System

Abstract

A system is provided.SOLUTION: A system comprising: means for storing inputted system requirements; means for generating source code using a generative AI model based on the stored system requirements; means for storing the generated source code; means for evaluating the stored source code using the generative AI model; and means for determining and notifying a winner based on the evaluation results.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] The present invention relates to a system that enables competition among engineers who develop systems efficiently in a short period of time. In conventional technology, time and cost have been major obstacles in the system development process. Fair evaluation also requires a large amount of human resources. Furthermore, there are limited methods for quickly discovering and hiring excellent engineers. To address these issues, the present invention aims to provide a mechanism that utilizes generative AI to enable efficient and fair competition in system development. [Means for solving the problem]

[0005] The present invention first provides a means for users to input system requirements and has a means for saving those requirements. It also provides a means for a generative AI model to generate source code based on the saved requirements and a means for saving the generated source code. It then provides a means for evaluating the saved source code using the generative AI model and includes a means for determining and notifying a winner based on the evaluation results. This system allows participants to efficiently build systems and has their results fairly evaluated. Furthermore, the winner is provided with a prize and the right to join the company, making it possible to quickly discover and hire talented engineers.

[0006] "System requirements" refers to the functions and specifications required when developing a system.

[0007] "Generative AI model" refers to an algorithm or model for automatically generating source code using artificial intelligence techniques.

[0008] "Source code" refers to text information that describes a program and that can be interpreted and executed by a computer.

[0009] "User interface" refers to the input and output means by which a user interacts with a system.

[0010] "Evaluation" refers to reviewing the quality and functionality of the generated source code and ranking it based on evaluation criteria.

[0011] "Winner" means the participant who receives the highest score based on the evaluation results and is recognized as the winner of the Contest.

[0012] "Prize" means the monetary reward offered to the winner based on the outcome of the competition.

[0013] "Rights to join" refers to the right to offer the winner the opportunity to join a specific company. [Brief explanation of the drawings]

[0014] [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

[0015] 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.

[0016] First, the terms used in the following description will be explained.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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."

[0035] The present invention provides a system that automatically generates, evaluates, and competes systems based on system requirements entered by the user using a generative AI model. The specific process flow for the program implementation of this system is described below.

[0036] System requirements input phase

[0037] A user enters system requirements using a web portal. The requirements are sent from the device to a server, which stores them in a database.

[0038] System construction phase

[0039] The server provides the stored system requirements to the generative AI model. The device uses the generative AI model to automatically generate source code based on the system requirements. This source code is sent from the device to the server, which stores it in a database.

[0040] Deliverables submission phase

[0041] Users upload the generated source code to a web portal, and the server receives the uploaded source code and stores it in a database.

[0042] Review Phase

[0043] The stored source code is evaluated by a generative AI review model running on a server. The evaluation model assigns a score based on criteria such as the quality, functionality, and efficiency of the source code. This score is stored in a database and later displayed as a ranking.

[0044] Result announcement phase

[0045] The server will determine the winner based on the evaluation results. The winner will be offered a prize and the right to join the company. The server will then notify the user of the results.

[0046] Specific examples

[0047] For example, suppose a user inputs the system requirement "e-commerce website," which includes "displaying a product list," "cart function," and "payment function." The terminal uses a generative AI model to generate source code containing these functions and sends the source code to the server. The user then uploads the source code to a web portal, and the server evaluates it. Based on the evaluation results, the user with the highest evaluation is selected as the winner and offered a prize and employment opportunities.

[0048] This system enables efficient system development in a short period of time, and allows the selection of excellent engineers through fair evaluation. In this way, the present invention improves the speed and quality of system development while reducing development costs.

[0049] The processing flow will be explained below.

[0050] Step 1:

[0051] A user enters their system requirements using a web portal. The user enters the required features and specifications into the input boxes and clicks the submit button.

[0052] Step 2:

[0053] The device sends the system requirements entered by the user to the server. The system requirements are transferred in a data format such as JSON.

[0054] Step 3:

[0055] The server stores the received system requirements in a database, where the user ID and the requirements information are stored as associated records.

[0056] Step 4:

[0057] The server provides the stored system requirements to the generative AI model, which then passes the requirements to the generative AI model through an appropriate API or interface.

[0058] Step 5:

[0059] The device automatically generates source code based on the system requirements using a generative AI model, which analyzes the stored requirements and generates program code accordingly.

[0060] Step 6:

[0061] The terminal sends the generated source code to the server, which transfers the source code in text format or in an archive file format.

[0062] Step 7:

[0063] The server stores the received source code in a database. The generated source code is stored in association with the user ID.

[0064] Step 8:

[0065] The user uploads the generated source code using a web portal. The user attaches the generated source code file to an upload form and submits it to the server.

[0066] Step 9:

[0067] The server receives the uploaded source code and stores it in a database along with the user ID.

[0068] Step 10:

[0069] The server provides the stored source code to the generated AI review model, which then passes the source code to the review model and issues instructions for evaluation.

[0070] Step 11:

[0071] A generative AI review model evaluates and scores source code quality and functionality, based on criteria such as code efficiency, maintainability, and functional completeness.

[0072] Step 12:

[0073] The server saves the evaluation results in a database and creates a ranking. The evaluation results are saved in the form of user ID and score, and are displayed as a ranking.

[0074] Step 13:

[0075] The server will determine the winner based on the evaluation results. The user with the highest score will be selected as the winner.

[0076] Step 14:

[0077] The server will notify the winners of their prize money and employment opportunities via email and the web portal's messaging system.

[0078] Example 1

[0079] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0080] Modern system development requires the rapid and efficient generation of high-quality source code and the ability to receive fair evaluations. However, doing this manually requires a great deal of time and effort. A system is also needed to evaluate the technical capabilities of system developers and provide appropriate compensation and employment opportunities based on the evaluation results. However, traditional methods make it difficult to manage these processes in an integrated manner.

[0081] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0082] In this invention, the server includes means for saving input system requirements, means for generating source code using a generative AI model based on the saved system requirements, means for saving the generated source code, means for viewing, editing, and resaving the generated source code, means for evaluating the saved source code using the generative AI model, and means for determining and notifying a winner based on the evaluation results. This enables the system development process to be accelerated and efficient, and makes it possible to select excellent engineers through fair evaluation and provide them with appropriate compensation and employment opportunities.

[0083] "System requirements" are requirements regarding specifications such as system functions, performance, and constraints.

[0084] A "generative AI model" is a model that uses artificial intelligence technology to automatically generate source code based on specified requirements and prompts.

[0085] "User interface" refers to the interactive screens and forms through which users enter system requirements.

[0086] "Source code" is the text of a program written in a programming language to realize the functions of a system.

[0087] A "server" is a computer system that processes requests from clients (terminals) via a network, stores data, and performs calculations.

[0088] An "evaluation model" is an algorithm or program for evaluating the quality, functionality, efficiency, etc. of generated source code.

[0089] "Winner" refers to the participant who receives the best score based on the evaluation results.

[0090] "Prize" means the monetary reward offered to a winner.

[0091] "Right to join a company" refers to the right to offer outstanding candidates employment opportunities at a specific company.

[0092] A "database" is a system for efficiently storing, retrieving, and managing structured information.

[0093] The present invention provides a system that automatically generates, evaluates, and competes systems based on system requirements entered by the user using a generative AI model. The specific details of the program implementation of this system are shown below.

[0094] System requirements input phase

[0095] The user enters system requirements using a web portal. Using the user interface provided through a browser, the user enters system requirements in text boxes and list-style fields. For example, requirements such as "e-commerce site," "product list display," "cart function," and "payment function" can be entered. The entered requirements are sent from the terminal to the server, which stores them in a database. A relational database management system such as MySQL is used for the database.

[0096] System construction phase

[0097] The server provides the saved system requirements to a generative AI model (e.g., OpenAI's GPT-4 model). The generative AI model generates source code that meets the system requirements based on a prompt. An example of a prompt is "Generate Python code for an e-commerce site with product listing, cart functionality, and payment feature."

[0098] The generated source code is sent by the terminal to the server, which stores it in a database. Before saving, users are also provided with the ability to view, edit, and resave the source code. This function allows users to check the generated source code and make corrections as necessary.

[0099] Deliverables submission phase

[0100] Users upload the final source code using a web portal. The server receives the uploaded source code and stores it in a database. This process allows for centralized management of source code based on system requirements.

[0101] Review Phase

[0102] The stored source code is evaluated by a generative AI review model run by the server. The evaluation criteria consider the quality, functionality, and efficiency of the source code. The evaluation model assigns a score to each source code based on these criteria. The evaluation results are stored in a database and can later be displayed as a ranking.

[0103] Result announcement phase

[0104] The server will determine the winner based on the evaluation results. The winner will be offered a prize and the right to join a company. The server will notify the user of the results directly.

