System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting system requirements from users; means for automatically generating a system code by a generation AI based on the collected requirements; means for holding a system construction contest by a plurality of engineers; means for evaluating systems submitted by the engineers based on evaluation criteria and selecting a winner; means for providing the winner with a prize or an admission right; and means for implementing the system using the obtained source code.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In today's market environment, there is a labor shortage due to population decline and the promotion of digital transformation (DX). It is also important for companies to reduce system development costs and build systems in a short period of time. However, meeting these requirements using traditional system development methods is difficult, and high costs and long development times are problems. Furthermore, there are limited means of discovering talented engineers and hiring them as immediate assets. The purpose of this invention is to solve these problems and provide a means to build systems efficiently and quickly and discover talented engineers. [Means for solving the problem]

[0005] The present invention provides the following means: a means for collecting system requirements from users; a means for automatically generating system code using a generative AI based on the collected requirements; a means for holding a system construction contest among multiple engineers; a means for evaluating systems submitted by the engineers based on evaluation criteria and selecting winners; a means for offering prize money or employment rights to the winners; and a means for implementing the system using the obtained source code. Specifically, users enter system requirements through a form, which is received and organized by a server. Next, a generative AI model generates system code based on the requirements, and engineers build and submit a system based on this code. Finally, the submitted systems are evaluated, and the best engineers are awarded prize money or employment rights, and the winning code is implemented to launch the system.

[0006] "System requirements" are specific requirements for the functions and characteristics of a system that users desire.

[0007] A "user" is an individual or group that uses the system, and in the present invention, is a person who plays a role in providing system requirements.

[0008] "Generative AI" refers to algorithms that use artificial intelligence techniques to automatically generate code or other information based on given requirements.

[0009] "System code" is a set of instructions written in a programming language that causes a computer to operate.

[0010] An "engineer" is a professional who is responsible for designing, building, testing, and maintaining a system, and in the present invention, is a person who participates in a contest to build a system.

[0011] A "contest" is an event in which participants compete against each other on a specific task and compete for success.

[0012] "Evaluation Criteria" are the metrics or standards for evaluating submitted systems, including, for example, functional completeness and code efficiency.

[0013] "Winners" are engineers who receive high marks in the competition and are eligible to receive prize money and other benefits.

[0014] "Prize" means a monetary reward offered to a Contest winner.

[0015] "Right of Employment" means the right to take up a position offered to the winner of the contest.

[0016] A "server" is a computer system that provides and receives information via a network, and in the present invention is responsible for collecting system requirements, executing, evaluating, notifying, and implementing the generative AI.

[0017] "Source code" means the set of high-level instructions used to design and build a program, written in a form that is easy for humans to understand.

[0018] "Implementation" is the process of assembling and running a designed system in an operational form. [Brief explanation of the drawings]

[0019] [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

[0020] 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.

[0021] First, the terms used in the following description will be explained.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 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.

[0030] 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).

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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."

[0040] The present invention provides a system construction process that utilizes generative AI. The series of processes is explained below.

[0041] First, the user inputs the system requirements (e.g., system name, required functions, deadline). This input is done via a web form or application, and the terminal sends it to the server. The server receives the requirements from the user and organizes them for further processing. At this stage, the system requirements are saved in dictionary format.

[0042] Next, the server calls a generative AI model based on the collected system requirements to automatically generate system code. The generative AI model could use OpenAI's GPT-3, for example. Based on the collected requirements, the generative AI model generates appropriate program code, which the server receives.

[0043] After that, users (engineers) participate in the contest. The contest is an event where engineers submit systems they have built using generative AI. Engineers build systems based on specified system requirements and submit their results to the server.

[0044] The server evaluates the submitted systems based on a set of criteria, including the completeness of the system's functions and the efficiency of its code. Based on the results, the server selects winners and offers prize money and employment opportunities to the engineers who build the best systems.

[0045] Finally, the server will implement the system using the source code obtained, deploy the winner's code, and put the system into operation. This deployment process will be adjusted according to the actual business environment and user requirements.

[0046] Specific examples

[0047] For example, consider building an online shopping system. The user inputs the following requirements:

[0048] System name: Online shopping

[0049] Required functions: cart function, payment function

[0050] Deadline: 1 week later

[0051] The server receives these requirements and passes them to a generative AI model. Based on this, the generative AI model generates basic code for the online shopping system. Engineers build systems based on this code and submit them. The server evaluates the submitted systems and selects the top three engineers. These engineers are offered prize money and employment opportunities. Finally, the server implements the winning code and launches the online shopping system.

[0052] This process allows systems to be built efficiently in a short period of time, significantly reducing system development costs, while also enabling the discovery and recruitment of talented engineers.

[0053] The processing flow will be explained below.

[0054] Step 1:

[0055] A user enters system requirements (e.g., system name, required features, deadline) through a web form or application.

[0056] Step 2:

[0057] The terminal transmits the input requirements to the server.

[0058] Step 3:

[0059] The server organizes the received requirements, converts them into dictionary format, and saves them.

[0060] Step 4:

[0061] The server sends the collected requirements to the API of the generative AI model, which then automatically generates system code.

[0062] Step 5:

[0063] The generative AI model generates system code based on the given requirements, which is then received by the server.

[0064] Step 6:

[0065] Users (engineers) participate in the contest and build systems using generative AI models.

[0066] Step 7:

[0067] The engineer submits the system he built to the server.

[0068] Step 8:

[0069] The server evaluates the submitted systems based on criteria, including the completeness of the system's functionality and the efficiency of its code.

[0070] Step 9:

[0071] The server will select winners based on the evaluation results, and will offer prize money and employment rights to engineers who build excellent systems.

[0072] Step 10:

[0073] The server will implement the system using the winner's source code, deploy the system and put it into operation.

[0074] The above is the specific processing flow of the system construction process using generative AI.

[0075] Example 1

[0076] 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."

[0077] Traditional system development processes have had problems such as long development times and rising costs. Furthermore, there are limited means for quickly evaluating and hiring the right engineers. These issues make it difficult to improve the efficiency of system development and find talented engineers.

[0078] 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.

[0079] In this invention, the server includes means for collecting system requirements from users, means for automatically generating a system program using artificial intelligence based on the collected requirements, means for holding a system construction contest among multiple engineers, means for evaluating systems submitted by the engineers based on evaluation criteria and selecting winners, means for providing rewards or employment rights to the winners, and means for implementing the system using the obtained source code. This makes it possible to improve the efficiency of system development and quickly evaluate and discover talented engineers.

[0080] definition statement

[0081] "System requirements" refers to information that includes the functions and conditions necessary to build a system.

[0082] "User" means an individual or entity that provides system requirements and intends to use the system.

[0083] "Collect" refers to obtaining, organizing, and storing information provided by users.

[0084] "Generative AI" is a system that uses artificial intelligence technology to generate new information and programs.

[0085] A "system program" is a collection of code or scripts written to implement a specific function.

[0086] "Automatic generation" refers to the mechanical creation of programs or information without human intervention.

[0087] An "engineer" is a professional who specializes in system construction and program development.

[0088] A "system construction contest" is an event in which multiple engineers build systems based on specified requirements and compete with each other for the best results.

[0089] "Evaluation criteria" are the indicators and standards for evaluating submitted systems and programs.

[0090] A "prize winner" is a person or organization that has demonstrated outstanding achievement in a contest or other competition.

[0091] "Reward" is the consideration of money, goods, etc. provided to those who achieve outstanding results.

[0092] "Right of employment" refers to being qualified to fill a particular job or role.

[0093] "Source code" is the original program text that describes the operation of a system or application.

[0094] "Implementation" refers to the process of giving shape to a designed system or program in a form that actually works.

[0095] MODE FOR CARRYING OUT THE INVENTION

[0096] This invention provides a system construction process that utilizes a generative AI model. This system allows efficient system development through a series of processes: a user inputs system requirements, a server automatically generates system code using a generative AI model, and then engineers participate in a system construction contest and are evaluated.

[0097] Hardware and Software

[0098] Users use devices (PCs, smartphones, etc.) to enter system requirements through web forms or applications, and the data entered by the user is sent from the device to a server via the Internet.

[0099] The server receives and organizes the input requirements. It uses a database to store the requirements in dictionary format. Specifically, the server stores the data in JSON format, with fields such as the system name, required functionality, and deadline.

[0100] Next, the server calls a generative AI model (e.g., OpenAI's GPT-3) based on the collected requirements and automatically generates system code. The server then calls the API of the generative AI model and sends prompt statements based on the requirements to the generative AI model.

[0101] The server receives the code returned by the generative AI model and saves it in a format that can be used by engineers. After that, users (engineers) use their devices to participate in the system construction contest. The engineers build a system based on the generated basic code and upload the results back to the server.

[0102] The server evaluates the submitted systems based on criteria, such as the completeness of the system's functionality and the efficiency of its code, using automated test scripts and static analysis tools.

[0103] Finally, the server will select winners based on the evaluation results and provide them with rewards and employment rights. The server will deploy the source code provided by the winners, adjust it according to the actual business environment and user requirements, and put the system into operation.

[0104] Specific examples

[0105] For example, when building an online shopping system, the user inputs the following requirements:

[0106] System name: Online shopping

[0107] Required functions: cart function, payment function

[0108] Deadline: 1 week later

[0109] The server receives these requirements and passes them to a generative AI model, which then generates basic code for the online shopping system. Here's an example prompt:

[0110] System name: Online Shopping

[0111] Required features: cart function, payment function

[0112] Deadline: 1 week later

[0113] Generate Python code based on this requirement.

[0114] Based on the generated code, users (engineers) build and submit systems. The server evaluates the submitted systems and selects the top three engineers. These engineers are offered rewards and employment rights. Finally, the server implements the winning code and launches the online shopping system.

[0115] The above process allows systems to be built efficiently in a short period of time, reducing development costs and enabling the discovery and recruitment of talented engineers.

[0116] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0117] Processing Steps

[0118] Step 1:

[0119] Users input system requirements through a web form or application, and the input system requirements (e.g., system name, required functions, deadline) are sent from the terminal to the server.

[0120] Input: System name, required functionality, deadline

[0121] Output: User-entered system requirements data

[0122] Specific operation: The user enters "online shopping," "cart function, payment function," and "one week later" into the form on the terminal, and clicks the "Submit" button.

[0123] Step 2:

[0124] The server organizes the system requirements received from the terminals and stores them in a database in dictionary format.

[0125] Input: System requirements data sent from the device

[0126] Output: Organized requirements data (dictionary format)

[0127] Specific operation: The server parses the data received in JSON format and saves it into the fields "System name," "Required functions," and "Deadline."

[0128] Step 3:

[0129] The server generates a prompt sentence based on the collected requirements and calls the API of a generative AI model (e.g., OpenAI GPT-3).

[0130] Input: Organized requirements data

[0131] Output: Prompt text to send to the generative AI model

[0132] Specific operation: The server generates a prompt text "System name: online shopping, Required functions: cart function, payment function, Deadline: 1 week later" and sends it to the API of the generative AI model.

[0133] Step 4:

[0134] The generative AI model generates system code based on the prompt sentence and returns it to the server.

[0135] Input: prompt statement

[0136] Output: Generated system code

[0137] Specific operation: The generative AI model parses the prompt sentence, generates Python code, and sends it back to the server.

[0138] Step 5:

[0139] The server receives the generated system code, formats it in a format that can be used by engineers, and saves it.

[0140] Input: System code received from the generative AI model

[0141] Output: pretty-printed system code

[0142] What it does: The server formats the code and stores it in a repository where engineers can download it.

[0143] Step 6:

[0144] Users (engineers) use their own terminals to participate in the system construction contest and build a system based on the provided system code.

[0145] Input: Formatted system code

[0146] Output: System built by engineers

[0147] Specific operation: Engineers import the provided code into their own development environment and add features or make improvements.

[0148] Step 7:

[0149] The user (engineer) submits the constructed system to the server.

[0150] Input: System built by engineers

[0151] Output: System code uploaded to the server

[0152] Specific operation: The engineer attaches a file to a form to upload the completed system code to the server and clicks the "Submit" button.

[0153] Step 8:

[0154] The server evaluates the submitted systems based on the evaluation criteria and assigns them a score.

[0155] Input: Submitted system code

[0156] Output: Evaluation result (score)

[0157] What it does: The server uses automated test scripts and static analysis tools to evaluate the system's functional completeness and code efficiency.

[0158] Step 9:

[0159] The server will select winners based on the evaluation results and notify them of their rewards and employment rights.

[0160] Input: Evaluation result (score)

[0161] Output: Winner selection and notification

[0162] Specific operation: The server selects the top three engineers based on the evaluation results and sends a notification email.

[0163] Step 10:

[0164] The server deploys the obtained source code and begins operation in the production environment.

[0165] Input: Winner's source code

[0166] Output: Operational system

[0167] What happens: The server runs the deploy script to put the system into production, updating configuration files and initializing the database as needed.

[0168] (Application example 1)

[0169] 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."

[0170] In the traditional system construction process, users must define system requirements in detail, and engineers must manually develop code based on those requirements, which requires a significant amount of time and effort. Furthermore, in complex systems such as virtual stores, users often find it difficult to intuitively input requirements. This has led to issues with reduced efficiency and speed in system construction.

[0171] 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.

[0172] In this invention, the server includes a means for converting user input into text data using voice recognition technology, a means for providing a visual interface for the user via a device such as smart glasses, and a means for implementing the system using the source code used, which allows the user to intuitively input system requirements and enables efficient and rapid system construction.

[0173] "Speech recognition technology" refers to technology that converts a user's voice into text data.

[0174] "Text data" refers to character string data generated using speech recognition technology.

[0175] "Smart glasses" refers to a wearable device that provides information to the user as a visual interface.

[0176] A "visual interface" is a means of providing information visually to a user, including displays and AR technology.

[0177] A "generative AI model" refers to an artificial intelligence model that automatically generates program code based on user input data.

[0178] "Server" refers to a computer system that processes and stores data.

[0179] "System requirements" refer to the specific functions and conditions that users require from a system.

[0180] "Source code" refers to the code of a program written to operate a system.

[0181] "Deployment" refers to the process of placing source code into an actual production environment and running the system.

[0182] "Engineer" refers to a technician in charge of system design and development.

[0183] A "contest" refers to a competitive event in which engineers compete to see who can build the best systems.

[0184] "Evaluation criteria" refers to specific performance and functional indicators that a system must meet.

[0185] "Winner" means the person who submitted the most outstanding work based on the evaluation criteria.

[0186] "Reward" refers to the monetary incentive offered to the winner.

[0187] "Contract Rights" means the formal contract rights provided to the Prize Winner.

[0188] This invention relates to a system that efficiently collects system requirements using voice recognition technology and automatically generates program code using a generative AI model. The system provides a visual interface to users via smart glasses and assists in data processing and code deployment on a server.

[0189] The user wears the smart glasses and uses voice recognition technology to input system requirements by voice. The smart glasses are equipped with a speech recognition engine such as the Google Cloud Speech-to-Text API, which converts the voice input into text data with high accuracy. This text data is then sent to the server. The server analyzes the system requirements received from the user and generates appropriate prompts.

[0190] As a concrete example, consider the case of building an online shopping system. A user inputs the following requirements by voice through smart glasses:

[0191] System requirements:

[0192] System name: Online shopping system

[0193] Required functions: product list display function, cart function, voice payment function

[0194] Deadline: 1 week later

[0195] The server receives these requirements as text data and generates a prompt to proceed, such as:

[0196] Generate basic program code for an online shopping system based on the following requirements:

[0197] Requirements:

[0198] System name: Online shopping system

[0199] Required features: Product list display function, cart function, voice payment function

[0200] Deadline: 1 week later

[0201] Using a generative AI model (e.g., OpenAI's GPT-3), appropriate program code is generated based on this prompt. The generated code is then submitted to a competition in which engineers participate and are evaluated based on criteria. The best engineers are offered rewards or contract rights.

[0202] Finally, the server deploys the best source code obtained, and the system moves into production. Deployment tools such as Jenkins can be used for deployment. This system allows users to intuitively and efficiently input system requirements and build high-quality systems in a short period of time.

[0203] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0204] Step 1:

[0205] The user wears the smart glasses and inputs system requirements using voice recognition technology, which uses the smart glasses' built-in microphone to convert speech into text data via the Google Cloud Speech-to-Text API. The input for this step is the user's voice input, and the output is the converted text data.

[0206] Step 2:

[0207] The server receives the text data (system requirements) sent from the smart glasses and stores it in a database. The received text data is organized in a dictionary format. The input of this step is the text data, and the output is the system requirements stored in the database.

[0208] Step 3:

[0209] The server generates prompt sentences for the generative AI model based on the saved system requirements. The prompt sentences are used in API calls to the generative AI model (such as OpenAI's GPT-3). The input of this step is the organized system requirements, and the output is the generated prompt sentences.

[0210] Step 4:

[0211] Using the generated prompt sentence, the server calls the API of the generative AI model to generate program code. The generative AI model automatically generates appropriate code based on the prompt sentence. The input of this step is the prompt sentence, and the output is the generated program code.

[0212] Step 5:

[0213] Engineers receive the generated code from the server and participate in a system construction contest. Based on the specified system requirements, the engineers customize the generated code and build the final system. The input of this step is the generated program code, and the output is the system built by the engineers.

[0214] Step 6:

[0215] The server evaluates the systems submitted by engineers based on the evaluation criteria. The evaluation is based on multiple indicators such as the completeness of the system's functions and the efficiency of the code. The input of this step is the engineer's submitted system, and the output is an evaluation score and ranking.

