Registration complete" is displayed, and if login is successful, access to the system is permitted. If authentication is unsuccessful, an "Error message" is displayed.

[1225] Step 2: Obtaining specialist profiles and generating interview forms

[1226] Input: The server retrieves the specialist's profile information from the database.

[1227] Specific operation: The server accesses the database to obtain the profile information of the target specialist, and passes the obtained information to the generation AI to generate customized questions.

[1228] Data processing and calculation: Generative AI (e.g., OpenAI GPT-3) generates customized questions based on the profile information obtained.

[1229] Output: The generated customized questions are output in text format, which the server reconstructs into an interview form and sends to the specialist's terminal.

[1230] Step 3: Fill in and submit the interview form

[1231] Input: The specialist uses the terminal to input answers into the interview form.

[1232] Specific operation: The terminal displays the interview form, and the specialist enters the necessary answers. Once the input is complete, the specialist presses the send button. The terminal then sends this to the server.

[1233] Data processing and calculation: The server stores the received response data in a database.

[1234] Output: The answer data is saved in the database. A success message is displayed on the specialist's terminal.

[1235] Step 4: Emotional state analysis by the emotion engine

[1236] Input: The answer data from the interview form is saved on the server.

[1237] Specific operation: The server launches an emotion engine (e.g., IBM Watson Tone Analyzer) to analyze the saved response data.

[1238] Data processing and calculation: The emotion engine analyzes the response data and recognizes the emotional state.

[1239] Output: The analysis results are saved in a database along with the response data.

[1240] Step 5: Article generation

[1241] Input: Answer data stored in the database and the analysis results of the emotional state.

[1242] Specific operation: The server passes the saved response data and the analysis results of the emotional state back to the generation AI, which then generates a detailed article.

[1243] Data processing and calculation: Generative AI generates specific and detailed articles based on this data.

[1244] Output: The generated articles are stored in the database.

[1245] Step 6: Publish your article

[1246] Input: Generated article data.

[1247] Specific operation: The server retrieves article data from the database and displays it on the platform.

[1248] Data processing and calculation: Article data is formatted and its layout is adjusted.

[1249] Output: The article is published and available for all users to see.

[1250] Step 7: Providing and collecting user feedback

[1251] Input: User-provided feedback.

[1252] Specific operation: The terminal displays the feedback form, the user enters the feedback, and when the user presses the send button, the terminal sends it to the server.

[1253] Data processing and calculation: The server stores the received feedback data in a database.

[1254] Output: Feedback data is saved in the database. A success message is displayed.

[1255] Step 8: Analyze the feedback emotional state with the Emotion Engine

[1256] Input: User feedback data.

[1257] Specific operation: The server starts the emotion engine and analyzes the stored feedback data.

[1258] Data processing and computation: The emotion engine analyzes the feedback data and recognizes the emotional state.

[1259] Output: The analysis results are stored in a database along with the feedback data.

[1260] Step 9: Improve your content

[1261] Input: Feedback data and the analysis results of its emotional state.

[1262] Specific operation: The server analyzes this data and generates suggestions for future content improvements.

[1263] Data processing and calculation: Statistical analysis and trend analysis are carried out, and specific improvement plans are created.

[1264] Output: An improvement plan is developed and reflected in future content creation.

[1265] (Application example 2)

[1266] 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."

[1267] Conventional interview article generation systems have had difficulty in fully utilizing user feedback to improve content quality. In particular, they lacked technology for analyzing the emotional aspects of feedback, making it difficult to individually optimize the user experience.

[1268] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for conducting interviews with people who have specialized knowledge and experience in a specific field using an automatic generation AI and generating an article based on the interview results, means for a user to register or log in, means for generating an interview form and sending it to the target person, means for writing an article based on the interview results using the generation AI and publishing the article, means for collecting user feedback on the article and using the feedback data to improve the content, and means for analyzing the feedback data using an emotion engine and improving the content based on user emotions. This makes it possible to analyze users' emotional feedback and generate individually optimized, high-quality content.

[1269] "Automatic generation AI" is a technology that uses artificial intelligence to automatically generate interviews and texts without the need for humans to do it manually.

[1270] An "interview form" is an electronic format for framing specific questions and soliciting responses from a person with specialized knowledge or experience.

[1271] "Generative AI" is an artificial intelligence system that automatically generates text, articles, and questions based on input data.

[1272] "Articling" is the process of compiling collected information and data into text and presenting it to readers.

[1273] "Feedback" refers to response information such as opinions, impressions, and evaluations provided by users.

[1274] The "emotion engine" is a system that analyzes the emotions contained in the answers and feedback of users and experts and determines whether they are positive or negative.

[1275] A "server" is a computer system that processes, stores, and communicates data.

[1276] "Content improvement" is the process of making changes and revisions to improve the quality of the information and articles we provide, based on recent user feedback and analysis.

[1277] This invention is a system that uses automatic generation AI to conduct interviews with people with specialized knowledge and experience in a specific field (hereinafter referred to as experts), generates and publishes the results as articles, and further improves the quality of content by analyzing user feedback with an emotion engine.

[1278] 1. User Registration / Login

[1279] Hardware: Smartphones, tablets

[1280] Software: Frontend (React Native), Backend (Node.js), Database (MongoDB)

[1281] process:

[1282] A user signs up or logs in.

[1283] The front end provides user input information as a form.

[1284] The user's input information (username, password, email address) is sent to the server.

[1285] The server receives the information and stores it in a database or performs authentication.

[1286] 2. Generate an interview form

[1287] Hardware: Server

[1288] Software: Generative AI model (OpenAI GPT-4), database (MongoDB)

[1289] process:

[1290] The server retrieves the expert's profile information from the database.

[1291] Enter your profile information into the generative AI to generate customized questions.

[1292] The generated questions are reconstructed as an interview form and sent to the expert.

[1293] 3. Receiving and analyzing interview responses

[1294] Hardware: Server

[1295] Software: Frontend (React Native), Backend (Node.js), Sentiment Engine (Sentiment Analysis API)

[1296] process:

[1297] Experts will answer the interview form.

[1298] The response data is sent to the server.

[1299] The server stores the received response data in a database.

[1300] Activate the emotion engine to recognize the emotional state of the person at the time of answering.

[1301] The response data is saved along with the recognition results.

[1302] 4. Article creation and preparation for publication

[1303] Hardware: Server

[1304] Software: Generative AI model (OpenAI GPT-4), database (MongoDB)

[1305] process:

[1306] The server passes the saved response data to the generative AI model.

[1307] Generative AI models create detailed articles.

[1308] Store the article in a database and prepare it for publication.

