System

Abstract

A system is provided.SOLUTION: A system comprising: means for utilizing a generative artificial intelligence model to generate program code based on prompts input by a user; means for returning code suggestions for the input prompts to the user; means for receiving feedback from the user and again generating program code with the generative artificial intelligence model based on the feedback; means for returning the generated improved program code to the user; and means for managing the progress of the project.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Traditional program development has limitations in providing an efficient and creative development experience. In particular, developers often use multiple tools and resources to generate code and solve problems, which hinders efficiency. Furthermore, limited means of receiving appropriate feedback on problems and challenges encountered during the development process often delays project progress. The present invention aims to solve these issues and provide users with an efficient and creative development experience. [Means for solving the problem]

[0005] The present invention provides a system for generating program code using a generative artificial intelligence model based on prompts entered by a user. The system includes a means for returning code suggestions to the user in response to the entered prompts and receiving feedback from the user. The system further includes a function for regenerating program code using the generative artificial intelligence model based on the feedback and returning the generated improved program code to the user. The system also includes a means for managing project progress, registering resources required by a user when creating a new project in a database, and notifying the user when project creation is complete. The system also includes a function for creating and authenticating a user account, verifying the entered authentication information in a database, and generating a session token upon success. In this way, users can progress their projects while interacting with AI, thereby demonstrating greater productivity and creativity.

[0006] "User" refers to an individual or organization that develops programs using the Aibou AI system.

[0007] A "prompt" refers to the development objectives or problem story entered by the user, and is the input information passed to the generative artificial intelligence model.

[0008] A "generative artificial intelligence model" is an AI technology that generates appropriate code or solutions based on prompts entered by the user.

[0009] "Program code" refers to source code or machine code that constitutes part or all of a computer program.

[0010] "Proposal" refers to presenting to the user the program code or solution generated by the generative artificial intelligence model.

[0011] "Feedback" refers to the evaluations and opinions that users give regarding proposed program code.

[0012] A "project" is a unit of work that brings together a series of development tasks to achieve a specific purpose.

[0013] "Progress management" refers to activities to monitor the progress of a project and support the progress of tasks and problem solving.

[0014] A "database" is a system for organizing and efficiently managing data used within a system.

[0015] A "session token" is a unique identification code that is generated when a user's authentication information is verified and authentication is successful. [Brief explanation of the drawings]

[0016] [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

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] 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).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] The present invention is a system that generates program code by utilizing a generative artificial intelligence model based on prompts entered by a user. Specific embodiments of the "Aibou AI" system are described below.

[0038] User Registration and Authentication

[0039] First, a user creates an account to use the system. At this time, the user enters authentication information such as an email address and password. The device sends this information to the server. The server stores the entered information in a database and sends a confirmation email to the user. When the user clicks the link in the confirmation email, the account is activated. The user can log in to the platform by entering their authentication information on the login screen and receiving a session token.

[0040] Creating a Project

[0041] After logging in, the user can create a new project. When the user presses the "Create a new project" button, the device notifies the server of the operation. The server generates an ID for the new project and registers it in the database. When the project creation is complete, the user is notified.

[0042] Inputting development objectives and problem stories

[0043] Next, the user enters the development objectives and problem story on the project details page. This information is sent from the device to the server, which passes it on to the generative AI model, which then generates the appropriate program code based on the prompts.

[0044] AI-powered suggestions and feedback

[0045] The program code generated by the generative AI model is proposed to the user by the server. The user can review the proposed code and enter feedback. This feedback may include improvements to the code or features they would like to add. The device sends this feedback to the server, which then instructs the generative AI model to prompt again. The generative AI model then generates new code, which is proposed again. By repeating this process, the user can obtain high-quality program code.

[0046] Project progress management

[0047] Users can manage the progress of projects and input task progress and new assignments. The device sends this information to the server, which records the progress in a database. Users can also pose questions about specific problems, which the server sends to the generative AI model. The answers from the generative AI are sent back to the user and used as a reference for moving on to the next task.

[0048] Specific examples

[0049] For example, suppose a user inputs a problem story such as "I want to implement a new user authentication system." This information is sent to the server, and a basic user authentication code is generated by the generative AI model. The user checks this code and provides feedback on "strengthening security." Based on this feedback, the server uses the generative AI model to generate a new code with appropriate security features and send it back to the user. In this way, the process of implementing a high-quality program through dialogue between the user and AI is repeated.

[0050] The system allows users to efficiently and creatively progress projects, achieving high productivity and high-quality results in the development of computer programs.

[0051] The processing flow will be explained below.

[0052] User Registration and Authentication

[0053] Step 1:

[0054] The user launches the app and enters their email address and password on the account creation screen.

[0055] Step 2:

[0056] The terminal transmits the input information to the server.

[0057] Step 3:

[0058] The server stores the received information in a database and sends a confirmation email to the user's email address.

[0059] Step 4:

[0060] The user receives a confirmation email and clicks the link in the email to activate their account.

[0061] Step 5:

[0062] The user enters their email address and password on the login screen and clicks the login button.

[0063] Step 6:

[0064] The terminal sends the input information to the server.

[0065] Step 7:

[0066] The server checks the entered authentication information against a database, and if it matches, it generates a session token and returns it to the terminal.

[0067] Step 8:

[0068] The user receives a session token and successfully logs in.

[0069] Creating a Project

[0070] Step 1:

[0071] The user presses the "Create a new project" button within the app.

[0072] Step 2:

[0073] The terminal notifies the server of this operation.

[0074] Step 3:

[0075] The server generates an ID for the new project and registers the project in the database.

[0076] Step 4:

[0077] The server will return a notification of project creation completion and a new project ID to the device.

[0078] Step 5:

[0079] The user will receive a new project ID and the project creation will be complete.

[0080] Inputting development objectives and problem stories

[0081] Step 1:

[0082] The user enters a task story such as "Implementation of a user authentication system" on the project details screen.

[0083] Step 2:

[0084] The device sends the input to the server.

[0085] Step 3:

[0086] The server receives the challenge story and sends it as an input prompt to the generative artificial intelligence model.

[0087] AI-powered suggestions and feedback

[0088] Step 1:

[0089] The server uses a generative artificial intelligence model to generate appropriate code based on the problem story and suggests it to the user.

[0090] Step 2:

[0091] The user reviews the proposed code.

[0092] Step 3:

[0093] The user enters feedback about the code and presses the submit button.

[0094] Step 4:

[0095] The device sends the feedback content to the server.

[0096] Step 5:

[0097] The server receives the feedback and prompts the generative artificial intelligence model again to generate new code.

[0098] Step 6:

[0099] The server sends the improved code back to the user.

[0100] Project progress management

[0101] Step 1:

[0102] Users update task progress within the app, entering progress and new assignments.

[0103] Step 2:

[0104] The device sends the input to the server.

[0105] Step 3:

[0106] The server records the progress in a database.

[0107] Step 4:

[0108] The user types in a question about a specific issue and hits the submit button.

[0109] Step 5:

[0110] The device sends the question to the server.

[0111] Step 6:

[0112] The server sends the question to a generative artificial intelligence model, which generates an answer.

[0113] Step 7:

[0114] The server sends the AI's answer back to the user.

[0115] Step 8:

[0116] The user receives the answer and proceeds to the next task.

[0117] Example: Implementing a user authentication system

[0118] Step 1:

[0119] A user enters a problem story stating, "I want to implement a new user authentication system."

[0120] Step 2:

[0121] The device sends input to the server.

[0122] Step 3:

[0123] The server sends the problem story to the generative artificial intelligence model.

[0124] Step 4:

[0125] The server uses a generative artificial intelligence model to generate a basic user authentication code.

[0126] Step 5:

[0127] The user reviews the proposed code.

[0128] Step 6:

[0129] Users provide feedback on "strengthened security."

[0130] Step 7:

[0131] The device sends the feedback content to the server.

[0132] Step 8:

[0133] The server regenerates the code using a generative artificial intelligence model based on the feedback.

[0134] Step 9:

[0135] The server sends the improved code back to the user.

[0136] Step 10:

[0137] The user reviews the proposed code and proceeds to implementation.

[0138] Example 1

[0139] 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."

[0140] In conventional program code generation systems, when users provide feedback on generated code, the feedback is not reflected promptly, reducing the efficiency of generating high-quality programs. Additionally, creating new projects and managing projects requires a lot of effort, reducing productivity. Furthermore, when users have questions about specific technical issues, there are limited ways to receive quick and accurate answers, which can delay project progress.

[0141] 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.

[0142] In this invention, the server includes: means for generating program code using a generative artificial intelligence model based on prompts entered by a user; means for returning code suggestions for the entered prompts to the user; means for receiving feedback from the user and regenerating program code using the generative artificial intelligence model based on the feedback; means for returning the generated improved program code to the user; means for managing project progress; means for allowing the user to input project progress and new challenges; means for recording the input information in a database; means for the user to enter questions about specific problems and send them to the generative artificial intelligence model; means for providing the user with answers from the generative artificial intelligence model; means for the user to create and authenticate an account; means for verifying the entered authentication information in the database and generating a security token if successful; and means for notifying the user of authentication completion. This enables fast and efficient program code generation and feedback integration, simplifies project management, and provides fast and accurate answers to specific technical problems.

[0143] "User" means an individual or organization that uses the system to generate program code or manage projects.

[0144] A "prompt" is an instruction or question that a user enters into a generative artificial intelligence model, which then generates code based on that information.

[0145] "Generative artificial intelligence model" refers to an artificial intelligence technique that generates program code based on given prompts.

[0146] "Program Code" means the executable scripts or snippets of software that a generative artificial intelligence model generates based on prompts.

[0147] "Feedback" refers to requests for corrections or suggestions for improvements made by users to the generated program code.

[0148] A "security token" is a secure credential used by an authenticated user during a session to secure access rights.

[0149] A "project" is an individual development task or goal that a user creates within the system and manages its progress.

[0150] "Database" means a digital record system for storing and managing user information, project information, feedback, etc. within the system.

[0151] "Server" refers to a central computing device or service that processes user requests, generates code using generative artificial intelligence models, and performs database operations.

[0152] "Authentication information" refers to information such as an email address and password that a user uses to log in to a system.

[0153] A "session token" is a unique string used to identify a session, issued after a user has been successfully authenticated.

[0154] A "question" is a specific technical problem or question that a user enters into the system to receive an answer from the generative artificial intelligence model.

[0155] The present invention is a system that generates program code using a generative artificial intelligence model based on prompts entered by a user. This system operates through the mutual cooperation of a server, a terminal, and a user.

[0156] User Registration and Authentication

[0157] First, a user creates an account to use the system. The user enters their email address and password, which the device sends to the server. The server saves the entered information in a database and automatically sends a confirmation email to the user. When the user clicks the link in the confirmation email, the server activates the account. The user enters their email address and password on the login screen, and if the server successfully authenticates them, it issues a session token.

[0158] Creating a Project

[0159] After logging in, the user presses the "Create a new project" button, and the device notifies the server of the operation. The server generates an ID for the new project and registers it in the database. Once the project creation is complete, the server notifies the user.

[0160] Inputting development objectives and problem stories

[0161] The user enters the development objectives and problem story on the project details page. The device sends this information to the server, which passes it to the generative AI model. The generative AI model generates the appropriate program code based on the prompts.

[0162] AI-powered suggestions and feedback

[0163] The program code generated by the generative AI model is proposed to the user by the server. The user reviews the proposed code and enters feedback on areas for improvement or features they would like to add. The device then sends this feedback to the server, which then instructs the generative AI model to reprompt again. By repeating this process, the user obtains high-quality program code.

[0164] Project progress management

[0165] Users input the progress of tasks and new challenges within a project. The device sends this information to the server, which records it in a database. Users can also input questions about specific problems, which the device sends to the server, which passes them on to the generative AI model. The server provides the answer from the generative AI model to the user, and uses it as a reference for the next task.

[0166] Specific examples

[0167] For example, suppose a user inputs a problem story such as "I want to implement a new user authentication system." This information is sent to the server, and a basic user authentication code is generated by a generative artificial intelligence model. The user reviews this code and provides feedback such as "strengthen security." Based on this feedback, the server uses the generative artificial intelligence model again to generate code with appropriate security functions. This process is repeated until a high-quality program is implemented through dialogue between the user and AI.

[0168] An example of a prompt to be input to the generative AI model is "Please implement a user authentication system using JWT in Ruby on Rails." Users can review the program code generated based on this prompt and provide feedback to obtain higher quality code.

[0169] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0170] Step 1: User enters account information

[0171] The user enters their email address and password on the system's account creation screen. The entered authentication information is sent to the server by the terminal. The server stores the received authentication information in a database and automatically sends a confirmation email. Data verification is performed to ensure that the email address has been entered correctly, and the confirmation email is sent.

[0172] Input: Email address, password

[0173] Output: Send confirmation email, save information to database

[0174] Step 2: User clicks on the link in the confirmation email

[0175] The user clicks on the link in the confirmation email they receive, which triggers a process on the server to activate the account and update the user's status in the database.

[0176] Input: Click on the link in the confirmation email

[0177] Output: Account activated, database updated

[0178] Step 3: User enters login information

[0179] The user enters their email address and password on the login screen. The information is sent by the device to the server, which checks it against the authentication information in its database. If there is a match, the server issues a session token and sends it back to the user.

[0180] Input: Email address, password

[0181] Output: Session token issued, user authenticated

[0182] Step 4: User creates a new project

[0183] The user presses the "Create a new project" button on the project creation screen. The device notifies the server of this operation, and the server generates an ID for the new project and registers it in the database. The user is notified that the project has been created.

[0184] Input: Project creation operation

[0185] Output: Project ID generation, project registration in the database, and notification of completion

[0186] Step 5: User enters project details

[0187] The user enters the development objectives and problem story on the project details page. The data is sent to the server by the terminal, and the server passes it to the generative AI model. The generative AI model generates program code based on the prompts.

[0188] Input: Issue story, development objectives

[0189] Output: Sending prompts to a generative artificial intelligence model, generating program code

[0190] Step 6: The server presents the generated code to the user

[0191] The server proposes program code generated by the generative artificial intelligence model to the user, who then reviews the code and provides feedback.

[0192] Input: Program code generated by a generative artificial intelligence model

[0193] Output: Code suggestions to user, waiting for feedback

[0194] Step 7: Users submit feedback

[0195] Users review the proposed program code and provide feedback on improvements and additional features from their devices to the server, which then passes this feedback back to the generative artificial intelligence model as prompts.

[0196] Input: Feedback

[0197] Output: Reprompt for generative artificial intelligence models

[0198] Step 8: The server generates and suggests improved code

[0199] The generative artificial intelligence model generates improved program code based on the new feedback, which the server then proposes to the user again, and this process is repeated until the user is satisfied.

[0200] Input: Improved code generation using generative artificial intelligence models

[0201] Output: Suggested code improvements to the user

[0202] Step 9: Let users manage project progress

[0203] Users enter task progress and new issues on the project management screen, and the information is sent from the device to the server, which records this information in a database.

[0204] Input: Task progress, new assignments

[0205] Output: Record information in a database

[0206] Step 10: User enters question about specific technical issue

[0207] Users enter questions about specific technical issues and send them from their devices to a server, which passes the questions to a generative artificial intelligence model to obtain answers, which the server then provides to the user.

[0208] Input: Technical question

[0209] Output: Answer from the generative artificial intelligence model, providing the answer to the user

[0210] Through the above processing steps, the system can provide users with efficient program generation and project management.

[0211] (Application example 1)

[0212] 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."

[0213] Automation and efficiency are key challenges in modern factories. In particular, the operating programs for robots and other machines operating in factories are often highly complex and require specialized engineers, resulting in significant time and cost. Furthermore, improving and adapting existing programs is not easy, and the process of incorporating feedback is cumbersome. Given these circumstances, a system is needed to quickly and efficiently generate and improve the operating programs for machines in factories.

[0214] 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.

[0215] In this invention, the server includes means for generating program code using a generative artificial intelligence model based on prompts input by a user, means for returning code suggestions for the input prompts to the user, means for receiving feedback from the user and generating program code again using the generative artificial intelligence model based on the feedback, means for returning the generated improved program code to the user, means for managing the progress of the project, and means for generating operating programs for machines operating in a factory and improving the operation of the machines, thereby enabling users to easily generate and improve operating programs for machines.

[0216] A "generative artificial intelligence model" is a type of artificial intelligence algorithm that can generate new data or program code based on input data.

[0217] A "prompt" is a sentence or piece of text that indicates an instruction or request that the user enters.

[0218] "Program code" refers to a set of instructions for controlling machine operations, such as a computer-executable binary file or script.

[0219] "Feedback" refers to opinions and requests for improvement from users regarding the generated program code.

[0220] "Factory machinery" refers to robots and other automated devices used to perform production lines and automated tasks.

[0221] A "session token" is a temporary identifier used to keep a user authenticated to a system.

[0222] A "database" is a system that efficiently stores large amounts of data and enables it to be searched and processed.

[0223] "Project management" refers to the overall process of planning, executing, and monitoring work to achieve project goals.

[0224] This invention is a system for efficiently generating and improving the operating programs of machines operating in a factory. This system mainly uses a server, a terminal (smartphone), and a generative artificial intelligence model.

[0225] composition

[0226] Hardware

[0227] Device: iOS or Android smartphone.

[0228] Server: Cloud-based server.

[0229] Factory machinery: Robots and other automated equipment.

[0230] software

[0231] Front-end: Smartphone application using React Native.

[0232] Backend: Server-side application using Node.js.

[0233] Database: MongoDB.

[0234] Generative artificial intelligence model: OpenAI GPT-3.

[0235] Authentication: Firebase Authentication.

[0236] Processing flow

[0237] 1. User Registration and Authentication:

[0238] The user enters their email address and password using a terminal. This information is authenticated using Firebase Authentication, and if authentication is successful, the user information is stored in MongoDB. If successful, a session token is generated and the user is notified that authentication has been completed.

[0239] 2. Create a project:

[0240] A user presses the "Create a new project" button to create a new project. This operation is notified to the Node.js server, which generates a new project ID and registers it in MongoDB. The user is notified that the project creation is complete.

[0241] 3. Enter the assignment story:

[0242] Users enter their assignment story on the project details page, and this information is sent from the device to the server, which then sends prompts to the generative artificial intelligence model (GPT-3).

[0243] 4. AI Code Generation:

[0244] GPT-3 generates program code based on the prompts entered, and the code is sent back to the user via a server.

[0245] 5. Feedback and Improvements:

[0246] The user reviews the proposed code and provides feedback, which is then sent back to GPT-3 via the server, which generates a new code and sends the improved code back to the user.

[0247] 6. Project Progress Management:

[0248] Users can manage the progress of their projects, input task progress and new challenges, and store this information on the server. Users can also pose questions about specific problems and receive answers from GPT-3.

[0249] This system allows users to efficiently generate and improve operating programs for machines operating in factories. For example, if a user inputs, "I want to implement a robot operation that places part A in a specified position," GPT-3 generates program code based on that. Furthermore, if the user inputs feedback such as, "To improve position accuracy, we need a function to adjust using sensor input," GPT-3 generates improved code based on this feedback.

[0250] Example prompt sentence:

[0251] Generate code like this: "I want to implement a robot that places part A in a predetermined position. I need to adjust the position using sensor input to improve accuracy."

[0252] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0253] Step 1:

[0254] The user creates an account and enters authentication information. The device sends this information (email address, password) to the server. The server verifies this information using Firebase Authentication and generates a session token if authentication is successful. Next, a notification that authentication is complete is sent. The input is the user's authentication information, and the output is a session token and a notification that authentication is complete.

[0255] Step 2:

[0256] The user presses the "Create a new project" button. This operation is notified to the server from the terminal. The server generates a new project ID and registers this project ID and related information in MongoDB. When the project creation is complete, the terminal is notified. The input is a project creation request, and the output is the new project ID and its notification.

[0257] Step 3:

[0258] The user goes to the project details page and inputs the problem story (for example, "I want to implement a robot behavior that places part A in a designated position"). The device sends this input to the server. The server then sends this prompt to the API of the generative artificial intelligence model (GPT-3). The input is the problem story, and the output is the prompt for generation.

[0259] Step 4:

[0260] The server receives the program code generated by GPT-3. Then, it sends this code to the terminal, and the user confirms this code. Here, the input is the program code generated by GPT-3, and the output is the code suggested to the user.

[0261] Step 5:

[0262] The user checks the code and enters feedback (e.g., "To improve location accuracy, we need the ability to adjust using sensor inputs"). The device sends this feedback to the server, which then sends a new prompt to GPT-3, including this feedback. The input is the user's feedback, and the output is the improved prompt.

[0263] Step 6:

[0264] The server receives the newly generated improved program code from GPT-3 and sends it to the device. The user can review this code again and provide further feedback if necessary. This process is repeated. The input is the improved code generated by GPT-3, and the output is the improved code suggested to the user.

[0265] Step 7:

[0266] Users manage the progress of their projects and, if new issues arise, enter them into the system. The device sends this information to the server and stores it in MongoDB. The input is new issues and progress updates, and the output is updated progress data.