[0216] Step 7:

[0217] The server selects winners based on the rankings and provides rewards or contract rights to the winners. The input of this step is the evaluation score and ranking, and the output is the list of winners and the provision of rewards or contract rights.

[0218] Step 8:

[0219] The server uses the winner's source code to implement the virtual store system. A deployment tool such as Jenkins is used for deployment. The input for this step is the winner's source code, and the output is the actual virtual store system that will be put into operation.

[0220] 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.

[0221] This invention provides a system that combines a system construction process using generative AI with an emotion engine that recognizes user emotions. The series of processes is explained below.

[0222] First, the user inputs the system requirements (e.g., system name, required functions, deadline). This input is done via a web form or application, and the terminal sends this to the server. The server receives and organizes the requirements received from the user.

[0223] The server then uses an emotion engine to recognize emotions based on the user's input data. The emotion engine uses natural language processing technology to analyze emotions from the user's text input and feeds the results back to the system requirements collection means. For example, if the user inputs "I want to complete it quickly," the urgency is recognized.

[0224] The server then calls the generative AI model based on the collected requirements and automatically generates system code. Here, the analysis results from the emotion engine are also reflected in the generative AI model, so if the user is in a hurry, for example, code that prioritizes development speed will be generated.

[0225] Users (engineers) participate in the contest and build systems based on basic system code provided by the generative AI model. The engineers then submit the systems they build to the server.

[0226] The server will evaluate the submitted systems based on criteria, including the completeness of the system's functions and the efficiency of the code. Based on the results, the server will select winners and offer prize money and employment opportunities to the engineers who build the best systems.

[0227] Finally, the server will use the source code obtained to implement the system and put it into operation. The system deployment process will be adjusted according to the actual business environment and user requirements.

[0228] Specific examples

[0229] For example, consider a user building an online shopping system. The user inputs the following requirements:

[0230] System name: Online shopping

[0231] Required functions: cart function, payment function

[0232] Deadline: 1 week later

[0233] The server receives these requirements and further analyzes the user's emotions using an emotion engine. For example, if the user adds, "I need this to be done quickly," the emotion engine recognizes the urgency. The server sends this emotion data to a generative AI model, which generates code that can also handle urgent requirements.

[0234] Engineers build and submit systems based on this generated code. The server evaluates the submitted systems and selects the top three engineers. These engineers are offered prize money and employment opportunities. Finally, the server implements the winner's code and launches the online shopping system.

[0235] This process allows systems to be built efficiently in a short period of time, significantly reducing system development costs. Also, by reflecting user emotions, it is possible to provide a system that provides greater satisfaction.

[0236] The processing flow will be explained below.

[0237] Step 1:

[0238] The user enters system requirements (e.g., system name, required functions, deadline) through a web form or application. For example, the user enters requirements such as "online shopping," "cart function," "payment function," and "one week later."

[0239] Step 2:

[0240] The terminal transmits the input requirements to the server, and the user's terminal transmits the input data to the server via the Internet.

[0241] Step 3:

[0242] The server organizes the received requirements and converts them into a dictionary format. The server analyzes the received data and organizes and saves information such as the system name, required functions, and deadlines.

[0243] Step 4:

[0244] The server uses an emotion engine to recognize emotions from the user's input data. The emotion engine uses natural language processing technology to analyze emotions from the user's text input. For example, if the user enters "I want to finish it quickly," the emotion engine will recognize the user's high sense of urgency.

[0245] Step 5:

[0246] The emotion engine reflects the emotion analysis results in the system requirements, and the server stores the recognized emotion data (e.g., high urgency) as part of the requirements.

[0247] Step 6:

[0248] The server automatically generates system code by invoking a generative AI model based on the requirements and emotion data collected. The generative AI model (e.g., GPT-3) generates system code based on the requirements and emotion data.

[0249] Step 7:

[0250] The server stores the generated system code and makes it accessible to users (engineers). Engineers access the generated system code and make any necessary modifications or additions.

[0251] Step 8:

[0252] Users (engineers) participate in the contest and build a system based on the basic system code provided by the generative AI model. The engineers then modify and expand the code, aiming to complete the system.

[0253] Step 9:

[0254] Engineers submit the completed system to the server. Engineers upload the completed system code to the server.

[0255] Step 10:

[0256] The server evaluates the submitted systems based on criteria, including the completeness of the system's functionality and the efficiency of the code. The server then scores each engineer's system based on these criteria.

[0257] Step 11:

[0258] The server will select winners based on the evaluation results, and offer prize money and employment rights to the engineers who have built the best systems. The server will select the engineers with the highest scores and notify them.

[0259] Step 12:

[0260] The server will implement the system using the winner's source code and begin operation. The server will then import the winner's code and deploy it to the actual production environment.

[0261] For example, if a user inputs, "I want to build an online shopping system, I need a cart function and a payment function, the deadline is one week from now, I'm in a hurry," the server will recognize these requirements and the urgency, and generate system code that can quickly respond using a generative AI model. Engineers will build a system based on this, and the best system will be selected after evaluation and finally deployed. This process makes it possible to build high-quality systems in a short period of time.

[0262] Example 2

[0263] 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."

[0264] In conventional system development processes, it is difficult to fully reflect factors such as user emotions and urgency, resulting in low user satisfaction. Furthermore, while there has been some technological progress in automatic system code generation, there is a lack of a method for quickly and efficiently responding to specific user requirements. Therefore, there is a need to establish an efficient system development method that simultaneously considers user requirements and emotions.

[0265] 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.

[0266] In this invention, the server includes means for collecting system requirements from users, means for using an emotion engine that recognizes user emotions, means for evaluating and feeding back the emotion data recognized by the emotion engine, and means for automatically generating system code using a generation AI based on the collected requirements and emotion data. This enables the construction of an efficient system that simultaneously reflects user requirements and emotions.

[0267] "System requirements" refers to elements necessary for system construction, such as the system name, required functions, deadlines, etc., collected from users.

[0268] An "emotion engine" is a machine learning model or algorithm that uses natural language processing technology to analyze and recognize emotions from user input data.

[0269] "Emotion data" refers to the user's emotional information recognized by the emotion engine, and indicates the urgency and priority of the requirement.

[0270] "Generative AI" refers to an artificial intelligence system that automatically generates system code based on collected requirements and emotional data.

[0271] "Initial system code" refers to the code that contains the basic structure of the system, which is automatically generated by the generation AI.

[0272] The "Engineer System Building Contest" refers to a competition in which multiple engineers build systems based on initial system code provided by a generative AI model and compete based on the results.

[0273] "Evaluation Criteria" refers to the standards for evaluating submitted systems, including the completeness of the system's functionality and the efficiency of its code.

[0274] "Rights to join" refers to the right to join a specific company or project that is offered to engineers when they win a system construction contest.

[0275] "Source code" refers to the human-readable form of program code created by engineers to define the behavior of a program.

[0276] "Implementation means" refers to the process or method for using the source code obtained to deploy and operate the system in an actual operating environment.

[0277] This invention is a system that uses a generative AI model to automatically generate system code, recognizes user emotions, and reflects them in the system construction process. This system includes a server with an emotion engine, a terminal that receives user input, and a function for automatically generating system code using generative AI.

[0278] First, the user enters the system requirements using a web form or application. Input items include the system name, required functions, and deadline. This input data is sent to the server via the terminal. The data is encrypted and reaches the server in a secure manner.

[0279] The server organizes the received system requirements and uses an emotion engine to recognize the user's emotions. The emotion engine uses natural language processing technology to analyze emotions from the user's text input. For example, if the user enters "I want to finish it quickly," the emotion engine will recognize the urgency.

[0280] The server then evaluates the emotion data recognized by the emotion engine and feeds it back into a database of system requirements, which are then used by the generative AI model to generate system code.

[0281] The server calls the API of the generative AI model based on the collected requirements and emotion data, and automatically generates system code. This generative AI model generates optimal code according to the provided prompt. An example of a prompt is shown below:

[0282] System name: Online Shopping

[0283] Required features: cart function, payment function

[0284] Deploy to: AWS

[0285] Additional information: The user expressed a desire to "finish quickly"

[0286] Deadline: 1 week

[0287] The user (engineer) builds a system based on the initial system code provided by the generative AI model. The engineer then submits the built system to the server. The server evaluates the submitted systems based on evaluation criteria and selects the top engineer. The evaluation criteria include the completeness of the system's functions and the efficiency of the code.

[0288] Finally, the server implements the system using the source code obtained and puts it into operation. The system is adjusted according to the actual business environment and user requirements, enabling efficient and rapid operation.

[0289] The above process makes it possible to build a system that simultaneously considers the user's requirements and emotions, and to provide a high-quality system in a short period of time.

[0290] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0291] Step 1:

[0292] Users enter system requirements (system name, required functions, deadline) using a web form or application, and the entered data is sent to the server via the terminal.

[0293] Input: System name, required functionality, deadline, etc.

[0294] Output: Requirement data sent to the server

[0295] Specifically, after the requirements are entered, a button is clicked and the data is sent to the server, where it is encrypted and transmitted over a secure channel.

[0296] Step 2:

[0297] The server organizes the received requirements data and analyzes the sentiment from the user's input text using an emotion engine, which uses natural language processing algorithms (e.g., sentiment analysis APIs).

[0298] Input: Requirement data sent by the user

[0299] Output: Parsed emotion data

[0300] Specifically, the server analyzes the received data and inputs the text data into the emotion engine, which then analyzes emotions such as urgency and anxiety and returns the data.

[0301] Step 3:

[0302] The server evaluates the emotion analysis results from the emotion engine and feeds them back to the system requirements database, so that the analysis results can be used in the next step.

[0303] Input: Sentiment analysis results

[0304] Output: Updated system requirements database

[0305] Specifically, the results of the sentiment analysis are stored in a database, which serves as reference data for the next generative AI model to generate code.

[0306] Step 4:

[0307] The server calls the API of the generative AI model and automatically generates system code based on the collected requirements and emotion data. The generative AI model generates code using prompt sentences as input.

[0308] Input: System requirements, emotion data

[0309] Output: Auto-generated initial system code

[0310] Specifically, the server inputs the following prompt sentence into the generative AI model:

[0311] System name: Online Shopping

[0312] Required features: cart function, payment function

[0313] Deploy to: AWS

[0314] Additional information: The user expressed a desire to "finish quickly"

[0315] Deadline: 1 week

[0316] This allows the generative AI model to generate system code.

[0317] Step 5:

[0318] The user (engineer) receives the generated initial system code and builds the system. The engineer customizes the code and runs tests.

[0319] Input: Initial system code provided by the generative AI model

[0320] Output: The constructed system

[0321] Specifically, engineers use an IDE to develop and adjust code, then check its operation in a test environment.

[0322] Step 6:

[0323] Users (engineers) submit their completed systems to the server. The submitted system code must follow a specified format and procedure.

[0324] Input: System code built by engineers

[0325] Output: The system submitted to the server

[0326] Specifically, an engineer uses a submission interface to upload the system to a server.

[0327] Step 7:

[0328] The server evaluates submitted systems based on criteria, including the completeness of the system's functionality and the efficiency of its code.

[0329] Input: Submitted system code

[0330] Output: Evaluation results

[0331] Specifically, the server evaluates the systems through an automated rating system or rating committee and assigns them a score or ranking.

[0332] Step 8:

[0333] The server will select the winners based on the evaluation results and provide them with prize money and employment opportunities.

[0334] Input: Evaluation result

[0335] Output: Selection of winners and award of prize money and employment rights

[0336] Specifically, the server sends a notification to the senior engineer and executes the procedure for providing the bonus and employment rights.

[0337] Step 9:

[0338] Finally, the server implements the system using the source code it has obtained and begins operation.

[0339] Input: The source code of the winner

[0340] Output: Implemented system

[0341] As a concrete operation, the server executes the deployment process automatically or manually and starts the system operation, thereby providing a high-quality system that reflects the user's requirements and feelings.

[0342] (Application example 2)

[0343] 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."

[0344] In modern system development processes, system code is often generated based only on simple functional requirements without considering user emotions. This often results in insufficient responses to users' actual needs and urgency. Furthermore, particularly in brick-and-mortar stores, product recommendations do not reflect users' emotional state, making it difficult to improve customer satisfaction.

[0345] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting system requirements from a user, means for automatically generating system code using a generation AI based on the collected requirements, means for analyzing the user's emotional state using emotion recognition software and reflecting the analysis results in the generation AI, and means for displaying information to the user via a smart device and making optimal suggestions based on the user's emotional state. This enables code generation that reflects the user's emotions and optimal product suggestions based on real-time emotion analysis.

[0346] "System requirements" are specific requirements such as functions, characteristics, deadlines, etc. that users require from a system.

[0347] "Generative AI" is an artificial intelligence technology that automatically generates program code using pre-trained models.

[0348] "Engineer" refers to an engineer with specialized knowledge who designs and develops systems.

[0349] A "construction contest" is a competition in which multiple engineers build systems and compete against each other in terms of their technical skills.

[0350] "Evaluation criteria" are indicators or standards for evaluating the quality and performance of submitted systems or programs.

[0351] "Reward" refers to the money or benefits provided to engineers in exchange for winning the award.

[0352] "Right of entry" refers to the right given to engineers to join a company.

[0353] "Program code" means a set of instructions written to run a system or piece of software.

[0354] "Implementation" is the activity of developing and constructing a designed system or program in a form that can actually be used.

[0355] "Emotion recognition software" is a program that analyzes a user's emotional state from facial expressions, voice, etc.

[0356] "Smart devices" refer to advanced devices that have internet connectivity and can run a variety of applications.

[0357] To implement this invention, the following system configuration and processing are required. The system consists of a user, a server, and a smart device (e.g., smart glasses). The entire system operates around emotion recognition software and a generative AI model.

[0358] System configuration

[0359] 1. User interface: The user uses an interface (e.g., a web form or an application) to input system requirements. Through this interface, the user inputs system requirements (system name, required functions, deadline, etc.).

[0360] 2. Server: The server is implemented with a program that provides the following functions:

[0361] Data collection: Receiving and organizing user input data.

[0362] Emotion analysis: Using emotion recognition software (e.g., Amazon Rekognition), emotions are analyzed from user input data, facial expressions, and voice.

[0363] Generative AI model: Invoke a generative AI model (e.g., OpenAI GPT-4) to automatically generate system code based on the collected requirements and sentiment data.

[0364] Evaluation and selection: A system building contest will be held among multiple engineers, and the submitted systems will be evaluated based on the evaluation criteria to select the winners.

[0365] Reward Offer: Offer rewards or employment rights to winners.

[0366] Implementation and deployment: Using the obtained program code, the system is implemented and put into operation.

[0367] 3. Smart devices: Smart devices such as smart glasses will be used to analyze users' emotions in real time and make optimal product recommendations.

[0368] Emotion analysis: The smart glasses' camera and microphone capture the user's facial expressions and voice and send them to the server.

[0369] Information display: Optimal suggestions and product information based on emotional data are displayed on smart glasses.

[0370] Specific example explanation

[0371] Take the example of a user using smart glasses while shopping in a brick-and-mortar store.

[0372] 1. Data capture: When a user looks at an item in a store, the camera and microphone in the smart glasses capture facial and voice data.

[0373] 2. Emotion analysis: The captured data is sent to a server and analyzed by emotion recognition software.

[0374] 3. Generative AI model: Based on the analyzed emotional state and collected system requirements, the generative AI model (GPT-4) generates optimal product suggestions.

[0375] 4. Information display: The generated suggestions are displayed to the user in real time through the smart glasses.

[0376] Prompt Sentence Examples

[0377] TXT

[0378] Emotion recognition software API call

[0379] emotion_data = recognize_emotion(captured_image, captured_audio)

[0380] Prompt sentence for generative AI model

[0381] prompt_text = "Generate the best product suggestions if the user is feeling " + emotion_data['emotion'] + "."

[0382] Invoke the GPT-4 model

[0383] optimized_recommendation = generate_recommendation(prompt_text)

[0384] Displaying suggested product information on smart glasses

[0385] display_on_smart_glasses(optimized_recommendation)

[0386] The configuration and processing of this system makes it possible to build an optimal system that reflects the user's emotions and make real-time suggestions, thereby providing a shopping experience that highly satisfies the user.

[0387] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0388] Step 1:

[0389] The user inputs system requirements. The system name, required functions, deadline, etc. are entered through an input interface (e.g., a web form or application), and this is sent from the terminal to the server. Input data might include the system name "online shopping," required functions "cart function, payment function," and deadline "one week later." This data is sent to the server as output.

[0390] Step 2:

[0391] The server organizes the received system requirements data and sends it to emotion recognition software. The data also includes additional information such as the user's "I want to complete this quickly." The emotion recognition software analyzes this text data and identifies the user's emotional state. The output is emotion data such as "high urgency."

[0392] Step 3:

[0393] The server sends the emotion data obtained from the emotion recognition software and the system requirements to the generative AI model, and creates a prompt that automatically generates the system code. For example, it creates a prompt that reads, "If the user feels a high level of urgency, please generate code for the system name online shopping, with the required functions cart and payment functions, so that it can be completed within one week." This prompt is then sent to the generative AI model as output.

[0394] Step 4:

[0395] The server holds a system building contest among multiple engineers based on the system code obtained from the generative AI model. The engineers build systems based on this code and submit them to the server. The input is the system code built by the engineers, and the output is the collection of multiple submitted systems on the server.