[1309] 5. Publish the article and analyze the feedback

[1310] Hardware: smartphones, tablets, servers

[1311] Software: Frontend (React Native), Backend (Node.js), Sentiment Engine (Sentiment Analysis API)

[1312] process:

[1313] The server displays the generated articles on the platform.

[1314] Users view articles and provide feedback.

[1315] The feedback data is sent to the server and analyzed by the emotion engine.

[1316] Content improvements are made based on the recognition results.

[1317] Examples:

[1318] Example of system operation

[1319] The server generates interviews with famous chefs in the culinary field.

[1320] Sample questions: "What was the most challenging aspect of developing your latest recipe?", "What was the most important lesson you learned during the cooking process?"

[1321] A user reads an article and provides feedback saying, "This article was very helpful. I'd like to learn more about it."

[1322] Example prompt sentence:

[1323] Prompt to be input to the generated AI:

[1324] “Based on the chef’s profile provided, generate customized questions about his / her recent projects and learnings.”

[1325] Example of generated question:

[1326] "Tell me about your most recent recipe development. What made it particularly challenging?"

[1327] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1328] Step 1:

[1329] A user registers or logs in. Using a smartphone or tablet, the user enters their name, password, and email address. The information is compiled into a form and sent from the device to the server. The server receives it and stores it in a database, or authenticates it in the case of a login. The input data is the username, password, and email address, and the output is approval of the registration or authentication result for the login.

[1330] Step 2:

[1331] The server retrieves the expert's profile information from the database. This profile information is basic data about the expert (such as name, career history, and area of ​​expertise). Input data for the generation AI is constructed based on the retrieved profile information. The generation AI generates customized interview questions based on the given profile information. The input to the generation AI is the profile information, and the output is customized questions.

[1332] Step 3:

[1333] The generated questions are reconstructed as an interview form, which the server sends to the expert. The expert receives the interview form on his / her terminal and enters answers to each question. At this time, the terminal sends the expert's input data to the server, and the sent answer data is temporarily stored in the terminal's memory. The input data are the generated questions and the expert's answers, and the output is the data sent to the server.

[1334] Step 4:

[1335] The server stores the received response data in a database. During this process, the server activates an emotion engine to perform emotion analysis on the response data. The input data to the server is the response data, to which emotion labels are assigned by the emotion engine. The output is the analyzed emotion data and its corresponding label.

[1336] Step 5:

[1337] The server passes the saved response data and emotion labels to the generation AI, which then generates a detailed article. The generation AI uses this information to create specific and detailed article text. The input data to the generation AI are the response data and emotion labels, and the output is the generated article text.

[1338] Step 6:

[1339] The generated article text is stored in a database by the server and displayed on the platform when it is ready to be published. Other users can view the article and provide feedback. Viewers can enter feedback using their smartphones or tablets and send it to the server. The input data is the user feedback, and the output is the feedback data.

[1340] Step 7:

[1341] The server receives the feedback data and analyzes it using an emotion engine. Based on the analysis results, the server improves the content. The input data for feedback is the user's impressions and evaluations, and the output is feedback data with emotion labels. This data is used as a reference for future content generation and improvements.

[1342] 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.

[1343] 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.

[1344] 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.

[1345] [Fourth embodiment]

[1346] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1347] 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.

[1348] 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).

[1349] 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.

[1350] 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.

[1351] 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).

[1352] 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.

[1353] 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.

[1354] 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.

[1355] 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.

[1356] 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.

[1357] 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.

[1358] 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."

[1359] This invention is a system that uses automatic generation AI to conduct interviews with people who have specialized knowledge and experience in a specific field (hereinafter referred to as specialists), generates the interview results as articles, and provides them to users. This system is composed of the following steps.

[1360] First, a user registers or logs in. When registering, the device provides a form for entering basic information such as username, password, and email address, which is then sent to the server. The server verifies the received information and stores it in a database if there are no problems. Similarly, if an existing user enters login information, the server authenticates them and, if successful, allows the user to access the system.

[1361] Next, an interview form for the specialist is generated. The server retrieves the specialist's profile information from the database and passes it to the generation AI to generate customized questions. The generated questions are reconstructed as an interview form and sent to the specialist's device.

[1362] Next, the specialist uses the terminal to enter answers into the interview form and send them to the server, which then stores the received answer data in a database.

[1363] The server then passes the saved response data back to the AI ​​generator to generate a detailed article, which is then stored in a database by the server and prepared for publication.

[1364] Once an article is published, the server displays it on the platform for all users to see, and users can provide feedback on the article, which is sent back to the server and stored in a database.

[1365] As a concrete example, suppose a specialist who is an expert in a particular field (e.g., craft making) logs into the system and updates his or her profile. Based on this profile information, the server generates customized questions such as, "Tell us about your most challenging project" and "What important lessons did you learn through that project?" These questions are provided to the specialist as an interview form, and the specialist answers them. After the response data is sent and stored on the server, the generation AI uses the content to create a detailed article. This article is finally published, allowing other users to view it and discover the appeal of crafts as a new hobby, as well as provide feedback.

[1366] In this way, the system allows for the effective sharing of specialized knowledge and experience, enabling many users to discover new hobbies and interests.

[1367] The processing flow will be explained below.

[1368] Step 1:

[1369] The user registers or logs in. The user clicks the "Register" button on the device and enters the user name, password, email address, etc. Once the registration information is complete, the device sends this information to the server.

[1370] Step 2:

[1371] The server verifies the received user information. It checks the email address format and password strength, and if there are no problems, it saves the user information in the database. It returns a message to the user that registration is complete.

[1372] Step 3:

[1373] The terminal displays a login screen, and the user enters a username and password. The terminal then sends the input data to the server.

[1374] Step 4:

[1375] The server verifies the login information it receives. If it is correct, it authenticates the user and allows access. If it is incorrect, it returns an error message.

[1376] Step 5:

[1377] The server retrieves the specialist's profile information from the database, including the specialist's area of ​​expertise and past experience.

[1378] Step 6:

[1379] The server passes the acquired profile information to the generation AI, which generates customized interview questions. The generated questions are then reconstructed into an interview form.

[1380] Step 7:

[1381] The server sends the generated interview form to the specialist's terminal, which displays it to the specialist.

[1382] Step 8:

[1383] The user (specialist) enters answers into the interview form. After entering the necessary answers, the user clicks the "Submit" button and the answer data is sent to the server.

[1384] Step 9:

[1385] The server saves the received response data in a database, and once saving is complete, returns a notification of transmission completion to the device.

[1386] Step 10:

[1387] The server then passes the saved response data back to the AI ​​generator, which then generates a detailed article based on that data.

[1388] Step 11:

[1389] The server saves the generated article to the database, and once saved, sets the status to "ready to publish".

[1390] Step 12:

[1391] The server publishes new articles on the platform, where they become available for all users to view.