[0267] 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.

[0268] The present invention is a system that utilizes a generative artificial intelligence model to generate program code based on user prompts. It also includes a means for improving the code by incorporating user feedback and managing the progress of the project. It also combines an emotion engine that recognizes the user's emotions to provide support tailored to the user's emotions.

[0269] User Registration and Authentication

[0270] First, the user launches the app and enters their email address and password on the account creation screen. The device sends this information to the server, which stores it in a database. A confirmation email is sent to the user, and the user clicks on a link to activate their account. The user enters their login information and receives a session token, logging them into the platform.

[0271] Creating a Project

[0272] After logging in, a user can create a new project by pressing the "Create a new project" button in the app. The device notifies the server of this operation, and the server generates a new project ID and registers it in the database. Once the project creation is complete, the user is notified and provided with the new project ID.

[0273] Inputting development objectives and problem stories

[0274] The user enters the development objectives and problem story on the project details page. This information is sent from the device to the server, which passes it to the generative AI model. The generative AI model generates the appropriate program code based on the prompts.

[0275] AI-powered suggestions and feedback

[0276] The program code generated by the page-generating AI model is proposed to the user by the server. The user reviews the proposed code, enters feedback, and submits it. The device sends this to the server, which then sends the feedback back to the generative AI model to generate new code. This code is then sent back to the user, who can review it for improvements.

[0277] Project progress management

[0278] Users manage the progress of their projects, inputting task progress and new assignments. The device sends this information to a server, which records the progress in a database. Users ask questions about specific problems, and the server sends the questions to a generative artificial intelligence model to generate answers. The answers are sent back to the user and used as a reference for moving on to the next task.

[0279] Supported by an emotional engine

[0280] Furthermore, the emotion engine recognizes the user's emotions based on the prompts and feedback they provide. The emotion engine records the user's emotional data and uses this data to improve project progress management and generative AI model suggestions. Specifically, if the user is feeling stressed, the system will provide more step-by-step advice.

[0281] Specific examples

[0282] For example, suppose a user inputs a problem story such as "I want to implement a new user authentication system." This information is sent to the server, and a generative AI model generates a basic user authentication code. The user reviews the code and provides feedback on "strengthening security." The server then uses the generative AI model to generate a new code based on the feedback, and sends the improved code back to the user. Furthermore, the emotion engine detects the user's stress level, and the system can provide more detailed explanations and additional documentation, allowing development to proceed while reducing the user's stress.

[0283] In this way, the system of the present invention allows users to progress projects efficiently and creatively, and achieve high-quality results through project progress management and emotional support.

[0284] The processing flow will be explained below.

[0285] User Registration and Authentication

[0286] Step 1:

[0287] The user launches the app and enters their email address and password on the account creation screen.

[0288] Step 2:

[0289] The terminal transmits the input information to the server.

[0290] Step 3:

[0291] The server stores the received information in a database and sends a confirmation email to the user's email address.

[0292] Step 4:

[0293] The user receives a confirmation email and clicks the link in the email to activate their account.

[0294] Step 5:

[0295] The user enters their email address and password on the login screen and clicks the login button.

[0296] Step 6:

[0297] The terminal sends the input information to the server.

[0298] Step 7:

[0299] The server checks the entered authentication information against a database, and if it matches, it generates a session token and returns it to the terminal.

[0300] Step 8:

[0301] The user receives a session token and successfully logs in.

[0302] Creating a Project

[0303] Step 1:

[0304] The user presses the "Create a new project" button within the app.

[0305] Step 2:

[0306] The terminal notifies the server of this operation.

[0307] Step 3:

[0308] The server generates an ID for the new project and registers the project in the database.

[0309] Step 4:

[0310] The server will return a notification of project creation completion and a new project ID to the device.

[0311] Step 5:

[0312] The user will receive a new project ID and the project creation will be complete.

[0313] Inputting development objectives and problem stories

[0314] Step 1:

[0315] The user enters a task story such as "Implementation of a user authentication system" on the project details screen.

[0316] Step 2:

[0317] The device sends the input to the server.

[0318] Step 3:

[0319] The server receives the challenge story and sends it as an input prompt to the generative artificial intelligence model.

[0320] AI-powered suggestions and feedback

[0321] Step 1:

[0322] The server uses a generative artificial intelligence model to generate appropriate code based on the problem story.

[0323] Step 2:

[0324] The server presents the generated code to the user.

[0325] Step 3:

[0326] The user reviews the proposed code.

[0327] Step 4:

[0328] The user enters feedback about the code and presses the submit button.

[0329] Step 5:

[0330] The device sends the feedback content to the server.

[0331] Step 6:

[0332] The server receives the feedback and uses a generative artificial intelligence model to prompt again and generate a new code.

[0333] Step 7:

[0334] The server sends the improved code back to the user.

[0335] Project progress management

[0336] Step 1:

[0337] Users update task progress within the app, entering progress and new assignments.

[0338] Step 2:

[0339] The device sends the input to the server.

[0340] Step 3:

[0341] The server records the progress in a database.

[0342] Step 4:

[0343] The user types in a question about a specific issue and hits the submit button.

[0344] Step 5:

[0345] The device sends the question to the server.

[0346] Step 6:

[0347] The server sends the question to a generative artificial intelligence model, which generates an answer.

[0348] Step 7:

[0349] The server sends the answer from the generative artificial intelligence model back to the user.

[0350] Step 8:

[0351] The user receives the answer and proceeds to the next task.

[0352] Supported by an emotional engine

[0353] Step 1:

[0354] When users enter prompts or feedback, the emotion engine analyzes their facial expressions, tone of voice, and other factors to recognize their emotions.

[0355] Step 2:

[0356] The device transmits the recognized emotion data to the server.

[0357] Step 3:

[0358] The server receives the emotional data and records the user's emotional state.

[0359] Step 4:

[0360] The server sends the emotional data as feedback to the generative artificial intelligence model, which then adjusts the content of the proposed code.

[0361] Step 5:

[0362] The server suggests tailored codes and messages to the user.

[0363] Step 6:

[0364] The user reviews the system's suggestions and provides feedback again if they do not like them.

[0365] Example: Implementing a user authentication system

[0366] Step 1:

[0367] A user enters a problem story stating, "I want to implement a new user authentication system."

[0368] Step 2:

[0369] The device sends input to the server.

[0370] Step 3:

[0371] The server sends the problem story to the generative artificial intelligence model.

[0372] Step 4:

[0373] The server uses a generative artificial intelligence model to generate a basic user authentication code.

[0374] Step 5:

[0375] The user reviews the proposed code.

[0376] Step 6:

[0377] Users provide feedback on "strengthened security."

[0378] Step 7:

[0379] The device sends the feedback content to the server.

[0380] Step 8:

[0381] The server regenerates the code using a generative artificial intelligence model based on the feedback.

[0382] Step 9:

[0383] The server sends the improved code back to the user.

[0384] Step 10:

[0385] The user reviews the proposed code and proceeds to implementation.

[0386] Step 11:

[0387] The server uses an emotion engine to monitor the user's stress level.

[0388] Step 12:

[0389] If the emotion engine recognizes a user's stress level as high, the server instructs the generative artificial intelligence model to provide a more detailed explanation or additional supporting information.

[0390] Step 13:

[0391] The user receives detailed explanations and additional support information, then reviews and implements the code again.

[0392] Example 2

[0393] 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."

[0394] Previous code generation systems focused on generating code based on user prompts and improving it through feedback, but lacked support that took into account the user's emotional state. This resulted in insufficient support when users faced stressful situations or difficult tasks, which could stall project progress. Furthermore, there were limited ways for users to efficiently manage project progress and tasks.

[0395] 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.

[0396] In this invention, the server includes means for generating program code using a generative artificial intelligence model based on prompts entered by the user, means for returning code suggestions for the entered prompts to the user, means for receiving feedback from the user and regenerating program code using the generative artificial intelligence model based on the feedback, means for returning the generated improved program code to the user, means for managing the progress of the project, means for recognizing the user's emotions based on the prompts and feedback entered by the user, and means for adjusting the suggestions and support content of the generative artificial intelligence model based on the emotions, thereby enabling the user to progress through the project efficiently and comfortably.

[0397] A "prompt" is an instruction that a user inputs to a generative artificial intelligence model.

[0398] A "generative artificial intelligence model" is an algorithm or system that generates program code based on user prompts.

[0399] "Program code" means text that contains instructions that a computer can execute.

[0400] "Feedback" means evaluations and requests for corrections made by users to the generated program code.

[0401] "Project progress management" refers to the means and methods for managing the progress and tasks of a project and for moving the project forward efficiently.

[0402] "Emotion recognizer" refers to a system or algorithm that recognizes a user's emotions or stress state based on user input and feedback.

[0403] "Means for adjusting support content" refers to means or methods for taking the user's feelings into consideration and providing appropriate support and supplementary information.

[0404] To implement the present invention, the user, the terminal, and the server must work together. Specific hardware and software for each step will be described in order.

[0405] First, when a user launches the application, they use a device such as a smartphone or PC. The user enters their email address and password on the account creation screen, and the device sends this information to the server. The server stores the received information in a database and sends a confirmation email to the user. The user activates their account by clicking the link in the confirmation email.

[0406] Next, the user enters their email address and password on the login screen, and the device sends the login information to the server. The server verifies the information and, if valid, issues a session token and sends it to the user. The user receives the session token and can log in to the platform.

[0407] After logging in, the user presses the "Create a new project" button, and the device notifies the server of this operation. The server generates a new project ID and saves this information in the database, creating the project. The server then returns the project ID to the user, notifying them that the new project has been created.

[0408] When a user enters the development objectives and problem story on the project details page, the device sends this information to the server, which then passes the received information to a generative artificial intelligence model, which uses powerful data center or cloud-based computing resources to generate the optimal program code for the specified conditions.

[0409] The generated program code is proposed to the user by the server, who then confirms it. If the user provides appropriate feedback, the device sends this feedback to the server. The server then passes the feedback back to the generative artificial intelligence model, which then generates new program code. This process is repeated until the user is satisfied.

[0410] The system always takes the user's emotions into consideration, and the emotion engine intervenes when the user is feeling particularly stressed. The emotion engine analyzes the user's emotions from their input and feedback and provides appropriate support and auxiliary information, allowing the user to proceed with the project more efficiently and comfortably.

[0411] As a concrete example, suppose a user inputs a problem story such as "I want to implement a new user authentication system." This information is sent to the server, and a generative AI model generates a basic user authentication code. The user checks the code and provides feedback on "strengthening security." Based on this feedback, the server uses the generative AI model again to generate an improved code and sends it back to the user. During this process, the emotion engine detects the user's stress, and the system reduces the user's stress by providing detailed explanations and additional documentation.

[0412] Users can also pose questions about specific problems, and the server sends the questions to a generative artificial intelligence model that generates an appropriate answer, which is then sent back to the user to guide them through the next task.

[0413] Thus, the embodiments of the invention allow users to efficiently progress projects and achieve high-quality results, while the support provided by the emotion engine allows users to work more comfortably.

[0414] Examples of prompts include:

[0415] "I want to implement a new user authentication system."

[0416] "I want a database search function to be added."

[0417] "I want the user interface design to be modern."

[0418] The above is a specific embodiment of the present invention.

[0419] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0420] Step 1:

[0421] Create an account

[0422] The user launches the application and enters their email address and password on the account creation screen. The device sends this information to the server. The server stores the received information in a database and sends a confirmation email to the user. The user clicks on the link in the confirmation email to activate their account.

[0423] Input: User's email address, password

[0424] Data processing / calculation: The server stores the information in a database and sends it by email.

[0425] Output: Confirmation email, account activation

[0426] Step 2:

[0427] Log in

[0428] The user enters their email address and password on the login screen. The device sends this information to the server. The server verifies the information and, if valid, issues a session token and sends it to the user. The user receives the session token and logs in to the platform.

[0429] Input: User's email address, password

[0430] Data processing / calculation: Server checks information and generates session token

[0431] Output: Session token, login successful

[0432] Step 3:

[0433] Creating a new project

[0434] After logging in, the user presses the "Create a new project" button. The device notifies the server of this action. The server generates a new project ID and saves it in the database. The server then returns the project ID to the user, notifying them that a new project has been created.

[0435] Input: User clicks Create button

[0436] Data processing / calculation: The server generates a project ID and saves it in the database

[0437] Output: New project ID, project created notification

[0438] Step 4:

[0439] Entering Project Details

[0440] The user enters the development objectives and problem story on the project details page. The device sends this information to the server. The server passes the received information to a generative artificial intelligence model, which uses computing resources to generate program code.

[0441] Input: Development objectives, problem story

[0442] Data processing / calculation: The server passes the information to the generative artificial intelligence model, generating code.

[0443] Output: Generated program code

[0444] Step 5:

[0445] Code Generation and Suggestions

[0446] A generative artificial intelligence model generates program code based on the input prompts, and the server suggests the generated code to the user.

[0447] Input: Program code from a generative artificial intelligence model

[0448] Data processing / calculation: The server transmits the code to the user

[0449] Output: User-suggested program code

[0450] Step 6:

[0451] Feedback and Improvements

[0452] The user reviews the proposed code and enters feedback. The device sends the feedback to the server. The server resubmits the feedback to the generative AI model, which generates new program code. The server then sends the improved code back to the user.

[0453] Input: User feedback

[0454] Data processing / calculation: The server passes the feedback to the generative AI model, and then regenerates it.

[0455] Output: Improved program code

[0456] Step 7:

[0457] Task progress management

[0458] The user manages the progress of the project, inputting task progress and new issues. The device sends the input information to the server, which records the progress in a database.

[0459] Input: Task progress information, new assignments

[0460] Data processing / calculation: The server records the progress in the database

[0461] Output: Updated progress data

[0462] Step 8:

[0463] Questions and Answers

[0464] The user poses a question about a specific problem. The device sends this question to a server. The server sends the question to a generative artificial intelligence model, which generates an answer. The server sends the generated answer to the user.

[0465] Input: User question

[0466] Data processing / calculation: The server sends the question to the generative AI model, which generates the answer.

[0467] Output: The answer provided to the user

[0468] Step 9:

[0469] Emotion assessment and response

[0470] The emotion engine recognizes emotions based on user input and feedback, and the server records the emotion data and uses it to tailor the generative AI model's suggestions and support.

[0471] Input: User input, feedback

[0472] Data processing / calculation: The emotion engine evaluates emotions, and the server records the emotion data.

[0473] Output: Tailored support and feedback

[0474] (Application example 2)

[0475] 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."

[0476] While conventional program code generation systems using generative artificial intelligence models can generate and improve code based on user prompts, they lack a means to recognize user emotions and provide support accordingly, making it difficult to efficiently progress projects while reducing user stress. Furthermore, there are insufficient means for managing project progress in real time and incorporating feedback. To solve these problems, a system with support and real-time management capabilities that respond to user emotions is needed.

[0477] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0478] This invention includes means for generating program code using a generative artificial intelligence model based on prompts entered by a user, means for returning code suggestions for the entered prompts to the user, means for receiving feedback from the user and generating program code again using the generative artificial intelligence model based on the feedback, means for returning the generated improved program code to the user, means for project progress management, means for recognizing user emotion data and adapting project progress management and code suggestions based on the user emotion data, and means for saving the user's task progress in a database and updating the progress status in real time. This allows program code to be generated and improved while taking user emotions into consideration, and makes it possible to more efficiently manage project progress and reflect feedback in real time.

[0479] A "generative artificial intelligence model" is an artificial intelligence technology that generates program code based on prompts entered by the user and optimizes its content.

[0480] A "prompt" is text information that explains the purpose or task the user is entering.

[0481] "Program code" means text that contains instructions necessary for a computer to follow instructions.

[0482] "Feedback" is information indicating the user's evaluation of the generated program code and suggestions for improvement.

[0483] "Emotional data" is emotional information extracted from user input and feedback, and is data that reflects the user's psychological state.

[0484] "Task progress status" is information that indicates the progress of each task in a project.

[0485] A "database" is a system that manages and stores a collection of structured data.

[0486] "Real-time updates" means that input information and processing results are instantly reflected in the system.

[0487] "User" means an individual or organization that uses the system to generate program code or manage projects.

[0488] A "project" is a planned series of tasks or activities designed to achieve a specific purpose.

[0489] The system for implementing this invention allows users to input prompt sentences and generate and improve program code using a generative artificial intelligence model. Specifically, it involves three main elements working together: a server, a terminal, and a user.

[0490] Hardware and Software Configuration

[0491] The server has a generative artificial intelligence model (e.g., OpenAI's GPT-4) and an emotion recognition engine (e.g., Microsoft Azure's Text Analytics) installed. The server receives a prompt from the user, generates program code using the generative artificial intelligence model, and analyzes the user's emotions using the emotion recognition engine.

[0492] The device (smartphone or PC) acts as the user interface. The device sends prompts and feedback entered by the user to the server, and is equipped with an application (for example, a backend built with the Django framework and a frontend built with React) to receive and display the generated program code and emotion recognition results.

[0493] Users operate the device to create projects, enter prompts, provide feedback, and more.

[0494] Data processing and calculation flow

[0495] 1. User Registration and Authentication

[0496] The user enters their email address and password using the terminal application and submits them to the server, which validates the information using Django's user authentication functionality, stores it in a PostgreSQL database, and, if authentication is successful, generates a session token and sends it back to the user.

[0497] 2. Create a project

[0498] When the user clicks the "Create a new project" button, the device notifies the server of this action. The server generates a new project ID and registers it in the database. Once the project creation is complete, the user is notified and provided with the new project ID.

[0499] 3. Entering prompt statements and generating code

[0500] The user enters a prompt on the project details page and sends it to the server, which then passes the prompt to the generative artificial intelligence model to generate program code.

[0501] 4. Suggestions and Feedback

[0502] The generated program code is sent from the server to the terminal and displayed to the user. The user reviews the code and provides feedback. The terminal sends this feedback to the server, which then uses the generative artificial intelligence model to improve the program code.

[0503] 5. Emotional awareness and support

[0504] Emotional data is collected from user feedback and input and analyzed by an emotion recognition engine on the server. Based on the analysis results, if the user's stress level is high, more detailed explanations or additional documentation will be provided.

[0505] Specific examples

[0506] For example, suppose a user enters the prompt, "I want to implement a new quality inspection system." This information is sent to the server, and a generative AI model generates the basic program code for the quality inspection system. The user reviews the code and provides feedback, saying, "I want to improve the inspection accuracy." The server then uses the generative AI model to improve the program code based on the feedback and sends it back to the user. Furthermore, an emotion recognition engine detects the user's level of excitement and provides additional detailed explanations to reduce stress.

[0507] This system allows users to effectively generate and improve program code and efficiently advance projects.

[0508] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0509] Step 1: User Registration and Authentication

[0510] The user enters their email address and password in the terminal application and sends a registration request to the server. The server receives the input and uses Django's user authentication function to store the registration information in a database (PostgreSQL). The server then sends the user a confirmation email, and when the user clicks on the link, the account is activated. When the user enters their login information again, the server authenticates them and, if successful, generates a session token and sends it back to the user.

[0511] Step 2: Create a project

[0512] The user presses the "Create a new project" button in the app, and the device notifies the server of the operation. The server generates a new project ID and registers this information in the database. Once the project creation is complete, the server returns the new project ID to the user and notifies them that the project has been created.

[0513] Step 3: Enter the prompt statement

[0514] The user enters a prompt on the project details page, and the device sends this information to the server. The entered prompt is passed to a generative artificial intelligence model (OpenAI GPT-4). The server inputs the prompt into the AI ​​model and instructs it to generate program code. The generated program code is temporarily stored on the server.

[0515] Step 4: Code suggestions and feedback

[0516] The server sends the generated program code to the terminal, which displays it to the user. The user checks the code and enters feedback if necessary. The feedback is sent from the terminal to the server. The server passes this feedback back to the generative artificial intelligence model, instructing it to generate improved program code.

[0517] Step 5: Submitting the improved code

[0518] The server then sends the improved program code generated by the generative artificial intelligence model back to the device, which then displays the improved program code to the user and repeats the process until feedback is received. With each iteration of the improvement, the server saves the progress record in the database and updates the project's progress.

[0519] Step 6: Emotional awareness and support

[0520] The device sends the feedback and prompts entered by the user to the server, which then uses an emotion recognition engine (Microsoft Azure Text Analytics) to analyze the user's emotional data. Based on the analysis results, if the user's stress level is high, the server generates emotionally appropriate support information (e.g., step-by-step guides or additional documentation) and provides it to the user via the device.

[0521] Step 7: Real-time updates on task progress

[0522] Users operate their devices to input task progress, and the devices send that information to the server, which then stores the task progress in a database and updates it in real time, allowing users to always have the most up-to-date information on the progress of the entire project.

[0523] 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.

[0524] 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.

[0525] 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.

[0526] [Second embodiment]

[0527] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0528] 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.

[0529] 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).

[0530] 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.

[0531] 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.

[0532] 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).

[0533] 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.

[0534] 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.

[0535] 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.