[0396] Step 5:

[0397] The server evaluates each submitted system based on evaluation criteria, which include functional completeness, code efficiency, etc. The output is an evaluation result for each system.

[0398] Step 6:

[0399] The server selects winners based on the evaluation results, and provides rewards and employment opportunities to the winners. The output is a list of winners and the reward details.

[0400] Step 7:

[0401] The server implements the system using the obtained best system code and starts operation. The output is a working system that is built and available to users.

[0402] 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.

[0403] 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.

[0404] 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.

[0405] [Second embodiment]

[0406] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0407] 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.

[0408] 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).

[0409] 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.

[0410] 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.

[0411] 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).

[0412] 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.

[0413] 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.

[0414] 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.

[0415] 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.

[0416] 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.

[0417] 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."

[0418] The present invention provides a system construction process that utilizes generative AI. The series of processes is explained below.

[0419] First, the user inputs the system requirements (e.g., system name, required functions, deadline). This input is done via a web form or application, and the terminal sends it to the server. The server receives the requirements from the user and organizes them for further processing. At this stage, the system requirements are saved in dictionary format.

[0420] Next, the server calls a generative AI model based on the collected system requirements to automatically generate system code. The generative AI model could use OpenAI's GPT-3, for example. Based on the collected requirements, the generative AI model generates appropriate program code, which the server receives.

[0421] After that, users (engineers) participate in the contest. The contest is an event where engineers submit systems they have built using generative AI. Engineers build systems based on specified system requirements and submit their results to the server.

[0422] The server evaluates the submitted systems based on a set of criteria, including the completeness of the system's functions and the efficiency of its code. Based on the results, the server selects winners and offers prize money and employment opportunities to the engineers who build the best systems.

[0423] Finally, the server will implement the system using the source code obtained, deploy the winner's code, and put the system into operation. This deployment process will be adjusted according to the actual business environment and user requirements.

[0424] Specific examples

[0425] For example, consider building an online shopping system. The user inputs the following requirements:

[0426] System name: Online shopping

[0427] Required functions: cart function, payment function

[0428] Deadline: 1 week later

[0429] The server receives these requirements and passes them to a generative AI model. Based on this, the generative AI model generates basic code for the online shopping system. Engineers build systems based on this code and submit them. The server evaluates the submitted systems and selects the top three engineers. These engineers are offered prize money and employment opportunities. Finally, the server implements the winning code and launches the online shopping system.

[0430] This process allows systems to be built efficiently in a short period of time, significantly reducing system development costs, while also enabling the discovery and recruitment of talented engineers.

[0431] The processing flow will be explained below.

[0432] Step 1:

[0433] A user enters system requirements (e.g., system name, required features, deadline) through a web form or application.

[0434] Step 2:

[0435] The terminal transmits the input requirements to the server.

[0436] Step 3:

[0437] The server organizes the received requirements, converts them into dictionary format, and saves them.

[0438] Step 4:

[0439] The server sends the collected requirements to the API of the generative AI model, which then automatically generates system code.

[0440] Step 5:

[0441] The generative AI model generates system code based on the given requirements, which is then received by the server.

[0442] Step 6:

[0443] Users (engineers) participate in the contest and build systems using generative AI models.

[0444] Step 7:

[0445] The engineer submits the system he built to the server.

[0446] Step 8:

[0447] The server evaluates the submitted systems based on criteria, including the completeness of the system's functionality and the efficiency of its code.

[0448] Step 9:

[0449] The server will select winners based on the evaluation results, and will offer prize money and employment rights to engineers who build excellent systems.

[0450] Step 10:

[0451] The server will implement the system using the winner's source code, deploy the system and put it into operation.

[0452] The above is the specific processing flow of the system construction process using generative AI.

[0453] Example 1

[0454] 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."

[0455] Traditional system development processes have had problems such as long development times and rising costs. Furthermore, there are limited means for quickly evaluating and hiring the right engineers. These issues make it difficult to improve the efficiency of system development and find talented engineers.

[0456] 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.

[0457] In this invention, the server includes means for collecting system requirements from users, means for automatically generating a system program using artificial intelligence based on the collected requirements, means for holding a system construction contest among multiple engineers, means for evaluating systems submitted by the engineers based on evaluation criteria and selecting winners, means for providing rewards or employment rights to the winners, and means for implementing the system using the obtained source code. This makes it possible to improve the efficiency of system development and quickly evaluate and discover talented engineers.

[0458] definition statement

[0459] "System requirements" refers to information that includes the functions and conditions necessary to build a system.

[0460] "User" means an individual or entity that provides system requirements and intends to use the system.

[0461] "Collect" refers to obtaining, organizing, and storing information provided by users.

[0462] "Generative AI" is a system that uses artificial intelligence technology to generate new information and programs.

[0463] A "system program" is a collection of code or scripts written to implement a specific function.

[0464] "Automatic generation" refers to the mechanical creation of programs or information without human intervention.

[0465] An "engineer" is a professional who specializes in system construction and program development.

[0466] A "system construction contest" is an event in which multiple engineers build systems based on specified requirements and compete with each other for the best results.

[0467] "Evaluation criteria" are the indicators and standards for evaluating submitted systems and programs.

[0468] A "prize winner" is a person or organization that has demonstrated outstanding achievement in a contest or other competition.

[0469] "Reward" is the consideration of money, goods, etc. provided to those who achieve outstanding results.

[0470] "Right of employment" refers to being qualified to fill a particular job or role.

[0471] "Source code" is the original program text that describes the operation of a system or application.

[0472] "Implementation" refers to the process of giving shape to a designed system or program in a form that actually works.

[0473] MODE FOR CARRYING OUT THE INVENTION

[0474] This invention provides a system construction process that utilizes a generative AI model. This system allows efficient system development through a series of processes: a user inputs system requirements, a server automatically generates system code using a generative AI model, and then engineers participate in a system construction contest and are evaluated.

[0475] Hardware and Software

[0476] Users use devices (PCs, smartphones, etc.) to enter system requirements through web forms or applications, and the data entered by the user is sent from the device to a server via the Internet.

[0477] The server receives and organizes the input requirements. It uses a database to store the requirements in dictionary format. Specifically, the server stores the data in JSON format, with fields such as the system name, required functionality, and deadline.

[0478] Next, the server calls a generative AI model (e.g., OpenAI's GPT-3) based on the collected requirements and automatically generates system code. The server then calls the API of the generative AI model and sends prompt statements based on the requirements to the generative AI model.

[0479] The server receives the code returned by the generative AI model and saves it in a format that can be used by engineers. After that, users (engineers) use their devices to participate in the system construction contest. The engineers build a system based on the generated basic code and upload the results back to the server.

[0480] The server evaluates the submitted systems based on criteria, such as the completeness of the system's functionality and the efficiency of its code, using automated test scripts and static analysis tools.

[0481] Finally, the server will select winners based on the evaluation results and provide them with rewards and employment rights. The server will deploy the source code provided by the winners, adjust it according to the actual business environment and user requirements, and put the system into operation.

[0482] Specific examples

[0483] For example, when building an online shopping system, the user inputs the following requirements:

[0484] System name: Online shopping

[0485] Required functions: cart function, payment function

[0486] Deadline: 1 week later

[0487] The server receives these requirements and passes them to a generative AI model, which then generates basic code for the online shopping system. Here's an example prompt:

[0488] System name: Online Shopping

[0489] Required features: cart function, payment function

[0490] Deadline: 1 week later

[0491] Generate Python code based on this requirement.

[0492] Based on the generated code, users (engineers) build and submit systems. The server evaluates the submitted systems and selects the top three engineers. These engineers are offered rewards and employment rights. Finally, the server implements the winning code and launches the online shopping system.

[0493] The above process allows systems to be built efficiently in a short period of time, reducing development costs and enabling the discovery and recruitment of talented engineers.

[0494] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0495] Processing Steps

[0496] Step 1:

[0497] Users input system requirements through a web form or application, and the input system requirements (e.g., system name, required functions, deadline) are sent from the terminal to the server.

[0498] Input: System name, required functionality, deadline

[0499] Output: User-entered system requirements data

[0500] Specific operation: The user enters "online shopping," "cart function, payment function," and "one week later" into the form on the terminal, and clicks the "Submit" button.

[0501] Step 2:

[0502] The server organizes the system requirements received from the terminals and stores them in a database in dictionary format.

[0503] Input: System requirements data sent from the device

[0504] Output: Organized requirements data (dictionary format)

[0505] Specific operation: The server parses the data received in JSON format and saves it into the fields "System name," "Required functions," and "Deadline."

[0506] Step 3:

[0507] The server generates a prompt sentence based on the collected requirements and calls the API of a generative AI model (e.g., OpenAI GPT-3).

[0508] Input: Organized requirements data

[0509] Output: Prompt text to send to the generative AI model

[0510] Specific operation: The server generates a prompt text "System name: online shopping, Required functions: cart function, payment function, Deadline: 1 week later" and sends it to the API of the generative AI model.

[0511] Step 4:

[0512] The generative AI model generates system code based on the prompt sentence and returns it to the server.

[0513] Input: prompt statement

[0514] Output: Generated system code

[0515] Specific operation: The generative AI model parses the prompt sentence, generates Python code, and sends it back to the server.

[0516] Step 5:

[0517] The server receives the generated system code, formats it in a format that can be used by engineers, and saves it.

[0518] Input: System code received from the generative AI model

[0519] Output: pretty-printed system code

[0520] What it does: The server formats the code and stores it in a repository where engineers can download it.

[0521] Step 6:

[0522] Users (engineers) use their own terminals to participate in the system construction contest and build a system based on the provided system code.

[0523] Input: Formatted system code

[0524] Output: System built by engineers

[0525] Specific operation: Engineers import the provided code into their own development environment and add features or make improvements.

[0526] Step 7:

[0527] The user (engineer) submits the constructed system to the server.

[0528] Input: System built by engineers

[0529] Output: System code uploaded to the server

[0530] Specific operation: The engineer attaches a file to a form to upload the completed system code to the server and clicks the "Submit" button.

[0531] Step 8:

[0532] The server evaluates the submitted systems based on the evaluation criteria and assigns them a score.

[0533] Input: Submitted system code

[0534] Output: Evaluation result (score)

[0535] What it does: The server uses automated test scripts and static analysis tools to evaluate the system's functional completeness and code efficiency.

[0536] Step 9:

[0537] The server will select winners based on the evaluation results and notify them of their rewards and employment rights.

[0538] Input: Evaluation result (score)

[0539] Output: Winner selection and notification

[0540] Specific operation: The server selects the top three engineers based on the evaluation results and sends a notification email.

[0541] Step 10:

[0542] The server deploys the obtained source code and begins operation in the production environment.

[0543] Input: Winner's source code

[0544] Output: Operational system

[0545] What happens: The server runs the deploy script to put the system into production, updating configuration files and initializing the database as needed.

[0546] (Application example 1)

[0547] 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."

[0548] In the traditional system construction process, users must define system requirements in detail, and engineers must manually develop code based on those requirements, which requires a significant amount of time and effort. Furthermore, in complex systems such as virtual stores, users often find it difficult to intuitively input requirements. This has led to issues with reduced efficiency and speed in system construction.

[0549] 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.

[0550] In this invention, the server includes a means for converting user input into text data using voice recognition technology, a means for providing a visual interface for the user via a device such as smart glasses, and a means for implementing the system using the source code used, which allows the user to intuitively input system requirements and enables efficient and rapid system construction.

[0551] "Speech recognition technology" refers to technology that converts a user's voice into text data.

[0552] "Text data" refers to character string data generated using speech recognition technology.

[0553] "Smart glasses" refers to a wearable device that provides information to the user as a visual interface.

[0554] A "visual interface" is a means of providing information visually to a user, including displays and AR technology.

[0555] A "generative AI model" refers to an artificial intelligence model that automatically generates program code based on user input data.

[0556] "Server" refers to a computer system that processes and stores data.

[0557] "System requirements" refer to the specific functions and conditions that users require from a system.

[0558] "Source code" refers to the code of a program written to operate a system.

[0559] "Deployment" refers to the process of placing source code into an actual production environment and running the system.

[0560] "Engineer" refers to a technician in charge of system design and development.

[0561] A "contest" refers to a competitive event in which engineers compete to see who can build the best systems.

[0562] "Evaluation criteria" refers to specific performance and functional indicators that a system must meet.

[0563] "Winner" means the person who submitted the most outstanding work based on the evaluation criteria.

[0564] "Reward" refers to the monetary incentive offered to the winner.

[0565] "Contract Rights" means the formal contract rights provided to the Prize Winner.

[0566] This invention relates to a system that efficiently collects system requirements using voice recognition technology and automatically generates program code using a generative AI model. The system provides a visual interface to users via smart glasses and assists in data processing and code deployment on a server.

[0567] The user wears the smart glasses and uses voice recognition technology to input system requirements by voice. The smart glasses are equipped with a speech recognition engine such as the Google Cloud Speech-to-Text API, which converts the voice input into text data with high accuracy. This text data is then sent to the server. The server analyzes the system requirements received from the user and generates appropriate prompts.

[0568] As a concrete example, consider the case of building an online shopping system. A user inputs the following requirements by voice through smart glasses:

[0569] System requirements:

[0570] System name: Online shopping system

[0571] Required functions: product list display function, cart function, voice payment function

[0572] Deadline: 1 week later

[0573] The server receives these requirements as text data and generates a prompt to proceed, such as:

[0574] Generate basic program code for an online shopping system based on the following requirements:

[0575] Requirements:

[0576] System name: Online shopping system

[0577] Required features: Product list display function, cart function, voice payment function

[0578] Deadline: 1 week later

[0579] Using a generative AI model (e.g., OpenAI's GPT-3), appropriate program code is generated based on this prompt. The generated code is then submitted to a competition in which engineers participate and are evaluated based on criteria. The best engineers are offered rewards or contract rights.

[0580] Finally, the server deploys the best source code obtained, and the system moves into production. Deployment tools such as Jenkins can be used for deployment. This system allows users to intuitively and efficiently input system requirements and build high-quality systems in a short period of time.

[0581] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0582] Step 1:

[0583] The user wears the smart glasses and inputs system requirements using voice recognition technology, which uses the smart glasses' built-in microphone to convert speech into text data via the Google Cloud Speech-to-Text API. The input for this step is the user's voice input, and the output is the converted text data.

[0584] Step 2:

[0585] The server receives the text data (system requirements) sent from the smart glasses and stores it in a database. The received text data is organized in a dictionary format. The input of this step is the text data, and the output is the system requirements stored in the database.

[0586] Step 3:

[0587] The server generates prompt sentences for the generative AI model based on the saved system requirements. The prompt sentences are used in API calls to the generative AI model (such as OpenAI's GPT-3). The input of this step is the organized system requirements, and the output is the generated prompt sentences.

[0588] Step 4:

[0589] Using the generated prompt sentence, the server calls the API of the generative AI model to generate program code. The generative AI model automatically generates appropriate code based on the prompt sentence. The input of this step is the prompt sentence, and the output is the generated program code.

[0590] Step 5:

[0591] Engineers receive the generated code from the server and participate in a system construction contest. Based on the specified system requirements, the engineers customize the generated code and build the final system. The input of this step is the generated program code, and the output is the system built by the engineers.

[0592] Step 6:

[0593] The server evaluates the systems submitted by engineers based on the evaluation criteria. The evaluation is based on multiple indicators such as the completeness of the system's functions and the efficiency of the code. The input of this step is the engineer's submitted system, and the output is an evaluation score and ranking.

[0594] Step 7:

[0595] The server selects winners based on the rankings and provides rewards or contract rights to the winners. The input of this step is the evaluation score and ranking, and the output is the list of winners and the provision of rewards or contract rights.

[0596] Step 8:

[0597] The server uses the winner's source code to implement the virtual store system. A deployment tool such as Jenkins is used for deployment. The input for this step is the winner's source code, and the output is the actual virtual store system that will be put into operation.

[0598] 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.

[0599] This invention provides a system that combines a system construction process using generative AI with an emotion engine that recognizes user emotions. The series of processes is explained below.

[0600] First, the user inputs the system requirements (e.g., system name, required functions, deadline). This input is done via a web form or application, and the terminal sends this to the server. The server receives and organizes the requirements received from the user.

[0601] The server then uses an emotion engine to recognize emotions based on the user's input data. The emotion engine uses natural language processing technology to analyze emotions from the user's text input and feeds the results back to the system requirements collection means. For example, if the user inputs "I want to complete it quickly," the urgency is recognized.

[0602] The server then calls the generative AI model based on the collected requirements and automatically generates system code. Here, the analysis results from the emotion engine are also reflected in the generative AI model, so if the user is in a hurry, for example, code that prioritizes development speed will be generated.

[0603] Users (engineers) participate in the contest and build systems based on basic system code provided by the generative AI model. The engineers then submit the systems they build to the server.

[0604] The server will evaluate the submitted systems based on criteria, including the completeness of the system's functions and the efficiency of the code. Based on the results, the server will select winners and offer prize money and employment opportunities to the engineers who build the best systems.

[0605] Finally, the server will use the source code obtained to implement the system and put it into operation. The system deployment process will be adjusted according to the actual business environment and user requirements.

[0606] Specific examples

[0607] For example, consider a user building an online shopping system. The user inputs the following requirements:

[0608] System name: Online shopping

[0609] Required functions: cart function, payment function

[0610] Deadline: 1 week later

[0611] The server receives these requirements and further analyzes the user's emotions using an emotion engine. For example, if the user adds, "I need this to be done quickly," the emotion engine recognizes the urgency. The server sends this emotion data to a generative AI model, which generates code that can also handle urgent requirements.