[1392] Step 13:

[1393] The device displays a notification of the published article to the user, who can then view the article and post comments and impressions.

[1394] Step 14:

[1395] The user enters feedback on the article and clicks the "Submit" button. The device sends the feedback to the server.

[1396] Step 15:

[1397] The server saves the received feedback in the database, and once saving is complete, returns a feedback completion notification to the user.

[1398] Through these steps, this system can effectively compile interviews with specialists with specialized knowledge and experience into articles, and provide many users with new hobbies and interests.

[1399] Example 1

[1400] 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."

[1401] The present invention aims to provide a system that allows users to easily acquire new knowledge and interests by automatically conducting interviews with people who have specialized knowledge and experience in a specific field and generating and publishing the results of those interviews as articles.The objective of this system is to automate the process of effectively collecting specialized information and turning it into articles, thereby improving user convenience.

[1402] 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.

[1403] In this invention, the server includes a means for a user to register or log in, a means for transmitting user information to the server using a terminal, and a means for verifying the user information received by the server and storing it in a database, thereby enabling user information to be registered and managed reliably.

[1404] The server includes a means for acquiring profile information of the target person and generating customized questions using a generative AI model, a means for generating an interview form and sending it to the target person, and a means for the target person to answer the interview form and send it to the server using a terminal, thereby enabling individual interviews to be conducted efficiently and automatically.

[1405] Furthermore, the server includes means for creating articles based on the interview results using the generative AI model and storing the articles in a database, means for publishing the articles and making them available for other users to view, and means for collecting user feedback on the articles and storing the feedback in a database, thereby enabling the generated articles to be published quickly and for the articles to be improved based on user feedback.

[1406] A "user" is a person who accesses the system and provides information or views content.

[1407] A "terminal" is a device used by a user for operation, and includes, for example, a computer, a smartphone, a tablet, and the like.

[1408] The "Server" is the central computer system that receives, verifies, and stores user-submitted information and automates the interview using the generative AI model.

[1409] A "database" is a system that systematically stores user information, interview results, generated articles, feedback, etc.

[1410] "Profile information" is information about a person with specialized knowledge or experience in a particular field, and is used to generate customized questions.

[1411] A "generative AI model" is an artificial intelligence model that automatically generates new content based on generated text, and includes, for example, models that use natural language processing technology.

[1412] An "Interview Form" is an electronic form for presenting customized questions to a Specialist.

[1413] "Response data" refers to the response information entered by the subject in the interview form.

[1414] An "article" is text content generated using a generative AI model based on interview form response data.

[1415] "Feedback" refers to comment information such as impressions and suggestions for improvement provided by users regarding an article.

[1416] "Publishing" refers to the act of displaying the generated article on a web platform so that it can be viewed by general users.

[1417] This invention is a system that uses automatic generation AI to conduct interviews with people with specialized knowledge and experience (hereinafter referred to as specialists), generates articles based on the interview results, and provides them to users. This system is implemented using the following specific hardware and software.

[1418] First, a user accesses the system using a terminal. The terminal can be a computer, smartphone, tablet, etc. The user registers or logs in. The terminal provides a form for entering user information, and the information entered by the user is sent to the server. This information includes the user name, password, email address, etc.

[1419] The server verifies the received user information and stores it in the database if there are no problems. Validation can be performed using a web framework such as Django. For new users, the server verifies that the registration information does not overlap with existing data, and for valid logins, the server verifies that the entered information matches the information in the database.

[1420] Next, the server retrieves the specialist's profile information from the database. Based on the retrieved information, it generates customized questions. This process uses a generative AI model (e.g., OpenAI's GPT-3). The prompt for the generative AI model is as follows:

[1421] Example prompt sentence:

[1422] "The specialist's name is ____. He is an expert in crafting. Generate questions for him such as:

[1423] 1. Tell us about your most challenging project.

[1424] 2. What are some important lessons you learned through the project?

[1425] 3. What crafts would you recommend for beginners?

[1426] The server reconstructs the generated questions as an interview form and sends it to the specialist's terminal. The specialist uses the terminal to enter answers into the interview form, and the terminal sends the entered answers to the server. The server stores the received answer data in a database.

[1427] The server then passes the saved response data back to the generation AI, which then generates a detailed article. For example, the generation AI might construct a sentence like, "Mr. / Ms. XX's most challenging project was XX." The generated article is then stored in a database by the server, ready for publication.

[1428] Once an article is published, the server displays it on the platform for all users to view, allowing them to gain new knowledge and interest. Furthermore, users can provide feedback on articles, which they send from their devices to the server. The server stores the received feedback in a database and uses it to improve the article.

[1429] This system automatically collects and systematically shares specialized knowledge and experience. Furthermore, by improving the content of articles based on user feedback, it becomes possible to provide more useful information. This is a specific embodiment of the present invention.

[1430] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1431] Step 1:

[1432] User registration or login

[1433] 1.1 A user accesses the system from a terminal through a web browser.

[1434] 1.2 The device displays a form for the user to sign up or log in.

[1435] Input: Personal information such as username, password, and email address

[1436] Output: User information to be sent

[1437] 1.3 The user enters the required information and clicks the "Submit" button.

[1438] 1.4 The terminal sends the entered information to the server.

[1439] Step 2:

[1440] Server verifies and stores user information

[1441] 2.1 The server verifies the received user information.

[1442] Input: Submitted user information

[1443] Output: Verification result (success / failure)

[1444] 2.2 In the case of new registration, the server checks whether the information is a duplicate of existing data in the database. In the case of login, the server checks whether the input information matches the information in the database.

[1445] 2.3 If the verification is successful, the server stores the user information in the database.

[1446] 2.4 The server then sends a message to the terminal indicating successful authentication.

[1447] Input: Validation result

[1448] Output: Authentication message

[1449] Step 3:

[1450] Obtaining specialist profile information and generating customized questions

[1451] 3.1 The server retrieves the specialist's profile information from the database.

[1452] Input: Specialist User ID

[1453] Output: Profile information

[1454] 3.2 Based on the profile information obtained by the server, a prompt sentence is input to the generative AI model (e.g., OpenAI GPT-3).

[1455] Input: Profile information, prompt text

[1456] Output: Customized question

[1457] 3.3 The server reconstructs the generated questions into an interview form and sends it to the specialist's terminal.

[1458] Input: Customized Question

[1459] Output: Interview form

[1460] Step 4:

[1461] Enter and submit answers to the interview form

[1462] 4.1 The specialist uses the terminal to enter responses into the interview form.

[1463] Input: Interview Form

[1464] Output: Response data

[1465] 4.2 The Specialist completes the response and clicks the "Submit" button.

[1466] 4.3 The terminal sends the entered response data to the server.

[1467] Step 5:

[1468] Response data saved on the server

[1469] 5.1 The server validates the response data received.