[0536] 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.

[0537] 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.

[0538] 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."

[0539] The present invention is a system that generates program code by utilizing a generative artificial intelligence model based on prompts entered by a user. Specific embodiments of the "Aibou AI" system are described below.

[0540] User Registration and Authentication

[0541] First, a user creates an account to use the system. At this time, the user enters authentication information such as an email address and password. The device sends this information to the server. The server stores the entered information in a database and sends a confirmation email to the user. When the user clicks the link in the confirmation email, the account is activated. The user can log in to the platform by entering their authentication information on the login screen and receiving a session token.

[0542] Creating a Project

[0543] After logging in, the user can create a new project. When the user presses the "Create a new project" button, the device notifies the server of the operation. The server generates an ID for the new project and registers it in the database. When the project creation is complete, the user is notified.

[0544] Inputting development objectives and problem stories

[0545] Next, the user enters the development objectives and problem story on the project details page. This information is sent from the device to the server, which passes it on to the generative AI model, which then generates the appropriate program code based on the prompts.

[0546] AI-powered suggestions and feedback

[0547] The program code generated by the generative AI model is proposed to the user by the server. The user can review the proposed code and enter feedback. This feedback may include improvements to the code or features they would like to add. The device sends this feedback to the server, which then instructs the generative AI model to prompt again. The generative AI model then generates new code, which is proposed again. By repeating this process, the user can obtain high-quality program code.

[0548] Project progress management

[0549] Users can manage the progress of projects and input task progress and new assignments. The device sends this information to the server, which records the progress in a database. Users can also pose questions about specific problems, which the server sends to the generative AI model. The answers from the generative AI are sent back to the user and used as a reference for moving on to the next task.

[0550] Specific examples

[0551] For example, suppose a user inputs a problem story such as "I want to implement a new user authentication system." This information is sent to the server, and a basic user authentication code is generated by the generative AI model. The user checks this code and provides feedback on "strengthening security." Based on this feedback, the server uses the generative AI model to generate a new code with appropriate security features and send it back to the user. In this way, the process of implementing a high-quality program through dialogue between the user and AI is repeated.

[0552] The system allows users to efficiently and creatively progress projects, achieving high productivity and high-quality results in the development of computer programs.

[0553] The processing flow will be explained below.

[0554] User Registration and Authentication

[0555] Step 1:

[0556] The user launches the app and enters their email address and password on the account creation screen.

[0557] Step 2:

[0558] The terminal transmits the input information to the server.

[0559] Step 3:

[0560] The server stores the received information in a database and sends a confirmation email to the user's email address.

[0561] Step 4:

[0562] The user receives a confirmation email and clicks the link in the email to activate their account.

[0563] Step 5:

[0564] The user enters their email address and password on the login screen and clicks the login button.

[0565] Step 6:

[0566] The terminal sends the input information to the server.

[0567] Step 7:

[0568] The server checks the entered authentication information against a database, and if it matches, it generates a session token and returns it to the terminal.

[0569] Step 8:

[0570] The user receives a session token and successfully logs in.

[0571] Creating a Project

[0572] Step 1:

[0573] The user presses the "Create a new project" button within the app.

[0574] Step 2:

[0575] The terminal notifies the server of this operation.

[0576] Step 3:

[0577] The server generates an ID for the new project and registers the project in the database.

[0578] Step 4:

[0579] The server will return a notification of project creation completion and a new project ID to the device.

[0580] Step 5:

[0581] The user will receive a new project ID and the project creation will be complete.

[0582] Inputting development objectives and problem stories

[0583] Step 1:

[0584] The user enters a task story such as "Implementation of a user authentication system" on the project details screen.

[0585] Step 2:

[0586] The device sends the input to the server.

[0587] Step 3:

[0588] The server receives the challenge story and sends it as an input prompt to the generative artificial intelligence model.

[0589] AI-powered suggestions and feedback

[0590] Step 1:

[0591] The server uses a generative artificial intelligence model to generate appropriate code based on the problem story and suggests it to the user.

[0592] Step 2:

[0593] The user reviews the proposed code.

[0594] Step 3:

[0595] The user enters feedback about the code and presses the submit button.

[0596] Step 4:

[0597] The device sends the feedback content to the server.

[0598] Step 5:

[0599] The server receives the feedback and prompts the generative artificial intelligence model again to generate new code.

[0600] Step 6:

[0601] The server sends the improved code back to the user.

[0602] Project progress management

[0603] Step 1:

[0604] Users update task progress within the app, entering progress and new assignments.

[0605] Step 2:

[0606] The device sends the input to the server.

[0607] Step 3:

[0608] The server records the progress in a database.

[0609] Step 4:

[0610] The user types in a question about a specific issue and hits the submit button.

[0611] Step 5:

[0612] The device sends the question to the server.

[0613] Step 6:

[0614] The server sends the question to a generative artificial intelligence model, which generates an answer.

[0615] Step 7:

[0616] The server sends the AI's answer back to the user.

[0617] Step 8:

[0618] The user receives the answer and proceeds to the next task.

[0619] Example: Implementing a user authentication system

[0620] Step 1:

[0621] A user enters a problem story stating, "I want to implement a new user authentication system."

[0622] Step 2:

[0623] The device sends input to the server.

[0624] Step 3:

[0625] The server sends the problem story to the generative artificial intelligence model.

[0626] Step 4:

[0627] The server uses a generative artificial intelligence model to generate a basic user authentication code.

[0628] Step 5:

[0629] The user reviews the proposed code.

[0630] Step 6:

[0631] Users provide feedback on "strengthened security."

[0632] Step 7:

[0633] The device sends the feedback content to the server.

[0634] Step 8:

[0635] The server regenerates the code using a generative artificial intelligence model based on the feedback.

[0636] Step 9:

[0637] The server sends the improved code back to the user.

[0638] Step 10:

[0639] The user reviews the proposed code and proceeds to implementation.

[0640] Example 1

[0641] 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."

[0642] In conventional program code generation systems, when users provide feedback on generated code, the feedback is not reflected promptly, reducing the efficiency of generating high-quality programs. Additionally, creating new projects and managing projects requires a lot of effort, reducing productivity. Furthermore, when users have questions about specific technical issues, there are limited ways to receive quick and accurate answers, which can delay project progress.

[0643] 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.

[0644] In this invention, the server includes: means for generating program code using a generative artificial intelligence model based on prompts entered by a user; means for returning code suggestions for the entered prompts to the user; means for receiving feedback from the user and regenerating program code using the generative artificial intelligence model based on the feedback; means for returning the generated improved program code to the user; means for managing project progress; means for allowing the user to input project progress and new challenges; means for recording the input information in a database; means for the user to enter questions about specific problems and send them to the generative artificial intelligence model; means for providing the user with answers from the generative artificial intelligence model; means for the user to create and authenticate an account; means for verifying the entered authentication information in the database and generating a security token if successful; and means for notifying the user of authentication completion. This enables fast and efficient program code generation and feedback integration, simplifies project management, and provides fast and accurate answers to specific technical problems.

[0645] "User" means an individual or organization that uses the system to generate program code or manage projects.

[0646] A "prompt" is an instruction or question that a user enters into a generative artificial intelligence model, which then generates code based on that information.

[0647] "Generative artificial intelligence model" refers to an artificial intelligence technique that generates program code based on given prompts.

[0648] "Program Code" means the executable scripts or snippets of software that a generative artificial intelligence model generates based on prompts.

[0649] "Feedback" refers to requests for corrections or suggestions for improvements made by users to the generated program code.

[0650] A "security token" is a secure credential used by an authenticated user during a session to secure access rights.

[0651] A "project" is an individual development task or goal that a user creates within the system and manages its progress.

[0652] "Database" means a digital record system for storing and managing user information, project information, feedback, etc. within the system.

[0653] "Server" refers to a central computing device or service that processes user requests, generates code using generative artificial intelligence models, and performs database operations.

[0654] "Authentication information" refers to information such as an email address and password that a user uses to log in to a system.

[0655] A "session token" is a unique string used to identify a session, issued after a user has been successfully authenticated.

[0656] A "question" is a specific technical problem or question that a user enters into the system to receive an answer from the generative artificial intelligence model.

[0657] The present invention is a system that generates program code using a generative artificial intelligence model based on prompts entered by a user. This system operates through the mutual cooperation of a server, a terminal, and a user.

[0658] User Registration and Authentication

[0659] First, a user creates an account to use the system. The user enters their email address and password, which the device sends to the server. The server saves the entered information in a database and automatically sends a confirmation email to the user. When the user clicks the link in the confirmation email, the server activates the account. The user enters their email address and password on the login screen, and if the server successfully authenticates them, it issues a session token.

[0660] Creating a Project

[0661] After logging in, the user presses the "Create a new project" button, and the device notifies the server of the operation. The server generates an ID for the new project and registers it in the database. Once the project creation is complete, the server notifies the user.

[0662] Inputting development objectives and problem stories

[0663] The user enters the development objectives and problem story on the project details page. The device sends this information to the server, which passes it to the generative AI model. The generative AI model generates the appropriate program code based on the prompts.

[0664] AI-powered suggestions and feedback

[0665] The program code generated by the generative AI model is proposed to the user by the server. The user reviews the proposed code and enters feedback on areas for improvement or features they would like to add. The device then sends this feedback to the server, which then instructs the generative AI model to reprompt again. By repeating this process, the user obtains high-quality program code.

[0666] Project progress management

[0667] Users input the progress of tasks and new challenges within a project. The device sends this information to the server, which records it in a database. Users can also input questions about specific problems, which the device sends to the server, which passes them on to the generative AI model. The server provides the answer from the generative AI model to the user, and uses it as a reference for the next task.

[0668] Specific examples

[0669] For example, suppose a user inputs a problem story such as "I want to implement a new user authentication system." This information is sent to the server, and a basic user authentication code is generated by a generative artificial intelligence model. The user reviews this code and provides feedback such as "strengthen security." Based on this feedback, the server uses the generative artificial intelligence model again to generate code with appropriate security functions. This process is repeated until a high-quality program is implemented through dialogue between the user and AI.

[0670] An example of a prompt to be input to the generative AI model is "Please implement a user authentication system using JWT in Ruby on Rails." Users can review the program code generated based on this prompt and provide feedback to obtain higher quality code.

[0671] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0672] Step 1: User enters account information

[0673] The user enters their email address and password on the system's account creation screen. The entered authentication information is sent to the server by the terminal. The server stores the received authentication information in a database and automatically sends a confirmation email. Data verification is performed to ensure that the email address has been entered correctly, and the confirmation email is sent.

[0674] Input: Email address, password

[0675] Output: Send confirmation email, save information to database

[0676] Step 2: User clicks on the link in the confirmation email

[0677] The user clicks on the link in the confirmation email they receive, which triggers a process on the server to activate the account and update the user's status in the database.

[0678] Input: Click on the link in the confirmation email

[0679] Output: Account activated, database updated

[0680] Step 3: User enters login information

[0681] The user enters their email address and password on the login screen. The information is sent by the device to the server, which checks it against the authentication information in its database. If there is a match, the server issues a session token and sends it back to the user.

[0682] Input: Email address, password

[0683] Output: Session token issued, user authenticated

[0684] Step 4: User creates a new project

[0685] The user presses the "Create a new project" button on the project creation screen. The device notifies the server of this operation, and the server generates an ID for the new project and registers it in the database. The user is notified that the project has been created.

[0686] Input: Project creation operation

[0687] Output: Project ID generation, project registration in the database, and notification of completion

[0688] Step 5: User enters project details

[0689] The user enters the development objectives and problem story on the project details page. The data is sent to the server by the terminal, and the server passes it to the generative AI model. The generative AI model generates program code based on the prompts.

[0690] Input: Issue story, development objectives

[0691] Output: Sending prompts to a generative artificial intelligence model, generating program code

[0692] Step 6: The server presents the generated code to the user

[0693] The server proposes program code generated by the generative artificial intelligence model to the user, who then reviews the code and provides feedback.

[0694] Input: Program code generated by a generative artificial intelligence model

[0695] Output: Code suggestions to user, waiting for feedback

[0696] Step 7: Users submit feedback

[0697] Users review the proposed program code and provide feedback on improvements and additional features from their devices to the server, which then passes this feedback back to the generative artificial intelligence model as prompts.

[0698] Input: Feedback

[0699] Output: Reprompt for generative artificial intelligence models

[0700] Step 8: The server generates and suggests improved code

[0701] The generative artificial intelligence model generates improved program code based on the new feedback, which the server then proposes to the user again, and this process is repeated until the user is satisfied.

[0702] Input: Improved code generation using generative artificial intelligence models

[0703] Output: Suggested code improvements to the user

[0704] Step 9: Let users manage project progress

[0705] Users enter task progress and new issues on the project management screen, and the information is sent from the device to the server, which records this information in a database.

[0706] Input: Task progress, new assignments

[0707] Output: Record information in a database

[0708] Step 10: User enters question about specific technical issue

[0709] Users enter questions about specific technical issues and send them from their devices to a server, which passes the questions to a generative artificial intelligence model to obtain answers, which the server then provides to the user.

[0710] Input: Technical question

[0711] Output: Answer from the generative artificial intelligence model, providing the answer to the user

[0712] Through the above processing steps, the system can provide users with efficient program generation and project management.

[0713] (Application example 1)

[0714] 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."

[0715] Automation and efficiency are key challenges in modern factories. In particular, the operating programs for robots and other machines operating in factories are often highly complex and require specialized engineers, resulting in significant time and cost. Furthermore, improving and adapting existing programs is not easy, and the process of incorporating feedback is cumbersome. Given these circumstances, a system is needed to quickly and efficiently generate and improve the operating programs for machines in factories.

[0716] 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.

[0717] In this invention, the server includes means for generating program code using a generative artificial intelligence model based on prompts input by a user, means for returning code suggestions for the input prompts to the user, means for receiving feedback from the user and generating program code again using the generative artificial intelligence model based on the feedback, means for returning the generated improved program code to the user, means for managing the progress of the project, and means for generating operating programs for machines operating in a factory and improving the operation of the machines, thereby enabling users to easily generate and improve operating programs for machines.

[0718] A "generative artificial intelligence model" is a type of artificial intelligence algorithm that can generate new data or program code based on input data.

[0719] A "prompt" is a sentence or piece of text that indicates an instruction or request that the user enters.

[0720] "Program code" refers to a set of instructions for controlling machine operations, such as a computer-executable binary file or script.

[0721] "Feedback" refers to opinions and requests for improvement from users regarding the generated program code.

[0722] "Factory machinery" refers to robots and other automated devices used to perform production lines and automated tasks.

[0723] A "session token" is a temporary identifier used to keep a user authenticated to a system.

[0724] A "database" is a system that efficiently stores large amounts of data and enables it to be searched and processed.

[0725] "Project management" refers to the overall process of planning, executing, and monitoring work to achieve project goals.

[0726] This invention is a system for efficiently generating and improving the operating programs of machines operating in a factory. This system mainly uses a server, a terminal (smartphone), and a generative artificial intelligence model.

[0727] composition

[0728] Hardware

[0729] Device: iOS or Android smartphone.

[0730] Server: Cloud-based server.

[0731] Factory machinery: Robots and other automated equipment.

[0732] software

[0733] Front-end: Smartphone application using React Native.

[0734] Backend: Server-side application using Node.js.

[0735] Database: MongoDB.

[0736] Generative artificial intelligence model: OpenAI GPT-3.

[0737] Authentication: Firebase Authentication.

[0738] Processing flow

[0739] 1. User Registration and Authentication:

[0740] The user enters their email address and password using a terminal. This information is authenticated using Firebase Authentication, and if authentication is successful, the user information is stored in MongoDB. If successful, a session token is generated and the user is notified that authentication has been completed.

[0741] 2. Create a project:

[0742] A user presses the "Create a new project" button to create a new project. This operation is notified to the Node.js server, which generates a new project ID and registers it in MongoDB. The user is notified that the project creation is complete.

[0743] 3. Enter the assignment story:

[0744] Users enter their assignment story on the project details page, and this information is sent from the device to the server, which then sends prompts to the generative artificial intelligence model (GPT-3).

[0745] 4. AI Code Generation:

[0746] GPT-3 generates program code based on the prompts entered, and the code is sent back to the user via a server.

[0747] 5. Feedback and Improvements:

[0748] The user reviews the proposed code and provides feedback, which is then sent back to GPT-3 via the server, which generates a new code and sends the improved code back to the user.

[0749] 6. Project Progress Management:

[0750] Users can manage the progress of their projects, input task progress and new challenges, and store this information on the server. Users can also pose questions about specific problems and receive answers from GPT-3.

[0751] This system allows users to efficiently generate and improve operating programs for machines operating in factories. For example, if a user inputs, "I want to implement a robot operation that places part A in a specified position," GPT-3 generates program code based on that. Furthermore, if the user inputs feedback such as, "To improve position accuracy, we need a function to adjust using sensor input," GPT-3 generates improved code based on this feedback.

[0752] Example prompt sentence:

[0753] Generate code like this: "I want to implement a robot that places part A in a predetermined position. I need to adjust the position using sensor input to improve accuracy."

[0754] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0755] Step 1:

[0756] The user creates an account and enters authentication information. The device sends this information (email address, password) to the server. The server verifies this information using Firebase Authentication and generates a session token if authentication is successful. Next, a notification that authentication is complete is sent. The input is the user's authentication information, and the output is a session token and a notification that authentication is complete.

[0757] Step 2:

[0758] The user presses the "Create a new project" button. This operation is notified to the server from the terminal. The server generates a new project ID and registers this project ID and related information in MongoDB. When the project creation is complete, the terminal is notified. The input is a project creation request, and the output is the new project ID and its notification.

[0759] Step 3:

[0760] The user goes to the project details page and inputs the problem story (for example, "I want to implement a robot behavior that places part A in a designated position"). The device sends this input to the server. The server then sends this prompt to the API of the generative artificial intelligence model (GPT-3). The input is the problem story, and the output is the prompt for generation.

[0761] Step 4:

[0762] The server receives the program code generated by GPT-3. Then, it sends this code to the terminal, and the user confirms this code. Here, the input is the program code generated by GPT-3, and the output is the code suggested to the user.

[0763] Step 5:

[0764] The user checks the code and enters feedback (e.g., "To improve location accuracy, we need the ability to adjust using sensor inputs"). The device sends this feedback to the server, which then sends a new prompt to GPT-3, including this feedback. The input is the user's feedback, and the output is the improved prompt.

[0765] Step 6:

[0766] The server receives the newly generated improved program code from GPT-3 and sends it to the device. The user can review this code again and provide further feedback if necessary. This process is repeated. The input is the improved code generated by GPT-3, and the output is the improved code suggested to the user.

[0767] Step 7:

[0768] Users manage the progress of their projects and, if new issues arise, enter them into the system. The device sends this information to the server and stores it in MongoDB. The input is new issues and progress updates, and the output is updated progress data.

[0769] 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.

[0770] The present invention is a system that utilizes a generative artificial intelligence model to generate program code based on user prompts. It also includes a means for improving the code by incorporating user feedback and managing the progress of the project. It also combines an emotion engine that recognizes the user's emotions to provide support tailored to the user's emotions.

[0771] User Registration and Authentication

[0772] First, the user launches the app and enters their email address and password on the account creation screen. The device sends this information to the server, which stores it in a database. A confirmation email is sent to the user, and the user clicks on a link to activate their account. The user enters their login information and receives a session token, logging them into the platform.

[0773] Creating a Project

[0774] After logging in, a user can create a new project by pressing the "Create a new project" button in the app. The device notifies the server of this operation, and the server generates a new project ID and registers it in the database. Once the project creation is complete, the user is notified and provided with the new project ID.

[0775] Inputting development objectives and problem stories

[0776] The user enters the development objectives and problem story on the project details page. This information is sent from the device to the server, which passes it to the generative AI model. The generative AI model generates the appropriate program code based on the prompts.

[0777] AI-powered suggestions and feedback

[0778] The program code generated by the page-generating AI model is proposed to the user by the server. The user reviews the proposed code, enters feedback, and submits it. The device sends this to the server, which then sends the feedback back to the generative AI model to generate new code. This code is then sent back to the user, who can review it for improvements.

[0779] Project progress management

[0780] Users manage the progress of their projects, inputting task progress and new assignments. The device sends this information to a server, which records the progress in a database. Users ask questions about specific problems, and the server sends the questions to a generative artificial intelligence model to generate answers. The answers are sent back to the user and used as a reference for moving on to the next task.

[0781] Supported by an emotional engine

[0782] Furthermore, the emotion engine recognizes the user's emotions based on the prompts and feedback they provide. The emotion engine records the user's emotional data and uses this data to improve project progress management and generative AI model suggestions. Specifically, if the user is feeling stressed, the system will provide more step-by-step advice.

[0783] Specific examples

[0784] For example, suppose a user inputs a problem story such as "I want to implement a new user authentication system." This information is sent to the server, and a generative AI model generates a basic user authentication code. The user reviews the code and provides feedback on "strengthening security." The server then uses the generative AI model to generate a new code based on the feedback, and sends the improved code back to the user. Furthermore, the emotion engine detects the user's stress level, and the system can provide more detailed explanations and additional documentation, allowing development to proceed while reducing the user's stress.