[0105] Specific examples

[0106] For example, a user may input the system requirement "e-commerce site," which includes "product listing," "cart functionality," and "payment functionality." The server sends the generative AI model a prompt: "Generate Python code for an e-commerce site with product listing, cart functionality, and payment feature." The server then receives the generated source code. The user then uploads the final source code to a web portal, and the server evaluates it. The user with the highest evaluation is selected as the winner and is offered a cash prize and employment opportunities.

[0107] This system allows for efficient system development in a short period of time, and allows for the selection of excellent engineers through fair evaluation. In this way, the present invention improves the speed and quality of system development while reducing development costs.

[0108] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0109] Step 1:

[0110] A user accesses a web portal and enters system requirements. They fill in the web portal form with details such as "e-commerce site," "product list display," "cart function," and "payment function." This becomes the input data. The entered system requirements are sent from the terminal to the server via an HTTP POST request. The server receives them and stores them in a database. A relational database management system such as MySQL is used for the database.

[0111] Input: System requirements entered by the user in a web form

[0112] Output: System requirements data sent to the server

[0113] Step 2:

[0114] The server retrieves the system requirements stored in the database and provides them to a generative AI model. The generative AI model (e.g., OpenAI's GPT-4 model) generates source code based on the system requirements, using the prompt "Generate Python code for an e-commerce site with product listing, cart functionality, and payment feature." The generated source code is sent to the terminal.

[0115] Input: System requirements stored in the database

[0116] Output: Source code generated by the generative AI model

[0117] Step 3:

[0118] The device sends the source code received from the generative AI model to the server, which receives the source code and stores it in a database. At this time, the source code is temporarily stored in the file system and its contents are stored in the database.

[0119] Input: Source code received from the generative AI model

[0120] Output: Source code stored in a database

[0121] Step 4:

[0122] Users have the ability to view, edit, and re-save source code through a web portal, and the edited source code is then sent back to the server, which then re-stores it in the database.

[0123] Input: User-edited source code

[0124] Output: Source code resaved to the database

[0125] Step 5:

[0126] Users upload the final source code to a web portal, and the server receives the uploaded source code and stores it in the database in its final form, thus keeping the final source code in the system.

[0127] Input: The final source code uploaded by the user

[0128] Output: Final source code stored in a database

[0129] Step 6:

[0130] The server then provides the final source code stored in the database to the generative AI review model for evaluation. The evaluation model evaluates the source code's quality, functionality, and efficiency, and assigns a score based on each criterion. The evaluation results are then stored in the database again.

[0131] Input: Final source code stored in the database

[0132] Output: Evaluation result score

[0133] Step 7:

[0134] The server will determine the winner based on the evaluation results. The evaluation results will be tallied and the user with the highest score will be selected as the winner. The winner will be notified directly by the server and will be offered a prize money and the right to join the company.

[0135] Input: Evaluation result score

[0136] Output: Winner determination and notification

[0137] This system improves the speed and quality of system development through a series of processing steps, and enables the selection of excellent engineers through fair evaluation.

[0138] (Application example 1)

[0139] 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."

[0140] In the past, it was difficult to quickly and efficiently develop factory automation systems and robot operation plans. In particular, there was a lack of means to design operation plans suited to individual factories and work processes and to properly evaluate their quality and efficiency. Furthermore, building such systems required a great deal of time and cost, which hindered the adoption of automation in small and medium-sized factories and sites with special needs.

[0141] 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.

[0142] In this invention, the server includes a means for saving input system requirements, a means for generating source code using a generative AI model based on the saved system requirements, and a means for saving the generated source code. This provides a means for inputting factory automation system requirements and automatically generating factory work processes and robot operation plans based on the requirements, and a means for evaluating the generated operation plans and source code and assigning scores that take efficiency and quality into consideration, enabling the rapid and high-quality construction of factory automation systems.

[0143] "System requirements" refer to the functions and characteristics that a user expects from a particular system or application.

[0144] A "generative AI model" refers to an artificial intelligence model that automatically generates source code or other output based on input data or requirements.

[0145] "Source code" refers to machine-readable program code for programming the operation of a system or application.

[0146] "Storage" refers to storing data or information in a way that allows it to be accessed at a later time.

[0147] "Evaluation" refers to judging the quality and efficiency of the generated source code and operation plan.

[0148] "Winner" refers to the user or team that receives the highest score based on the evaluation results.

[0149] "Factory automation system" refers to a system for automating manufacturing and other work processes in a factory.

[0150] An "operation plan" refers to the specific operating procedures for robots and automated equipment used in a factory.

[0151] "Score" refers to the score or rating assigned by a rating model.

[0152] This invention is a system for quickly and efficiently constructing factory automation systems and robot operation plans. Specifically, the system automatically generates systems based on user input system requirements using a generative AI model, evaluates them, and then selects the best system through a competition.

[0153] First, a user inputs system requirements, such as a factory automation system or a robot's operation plan, via a web portal. These requirements are sent to a server and stored in a database. The server then provides the stored system requirements to a generative AI model, which the user's device uses to generate optimal source code and an operation plan. The generated source code is then sent back to the server and stored in the database.

[0154] Next, the user uploads the generated source code and operation plan to a web portal. The server receives the uploaded source code and operation plan and evaluates its quality, functionality, efficiency, etc. using a generative AI evaluation model. The scores assigned by the evaluation model are stored in a database and later displayed as a ranking.

[0155] Based on the evaluation results, the server will determine the user with the highest evaluation as the winner and notify them. The winner will be offered a reward and the opportunity to join the company. This system makes it possible to efficiently build high-quality factory automation systems and robot operation plans in a short period of time.

[0156] The specific hardware and software used will include servers, smartphones, and tablets. The software will use Flask as a web application framework and JSON as the data storage format. Advanced generative AI models such as GPT-4 are expected to be used.

[0157] For example, if a factory engineer inputs a requirement such as "a motion plan for a package sorting robot," the generative AI model will generate an optimal motion plan and corresponding source code based on this requirement, which will then be implemented in the factory robot, resulting in a 30% improvement in the robot's operating efficiency.

[0158] Example prompt sentence:

[0159] The user has entered a requirement: "Action plan for a package sorting robot." Based on this requirement, generate and evaluate the optimal logic and source code. Also, provide a plan that takes into account efficiency and safety. The generated source code should look like this:

[0160] In this way, the present invention makes it possible to quickly and efficiently construct and evaluate operation plans for factory automation systems and robots.

[0161] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0162] Step 1:

[0163] The user enters system requirements through a web portal. Specifically, the user uses the user interface to enter detailed requirements for the factory automation system and robot operation plans. The input data is sent to the server in JSON format. Input: System requirements entered by the user. Output: System requirements sent to the server and saved.

[0164] Step 2:

[0165] The server receives the system requirements and stores them in a database. Specifically, it parses the received data and stores it in the database in the correct format. Input: Received system requirements in JSON format. Output: System requirements stored in the database.

[0166] Step 3:

[0167] The server retrieves system requirements from the database and provides them to the generative AI model. Specifically, it converts the data retrieved from the database into a format that the generative AI model can understand and inputs it into the model. Input: System requirements stored in the database. Output: System requirements input into the generative AI model.

[0168] Step 4:

[0169] A generative AI model generates source code based on system requirements. Specifically, a generative AI model (e.g., GPT-4) generates optimal source code based on the provided requirements. Input: System requirements. Output: Generated source code.

[0170] Step 5:

[0171] The generated source code is sent to the server and stored in the database. Specifically, the source code output from the generative AI model is sent to the server and stored in the database in an appropriate format. Input: Source code generated by the generative AI model. Output: Source code stored in the database.

[0172] Step 6:

[0173] The user uploads the generated source code and action plan to the web portal. Specifically, the user selects the generated source code from the user interface and clicks the upload button. Input: Generated source code. Output: Source code uploaded to the server.

[0174] Step 7:

[0175] The server receives the uploaded source code and action plan and evaluates it using a generative AI evaluation model. Specifically, the source code is input into the evaluation model, and a score is calculated based on the evaluation of quality, efficiency, functionality, etc. Input: Uploaded source code. Output: Score calculated by the evaluation model.

[0176] Step 8:

[0177] The evaluation results are stored in a database, and the server determines and notifies the winner based on the results. Specifically, it compares the scores of each source code, selects the user with the highest score as the winner, and notifies the result. Input: Evaluation result score. Output: Determination and notification of the winner.

[0178] Through the above processing steps, this system is able to quickly and efficiently generate and evaluate operation plans for factory automation systems and robots.

[0179] 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.

[0180] This invention combines an emotion engine that recognizes the user's emotions with a system that automatically generates, evaluates, and competes systems based on user input system requirements using a generative AI model. The specific processing flow for the program implementation of this system is described below.

[0181] System requirements input phase

[0182] A user enters system requirements using a web portal. The requirements are sent from the device to a server, which stores them in a database.

[0183] In this phase, the emotion engine analyzes the user's emotional state in real time. The emotion data entered by the user is sent to the server and stored in a database along with the system requirements.