[1470] Input: Submitted response data

[1471] Output: Verification results

[1472] 5.2 If the verification is successful, the server stores the response data in the database.

[1473] Input: Validated response data

[1474] Output: Answer data stored in a database

[1475] Step 6:

[1476] Generating interview articles using generative AI models

[1477] 6.1 The server passes the saved answer data to a generative AI model (e.g., OpenAI GPT-3) to generate detailed articles.

[1478] Input: Response data

[1479] Output: The generated article

[1480] 6.2 The server stores the generated articles in a database.

[1481] Step 7:

[1482] Publish your article and gather feedback

[1483] 7.1 The server displays the ready-to-publish articles on the web platform.

[1484] Input: Generated article

[1485] Output: Published articles

[1486] 7.2 Users view articles and provide feedback.

[1487] Input: Feedback information

[1488] Output: Feedback to be sent

[1489] 7.3 The device sends the user-entered feedback to the server.

[1490] 7.4 The server stores the received feedback in a database.

[1491] Input: Submitted feedback

[1492] Output: Feedback stored in a database

[1493] (Application example 1)

[1494] 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."

[1495] Conventional article generation systems using human interviews have faced challenges such as the high labor costs of conducting interviews and writing articles, as well as the difficulty of sharing specialized knowledge. Furthermore, the generated content needed to be provided in a format that was useful to a wide range of users, not limited to a specific category. However, previous technology did not provide a means to easily conduct interviews, generate articles, and publish them as a smartphone application.

[1496] 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.

[1497] In this invention, the server includes: means for conducting interviews with people with specialized knowledge and experience in a specific field using automatic generation AI and generating articles based on the interview results; means for users to register or log in; means for generating interview forms and sending them to the target individuals; means for using the generation AI to write articles about the interview results and publishing the articles; means for collecting user feedback on the articles and using it to improve content; means for making the generated articles available to other users in a content distribution service; and means for installing the articles as a smartphone application. This allows experts' knowledge and experience to be shared effectively, enabling users to discover new knowledge and interests. Furthermore, the smartphone application improves convenience and accessibility, potentially attracting a wide range of users.

[1498] A "person with specialized knowledge or experience in a particular field" is a person who has in-depth knowledge or practical experience in a particular specialized field that goes beyond general understanding.

[1499] An "interview" is a form of communication in which specific questions are answered by someone with specialized knowledge or experience.

[1500] "Automatic generation AI" refers to programs or systems that use artificial intelligence technology to automatically generate sentences, questions, articles, etc.

[1501] An "article" is written content that is based on interview results or other information.

[1502] "User registration" is the process by which a new user registers the personal information and authentication information required to use the system.

[1503] "Login" refers to the process by which an existing user enters the necessary authentication information to access a system and is authenticated.

[1504] An "interview form" is a written or electronic format that provides the questions and information needed to conduct an interview.

[1505] "Profile information" refers to personal information about the person being interviewed, such as their background, area of ​​expertise, and experience.

[1506] "Customized Questions" are individual questions created to drill down into specific topics based on a person's profile information.

[1507] "Feedback" refers to ratings and opinions provided by users regarding articles and content.

[1508] A "content distribution service" is a service that makes generated content available on the Internet so that users can view and access it.

[1509] A "smartphone application" is a software program that runs on a smartphone and through which services can be used.

[1510] A "database" is a system for efficiently and safely storing and managing collected data and information.

[1511] The system for implementing this invention uses an automatic generation AI to conduct interviews with people with specialized knowledge and experience in a specific field, and then generates an article based on the results of the interview and provides it to users. This system is primarily based on the interaction between a server, a terminal, and a user.

[1512] System configuration

[1513] 1. User Registration and Login:

[1514] Server: The user is presented with a form to register and enters basic information such as username, password, email address, etc. The information is sent to the server, which validates it and stores it in a database. Similarly, when an existing user logs in, the information is authenticated and, if successful, the user is granted system access.

[1515] 2. Generate the interview form:

[1516] Server: Retrieves specialist profile information from the database and passes it to the generation AI to generate customized questions. The generated questions are organized into an interview form and sent to the specialist's device.

[1517] 3. Collecting interview responses:

[1518] Terminal: The specialist enters answers into the interview form and sends the answers to the server via the terminal.

[1519] Server: Stores the received response data in a database.

[1520] 4. Article generation and publishing:

[1521] Server: The saved response data is passed to the AI ​​again to generate detailed articles. The generated articles are stored in a database and can be viewed by other users once they are ready to be published. They can also be provided in a format that can be installed as a smartphone application.

[1522] 5. Gathering Feedback:

[1523] Users: can provide feedback on articles, which will be sent to the server and stored in the database to improve the content.

[1524] Processing Details

[1525] 1. Hardware and Software:

[1526] Server: Runs the main program and manages the database. Builds an API server using the Flask framework and manages the database using SQLite.

[1527] Terminal: Devices used by specialists and general users, including smartphones, tablets, etc.

[1528] Generative AI models: Used for specific interview question generation and article generation. These include models like InterviewAI and ArticleGenerationAI.

[1529] Specific examples

[1530] Example of interview generation for experts

[1531] Profile Information:

[1532] Name: Yamada Taro

[1533] Specialty: Crafts

[1534] prompt:

[1535] Taro Yamada, tell us about your most challenging craft project and the lessons you learned.

[1536] Example questions generated:

[1537] 1. Tell us about your most challenging project.

[1538] 2. What are some important lessons you learned through the project?

[1539] The purpose of this system is to effectively share specialized knowledge and experience with many users through such concrete examples. Because it can be used through a smartphone application, it is convenient and accessible, and we expect it to be used by a wide range of users.

[1540] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1541] Step 1:

[1542] User Registration

[1543] User: To create a new account, a user enters basic information such as a username, password, and email address.

[1544] Server: The server receives this basic information, verifies the validity of the data, and if there are no problems, stores this information in a database (SQLite).

[1545] Input: Username, Password, Email Address.

[1546] Output: Validated user data is stored in the database.

[1547] Step 2:

[1548] Log in

[1549] User: An existing user logs into the system by entering their username and password.

[1550] Server: The server receives the entered authentication information, checks it against existing data in a database, and if successful, grants the user access to the system.

[1551] Input: Username, Password.

[1552] Output: If authentication is successful, grant access to the system. If authentication fails, return an error message.

[1553] Step 3:

[1554] Obtaining profile information and generating questions

[1555] Server: Retrieves specialist profile information from the database and passes it to the generation AI (InterviewAI).

[1556] Generative AI: Generates customized questions based on profile information.

[1557] Input: Specialist profile information.

[1558] Output: A customized interview form.