[0612] Engineers build and submit systems based on this generated code. The server evaluates the submitted systems and selects the top three engineers. These engineers are offered prize money and employment opportunities. Finally, the server implements the winner's code and launches the online shopping system.

[0613] This process allows systems to be built efficiently in a short period of time, significantly reducing system development costs. Also, by reflecting user emotions, it is possible to provide a system that provides greater satisfaction.

[0614] The processing flow will be explained below.

[0615] Step 1:

[0616] The user enters system requirements (e.g., system name, required functions, deadline) through a web form or application. For example, the user enters requirements such as "online shopping," "cart function," "payment function," and "one week later."

[0617] Step 2:

[0618] The terminal transmits the input requirements to the server, and the user's terminal transmits the input data to the server via the Internet.

[0619] Step 3:

[0620] The server organizes the received requirements and converts them into a dictionary format. The server analyzes the received data and organizes and saves information such as the system name, required functions, and deadlines.

[0621] Step 4:

[0622] The server uses an emotion engine to recognize emotions from the user's input data. The emotion engine uses natural language processing technology to analyze emotions from the user's text input. For example, if the user enters "I want to finish it quickly," the emotion engine will recognize the user's high sense of urgency.

[0623] Step 5:

[0624] The emotion engine reflects the emotion analysis results in the system requirements, and the server stores the recognized emotion data (e.g., high urgency) as part of the requirements.

[0625] Step 6:

[0626] The server automatically generates system code by invoking a generative AI model based on the requirements and emotion data collected. The generative AI model (e.g., GPT-3) generates system code based on the requirements and emotion data.

[0627] Step 7:

[0628] The server stores the generated system code and makes it accessible to users (engineers). Engineers access the generated system code and make any necessary modifications or additions.

[0629] Step 8:

[0630] Users (engineers) participate in the contest and build a system based on the basic system code provided by the generative AI model. The engineers then modify and expand the code, aiming to complete the system.

[0631] Step 9:

[0632] Engineers submit the completed system to the server. Engineers upload the completed system code to the server.

[0633] Step 10:

[0634] The server evaluates the submitted systems based on criteria, including the completeness of the system's functionality and the efficiency of the code. The server then scores each engineer's system based on these criteria.

[0635] Step 11:

[0636] The server will select winners based on the evaluation results, and offer prize money and employment rights to the engineers who have built the best systems. The server will select the engineers with the highest scores and notify them.

[0637] Step 12:

[0638] The server will implement the system using the winner's source code and begin operation. The server will then import the winner's code and deploy it to the actual production environment.

[0639] For example, if a user inputs, "I want to build an online shopping system, I need a cart function and a payment function, the deadline is one week from now, I'm in a hurry," the server will recognize these requirements and the urgency, and generate system code that can quickly respond using a generative AI model. Engineers will build a system based on this, and the best system will be selected after evaluation and finally deployed. This process makes it possible to build high-quality systems in a short period of time.

[0640] Example 2

[0641] 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."

[0642] In conventional system development processes, it is difficult to fully reflect factors such as user emotions and urgency, resulting in low user satisfaction. Furthermore, while there has been some technological progress in automatic system code generation, there is a lack of a method for quickly and efficiently responding to specific user requirements. Therefore, there is a need to establish an efficient system development method that simultaneously considers user requirements and emotions.

[0643] 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.

[0644] In this invention, the server includes means for collecting system requirements from users, means for using an emotion engine that recognizes user emotions, means for evaluating and feeding back the emotion data recognized by the emotion engine, and means for automatically generating system code using a generation AI based on the collected requirements and emotion data. This enables the construction of an efficient system that simultaneously reflects user requirements and emotions.

[0645] "System requirements" refers to elements necessary for system construction, such as the system name, required functions, deadlines, etc., collected from users.

[0646] An "emotion engine" is a machine learning model or algorithm that uses natural language processing technology to analyze and recognize emotions from user input data.

[0647] "Emotion data" refers to the user's emotional information recognized by the emotion engine, and indicates the urgency and priority of the requirement.

[0648] "Generative AI" refers to an artificial intelligence system that automatically generates system code based on collected requirements and emotional data.

[0649] "Initial system code" refers to the code that contains the basic structure of the system, which is automatically generated by the generation AI.

[0650] The "Engineer System Building Contest" refers to a competition in which multiple engineers build systems based on initial system code provided by a generative AI model and compete based on the results.

[0651] "Evaluation Criteria" refers to the standards for evaluating submitted systems, including the completeness of the system's functionality and the efficiency of its code.

[0652] "Rights to join" refers to the right to join a specific company or project that is offered to engineers when they win a system construction contest.

[0653] "Source code" refers to the human-readable form of program code created by engineers to define the behavior of a program.

[0654] "Implementation means" refers to the process or method for using the source code obtained to deploy and operate the system in an actual operating environment.

[0655] This invention is a system that uses a generative AI model to automatically generate system code, recognizes user emotions, and reflects them in the system construction process. This system includes a server with an emotion engine, a terminal that receives user input, and a function for automatically generating system code using generative AI.

[0656] First, the user enters the system requirements using a web form or application. Input items include the system name, required functions, and deadline. This input data is sent to the server via the terminal. The data is encrypted and reaches the server in a secure manner.

[0657] The server organizes the received system requirements and uses an emotion engine to recognize the user's emotions. The emotion engine uses natural language processing technology to analyze emotions from the user's text input. For example, if the user enters "I want to finish it quickly," the emotion engine will recognize the urgency.

[0658] The server then evaluates the emotion data recognized by the emotion engine and feeds it back into a database of system requirements, which are then used by the generative AI model to generate system code.

[0659] The server calls the API of the generative AI model based on the collected requirements and emotion data, and automatically generates system code. This generative AI model generates optimal code according to the provided prompt. An example of a prompt is shown below:

[0660] System name: Online Shopping

[0661] Required features: cart function, payment function

[0662] Deploy to: AWS

[0663] Additional information: The user expressed a desire to "finish quickly"

[0664] Deadline: 1 week

[0665] The user (engineer) builds a system based on the initial system code provided by the generative AI model. The engineer then submits the built system to the server. The server evaluates the submitted systems based on evaluation criteria and selects the top engineer. The evaluation criteria include the completeness of the system's functions and the efficiency of the code.

[0666] Finally, the server implements the system using the source code obtained and puts it into operation. The system is adjusted according to the actual business environment and user requirements, enabling efficient and rapid operation.

[0667] The above process makes it possible to build a system that simultaneously considers the user's requirements and emotions, and to provide a high-quality system in a short period of time.

[0668] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0669] Step 1:

[0670] Users enter system requirements (system name, required functions, deadline) using a web form or application, and the entered data is sent to the server via the terminal.

[0671] Input: System name, required functionality, deadline, etc.

[0672] Output: Requirement data sent to the server

[0673] Specifically, after the requirements are entered, a button is clicked and the data is sent to the server, where it is encrypted and transmitted over a secure channel.

[0674] Step 2:

[0675] The server organizes the received requirements data and analyzes the sentiment from the user's input text using an emotion engine, which uses natural language processing algorithms (e.g., sentiment analysis APIs).

[0676] Input: Requirement data sent by the user

[0677] Output: Parsed emotion data

[0678] Specifically, the server analyzes the received data and inputs the text data into the emotion engine, which then analyzes emotions such as urgency and anxiety and returns the data.

[0679] Step 3:

[0680] The server evaluates the emotion analysis results from the emotion engine and feeds them back to the system requirements database, so that the analysis results can be used in the next step.

[0681] Input: Sentiment analysis results

[0682] Output: Updated system requirements database

[0683] Specifically, the results of the sentiment analysis are stored in a database, which serves as reference data for the next generative AI model to generate code.

[0684] Step 4:

[0685] The server calls the API of the generative AI model and automatically generates system code based on the collected requirements and emotion data. The generative AI model generates code using prompt sentences as input.

[0686] Input: System requirements, emotion data

[0687] Output: Auto-generated initial system code

[0688] Specifically, the server inputs the following prompt sentence into the generative AI model:

[0689] System name: Online Shopping

[0690] Required features: cart function, payment function

[0691] Deploy to: AWS

[0692] Additional information: The user expressed a desire to "finish quickly"

[0693] Deadline: 1 week

[0694] This allows the generative AI model to generate system code.

[0695] Step 5:

[0696] The user (engineer) receives the generated initial system code and builds the system. The engineer customizes the code and runs tests.

[0697] Input: Initial system code provided by the generative AI model

[0698] Output: The constructed system

[0699] Specifically, engineers use an IDE to develop and adjust code, then check its operation in a test environment.

[0700] Step 6:

[0701] Users (engineers) submit their completed systems to the server. The submitted system code must follow a specified format and procedure.

[0702] Input: System code built by engineers

[0703] Output: The system submitted to the server

[0704] Specifically, an engineer uses a submission interface to upload the system to a server.

[0705] Step 7:

[0706] The server evaluates submitted systems based on criteria, including the completeness of the system's functionality and the efficiency of its code.

[0707] Input: Submitted system code

[0708] Output: Evaluation results

[0709] Specifically, the server evaluates the systems through an automated rating system or rating committee and assigns them a score or ranking.

[0710] Step 8:

[0711] The server will select the winners based on the evaluation results and provide them with prize money and employment opportunities.

[0712] Input: Evaluation result

[0713] Output: Selection of winners and award of prize money and employment rights

[0714] Specifically, the server sends a notification to the senior engineer and executes the procedure for providing the bonus and employment rights.

[0715] Step 9:

[0716] Finally, the server implements the system using the source code it has obtained and begins operation.

[0717] Input: The source code of the winner

[0718] Output: Implemented system

[0719] As a concrete operation, the server executes the deployment process automatically or manually and starts the system operation, thereby providing a high-quality system that reflects the user's requirements and feelings.

[0720] (Application example 2)

[0721] 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."

[0722] In modern system development processes, system code is often generated based only on simple functional requirements without considering user emotions. This often results in insufficient responses to users' actual needs and urgency. Furthermore, particularly in brick-and-mortar stores, product recommendations do not reflect users' emotional state, making it difficult to improve customer satisfaction.

[0723] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting system requirements from a user, means for automatically generating system code using a generation AI based on the collected requirements, means for analyzing the user's emotional state using emotion recognition software and reflecting the analysis results in the generation AI, and means for displaying information to the user via a smart device and making optimal suggestions based on the user's emotional state. This enables code generation that reflects the user's emotions and optimal product suggestions based on real-time emotion analysis.

[0724] "System requirements" are specific requirements such as functions, characteristics, deadlines, etc. that users require from a system.

[0725] "Generative AI" is an artificial intelligence technology that automatically generates program code using pre-trained models.

[0726] "Engineer" refers to an engineer with specialized knowledge who designs and develops systems.

[0727] A "construction contest" is a competition in which multiple engineers build systems and compete against each other in terms of their technical skills.

[0728] "Evaluation criteria" are indicators or standards for evaluating the quality and performance of submitted systems or programs.

[0729] "Reward" refers to the money or benefits provided to engineers in exchange for winning the award.

[0730] "Right of entry" refers to the right given to engineers to join a company.

[0731] "Program code" means a set of instructions written to run a system or piece of software.

[0732] "Implementation" is the activity of developing and constructing a designed system or program in a form that can actually be used.

[0733] "Emotion recognition software" is a program that analyzes a user's emotional state from facial expressions, voice, etc.

[0734] "Smart devices" refer to advanced devices that have internet connectivity and can run a variety of applications.

[0735] To implement this invention, the following system configuration and processing are required. The system consists of a user, a server, and a smart device (e.g., smart glasses). The entire system operates around emotion recognition software and a generative AI model.

[0736] System configuration

[0737] 1. User interface: The user uses an interface (e.g., a web form or an application) to input system requirements. Through this interface, the user inputs system requirements (system name, required functions, deadline, etc.).

[0738] 2. Server: The server is implemented with a program that provides the following functions:

[0739] Data collection: Receiving and organizing user input data.

[0740] Emotion analysis: Using emotion recognition software (e.g., Amazon Rekognition), emotions are analyzed from user input data, facial expressions, and voice.

[0741] Generative AI model: Invoke a generative AI model (e.g., OpenAI GPT-4) to automatically generate system code based on the collected requirements and sentiment data.

[0742] Evaluation and selection: A system building contest will be held among multiple engineers, and the submitted systems will be evaluated based on the evaluation criteria to select the winners.

[0743] Reward Offer: Offer rewards or employment rights to winners.

[0744] Implementation and deployment: Using the obtained program code, the system is implemented and put into operation.

[0745] 3. Smart devices: Smart devices such as smart glasses will be used to analyze users' emotions in real time and make optimal product recommendations.

[0746] Emotion analysis: The smart glasses' camera and microphone capture the user's facial expressions and voice and send them to the server.

[0747] Information display: Optimal suggestions and product information based on emotional data are displayed on smart glasses.

[0748] Specific example explanation

[0749] Take the example of a user using smart glasses while shopping in a brick-and-mortar store.

[0750] 1. Data capture: When a user looks at an item in a store, the camera and microphone in the smart glasses capture facial and voice data.

[0751] 2. Emotion analysis: The captured data is sent to a server and analyzed by emotion recognition software.

[0752] 3. Generative AI model: Based on the analyzed emotional state and collected system requirements, the generative AI model (GPT-4) generates optimal product suggestions.

[0753] 4. Information display: The generated suggestions are displayed to the user in real time through the smart glasses.

[0754] Prompt Sentence Examples

[0755] TXT

[0756] Emotion recognition software API call

[0757] emotion_data = recognize_emotion(captured_image, captured_audio)

[0758] Prompt sentence for generative AI model

[0759] prompt_text = "Generate the best product suggestions if the user is feeling " + emotion_data['emotion'] + "."

[0760] Invoke the GPT-4 model

[0761] optimized_recommendation = generate_recommendation(prompt_text)

[0762] Displaying suggested product information on smart glasses

[0763] display_on_smart_glasses(optimized_recommendation)

[0764] The configuration and processing of this system makes it possible to build an optimal system that reflects the user's emotions and make real-time suggestions, thereby providing a shopping experience that highly satisfies the user.

[0765] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0766] Step 1:

[0767] The user inputs system requirements. The system name, required functions, deadline, etc. are entered through an input interface (e.g., a web form or application), and this is sent from the terminal to the server. Input data might include the system name "online shopping," required functions "cart function, payment function," and deadline "one week later." This data is sent to the server as output.

[0768] Step 2:

[0769] The server organizes the received system requirements data and sends it to emotion recognition software. The data also includes additional information such as the user's "I want to complete this quickly." The emotion recognition software analyzes this text data and identifies the user's emotional state. The output is emotion data such as "high urgency."

[0770] Step 3:

[0771] The server sends the emotion data obtained from the emotion recognition software and the system requirements to the generative AI model, and creates a prompt that automatically generates the system code. For example, it creates a prompt that reads, "If the user feels a high level of urgency, please generate code for the system name online shopping, with the required functions cart and payment functions, so that it can be completed within one week." This prompt is then sent to the generative AI model as output.

[0772] Step 4:

[0773] The server holds a system building contest among multiple engineers based on the system code obtained from the generative AI model. The engineers build systems based on this code and submit them to the server. The input is the system code built by the engineers, and the output is the collection of multiple submitted systems on the server.

[0774] Step 5:

[0775] The server evaluates each submitted system based on evaluation criteria, which include functional completeness, code efficiency, etc. The output is an evaluation result for each system.

[0776] Step 6:

[0777] The server selects winners based on the evaluation results, and provides rewards and employment opportunities to the winners. The output is a list of winners and the reward details.

[0778] Step 7:

[0779] The server implements the system using the obtained best system code and starts operation. The output is a working system that is built and available to users.

[0780] 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.

[0781] 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.

[0782] 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.

[0783] [Third embodiment]

[0784] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0785] 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.

[0786] 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).

[0787] 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.

[0788] 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.

[0789] 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).

[0790] 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.

[0791] 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.

[0792] 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.

[0793] 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.

[0794] 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.

[0795] 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."

[0796] The present invention provides a system construction process that utilizes generative AI. The series of processes is explained below.

[0797] First, the user inputs the system requirements (e.g., system name, required functions, deadline). This input is done via a web form or application, and the terminal sends it to the server. The server receives the requirements from the user and organizes them for further processing. At this stage, the system requirements are saved in dictionary format.

[0798] Next, the server calls a generative AI model based on the collected system requirements to automatically generate system code. The generative AI model could use OpenAI's GPT-3, for example. Based on the collected requirements, the generative AI model generates appropriate program code, which the server receives.

[0799] After that, users (engineers) participate in the contest. The contest is an event where engineers submit systems they have built using generative AI. Engineers build systems based on specified system requirements and submit their results to the server.

[0800] The server evaluates the submitted systems based on a set of criteria, including the completeness of the system's functions and the efficiency of its code. Based on the results, the server selects winners and offers prize money and employment opportunities to the engineers who build the best systems.

[0801] Finally, the server will implement the system using the source code obtained, deploy the winner's code, and put the system into operation. This deployment process will be adjusted according to the actual business environment and user requirements.