[0184] System construction phase

[0185] The server provides the stored system requirements to the generative AI model. The device uses the generative AI model to automatically generate source code based on the system requirements. This source code is sent from the device to the server, which stores it in a database.

[0186] The emotion engine also monitors the user's emotions during this phase, for example, recording the stress or satisfaction the user feels during the code generation process and sending this data to the server.

[0187] Deliverables submission phase

[0188] Users upload the generated source code to a web portal, and the server receives the uploaded source code and stores it in a database.

[0189] Review Phase

[0190] The stored source code is evaluated by a generative AI review model running on a server. The evaluation model assigns a score based on criteria such as the quality, functionality, and efficiency of the source code. This score is stored in a database and later displayed as a ranking.

[0191] Emotion data obtained from the emotion engine is also reflected in the evaluation process. For example, high-quality source code under low stress conditions can earn additional evaluation points.

[0192] Result announcement phase

[0193] The server will determine the winner based on the evaluation results. The winner will be offered a prize and the right to join the company. The server will then notify the user of the results.

[0194] Specific examples

[0195] For example, suppose a user inputs the system requirements for an "e-commerce website." These requirements include displaying a product list, a cart function, and a payment function. The terminal uses a generative AI model to generate source code containing these functions and sends the source code to the server. During this process, an emotion engine monitors the user's emotions. For example, if the user expresses high satisfaction during this process, the emotion data is also saved. The user then uploads the source code to a web portal, where the server evaluates it. The emotion data is reflected in the evaluation results, and the user with the highest evaluation is selected as the winner and offered a cash prize and employment opportunities.

[0196] This system enables efficient system development in a short period of time and selects excellent engineers through fair evaluation. Furthermore, by incorporating user emotional data into the evaluation process, a more human-centered evaluation becomes possible, leading to improved user satisfaction and experience.

[0197] The processing flow will be explained below.

[0198] Step 1:

[0199] A user enters their system requirements using a web portal. The user enters the required features and specifications into the input boxes and clicks the submit button.

[0200] Step 2:

[0201] The device sends the system requirements entered by the user to the server. The system requirements are transferred in a data format such as JSON.

[0202] Step 3:

[0203] The server stores the received system requirements in a database, where the user ID and the requirements information are stored as associated records.

[0204] Step 4:

[0205] The device's built-in emotion engine analyzes the user's emotions in real time while they are entering system requirements, detecting stress, excitement, and satisfaction from the user's facial expressions, voice, and input speed.

[0206] Step 5:

[0207] The device transmits the analyzed emotion data along with the system requirements to the server, where the emotion data is stored together with the requirements data.

[0208] Step 6:

[0209] The server provides the stored system requirements to the generative AI model, which then passes the requirements to the generative AI model through an appropriate API or interface.

[0210] Step 7:

[0211] The device automatically generates source code based on the system requirements using a generative AI model, which analyzes the stored requirements and generates program code accordingly.

[0212] Step 8:

[0213] The terminal sends the generated source code to the server, which transfers the source code in text format or in an archive file format.

[0214] Step 9:

[0215] The server stores the received source code in a database. The generated source code is stored in association with the user ID.

[0216] Step 10:

[0217] The user uploads the generated source code using a web portal. The user attaches the generated source code file to an upload form and submits it to the server.

[0218] Step 11:

[0219] The server receives the uploaded source code and stores it in a database along with the user ID.

[0220] Step 12:

[0221] The server provides the stored source code to the generated AI review model, which then passes the source code to the review model and issues instructions for evaluation.

[0222] Step 13:

[0223] A generative AI review model evaluates and scores source code quality and functionality, based on criteria such as code efficiency, maintainability, and functional completeness.

[0224] Step 14:

[0225] The server saves the evaluation results in a database and creates a ranking. The evaluation results are saved in the form of user ID and score, and are displayed as a ranking.

[0226] Step 15:

[0227] Emotion data obtained from the emotion engine is also reflected in the evaluation process. For example, high-quality source code under low stress conditions can earn additional evaluation points.

[0228] Step 16:

[0229] The server will determine the winner based on the evaluation results. The user with the highest score will be selected as the winner.

[0230] Step 17:

[0231] The server will notify the winners of their prize money and employment opportunities via email and the web portal's messaging system.

[0232] Example 2

[0233] 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."

[0234] In recent years, there has been a demand for more efficient system development, but conventional methods often involve manual processes, from inputting system requirements to generating source code and evaluating it. This tends to depend on the skills and experience of the developer, making fair and efficient evaluation difficult. Furthermore, there is no established evaluation method that takes into account the emotional state of the developer during the development process, making it difficult to fully improve user satisfaction and experience. Therefore, a system that automates system development and performs evaluations that take into account the developer's emotional data is needed.

[0235] 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.

[0236] In this invention, the server includes means for saving input system requirements, means for generating source code using a generative AI model based on the saved system requirements, means for saving the generated source code, means for analyzing users' emotional states in real time and saving emotional data, means for reflecting the emotional data in the evaluation process, and means for determining and notifying a winner based on the evaluation results. This makes it possible to efficiently and automatically develop systems and to perform fair evaluations that take users' emotional states into account.

[0237] "System requirements" indicate the specific functions, performance, constraints, etc. required for the system to be developed.

[0238] A "generative AI model" is an algorithm or program that uses artificial intelligence technology to automatically generate source code.

[0239] "Source code" means a set of program instructions written in a programming language that can be executed by a computer.

[0240] A "server" is a computer system that stores, processes, and manages data, and provides necessary services in response to requests from clients.

[0241] A "terminal" is a device operated by a user to communicate with a server, such as a PC or smartphone.

[0242] An "emotion engine" is software or hardware that analyzes a user's emotional state and outputs the analysis results as data.

[0243] "Evaluation" is the act of analyzing the quality, functionality, efficiency, etc. of the generated source code and assigning it a score or ranking.

[0244] The "Winner" is the participant who receives the highest score based on the evaluation results.

[0245] "Notification" is the act of transmitting results or information from the server to the user, usually via email or a messaging system.

[0246] "Emotion data" refers to data that indicates the user's emotional state analyzed by the emotion engine, and includes stress level, satisfaction level, and the like.

[0247] The "evaluation process" refers to a series of steps to conduct a fair and objective evaluation based on the generated source code and emotional data.

[0248] The present invention combines an emotion engine that recognizes the user's emotions with a system in which a user inputs system requirements and a generative AI model is used to automatically generate and evaluate a system based on those requirements.

[0249] System requirements input phase

[0250] Users use a web portal to enter system requirements, which are then sent from their devices to a server, which stores them in a database. The web portal runs in a standard web browser and uses HTML and JavaScript to create the user interface.

[0251] Using data from the webcam and keyboard input speed, the emotion engine analyzes the user's emotional state in real time, and this emotion data, along with the system requirements, is sent to the server and stored in a database.

[0252] System construction phase

[0253] The server retrieves the stored system requirements and provides them to a generative AI model, which is built using the latest AI technologies, including natural language processing techniques and machine learning algorithms.

[0254] The device uses a generative AI model to automatically generate source code based on system requirements. The generated source code is written in a common programming language (e.g., Python or JavaScript). The generated source code is sent from the device to a server, which stores it in a database.

[0255] During this phase, the emotion engine also monitors the user's emotions and sends the data to the server for storage, including the level of stress and satisfaction the user feels during code generation.

[0256] Deliverables submission phase

[0257] Users upload the generated source code through a web portal, which is then received by the server and stored in a database.

[0258] Review Phase

[0259] The server provides the stored source code to a generative AI review model, which evaluates and scores the source code based on its quality, functionality, efficiency, etc. The evaluation results are stored in a database and later displayed as a ranking.

[0260] Emotional data is also taken into account in this evaluation process: for example, users who generate high-quality source code under low stress conditions are awarded additional evaluation points.

[0261] Result announcement phase

[0262] The server will determine the winner based on the evaluation results. The winner will be given rewards, employment opportunities, etc. The server will then send a notification of the results to the user.

[0263] Specific examples

[0264] For example, if a user inputs the system requirement "e-commerce site," this requirement includes "displaying a product list," "cart function," and "payment function." The terminal uses a generative AI model to generate source code including these functions and sends the source code to the server. During this process, an emotion engine monitors the user's emotions, and if the user expresses high satisfaction with the process, the emotion data is also saved. The user then uploads the source code to a web portal, and the server evaluates it. The emotion data is reflected in the evaluation results, and the user with the highest evaluation is selected as the winner and offered rewards and employment opportunities.

[0265] Prompt Sentence Examples

[0266] "The system requirements for an e-commerce site include product listing, shopping cart functionality, and payment functionality. Please generate source code using a generative AI model based on these requirements."

[0267] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0268] System processing flow

[0269] Step 1:

[0270] A user opens a web portal and inputs system requirements. The user inputs "Build an e-commerce site," and the requirements include "Display a product list," "Cart function," and "Payment function." The input system requirements are sent to the server by the terminal. At this point, the input data are the system requirements, and the output data are the system requirements sent to the server.