[1559] Server: Reconstructs the generated questions into an interview form and sends it to the specialist's terminal.

[1560] Step 4:

[1561] Enter and submit your interview answers

[1562] Specialist: Enter answers into the interview form and send them to the server via the terminal.

[1563] Server: Stores the received response data in a database.

[1564] Input: Specialist response data.

[1565] Output: Response data stored in a database.

[1566] Step 5:

[1567] Article Generation

[1568] Server: Pass the saved answer data to the generation AI (ArticleGenerationAI) to generate detailed articles.

[1569] Generative AI: Generates articles based on response data.

[1570] Input: Specialist response data.

[1571] Output: The generated article.

[1572] Server: Stores the generated articles in a database and prepares them for publication.

[1573] Step 6:

[1574] Article published

[1575] Server: The generated articles are published on the platform, allowing users to view them. They are also provided in a format that can be installed as a smartphone application.

[1576] Input: The generated article.

[1577] Output: The published article.

[1578] Step 7:

[1579] Feedback collection and storage

[1580] Users: Can view articles and provide feedback.

[1581] Server: Receives user feedback and stores it in a database.

[1582] Input: User feedback.

[1583] Output: Feedback stored in a database.

[1584] 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.

[1585] This invention is a system that uses an automatic generation AI to conduct interviews with people with specialized knowledge and experience in a specific field (hereinafter referred to as specialists), generates articles based on the results of the interviews, and then uses an emotion engine to analyze user feedback and emotions at the time of responses, thereby improving the quality of the content. This system is composed of the following steps.

[1586] First, a user registers or logs in. When registering, the device provides a form for entering basic information such as username, password, and email address. Once the information is entered, the device sends this information to the server. The server verifies the received information and stores it in the database if there are no problems. If an existing user enters login information, the server performs authentication, and if successful, the user can access the system.

[1587] Next, an interview form for the specialist is generated. The server retrieves the specialist's profile information from the database and passes it to the generation AI to generate customized questions. The generated questions are reconstructed as an interview form and sent to the specialist's device.

[1588] The specialist uses a terminal to enter answers into the interview form and send them to the server. The server stores the received answer data in a database. At this point, the server activates an emotion engine to analyze the answer data and recognize the emotional state of the specialist at the time of answering. The recognition results are stored along with the answer data and can be used to improve the quality of the interview content.

[1589] The server then passes the saved response data back to the AI ​​generator to generate a detailed article. The AI ​​uses this data to create a specific and detailed article. The generated article is then stored in the database by the server, ready for publication.

[1590] Once an article is published, the server displays it on the platform for all users to view. Users can also provide feedback on the article. When the feedback data is sent to the server, an emotion engine analyzes the content and recognizes the user's emotional state. Based on the recognition results, the server improves the content.

[1591] As a concrete example, consider a scenario in which a craftsman logs into the system and updates his or her profile. Based on this information, the server generates questions such as, "Tell us about your most challenging project" and "What important lessons did you learn from that project?" The specialist fills out an interview form, and the emotion engine analyzes the specialist's emotional state. The server stores the response data along with the specialist's emotional state, and then publishes a detailed article based on this information on the platform. When other users view the article and provide feedback, the emotion engine is also used, and future content is improved based on the obtained emotional data.

[1592] In this way, this system can effectively turn interviews with specialists with specialized knowledge and experience into articles, and by utilizing an emotion engine, it is possible to provide many users with new hobbies and interests.

[1593] The processing flow will be explained below.

[1594] Step 1:

[1595] A user registers or logs in. The user clicks the "Register" button on the device and enters information such as a username, password, and email address. Once the information is entered, the device sends it to the server.

[1596] Step 2:

[1597] The server verifies the user information it receives. It checks the email address format and password strength, and if there are no problems, it saves the user information in the database. It returns a message to the user that registration is complete to the terminal. If an existing user enters login information, the server performs authentication processing, and if successful, grants the user access rights.

[1598] Step 3:

[1599] The server retrieves the specialist's profile information from the database, including their area of ​​expertise, past projects, experience, etc.

[1600] Step 4:

[1601] The server passes the acquired profile information to the generation AI, which generates customized interview questions. The generation AI then creates the questions and reconstructs them into an interview form.

[1602] Step 5:

[1603] The server sends the generated interview form to the specialist's terminal, which displays the interview form and allows the specialist to enter answers.

[1604] Step 6:

[1605] The user (specialist) uses the terminal to enter answers into the interview form. Once the answers are complete, the user clicks the "Submit" button to send the answer data to the server.

[1606] Step 7:

[1607] The server stores the received answer data in a database. At this time, the server activates an emotion engine to analyze the data to recognize the emotional state of the specialist at the time of answering. The analysis results are stored together with the answer data.

[1608] Step 8:

[1609] The server then passes the saved response data back to the AI ​​generator, which then creates a detailed article based on the interview content.

[1610] Step 9:

[1611] The server saves the generated article to the database, and once done sets the status to indicate that the article is ready to be published.

[1612] Step 10:

[1613] The server publishes new articles on the platform, where they become available for all users to view.

[1614] Step 11:

[1615] The device displays a notification of the published article to the user, who can then view the article and post comments and impressions.

[1616] Step 12:

[1617] The user enters feedback on the article and clicks the "Submit" button. The device sends the feedback to the server.

[1618] Step 13:

[1619] The server stores the received feedback in a database. At this time, the server activates the emotion engine again to analyze the user's feedback and recognize their emotional state. The server then improves the content based on the analysis results.

[1620] Step 14:

[1621] The server sends a feedback completion notification to the terminal, which the terminal displays to the user, completing the feedback process.

[1622] Through these steps, this system can effectively turn interviews with specialists with specialized knowledge and experience into articles, and by using an emotion engine to analyze user feedback and the emotions expressed when answering, it can improve the quality of the content and provide many users with new hobbies and interests.

[1623] Example 2

[1624] 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."

[1625] In order to effectively turn interviews with specialists (people with specialized knowledge and experience in a specific field) into articles and improve the quality of those articles, it is important to improve the content by incorporating the depth and variety of the interview content and reader feedback. However, conventional systems have difficulty incorporating the emotions of specialists and readers, making it difficult to fully utilize feedback to improve the content. Furthermore, there is a lack of customization in the automatic generation of interview questions and the article-writing process, which means that the results of specialized interviews are not fully reflected in the articles.

[1626] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1627] In this invention, the server includes means for using an automatic generation AI to conduct interviews with people who have specialized knowledge and experience in a specific field and generate articles based on the interview results, means for a user to register or log in, means for generating an interview form and sending it to the person, means for using the generation AI to write an article about the interview results and publishing the article, means for collecting user feedback on the article and using the feedback to improve the content, means for using an emotion engine to analyze the person's emotional state at the time of their response, and means for using the emotion engine to analyze the emotional state of the user's feedback. This makes it possible to improve the quality of specialized interviews by taking the emotional state into consideration and to continuously improve the content based on the feedback.