[0785] In this way, the system of the present invention allows users to progress projects efficiently and creatively, and achieve high-quality results through project progress management and emotional support.

[0786] The processing flow will be explained below.

[0787] User Registration and Authentication

[0788] Step 1:

[0789] The user launches the app and enters their email address and password on the account creation screen.

[0790] Step 2:

[0791] The terminal transmits the input information to the server.

[0792] Step 3:

[0793] The server stores the received information in a database and sends a confirmation email to the user's email address.

[0794] Step 4:

[0795] The user receives a confirmation email and clicks the link in the email to activate their account.

[0796] Step 5:

[0797] The user enters their email address and password on the login screen and clicks the login button.

[0798] Step 6:

[0799] The terminal sends the input information to the server.

[0800] Step 7:

[0801] The server checks the entered authentication information against a database, and if it matches, it generates a session token and returns it to the terminal.

[0802] Step 8:

[0803] The user receives a session token and successfully logs in.

[0804] Creating a Project

[0805] Step 1:

[0806] The user presses the "Create a new project" button within the app.

[0807] Step 2:

[0808] The terminal notifies the server of this operation.

[0809] Step 3:

[0810] The server generates an ID for the new project and registers the project in the database.

[0811] Step 4:

[0812] The server will return a notification of project creation completion and a new project ID to the device.

[0813] Step 5:

[0814] The user will receive a new project ID and the project creation will be complete.

[0815] Inputting development objectives and problem stories

[0816] Step 1:

[0817] The user enters a task story such as "Implementation of a user authentication system" on the project details screen.

[0818] Step 2:

[0819] The device sends the input to the server.

[0820] Step 3:

[0821] The server receives the challenge story and sends it as an input prompt to the generative artificial intelligence model.

[0822] AI-powered suggestions and feedback

[0823] Step 1:

[0824] The server uses a generative artificial intelligence model to generate appropriate code based on the problem story.

[0825] Step 2:

[0826] The server presents the generated code to the user.

[0827] Step 3:

[0828] The user reviews the proposed code.

[0829] Step 4:

[0830] The user enters feedback about the code and presses the submit button.

[0831] Step 5:

[0832] The device sends the feedback content to the server.

[0833] Step 6:

[0834] The server receives the feedback and uses a generative artificial intelligence model to prompt again and generate a new code.

[0835] Step 7:

[0836] The server sends the improved code back to the user.

[0837] Project progress management

[0838] Step 1:

[0839] Users update task progress within the app, entering progress and new assignments.

[0840] Step 2:

[0841] The device sends the input to the server.

[0842] Step 3:

[0843] The server records the progress in a database.

[0844] Step 4:

[0845] The user types in a question about a specific issue and hits the submit button.

[0846] Step 5:

[0847] The device sends the question to the server.

[0848] Step 6:

[0849] The server sends the question to a generative artificial intelligence model, which generates an answer.

[0850] Step 7:

[0851] The server sends the answer from the generative artificial intelligence model back to the user.

[0852] Step 8:

[0853] The user receives the answer and proceeds to the next task.

[0854] Supported by an emotional engine

[0855] Step 1:

[0856] When users enter prompts or feedback, the emotion engine analyzes their facial expressions, tone of voice, and other factors to recognize their emotions.

[0857] Step 2:

[0858] The device transmits the recognized emotion data to the server.

[0859] Step 3:

[0860] The server receives the emotional data and records the user's emotional state.

[0861] Step 4:

[0862] The server sends the emotional data as feedback to the generative artificial intelligence model, which then adjusts the content of the proposed code.

[0863] Step 5:

[0864] The server suggests tailored codes and messages to the user.

[0865] Step 6:

[0866] The user reviews the system's suggestions and provides feedback again if they do not like them.

[0867] Example: Implementing a user authentication system

[0868] Step 1:

[0869] A user enters a problem story stating, "I want to implement a new user authentication system."

[0870] Step 2:

[0871] The device sends input to the server.

[0872] Step 3:

[0873] The server sends the problem story to the generative artificial intelligence model.

[0874] Step 4:

[0875] The server uses a generative artificial intelligence model to generate a basic user authentication code.

[0876] Step 5:

[0877] The user reviews the proposed code.

[0878] Step 6:

[0879] Users provide feedback on "strengthened security."

[0880] Step 7:

[0881] The device sends the feedback content to the server.

[0882] Step 8:

[0883] The server regenerates the code using a generative artificial intelligence model based on the feedback.

[0884] Step 9:

[0885] The server sends the improved code back to the user.

[0886] Step 10:

[0887] The user reviews the proposed code and proceeds to implementation.

[0888] Step 11:

[0889] The server uses an emotion engine to monitor the user's stress level.

[0890] Step 12:

[0891] If the emotion engine recognizes a user's stress level as high, the server instructs the generative artificial intelligence model to provide a more detailed explanation or additional supporting information.

[0892] Step 13:

[0893] The user receives detailed explanations and additional support information, then reviews and implements the code again.

[0894] Example 2

[0895] 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."

[0896] Previous code generation systems focused on generating code based on user prompts and improving it through feedback, but lacked support that took into account the user's emotional state. This resulted in insufficient support when users faced stressful situations or difficult tasks, which could stall project progress. Furthermore, there were limited ways for users to efficiently manage project progress and tasks.

[0897] 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.

[0898] In this invention, the server includes means for generating program code using a generative artificial intelligence model based on prompts entered by the user, means for returning code suggestions for the entered prompts to the user, means for receiving feedback from the user and regenerating program code using the generative artificial intelligence model based on the feedback, means for returning the generated improved program code to the user, means for managing the progress of the project, means for recognizing the user's emotions based on the prompts and feedback entered by the user, and means for adjusting the suggestions and support content of the generative artificial intelligence model based on the emotions, thereby enabling the user to progress through the project efficiently and comfortably.

[0899] A "prompt" is an instruction that a user inputs to a generative artificial intelligence model.

[0900] A "generative artificial intelligence model" is an algorithm or system that generates program code based on user prompts.

[0901] "Program code" means text that contains instructions that a computer can execute.

[0902] "Feedback" means evaluations and requests for corrections made by users to the generated program code.

[0903] "Project progress management" refers to the means and methods for managing the progress and tasks of a project and for moving the project forward efficiently.

[0904] "Emotion recognizer" refers to a system or algorithm that recognizes a user's emotions or stress state based on user input and feedback.

[0905] "Means for adjusting support content" refers to means or methods for taking the user's feelings into consideration and providing appropriate support and supplementary information.

[0906] To implement the present invention, the user, the terminal, and the server must work together. Specific hardware and software for each step will be described in order.

[0907] First, when a user launches the application, they use a device such as a smartphone or PC. The user enters their email address and password on the account creation screen, and the device sends this information to the server. The server stores the received information in a database and sends a confirmation email to the user. The user activates their account by clicking the link in the confirmation email.

[0908] Next, the user enters their email address and password on the login screen, and the device sends the login information to the server. The server verifies the information and, if valid, issues a session token and sends it to the user. The user receives the session token and can log in to the platform.

[0909] After logging in, the user presses the "Create a new project" button, and the device notifies the server of this operation. The server generates a new project ID and saves this information in the database, creating the project. The server then returns the project ID to the user, notifying them that the new project has been created.

[0910] When a user enters the development objectives and problem story on the project details page, the device sends this information to the server, which then passes the received information to a generative artificial intelligence model, which uses powerful data center or cloud-based computing resources to generate the optimal program code for the specified conditions.

[0911] The generated program code is proposed to the user by the server, who then confirms it. If the user provides appropriate feedback, the device sends this feedback to the server. The server then passes the feedback back to the generative artificial intelligence model, which then generates new program code. This process is repeated until the user is satisfied.

[0912] The system always takes the user's emotions into consideration, and the emotion engine intervenes when the user is feeling particularly stressed. The emotion engine analyzes the user's emotions from their input and feedback and provides appropriate support and auxiliary information, allowing the user to proceed with the project more efficiently and comfortably.

[0913] As a concrete example, suppose a user inputs a problem story such as "I want to implement a new user authentication system." This information is sent to the server, and a generative AI model generates a basic user authentication code. The user checks the code and provides feedback on "strengthening security." Based on this feedback, the server uses the generative AI model again to generate an improved code and sends it back to the user. During this process, the emotion engine detects the user's stress, and the system reduces the user's stress by providing detailed explanations and additional documentation.

[0914] Users can also pose questions about specific problems, and the server sends the questions to a generative artificial intelligence model that generates an appropriate answer, which is then sent back to the user to guide them through the next task.

[0915] Thus, the embodiments of the invention allow users to efficiently progress projects and achieve high-quality results, while the support provided by the emotion engine allows users to work more comfortably.

[0916] Examples of prompts include:

[0917] "I want to implement a new user authentication system."

[0918] "I want a database search function to be added."

[0919] "I want the user interface design to be modern."

[0920] The above is a specific embodiment of the present invention.

[0921] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0922] Step 1:

[0923] Create an account

[0924] The user launches the application and enters their email address and password on the account creation screen. The device sends this information to the server. The server stores the received information in a database and sends a confirmation email to the user. The user clicks on the link in the confirmation email to activate their account.

[0925] Input: User's email address, password

[0926] Data processing / calculation: The server stores the information in a database and sends it by email.

[0927] Output: Confirmation email, account activation

[0928] Step 2:

[0929] Log in

[0930] The user enters their email address and password on the login screen. The device sends this information to the server. The server verifies the information and, if valid, issues a session token and sends it to the user. The user receives the session token and logs in to the platform.

[0931] Input: User's email address, password

[0932] Data processing / calculation: Server checks information and generates session token

[0933] Output: Session token, login successful

[0934] Step 3:

[0935] Creating a new project

[0936] After logging in, the user presses the "Create a new project" button. The device notifies the server of this action. The server generates a new project ID and saves it in the database. The server then returns the project ID to the user, notifying them that a new project has been created.

[0937] Input: User clicks Create button

[0938] Data processing / calculation: The server generates a project ID and saves it in the database

[0939] Output: New project ID, project created notification

[0940] Step 4:

[0941] Entering Project Details

[0942] The user enters the development objectives and problem story on the project details page. The device sends this information to the server. The server passes the received information to a generative artificial intelligence model, which uses computing resources to generate program code.

[0943] Input: Development objectives, problem story

[0944] Data processing / calculation: The server passes the information to the generative artificial intelligence model, generating code.

[0945] Output: Generated program code

[0946] Step 5:

[0947] Code Generation and Suggestions

[0948] A generative artificial intelligence model generates program code based on the input prompts, and the server suggests the generated code to the user.

[0949] Input: Program code from a generative artificial intelligence model

[0950] Data processing / calculation: The server transmits the code to the user

[0951] Output: User-suggested program code

[0952] Step 6:

[0953] Feedback and Improvements

[0954] The user reviews the proposed code and enters feedback. The device sends the feedback to the server. The server resubmits the feedback to the generative AI model, which generates new program code. The server then sends the improved code back to the user.

[0955] Input: User feedback

[0956] Data processing / calculation: The server passes the feedback to the generative AI model, and then regenerates it.

[0957] Output: Improved program code

[0958] Step 7:

[0959] Task progress management

[0960] The user manages the progress of the project, inputting task progress and new issues. The device sends the input information to the server, which records the progress in a database.

[0961] Input: Task progress information, new assignments

[0962] Data processing / calculation: The server records the progress in the database

[0963] Output: Updated progress data

[0964] Step 8:

[0965] Questions and Answers

[0966] The user poses a question about a specific problem. The device sends this question to a server. The server sends the question to a generative artificial intelligence model, which generates an answer. The server sends the generated answer to the user.

[0967] Input: User question

[0968] Data processing / calculation: The server sends the question to the generative AI model, which generates the answer.

[0969] Output: The answer provided to the user

[0970] Step 9:

[0971] Emotion assessment and response

[0972] The emotion engine recognizes emotions based on user input and feedback, and the server records the emotion data and uses it to tailor the generative AI model's suggestions and support.

[0973] Input: User input, feedback

[0974] Data processing / calculation: The emotion engine evaluates emotions, and the server records the emotion data.

[0975] Output: Tailored support and feedback

[0976] (Application example 2)

[0977] 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."

[0978] While conventional program code generation systems using generative artificial intelligence models can generate and improve code based on user prompts, they lack a means to recognize user emotions and provide support accordingly, making it difficult to efficiently progress projects while reducing user stress. Furthermore, there are insufficient means for managing project progress in real time and incorporating feedback. To solve these problems, a system with support and real-time management capabilities that respond to user emotions is needed.

[0979] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0980] This invention includes means for generating program code using a generative artificial intelligence model based on prompts entered by a user, means for returning code suggestions for the entered prompts to the user, means for receiving feedback from the user and generating program code again using the generative artificial intelligence model based on the feedback, means for returning the generated improved program code to the user, means for project progress management, means for recognizing user emotion data and adapting project progress management and code suggestions based on the user emotion data, and means for saving the user's task progress in a database and updating the progress status in real time. This allows program code to be generated and improved while taking user emotions into consideration, and makes it possible to more efficiently manage project progress and reflect feedback in real time.

[0981] A "generative artificial intelligence model" is an artificial intelligence technology that generates program code based on prompts entered by the user and optimizes its content.

[0982] A "prompt" is text information that explains the purpose or task the user is entering.

[0983] "Program code" means text that contains instructions necessary for a computer to follow instructions.

[0984] "Feedback" is information indicating the user's evaluation of the generated program code and suggestions for improvement.

[0985] "Emotional data" is emotional information extracted from user input and feedback, and is data that reflects the user's psychological state.

[0986] "Task progress status" is information that indicates the progress of each task in a project.

[0987] A "database" is a system that manages and stores a collection of structured data.

[0988] "Real-time updates" means that input information and processing results are instantly reflected in the system.

[0989] "User" means an individual or organization that uses the system to generate program code or manage projects.

[0990] A "project" is a planned series of tasks or activities designed to achieve a specific purpose.

[0991] The system for implementing this invention allows users to input prompt sentences and generate and improve program code using a generative artificial intelligence model. Specifically, it involves three main elements working together: a server, a terminal, and a user.

[0992] Hardware and Software Configuration

[0993] The server has a generative artificial intelligence model (e.g., OpenAI's GPT-4) and an emotion recognition engine (e.g., Microsoft Azure's Text Analytics) installed. The server receives a prompt from the user, generates program code using the generative artificial intelligence model, and analyzes the user's emotions using the emotion recognition engine.

[0994] The device (smartphone or PC) acts as the user interface. The device sends prompts and feedback entered by the user to the server, and is equipped with an application (for example, a backend built with the Django framework and a frontend built with React) to receive and display the generated program code and emotion recognition results.

[0995] Users operate the device to create projects, enter prompts, provide feedback, and more.

[0996] Data processing and calculation flow

[0997] 1. User Registration and Authentication

[0998] The user enters their email address and password using the terminal application and submits them to the server, which validates the information using Django's user authentication functionality, stores it in a PostgreSQL database, and, if authentication is successful, generates a session token and sends it back to the user.

[0999] 2. Create a project

[1000] When the user clicks the "Create a new project" button, the device notifies the server of this action. The server generates a new project ID and registers it in the database. Once the project creation is complete, the user is notified and provided with the new project ID.

[1001] 3. Entering prompt statements and generating code

[1002] The user enters a prompt on the project details page and sends it to the server, which then passes the prompt to the generative artificial intelligence model to generate program code.

[1003] 4. Suggestions and Feedback

[1004] The generated program code is sent from the server to the terminal and displayed to the user. The user reviews the code and provides feedback. The terminal sends this feedback to the server, which then uses the generative artificial intelligence model to improve the program code.

[1005] 5. Emotional awareness and support

[1006] Emotional data is collected from user feedback and input and analyzed by an emotion recognition engine on the server. Based on the analysis results, if the user's stress level is high, more detailed explanations or additional documentation will be provided.

[1007] Specific examples

[1008] For example, suppose a user enters the prompt, "I want to implement a new quality inspection system." This information is sent to the server, and a generative AI model generates the basic program code for the quality inspection system. The user reviews the code and provides feedback, saying, "I want to improve the inspection accuracy." The server then uses the generative AI model to improve the program code based on the feedback and sends it back to the user. Furthermore, an emotion recognition engine detects the user's level of excitement and provides additional detailed explanations to reduce stress.

[1009] This system allows users to effectively generate and improve program code and efficiently advance projects.

[1010] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1011] Step 1: User Registration and Authentication

[1012] The user enters their email address and password in the terminal application and sends a registration request to the server. The server receives the input and uses Django's user authentication function to store the registration information in a database (PostgreSQL). The server then sends the user a confirmation email, and when the user clicks on the link, the account is activated. When the user enters their login information again, the server authenticates them and, if successful, generates a session token and sends it back to the user.

[1013] Step 2: Create a project

[1014] The user presses the "Create a new project" button in the app, and the device notifies the server of the operation. The server generates a new project ID and registers this information in the database. Once the project creation is complete, the server returns the new project ID to the user and notifies them that the project has been created.

[1015] Step 3: Enter the prompt statement

[1016] The user enters a prompt on the project details page, and the device sends this information to the server. The entered prompt is passed to a generative artificial intelligence model (OpenAI GPT-4). The server inputs the prompt into the AI ​​model and instructs it to generate program code. The generated program code is temporarily stored on the server.

[1017] Step 4: Code suggestions and feedback

[1018] The server sends the generated program code to the terminal, which displays it to the user. The user checks the code and enters feedback if necessary. The feedback is sent from the terminal to the server. The server passes this feedback back to the generative artificial intelligence model, instructing it to generate improved program code.

[1019] Step 5: Submitting the improved code

[1020] The server then sends the improved program code generated by the generative artificial intelligence model back to the device, which then displays the improved program code to the user and repeats the process until feedback is received. With each iteration of the improvement, the server saves the progress record in the database and updates the project's progress.

[1021] Step 6: Emotional awareness and support

[1022] The device sends the feedback and prompts entered by the user to the server, which then uses an emotion recognition engine (Microsoft Azure Text Analytics) to analyze the user's emotional data. Based on the analysis results, if the user's stress level is high, the server generates emotionally appropriate support information (e.g., step-by-step guides or additional documentation) and provides it to the user via the device.

[1023] Step 7: Real-time updates on task progress

[1024] Users operate their devices to input task progress, and the devices send that information to the server, which then stores the task progress in a database and updates it in real time, allowing users to always have the most up-to-date information on the progress of the entire project.

[1025] 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.

[1026] 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.

[1027] 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.

[1028] [Third embodiment]

[1029] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1030] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1031] 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).

[1032] 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.

[1033] 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.

[1034] 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).

[1035] 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.

[1036] 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.

[1037] 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.

[1038] 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.

[1039] 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.

[1040] 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."

[1041] The present invention is a system that generates program code by utilizing a generative artificial intelligence model based on prompts entered by a user. Specific embodiments of the "Aibou AI" system are described below.

[1042] User Registration and Authentication

[1043] First, a user creates an account to use the system. At this time, the user enters authentication information such as an email address and password. The device sends this information to the server. The server stores the entered information in a database and sends a confirmation email to the user. When the user clicks the link in the confirmation email, the account is activated. The user can log in to the platform by entering their authentication information on the login screen and receiving a session token.

[1044] Creating a Project

[1045] After logging in, the user can create a new project. When the user presses the "Create a new project" button, the device notifies the server of the operation. The server generates an ID for the new project and registers it in the database. When the project creation is complete, the user is notified.

[1046] Inputting development objectives and problem stories

[1047] Next, the user enters the development objectives and problem story on the project details page. This information is sent from the device to the server, which passes it on to the generative AI model, which then generates the appropriate program code based on the prompts.

[1048] AI-powered suggestions and feedback

[1049] The program code generated by the generative AI model is proposed to the user by the server. The user can review the proposed code and enter feedback. This feedback may include improvements to the code or features they would like to add. The device sends this feedback to the server, which then instructs the generative AI model to prompt again. The generative AI model then generates new code, which is proposed again. By repeating this process, the user can obtain high-quality program code.

[1050] Project progress management

[1051] Users can manage the progress of projects and input task progress and new assignments. The device sends this information to the server, which records the progress in a database. Users can also pose questions about specific problems, which the server sends to the generative AI model. The answers from the generative AI are sent back to the user and used as a reference for moving on to the next task.

[1052] Specific examples

[1053] For example, suppose a user inputs a problem story such as "I want to implement a new user authentication system." This information is sent to the server, and a basic user authentication code is generated by the generative AI model. The user checks this code and provides feedback on "strengthening security." Based on this feedback, the server uses the generative AI model to generate a new code with appropriate security features and send it back to the user. In this way, the process of implementing a high-quality program through dialogue between the user and AI is repeated.

[1054] The system allows users to efficiently and creatively progress projects, achieving high productivity and high-quality results in the development of computer programs.

[1055] The processing flow will be explained below.