[0271] Operation details:

[0272] Using a web browser, the user enters the system requirements into a form on the web portal and clicks the "Submit" button.

[0273] Step 2:

[0274] The server stores the received system requirements in a database. The server checks the integrity of the entered data and ensures that all required fields are present. At this point, the input data are the system requirements sent from the terminal, and the output data are the system requirements stored in the database.

[0275] Operation details:

[0276] The server receives the HTTP request and stores it in a database.

[0277] Step 3:

[0278] The emotion engine analyzes the user's emotional state in real time. Data such as webcam and keyboard input speed are used for the analysis. This emotion data, along with system requirements, is sent to the server and stored in a database. The input data is raw emotion data, and the output data is analyzed emotion data.

[0279] Operation details:

[0280] The emotion engine analyzes webcam footage and infers emotions from the user's facial expressions and eye movements.

[0281] Step 4:

[0282] The server provides the saved system requirements to the generative AI model, which receives the prompt and generates source code based on it. The input data are the system requirements and the prompt, and the output data is the generated source code.

[0283] Operation details:

[0284] The server sends a prompt to the generative AI model, such as "Please generate source code based on the following system requirements: product list display, cart function, and payment function."

[0285] Step 5:

[0286] The terminal uses the generative AI model to automatically generate source code based on the system requirements. The generated source code is sent from the terminal to the server and stored in a database. The input data is the prompt provided to the generative AI model, and the output data is the generated source code.

[0287] Operation details:

[0288] The device inputs a prompt into the generative AI model, receives the generated source code, and uploads it to the server.

[0289] Step 6:

[0290] The server saves the generated source code in a database. When saving, it checks the data consistency and confirms the format of the required files. The input data is the source code sent from the terminal, and the output data is the source code saved in the database.

[0291] Operation details:

[0292] The server receives the source code uploaded via HTTP request and stores it in a database.

[0293] Step 7:

[0294] The emotion engine monitors the user's emotions even while generating source code. Emotion data is periodically sent to the server and stored in a database in association with system requirements. The input data is raw data of the user's emotions, and the output data is analyzed emotion data.

[0295] Operation details:

[0296] The emotion engine sequentially analyzes the user's facial expressions and behavior during the generation process and transmits the emotional state to the server in real time.

[0297] Step 8:

[0298] The user uploads the generated source code to the server through a web portal. At this point, the input data is the generated source code, and the output data is the source code sent to the server.

[0299] Operation details:

[0300] The user accesses the web portal and uploads the generated source code file by selecting the file using the file specification button and clicking the "Upload" button.

[0301] Step 9:

[0302] The server provides the stored source code to the generative AI review model for evaluation. The evaluation results also reflect emotional data. The input data are the source code and emotional data, and the output data is the evaluation score.

[0303] Operation details:

[0304] The server sends the source code file to the generative AI review model along with a prompt saying, "Please rate this source code for quality, functionality, and efficiency."

[0305] Step 10:

[0306] The server determines the winner based on the evaluation results and notifies the user of the result. The winner will be offered rewards and employment opportunities. The input data is the evaluation score, and the output data is the winner notification and reward information.

[0307] Operation details:

[0308] The server tally the evaluation scores, determine the user with the highest score, and notify the user of the result via email or internal message.

[0309] (Application example 2)

[0310] 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."

[0311] In conventional systems, after users input system requirements, the system is automatically generated and evaluated, but the user's emotional data is not reflected in the process, making it difficult to conduct efficient, human-centered evaluations. Furthermore, there was a lack of efficient means for generating high-quality source code for factory robot control systems. This resulted in poor user satisfaction and experience, making appropriate evaluations difficult.

[0312] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0313] In this invention, the server includes means for saving input system requirements and emotion data, means for generating source code using a generative AI model based on the saved system requirements, and means for saving the generated source code, thereby enabling automatic generation and evaluation of high-quality source code based on the system requirements while reflecting the user's emotion data.

[0314] "System requirements" refers to specific requirements or conditions regarding the operation or functionality of a system.

[0315] "Emotion data" is data that reflects the user's mental state, and includes information such as stress level and satisfaction level.

[0316] "Storage means" refers to a function for temporarily or permanently storing input data and generated source code.

[0317] A "generative AI model" refers to an artificial intelligence algorithm that automatically generates source code or other output based on given requirements or conditions.

[0318] "Evaluation means" refers to functions for evaluating the quality, functionality, efficiency, etc. of the generated source code and system.

[0319] "User interface" refers to the interactive screens and components that allow a user to interact with a system and input data.

[0320] "Notification means" refers to a function for conveying information such as evaluation results and winner selection to users.

[0321] "Benefits" refers to any rewards or rights provided as a result of an evaluation.

[0322] The hardware required to realize this application example includes a server, a user device, and sensors (camera, microphone, etc.) for acquiring emotion data. The software includes the Python programming language, a generative AI model library (AIModel), an emotion recognition library (EmotionEngine), and a database operation library (Database).

[0323] Overall system flow

[0324] The server first receives the system requirements and emotion data entered by the user through the terminal and stores them in a database. Next, it generates source code using a generative AI model based on the stored system requirements. The generated source code is then stored in the database by the server.

[0325] The server then evaluates the stored source code. This evaluation takes into account the generative AI model as well as the user's emotional data. For example, if the user's stress level while entering the system requirements is low, the evaluation score will increase. The server then determines and notifies the winner based on the evaluation results.

[0326] Step-by-step details

[0327] 1. System requirements input:

[0328] When a user inputs system requirements using the terminal's user interface, the emotion engine analyzes emotions in real time, and these data are sent to the server and stored in a database.

[0329] 2. System construction:

[0330] The server retrieves the saved system requirements and uses the generative AI model to generate source code based on the requirements. During this generation process, the emotion engine continues to analyze the user's emotions, which are also stored in the database.

[0331] 3. Evaluation:

[0332] The server evaluates the generated source code, using the generative AI model and user emotion data to calculate an overall score.

[0333] 4. Result notification:

[0334] The server will determine and notify the winner based on the evaluation results, and the winner will receive a prize.

[0335] Specific examples

[0336] For example, consider the case where a user inputs a system requirement such as "a robot control system that can assemble parts at high speed." As the user inputs the requirement, the emotion engine analyzes the user's emotion data, and the server stores this data in a database. Next, a generative AI model generates source code for controlling the robot based on the requirement. The generated source code and emotion data are again stored in the database. The server then uses the generative AI model to evaluate the source code, and determines and notifies the winner based on the evaluation results and emotion data.

[0337] Example prompts to input to the generative AI model

[0338] "Generate source code for a robotic control system that assembles parts at high speed. Requirements are: high speed, high accuracy."

[0339] By inputting this prompt into the AI ​​model, the appropriate source code is generated.

[0340] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0341] Step 1:

[0342] The user inputs system requirements using the user interface of the device. The input system requirements are sent from the device to the server. At that time, the emotion engine analyzes the user's emotion data in real time, and this emotion data is also sent to the server. The server stores the system requirements and emotion data in a database.

[0343] Step 2:

[0344] The server retrieves the system requirements stored in the database. It provides the retrieved system requirements to the generation AI model, which then generates source code based on the system requirements. During this generation process, the emotion engine continues to analyze the user's emotions, which are also sent to the server and stored in the database. The server then stores the generated source code in the database.

[0345] Step 3:

[0346] The server retrieves the generated source code from the database and uses a generative AI model to evaluate the quality, functionality, efficiency, etc. of the source code. The evaluation uses information about the source code itself and stored emotional data. For example, if the user's stress level is low based on the emotional data, the server increases the evaluation score. The evaluation results are stored in the database by the server.

[0347] Step 4:

[0348] The server determines the winner based on the evaluation results stored in the database. When determining the winner, the evaluation results and emotional data are taken into consideration comprehensively. For example, the winner will be the user who generates high-quality source code while working with low stress. After the winner is determined, the server will notify the user.

[0349] Step 5:

[0350] The server processes the delivery of prizes and rewards to winners, including using a management system to arrange and deliver physical and digital rewards, and winners receive notifications and details via email and a user interface.

[0351] Through these steps, the system operates smoothly and enables efficient and human-centered evaluation.

[0352] 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.

[0353] 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.

[0354] 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.

[0355] [Second embodiment]

[0356] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0357] 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.

[0358] 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).

[0359] 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.

[0360] 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.

[0361] 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).

[0362] 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.

[0363] 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.

[0364] 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.

[0365] 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.

[0366] 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.

[0367] 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."

[0368] The present invention provides a system that automatically generates, evaluates, and competes systems based on system requirements entered by the user using a generative AI model. The specific process flow for the program implementation of this system is described below.

[0369] System requirements input phase

[0370] A user enters system requirements using a web portal. The requirements are sent from the device to a server, which stores them in a database.

[0371] System construction phase

[0372] The server provides the stored system requirements to the generative AI model. The device uses the generative AI model to automatically generate source code based on the system requirements. This source code is sent from the device to the server, which stores it in a database.