[0802] Specific examples

[0803] For example, consider building an online shopping system. The user inputs the following requirements:

[0804] System name: Online shopping

[0805] Required functions: cart function, payment function

[0806] Deadline: 1 week later

[0807] The server receives these requirements and passes them to a generative AI model. Based on this, the generative AI model generates basic code for the online shopping system. Engineers build systems based on this code and submit them. The server evaluates the submitted systems and selects the top three engineers. These engineers are offered prize money and employment opportunities. Finally, the server implements the winning code and launches the online shopping system.

[0808] This process allows systems to be built efficiently in a short period of time, significantly reducing system development costs, while also enabling the discovery and recruitment of talented engineers.

[0809] The processing flow will be explained below.

[0810] Step 1:

[0811] A user enters system requirements (e.g., system name, required features, deadline) through a web form or application.

[0812] Step 2:

[0813] The terminal transmits the input requirements to the server.

[0814] Step 3:

[0815] The server organizes the received requirements, converts them into dictionary format, and saves them.

[0816] Step 4:

[0817] The server sends the collected requirements to the API of the generative AI model, which then automatically generates system code.

[0818] Step 5:

[0819] The generative AI model generates system code based on the given requirements, which is then received by the server.

[0820] Step 6:

[0821] Users (engineers) participate in the contest and build systems using generative AI models.

[0822] Step 7:

[0823] The engineer submits the system he built to the server.

[0824] Step 8:

[0825] The server evaluates the submitted systems based on criteria, including the completeness of the system's functionality and the efficiency of its code.

[0826] Step 9:

[0827] The server will select winners based on the evaluation results, and will offer prize money and employment rights to engineers who build excellent systems.

[0828] Step 10:

[0829] The server will implement the system using the winner's source code, deploy the system and put it into operation.

[0830] The above is the specific processing flow of the system construction process using generative AI.

[0831] Example 1

[0832] 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."

[0833] Traditional system development processes have had problems such as long development times and rising costs. Furthermore, there are limited means for quickly evaluating and hiring the right engineers. These issues make it difficult to improve the efficiency of system development and find talented engineers.

[0834] 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.

[0835] In this invention, the server includes means for collecting system requirements from users, means for automatically generating a system program using artificial intelligence based on the collected requirements, means for holding a system construction contest among multiple engineers, means for evaluating systems submitted by the engineers based on evaluation criteria and selecting winners, means for providing rewards or employment rights to the winners, and means for implementing the system using the obtained source code. This makes it possible to improve the efficiency of system development and quickly evaluate and discover talented engineers.

[0836] definition statement

[0837] "System requirements" refers to information that includes the functions and conditions necessary to build a system.

[0838] "User" means an individual or entity that provides system requirements and intends to use the system.

[0839] "Collect" refers to obtaining, organizing, and storing information provided by users.

[0840] "Generative AI" is a system that uses artificial intelligence technology to generate new information and programs.

[0841] A "system program" is a collection of code or scripts written to implement a specific function.

[0842] "Automatic generation" refers to the mechanical creation of programs or information without human intervention.

[0843] An "engineer" is a professional who specializes in system construction and program development.

[0844] A "system construction contest" is an event in which multiple engineers build systems based on specified requirements and compete with each other for the best results.

[0845] "Evaluation criteria" are the indicators and standards for evaluating submitted systems and programs.

[0846] A "prize winner" is a person or organization that has demonstrated outstanding achievement in a contest or other competition.

[0847] "Reward" is the consideration of money, goods, etc. provided to those who achieve outstanding results.

[0848] "Right of employment" refers to being qualified to fill a particular job or role.

[0849] "Source code" is the original program text that describes the operation of a system or application.

[0850] "Implementation" refers to the process of giving shape to a designed system or program in a form that actually works.

[0851] MODE FOR CARRYING OUT THE INVENTION

[0852] This invention provides a system construction process that utilizes a generative AI model. This system allows efficient system development through a series of processes: a user inputs system requirements, a server automatically generates system code using a generative AI model, and then engineers participate in a system construction contest and are evaluated.

[0853] Hardware and Software

[0854] Users use devices (PCs, smartphones, etc.) to enter system requirements through web forms or applications, and the data entered by the user is sent from the device to a server via the Internet.

[0855] The server receives and organizes the input requirements. It uses a database to store the requirements in dictionary format. Specifically, the server stores the data in JSON format, with fields such as the system name, required functionality, and deadline.

[0856] Next, the server calls a generative AI model (e.g., OpenAI's GPT-3) based on the collected requirements and automatically generates system code. The server then calls the API of the generative AI model and sends prompt statements based on the requirements to the generative AI model.

[0857] The server receives the code returned by the generative AI model and saves it in a format that can be used by engineers. After that, users (engineers) use their devices to participate in the system construction contest. The engineers build a system based on the generated basic code and upload the results back to the server.

[0858] The server evaluates the submitted systems based on criteria, such as the completeness of the system's functionality and the efficiency of its code, using automated test scripts and static analysis tools.

[0859] Finally, the server will select winners based on the evaluation results and provide them with rewards and employment rights. The server will deploy the source code provided by the winners, adjust it according to the actual business environment and user requirements, and put the system into operation.

[0860] Specific examples

[0861] For example, when building an online shopping system, the user inputs the following requirements:

[0862] System name: Online shopping

[0863] Required functions: cart function, payment function

[0864] Deadline: 1 week later

[0865] The server receives these requirements and passes them to a generative AI model, which then generates basic code for the online shopping system. Here's an example prompt:

[0866] System name: Online Shopping

[0867] Required features: cart function, payment function

[0868] Deadline: 1 week later

[0869] Generate Python code based on this requirement.

[0870] Based on the generated code, users (engineers) build and submit systems. The server evaluates the submitted systems and selects the top three engineers. These engineers are offered rewards and employment rights. Finally, the server implements the winning code and launches the online shopping system.

[0871] The above process allows systems to be built efficiently in a short period of time, reducing development costs and enabling the discovery and recruitment of talented engineers.

[0872] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0873] Processing Steps

[0874] Step 1:

[0875] Users input system requirements through a web form or application, and the input system requirements (e.g., system name, required functions, deadline) are sent from the terminal to the server.

[0876] Input: System name, required functionality, deadline

[0877] Output: User-entered system requirements data

[0878] Specific operation: The user enters "online shopping," "cart function, payment function," and "one week later" into the form on the terminal, and clicks the "Submit" button.

[0879] Step 2:

[0880] The server organizes the system requirements received from the terminals and stores them in a database in dictionary format.

[0881] Input: System requirements data sent from the device

[0882] Output: Organized requirements data (dictionary format)

[0883] Specific operation: The server parses the data received in JSON format and saves it into the fields "System name," "Required functions," and "Deadline."

[0884] Step 3:

[0885] The server generates a prompt sentence based on the collected requirements and calls the API of a generative AI model (e.g., OpenAI GPT-3).

[0886] Input: Organized requirements data

[0887] Output: Prompt text to send to the generative AI model

[0888] Specific operation: The server generates a prompt text "System name: online shopping, Required functions: cart function, payment function, Deadline: 1 week later" and sends it to the API of the generative AI model.

[0889] Step 4:

[0890] The generative AI model generates system code based on the prompt sentence and returns it to the server.

[0891] Input: prompt statement

[0892] Output: Generated system code

[0893] Specific operation: The generative AI model parses the prompt sentence, generates Python code, and sends it back to the server.

[0894] Step 5:

[0895] The server receives the generated system code, formats it in a format that can be used by engineers, and saves it.

[0896] Input: System code received from the generative AI model

[0897] Output: pretty-printed system code

[0898] What it does: The server formats the code and stores it in a repository where engineers can download it.

[0899] Step 6:

[0900] Users (engineers) use their own terminals to participate in the system construction contest and build a system based on the provided system code.

[0901] Input: Formatted system code

[0902] Output: System built by engineers

[0903] Specific operation: Engineers import the provided code into their own development environment and add features or make improvements.

[0904] Step 7:

[0905] The user (engineer) submits the constructed system to the server.

[0906] Input: System built by engineers

[0907] Output: System code uploaded to the server

[0908] Specific operation: The engineer attaches a file to a form to upload the completed system code to the server and clicks the "Submit" button.

[0909] Step 8:

[0910] The server evaluates the submitted systems based on the evaluation criteria and assigns them a score.

[0911] Input: Submitted system code

[0912] Output: Evaluation result (score)

[0913] What it does: The server uses automated test scripts and static analysis tools to evaluate the system's functional completeness and code efficiency.

[0914] Step 9:

[0915] The server will select winners based on the evaluation results and notify them of their rewards and employment rights.

[0916] Input: Evaluation result (score)

[0917] Output: Winner selection and notification

[0918] Specific operation: The server selects the top three engineers based on the evaluation results and sends a notification email.

[0919] Step 10:

[0920] The server deploys the obtained source code and begins operation in the production environment.

[0921] Input: Winner's source code

[0922] Output: Operational system

[0923] What happens: The server runs the deploy script to put the system into production, updating configuration files and initializing the database as needed.

[0924] (Application example 1)

[0925] 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."

[0926] In the traditional system construction process, users must define system requirements in detail, and engineers must manually develop code based on those requirements, which requires a significant amount of time and effort. Furthermore, in complex systems such as virtual stores, users often find it difficult to intuitively input requirements. This has led to issues with reduced efficiency and speed in system construction.

[0927] 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.

[0928] In this invention, the server includes a means for converting user input into text data using voice recognition technology, a means for providing a visual interface for the user via a device such as smart glasses, and a means for implementing the system using the source code used, which allows the user to intuitively input system requirements and enables efficient and rapid system construction.

[0929] "Speech recognition technology" refers to technology that converts a user's voice into text data.

[0930] "Text data" refers to character string data generated using speech recognition technology.

[0931] "Smart glasses" refers to a wearable device that provides information to the user as a visual interface.

[0932] A "visual interface" is a means of providing information visually to a user, including displays and AR technology.

[0933] A "generative AI model" refers to an artificial intelligence model that automatically generates program code based on user input data.

[0934] "Server" refers to a computer system that processes and stores data.

[0935] "System requirements" refer to the specific functions and conditions that users require from a system.

[0936] "Source code" refers to the code of a program written to operate a system.

[0937] "Deployment" refers to the process of placing source code into an actual production environment and running the system.

[0938] "Engineer" refers to a technician in charge of system design and development.

[0939] A "contest" refers to a competitive event in which engineers compete to see who can build the best systems.

[0940] "Evaluation criteria" refers to specific performance and functional indicators that a system must meet.

[0941] "Winner" means the person who submitted the most outstanding work based on the evaluation criteria.

[0942] "Reward" refers to the monetary incentive offered to the winner.

[0943] "Contract Rights" means the formal contract rights provided to the Prize Winner.

[0944] This invention relates to a system that efficiently collects system requirements using voice recognition technology and automatically generates program code using a generative AI model. The system provides a visual interface to users via smart glasses and assists in data processing and code deployment on a server.

[0945] The user wears the smart glasses and uses voice recognition technology to input system requirements by voice. The smart glasses are equipped with a speech recognition engine such as the Google Cloud Speech-to-Text API, which converts the voice input into text data with high accuracy. This text data is then sent to the server. The server analyzes the system requirements received from the user and generates appropriate prompts.

[0946] As a concrete example, consider the case of building an online shopping system. A user inputs the following requirements by voice through smart glasses:

[0947] System requirements:

[0948] System name: Online shopping system

[0949] Required functions: product list display function, cart function, voice payment function

[0950] Deadline: 1 week later

[0951] The server receives these requirements as text data and generates a prompt to proceed, such as:

[0952] Generate basic program code for an online shopping system based on the following requirements:

[0953] Requirements:

[0954] System name: Online shopping system

[0955] Required features: Product list display function, cart function, voice payment function

[0956] Deadline: 1 week later

[0957] Using a generative AI model (e.g., OpenAI's GPT-3), appropriate program code is generated based on this prompt. The generated code is then submitted to a competition in which engineers participate and are evaluated based on criteria. The best engineers are offered rewards or contract rights.

[0958] Finally, the server deploys the best source code obtained, and the system moves into production. Deployment tools such as Jenkins can be used for deployment. This system allows users to intuitively and efficiently input system requirements and build high-quality systems in a short period of time.

[0959] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0960] Step 1:

[0961] The user wears the smart glasses and inputs system requirements using voice recognition technology, which uses the smart glasses' built-in microphone to convert speech into text data via the Google Cloud Speech-to-Text API. The input for this step is the user's voice input, and the output is the converted text data.

[0962] Step 2:

[0963] The server receives the text data (system requirements) sent from the smart glasses and stores it in a database. The received text data is organized in a dictionary format. The input of this step is the text data, and the output is the system requirements stored in the database.

[0964] Step 3:

[0965] The server generates prompt sentences for the generative AI model based on the saved system requirements. The prompt sentences are used in API calls to the generative AI model (such as OpenAI's GPT-3). The input of this step is the organized system requirements, and the output is the generated prompt sentences.

[0966] Step 4:

[0967] Using the generated prompt sentence, the server calls the API of the generative AI model to generate program code. The generative AI model automatically generates appropriate code based on the prompt sentence. The input of this step is the prompt sentence, and the output is the generated program code.

[0968] Step 5:

[0969] Engineers receive the generated code from the server and participate in a system construction contest. Based on the specified system requirements, the engineers customize the generated code and build the final system. The input of this step is the generated program code, and the output is the system built by the engineers.

[0970] Step 6:

[0971] The server evaluates the systems submitted by engineers based on the evaluation criteria. The evaluation is based on multiple indicators such as the completeness of the system's functions and the efficiency of the code. The input of this step is the engineer's submitted system, and the output is an evaluation score and ranking.

[0972] Step 7:

[0973] The server selects winners based on the rankings and provides rewards or contract rights to the winners. The input of this step is the evaluation score and ranking, and the output is the list of winners and the provision of rewards or contract rights.

[0974] Step 8:

[0975] The server uses the winner's source code to implement the virtual store system. A deployment tool such as Jenkins is used for deployment. The input for this step is the winner's source code, and the output is the actual virtual store system that will be put into operation.

[0976] 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.

[0977] This invention provides a system that combines a system construction process using generative AI with an emotion engine that recognizes user emotions. The series of processes is explained below.

[0978] First, the user inputs the system requirements (e.g., system name, required functions, deadline). This input is done via a web form or application, and the terminal sends this to the server. The server receives and organizes the requirements received from the user.

[0979] The server then uses an emotion engine to recognize emotions based on the user's input data. The emotion engine uses natural language processing technology to analyze emotions from the user's text input and feeds the results back to the system requirements collection means. For example, if the user inputs "I want to complete it quickly," the urgency is recognized.

[0980] The server then calls the generative AI model based on the collected requirements and automatically generates system code. Here, the analysis results from the emotion engine are also reflected in the generative AI model, so if the user is in a hurry, for example, code that prioritizes development speed will be generated.

[0981] Users (engineers) participate in the contest and build systems based on basic system code provided by the generative AI model. The engineers then submit the systems they build to the server.

[0982] The server will evaluate the submitted systems based on criteria, including the completeness of the system's functions and the efficiency of the code. Based on the results, the server will select winners and offer prize money and employment opportunities to the engineers who build the best systems.

[0983] Finally, the server will use the source code obtained to implement the system and put it into operation. The system deployment process will be adjusted according to the actual business environment and user requirements.

[0984] Specific examples

[0985] For example, consider a user building an online shopping system. The user inputs the following requirements:

[0986] System name: Online shopping

[0987] Required functions: cart function, payment function

[0988] Deadline: 1 week later

[0989] The server receives these requirements and further analyzes the user's emotions using an emotion engine. For example, if the user adds, "I need this to be done quickly," the emotion engine recognizes the urgency. The server sends this emotion data to a generative AI model, which generates code that can also handle urgent requirements.

[0990] Engineers build and submit systems based on this generated code. The server evaluates the submitted systems and selects the top three engineers. These engineers are offered prize money and employment opportunities. Finally, the server implements the winner's code and launches the online shopping system.

[0991] This process allows systems to be built efficiently in a short period of time, significantly reducing system development costs. Also, by reflecting user emotions, it is possible to provide a system that provides greater satisfaction.

[0992] The processing flow will be explained below.

[0993] Step 1:

[0994] The user enters system requirements (e.g., system name, required functions, deadline) through a web form or application. For example, the user enters requirements such as "online shopping," "cart function," "payment function," and "one week later."

[0995] Step 2:

[0996] The terminal transmits the input requirements to the server, and the user's terminal transmits the input data to the server via the Internet.

[0997] Step 3:

[0998] The server organizes the received requirements and converts them into a dictionary format. The server analyzes the received data and organizes and saves information such as the system name, required functions, and deadlines.

[0999] Step 4:

[1000] The server uses an emotion engine to recognize emotions from the user's input data. The emotion engine uses natural language processing technology to analyze emotions from the user's text input. For example, if the user enters "I want to finish it quickly," the emotion engine will recognize the user's high sense of urgency.

[1001] Step 5:

[1002] The emotion engine reflects the emotion analysis results in the system requirements, and the server stores the recognized emotion data (e.g., high urgency) as part of the requirements.

[1003] Step 6:

[1004] The server automatically generates system code by invoking a generative AI model based on the requirements and emotion data collected. The generative AI model (e.g., GPT-3) generates system code based on the requirements and emotion data.

[1005] Step 7:

[1006] The server stores the generated system code and makes it accessible to users (engineers). Engineers access the generated system code and make any necessary modifications or additions.

[1007] Step 8:

[1008] Users (engineers) participate in the contest and build a system based on the basic system code provided by the generative AI model. The engineers then modify and expand the code, aiming to complete the system.