[1628] "Automatic generation AI" is an artificial intelligence system that automatically generates text using natural language processing technology.

[1629] A "server" is a central processing unit that processes and manages data on a network.

[1630] A "terminal" is a device through which a user enters data or accesses information.

[1631] "User registration" is the process by which a user provides information about themselves and creates an account in order to use the system.

[1632] "Login" is the process by which an existing user is authenticated to access a system.

[1633] An "interview form" is a formal document containing specific questions that the interviewee uses to write their responses.

[1634] "Generative AI" is an artificial intelligence model that automatically generates new text based on given data or prompts.

[1635] "Articling" is the process of converting received data and information into an article format for readers.

[1636] "Publishing" is the process of making a generated article accessible to the public.

[1637] "Feedback" refers to the evaluations and opinions that users provide regarding articles and services.

[1638] An "emotion engine" is a software system for analyzing emotions in text and recognizing emotional states.

[1639] "Emotional state" refers to the emotional response of the person who generated the text and the user who provided the feedback.

[1640] A "database" is a system for storing and managing structured data.

[1641] "Profile information" refers to detailed information such as the background and qualifications of a user or expert.

[1642] This invention is a system that uses automatic generation AI to conduct interviews with people (specialists) who have specialized knowledge and experience in a specific field, generates the interview results as articles, and further improves the quality of content by using an emotion engine to analyze user feedback and emotions at the time of response.

[1643] The system includes the following major hardware and software components:

[1644] Server: The central unit that processes, manages, and stores data.

[1645] Terminal: A device that allows a user to input data or display information. Examples include personal computers and smartphones.

[1646] Generative AI: An artificial intelligence system that generates text based on interview results and prompts. OpenAI GPT-3 is used as an example.

[1647] Emotion engine: Software that analyzes the emotional state of text provided by a user or specialist. For example, IBM Watson Tone Analyzer is used.

[1648] System Overview

[1649] First, a user registers or logs in. The device provides a form for entering basic information such as username, password, and email address, and then sends the information to the server. The server verifies the received information and stores it in a database if there are no problems. If the user is an existing user, the server authenticates the entered login information, and if successful, the user is allowed to access the system.

[1650] Next, an interview form for the specialist is generated. The server retrieves the specialist's profile information from the database and passes it to the generation AI to generate customized questions. For example, a question might be generated such as, "Tell us about your most challenging project." The generated questions are reconstructed as an interview form and sent to the specialist's device.

[1651] The specialist uses a terminal to enter answers into the interview form and send them to the server. The server stores the received answer data in a database. At this point, the server activates an emotion engine to analyze the emotional state of the specialist at the time of answering. The analysis results are stored along with the answer data and are used to improve the quality of the interview content.

[1652] The server then passes the saved response data back to the AI ​​generator to generate a detailed article. The generated article is specific and detailed. For example, a detailed article is generated based on the interview responses, such as "what the specialist described as the most challenging project." The generated article is then stored in a database by the server and prepared for publication.

[1653] Once an article is published, the server displays it on the platform for all users to view. Users can also provide feedback on the article. When the feedback data is sent to the server, the emotion engine analyzes its content and recognizes the user's emotional state. Based on the recognition results, the server improves the content.

[1654] Examples of concrete examples and prompts

[1655] Specific examples

[1656] Consider a scenario in which a craftsman logs into the system and updates his or her profile. During this process, the server generates questions based on the specialist's profile information, such as "Tell us about your most challenging project" and "What important lessons did you learn through this project?" The specialist fills out an interview form, and the emotion engine analyzes the specialist's emotional state. The server stores the emotional state along with the response data, and publishes a detailed article based on this information on the platform. Furthermore, the emotion engine is also used when other users view the article and provide feedback on their impressions and opinions. The obtained emotion data is used to improve future content.

[1657] Prompt Sentence Examples

[1658] "Consider questions that can be generated based on the specialist's profile information. For example, generate questions about their most challenging project and the key lessons learned through that project."

[1659] In this way, this system can effectively turn interviews with specialists with specialized knowledge and experience into articles, and by utilizing an emotion engine, it is possible to provide many users with new hobbies and interests.

[1660] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1661] Step 1: User registration and login

[1662] Input: A user accesses the new registration or login page using a terminal. If registering for the first time, they enter basic information such as their username, password, and email address. If they are an existing user, they enter their username and password.

[1663] Specific operation: The terminal displays a new registration form or login form. The user enters the required information and presses the submit button. The terminal then sends this information to the server.

[1664] Data processing and calculation: The server verifies the received information and stores it in the database in the case of new registration. In the case of login, it compares it with the information stored in the database.

[1665] Output: If new registration is successful, the message "Registration complete" is displayed, and if login is successful, access to the system is permitted. If authentication is unsuccessful, an "Error message" is displayed.

[1666] Step 2: Obtaining specialist profiles and generating interview forms

[1667] Input: The server retrieves the specialist's profile information from the database.

[1668] Specific operation: The server accesses the database to obtain the profile information of the target specialist, and passes the obtained information to the generation AI to generate customized questions.

[1669] Data processing and calculation: Generative AI (e.g., OpenAI GPT-3) generates customized questions based on the profile information obtained.

[1670] Output: The generated customized questions are output in text format, which the server reconstructs into an interview form and sends to the specialist's terminal.

[1671] Step 3: Fill in and submit the interview form

[1672] Input: The specialist uses the terminal to input answers into the interview form.

[1673] Specific operation: The terminal displays the interview form, and the specialist enters the necessary answers. Once the input is complete, the specialist presses the send button. The terminal then sends this to the server.

[1674] Data processing and calculation: The server stores the received response data in a database.

[1675] Output: The answer data is saved in the database. A success message is displayed on the specialist's terminal.

[1676] Step 4: Emotional state analysis by the emotion engine

[1677] Input: The answer data from the interview form is saved on the server.

[1678] Specific operation: The server launches an emotion engine (e.g., IBM Watson Tone Analyzer) to analyze the saved response data.

[1679] Data processing and calculation: The emotion engine analyzes the response data and recognizes the emotional state.

[1680] Output: The analysis results are saved in a database along with the response data.

[1681] Step 5: Article generation

[1682] Input: Answer data stored in the database and the analysis results of the emotional state.

[1683] Specific operation: The server passes the saved response data and the analysis results of the emotional state back to the generation AI, which then generates a detailed article.

[1684] Data processing and calculation: Generative AI generates specific and detailed articles based on this data.

[1685] Output: The generated articles are stored in the database.

[1686] Step 6: Publish your article

[1687] Input: Generated article data.