[0373] Deliverables submission phase

[0374] Users upload the generated source code to a web portal, and the server receives the uploaded source code and stores it in a database.

[0375] Review Phase

[0376] The stored source code is evaluated by a generative AI review model running on a server. The evaluation model assigns a score based on criteria such as the quality, functionality, and efficiency of the source code. This score is stored in a database and later displayed as a ranking.

[0377] Result announcement phase

[0378] The server will determine the winner based on the evaluation results. The winner will be offered a prize and the right to join the company. The server will then notify the user of the results.

[0379] Specific examples

[0380] For example, suppose a user inputs the system requirement "e-commerce website," which includes "displaying a product list," "cart function," and "payment function." The terminal uses a generative AI model to generate source code containing these functions and sends the source code to the server. The user then uploads the source code to a web portal, and the server evaluates it. Based on the evaluation results, the user with the highest evaluation is selected as the winner and offered a prize and employment opportunities.

[0381] This system enables efficient system development in a short period of time, and allows the selection of excellent engineers through fair evaluation. In this way, the present invention improves the speed and quality of system development while reducing development costs.

[0382] The processing flow will be explained below.

[0383] Step 1:

[0384] A user enters their system requirements using a web portal. The user enters the required features and specifications into the input boxes and clicks the submit button.

[0385] Step 2:

[0386] The device sends the system requirements entered by the user to the server. The system requirements are transferred in a data format such as JSON.

[0387] Step 3:

[0388] The server stores the received system requirements in a database, where the user ID and the requirements information are stored as associated records.

[0389] Step 4:

[0390] The server provides the stored system requirements to the generative AI model, which then passes the requirements to the generative AI model through an appropriate API or interface.

[0391] Step 5:

[0392] The device automatically generates source code based on the system requirements using a generative AI model, which analyzes the stored requirements and generates program code accordingly.

[0393] Step 6:

[0394] The terminal sends the generated source code to the server, which transfers the source code in text format or in an archive file format.

[0395] Step 7:

[0396] The server stores the received source code in a database. The generated source code is stored in association with the user ID.

[0397] Step 8:

[0398] The user uploads the generated source code using a web portal. The user attaches the generated source code file to an upload form and submits it to the server.

[0399] Step 9:

[0400] The server receives the uploaded source code and stores it in a database along with the user ID.

[0401] Step 10:

[0402] The server provides the stored source code to the generated AI review model, which then passes the source code to the review model and issues instructions for evaluation.

[0403] Step 11:

[0404] A generative AI review model evaluates and scores source code quality and functionality, based on criteria such as code efficiency, maintainability, and functional completeness.

[0405] Step 12:

[0406] The server saves the evaluation results in a database and creates a ranking. The evaluation results are saved in the form of user ID and score, and are displayed as a ranking.

[0407] Step 13:

[0408] The server will determine the winner based on the evaluation results. The user with the highest score will be selected as the winner.

[0409] Step 14:

[0410] The server will notify the winners of their prize money and employment opportunities via email and the web portal's messaging system.

[0411] Example 1

[0412] 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."

[0413] Modern system development requires the rapid and efficient generation of high-quality source code and the ability to receive fair evaluations. However, doing this manually requires a great deal of time and effort. A system is also needed to evaluate the technical capabilities of system developers and provide appropriate compensation and employment opportunities based on the evaluation results. However, traditional methods make it difficult to manage these processes in an integrated manner.

[0414] 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.

[0415] In this invention, the server includes means for saving input system requirements, means for generating source code using a generative AI model based on the saved system requirements, means for saving the generated source code, means for viewing, editing, and resaving the generated source code, means for evaluating the saved source code using the generative AI model, and means for determining and notifying a winner based on the evaluation results. This enables the system development process to be accelerated and efficient, and makes it possible to select excellent engineers through fair evaluation and provide them with appropriate compensation and employment opportunities.

[0416] "System requirements" are requirements regarding specifications such as system functions, performance, and constraints.

[0417] A "generative AI model" is a model that uses artificial intelligence technology to automatically generate source code based on specified requirements and prompts.

[0418] "User interface" refers to the interactive screens and forms through which users enter system requirements.

[0419] "Source code" is the text of a program written in a programming language to realize the functions of a system.

[0420] A "server" is a computer system that processes requests from clients (terminals) via a network, stores data, and performs calculations.

[0421] An "evaluation model" is an algorithm or program for evaluating the quality, functionality, efficiency, etc. of generated source code.

[0422] "Winner" refers to the participant who receives the best score based on the evaluation results.

[0423] "Prize" means the monetary reward offered to a winner.

[0424] "Right to join a company" refers to the right to offer outstanding candidates employment opportunities at a specific company.

[0425] A "database" is a system for efficiently storing, retrieving, and managing structured information.

[0426] The present invention provides a system that automatically generates, evaluates, and competes systems based on system requirements entered by the user using a generative AI model. The specific details of the program implementation of this system are shown below.

[0427] System requirements input phase

[0428] The user enters system requirements using a web portal. Using the user interface provided through a browser, the user enters system requirements in text boxes and list-style fields. For example, requirements such as "e-commerce site," "product list display," "cart function," and "payment function" can be entered. The entered requirements are sent from the terminal to the server, which stores them in a database. A relational database management system such as MySQL is used for the database.

[0429] System construction phase

[0430] The server provides the saved system requirements to a generative AI model (e.g., OpenAI's GPT-4 model). The generative AI model generates source code that meets the system requirements based on a prompt. An example of a prompt is "Generate Python code for an e-commerce site with product listing, cart functionality, and payment feature."

[0431] The generated source code is sent by the terminal to the server, which stores it in a database. Before saving, users are also provided with the ability to view, edit, and resave the source code. This function allows users to check the generated source code and make corrections as necessary.

[0432] Deliverables submission phase

[0433] Users upload the final source code using a web portal. The server receives the uploaded source code and stores it in a database. This process allows for centralized management of source code based on system requirements.

[0434] Review Phase

[0435] The stored source code is evaluated by a generative AI review model run by the server. The evaluation criteria consider the quality, functionality, and efficiency of the source code. The evaluation model assigns a score to each source code based on these criteria. The evaluation results are stored in a database and can later be displayed as a ranking.

[0436] Result announcement phase

[0437] The server will determine the winner based on the evaluation results. The winner will be offered a prize and the right to join a company. The server will notify the user of the results directly.

[0438] Specific examples

[0439] For example, a user may input the system requirement "e-commerce site," which includes "product listing," "cart functionality," and "payment functionality." The server sends the generative AI model a prompt: "Generate Python code for an e-commerce site with product listing, cart functionality, and payment feature." The server then receives the generated source code. The user then uploads the final source code to a web portal, and the server evaluates it. The user with the highest evaluation is selected as the winner and is offered a cash prize and employment opportunities.

[0440] This system allows for efficient system development in a short period of time, and allows for the selection of excellent engineers through fair evaluation. In this way, the present invention improves the speed and quality of system development while reducing development costs.

[0441] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0442] Step 1:

[0443] A user accesses a web portal and enters system requirements. They fill in the web portal form with details such as "e-commerce site," "product list display," "cart function," and "payment function." This becomes the input data. The entered system requirements are sent from the terminal to the server via an HTTP POST request. The server receives them and stores them in a database. A relational database management system such as MySQL is used for the database.

[0444] Input: System requirements entered by the user in a web form

[0445] Output: System requirements data sent to the server

[0446] Step 2:

[0447] The server retrieves the system requirements stored in the database and provides them to a generative AI model. The generative AI model (e.g., OpenAI's GPT-4 model) generates source code based on the system requirements, using the prompt "Generate Python code for an e-commerce site with product listing, cart functionality, and payment feature." The generated source code is sent to the terminal.

[0448] Input: System requirements stored in the database

[0449] Output: Source code generated by the generative AI model

[0450] Step 3:

[0451] The device sends the source code received from the generative AI model to the server, which receives the source code and stores it in a database. At this time, the source code is temporarily stored in the file system and its contents are stored in the database.

[0452] Input: Source code received from the generative AI model

[0453] Output: Source code stored in a database

[0454] Step 4:

[0455] Users have the ability to view, edit, and re-save source code through a web portal, and the edited source code is then sent back to the server, which then re-stores it in the database.

[0456] Input: User-edited source code

[0457] Output: Source code resaved to the database

[0458] Step 5:

[0459] Users upload the final source code to a web portal, and the server receives the uploaded source code and stores it in the database in its final form, thus keeping the final source code in the system.

[0460] Input: The final source code uploaded by the user

[0461] Output: Final source code stored in a database

[0462] Step 6:

[0463] The server then provides the final source code stored in the database to the generative AI review model for evaluation. The evaluation model evaluates the source code's quality, functionality, and efficiency, and assigns a score based on each criterion. The evaluation results are then stored in the database again.