[1056] User Registration and Authentication

[1057] Step 1:

[1058] The user launches the app and enters their email address and password on the account creation screen.

[1059] Step 2:

[1060] The terminal transmits the input information to the server.

[1061] Step 3:

[1062] The server stores the received information in a database and sends a confirmation email to the user's email address.

[1063] Step 4:

[1064] The user receives a confirmation email and clicks the link in the email to activate their account.

[1065] Step 5:

[1066] The user enters their email address and password on the login screen and clicks the login button.

[1067] Step 6:

[1068] The terminal sends the input information to the server.

[1069] Step 7:

[1070] The server checks the entered authentication information against a database, and if it matches, it generates a session token and returns it to the terminal.

[1071] Step 8:

[1072] The user receives a session token and successfully logs in.

[1073] Creating a Project

[1074] Step 1:

[1075] The user presses the "Create a new project" button within the app.

[1076] Step 2:

[1077] The terminal notifies the server of this operation.

[1078] Step 3:

[1079] The server generates an ID for the new project and registers the project in the database.

[1080] Step 4:

[1081] The server will return a notification of project creation completion and a new project ID to the device.

[1082] Step 5:

[1083] The user will receive a new project ID and the project creation will be complete.

[1084] Inputting development objectives and problem stories

[1085] Step 1:

[1086] The user enters a task story such as "Implementation of a user authentication system" on the project details screen.

[1087] Step 2:

[1088] The device sends the input to the server.

[1089] Step 3:

[1090] The server receives the challenge story and sends it as an input prompt to the generative artificial intelligence model.

[1091] AI-powered suggestions and feedback

[1092] Step 1:

[1093] The server uses a generative artificial intelligence model to generate appropriate code based on the problem story and suggests it to the user.

[1094] Step 2:

[1095] The user reviews the proposed code.

[1096] Step 3:

[1097] The user enters feedback about the code and presses the submit button.

[1098] Step 4:

[1099] The device sends the feedback content to the server.

[1100] Step 5:

[1101] The server receives the feedback and prompts the generative artificial intelligence model again to generate new code.

[1102] Step 6:

[1103] The server sends the improved code back to the user.

[1104] Project progress management

[1105] Step 1:

[1106] Users update task progress within the app, entering progress and new assignments.

[1107] Step 2:

[1108] The device sends the input to the server.

[1109] Step 3:

[1110] The server records the progress in a database.

[1111] Step 4:

[1112] The user types in a question about a specific issue and hits the submit button.

[1113] Step 5:

[1114] The device sends the question to the server.

[1115] Step 6:

[1116] The server sends the question to a generative artificial intelligence model, which generates an answer.

[1117] Step 7:

[1118] The server sends the AI's answer back to the user.

[1119] Step 8:

[1120] The user receives the answer and proceeds to the next task.

[1121] Example: Implementing a user authentication system

[1122] Step 1:

[1123] A user enters a problem story stating, "I want to implement a new user authentication system."

[1124] Step 2:

[1125] The device sends input to the server.

[1126] Step 3:

[1127] The server sends the problem story to the generative artificial intelligence model.

[1128] Step 4:

[1129] The server uses a generative artificial intelligence model to generate a basic user authentication code.

[1130] Step 5:

[1131] The user reviews the proposed code.

[1132] Step 6:

[1133] Users provide feedback on "strengthened security."

[1134] Step 7:

[1135] The device sends the feedback content to the server.

[1136] Step 8:

[1137] The server regenerates the code using a generative artificial intelligence model based on the feedback.

[1138] Step 9:

[1139] The server sends the improved code back to the user.

[1140] Step 10:

[1141] The user reviews the proposed code and proceeds to implementation.

[1142] Example 1

[1143] 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."

[1144] In conventional program code generation systems, when users provide feedback on generated code, the feedback is not reflected promptly, reducing the efficiency of generating high-quality programs. Additionally, creating new projects and managing projects requires a lot of effort, reducing productivity. Furthermore, when users have questions about specific technical issues, there are limited ways to receive quick and accurate answers, which can delay project progress.

[1145] 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.

[1146] In this invention, the server includes: means for generating program code using a generative artificial intelligence model based on prompts entered by a user; means for returning code suggestions for the entered prompts to the user; means for receiving feedback from the user and regenerating program code using the generative artificial intelligence model based on the feedback; means for returning the generated improved program code to the user; means for managing project progress; means for allowing the user to input project progress and new challenges; means for recording the input information in a database; means for the user to enter questions about specific problems and send them to the generative artificial intelligence model; means for providing the user with answers from the generative artificial intelligence model; means for the user to create and authenticate an account; means for verifying the entered authentication information in the database and generating a security token if successful; and means for notifying the user of authentication completion. This enables fast and efficient program code generation and feedback integration, simplifies project management, and provides fast and accurate answers to specific technical problems.

[1147] "User" means an individual or organization that uses the system to generate program code or manage projects.

[1148] A "prompt" is an instruction or question that a user enters into a generative artificial intelligence model, which then generates code based on that information.

[1149] "Generative artificial intelligence model" refers to an artificial intelligence technique that generates program code based on given prompts.

[1150] "Program Code" means the executable scripts or snippets of software that a generative artificial intelligence model generates based on prompts.

[1151] "Feedback" refers to requests for corrections or suggestions for improvements made by users to the generated program code.

[1152] A "security token" is a secure credential used by an authenticated user during a session to secure access rights.

[1153] A "project" is an individual development task or goal that a user creates within the system and manages its progress.

[1154] "Database" means a digital record system for storing and managing user information, project information, feedback, etc. within the system.

[1155] "Server" refers to a central computing device or service that processes user requests, generates code using generative artificial intelligence models, and performs database operations.

[1156] "Authentication information" refers to information such as an email address and password that a user uses to log in to a system.

[1157] A "session token" is a unique string used to identify a session, issued after a user has been successfully authenticated.

[1158] A "question" is a specific technical problem or question that a user enters into the system to receive an answer from the generative artificial intelligence model.

[1159] The present invention is a system that generates program code using a generative artificial intelligence model based on prompts entered by a user. This system operates through the mutual cooperation of a server, a terminal, and a user.

[1160] User Registration and Authentication

[1161] First, a user creates an account to use the system. The user enters their email address and password, which the device sends to the server. The server saves the entered information in a database and automatically sends a confirmation email to the user. When the user clicks the link in the confirmation email, the server activates the account. The user enters their email address and password on the login screen, and if the server successfully authenticates them, it issues a session token.

[1162] Creating a Project

[1163] After logging in, the user presses the "Create a new project" button, and the device notifies the server of the operation. The server generates an ID for the new project and registers it in the database. Once the project creation is complete, the server notifies the user.

[1164] Inputting development objectives and problem stories

[1165] The user enters the development objectives and problem story on the project details page. The device sends this information to the server, which passes it to the generative AI model. The generative AI model generates the appropriate program code based on the prompts.

[1166] AI-powered suggestions and feedback

[1167] The program code generated by the generative AI model is proposed to the user by the server. The user reviews the proposed code and enters feedback on areas for improvement or features they would like to add. The device then sends this feedback to the server, which then instructs the generative AI model to reprompt again. By repeating this process, the user obtains high-quality program code.

[1168] Project progress management

[1169] Users input the progress of tasks and new challenges within a project. The device sends this information to the server, which records it in a database. Users can also input questions about specific problems, which the device sends to the server, which passes them on to the generative AI model. The server provides the answer from the generative AI model to the user, and uses it as a reference for the next task.

[1170] Specific examples

[1171] For example, suppose a user inputs a problem story such as "I want to implement a new user authentication system." This information is sent to the server, and a basic user authentication code is generated by a generative artificial intelligence model. The user reviews this code and provides feedback such as "strengthen security." Based on this feedback, the server uses the generative artificial intelligence model again to generate code with appropriate security functions. This process is repeated until a high-quality program is implemented through dialogue between the user and AI.

[1172] An example of a prompt to be input to the generative AI model is "Please implement a user authentication system using JWT in Ruby on Rails." Users can review the program code generated based on this prompt and provide feedback to obtain higher quality code.

[1173] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1174] Step 1: User enters account information

[1175] The user enters their email address and password on the system's account creation screen. The entered authentication information is sent to the server by the terminal. The server stores the received authentication information in a database and automatically sends a confirmation email. Data verification is performed to ensure that the email address has been entered correctly, and the confirmation email is sent.

[1176] Input: Email address, password

[1177] Output: Send confirmation email, save information to database

[1178] Step 2: User clicks on the link in the confirmation email

[1179] The user clicks on the link in the confirmation email they receive, which triggers a process on the server to activate the account and update the user's status in the database.

[1180] Input: Click on the link in the confirmation email

[1181] Output: Account activated, database updated

[1182] Step 3: User enters login information

[1183] The user enters their email address and password on the login screen. The information is sent by the device to the server, which checks it against the authentication information in its database. If there is a match, the server issues a session token and sends it back to the user.

[1184] Input: Email address, password

[1185] Output: Session token issued, user authenticated

[1186] Step 4: User creates a new project

[1187] The user presses the "Create a new project" button on the project creation screen. The device notifies the server of this operation, and the server generates an ID for the new project and registers it in the database. The user is notified that the project has been created.

[1188] Input: Project creation operation

[1189] Output: Project ID generation, project registration in the database, and notification of completion

[1190] Step 5: User enters project details

[1191] The user enters the development objectives and problem story on the project details page. The data is sent to the server by the terminal, and the server passes it to the generative AI model. The generative AI model generates program code based on the prompts.

[1192] Input: Issue story, development objectives

[1193] Output: Sending prompts to a generative artificial intelligence model, generating program code

[1194] Step 6: The server presents the generated code to the user

[1195] The server proposes program code generated by the generative artificial intelligence model to the user, who then reviews the code and provides feedback.

[1196] Input: Program code generated by a generative artificial intelligence model

[1197] Output: Code suggestions to user, waiting for feedback

[1198] Step 7: Users submit feedback

[1199] Users review the proposed program code and provide feedback on improvements and additional features from their devices to the server, which then passes this feedback back to the generative artificial intelligence model as prompts.

[1200] Input: Feedback

[1201] Output: Reprompt for generative artificial intelligence models

[1202] Step 8: The server generates and suggests improved code

[1203] The generative artificial intelligence model generates improved program code based on the new feedback, which the server then proposes to the user again, and this process is repeated until the user is satisfied.

[1204] Input: Improved code generation using generative artificial intelligence models

[1205] Output: Suggested code improvements to the user

[1206] Step 9: Let users manage project progress

[1207] Users enter task progress and new issues on the project management screen, and the information is sent from the device to the server, which records this information in a database.

[1208] Input: Task progress, new assignments

[1209] Output: Record information in a database

[1210] Step 10: User enters question about specific technical issue

[1211] Users enter questions about specific technical issues and send them from their devices to a server, which passes the questions to a generative artificial intelligence model to obtain answers, which the server then provides to the user.

[1212] Input: Technical question

[1213] Output: Answer from the generative artificial intelligence model, providing the answer to the user

[1214] Through the above processing steps, the system can provide users with efficient program generation and project management.

[1215] (Application example 1)

[1216] 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."

[1217] Automation and efficiency are key challenges in modern factories. In particular, the operating programs for robots and other machines operating in factories are often highly complex and require specialized engineers, resulting in significant time and cost. Furthermore, improving and adapting existing programs is not easy, and the process of incorporating feedback is cumbersome. Given these circumstances, a system is needed to quickly and efficiently generate and improve the operating programs for machines in factories.

[1218] 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.

[1219] In this invention, the server includes means for generating program code using a generative artificial intelligence model based on prompts input by a user, means for returning code suggestions for the input prompts to the user, means for receiving feedback from the user and generating program code again using the generative artificial intelligence model based on the feedback, means for returning the generated improved program code to the user, means for managing the progress of the project, and means for generating operating programs for machines operating in a factory and improving the operation of the machines, thereby enabling users to easily generate and improve operating programs for machines.

[1220] A "generative artificial intelligence model" is a type of artificial intelligence algorithm that can generate new data or program code based on input data.

[1221] A "prompt" is a sentence or piece of text that indicates an instruction or request that the user enters.

[1222] "Program code" refers to a set of instructions for controlling machine operations, such as a computer-executable binary file or script.

[1223] "Feedback" refers to opinions and requests for improvement from users regarding the generated program code.

[1224] "Factory machinery" refers to robots and other automated devices used to perform production lines and automated tasks.

[1225] A "session token" is a temporary identifier used to keep a user authenticated to a system.

[1226] A "database" is a system that efficiently stores large amounts of data and enables it to be searched and processed.

[1227] "Project management" refers to the overall process of planning, executing, and monitoring work to achieve project goals.

[1228] This invention is a system for efficiently generating and improving the operating programs of machines operating in a factory. This system mainly uses a server, a terminal (smartphone), and a generative artificial intelligence model.

[1229] composition

[1230] Hardware

[1231] Device: iOS or Android smartphone.

[1232] Server: Cloud-based server.

[1233] Factory machinery: Robots and other automated equipment.

[1234] software

[1235] Front-end: Smartphone application using React Native.

[1236] Backend: Server-side application using Node.js.

[1237] Database: MongoDB.

[1238] Generative artificial intelligence model: OpenAI GPT-3.

[1239] Authentication: Firebase Authentication.

[1240] Processing flow

[1241] 1. User Registration and Authentication:

[1242] The user enters their email address and password using a terminal. This information is authenticated using Firebase Authentication, and if authentication is successful, the user information is stored in MongoDB. If successful, a session token is generated and the user is notified that authentication has been completed.

[1243] 2. Create a project:

[1244] A user presses the "Create a new project" button to create a new project. This operation is notified to the Node.js server, which generates a new project ID and registers it in MongoDB. The user is notified that the project creation is complete.

[1245] 3. Enter the assignment story:

[1246] Users enter their assignment story on the project details page, and this information is sent from the device to the server, which then sends prompts to the generative artificial intelligence model (GPT-3).

[1247] 4. AI Code Generation:

[1248] GPT-3 generates program code based on the prompts entered, and the code is sent back to the user via a server.

[1249] 5. Feedback and Improvements:

[1250] The user reviews the proposed code and provides feedback, which is then sent back to GPT-3 via the server, which generates a new code and sends the improved code back to the user.

[1251] 6. Project Progress Management:

[1252] Users can manage the progress of their projects, input task progress and new challenges, and store this information on the server. Users can also pose questions about specific problems and receive answers from GPT-3.

[1253] This system allows users to efficiently generate and improve operating programs for machines operating in factories. For example, if a user inputs, "I want to implement a robot operation that places part A in a specified position," GPT-3 generates program code based on that. Furthermore, if the user inputs feedback such as, "To improve position accuracy, we need a function to adjust using sensor input," GPT-3 generates improved code based on this feedback.

[1254] Example prompt sentence:

[1255] Generate code like this: "I want to implement a robot that places part A in a predetermined position. I need to adjust the position using sensor input to improve accuracy."

[1256] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1257] Step 1:

[1258] The user creates an account and enters authentication information. The device sends this information (email address, password) to the server. The server verifies this information using Firebase Authentication and generates a session token if authentication is successful. Next, a notification that authentication is complete is sent. The input is the user's authentication information, and the output is a session token and a notification that authentication is complete.

[1259] Step 2:

[1260] The user presses the "Create a new project" button. This operation is notified to the server from the terminal. The server generates a new project ID and registers this project ID and related information in MongoDB. When the project creation is complete, the terminal is notified. The input is a project creation request, and the output is the new project ID and its notification.

[1261] Step 3:

[1262] The user goes to the project details page and inputs the problem story (for example, "I want to implement a robot behavior that places part A in a designated position"). The device sends this input to the server. The server then sends this prompt to the API of the generative artificial intelligence model (GPT-3). The input is the problem story, and the output is the prompt for generation.

[1263] Step 4:

[1264] The server receives the program code generated by GPT-3. Then, it sends this code to the terminal, and the user confirms this code. Here, the input is the program code generated by GPT-3, and the output is the code suggested to the user.

[1265] Step 5:

[1266] The user checks the code and enters feedback (e.g., "To improve location accuracy, we need the ability to adjust using sensor inputs"). The device sends this feedback to the server, which then sends a new prompt to GPT-3, including this feedback. The input is the user's feedback, and the output is the improved prompt.

[1267] Step 6:

[1268] The server receives the newly generated improved program code from GPT-3 and sends it to the device. The user can review this code again and provide further feedback if necessary. This process is repeated. The input is the improved code generated by GPT-3, and the output is the improved code suggested to the user.

[1269] Step 7:

[1270] Users manage the progress of their projects and, if new issues arise, enter them into the system. The device sends this information to the server and stores it in MongoDB. The input is new issues and progress updates, and the output is updated progress data.

[1271] 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.

[1272] The present invention is a system that utilizes a generative artificial intelligence model to generate program code based on user prompts. It also includes a means for improving the code by incorporating user feedback and managing the progress of the project. It also combines an emotion engine that recognizes the user's emotions to provide support tailored to the user's emotions.

[1273] User Registration and Authentication

[1274] First, the user launches the app and enters their email address and password on the account creation screen. The device sends this information to the server, which stores it in a database. A confirmation email is sent to the user, and the user clicks on a link to activate their account. The user enters their login information and receives a session token, logging them into the platform.

[1275] Creating a Project

[1276] After logging in, a user can create a new project by pressing the "Create a new project" button in the app. The device notifies the server of this operation, and the server generates a new project ID and registers it in the database. Once the project creation is complete, the user is notified and provided with the new project ID.

[1277] Inputting development objectives and problem stories

[1278] The user enters the development objectives and problem story on the project details page. This information is sent from the device to the server, which passes it to the generative AI model. The generative AI model generates the appropriate program code based on the prompts.

[1279] AI-powered suggestions and feedback

[1280] The program code generated by the page-generating AI model is proposed to the user by the server. The user reviews the proposed code, enters feedback, and submits it. The device sends this to the server, which then sends the feedback back to the generative AI model to generate new code. This code is then sent back to the user, who can review it for improvements.

[1281] Project progress management

[1282] Users manage the progress of their projects, inputting task progress and new assignments. The device sends this information to a server, which records the progress in a database. Users ask questions about specific problems, and the server sends the questions to a generative artificial intelligence model to generate answers. The answers are sent back to the user and used as a reference for moving on to the next task.

[1283] Supported by an emotional engine

[1284] Furthermore, the emotion engine recognizes the user's emotions based on the prompts and feedback they provide. The emotion engine records the user's emotional data and uses this data to improve project progress management and generative AI model suggestions. Specifically, if the user is feeling stressed, the system will provide more step-by-step advice.

[1285] Specific examples

[1286] For example, suppose a user inputs a problem story such as "I want to implement a new user authentication system." This information is sent to the server, and a generative AI model generates a basic user authentication code. The user reviews the code and provides feedback on "strengthening security." The server then uses the generative AI model to generate a new code based on the feedback, and sends the improved code back to the user. Furthermore, the emotion engine detects the user's stress level, and the system can provide more detailed explanations and additional documentation, allowing development to proceed while reducing the user's stress.

[1287] In this way, the system of the present invention allows users to progress projects efficiently and creatively, and achieve high-quality results through project progress management and emotional support.

[1288] The processing flow will be explained below.

[1289] User Registration and Authentication

[1290] Step 1:

[1291] The user launches the app and enters their email address and password on the account creation screen.

[1292] Step 2:

[1293] The terminal transmits the input information to the server.

[1294] Step 3:

[1295] The server stores the received information in a database and sends a confirmation email to the user's email address.

[1296] Step 4:

[1297] The user receives a confirmation email and clicks the link in the email to activate their account.

[1298] Step 5:

[1299] The user enters their email address and password on the login screen and clicks the login button.

[1300] Step 6:

[1301] The terminal sends the input information to the server.

[1302] Step 7:

[1303] The server checks the entered authentication information against a database, and if it matches, it generates a session token and returns it to the terminal.

[1304] Step 8:

[1305] The user receives a session token and successfully logs in.

[1306] Creating a Project

[1307] Step 1:

[1308] The user presses the "Create a new project" button within the app.

[1309] Step 2:

[1310] The terminal notifies the server of this operation.

[1311] Step 3:

[1312] The server generates an ID for the new project and registers the project in the database.

[1313] Step 4:

[1314] The server will return a notification of project creation completion and a new project ID to the device.

[1315] Step 5:

[1316] The user will receive a new project ID and the project creation will be complete.

[1317] Inputting development objectives and problem stories

[1318] Step 1:

[1319] The user enters a task story such as "Implementation of a user authentication system" on the project details screen.

[1320] Step 2:

[1321] The device sends the input to the server.

[1322] Step 3:

[1323] The server receives the challenge story and sends it as an input prompt to the generative artificial intelligence model.

[1324] AI-powered suggestions and feedback

[1325] Step 1:

[1326] The server uses a generative artificial intelligence model to generate appropriate code based on the problem story.

[1327] Step 2:

[1328] The server presents the generated code to the user.

[1329] Step 3:

[1330] The user reviews the proposed code.

[1331] Step 4:

[1332] The user enters feedback about the code and presses the submit button.