[1009] Step 9:

[1010] Engineers submit the completed system to the server. Engineers upload the completed system code to the server.

[1011] Step 10:

[1012] The server evaluates the submitted systems based on criteria, including the completeness of the system's functionality and the efficiency of the code. The server then scores each engineer's system based on these criteria.

[1013] Step 11:

[1014] The server will select winners based on the evaluation results, and offer prize money and employment rights to the engineers who have built the best systems. The server will select the engineers with the highest scores and notify them.

[1015] Step 12:

[1016] The server will implement the system using the winner's source code and begin operation. The server will then import the winner's code and deploy it to the actual production environment.

[1017] For example, if a user inputs, "I want to build an online shopping system, I need a cart function and a payment function, the deadline is one week from now, I'm in a hurry," the server will recognize these requirements and the urgency, and generate system code that can quickly respond using a generative AI model. Engineers will build a system based on this, and the best system will be selected after evaluation and finally deployed. This process makes it possible to build high-quality systems in a short period of time.

[1018] Example 2

[1019] 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."

[1020] In conventional system development processes, it is difficult to fully reflect factors such as user emotions and urgency, resulting in low user satisfaction. Furthermore, while there has been some technological progress in automatic system code generation, there is a lack of a method for quickly and efficiently responding to specific user requirements. Therefore, there is a need to establish an efficient system development method that simultaneously considers user requirements and emotions.

[1021] 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.

[1022] In this invention, the server includes means for collecting system requirements from users, means for using an emotion engine that recognizes user emotions, means for evaluating and feeding back the emotion data recognized by the emotion engine, and means for automatically generating system code using a generation AI based on the collected requirements and emotion data. This enables the construction of an efficient system that simultaneously reflects user requirements and emotions.

[1023] "System requirements" refers to elements necessary for system construction, such as the system name, required functions, deadlines, etc., collected from users.

[1024] An "emotion engine" is a machine learning model or algorithm that uses natural language processing technology to analyze and recognize emotions from user input data.

[1025] "Emotion data" refers to the user's emotional information recognized by the emotion engine, and indicates the urgency and priority of the requirement.

[1026] "Generative AI" refers to an artificial intelligence system that automatically generates system code based on collected requirements and emotional data.

[1027] "Initial system code" refers to the code that contains the basic structure of the system, which is automatically generated by the generation AI.

[1028] The "Engineer System Building Contest" refers to a competition in which multiple engineers build systems based on initial system code provided by a generative AI model and compete based on the results.

[1029] "Evaluation Criteria" refers to the standards for evaluating submitted systems, including the completeness of the system's functionality and the efficiency of its code.

[1030] "Rights to join" refers to the right to join a specific company or project that is offered to engineers when they win a system construction contest.

[1031] "Source code" refers to the human-readable form of program code created by engineers to define the behavior of a program.

[1032] "Implementation means" refers to the process or method for using the source code obtained to deploy and operate the system in an actual operating environment.

[1033] This invention is a system that uses a generative AI model to automatically generate system code, recognizes user emotions, and reflects them in the system construction process. This system includes a server with an emotion engine, a terminal that receives user input, and a function for automatically generating system code using generative AI.

[1034] First, the user enters the system requirements using a web form or application. Input items include the system name, required functions, and deadline. This input data is sent to the server via the terminal. The data is encrypted and reaches the server in a secure manner.

[1035] The server organizes the received system requirements and uses an emotion engine to recognize the user's emotions. The emotion engine uses natural language processing technology to analyze emotions from the user's text input. For example, if the user enters "I want to finish it quickly," the emotion engine will recognize the urgency.

[1036] The server then evaluates the emotion data recognized by the emotion engine and feeds it back into a database of system requirements, which are then used by the generative AI model to generate system code.

[1037] The server calls the API of the generative AI model based on the collected requirements and emotion data, and automatically generates system code. This generative AI model generates optimal code according to the provided prompt. An example of a prompt is shown below:

[1038] System name: Online Shopping

[1039] Required features: cart function, payment function

[1040] Deploy to: AWS

[1041] Additional information: The user expressed a desire to "finish quickly"

[1042] Deadline: 1 week

[1043] The user (engineer) builds a system based on the initial system code provided by the generative AI model. The engineer then submits the built system to the server. The server evaluates the submitted systems based on evaluation criteria and selects the top engineer. The evaluation criteria include the completeness of the system's functions and the efficiency of the code.

[1044] Finally, the server implements the system using the source code obtained and puts it into operation. The system is adjusted according to the actual business environment and user requirements, enabling efficient and rapid operation.

[1045] The above process makes it possible to build a system that simultaneously considers the user's requirements and emotions, and to provide a high-quality system in a short period of time.

[1046] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1047] Step 1:

[1048] Users enter system requirements (system name, required functions, deadline) using a web form or application, and the entered data is sent to the server via the terminal.

[1049] Input: System name, required functionality, deadline, etc.

[1050] Output: Requirement data sent to the server

[1051] Specifically, after the requirements are entered, a button is clicked and the data is sent to the server, where it is encrypted and transmitted over a secure channel.

[1052] Step 2:

[1053] The server organizes the received requirements data and analyzes the sentiment from the user's input text using an emotion engine, which uses natural language processing algorithms (e.g., sentiment analysis APIs).

[1054] Input: Requirement data sent by the user

[1055] Output: Parsed emotion data

[1056] Specifically, the server analyzes the received data and inputs the text data into the emotion engine, which then analyzes emotions such as urgency and anxiety and returns the data.

[1057] Step 3:

[1058] The server evaluates the emotion analysis results from the emotion engine and feeds them back to the system requirements database, so that the analysis results can be used in the next step.

[1059] Input: Sentiment analysis results

[1060] Output: Updated system requirements database

[1061] Specifically, the results of the sentiment analysis are stored in a database, which serves as reference data for the next generative AI model to generate code.

[1062] Step 4:

[1063] The server calls the API of the generative AI model and automatically generates system code based on the collected requirements and emotion data. The generative AI model generates code using prompt sentences as input.

[1064] Input: System requirements, emotion data

[1065] Output: Auto-generated initial system code

[1066] Specifically, the server inputs the following prompt sentence into the generative AI model:

[1067] System name: Online Shopping

[1068] Required features: cart function, payment function

[1069] Deploy to: AWS

[1070] Additional information: The user expressed a desire to "finish quickly"

[1071] Deadline: 1 week

[1072] This allows the generative AI model to generate system code.

[1073] Step 5:

[1074] The user (engineer) receives the generated initial system code and builds the system. The engineer customizes the code and runs tests.

[1075] Input: Initial system code provided by the generative AI model

[1076] Output: The constructed system

[1077] Specifically, engineers use an IDE to develop and adjust code, then check its operation in a test environment.

[1078] Step 6:

[1079] Users (engineers) submit their completed systems to the server. The submitted system code must follow a specified format and procedure.

[1080] Input: System code built by engineers

[1081] Output: The system submitted to the server

[1082] Specifically, an engineer uses a submission interface to upload the system to a server.

[1083] Step 7:

[1084] The server evaluates submitted systems based on criteria, including the completeness of the system's functionality and the efficiency of its code.

[1085] Input: Submitted system code

[1086] Output: Evaluation results

[1087] Specifically, the server evaluates the systems through an automated rating system or rating committee and assigns them a score or ranking.

[1088] Step 8:

[1089] The server will select the winners based on the evaluation results and provide them with prize money and employment opportunities.

[1090] Input: Evaluation result

[1091] Output: Selection of winners and award of prize money and employment rights

[1092] Specifically, the server sends a notification to the senior engineer and executes the procedure for providing the bonus and employment rights.

[1093] Step 9:

[1094] Finally, the server implements the system using the source code it has obtained and begins operation.

[1095] Input: The source code of the winner

[1096] Output: Implemented system

[1097] As a concrete operation, the server executes the deployment process automatically or manually and starts the system operation, thereby providing a high-quality system that reflects the user's requirements and feelings.

[1098] (Application example 2)

[1099] 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."

[1100] In modern system development processes, system code is often generated based only on simple functional requirements without considering user emotions. This often results in insufficient responses to users' actual needs and urgency. Furthermore, particularly in brick-and-mortar stores, product recommendations do not reflect users' emotional state, making it difficult to improve customer satisfaction.

[1101] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting system requirements from a user, means for automatically generating system code using a generation AI based on the collected requirements, means for analyzing the user's emotional state using emotion recognition software and reflecting the analysis results in the generation AI, and means for displaying information to the user via a smart device and making optimal suggestions based on the user's emotional state. This enables code generation that reflects the user's emotions and optimal product suggestions based on real-time emotion analysis.

[1102] "System requirements" are specific requirements such as functions, characteristics, deadlines, etc. that users require from a system.

[1103] "Generative AI" is an artificial intelligence technology that automatically generates program code using pre-trained models.

[1104] "Engineer" refers to an engineer with specialized knowledge who designs and develops systems.

[1105] A "construction contest" is a competition in which multiple engineers build systems and compete against each other in terms of their technical skills.

[1106] "Evaluation criteria" are indicators or standards for evaluating the quality and performance of submitted systems or programs.

[1107] "Reward" refers to the money or benefits provided to engineers in exchange for winning the award.

[1108] "Right of entry" refers to the right given to engineers to join a company.

[1109] "Program code" means a set of instructions written to run a system or piece of software.

[1110] "Implementation" is the activity of developing and constructing a designed system or program in a form that can actually be used.

[1111] "Emotion recognition software" is a program that analyzes a user's emotional state from facial expressions, voice, etc.

[1112] "Smart devices" refer to advanced devices that have internet connectivity and can run a variety of applications.

[1113] To implement this invention, the following system configuration and processing are required. The system consists of a user, a server, and a smart device (e.g., smart glasses). The entire system operates around emotion recognition software and a generative AI model.

[1114] System configuration

[1115] 1. User interface: The user uses an interface (e.g., a web form or an application) to input system requirements. Through this interface, the user inputs system requirements (system name, required functions, deadline, etc.).

[1116] 2. Server: The server is implemented with a program that provides the following functions:

[1117] Data collection: Receiving and organizing user input data.

[1118] Emotion analysis: Using emotion recognition software (e.g., Amazon Rekognition), emotions are analyzed from user input data, facial expressions, and voice.

[1119] Generative AI model: Invoke a generative AI model (e.g., OpenAI GPT-4) to automatically generate system code based on the collected requirements and sentiment data.

[1120] Evaluation and selection: A system building contest will be held among multiple engineers, and the submitted systems will be evaluated based on the evaluation criteria to select the winners.

[1121] Reward Offer: Offer rewards or employment rights to winners.

[1122] Implementation and deployment: Using the obtained program code, the system is implemented and put into operation.

[1123] 3. Smart devices: Smart devices such as smart glasses will be used to analyze users' emotions in real time and make optimal product recommendations.

[1124] Emotion analysis: The smart glasses' camera and microphone capture the user's facial expressions and voice and send them to the server.

[1125] Information display: Optimal suggestions and product information based on emotional data are displayed on smart glasses.

[1126] Specific example explanation

[1127] Take the example of a user using smart glasses while shopping in a brick-and-mortar store.

[1128] 1. Data capture: When a user looks at an item in a store, the camera and microphone in the smart glasses capture facial and voice data.

[1129] 2. Emotion analysis: The captured data is sent to a server and analyzed by emotion recognition software.

[1130] 3. Generative AI model: Based on the analyzed emotional state and collected system requirements, the generative AI model (GPT-4) generates optimal product suggestions.

[1131] 4. Information display: The generated suggestions are displayed to the user in real time through the smart glasses.

[1132] Prompt Sentence Examples

[1133] TXT

[1134] Emotion recognition software API call

[1135] emotion_data = recognize_emotion(captured_image, captured_audio)

[1136] Prompt sentence for generative AI model

[1137] prompt_text = "Generate the best product suggestions if the user is feeling " + emotion_data['emotion'] + "."

[1138] Invoke the GPT-4 model

[1139] optimized_recommendation = generate_recommendation(prompt_text)

[1140] Displaying suggested product information on smart glasses

[1141] display_on_smart_glasses(optimized_recommendation)

[1142] The configuration and processing of this system makes it possible to build an optimal system that reflects the user's emotions and make real-time suggestions, thereby providing a shopping experience that highly satisfies the user.

[1143] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1144] Step 1:

[1145] The user inputs system requirements. The system name, required functions, deadline, etc. are entered through an input interface (e.g., a web form or application), and this is sent from the terminal to the server. Input data might include the system name "online shopping," required functions "cart function, payment function," and deadline "one week later." This data is sent to the server as output.

[1146] Step 2:

[1147] The server organizes the received system requirements data and sends it to emotion recognition software. The data also includes additional information such as the user's "I want to complete this quickly." The emotion recognition software analyzes this text data and identifies the user's emotional state. The output is emotion data such as "high urgency."

[1148] Step 3:

[1149] The server sends the emotion data obtained from the emotion recognition software and the system requirements to the generative AI model, and creates a prompt that automatically generates the system code. For example, it creates a prompt that reads, "If the user feels a high level of urgency, please generate code for the system name online shopping, with the required functions cart and payment functions, so that it can be completed within one week." This prompt is then sent to the generative AI model as output.

[1150] Step 4:

[1151] The server holds a system building contest among multiple engineers based on the system code obtained from the generative AI model. The engineers build systems based on this code and submit them to the server. The input is the system code built by the engineers, and the output is the collection of multiple submitted systems on the server.

[1152] Step 5:

[1153] The server evaluates each submitted system based on evaluation criteria, which include functional completeness, code efficiency, etc. The output is an evaluation result for each system.

[1154] Step 6:

[1155] The server selects winners based on the evaluation results, and provides rewards and employment opportunities to the winners. The output is a list of winners and the reward details.

[1156] Step 7:

[1157] The server implements the system using the obtained best system code and starts operation. The output is a working system that is built and available to users.

[1158] 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.

[1159] 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.

[1160] 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.

[1161] [Fourth embodiment]

[1162] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1163] 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.

[1164] 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).

[1165] 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.

[1166] 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.

[1167] 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).

[1168] 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.

[1169] 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.

[1170] 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.

[1171] 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.

[1172] 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.

[1173] 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.

[1174] 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."

[1175] The present invention provides a system construction process that utilizes generative AI. The series of processes is explained below.

[1176] First, the user inputs the system requirements (e.g., system name, required functions, deadline). This input is done via a web form or application, and the terminal sends it to the server. The server receives the requirements from the user and organizes them for further processing. At this stage, the system requirements are saved in dictionary format.

[1177] Next, the server calls a generative AI model based on the collected system requirements to automatically generate system code. The generative AI model could use OpenAI's GPT-3, for example. Based on the collected requirements, the generative AI model generates appropriate program code, which the server receives.

[1178] After that, users (engineers) participate in the contest. The contest is an event where engineers submit systems they have built using generative AI. Engineers build systems based on specified system requirements and submit their results to the server.

[1179] The server evaluates the submitted systems based on a set of criteria, including the completeness of the system's functions and the efficiency of its code. Based on the results, the server selects winners and offers prize money and employment opportunities to the engineers who build the best systems.

[1180] Finally, the server will implement the system using the source code obtained, deploy the winner's code, and put the system into operation. This deployment process will be adjusted according to the actual business environment and user requirements.

[1181] Specific examples

[1182] For example, consider building an online shopping system. The user inputs the following requirements:

[1183] System name: Online shopping

[1184] Required functions: cart function, payment function

[1185] Deadline: 1 week later

[1186] The server receives these requirements and passes them to a generative AI model. Based on this, the generative AI model generates basic code for the online shopping system. Engineers build systems based on this code and submit them. The server evaluates the submitted systems and selects the top three engineers. These engineers are offered prize money and employment opportunities. Finally, the server implements the winning code and launches the online shopping system.

[1187] This process allows systems to be built efficiently in a short period of time, significantly reducing system development costs, while also enabling the discovery and recruitment of talented engineers.

[1188] The processing flow will be explained below.

[1189] Step 1:

[1190] A user enters system requirements (e.g., system name, required features, deadline) through a web form or application.

[1191] Step 2:

[1192] The terminal transmits the input requirements to the server.

[1193] Step 3:

[1194] The server organizes the received requirements, converts them into dictionary format, and saves them.

[1195] Step 4:

[1196] The server sends the collected requirements to the API of the generative AI model, which then automatically generates system code.

[1197] Step 5:

[1198] The generative AI model generates system code based on the given requirements, which is then received by the server.

[1199] Step 6:

[1200] Users (engineers) participate in the contest and build systems using generative AI models.

[1201] Step 7:

[1202] The engineer submits the system he built to the server.

[1203] Step 8:

[1204] The server evaluates the submitted systems based on criteria, including the completeness of the system's functionality and the efficiency of its code.

[1205] Step 9:

[1206] The server will select winners based on the evaluation results, and will offer prize money and employment rights to engineers who build excellent systems.

[1207] Step 10:

[1208] The server will implement the system using the winner's source code, deploy the system and put it into operation.

[1209] The above is the specific processing flow of the system construction process using generative AI.

[1210] Example 1

[1211] 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."

[1212] Traditional system development processes have had problems such as long development times and rising costs. Furthermore, there are limited means for quickly evaluating and hiring the right engineers. These issues make it difficult to improve the efficiency of system development and find talented engineers.

[1213] 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.