[0464] Input: Final source code stored in the database

[0465] Output: Evaluation result score

[0466] Step 7:

[0467] The server will determine the winner based on the evaluation results. The evaluation results will be tallied and the user with the highest score will be selected as the winner. The winner will be notified directly by the server and will be offered a prize money and the right to join the company.

[0468] Input: Evaluation result score

[0469] Output: Winner determination and notification

[0470] This system improves the speed and quality of system development through a series of processing steps, and enables the selection of excellent engineers through fair evaluation.

[0471] (Application example 1)

[0472] 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."

[0473] In the past, it was difficult to quickly and efficiently develop factory automation systems and robot operation plans. In particular, there was a lack of means to design operation plans suited to individual factories and work processes and to properly evaluate their quality and efficiency. Furthermore, building such systems required a great deal of time and cost, which hindered the adoption of automation in small and medium-sized factories and sites with special needs.

[0474] 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.

[0475] In this invention, the server includes a means for saving input system requirements, a means for generating source code using a generative AI model based on the saved system requirements, and a means for saving the generated source code. This provides a means for inputting factory automation system requirements and automatically generating factory work processes and robot operation plans based on the requirements, and a means for evaluating the generated operation plans and source code and assigning scores that take efficiency and quality into consideration, enabling the rapid and high-quality construction of factory automation systems.

[0476] "System requirements" refer to the functions and characteristics that a user expects from a particular system or application.

[0477] A "generative AI model" refers to an artificial intelligence model that automatically generates source code or other output based on input data or requirements.

[0478] "Source code" refers to machine-readable program code for programming the operation of a system or application.

[0479] "Storage" refers to storing data or information in a way that allows it to be accessed at a later time.

[0480] "Evaluation" refers to judging the quality and efficiency of the generated source code and operation plan.

[0481] "Winner" refers to the user or team that receives the highest score based on the evaluation results.

[0482] "Factory automation system" refers to a system for automating manufacturing and other work processes in a factory.

[0483] An "operation plan" refers to the specific operating procedures for robots and automated equipment used in a factory.

[0484] "Score" refers to the score or rating assigned by a rating model.

[0485] This invention is a system for quickly and efficiently constructing factory automation systems and robot operation plans. Specifically, the system automatically generates systems based on user input system requirements using a generative AI model, evaluates them, and then selects the best system through a competition.

[0486] First, a user inputs system requirements, such as a factory automation system or a robot's operation plan, via a web portal. These requirements are sent to a server and stored in a database. The server then provides the stored system requirements to a generative AI model, which the user's device uses to generate optimal source code and an operation plan. The generated source code is then sent back to the server and stored in the database.

[0487] Next, the user uploads the generated source code and operation plan to a web portal. The server receives the uploaded source code and operation plan and evaluates its quality, functionality, efficiency, etc. using a generative AI evaluation model. The scores assigned by the evaluation model are stored in a database and later displayed as a ranking.

[0488] Based on the evaluation results, the server will determine the user with the highest evaluation as the winner and notify them. The winner will be offered a reward and the opportunity to join the company. This system makes it possible to efficiently build high-quality factory automation systems and robot operation plans in a short period of time.

[0489] The specific hardware and software used will include servers, smartphones, and tablets. The software will use Flask as a web application framework and JSON as the data storage format. Advanced generative AI models such as GPT-4 are expected to be used.

[0490] For example, if a factory engineer inputs a requirement such as "a motion plan for a package sorting robot," the generative AI model will generate an optimal motion plan and corresponding source code based on this requirement, which will then be implemented in the factory robot, resulting in a 30% improvement in the robot's operating efficiency.

[0491] Example prompt sentence:

[0492] The user has entered a requirement: "Action plan for a package sorting robot." Based on this requirement, generate and evaluate the optimal logic and source code. Also, provide a plan that takes into account efficiency and safety. The generated source code should look like this:

[0493] In this way, the present invention makes it possible to quickly and efficiently construct and evaluate operation plans for factory automation systems and robots.

[0494] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0495] Step 1:

[0496] The user enters system requirements through a web portal. Specifically, the user uses the user interface to enter detailed requirements for the factory automation system and robot operation plans. The input data is sent to the server in JSON format. Input: System requirements entered by the user. Output: System requirements sent to the server and saved.

[0497] Step 2:

[0498] The server receives the system requirements and stores them in a database. Specifically, it parses the received data and stores it in the database in the correct format. Input: Received system requirements in JSON format. Output: System requirements stored in the database.

[0499] Step 3:

[0500] The server retrieves system requirements from the database and provides them to the generative AI model. Specifically, it converts the data retrieved from the database into a format that the generative AI model can understand and inputs it into the model. Input: System requirements stored in the database. Output: System requirements input into the generative AI model.

[0501] Step 4:

[0502] A generative AI model generates source code based on system requirements. Specifically, a generative AI model (e.g., GPT-4) generates optimal source code based on the provided requirements. Input: System requirements. Output: Generated source code.

[0503] Step 5:

[0504] The generated source code is sent to the server and stored in the database. Specifically, the source code output from the generative AI model is sent to the server and stored in the database in an appropriate format. Input: Source code generated by the generative AI model. Output: Source code stored in the database.

[0505] Step 6:

[0506] The user uploads the generated source code and action plan to the web portal. Specifically, the user selects the generated source code from the user interface and clicks the upload button. Input: Generated source code. Output: Source code uploaded to the server.

[0507] Step 7:

[0508] The server receives the uploaded source code and action plan and evaluates it using a generative AI evaluation model. Specifically, the source code is input into the evaluation model, and a score is calculated based on the evaluation of quality, efficiency, functionality, etc. Input: Uploaded source code. Output: Score calculated by the evaluation model.

[0509] Step 8:

[0510] The evaluation results are stored in a database, and the server determines and notifies the winner based on the results. Specifically, it compares the scores of each source code, selects the user with the highest score as the winner, and notifies the result. Input: Evaluation result score. Output: Determination and notification of the winner.

[0511] Through the above processing steps, this system is able to quickly and efficiently generate and evaluate operation plans for factory automation systems and robots.

[0512] 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.

[0513] This invention combines an emotion engine that recognizes the user's emotions with a system that automatically generates, evaluates, and competes systems based on user input system requirements using a generative AI model. The specific processing flow for the program implementation of this system is described below.

[0514] System requirements input phase

[0515] A user enters system requirements using a web portal. The requirements are sent from the device to a server, which stores them in a database.

[0516] In this phase, the emotion engine analyzes the user's emotional state in real time. The emotion data entered by the user is sent to the server and stored in a database along with the system requirements.

[0517] System construction phase

[0518] The server provides the stored system requirements to the generative AI model. The device uses the generative AI model to automatically generate source code based on the system requirements. This source code is sent from the device to the server, which stores it in a database.

[0519] The emotion engine also monitors the user's emotions during this phase, for example, recording the stress or satisfaction the user feels during the code generation process and sending this data to the server.

[0520] Deliverables submission phase

[0521] Users upload the generated source code to a web portal, and the server receives the uploaded source code and stores it in a database.

[0522] Review Phase

[0523] The stored source code is evaluated by a generative AI review model running on a server. The evaluation model assigns a score based on criteria such as the quality, functionality, and efficiency of the source code. This score is stored in a database and later displayed as a ranking.

[0524] Emotion data obtained from the emotion engine is also reflected in the evaluation process. For example, high-quality source code under low stress conditions can earn additional evaluation points.

[0525] Result announcement phase

[0526] The server will determine the winner based on the evaluation results. The winner will be offered a prize and the right to join the company. The server will then notify the user of the results.

[0527] Specific examples

[0528] For example, suppose a user inputs the system requirements for an "e-commerce website." These requirements include displaying a product list, a cart function, and a payment function. The terminal uses a generative AI model to generate source code containing these functions and sends the source code to the server. During this process, an emotion engine monitors the user's emotions. For example, if the user expresses high satisfaction during this process, the emotion data is also saved. The user then uploads the source code to a web portal, where the server evaluates it. The emotion data is reflected in the evaluation results, and the user with the highest evaluation is selected as the winner and offered a cash prize and employment opportunities.

[0529] This system enables efficient system development in a short period of time and selects excellent engineers through fair evaluation. Furthermore, by incorporating user emotional data into the evaluation process, a more human-centered evaluation becomes possible, leading to improved user satisfaction and experience.

[0530] The processing flow will be explained below.

[0531] Step 1:

[0532] A user enters their system requirements using a web portal. The user enters the required features and specifications into the input boxes and clicks the submit button.

[0533] Step 2:

[0534] The device sends the system requirements entered by the user to the server. The system requirements are transferred in a data format such as JSON.

[0535] Step 3:

[0536] The server stores the received system requirements in a database, where the user ID and the requirements information are stored as associated records.

[0537] Step 4:

[0538] The device's built-in emotion engine analyzes the user's emotions in real time while they are entering system requirements, detecting stress, excitement, and satisfaction from the user's facial expressions, voice, and input speed.