[1333] Step 5:

[1334] The device sends the feedback content to the server.

[1335] Step 6:

[1336] The server receives the feedback and uses a generative artificial intelligence model to prompt again and generate a new code.

[1337] Step 7:

[1338] The server sends the improved code back to the user.

[1339] Project progress management

[1340] Step 1:

[1341] Users update task progress within the app, entering progress and new assignments.

[1342] Step 2:

[1343] The device sends the input to the server.

[1344] Step 3:

[1345] The server records the progress in a database.

[1346] Step 4:

[1347] The user types in a question about a specific issue and hits the submit button.

[1348] Step 5:

[1349] The device sends the question to the server.

[1350] Step 6:

[1351] The server sends the question to a generative artificial intelligence model, which generates an answer.

[1352] Step 7:

[1353] The server sends the answer from the generative artificial intelligence model back to the user.

[1354] Step 8:

[1355] The user receives the answer and proceeds to the next task.

[1356] Supported by an emotional engine

[1357] Step 1:

[1358] When users enter prompts or feedback, the emotion engine analyzes their facial expressions, tone of voice, and other factors to recognize their emotions.

[1359] Step 2:

[1360] The device transmits the recognized emotion data to the server.

[1361] Step 3:

[1362] The server receives the emotional data and records the user's emotional state.

[1363] Step 4:

[1364] The server sends the emotional data as feedback to the generative artificial intelligence model, which then adjusts the content of the proposed code.

[1365] Step 5:

[1366] The server suggests tailored codes and messages to the user.

[1367] Step 6:

[1368] The user reviews the system's suggestions and provides feedback again if they do not like them.

[1369] Example: Implementing a user authentication system

[1370] Step 1:

[1371] A user enters a problem story stating, "I want to implement a new user authentication system."

[1372] Step 2:

[1373] The device sends input to the server.

[1374] Step 3:

[1375] The server sends the problem story to the generative artificial intelligence model.

[1376] Step 4:

[1377] The server uses a generative artificial intelligence model to generate a basic user authentication code.

[1378] Step 5:

[1379] The user reviews the proposed code.

[1380] Step 6:

[1381] Users provide feedback on "strengthened security."

[1382] Step 7:

[1383] The device sends the feedback content to the server.

[1384] Step 8:

[1385] The server regenerates the code using a generative artificial intelligence model based on the feedback.

[1386] Step 9:

[1387] The server sends the improved code back to the user.

[1388] Step 10:

[1389] The user reviews the proposed code and proceeds to implementation.

[1390] Step 11:

[1391] The server uses an emotion engine to monitor the user's stress level.

[1392] Step 12:

[1393] If the emotion engine recognizes a user's stress level as high, the server instructs the generative artificial intelligence model to provide a more detailed explanation or additional supporting information.

[1394] Step 13:

[1395] The user receives detailed explanations and additional support information, then reviews and implements the code again.

[1396] Example 2

[1397] 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."

[1398] Previous code generation systems focused on generating code based on user prompts and improving it through feedback, but lacked support that took into account the user's emotional state. This resulted in insufficient support when users faced stressful situations or difficult tasks, which could stall project progress. Furthermore, there were limited ways for users to efficiently manage project progress and tasks.

[1399] 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.

[1400] In this invention, the server includes means for generating program code using a generative artificial intelligence model based on prompts entered by the user, means for returning code suggestions for the entered prompts to the user, means for receiving feedback from the user and regenerating program code using the generative artificial intelligence model based on the feedback, means for returning the generated improved program code to the user, means for managing the progress of the project, means for recognizing the user's emotions based on the prompts and feedback entered by the user, and means for adjusting the suggestions and support content of the generative artificial intelligence model based on the emotions, thereby enabling the user to progress through the project efficiently and comfortably.

[1401] A "prompt" is an instruction that a user inputs to a generative artificial intelligence model.

[1402] A "generative artificial intelligence model" is an algorithm or system that generates program code based on user prompts.

[1403] "Program code" means text that contains instructions that a computer can execute.

[1404] "Feedback" means evaluations and requests for corrections made by users to the generated program code.

[1405] "Project progress management" refers to the means and methods for managing the progress and tasks of a project and for moving the project forward efficiently.

[1406] "Emotion recognizer" refers to a system or algorithm that recognizes a user's emotions or stress state based on user input and feedback.

[1407] "Means for adjusting support content" refers to means or methods for taking the user's feelings into consideration and providing appropriate support and supplementary information.

[1408] To implement the present invention, the user, the terminal, and the server must work together. Specific hardware and software for each step will be described in order.

[1409] First, when a user launches the application, they use a device such as a smartphone or PC. The user enters their email address and password on the account creation screen, and the device sends this information to the server. The server stores the received information in a database and sends a confirmation email to the user. The user activates their account by clicking the link in the confirmation email.

[1410] Next, the user enters their email address and password on the login screen, and the device sends the login information to the server. The server verifies the information and, if valid, issues a session token and sends it to the user. The user receives the session token and can log in to the platform.

[1411] After logging in, the user presses the "Create a new project" button, and the device notifies the server of this operation. The server generates a new project ID and saves this information in the database, creating the project. The server then returns the project ID to the user, notifying them that the new project has been created.

[1412] When a user enters the development objectives and problem story on the project details page, the device sends this information to the server, which then passes the received information to a generative artificial intelligence model, which uses powerful data center or cloud-based computing resources to generate the optimal program code for the specified conditions.

[1413] The generated program code is proposed to the user by the server, who then confirms it. If the user provides appropriate feedback, the device sends this feedback to the server. The server then passes the feedback back to the generative artificial intelligence model, which then generates new program code. This process is repeated until the user is satisfied.

[1414] The system always takes the user's emotions into consideration, and the emotion engine intervenes when the user is feeling particularly stressed. The emotion engine analyzes the user's emotions from their input and feedback and provides appropriate support and auxiliary information, allowing the user to proceed with the project more efficiently and comfortably.

[1415] As a concrete example, suppose a user inputs a problem story such as "I want to implement a new user authentication system." This information is sent to the server, and a generative AI model generates a basic user authentication code. The user checks the code and provides feedback on "strengthening security." Based on this feedback, the server uses the generative AI model again to generate an improved code and sends it back to the user. During this process, the emotion engine detects the user's stress, and the system reduces the user's stress by providing detailed explanations and additional documentation.

[1416] Users can also pose questions about specific problems, and the server sends the questions to a generative artificial intelligence model that generates an appropriate answer, which is then sent back to the user to guide them through the next task.

[1417] Thus, the embodiments of the invention allow users to efficiently progress projects and achieve high-quality results, while the support provided by the emotion engine allows users to work more comfortably.

[1418] Examples of prompts include:

[1419] "I want to implement a new user authentication system."

[1420] "I want a database search function to be added."

[1421] "I want the user interface design to be modern."

[1422] The above is a specific embodiment of the present invention.

[1423] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1424] Step 1:

[1425] Create an account

[1426] The user launches the application and enters their email address and password on the account creation screen. The device sends this information to the server. The server stores the received information in a database and sends a confirmation email to the user. The user clicks on the link in the confirmation email to activate their account.

[1427] Input: User's email address, password

[1428] Data processing / calculation: The server stores the information in a database and sends it by email.

[1429] Output: Confirmation email, account activation

[1430] Step 2:

[1431] Log in

[1432] The user enters their email address and password on the login screen. The device sends this information to the server. The server verifies the information and, if valid, issues a session token and sends it to the user. The user receives the session token and logs in to the platform.

[1433] Input: User's email address, password

[1434] Data processing / calculation: Server checks information and generates session token

[1435] Output: Session token, login successful

[1436] Step 3:

[1437] Creating a new project

[1438] After logging in, the user presses the "Create a new project" button. The device notifies the server of this action. The server generates a new project ID and saves it in the database. The server then returns the project ID to the user, notifying them that a new project has been created.

[1439] Input: User clicks Create button

[1440] Data processing / calculation: The server generates a project ID and saves it in the database

[1441] Output: New project ID, project created notification

[1442] Step 4:

[1443] Entering Project Details

[1444] The user enters the development objectives and problem story on the project details page. The device sends this information to the server. The server passes the received information to a generative artificial intelligence model, which uses computing resources to generate program code.

[1445] Input: Development objectives, problem story

[1446] Data processing / calculation: The server passes the information to the generative artificial intelligence model, generating code.

[1447] Output: Generated program code

[1448] Step 5:

[1449] Code Generation and Suggestions

[1450] A generative artificial intelligence model generates program code based on the input prompts, and the server suggests the generated code to the user.

[1451] Input: Program code from a generative artificial intelligence model

[1452] Data processing / calculation: The server transmits the code to the user

[1453] Output: User-suggested program code

[1454] Step 6:

[1455] Feedback and Improvements

[1456] The user reviews the proposed code and enters feedback. The device sends the feedback to the server. The server resubmits the feedback to the generative AI model, which generates new program code. The server then sends the improved code back to the user.

[1457] Input: User feedback

[1458] Data processing / calculation: The server passes the feedback to the generative AI model, and then regenerates it.

[1459] Output: Improved program code

[1460] Step 7:

[1461] Task progress management

[1462] The user manages the progress of the project, inputting task progress and new issues. The device sends the input information to the server, which records the progress in a database.

[1463] Input: Task progress information, new assignments

[1464] Data processing / calculation: The server records the progress in the database

[1465] Output: Updated progress data

[1466] Step 8:

[1467] Questions and Answers

[1468] The user poses a question about a specific problem. The device sends this question to a server. The server sends the question to a generative artificial intelligence model, which generates an answer. The server sends the generated answer to the user.

[1469] Input: User question

[1470] Data processing / calculation: The server sends the question to the generative AI model, which generates the answer.

[1471] Output: The answer provided to the user

[1472] Step 9:

[1473] Emotion assessment and response

[1474] The emotion engine recognizes emotions based on user input and feedback, and the server records the emotion data and uses it to tailor the generative AI model's suggestions and support.

[1475] Input: User input, feedback

[1476] Data processing / calculation: The emotion engine evaluates emotions, and the server records the emotion data.

[1477] Output: Tailored support and feedback

[1478] (Application example 2)

[1479] 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."

[1480] While conventional program code generation systems using generative artificial intelligence models can generate and improve code based on user prompts, they lack a means to recognize user emotions and provide support accordingly, making it difficult to efficiently progress projects while reducing user stress. Furthermore, there are insufficient means for managing project progress in real time and incorporating feedback. To solve these problems, a system with support and real-time management capabilities that respond to user emotions is needed.

[1481] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1482] This invention includes means for generating program code using a generative artificial intelligence model based on prompts entered by a user, means for returning code suggestions for the entered prompts to the user, means for receiving feedback from the user and generating program code again using the generative artificial intelligence model based on the feedback, means for returning the generated improved program code to the user, means for project progress management, means for recognizing user emotion data and adapting project progress management and code suggestions based on the user emotion data, and means for saving the user's task progress in a database and updating the progress status in real time. This allows program code to be generated and improved while taking user emotions into consideration, and makes it possible to more efficiently manage project progress and reflect feedback in real time.

[1483] A "generative artificial intelligence model" is an artificial intelligence technology that generates program code based on prompts entered by the user and optimizes its content.

[1484] A "prompt" is text information that explains the purpose or task the user is entering.

[1485] "Program code" means text that contains instructions necessary for a computer to follow instructions.

[1486] "Feedback" is information indicating the user's evaluation of the generated program code and suggestions for improvement.

[1487] "Emotional data" is emotional information extracted from user input and feedback, and is data that reflects the user's psychological state.

[1488] "Task progress status" is information that indicates the progress of each task in a project.

[1489] A "database" is a system that manages and stores a collection of structured data.

[1490] "Real-time updates" means that input information and processing results are instantly reflected in the system.

[1491] "User" means an individual or organization that uses the system to generate program code or manage projects.

[1492] A "project" is a planned series of tasks or activities designed to achieve a specific purpose.

[1493] The system for implementing this invention allows users to input prompt sentences and generate and improve program code using a generative artificial intelligence model. Specifically, it involves three main elements working together: a server, a terminal, and a user.

[1494] Hardware and Software Configuration

[1495] The server has a generative artificial intelligence model (e.g., OpenAI's GPT-4) and an emotion recognition engine (e.g., Microsoft Azure's Text Analytics) installed. The server receives a prompt from the user, generates program code using the generative artificial intelligence model, and analyzes the user's emotions using the emotion recognition engine.

[1496] The device (smartphone or PC) acts as the user interface. The device sends prompts and feedback entered by the user to the server, and is equipped with an application (for example, a backend built with the Django framework and a frontend built with React) to receive and display the generated program code and emotion recognition results.

[1497] Users operate the device to create projects, enter prompts, provide feedback, and more.

[1498] Data processing and calculation flow

[1499] 1. User Registration and Authentication

[1500] The user enters their email address and password using the terminal application and submits them to the server, which validates the information using Django's user authentication functionality, stores it in a PostgreSQL database, and, if authentication is successful, generates a session token and sends it back to the user.

[1501] 2. Create a project

[1502] When the user clicks the "Create a new project" button, the device notifies the server of this action. The server generates a new project ID and registers it in the database. Once the project creation is complete, the user is notified and provided with the new project ID.

[1503] 3. Entering prompt statements and generating code

[1504] The user enters a prompt on the project details page and sends it to the server, which then passes the prompt to the generative artificial intelligence model to generate program code.

[1505] 4. Suggestions and Feedback

[1506] The generated program code is sent from the server to the terminal and displayed to the user. The user reviews the code and provides feedback. The terminal sends this feedback to the server, which then uses the generative artificial intelligence model to improve the program code.

[1507] 5. Emotional awareness and support

[1508] Emotional data is collected from user feedback and input and analyzed by an emotion recognition engine on the server. Based on the analysis results, if the user's stress level is high, more detailed explanations or additional documentation will be provided.

[1509] Specific examples

[1510] For example, suppose a user enters the prompt, "I want to implement a new quality inspection system." This information is sent to the server, and a generative AI model generates the basic program code for the quality inspection system. The user reviews the code and provides feedback, saying, "I want to improve the inspection accuracy." The server then uses the generative AI model to improve the program code based on the feedback and sends it back to the user. Furthermore, an emotion recognition engine detects the user's level of excitement and provides additional detailed explanations to reduce stress.

[1511] This system allows users to effectively generate and improve program code and efficiently advance projects.

[1512] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1513] Step 1: User Registration and Authentication

[1514] The user enters their email address and password in the terminal application and sends a registration request to the server. The server receives the input and uses Django's user authentication function to store the registration information in a database (PostgreSQL). The server then sends the user a confirmation email, and when the user clicks on the link, the account is activated. When the user enters their login information again, the server authenticates them and, if successful, generates a session token and sends it back to the user.

[1515] Step 2: Create a project

[1516] The user presses the "Create a new project" button in the app, and the device notifies the server of the operation. The server generates a new project ID and registers this information in the database. Once the project creation is complete, the server returns the new project ID to the user and notifies them that the project has been created.

[1517] Step 3: Enter the prompt statement

[1518] The user enters a prompt on the project details page, and the device sends this information to the server. The entered prompt is passed to a generative artificial intelligence model (OpenAI GPT-4). The server inputs the prompt into the AI ​​model and instructs it to generate program code. The generated program code is temporarily stored on the server.

[1519] Step 4: Code suggestions and feedback

[1520] The server sends the generated program code to the terminal, which displays it to the user. The user checks the code and enters feedback if necessary. The feedback is sent from the terminal to the server. The server passes this feedback back to the generative artificial intelligence model, instructing it to generate improved program code.

[1521] Step 5: Submitting the improved code

[1522] The server then sends the improved program code generated by the generative artificial intelligence model back to the device, which then displays the improved program code to the user and repeats the process until feedback is received. With each iteration of the improvement, the server saves the progress record in the database and updates the project's progress.

[1523] Step 6: Emotional awareness and support

[1524] The device sends the feedback and prompts entered by the user to the server, which then uses an emotion recognition engine (Microsoft Azure Text Analytics) to analyze the user's emotional data. Based on the analysis results, if the user's stress level is high, the server generates emotionally appropriate support information (e.g., step-by-step guides or additional documentation) and provides it to the user via the device.

[1525] Step 7: Real-time updates on task progress

[1526] Users operate their devices to input task progress, and the devices send that information to the server, which then stores the task progress in a database and updates it in real time, allowing users to always have the most up-to-date information on the progress of the entire project.

[1527] 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.

[1528] 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.

[1529] 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.

[1530] [Fourth embodiment]

[1531] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1532] 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.

[1533] 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).

[1534] 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.

[1535] 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.

[1536] 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).

[1537] 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.

[1538] 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.

[1539] 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.

[1540] 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.

[1541] 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.

[1542] 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.

[1543] 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."

[1544] The present invention is a system that generates program code by utilizing a generative artificial intelligence model based on prompts entered by a user. Specific embodiments of the "Aibou AI" system are described below.

[1545] User Registration and Authentication

[1546] First, a user creates an account to use the system. At this time, the user enters authentication information such as an email address and password. The device sends this information to the server. The server stores the entered information in a database and sends a confirmation email to the user. When the user clicks the link in the confirmation email, the account is activated. The user can log in to the platform by entering their authentication information on the login screen and receiving a session token.

[1547] Creating a Project

[1548] After logging in, the user can create a new project. When the user presses the "Create a new project" button, the device notifies the server of the operation. The server generates an ID for the new project and registers it in the database. When the project creation is complete, the user is notified.

[1549] Inputting development objectives and problem stories

[1550] Next, the user enters the development objectives and problem story on the project details page. This information is sent from the device to the server, which passes it on to the generative AI model, which then generates the appropriate program code based on the prompts.

[1551] AI-powered suggestions and feedback

[1552] The program code generated by the generative AI model is proposed to the user by the server. The user can review the proposed code and enter feedback. This feedback may include improvements to the code or features they would like to add. The device sends this feedback to the server, which then instructs the generative AI model to prompt again. The generative AI model then generates new code, which is proposed again. By repeating this process, the user can obtain high-quality program code.

[1553] Project progress management

[1554] Users can manage the progress of projects and input task progress and new assignments. The device sends this information to the server, which records the progress in a database. Users can also pose questions about specific problems, which the server sends to the generative AI model. The answers from the generative AI are sent back to the user and used as a reference for moving on to the next task.

[1555] Specific examples

[1556] For example, suppose a user inputs a problem story such as "I want to implement a new user authentication system." This information is sent to the server, and a basic user authentication code is generated by the generative AI model. The user checks this code and provides feedback on "strengthening security." Based on this feedback, the server uses the generative AI model to generate a new code with appropriate security features and send it back to the user. In this way, the process of implementing a high-quality program through dialogue between the user and AI is repeated.

[1557] The system allows users to efficiently and creatively progress projects, achieving high productivity and high-quality results in the development of computer programs.

[1558] The processing flow will be explained below.

[1559] User Registration and Authentication

[1560] Step 1:

[1561] The user launches the app and enters their email address and password on the account creation screen.

[1562] Step 2:

[1563] The terminal transmits the input information to the server.

[1564] Step 3:

[1565] The server stores the received information in a database and sends a confirmation email to the user's email address.

[1566] Step 4:

[1567] The user receives a confirmation email and clicks the link in the email to activate their account.

[1568] Step 5:

[1569] The user enters their email address and password on the login screen and clicks the login button.

[1570] Step 6:

[1571] The terminal sends the input information to the server.

[1572] Step 7:

[1573] The server checks the entered authentication information against a database, and if it matches, it generates a session token and returns it to the terminal.

[1574] Step 8:

[1575] The user receives a session token and successfully logs in.

[1576] Creating a Project

[1577] Step 1:

[1578] The user presses the "Create a new project" button within the app.

[1579] Step 2:

[1580] The terminal notifies the server of this operation.

[1581] Step 3:

[1582] The server generates an ID for the new project and registers the project in the database.

[1583] Step 4:

[1584] The server will return a notification of project creation completion and a new project ID to the device.

[1585] Step 5:

[1586] The user will receive a new project ID and the project creation will be complete.

[1587] Inputting development objectives and problem stories

[1588] Step 1:

[1589] The user enters a task story such as "Implementation of a user authentication system" on the project details screen.

[1590] Step 2:

[1591] The device sends the input to the server.

[1592] Step 3:

[1593] The server receives the challenge story and sends it as an input prompt to the generative artificial intelligence model.

[1594] AI-powered suggestions and feedback

[1595] Step 1:

[1596] The server uses a generative artificial intelligence model to generate appropriate code based on the problem story and suggests it to the user.

[1597] Step 2:

[1598] The user reviews the proposed code.

[1599] Step 3:

[1600] The user enters feedback about the code and presses the submit button.

[1601] Step 4:

[1602] The device sends the feedback content to the server.

[1603] Step 5:

[1604] The server receives the feedback and prompts the generative artificial intelligence model again to generate new code.

[1605] Step 6:

[1606] The server sends the improved code back to the user.

[1607] Project progress management

[1608] Step 1:

[1609] Users update task progress within the app, entering progress and new assignments.

[1610] Step 2:

[1611] The device sends the input to the server.