[1688] Specific operation: The server retrieves article data from the database and displays it on the platform.

[1689] Data processing and calculation: Article data is formatted and its layout is adjusted.

[1690] Output: The article is published and available for all users to see.

[1691] Step 7: Providing and collecting user feedback

[1692] Input: User-provided feedback.

[1693] Specific operation: The terminal displays the feedback form, the user enters the feedback, and when the user presses the send button, the terminal sends it to the server.

[1694] Data processing and calculation: The server stores the received feedback data in a database.

[1695] Output: Feedback data is saved in the database. A success message is displayed.

[1696] Step 8: Analyze the feedback emotional state with the Emotion Engine

[1697] Input: User feedback data.

[1698] Specific operation: The server starts the emotion engine and analyzes the stored feedback data.

[1699] Data processing and computation: The emotion engine analyzes the feedback data and recognizes the emotional state.

[1700] Output: The analysis results are stored in a database along with the feedback data.

[1701] Step 9: Improve your content

[1702] Input: Feedback data and the analysis results of its emotional state.

[1703] Specific operation: The server analyzes this data and generates suggestions for future content improvements.

[1704] Data processing and calculation: Statistical analysis and trend analysis are carried out, and specific improvement plans are created.

[1705] Output: An improvement plan is developed and reflected in future content creation.

[1706] (Application example 2)

[1707] 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."

[1708] Conventional interview article generation systems have had difficulty in fully utilizing user feedback to improve content quality. In particular, they lacked technology for analyzing the emotional aspects of feedback, making it difficult to individually optimize the user experience.

[1709] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for conducting interviews with people who have specialized knowledge and experience in a specific field using an automatic generation AI and generating an article based on the interview results, means for a user to register or log in, means for generating an interview form and sending it to the target person, means for writing an article based on the interview results using the generation AI and publishing the article, means for collecting user feedback on the article and using the feedback data to improve the content, and means for analyzing the feedback data using an emotion engine and improving the content based on user emotions. This makes it possible to analyze users' emotional feedback and generate individually optimized, high-quality content.

[1710] "Automatic generation AI" is a technology that uses artificial intelligence to automatically generate interviews and texts without the need for humans to do it manually.

[1711] An "interview form" is an electronic format for framing specific questions and soliciting responses from a person with specialized knowledge or experience.

[1712] "Generative AI" is an artificial intelligence system that automatically generates text, articles, and questions based on input data.

[1713] "Articling" is the process of compiling collected information and data into text and presenting it to readers.

[1714] "Feedback" refers to response information such as opinions, impressions, and evaluations provided by users.

[1715] The "emotion engine" is a system that analyzes the emotions contained in the answers and feedback of users and experts and determines whether they are positive or negative.

[1716] A "server" is a computer system that processes, stores, and communicates data.

[1717] "Content improvement" is the process of making changes and revisions to improve the quality of the information and articles we provide, based on recent user feedback and analysis.

[1718] This invention is a system that uses automatic generation AI to conduct interviews with people with specialized knowledge and experience in a specific field (hereinafter referred to as experts), generates and publishes the results as articles, and further improves the quality of content by analyzing user feedback with an emotion engine.

[1719] 1. User Registration / Login

[1720] Hardware: Smartphones, tablets

[1721] Software: Frontend (React Native), Backend (Node.js), Database (MongoDB)

[1722] process:

[1723] A user signs up or logs in.

[1724] The front end provides user input information as a form.

[1725] The user's input information (username, password, email address) is sent to the server.

[1726] The server receives the information and stores it in a database or performs authentication.

[1727] 2. Generate an interview form

[1728] Hardware: Server

[1729] Software: Generative AI model (OpenAI GPT-4), database (MongoDB)

[1730] process:

[1731] The server retrieves the expert's profile information from the database.

[1732] Enter your profile information into the generative AI to generate customized questions.

[1733] The generated questions are reconstructed as an interview form and sent to the expert.

[1734] 3. Receiving and analyzing interview responses

[1735] Hardware: Server

[1736] Software: Frontend (React Native), Backend (Node.js), Sentiment Engine (Sentiment Analysis API)

[1737] process:

[1738] Experts will answer the interview form.

[1739] The response data is sent to the server.

[1740] The server stores the received response data in a database.

[1741] Activate the emotion engine to recognize the emotional state of the person at the time of answering.

[1742] The response data is saved along with the recognition results.

[1743] 4. Article creation and preparation for publication

[1744] Hardware: Server

[1745] Software: Generative AI model (OpenAI GPT-4), database (MongoDB)

[1746] process:

[1747] The server passes the saved response data to the generative AI model.

[1748] Generative AI models create detailed articles.

[1749] Store the article in a database and prepare it for publication.

[1750] 5. Publish the article and analyze the feedback

[1751] Hardware: smartphones, tablets, servers

[1752] Software: Frontend (React Native), Backend (Node.js), Sentiment Engine (Sentiment Analysis API)

[1753] process:

[1754] The server displays the generated articles on the platform.

[1755] Users view articles and provide feedback.

[1756] The feedback data is sent to the server and analyzed by the emotion engine.

[1757] Content improvements are made based on the recognition results.

[1758] Examples:

[1759] Example of system operation

[1760] The server generates interviews with famous chefs in the culinary field.

[1761] Sample questions: "What was the most challenging aspect of developing your latest recipe?", "What was the most important lesson you learned during the cooking process?"

[1762] A user reads an article and provides feedback saying, "This article was very helpful. I'd like to learn more about it."

[1763] Example prompt sentence:

[1764] Prompt to be input to the generated AI:

[1765] “Based on the chef’s profile provided, generate customized questions about his / her recent projects and learnings.”

[1766] Example of generated question:

[1767] "Tell me about your most recent recipe development. What made it particularly challenging?"

[1768] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1769] Step 1:

[1770] A user registers or logs in. Using a smartphone or tablet, the user enters their name, password, and email address. The information is compiled into a form and sent from the device to the server. The server receives it and stores it in a database, or authenticates it in the case of a login. The input data is the username, password, and email address, and the output is approval of the registration or authentication result for the login.

[1771] Step 2:

[1772] The server retrieves the expert's profile information from the database. This profile information is basic data about the expert (such as name, career history, and area of ​​expertise). Input data for the generation AI is constructed based on the retrieved profile information. The generation AI generates customized interview questions based on the given profile information. The input to the generation AI is the profile information, and the output is customized questions.

[1773] Step 3:

[1774] The generated questions are reconstructed as an interview form, which the server sends to the expert. The expert receives the interview form on his / her terminal and enters answers to each question. At this time, the terminal sends the expert's input data to the server, and the sent answer data is temporarily stored in the terminal's memory. The input data are the generated questions and the expert's answers, and the output is the data sent to the server.