[1214] In this invention, the server includes means for collecting system requirements from users, means for automatically generating a system program using artificial intelligence based on the collected requirements, means for holding a system construction contest among multiple engineers, means for evaluating systems submitted by the engineers based on evaluation criteria and selecting winners, means for providing rewards or employment rights to the winners, and means for implementing the system using the obtained source code. This makes it possible to improve the efficiency of system development and quickly evaluate and discover talented engineers.

[1215] definition statement

[1216] "System requirements" refers to information that includes the functions and conditions necessary to build a system.

[1217] "User" means an individual or entity that provides system requirements and intends to use the system.

[1218] "Collect" refers to obtaining, organizing, and storing information provided by users.

[1219] "Generative AI" is a system that uses artificial intelligence technology to generate new information and programs.

[1220] A "system program" is a collection of code or scripts written to implement a specific function.

[1221] "Automatic generation" refers to the mechanical creation of programs or information without human intervention.

[1222] An "engineer" is a professional who specializes in system construction and program development.

[1223] A "system construction contest" is an event in which multiple engineers build systems based on specified requirements and compete with each other for the best results.

[1224] "Evaluation criteria" are the indicators and standards for evaluating submitted systems and programs.

[1225] A "prize winner" is a person or organization that has demonstrated outstanding achievement in a contest or other competition.

[1226] "Reward" is the consideration of money, goods, etc. provided to those who achieve outstanding results.

[1227] "Right of employment" refers to being qualified to fill a particular job or role.

[1228] "Source code" is the original program text that describes the operation of a system or application.

[1229] "Implementation" refers to the process of giving shape to a designed system or program in a form that actually works.

[1230] MODE FOR CARRYING OUT THE INVENTION

[1231] This invention provides a system construction process that utilizes a generative AI model. This system allows efficient system development through a series of processes: a user inputs system requirements, a server automatically generates system code using a generative AI model, and then engineers participate in a system construction contest and are evaluated.

[1232] Hardware and Software

[1233] Users use devices (PCs, smartphones, etc.) to enter system requirements through web forms or applications, and the data entered by the user is sent from the device to a server via the Internet.

[1234] The server receives and organizes the input requirements. It uses a database to store the requirements in dictionary format. Specifically, the server stores the data in JSON format, with fields such as the system name, required functionality, and deadline.

[1235] Next, the server calls a generative AI model (e.g., OpenAI's GPT-3) based on the collected requirements and automatically generates system code. The server then calls the API of the generative AI model and sends prompt statements based on the requirements to the generative AI model.

[1236] The server receives the code returned by the generative AI model and saves it in a format that can be used by engineers. After that, users (engineers) use their devices to participate in the system construction contest. The engineers build a system based on the generated basic code and upload the results back to the server.

[1237] The server evaluates the submitted systems based on criteria, such as the completeness of the system's functionality and the efficiency of its code, using automated test scripts and static analysis tools.

[1238] Finally, the server will select winners based on the evaluation results and provide them with rewards and employment rights. The server will deploy the source code provided by the winners, adjust it according to the actual business environment and user requirements, and put the system into operation.

[1239] Specific examples

[1240] For example, when building an online shopping system, the user inputs the following requirements:

[1241] System name: Online shopping

[1242] Required functions: cart function, payment function

[1243] Deadline: 1 week later

[1244] The server receives these requirements and passes them to a generative AI model, which then generates basic code for the online shopping system. Here's an example prompt:

[1245] System name: Online Shopping

[1246] Required features: cart function, payment function

[1247] Deadline: 1 week later

[1248] Generate Python code based on this requirement.

[1249] Based on the generated code, users (engineers) build and submit systems. The server evaluates the submitted systems and selects the top three engineers. These engineers are offered rewards and employment rights. Finally, the server implements the winning code and launches the online shopping system.

[1250] The above process allows systems to be built efficiently in a short period of time, reducing development costs and enabling the discovery and recruitment of talented engineers.

[1251] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1252] Processing Steps

[1253] Step 1:

[1254] Users input system requirements through a web form or application, and the input system requirements (e.g., system name, required functions, deadline) are sent from the terminal to the server.

[1255] Input: System name, required functionality, deadline

[1256] Output: User-entered system requirements data

[1257] Specific operation: The user enters "online shopping," "cart function, payment function," and "one week later" into the form on the terminal, and clicks the "Submit" button.

[1258] Step 2:

[1259] The server organizes the system requirements received from the terminals and stores them in a database in dictionary format.

[1260] Input: System requirements data sent from the device

[1261] Output: Organized requirements data (dictionary format)

[1262] Specific operation: The server parses the data received in JSON format and saves it into the fields "System name," "Required functions," and "Deadline."

[1263] Step 3:

[1264] The server generates a prompt sentence based on the collected requirements and calls the API of a generative AI model (e.g., OpenAI GPT-3).

[1265] Input: Organized requirements data

[1266] Output: Prompt text to send to the generative AI model

[1267] Specific operation: The server generates a prompt text "System name: online shopping, Required functions: cart function, payment function, Deadline: 1 week later" and sends it to the API of the generative AI model.

[1268] Step 4:

[1269] The generative AI model generates system code based on the prompt sentence and returns it to the server.

[1270] Input: prompt statement

[1271] Output: Generated system code

[1272] Specific operation: The generative AI model parses the prompt sentence, generates Python code, and sends it back to the server.

[1273] Step 5:

[1274] The server receives the generated system code, formats it in a format that can be used by engineers, and saves it.

[1275] Input: System code received from the generative AI model

[1276] Output: pretty-printed system code

[1277] What it does: The server formats the code and stores it in a repository where engineers can download it.

[1278] Step 6:

[1279] Users (engineers) use their own terminals to participate in the system construction contest and build a system based on the provided system code.

[1280] Input: Formatted system code

[1281] Output: System built by engineers

[1282] Specific operation: Engineers import the provided code into their own development environment and add features or make improvements.

[1283] Step 7:

[1284] The user (engineer) submits the constructed system to the server.

[1285] Input: System built by engineers

[1286] Output: System code uploaded to the server

[1287] Specific operation: The engineer attaches a file to a form to upload the completed system code to the server and clicks the "Submit" button.

[1288] Step 8:

[1289] The server evaluates the submitted systems based on the evaluation criteria and assigns them a score.

[1290] Input: Submitted system code

[1291] Output: Evaluation result (score)

[1292] What it does: The server uses automated test scripts and static analysis tools to evaluate the system's functional completeness and code efficiency.

[1293] Step 9:

[1294] The server will select winners based on the evaluation results and notify them of their rewards and employment rights.

[1295] Input: Evaluation result (score)

[1296] Output: Winner selection and notification

[1297] Specific operation: The server selects the top three engineers based on the evaluation results and sends a notification email.

[1298] Step 10:

[1299] The server deploys the obtained source code and begins operation in the production environment.

[1300] Input: Winner's source code

[1301] Output: Operational system

[1302] What happens: The server runs the deploy script to put the system into production, updating configuration files and initializing the database as needed.

[1303] (Application example 1)

[1304] 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."

[1305] In the traditional system construction process, users must define system requirements in detail, and engineers must manually develop code based on those requirements, which requires a significant amount of time and effort. Furthermore, in complex systems such as virtual stores, users often find it difficult to intuitively input requirements. This has led to issues with reduced efficiency and speed in system construction.

[1306] 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.

[1307] In this invention, the server includes a means for converting user input into text data using voice recognition technology, a means for providing a visual interface for the user via a device such as smart glasses, and a means for implementing the system using the source code used, which allows the user to intuitively input system requirements and enables efficient and rapid system construction.

[1308] "Speech recognition technology" refers to technology that converts a user's voice into text data.

[1309] "Text data" refers to character string data generated using speech recognition technology.

[1310] "Smart glasses" refers to a wearable device that provides information to the user as a visual interface.

[1311] A "visual interface" is a means of providing information visually to a user, including displays and AR technology.

[1312] A "generative AI model" refers to an artificial intelligence model that automatically generates program code based on user input data.

[1313] "Server" refers to a computer system that processes and stores data.

[1314] "System requirements" refer to the specific functions and conditions that users require from a system.

[1315] "Source code" refers to the code of a program written to operate a system.

[1316] "Deployment" refers to the process of placing source code into an actual production environment and running the system.

[1317] "Engineer" refers to a technician in charge of system design and development.

[1318] A "contest" refers to a competitive event in which engineers compete to see who can build the best systems.

[1319] "Evaluation criteria" refers to specific performance and functional indicators that a system must meet.

[1320] "Winner" means the person who submitted the most outstanding work based on the evaluation criteria.

[1321] "Reward" refers to the monetary incentive offered to the winner.

[1322] "Contract Rights" means the formal contract rights provided to the Prize Winner.

[1323] This invention relates to a system that efficiently collects system requirements using voice recognition technology and automatically generates program code using a generative AI model. The system provides a visual interface to users via smart glasses and assists in data processing and code deployment on a server.

[1324] The user wears the smart glasses and uses voice recognition technology to input system requirements by voice. The smart glasses are equipped with a speech recognition engine such as the Google Cloud Speech-to-Text API, which converts the voice input into text data with high accuracy. This text data is then sent to the server. The server analyzes the system requirements received from the user and generates appropriate prompts.

[1325] As a concrete example, consider the case of building an online shopping system. A user inputs the following requirements by voice through smart glasses:

[1326] System requirements:

[1327] System name: Online shopping system

[1328] Required functions: product list display function, cart function, voice payment function

[1329] Deadline: 1 week later

[1330] The server receives these requirements as text data and generates a prompt to proceed, such as:

[1331] Generate basic program code for an online shopping system based on the following requirements:

[1332] Requirements:

[1333] System name: Online shopping system

[1334] Required features: Product list display function, cart function, voice payment function

[1335] Deadline: 1 week later

[1336] Using a generative AI model (e.g., OpenAI's GPT-3), appropriate program code is generated based on this prompt. The generated code is then submitted to a competition in which engineers participate and are evaluated based on criteria. The best engineers are offered rewards or contract rights.

[1337] Finally, the server deploys the best source code obtained, and the system moves into production. Deployment tools such as Jenkins can be used for deployment. This system allows users to intuitively and efficiently input system requirements and build high-quality systems in a short period of time.

[1338] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1339] Step 1:

[1340] The user wears the smart glasses and inputs system requirements using voice recognition technology, which uses the smart glasses' built-in microphone to convert speech into text data via the Google Cloud Speech-to-Text API. The input for this step is the user's voice input, and the output is the converted text data.

[1341] Step 2:

[1342] The server receives the text data (system requirements) sent from the smart glasses and stores it in a database. The received text data is organized in a dictionary format. The input of this step is the text data, and the output is the system requirements stored in the database.

[1343] Step 3:

[1344] The server generates prompt sentences for the generative AI model based on the saved system requirements. The prompt sentences are used in API calls to the generative AI model (such as OpenAI's GPT-3). The input of this step is the organized system requirements, and the output is the generated prompt sentences.

[1345] Step 4:

[1346] Using the generated prompt sentence, the server calls the API of the generative AI model to generate program code. The generative AI model automatically generates appropriate code based on the prompt sentence. The input of this step is the prompt sentence, and the output is the generated program code.

[1347] Step 5:

[1348] Engineers receive the generated code from the server and participate in a system construction contest. Based on the specified system requirements, the engineers customize the generated code and build the final system. The input of this step is the generated program code, and the output is the system built by the engineers.

[1349] Step 6:

[1350] The server evaluates the systems submitted by engineers based on the evaluation criteria. The evaluation is based on multiple indicators such as the completeness of the system's functions and the efficiency of the code. The input of this step is the engineer's submitted system, and the output is an evaluation score and ranking.

[1351] Step 7:

[1352] The server selects winners based on the rankings and provides rewards or contract rights to the winners. The input of this step is the evaluation score and ranking, and the output is the list of winners and the provision of rewards or contract rights.

[1353] Step 8:

[1354] The server uses the winner's source code to implement the virtual store system. A deployment tool such as Jenkins is used for deployment. The input for this step is the winner's source code, and the output is the actual virtual store system that will be put into operation.

[1355] 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.

[1356] This invention provides a system that combines a system construction process using generative AI with an emotion engine that recognizes user emotions. The series of processes is explained below.

[1357] First, the user inputs the system requirements (e.g., system name, required functions, deadline). This input is done via a web form or application, and the terminal sends this to the server. The server receives and organizes the requirements received from the user.

[1358] The server then uses an emotion engine to recognize emotions based on the user's input data. The emotion engine uses natural language processing technology to analyze emotions from the user's text input and feeds the results back to the system requirements collection means. For example, if the user inputs "I want to complete it quickly," the urgency is recognized.

[1359] The server then calls the generative AI model based on the collected requirements and automatically generates system code. Here, the analysis results from the emotion engine are also reflected in the generative AI model, so if the user is in a hurry, for example, code that prioritizes development speed will be generated.

[1360] Users (engineers) participate in the contest and build systems based on basic system code provided by the generative AI model. The engineers then submit the systems they build to the server.

[1361] The server will evaluate the submitted systems based on criteria, including the completeness of the system's functions and the efficiency of the code. Based on the results, the server will select winners and offer prize money and employment opportunities to the engineers who build the best systems.

[1362] Finally, the server will use the source code obtained to implement the system and put it into operation. The system deployment process will be adjusted according to the actual business environment and user requirements.

[1363] Specific examples

[1364] For example, consider a user building an online shopping system. The user inputs the following requirements:

[1365] System name: Online shopping

[1366] Required functions: cart function, payment function

[1367] Deadline: 1 week later

[1368] The server receives these requirements and further analyzes the user's emotions using an emotion engine. For example, if the user adds, "I need this to be done quickly," the emotion engine recognizes the urgency. The server sends this emotion data to a generative AI model, which generates code that can also handle urgent requirements.

[1369] Engineers build and submit systems based on this generated code. The server evaluates the submitted systems and selects the top three engineers. These engineers are offered prize money and employment opportunities. Finally, the server implements the winner's code and launches the online shopping system.

[1370] This process allows systems to be built efficiently in a short period of time, significantly reducing system development costs. Also, by reflecting user emotions, it is possible to provide a system that provides greater satisfaction.

[1371] The processing flow will be explained below.

[1372] Step 1:

[1373] The user enters system requirements (e.g., system name, required functions, deadline) through a web form or application. For example, the user enters requirements such as "online shopping," "cart function," "payment function," and "one week later."

[1374] Step 2:

[1375] The terminal transmits the input requirements to the server, and the user's terminal transmits the input data to the server via the Internet.

[1376] Step 3:

[1377] The server organizes the received requirements and converts them into a dictionary format. The server analyzes the received data and organizes and saves information such as the system name, required functions, and deadlines.

[1378] Step 4:

[1379] The server uses an emotion engine to recognize emotions from the user's input data. The emotion engine uses natural language processing technology to analyze emotions from the user's text input. For example, if the user enters "I want to finish it quickly," the emotion engine will recognize the user's high sense of urgency.

[1380] Step 5:

[1381] The emotion engine reflects the emotion analysis results in the system requirements, and the server stores the recognized emotion data (e.g., high urgency) as part of the requirements.

[1382] Step 6:

[1383] The server automatically generates system code by invoking a generative AI model based on the requirements and emotion data collected. The generative AI model (e.g., GPT-3) generates system code based on the requirements and emotion data.

[1384] Step 7:

[1385] The server stores the generated system code and makes it accessible to users (engineers). Engineers access the generated system code and make any necessary modifications or additions.

[1386] Step 8:

[1387] Users (engineers) participate in the contest and build a system based on the basic system code provided by the generative AI model. The engineers then modify and expand the code, aiming to complete the system.

[1388] Step 9:

[1389] Engineers submit the completed system to the server. Engineers upload the completed system code to the server.

[1390] Step 10:

[1391] The server evaluates the submitted systems based on criteria, including the completeness of the system's functionality and the efficiency of the code. The server then scores each engineer's system based on these criteria.

[1392] Step 11:

[1393] The server will select winners based on the evaluation results, and offer prize money and employment rights to the engineers who have built the best systems. The server will select the engineers with the highest scores and notify them.

[1394] Step 12:

[1395] The server will implement the system using the winner's source code and begin operation. The server will then import the winner's code and deploy it to the actual production environment.

[1396] For example, if a user inputs, "I want to build an online shopping system, I need a cart function and a payment function, the deadline is one week from now, I'm in a hurry," the server will recognize these requirements and the urgency, and generate system code that can quickly respond using a generative AI model. Engineers will build a system based on this, and the best system will be selected after evaluation and finally deployed. This process makes it possible to build high-quality systems in a short period of time.

[1397] Example 2

[1398] 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."

[1399] In conventional system development processes, it is difficult to fully reflect factors such as user emotions and urgency, resulting in low user satisfaction. Furthermore, while there has been some technological progress in automatic system code generation, there is a lack of a method for quickly and efficiently responding to specific user requirements. Therefore, there is a need to establish an efficient system development method that simultaneously considers user requirements and emotions.

[1400] 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.

[1401] In this invention, the server includes means for collecting system requirements from users, means for using an emotion engine that recognizes user emotions, means for evaluating and feeding back the emotion data recognized by the emotion engine, and means for automatically generating system code using a generation AI based on the collected requirements and emotion data. This enables the construction of an efficient system that simultaneously reflects user requirements and emotions.

[1402] "System requirements" refers to elements necessary for system construction, such as the system name, required functions, deadlines, etc., collected from users.

[1403] An "emotion engine" is a machine learning model or algorithm that uses natural language processing technology to analyze and recognize emotions from user input data.

[1404] "Emotion data" refers to the user's emotional information recognized by the emotion engine, and indicates the urgency and priority of the requirement.