[1612] Step 3:

[1613] The server records the progress in a database.

[1614] Step 4:

[1615] The user types in a question about a specific issue and hits the submit button.

[1616] Step 5:

[1617] The device sends the question to the server.

[1618] Step 6:

[1619] The server sends the question to a generative artificial intelligence model, which generates an answer.

[1620] Step 7:

[1621] The server sends the AI's answer back to the user.

[1622] Step 8:

[1623] The user receives the answer and proceeds to the next task.

[1624] Example: Implementing a user authentication system

[1625] Step 1:

[1626] A user enters a problem story stating, "I want to implement a new user authentication system."

[1627] Step 2:

[1628] The device sends input to the server.

[1629] Step 3:

[1630] The server sends the problem story to the generative artificial intelligence model.

[1631] Step 4:

[1632] The server uses a generative artificial intelligence model to generate a basic user authentication code.

[1633] Step 5:

[1634] The user reviews the proposed code.

[1635] Step 6:

[1636] Users provide feedback on "strengthened security."

[1637] Step 7:

[1638] The device sends the feedback content to the server.

[1639] Step 8:

[1640] The server regenerates the code using a generative artificial intelligence model based on the feedback.

[1641] Step 9:

[1642] The server sends the improved code back to the user.

[1643] Step 10:

[1644] The user reviews the proposed code and proceeds to implementation.

[1645] Example 1

[1646] 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."

[1647] In conventional program code generation systems, when users provide feedback on generated code, the feedback is not reflected promptly, reducing the efficiency of generating high-quality programs. Additionally, creating new projects and managing projects requires a lot of effort, reducing productivity. Furthermore, when users have questions about specific technical issues, there are limited ways to receive quick and accurate answers, which can delay project progress.

[1648] 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.

[1649] In this invention, the server includes: means for generating program code using a generative artificial intelligence model based on prompts entered by a user; means for returning code suggestions for the entered prompts to the user; means for receiving feedback from the user and regenerating program code using the generative artificial intelligence model based on the feedback; means for returning the generated improved program code to the user; means for managing project progress; means for allowing the user to input project progress and new challenges; means for recording the input information in a database; means for the user to enter questions about specific problems and send them to the generative artificial intelligence model; means for providing the user with answers from the generative artificial intelligence model; means for the user to create and authenticate an account; means for verifying the entered authentication information in the database and generating a security token if successful; and means for notifying the user of authentication completion. This enables fast and efficient program code generation and feedback integration, simplifies project management, and provides fast and accurate answers to specific technical problems.

[1650] "User" means an individual or organization that uses the system to generate program code or manage projects.

[1651] A "prompt" is an instruction or question that a user enters into a generative artificial intelligence model, which then generates code based on that information.

[1652] "Generative artificial intelligence model" refers to an artificial intelligence technique that generates program code based on given prompts.

[1653] "Program Code" means the executable scripts or snippets of software that a generative artificial intelligence model generates based on prompts.

[1654] "Feedback" refers to requests for corrections or suggestions for improvements made by users to the generated program code.

[1655] A "security token" is a secure credential used by an authenticated user during a session to secure access rights.

[1656] A "project" is an individual development task or goal that a user creates within the system and manages its progress.

[1657] "Database" means a digital record system for storing and managing user information, project information, feedback, etc. within the system.

[1658] "Server" refers to a central computing device or service that processes user requests, generates code using generative artificial intelligence models, and performs database operations.

[1659] "Authentication information" refers to information such as an email address and password that a user uses to log in to a system.

[1660] A "session token" is a unique string used to identify a session, issued after a user has been successfully authenticated.

[1661] A "question" is a specific technical problem or question that a user enters into the system to receive an answer from the generative artificial intelligence model.

[1662] The present invention is a system that generates program code using a generative artificial intelligence model based on prompts entered by a user. This system operates through the mutual cooperation of a server, a terminal, and a user.

[1663] User Registration and Authentication

[1664] First, a user creates an account to use the system. The user enters their email address and password, which the device sends to the server. The server saves the entered information in a database and automatically sends a confirmation email to the user. When the user clicks the link in the confirmation email, the server activates the account. The user enters their email address and password on the login screen, and if the server successfully authenticates them, it issues a session token.

[1665] Creating a Project

[1666] After logging in, the user presses the "Create a new project" button, and the device notifies the server of the operation. The server generates an ID for the new project and registers it in the database. Once the project creation is complete, the server notifies the user.

[1667] Inputting development objectives and problem stories

[1668] The user enters the development objectives and problem story on the project details page. The device sends this information to the server, which passes it to the generative AI model. The generative AI model generates the appropriate program code based on the prompts.

[1669] AI-powered suggestions and feedback

[1670] The program code generated by the generative AI model is proposed to the user by the server. The user reviews the proposed code and enters feedback on areas for improvement or features they would like to add. The device then sends this feedback to the server, which then instructs the generative AI model to reprompt again. By repeating this process, the user obtains high-quality program code.

[1671] Project progress management

[1672] Users input the progress of tasks and new challenges within a project. The device sends this information to the server, which records it in a database. Users can also input questions about specific problems, which the device sends to the server, which passes them on to the generative AI model. The server provides the answer from the generative AI model to the user, and uses it as a reference for the next task.

[1673] Specific examples

[1674] For example, suppose a user inputs a problem story such as "I want to implement a new user authentication system." This information is sent to the server, and a basic user authentication code is generated by a generative artificial intelligence model. The user reviews this code and provides feedback such as "strengthen security." Based on this feedback, the server uses the generative artificial intelligence model again to generate code with appropriate security functions. This process is repeated until a high-quality program is implemented through dialogue between the user and AI.

[1675] An example of a prompt to be input to the generative AI model is "Please implement a user authentication system using JWT in Ruby on Rails." Users can review the program code generated based on this prompt and provide feedback to obtain higher quality code.

[1676] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1677] Step 1: User enters account information

[1678] The user enters their email address and password on the system's account creation screen. The entered authentication information is sent to the server by the terminal. The server stores the received authentication information in a database and automatically sends a confirmation email. Data verification is performed to ensure that the email address has been entered correctly, and the confirmation email is sent.

[1679] Input: Email address, password

[1680] Output: Send confirmation email, save information to database

[1681] Step 2: User clicks on the link in the confirmation email

[1682] The user clicks on the link in the confirmation email they receive, which triggers a process on the server to activate the account and update the user's status in the database.

[1683] Input: Click on the link in the confirmation email

[1684] Output: Account activated, database updated

[1685] Step 3: User enters login information

[1686] The user enters their email address and password on the login screen. The information is sent by the device to the server, which checks it against the authentication information in its database. If there is a match, the server issues a session token and sends it back to the user.

[1687] Input: Email address, password

[1688] Output: Session token issued, user authenticated

[1689] Step 4: User creates a new project

[1690] The user presses the "Create a new project" button on the project creation screen. The device notifies the server of this operation, and the server generates an ID for the new project and registers it in the database. The user is notified that the project has been created.

[1691] Input: Project creation operation

[1692] Output: Project ID generation, project registration in the database, and notification of completion

[1693] Step 5: User enters project details

[1694] The user enters the development objectives and problem story on the project details page. The data is sent to the server by the terminal, and the server passes it to the generative AI model. The generative AI model generates program code based on the prompts.

[1695] Input: Issue story, development objectives

[1696] Output: Sending prompts to a generative artificial intelligence model, generating program code

[1697] Step 6: The server presents the generated code to the user

[1698] The server proposes program code generated by the generative artificial intelligence model to the user, who then reviews the code and provides feedback.

[1699] Input: Program code generated by a generative artificial intelligence model

[1700] Output: Code suggestions to user, waiting for feedback

[1701] Step 7: Users submit feedback

[1702] Users review the proposed program code and provide feedback on improvements and additional features from their devices to the server, which then passes this feedback back to the generative artificial intelligence model as prompts.

[1703] Input: Feedback

[1704] Output: Reprompt for generative artificial intelligence models

[1705] Step 8: The server generates and suggests improved code

[1706] The generative artificial intelligence model generates improved program code based on the new feedback, which the server then proposes to the user again, and this process is repeated until the user is satisfied.

[1707] Input: Improved code generation using generative artificial intelligence models

[1708] Output: Suggested code improvements to the user

[1709] Step 9: Let users manage project progress

[1710] Users enter task progress and new issues on the project management screen, and the information is sent from the device to the server, which records this information in a database.

[1711] Input: Task progress, new assignments

[1712] Output: Record information in a database

[1713] Step 10: User enters question about specific technical issue

[1714] Users enter questions about specific technical issues and send them from their devices to a server, which passes the questions to a generative artificial intelligence model to obtain answers, which the server then provides to the user.

[1715] Input: Technical question

[1716] Output: Answer from the generative artificial intelligence model, providing the answer to the user

[1717] Through the above processing steps, the system can provide users with efficient program generation and project management.

[1718] (Application example 1)

[1719] 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."

[1720] Automation and efficiency are key challenges in modern factories. In particular, the operating programs for robots and other machines operating in factories are often highly complex and require specialized engineers, resulting in significant time and cost. Furthermore, improving and adapting existing programs is not easy, and the process of incorporating feedback is cumbersome. Given these circumstances, a system is needed to quickly and efficiently generate and improve the operating programs for machines in factories.

[1721] 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.

[1722] In this invention, the server includes means for generating program code using a generative artificial intelligence model based on prompts input by a user, means for returning code suggestions for the input prompts to the user, means for receiving feedback from the user and generating program code again using the generative artificial intelligence model based on the feedback, means for returning the generated improved program code to the user, means for managing the progress of the project, and means for generating operating programs for machines operating in a factory and improving the operation of the machines, thereby enabling users to easily generate and improve operating programs for machines.

[1723] A "generative artificial intelligence model" is a type of artificial intelligence algorithm that can generate new data or program code based on input data.

[1724] A "prompt" is a sentence or piece of text that indicates an instruction or request that the user enters.

[1725] "Program code" refers to a set of instructions for controlling machine operations, such as a computer-executable binary file or script.

[1726] "Feedback" refers to opinions and requests for improvement from users regarding the generated program code.

[1727] "Factory machinery" refers to robots and other automated devices used to perform production lines and automated tasks.

[1728] A "session token" is a temporary identifier used to keep a user authenticated to a system.

[1729] A "database" is a system that efficiently stores large amounts of data and enables it to be searched and processed.

[1730] "Project management" refers to the overall process of planning, executing, and monitoring work to achieve project goals.

[1731] This invention is a system for efficiently generating and improving the operating programs of machines operating in a factory. This system mainly uses a server, a terminal (smartphone), and a generative artificial intelligence model.

[1732] composition

[1733] Hardware

[1734] Device: iOS or Android smartphone.

[1735] Server: Cloud-based server.

[1736] Factory machinery: Robots and other automated equipment.

[1737] software

[1738] Front-end: Smartphone application using React Native.

[1739] Backend: Server-side application using Node.js.

[1740] Database: MongoDB.

[1741] Generative artificial intelligence model: OpenAI GPT-3.

[1742] Authentication: Firebase Authentication.

[1743] Processing flow

[1744] 1. User Registration and Authentication:

[1745] The user enters their email address and password using a terminal. This information is authenticated using Firebase Authentication, and if authentication is successful, the user information is stored in MongoDB. If successful, a session token is generated and the user is notified that authentication has been completed.

[1746] 2. Create a project:

[1747] A user presses the "Create a new project" button to create a new project. This operation is notified to the Node.js server, which generates a new project ID and registers it in MongoDB. The user is notified that the project creation is complete.

[1748] 3. Enter the assignment story:

[1749] Users enter their assignment story on the project details page, and this information is sent from the device to the server, which then sends prompts to the generative artificial intelligence model (GPT-3).

[1750] 4. AI Code Generation:

[1751] GPT-3 generates program code based on the prompts entered, and the code is sent back to the user via a server.

[1752] 5. Feedback and Improvements:

[1753] The user reviews the proposed code and provides feedback, which is then sent back to GPT-3 via the server, which generates a new code and sends the improved code back to the user.

[1754] 6. Project Progress Management:

[1755] Users can manage the progress of their projects, input task progress and new challenges, and store this information on the server. Users can also pose questions about specific problems and receive answers from GPT-3.

[1756] This system allows users to efficiently generate and improve operating programs for machines operating in factories. For example, if a user inputs, "I want to implement a robot operation that places part A in a specified position," GPT-3 generates program code based on that. Furthermore, if the user inputs feedback such as, "To improve position accuracy, we need a function to adjust using sensor input," GPT-3 generates improved code based on this feedback.

[1757] Example prompt sentence:

[1758] Generate code like this: "I want to implement a robot that places part A in a predetermined position. I need to adjust the position using sensor input to improve accuracy."

[1759] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1760] Step 1:

[1761] The user creates an account and enters authentication information. The device sends this information (email address, password) to the server. The server verifies this information using Firebase Authentication and generates a session token if authentication is successful. Next, a notification that authentication is complete is sent. The input is the user's authentication information, and the output is a session token and a notification that authentication is complete.

[1762] Step 2:

[1763] The user presses the "Create a new project" button. This operation is notified to the server from the terminal. The server generates a new project ID and registers this project ID and related information in MongoDB. When the project creation is complete, the terminal is notified. The input is a project creation request, and the output is the new project ID and its notification.

[1764] Step 3:

[1765] The user goes to the project details page and inputs the problem story (for example, "I want to implement a robot behavior that places part A in a designated position"). The device sends this input to the server. The server then sends this prompt to the API of the generative artificial intelligence model (GPT-3). The input is the problem story, and the output is the prompt for generation.

[1766] Step 4:

[1767] The server receives the program code generated by GPT-3. Then, it sends this code to the terminal, and the user confirms this code. Here, the input is the program code generated by GPT-3, and the output is the code suggested to the user.

[1768] Step 5:

[1769] The user checks the code and enters feedback (e.g., "To improve location accuracy, we need the ability to adjust using sensor inputs"). The device sends this feedback to the server, which then sends a new prompt to GPT-3, including this feedback. The input is the user's feedback, and the output is the improved prompt.

[1770] Step 6:

[1771] The server receives the newly generated improved program code from GPT-3 and sends it to the device. The user can review this code again and provide further feedback if necessary. This process is repeated. The input is the improved code generated by GPT-3, and the output is the improved code suggested to the user.

[1772] Step 7:

[1773] Users manage the progress of their projects and, if new issues arise, enter them into the system. The device sends this information to the server and stores it in MongoDB. The input is new issues and progress updates, and the output is updated progress data.

[1774] 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.

[1775] The present invention is a system that utilizes a generative artificial intelligence model to generate program code based on user prompts. It also includes a means for improving the code by incorporating user feedback and managing the progress of the project. It also combines an emotion engine that recognizes the user's emotions to provide support tailored to the user's emotions.

[1776] User Registration and Authentication

[1777] First, the user launches the app and enters their email address and password on the account creation screen. The device sends this information to the server, which stores it in a database. A confirmation email is sent to the user, and the user clicks on a link to activate their account. The user enters their login information and receives a session token, logging them into the platform.

[1778] Creating a Project

[1779] After logging in, a user can create a new project by pressing the "Create a new project" button in the app. The device notifies the server of this operation, and the server generates a new project ID and registers it in the database. Once the project creation is complete, the user is notified and provided with the new project ID.

[1780] Inputting development objectives and problem stories

[1781] The user enters the development objectives and problem story on the project details page. This information is sent from the device to the server, which passes it to the generative AI model. The generative AI model generates the appropriate program code based on the prompts.

[1782] AI-powered suggestions and feedback

[1783] The program code generated by the page-generating AI model is proposed to the user by the server. The user reviews the proposed code, enters feedback, and submits it. The device sends this to the server, which then sends the feedback back to the generative AI model to generate new code. This code is then sent back to the user, who can review it for improvements.

[1784] Project progress management

[1785] Users manage the progress of their projects, inputting task progress and new assignments. The device sends this information to a server, which records the progress in a database. Users ask questions about specific problems, and the server sends the questions to a generative artificial intelligence model to generate answers. The answers are sent back to the user and used as a reference for moving on to the next task.

[1786] Supported by an emotional engine

[1787] Furthermore, the emotion engine recognizes the user's emotions based on the prompts and feedback they provide. The emotion engine records the user's emotional data and uses this data to improve project progress management and generative AI model suggestions. Specifically, if the user is feeling stressed, the system will provide more step-by-step advice.

[1788] Specific examples

[1789] For example, suppose a user inputs a problem story such as "I want to implement a new user authentication system." This information is sent to the server, and a generative AI model generates a basic user authentication code. The user reviews the code and provides feedback on "strengthening security." The server then uses the generative AI model to generate a new code based on the feedback, and sends the improved code back to the user. Furthermore, the emotion engine detects the user's stress level, and the system can provide more detailed explanations and additional documentation, allowing development to proceed while reducing the user's stress.

[1790] In this way, the system of the present invention allows users to progress projects efficiently and creatively, and achieve high-quality results through project progress management and emotional support.

[1791] The processing flow will be explained below.

[1792] User Registration and Authentication

[1793] Step 1:

[1794] The user launches the app and enters their email address and password on the account creation screen.

[1795] Step 2:

[1796] The terminal transmits the input information to the server.

[1797] Step 3:

[1798] The server stores the received information in a database and sends a confirmation email to the user's email address.

[1799] Step 4:

[1800] The user receives a confirmation email and clicks the link in the email to activate their account.

[1801] Step 5:

[1802] The user enters their email address and password on the login screen and clicks the login button.

[1803] Step 6:

[1804] The terminal sends the input information to the server.

[1805] Step 7:

[1806] The server checks the entered authentication information against a database, and if it matches, it generates a session token and returns it to the terminal.

[1807] Step 8:

[1808] The user receives a session token and successfully logs in.

[1809] Creating a Project

[1810] Step 1:

[1811] The user presses the "Create a new project" button within the app.

[1812] Step 2:

[1813] The terminal notifies the server of this operation.

[1814] Step 3:

[1815] The server generates an ID for the new project and registers the project in the database.

[1816] Step 4:

[1817] The server will return a notification of project creation completion and a new project ID to the device.

[1818] Step 5:

[1819] The user will receive a new project ID and the project creation will be complete.

[1820] Inputting development objectives and problem stories

[1821] Step 1:

[1822] The user enters a task story such as "Implementation of a user authentication system" on the project details screen.

[1823] Step 2:

[1824] The device sends the input to the server.

[1825] Step 3:

[1826] The server receives the challenge story and sends it as an input prompt to the generative artificial intelligence model.

[1827] AI-powered suggestions and feedback

[1828] Step 1:

[1829] The server uses a generative artificial intelligence model to generate appropriate code based on the problem story.

[1830] Step 2:

[1831] The server presents the generated code to the user.

[1832] Step 3:

[1833] The user reviews the proposed code.

[1834] Step 4:

[1835] The user enters feedback about the code and presses the submit button.

[1836] Step 5:

[1837] The device sends the feedback content to the server.

[1838] Step 6:

[1839] The server receives the feedback and uses a generative artificial intelligence model to prompt again and generate a new code.

[1840] Step 7:

[1841] The server sends the improved code back to the user.

[1842] Project progress management

[1843] Step 1:

[1844] Users update task progress within the app, entering progress and new assignments.

[1845] Step 2:

[1846] The device sends the input to the server.

[1847] Step 3:

[1848] The server records the progress in a database.

[1849] Step 4:

[1850] The user types in a question about a specific issue and hits the submit button.

[1851] Step 5:

[1852] The device sends the question to the server.

[1853] Step 6:

[1854] The server sends the question to a generative artificial intelligence model, which generates an answer.

[1855] Step 7:

[1856] The server sends the answer from the generative artificial intelligence model back to the user.

[1857] Step 8:

[1858] The user receives the answer and proceeds to the next task.

[1859] Supported by an emotional engine

[1860] Step 1:

[1861] When users enter prompts or feedback, the emotion engine analyzes their facial expressions, tone of voice, and other factors to recognize their emotions.

[1862] Step 2:

[1863] The device transmits the recognized emotion data to the server.

[1864] Step 3:

[1865] The server receives the emotional data and records the user's emotional state.

[1866] Step 4:

[1867] The server sends the emotional data as feedback to the generative artificial intelligence model, which then adjusts the content of the proposed code.

[1868] Step 5:

[1869] The server suggests tailored codes and messages to the user.

[1870] Step 6:

[1871] The user reviews the system's suggestions and provides feedback again if they do not like them.

[1872] Example: Implementing a user authentication system

[1873] Step 1:

[1874] A user enters a problem story stating, "I want to implement a new user authentication system."

[1875] Step 2:

[1876] The device sends input to the server.

[1877] Step 3:

[1878] The server sends the problem story to the generative artificial intelligence model.

[1879] Step 4:

[1880] The server uses a generative artificial intelligence model to generate a basic user authentication code.

[1881] Step 5:

[1882] The user reviews the proposed code.

[1883] Step 6:

[1884] Users provide feedback on "strengthened security."

[1885] Step 7:

[1886] The device sends the feedback content to the server.

[1887] Step 8:

[1888] The server regenerates the code using a generative artificial intelligence model based on the feedback.