[1775] Step 4:

[1776] The server stores the received response data in a database. During this process, the server activates an emotion engine to perform emotion analysis on the response data. The input data to the server is the response data, to which emotion labels are assigned by the emotion engine. The output is the analyzed emotion data and its corresponding label.

[1777] Step 5:

[1778] The server passes the saved response data and emotion labels to the generation AI, which then generates a detailed article. The generation AI uses this information to create specific and detailed article text. The input data to the generation AI are the response data and emotion labels, and the output is the generated article text.

[1779] Step 6:

[1780] The generated article text is stored in a database by the server and displayed on the platform when it is ready to be published. Other users can view the article and provide feedback. Viewers can enter feedback using their smartphones or tablets and send it to the server. The input data is the user feedback, and the output is the feedback data.

[1781] Step 7:

[1782] The server receives the feedback data and analyzes it using an emotion engine. Based on the analysis results, the server improves the content. The input data for feedback is the user's impressions and evaluations, and the output is feedback data with emotion labels. This data is used as a reference for future content generation and improvements.

[1783] 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.

[1784] 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.

[1785] 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.

[1786] 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.

[1787] 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.

[1788] 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.

[1789] 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).

[1790] 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.

[1791] 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."

[1792] 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.

[1793] 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).

[1794] 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.

[1795] 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.

[1796] 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.

[1797] 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.

[1798] 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.

[1799] 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.

[1800] 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.

[1801] 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.

[1802] 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.

[1803] 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.

[1804] The following is further disclosed regarding the above embodiment.

[1805] (Claim 1)

[1806] A method to use automated AI to conduct interviews with people with specialized knowledge and experience in a specific field and generate articles based on the results of those interviews.

[1807] A means for users to register or log in;

[1808] a means for generating an interview form and sending it to the subject;

[1809] A means to use generative AI to write articles based on the interview results and publish those articles;

[1810] A means of collecting user feedback on articles and using it to improve the content;

[1811] A system including:

[1812] (Claim 2)

[1813] The system of claim 1, further comprising a means for generating customized questions by the generation AI based on the profile information of the target person when generating the interview form.

[1814] (Claim 3)

[1815] 10. The system of claim 1, further comprising: means for publishing the generated article so that it can be viewed by other users; and means for storing feedback on the article in a database.

[1816] "Example 1"

[1817] (Claim 1)

[1818] A means for users to register or log in;

[1819] means for transmitting user information to a server using a terminal;

[1820] means for the server to verify the received user information and store it in a database;

[1821] A means for the server to retrieve profile information of the target person from the database and generate customized questions using a generative AI model;

[1822] a means for generating an interview form and sending it to the subject;

[1823] A means for the subject person to answer the interview form and send it to the server using a terminal;

[1824] A means for storing the received response data in a database by the server;

[1825] A means to write up the interview results using a generative AI model and store them in a database;

[1826] a means for publishing the generated article so that it can be viewed by other users;

[1827] a means for collecting user feedback on articles and storing it in a database;

[1828] A system including:

[1829] (Claim 2)

[1830] The system of claim 1, further comprising a means for generating customized questions using an AI model based on profile information of the target person when generating an interview form.

[1831] (Claim 3)

[1832] 2. The system according to claim 1, further comprising means for publishing the generated interview article so that it can be viewed by other users, and means for storing feedback on the article in a database.

[1833] "Application Example 1"

[1834] (Claim 1)

[1835] A method to use automated AI to conduct interviews with people with specialized knowledge and experience in a specific field and generate articles based on the results of those interviews.

[1836] A means for users to register or log in;

[1837] a means for generating an interview form and sending it to the subject;

[1838] A means to use generative AI to write articles based on the interview results and publish those articles;

[1839] A means of collecting user feedback on articles and using it to improve the content;

[1840] a means for enabling other users to view the generated article in the content distribution service;

[1841] A means that can be installed as a smartphone application,

[1842] A system including:

[1843] (Claim 2)

[1844] The system of claim 1, further comprising a means for generating customized questions by the generation AI based on the profile information of the target person when generating the interview form.

[1845] (Claim 3)

[1846] 10. The system of claim 1, further comprising: means for publishing the generated article so that it can be viewed by other users; and means for storing feedback on the article in a database.

[1847] "Example 2: Combining Emotion Engines"

[1848] (Claim 1)

[1849] A method to use automated AI to conduct interviews with people with specialized knowledge and experience in a specific field and generate articles based on the results of those interviews.

[1850] A means for users to register or log in;

[1851] a means for generating an interview form and sending it to the subject;

[1852] A means to use generative AI to write articles based on the interview results and publish those articles;

[1853] A means of collecting user feedback on articles and using it to improve the content;

[1854] means for analyzing the emotional state of the person at the time of the response using an emotion engine;

[1855] means for analyzing the emotional state of the user's feedback using an emotion engine;

[1856] A system including:

[1857] (Claim 2)

[1858] The system of claim 1, further comprising a means for generating customized questions by the generation AI based on the profile information of the target person when generating the interview form.

[1859] (Claim 3)

[1860] 10. The system of claim 1, further comprising: means for publishing the generated article so that it can be viewed by other users; and means for storing feedback on the article in a database.

[1861] "Application example 2 when combining emotion engines"

[1862] (Claim 1)

[1863] A method to use automated AI to conduct interviews with people with specialized knowledge and experience in a specific field and generate articles based on the results of those interviews.

[1864] A means for users to register or log in;

[1865] a means for generating an interview form and sending it to the subject;

[1866] A means to use generative AI to write articles based on the interview results and publish those articles;

[1867] A means of collecting user feedback on articles and using it to improve the content;

[1868] A means for analyzing the feedback data with an emotion engine and improving the content based on user emotions;

[1869] A system including:

[1870] (Claim 2)

[1871] The system of claim 1, further comprising a means for generating customized questions by the generation AI based on the profile information of the target person when generating the interview form.

[1872] (Claim 3)

[1873] 2. The system of claim 1, further comprising: means for publishing the generated article and making it viewable by other users; means for storing feedback on the article in a database; and means for analyzing the feedback data with an emotion engine. [Explanation of symbols]

[1874] 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 method to use automated AI to conduct interviews with people with specialized knowledge and experience in a specific field and generate articles based on the results of those interviews. A means for users to register or log in; a means for generating an interview form and sending it to the subject; A means to use generative AI to write articles based on the interview results and publish those articles; A means of collecting user feedback on articles and using it to improve the content; A system including:

2. The system according to claim 1, further comprising a means for generating customized questions by the generation AI based on the profile information of the target person when generating the interview form.

3. 2. The system of claim 1, further comprising: means for publishing the generated article so that it can be viewed by other users; and means for storing feedback on the article in a database.

Images