[1405] "Generative AI" refers to an artificial intelligence system that automatically generates system code based on collected requirements and emotional data.

[1406] "Initial system code" refers to the code that contains the basic structure of the system, which is automatically generated by the generation AI.

[1407] The "Engineer System Building Contest" refers to a competition in which multiple engineers build systems based on initial system code provided by a generative AI model and compete based on the results.

[1408] "Evaluation Criteria" refers to the standards for evaluating submitted systems, including the completeness of the system's functionality and the efficiency of its code.

[1409] "Rights to join" refers to the right to join a specific company or project that is offered to engineers when they win a system construction contest.

[1410] "Source code" refers to the human-readable form of program code created by engineers to define the behavior of a program.

[1411] "Implementation means" refers to the process or method for using the source code obtained to deploy and operate the system in an actual operating environment.

[1412] This invention is a system that uses a generative AI model to automatically generate system code, recognizes user emotions, and reflects them in the system construction process. This system includes a server with an emotion engine, a terminal that receives user input, and a function for automatically generating system code using generative AI.

[1413] First, the user enters the system requirements using a web form or application. Input items include the system name, required functions, and deadline. This input data is sent to the server via the terminal. The data is encrypted and reaches the server in a secure manner.

[1414] The server organizes the received system requirements and uses an emotion engine to recognize the user's emotions. The emotion engine uses natural language processing technology to analyze emotions from the user's text input. For example, if the user enters "I want to finish it quickly," the emotion engine will recognize the urgency.

[1415] The server then evaluates the emotion data recognized by the emotion engine and feeds it back into a database of system requirements, which are then used by the generative AI model to generate system code.

[1416] The server calls the API of the generative AI model based on the collected requirements and emotion data, and automatically generates system code. This generative AI model generates optimal code according to the provided prompt. An example of a prompt is shown below:

[1417] System name: Online Shopping

[1418] Required features: cart function, payment function

[1419] Deploy to: AWS

[1420] Additional information: The user expressed a desire to "finish quickly"

[1421] Deadline: 1 week

[1422] The user (engineer) builds a system based on the initial system code provided by the generative AI model. The engineer then submits the built system to the server. The server evaluates the submitted systems based on evaluation criteria and selects the top engineer. The evaluation criteria include the completeness of the system's functions and the efficiency of the code.

[1423] Finally, the server implements the system using the source code obtained and puts it into operation. The system is adjusted according to the actual business environment and user requirements, enabling efficient and rapid operation.

[1424] The above process makes it possible to build a system that simultaneously considers the user's requirements and emotions, and to provide a high-quality system in a short period of time.

[1425] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1426] Step 1:

[1427] Users enter system requirements (system name, required functions, deadline) using a web form or application, and the entered data is sent to the server via the terminal.

[1428] Input: System name, required functionality, deadline, etc.

[1429] Output: Requirement data sent to the server

[1430] Specifically, after the requirements are entered, a button is clicked and the data is sent to the server, where it is encrypted and transmitted over a secure channel.

[1431] Step 2:

[1432] The server organizes the received requirements data and analyzes the sentiment from the user's input text using an emotion engine, which uses natural language processing algorithms (e.g., sentiment analysis APIs).

[1433] Input: Requirement data sent by the user

[1434] Output: Parsed emotion data

[1435] Specifically, the server analyzes the received data and inputs the text data into the emotion engine, which then analyzes emotions such as urgency and anxiety and returns the data.

[1436] Step 3:

[1437] The server evaluates the emotion analysis results from the emotion engine and feeds them back to the system requirements database, so that the analysis results can be used in the next step.

[1438] Input: Sentiment analysis results

[1439] Output: Updated system requirements database

[1440] Specifically, the results of the sentiment analysis are stored in a database, which serves as reference data for the next generative AI model to generate code.

[1441] Step 4:

[1442] The server calls the API of the generative AI model and automatically generates system code based on the collected requirements and emotion data. The generative AI model generates code using prompt sentences as input.

[1443] Input: System requirements, emotion data

[1444] Output: Auto-generated initial system code

[1445] Specifically, the server inputs the following prompt sentence into the generative AI model:

[1446] System name: Online Shopping

[1447] Required features: cart function, payment function

[1448] Deploy to: AWS

[1449] Additional information: The user expressed a desire to "finish quickly"

[1450] Deadline: 1 week

[1451] This allows the generative AI model to generate system code.

[1452] Step 5:

[1453] The user (engineer) receives the generated initial system code and builds the system. The engineer customizes the code and runs tests.

[1454] Input: Initial system code provided by the generative AI model

[1455] Output: The constructed system

[1456] Specifically, engineers use an IDE to develop and adjust code, then check its operation in a test environment.

[1457] Step 6:

[1458] Users (engineers) submit their completed systems to the server. The submitted system code must follow a specified format and procedure.

[1459] Input: System code built by engineers

[1460] Output: The system submitted to the server

[1461] Specifically, an engineer uses a submission interface to upload the system to a server.

[1462] Step 7:

[1463] The server evaluates submitted systems based on criteria, including the completeness of the system's functionality and the efficiency of its code.

[1464] Input: Submitted system code

[1465] Output: Evaluation results

[1466] Specifically, the server evaluates the systems through an automated rating system or rating committee and assigns them a score or ranking.

[1467] Step 8:

[1468] The server will select the winners based on the evaluation results and provide them with prize money and employment opportunities.

[1469] Input: Evaluation result

[1470] Output: Selection of winners and award of prize money and employment rights

[1471] Specifically, the server sends a notification to the senior engineer and executes the procedure for providing the bonus and employment rights.

[1472] Step 9:

[1473] Finally, the server implements the system using the source code it has obtained and begins operation.

[1474] Input: The source code of the winner

[1475] Output: Implemented system

[1476] As a concrete operation, the server executes the deployment process automatically or manually and starts the system operation, thereby providing a high-quality system that reflects the user's requirements and feelings.

[1477] (Application example 2)

[1478] 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."

[1479] In modern system development processes, system code is often generated based only on simple functional requirements without considering user emotions. This often results in insufficient responses to users' actual needs and urgency. Furthermore, particularly in brick-and-mortar stores, product recommendations do not reflect users' emotional state, making it difficult to improve customer satisfaction.

[1480] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting system requirements from a user, means for automatically generating system code using a generation AI based on the collected requirements, means for analyzing the user's emotional state using emotion recognition software and reflecting the analysis results in the generation AI, and means for displaying information to the user via a smart device and making optimal suggestions based on the user's emotional state. This enables code generation that reflects the user's emotions and optimal product suggestions based on real-time emotion analysis.

[1481] "System requirements" are specific requirements such as functions, characteristics, deadlines, etc. that users require from a system.

[1482] "Generative AI" is an artificial intelligence technology that automatically generates program code using pre-trained models.

[1483] "Engineer" refers to an engineer with specialized knowledge who designs and develops systems.

[1484] A "construction contest" is a competition in which multiple engineers build systems and compete against each other in terms of their technical skills.

[1485] "Evaluation criteria" are indicators or standards for evaluating the quality and performance of submitted systems or programs.

[1486] "Reward" refers to the money or benefits provided to engineers in exchange for winning the award.

[1487] "Right of entry" refers to the right given to engineers to join a company.

[1488] "Program code" means a set of instructions written to run a system or piece of software.

[1489] "Implementation" is the activity of developing and constructing a designed system or program in a form that can actually be used.

[1490] "Emotion recognition software" is a program that analyzes a user's emotional state from facial expressions, voice, etc.

[1491] "Smart devices" refer to advanced devices that have internet connectivity and can run a variety of applications.

[1492] To implement this invention, the following system configuration and processing are required. The system consists of a user, a server, and a smart device (e.g., smart glasses). The entire system operates around emotion recognition software and a generative AI model.

[1493] System configuration

[1494] 1. User interface: The user uses an interface (e.g., a web form or an application) to input system requirements. Through this interface, the user inputs system requirements (system name, required functions, deadline, etc.).

[1495] 2. Server: The server is implemented with a program that provides the following functions:

[1496] Data collection: Receiving and organizing user input data.

[1497] Emotion analysis: Using emotion recognition software (e.g., Amazon Rekognition), emotions are analyzed from user input data, facial expressions, and voice.

[1498] Generative AI model: Invoke a generative AI model (e.g., OpenAI GPT-4) to automatically generate system code based on the collected requirements and sentiment data.

[1499] Evaluation and selection: A system building contest will be held among multiple engineers, and the submitted systems will be evaluated based on the evaluation criteria to select the winners.

[1500] Reward Offer: Offer rewards or employment rights to winners.

[1501] Implementation and deployment: Using the obtained program code, the system is implemented and put into operation.

[1502] 3. Smart devices: Smart devices such as smart glasses will be used to analyze users' emotions in real time and make optimal product recommendations.

[1503] Emotion analysis: The smart glasses' camera and microphone capture the user's facial expressions and voice and send them to the server.

[1504] Information display: Optimal suggestions and product information based on emotional data are displayed on smart glasses.

[1505] Specific example explanation

[1506] Take the example of a user using smart glasses while shopping in a brick-and-mortar store.

[1507] 1. Data capture: When a user looks at an item in a store, the camera and microphone in the smart glasses capture facial and voice data.

[1508] 2. Emotion analysis: The captured data is sent to a server and analyzed by emotion recognition software.

[1509] 3. Generative AI model: Based on the analyzed emotional state and collected system requirements, the generative AI model (GPT-4) generates optimal product suggestions.

[1510] 4. Information display: The generated suggestions are displayed to the user in real time through the smart glasses.

[1511] Prompt Sentence Examples

[1512] TXT

[1513] Emotion recognition software API call

[1514] emotion_data = recognize_emotion(captured_image, captured_audio)

[1515] Prompt sentence for generative AI model

[1516] prompt_text = "Generate the best product suggestions if the user is feeling " + emotion_data['emotion'] + "."

[1517] Invoke the GPT-4 model

[1518] optimized_recommendation = generate_recommendation(prompt_text)

[1519] Displaying suggested product information on smart glasses

[1520] display_on_smart_glasses(optimized_recommendation)

[1521] The configuration and processing of this system makes it possible to build an optimal system that reflects the user's emotions and make real-time suggestions, thereby providing a shopping experience that highly satisfies the user.

[1522] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1523] Step 1:

[1524] The user inputs system requirements. The system name, required functions, deadline, etc. are entered through an input interface (e.g., a web form or application), and this is sent from the terminal to the server. Input data might include the system name "online shopping," required functions "cart function, payment function," and deadline "one week later." This data is sent to the server as output.

[1525] Step 2:

[1526] The server organizes the received system requirements data and sends it to emotion recognition software. The data also includes additional information such as the user's "I want to complete this quickly." The emotion recognition software analyzes this text data and identifies the user's emotional state. The output is emotion data such as "high urgency."

[1527] Step 3:

[1528] The server sends the emotion data obtained from the emotion recognition software and the system requirements to the generative AI model, and creates a prompt that automatically generates the system code. For example, it creates a prompt that reads, "If the user feels a high level of urgency, please generate code for the system name online shopping, with the required functions cart and payment functions, so that it can be completed within one week." This prompt is then sent to the generative AI model as output.

[1529] Step 4:

[1530] The server holds a system building contest among multiple engineers based on the system code obtained from the generative AI model. The engineers build systems based on this code and submit them to the server. The input is the system code built by the engineers, and the output is the collection of multiple submitted systems on the server.

[1531] Step 5:

[1532] The server evaluates each submitted system based on evaluation criteria, which include functional completeness, code efficiency, etc. The output is an evaluation result for each system.

[1533] Step 6:

[1534] The server selects winners based on the evaluation results, and provides rewards and employment opportunities to the winners. The output is a list of winners and the reward details.

[1535] Step 7:

[1536] The server implements the system using the obtained best system code and starts operation. The output is a working system that is built and available to users.

[1537] 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.

[1538] 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.

[1539] 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.

[1540] 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.

[1541] 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.

[1542] 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.

[1543] 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).

[1544] 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.

[1545] 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."

[1546] 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.

[1547] 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).

[1548] 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.

[1549] 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.

[1550] 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.

[1551] 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.

[1552] 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.

[1553] 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.

[1554] 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.

[1555] 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.

[1556] 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.

[1557] 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.

[1558] The following is further disclosed regarding the above embodiment.

[1559] (Claim 1)

[1560] a means for gathering system requirements from users;

[1561] A means for automatically generating system code using generative AI based on the collected requirements;

[1562] A means to hold a system construction contest among multiple engineers,

[1563] a means for evaluating the systems submitted by the engineers based on the evaluation criteria and selecting a winner;

[1564] A means of offering prize money or employment rights to winners;

[1565] a means for implementing the system using the source code obtained; and

[1566] A system including:

[1567] (Claim 2)

[1568] 2. The system of claim 1, wherein the means for gathering system requirements includes means for receiving user input data and transmitting the input data to a server.

[1569] (Claim 3)

[1570] The system of claim 1, characterized in that the means for automatically generating system code using generative AI includes means for generating code by calling an API of a generative AI model based on collected requirements.

[1571] "Example 1"

[1572] (Claim 1)

[1573] a means for gathering system requirements from users;

[1574] A means for automatically generating a system program by a generative artificial intelligence based on the collected requirements;

[1575] A means of holding a system construction contest among multiple engineers;

[1576] a means for evaluating the systems submitted by the engineers based on the evaluation criteria and selecting a winner;

[1577] a means of providing rewards or employment rights to winners;

[1578] a means for implementing the system using the source code obtained; and

[1579] A system including:

[1580] (Claim 2)

[1581] 2. The system of claim 1, wherein the means for gathering system requirements includes means for receiving user input data and transmitting the input data to the data processing device.

[1582] (Claim 3)

[1583] The system described in claim 1, characterized in that the means for automatically generating a system program using generative artificial intelligence includes means for generating a program by calling an application program interface of the generative artificial intelligence model based on the collected requirements.

[1584] "Application Example 1"

[1585] (Claim 1)

[1586] a means for gathering system requirements from users;

[1587] A means for automatically generating system code using generative AI based on the collected requirements;

[1588] A means to hold a system construction contest among multiple engineers,

[1589] a means for evaluating the systems submitted by the engineers based on the evaluation criteria and selecting a winner;

[1590] a means of providing rewards or contract rights to prize winners;

[1591] means for converting user input into text data using speech recognition technology;

[1592] means for providing a visual interface for a user via a device such as smart glasses;

[1593] A means of implementing the system using the source code used;

[1594] A system including:

[1595] (Claim 2)

[1596] 2. The system of claim 1, wherein the means for gathering system requirements includes means for receiving user input data and transmitting the input data to a server.

[1597] (Claim 3)

[1598] The system of claim 1, characterized in that the means for automatically generating system code using generative AI includes means for generating code by calling an API of a generative AI model based on collected requirements.

[1599] "Example 2: Combining Emotion Engines"

[1600] (Claim 1)

[1601] a means for gathering system requirements from users;

[1602] a means for using an emotion engine to recognize the emotion of the user based on the collected requirements;

[1603] a means for evaluating and providing feedback to the emotion data recognized by the emotion engine;

[1604] A means for automatically generating system code using generative AI based on collected requirements and sentiment data;

[1605] A means to hold a system construction contest among multiple engineers,

[1606] a means for evaluating the systems submitted by the engineers based on the evaluation criteria and selecting a winner;

[1607] A means of offering prize money or employment rights to winners;

[1608] a means for implementing the system using the source code obtained; and

[1609] A system including:

[1610] (Claim 2)

[1611] 2. The system of claim 1, wherein the means for gathering system requirements includes means for receiving user input data and transmitting the input data to a server.

[1612] (Claim 3)

[1613] The system of claim 1, characterized in that the means for automatically generating system code using generative AI includes means for generating code by calling an API of a generative AI model based on collected requirements and emotion data.

[1614] "Application example 2 when combining emotion engines"

[1615] (Claim 1)

[1616] a means for gathering system requirements from users;

[1617] A means for automatically generating system code using generative AI based on the collected requirements;

[1618] A means of holding a system construction contest among multiple engineers;

[1619] a means for evaluating the systems submitted by the engineers based on the evaluation criteria and selecting a winner;

[1620] A means of providing rewards or entry rights to the winners;

[1621] a means for implementing the system using the obtained program code;

[1622] A means of analyzing the user's emotional state using emotion recognition software and reflecting the analysis results in the generating AI;

[1623] A means for displaying information to a user through a smart device and making optimal suggestions according to the user's emotional state;

[1624] A system including:

[1625] (Claim 2)

[1626] 2. The system of claim 1, wherein the means for gathering system requirements includes means for receiving user input data and transmitting the input data to a server.

[1627] (Claim 3)

[1628] The system of claim 1, characterized in that the means for automatically generating system code using generative AI includes means for generating code by calling an API of a generative AI model based on collected requirements. [Explanation of symbols]

[1629] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for gathering system requirements from users; A means for automatically generating system code using generative AI based on the collected requirements; A means to hold a system construction contest among multiple engineers, a means for evaluating the systems submitted by the engineers based on the evaluation criteria and selecting a winner; A means of offering prize money or employment rights to winners; a means for implementing the system using the source code obtained; and A system including:

2. 2. The system of claim 1, wherein the means for gathering system requirements includes means for receiving user input data and transmitting the input data to a server.

3. The system according to claim 1, characterized in that the means for automatically generating system code using the generative AI includes means for generating code by calling an API of the generative AI model based on the collected requirements.

Images