[1889] Step 9:

[1890] The server sends the improved code back to the user.

[1891] Step 10:

[1892] The user reviews the proposed code and proceeds to implementation.

[1893] Step 11:

[1894] The server uses an emotion engine to monitor the user's stress level.

[1895] Step 12:

[1896] If the emotion engine recognizes a user's stress level as high, the server instructs the generative artificial intelligence model to provide a more detailed explanation or additional supporting information.

[1897] Step 13:

[1898] The user receives detailed explanations and additional support information, then reviews and implements the code again.

[1899] Example 2

[1900] 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."

[1901] Previous code generation systems focused on generating code based on user prompts and improving it through feedback, but lacked support that took into account the user's emotional state. This resulted in insufficient support when users faced stressful situations or difficult tasks, which could stall project progress. Furthermore, there were limited ways for users to efficiently manage project progress and tasks.

[1902] 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.

[1903] In this invention, the server includes means for generating program code using a generative artificial intelligence model based on prompts entered by the user, means for returning code suggestions for the entered prompts to the user, means for receiving feedback from the user and regenerating program code using the generative artificial intelligence model based on the feedback, means for returning the generated improved program code to the user, means for managing the progress of the project, means for recognizing the user's emotions based on the prompts and feedback entered by the user, and means for adjusting the suggestions and support content of the generative artificial intelligence model based on the emotions, thereby enabling the user to progress through the project efficiently and comfortably.

[1904] A "prompt" is an instruction that a user inputs to a generative artificial intelligence model.

[1905] A "generative artificial intelligence model" is an algorithm or system that generates program code based on user prompts.

[1906] "Program code" means text that contains instructions that a computer can execute.

[1907] "Feedback" means evaluations and requests for corrections made by users to the generated program code.

[1908] "Project progress management" refers to the means and methods for managing the progress and tasks of a project and for moving the project forward efficiently.

[1909] "Emotion recognizer" refers to a system or algorithm that recognizes a user's emotions or stress state based on user input and feedback.

[1910] "Means for adjusting support content" refers to means or methods for taking the user's feelings into consideration and providing appropriate support and supplementary information.

[1911] To implement the present invention, the user, the terminal, and the server must work together. Specific hardware and software for each step will be described in order.

[1912] First, when a user launches the application, they use a device such as a smartphone or PC. The user enters their email address and password on the account creation screen, and the device sends this information to the server. The server stores the received information in a database and sends a confirmation email to the user. The user activates their account by clicking the link in the confirmation email.

[1913] Next, the user enters their email address and password on the login screen, and the device sends the login information to the server. The server verifies the information and, if valid, issues a session token and sends it to the user. The user receives the session token and can log in to the platform.

[1914] After logging in, the user presses the "Create a new project" button, and the device notifies the server of this operation. The server generates a new project ID and saves this information in the database, creating the project. The server then returns the project ID to the user, notifying them that the new project has been created.

[1915] When a user enters the development objectives and problem story on the project details page, the device sends this information to the server, which then passes the received information to a generative artificial intelligence model, which uses powerful data center or cloud-based computing resources to generate the optimal program code for the specified conditions.

[1916] The generated program code is proposed to the user by the server, who then confirms it. If the user provides appropriate feedback, the device sends this feedback to the server. The server then passes the feedback back to the generative artificial intelligence model, which then generates new program code. This process is repeated until the user is satisfied.

[1917] The system always takes the user's emotions into consideration, and the emotion engine intervenes when the user is feeling particularly stressed. The emotion engine analyzes the user's emotions from their input and feedback and provides appropriate support and auxiliary information, allowing the user to proceed with the project more efficiently and comfortably.

[1918] As a concrete example, suppose a user inputs a problem story such as "I want to implement a new user authentication system." This information is sent to the server, and a generative AI model generates a basic user authentication code. The user checks the code and provides feedback on "strengthening security." Based on this feedback, the server uses the generative AI model again to generate an improved code and sends it back to the user. During this process, the emotion engine detects the user's stress, and the system reduces the user's stress by providing detailed explanations and additional documentation.

[1919] Users can also pose questions about specific problems, and the server sends the questions to a generative artificial intelligence model that generates an appropriate answer, which is then sent back to the user to guide them through the next task.

[1920] Thus, the embodiments of the invention allow users to efficiently progress projects and achieve high-quality results, while the support provided by the emotion engine allows users to work more comfortably.

[1921] Examples of prompts include:

[1922] "I want to implement a new user authentication system."

[1923] "I want a database search function to be added."

[1924] "I want the user interface design to be modern."

[1925] The above is a specific embodiment of the present invention.

[1926] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1927] Step 1:

[1928] Create an account

[1929] The user launches the application and enters their email address and password on the account creation screen. The device sends this information to the server. The server stores the received information in a database and sends a confirmation email to the user. The user clicks on the link in the confirmation email to activate their account.

[1930] Input: User's email address, password

[1931] Data processing / calculation: The server stores the information in a database and sends it by email.

[1932] Output: Confirmation email, account activation

[1933] Step 2:

[1934] Log in

[1935] The user enters their email address and password on the login screen. The device sends this information to the server. The server verifies the information and, if valid, issues a session token and sends it to the user. The user receives the session token and logs in to the platform.

[1936] Input: User's email address, password

[1937] Data processing / calculation: Server checks information and generates session token

[1938] Output: Session token, login successful

[1939] Step 3:

[1940] Creating a new project

[1941] After logging in, the user presses the "Create a new project" button. The device notifies the server of this action. The server generates a new project ID and saves it in the database. The server then returns the project ID to the user, notifying them that a new project has been created.

[1942] Input: User clicks Create button

[1943] Data processing / calculation: The server generates a project ID and saves it in the database

[1944] Output: New project ID, project created notification

[1945] Step 4:

[1946] Entering Project Details

[1947] The user enters the development objectives and problem story on the project details page. The device sends this information to the server. The server passes the received information to a generative artificial intelligence model, which uses computing resources to generate program code.

[1948] Input: Development objectives, problem story

[1949] Data processing / calculation: The server passes the information to the generative artificial intelligence model, generating code.

[1950] Output: Generated program code

[1951] Step 5:

[1952] Code Generation and Suggestions

[1953] A generative artificial intelligence model generates program code based on the input prompts, and the server suggests the generated code to the user.

[1954] Input: Program code from a generative artificial intelligence model

[1955] Data processing / calculation: The server transmits the code to the user

[1956] Output: User-suggested program code

[1957] Step 6:

[1958] Feedback and Improvements

[1959] The user reviews the proposed code and enters feedback. The device sends the feedback to the server. The server resubmits the feedback to the generative AI model, which generates new program code. The server then sends the improved code back to the user.

[1960] Input: User feedback

[1961] Data processing / calculation: The server passes the feedback to the generative AI model, and then regenerates it.

[1962] Output: Improved program code

[1963] Step 7:

[1964] Task progress management

[1965] The user manages the progress of the project, inputting task progress and new issues. The device sends the input information to the server, which records the progress in a database.

[1966] Input: Task progress information, new assignments

[1967] Data processing / calculation: The server records the progress in the database

[1968] Output: Updated progress data

[1969] Step 8:

[1970] Questions and Answers

[1971] The user poses a question about a specific problem. The device sends this question to a server. The server sends the question to a generative artificial intelligence model, which generates an answer. The server sends the generated answer to the user.

[1972] Input: User question

[1973] Data processing / calculation: The server sends the question to the generative AI model, which generates the answer.

[1974] Output: The answer provided to the user

[1975] Step 9:

[1976] Emotion assessment and response

[1977] The emotion engine recognizes emotions based on user input and feedback, and the server records the emotion data and uses it to tailor the generative AI model's suggestions and support.

[1978] Input: User input, feedback

[1979] Data processing / calculation: The emotion engine evaluates emotions, and the server records the emotion data.

[1980] Output: Tailored support and feedback

[1981] (Application example 2)

[1982] 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."

[1983] While conventional program code generation systems using generative artificial intelligence models can generate and improve code based on user prompts, they lack a means to recognize user emotions and provide support accordingly, making it difficult to efficiently progress projects while reducing user stress. Furthermore, there are insufficient means for managing project progress in real time and incorporating feedback. To solve these problems, a system with support and real-time management capabilities that respond to user emotions is needed.

[1984] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1985] This invention includes means for generating program code using a generative artificial intelligence model based on prompts entered by a user, means for returning code suggestions for the entered prompts to the user, means for receiving feedback from the user and generating program code again using the generative artificial intelligence model based on the feedback, means for returning the generated improved program code to the user, means for project progress management, means for recognizing user emotion data and adapting project progress management and code suggestions based on the user emotion data, and means for saving the user's task progress in a database and updating the progress status in real time. This allows program code to be generated and improved while taking user emotions into consideration, and makes it possible to more efficiently manage project progress and reflect feedback in real time.

[1986] A "generative artificial intelligence model" is an artificial intelligence technology that generates program code based on prompts entered by the user and optimizes its content.

[1987] A "prompt" is text information that explains the purpose or task the user is entering.

[1988] "Program code" means text that contains instructions necessary for a computer to follow instructions.

[1989] "Feedback" is information indicating the user's evaluation of the generated program code and suggestions for improvement.

[1990] "Emotional data" is emotional information extracted from user input and feedback, and is data that reflects the user's psychological state.

[1991] "Task progress status" is information that indicates the progress of each task in a project.

[1992] A "database" is a system that manages and stores a collection of structured data.

[1993] "Real-time updates" means that input information and processing results are instantly reflected in the system.

[1994] "User" means an individual or organization that uses the system to generate program code or manage projects.

[1995] A "project" is a planned series of tasks or activities designed to achieve a specific purpose.

[1996] The system for implementing this invention allows users to input prompt sentences and generate and improve program code using a generative artificial intelligence model. Specifically, it involves three main elements working together: a server, a terminal, and a user.

[1997] Hardware and Software Configuration

[1998] The server has a generative artificial intelligence model (e.g., OpenAI's GPT-4) and an emotion recognition engine (e.g., Microsoft Azure's Text Analytics) installed. The server receives a prompt from the user, generates program code using the generative artificial intelligence model, and analyzes the user's emotions using the emotion recognition engine.

[1999] The device (smartphone or PC) acts as the user interface. The device sends prompts and feedback entered by the user to the server, and is equipped with an application (for example, a backend built with the Django framework and a frontend built with React) to receive and display the generated program code and emotion recognition results.

[2000] Users operate the device to create projects, enter prompts, provide feedback, and more.

[2001] Data processing and calculation flow

[2002] 1. User Registration and Authentication

[2003] The user enters their email address and password using the terminal application and submits them to the server, which validates the information using Django's user authentication functionality, stores it in a PostgreSQL database, and, if authentication is successful, generates a session token and sends it back to the user.

[2004] 2. Create a project

[2005] When the user clicks the "Create a new project" button, the device notifies the server of this action. The server generates a new project ID and registers it in the database. Once the project creation is complete, the user is notified and provided with the new project ID.

[2006] 3. Entering prompt statements and generating code

[2007] The user enters a prompt on the project details page and sends it to the server, which then passes the prompt to the generative artificial intelligence model to generate program code.

[2008] 4. Suggestions and Feedback

[2009] The generated program code is sent from the server to the terminal and displayed to the user. The user reviews the code and provides feedback. The terminal sends this feedback to the server, which then uses the generative artificial intelligence model to improve the program code.

[2010] 5. Emotional awareness and support

[2011] Emotional data is collected from user feedback and input and analyzed by an emotion recognition engine on the server. Based on the analysis results, if the user's stress level is high, more detailed explanations or additional documentation will be provided.

[2012] Specific examples

[2013] For example, suppose a user enters the prompt, "I want to implement a new quality inspection system." This information is sent to the server, and a generative AI model generates the basic program code for the quality inspection system. The user reviews the code and provides feedback, saying, "I want to improve the inspection accuracy." The server then uses the generative AI model to improve the program code based on the feedback and sends it back to the user. Furthermore, an emotion recognition engine detects the user's level of excitement and provides additional detailed explanations to reduce stress.

[2014] This system allows users to effectively generate and improve program code and efficiently advance projects.

[2015] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2016] Step 1: User Registration and Authentication

[2017] The user enters their email address and password in the terminal application and sends a registration request to the server. The server receives the input and uses Django's user authentication function to store the registration information in a database (PostgreSQL). The server then sends the user a confirmation email, and when the user clicks on the link, the account is activated. When the user enters their login information again, the server authenticates them and, if successful, generates a session token and sends it back to the user.

[2018] Step 2: Create a project

[2019] The user presses the "Create a new project" button in the app, and the device notifies the server of the operation. The server generates a new project ID and registers this information in the database. Once the project creation is complete, the server returns the new project ID to the user and notifies them that the project has been created.

[2020] Step 3: Enter the prompt statement

[2021] The user enters a prompt on the project details page, and the device sends this information to the server. The entered prompt is passed to a generative artificial intelligence model (OpenAI GPT-4). The server inputs the prompt into the AI ​​model and instructs it to generate program code. The generated program code is temporarily stored on the server.

[2022] Step 4: Code suggestions and feedback

[2023] The server sends the generated program code to the terminal, which displays it to the user. The user checks the code and enters feedback if necessary. The feedback is sent from the terminal to the server. The server passes this feedback back to the generative artificial intelligence model, instructing it to generate improved program code.

[2024] Step 5: Submitting the improved code

[2025] The server then sends the improved program code generated by the generative artificial intelligence model back to the device, which then displays the improved program code to the user and repeats the process until feedback is received. With each iteration of the improvement, the server saves the progress record in the database and updates the project's progress.

[2026] Step 6: Emotional awareness and support

[2027] The device sends the feedback and prompts entered by the user to the server, which then uses an emotion recognition engine (Microsoft Azure Text Analytics) to analyze the user's emotional data. Based on the analysis results, if the user's stress level is high, the server generates emotionally appropriate support information (e.g., step-by-step guides or additional documentation) and provides it to the user via the device.

[2028] Step 7: Real-time updates on task progress

[2029] Users operate their devices to input task progress, and the devices send that information to the server, which then stores the task progress in a database and updates it in real time, allowing users to always have the most up-to-date information on the progress of the entire project.

[2030] 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.

[2031] 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.

[2032] 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.

[2033] 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.

[2034] 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.

[2035] 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.

[2036] 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).

[2037] 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.

[2038] 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."

[2039] 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.

[2040] 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).

[2041] 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.

[2042] 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.

[2043] 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.

[2044] 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.

[2045] 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.

[2046] 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.

[2047] 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.

[2048] 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.

[2049] 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.

[2050] 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.

[2051] The following is further disclosed regarding the above embodiment.

[2052] (Claim 1)

[2053] means for generating program code utilizing a generative artificial intelligence model based on prompts entered by a user;

[2054] a means for sending code suggestions back to the user for the entered prompts;

[2055] A means for receiving feedback from a user and generating program code again using a generative artificial intelligence model based on the feedback;

[2056] a means for returning the generated improved program code to the user;

[2057] A system that includes a means of managing the progress of a project.

[2058] (Claim 2)

[2059] A means to allow a user to create a new project;

[2060] A means of registering the resources required to create a new project in the database;

[2061] 10. The system of claim 1, further comprising means for notifying completion of project creation.

[2062] (Claim 3)

[2063] A means for users to create and authenticate accounts;

[2064] A means to validate the entered authentication information against a database and generate a session token on success.

[2065] 10. The system of claim 1, further comprising means for notifying completion of authentication.

[2066] "Example 1"

[2067] (Claim 1)

[2068] means for generating program code utilizing a generative artificial intelligence model based on prompts entered by a user;

[2069] a means for returning code suggestions to the user in response to the entered prompt;

[2070] A means for receiving feedback from a user and generating program code again using the generative artificial intelligence model based on the feedback;

[2071] means for returning the generated improved program code to the user;

[2072] A means of managing the progress of the project;

[2073] A means for allowing users to input project progress and new assignments;

[2074] a means for recording the input information in a database;

[2075] A means for a user to input a question about a specific problem and transmit the question to an information processing device;

[2076] means for passing the question received by the information processing device to a generative artificial intelligence model and obtaining an answer;

[2077] a means for providing the answer to the user;

[2078] A means for users to create and authenticate their accounts;

[2079] A system that includes a means for validating entered authentication information against a database and, upon success, generating a security token.

[2080] (Claim 2)

[2081] a means for enabling a user to create a new project;

[2082] A means of registering the resources required to create a new project in the database;

[2083] Also includes a means to notify you when the project is complete

[2084] (Claim 3)

[2085] A means for users to create and authenticate their accounts;

[2086] means for verifying the entered authentication information in a database and, upon success, generating session establishment information;

[2087] 10. The system of claim 1, further comprising means for notifying completion of authentication.

[2088] "Application Example 1"

[2089] (Claim 1)

[2090] means for generating program code utilizing a generative artificial intelligence model based on prompts entered by a user;

[2091] a means for sending code suggestions back to the user for the entered prompts;

[2092] A means for receiving feedback from a user and generating program code again using a generative artificial intelligence model based on the feedback;

[2093] a means for returning the generated improved program code to the user;

[2094] A means of managing the progress of the project;

[2095] A means for generating an operation program for a machine operating in a factory and improving the operation of the machine;

[2096] A system including:

[2097] (Claim 2)

[2098] A means to allow a user to create a new project;

[2099] A means of registering the resources required to create a new project in the database;

[2100] A means of notifying the completion of project creation,

[2101] A means for inputting an operation request for a specific machine in a factory and applying a code generated based on the request to the machine

[2102] The system of claim 1 further comprising:

[2103] (Claim 3)

[2104] A means for users to create and authenticate accounts;

[2105] A means to validate the entered authentication information against a database and generate a session token on success.

[2106] a means for notifying the completion of authentication;

[2107] 10. The system according to claim 1, further comprising means for granting a user permission to operate a specific machine.

[2108] "Example 2: Combining Emotion Engines"

[2109] (Claim 1)

[2110] means for generating program code utilizing a generative artificial intelligence model based on prompts entered by a user;

[2111] a means for sending code suggestions back to the user for the entered prompts;

[2112] A means for receiving feedback from a user and generating program code again using a generative artificial intelligence model based on the feedback;

[2113] a means for returning the generated improved program code to the user;

[2114] A means of managing the progress of the project;

[2115] a means for recognizing user emotions based on user-entered prompts and feedback;

[2116] A means to adjust the suggestions and support content of the generative artificial intelligence model based on these emotions, and

[2117] A system including:

[2118] (Claim 2)

[2119] A means to allow a user to create a new project;

[2120] A means of registering the resources required to create a new project in the database;

[2121] 10. The system of claim 1, further comprising means for notifying completion of project creation.

[2122] (Claim 3)

[2123] A means for users to create and authenticate accounts;

[2124] A means to validate the entered authentication information against a database and generate a session token on success.

[2125] 10. The system of claim 1, further comprising means for notifying completion of authentication.

[2126] "Application example 2 when combining emotion engines"

[2127] (Claim 1)

[2128] means for generating program code utilizing a generative artificial intelligence model based on prompts entered by a user;

[2129] a means for sending code suggestions back to the user for the entered prompts;

[2130] A means for receiving feedback from a user and generating program code again using a generative artificial intelligence model based on the feedback;

[2131] a means for returning the generated improved program code to the user;

[2132] A means of managing the progress of the project;

[2133] A way to recognize user sentiment data and adapt project management and code suggestions accordingly.

[2134] A means of storing the user's task progress in a database and updating the progress in real time;

[2135] A system including:

[2136] (Claim 2)

[2137] A means to allow a user to create a new project;

[2138] A means of registering the resources required to create a new project in the database;

[2139] A means of notifying the completion of project creation,

[2140] A means for transmitting user input information to a server and passing it to a generative artificial intelligence model;

[2141] A means for receiving an output of the generative artificial intelligence model transmitted from the server;

[2142] By sending and receiving data with the server, the progress of tasks and feedback can be reflected.

[2143] 10. The system of claim 1, further comprising means for providing step-by-step advice and additional documentation based on emotion recognition.

[2144] (Claim 3)

[2145] A means for users to create and authenticate accounts;

[2146] A means to validate the entered authentication information against a database and generate a session token on success.

[2147] a means for notifying the completion of authentication;

[2148] A means to accurately detect stress levels through project progress management and the output of generative artificial intelligence models, and provide support according to the user's emotions.

[2149] The system of claim 1 further comprising: [Explanation of symbols]

[2150] 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. means for generating program code utilizing a generative artificial intelligence model based on prompts entered by a user; a means for sending code suggestions back to the user for the entered prompts; A means for receiving feedback from a user and generating program code again using a generative artificial intelligence model based on the feedback; a means for returning the generated improved program code to the user; A system that includes a means of managing the progress of a project.

2. A means to allow a user to create a new project; A means of registering the resources required to create a new project in the database; The system of claim 1 further comprising means for notifying completion of project creation.

3. A means for users to create and authenticate accounts; A means to validate the entered authentication information against a database and generate a session token on success.

10. The system of claim 1, further comprising means for notifying completion of authentication.

Images