[0539] Step 5:

[0540] The device transmits the analyzed emotion data along with the system requirements to the server, where the emotion data is stored together with the requirements data.

[0541] Step 6:

[0542] The server provides the stored system requirements to the generative AI model, which then passes the requirements to the generative AI model through an appropriate API or interface.

[0543] Step 7:

[0544] The device automatically generates source code based on the system requirements using a generative AI model, which analyzes the stored requirements and generates program code accordingly.

[0545] Step 8:

[0546] The terminal sends the generated source code to the server, which transfers the source code in text format or in an archive file format.

[0547] Step 9:

[0548] The server stores the received source code in a database. The generated source code is stored in association with the user ID.

[0549] Step 10:

[0550] The user uploads the generated source code using a web portal. The user attaches the generated source code file to an upload form and submits it to the server.

[0551] Step 11:

[0552] The server receives the uploaded source code and stores it in a database along with the user ID.

[0553] Step 12:

[0554] The server provides the stored source code to the generated AI review model, which then passes the source code to the review model and issues instructions for evaluation.

[0555] Step 13:

[0556] A generative AI review model evaluates and scores source code quality and functionality, based on criteria such as code efficiency, maintainability, and functional completeness.

[0557] Step 14:

[0558] The server saves the evaluation results in a database and creates a ranking. The evaluation results are saved in the form of user ID and score, and are displayed as a ranking.

[0559] Step 15:

[0560] Emotion data obtained from the emotion engine is also reflected in the evaluation process. For example, high-quality source code under low stress conditions can earn additional evaluation points.

[0561] Step 16:

[0562] The server will determine the winner based on the evaluation results. The user with the highest score will be selected as the winner.

[0563] Step 17:

[0564] The server will notify the winners of their prize money and employment opportunities via email and the web portal's messaging system.

[0565] Example 2

[0566] 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."

[0567] In recent years, there has been a demand for more efficient system development, but conventional methods often involve manual processes, from inputting system requirements to generating source code and evaluating it. This tends to depend on the skills and experience of the developer, making fair and efficient evaluation difficult. Furthermore, there is no established evaluation method that takes into account the emotional state of the developer during the development process, making it difficult to fully improve user satisfaction and experience. Therefore, a system that automates system development and performs evaluations that take into account the developer's emotional data is needed.

[0568] 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.

[0569] In this invention, the server includes means for saving input system requirements, means for generating source code using a generative AI model based on the saved system requirements, means for saving the generated source code, means for analyzing users' emotional states in real time and saving emotional data, means for reflecting the emotional data in the evaluation process, and means for determining and notifying a winner based on the evaluation results. This makes it possible to efficiently and automatically develop systems and to perform fair evaluations that take users' emotional states into account.

[0570] "System requirements" indicate the specific functions, performance, constraints, etc. required for the system to be developed.

[0571] A "generative AI model" is an algorithm or program that uses artificial intelligence technology to automatically generate source code.

[0572] "Source code" means a set of program instructions written in a programming language that can be executed by a computer.

[0573] A "server" is a computer system that stores, processes, and manages data, and provides necessary services in response to requests from clients.

[0574] A "terminal" is a device operated by a user to communicate with a server, such as a PC or smartphone.

[0575] An "emotion engine" is software or hardware that analyzes a user's emotional state and outputs the analysis results as data.

[0576] "Evaluation" is the act of analyzing the quality, functionality, efficiency, etc. of the generated source code and assigning it a score or ranking.

[0577] The "Winner" is the participant who receives the highest score based on the evaluation results.

[0578] "Notification" is the act of transmitting results or information from the server to the user, usually via email or a messaging system.

[0579] "Emotion data" refers to data that indicates the user's emotional state analyzed by the emotion engine, and includes stress level, satisfaction level, and the like.

[0580] The "evaluation process" refers to a series of steps to conduct a fair and objective evaluation based on the generated source code and emotional data.

[0581] The present invention combines an emotion engine that recognizes the user's emotions with a system in which a user inputs system requirements and a generative AI model is used to automatically generate and evaluate a system based on those requirements.

[0582] System requirements input phase

[0583] Users use a web portal to enter system requirements, which are then sent from their devices to a server, which stores them in a database. The web portal runs in a standard web browser and uses HTML and JavaScript to create the user interface.

[0584] Using data from the webcam, keyboard input speed, etc., the emotion engine analyzes the user's emotional state in real time. This emotion data, along with the system requirements, is also sent to the server and stored in a database.

[0585] System construction phase

[0586] The server retrieves the stored system requirements and provides them to a generative AI model, which is built using the latest AI technologies, including natural language processing techniques and machine learning algorithms.

[0587] The device uses a generative AI model to automatically generate source code based on system requirements. The generated source code is written in a common programming language (e.g., Python or JavaScript). The generated source code is sent from the device to a server, which stores it in a database.

[0588] During this phase, the emotion engine also monitors the user's emotions and sends the data to the server for storage, including the level of stress and satisfaction the user feels during code generation.

[0589] Deliverables submission phase

[0590] Users upload the generated source code through a web portal, which is then received by the server and stored in a database.

[0591] Review Phase

[0592] The server provides the stored source code to a generative AI review model, which evaluates and scores the source code based on its quality, functionality, efficiency, etc. The evaluation results are stored in a database and later displayed as a ranking.

[0593] Emotional data is also taken into account in this evaluation process: for example, users who generate high-quality source code under low stress conditions are awarded additional evaluation points.

[0594] Result announcement phase

[0595] The server will determine the winner based on the evaluation results. The winner will be given rewards, employment opportunities, etc. The server will then send a notification of the results to the user.

[0596] Specific examples

[0597] For example, if a user inputs the system requirement "e-commerce site," this requirement includes "displaying a product list," "cart function," and "payment function." The terminal uses a generative AI model to generate source code including these functions and sends the source code to the server. During this process, an emotion engine monitors the user's emotions, and if the user expresses high satisfaction with the process, the emotion data is also saved. The user then uploads the source code to a web portal, and the server evaluates it. The emotion data is reflected in the evaluation results, and the user with the highest evaluation is selected as the winner and offered rewards and employment opportunities.

[0598] Prompt Sentence Examples

[0599] "The system requirements for an e-commerce site include product listing, shopping cart functionality, and payment functionality. Please generate source code using a generative AI model based on these requirements."

[0600] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0601] System processing flow

[0602] Step 1:

[0603] A user opens a web portal and inputs system requirements. The user inputs "Build an e-commerce site," and the requirements include "Display a product list," "Cart function," and "Payment function." The input system requirements are sent to the server by the terminal. At this point, the input data are the system requirements, and the output data are the system requirements sent to the server.

[0604] Operation details:

[0605] Using a web browser, the user enters the system requirements into a form on the web portal and clicks the "Submit" button.

[0606] Step 2:

[0607] The server stores the received system requirements in a database. The server checks the integrity of the entered data and ensures that all required fields are present. At this point, the input data are the system requirements sent from the terminal, and the output data are the system requirements stored in the database.

[0608] Operation details:

[0609] The server receives the HTTP request and stores it in a database.

[0610] Step 3:

[0611] The emotion engine analyzes the user's emotional state in real time. Data such as webcam and keyboard input speed are used for the analysis. This emotion data, along with system requirements, is sent to the server and stored in a database. The input data is raw emotion data, and the output data is analyzed emotion data.

[0612] Operation details:

[0613] The emotion engine analyzes webcam footage and infers emotions from the user's facial expressions and eye movements.

[0614] Step 4:

[0615] The server provides the saved system requirements to the generative AI model, which receives the prompt and generates source code based on it. The input data are the system requirements and the prompt, and the output data is the generated source code.

[0616] Operation details:

[0617] The server sends a prompt to the generative AI model, such as "Please generate source code based on the following system requirements: product list display, cart function, and payment function."

[0618] Step 5:

[0619] The terminal uses the generative AI model to automatically generate source code based on the system requirements. The generated source code is sent from the terminal to the server and stored in a database. The input data is the prompt provided to the generative AI model, and the output data is the generated source code.

[0620] Operation details:

[0621] The device inputs a prompt into the generative AI model, receives the generated source code, and uploads it to the server.

[0622] Step 6:

[0623] The server saves the generated source code in a database. When saving, it checks the data consistency and confirms the format of the required files. The input data is the source code sent from the terminal, and the output data is the source code saved in the database.

[0624] Operation details:

[0625] The server receives the source code uploaded via HTTP request and stores it in a database.

[0626] Step 7:

[0627] The emotion engine monitors the user's emotions even while generating source code. Emotion data is periodically sent to the server and stored in a database in association with system requirements. The input data is raw data of the user's emotions, and the output data is analyzed emotion data.

[0628] Operation details:

[0629] The emotion engine sequentially analyzes the user's facial expressions and behavior during the generation process and transmits the emotional state to the server in real time.

[0630] Step 8:

[0631] The user uploads the generated source code to the server through a web portal. At this point, the input data is the generated source code, and the output data is the source code sent to the server.

[0632] Operation details:

[0633] The user accesses the web portal and uploads the generated source code file by selecting the file using the file specification button and clicking the "Upload" button.

[0634] Step 9:

[0635] The server provides the stored source code to the generative AI review model for evaluation. The evaluation results also reflect emotional data. The input data are the source code and emotional data, and the output data is the evaluation score.

[0636] Operation details:

[0637] The server sends the source code file to the generative AI review model along with a prompt saying, "Please rate this source code for quality, functionality, and efficiency."

[0638] Step 10:

[0639] The server determines the winner based on the evaluation results and notifies the user of the result. The winner will be offered rewards and employment opportunities. The input data is the evaluation score, and the output data is the winner notification and reward information.

[0640] Operation details:

[0641] The server tally the evaluation scores, determine the user with the highest score, and notify the user of the result via email or internal message.

[0642] (Application example 2)

[0643] 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."

[0644] In conventional systems, after users input system requirements, the system is automatically generated and evaluated, but the user's emotional data is not reflected in the process, making it difficult to conduct efficient, human-centered evaluations. Furthermore, there was a lack of efficient means for generating high-quality source code for factory robot control systems. This resulted in poor user satisfaction and experience, making appropriate evaluations difficult.

[0645] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0646] In this invention, the server includes means for saving input system requirements and emotion data, means for generating source code using a generative AI model based on the saved system requirements, and means for saving the generated source code, thereby enabling automatic generation and evaluation of high-quality source code based on the system requirements while reflecting the user's emotion data.

[0647] "System requirements" refers to specific requirements or conditions regarding the operation or functionality of a system.

[0648] "Emotion data" is data that reflects the user's mental state, and includes information such as stress level and satisfaction level.

[0649] "Storage means" refers to a function for temporarily or permanently storing input data and generated source code.

[0650] A "generative AI model" refers to an artificial intelligence algorithm that automatically generates source code or other output based on given requirements or conditions.

[0651] "Evaluation means" refers to functions for evaluating the quality, functionality, efficiency, etc. of the generated source code and system.

[0652] "User interface" refers to the interactive screens and components that allow a user to interact with a system and input data.

[0653] "Notification means" refers to a function for conveying information such as evaluation results and winner selection to users.

[0654] "Benefits" refers to any rewards or rights provided as a result of an evaluation.

[0655] The hardware required to realize this application example includes a server, a user device, and sensors (camera, microphone, etc.) for acquiring emotion data. The software includes the Python programming language, a generative AI model library (AIModel), an emotion recognition library (EmotionEngine), and a database operation library (Database).

[0656] Overall system flow

[0657] The server first receives the system requirements and emotion data entered by the user through the terminal and stores them in a database. Next, it generates source code using a generative AI model based on the stored system requirements. The generated source code is then stored in the database by the server.

[0658] The server then evaluates the stored source code. This evaluation takes into account the generative AI model as well as the user's emotional data. For example, if the user's stress level while entering the system requirements is low, the evaluation score will increase. The server then determines and notifies the winner based on the evaluation results.

[0659] Step-by-step details

[0660] 1. System requirements input:

[0661] When a user inputs system requirements using the terminal's user interface, the emotion engine analyzes emotions in real time, and these data are sent to the server and stored in a database.

[0662] 2. System construction:

[0663] The server retrieves the saved system requirements and uses the generative AI model to generate source code based on the requirements. During this generation process, the emotion engine continues to analyze the user's emotions, which are also stored in the database.

[0664] 3. Evaluation:

[0665] The server evaluates the generated source code, using the generative AI model and user emotion data to calculate an overall score.

[0666] 4. Result notification:

[0667] The server will determine and notify the winner based on the evaluation results, and the winner will receive a prize.

[0668] Specific examples

[0669] For example, consider the case where a user inputs a system requirement such as "a robot control system that can assemble parts at high speed." As the user inputs the requirement, the emotion engine analyzes the user's emotion data, and the server stores this data in a database. Next, a generative AI model generates source code for controlling the robot based on the requirement. The generated source code and emotion data are again stored in the database. The server then uses the generative AI model to evaluate the source code, and determines and notifies the winner based on the evaluation results and emotion data.

[0670] Example prompts to input to the generative AI model

[0671] "Generate source code for a robotic control system that assembles parts at high speed. Requirements are: high speed, high accuracy."

[0672] By inputting this prompt into the AI ​​model, the appropriate source code is generated.

[0673] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0674] Step 1:

[0675] The user inputs system requirements using the user interface of the device. The input system requirements are sent from the device to the server. At that time, the emotion engine analyzes the user's emotion data in real time, and this emotion data is also sent to the server. The server stores the system requirements and emotion data in a database.

[0676] Step 2:

[0677] The server retrieves the system requirements stored in the database. It provides the retrieved system requirements to the generation AI model, which then generates source code based on the system requirements. During this generation process, the emotion engine continues to analyze the user's emotions, which are also sent to the server and stored in the database. The server then stores the generated source code in the database.

[0678] Step 3:

[0679] The server retrieves the generated source code from the database and uses a generative AI model to evaluate the quality, functionality, efficiency, etc. of the source code. The evaluation uses information about the source code itself and stored emotional data. For example, if the user's stress level is low based on the emotional data, the server increases the evaluation score. The evaluation results are stored in the database by the server.

[0680] Step 4:

[0681] The server determines the winner based on the evaluation results stored in the database. When determining the winner, the evaluation results and emotional data are taken into consideration comprehensively. For example, the winner will be the user who generates high-quality source code while working with low stress. After the winner is determined, the server will notify the user.

[0682] Step 5:

[0683] The server processes the delivery of prizes and rewards to winners, including using a management system to arrange and deliver physical and digital rewards, and winners receive notifications and details via email and a user interface.

[0684] Through these steps, the system operates smoothly and enables efficient and human-centered evaluation.

[0685] 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.

[0686] 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.

[0687] 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.

[0688] [Third embodiment]

[0689] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0690] 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.

[0691] 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).

[0692] 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.

[0693] 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.

[0694] 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).

[0695] 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.

[0696] 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.

[0697] 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.

[0698] 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.

[0699] 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.

[0700] 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."

[0701] The present invention provides a system that automatically generates, evaluates, and competes systems based on system requirements entered by the user using a generative AI model. The specific process flow for the program implementation of this system is described below.

[0702] System requirements input phase

[0703] A user enters system requirements using a web portal. The requirements are sent from the device to a server, which stores them in a database.

[0704] System construction phase

[0705] The server provides the stored system requirements to the generative AI model. The device uses the generative AI model to automatically generate source code based on the system requirements. This source code is sent from the device to the server, which stores it in a database.

[0706] Deliverables submission phase

[0707] Users upload the generated source code to a web portal, and the server receives the uploaded source code and stores it in a database.

[0708] Review Phase

[0709] The stored source code is evaluated by a generative AI review model running on a server. The evaluation model assigns a score based on criteria such as the quality, functionality, and efficiency of the source code. This score is stored in a database and later displayed as a ranking.

[0710] Result announcement phase

[0711] The server will determine the winner based on the evaluation results. The winner will be offered a prize and the right to join the company. The server will then notify the user of the results.

[0712] Specific examples

[0713] For example, suppose a user inputs the system requirement "e-commerce website," which includes "displaying a product list," "cart function," and "payment function." The terminal uses a generative AI model to generate source code containing these functions and sends the source code to the server. The user then uploads the source code to a web portal, and the server evaluates it. Based on the evaluation results, the user with the highest evaluation is selected as the winner and offered a prize and employment opportunities.

[0714] This system enables efficient system development in a short period of time, and allows the selection of excellent engineers through fair evaluation. In this way, the present invention improves the speed and quality of system development while reducing development costs.

[0715] The processing flow will be explained below.

[0716] Step 1:

[0717] A user enters their system requirements using a web portal. The user enters the required features and specifications into the input boxes and clicks the submit button.

[0718] Step 2:

[0719] The device sends the system requirements entered by the user to the server. The system requirements are transferred in a data format such as JSON.

[0720] Step 3:

[0721] The server stores the received system requirements in a database, where the user ID and the requirements information are stored as associated records.

[0722] Step 4:

[0723] The server provides the stored system requirements to the generative AI model, which then passes the requirements to the generative AI model through an appropriate API or interface.

[0724] Step 5:

[0725] The device automatically generates source code based on the system requirements using a generative AI model, which analyzes the stored requirements and generates program code accordingly.

[0726] Step 6:

[0727] The terminal sends the generated source code to the server, which transfers the source code in text format or in an archive file format.

[0728] Step 7:

[0729] The server stores the received source code in a database. The generated source code is stored in association with the user ID.

[0730] Step 8:

[0731] The user uploads the generated source code using a web portal. The user attaches the generated source code file to an upload form and submits it to the server.

[0732] Step 9:

[0733] The server receives the uploaded source code and stores it in a database along with the user ID.

[0734] Step 10:

[0735] The server provides the stored source code to the generated AI review model, which then passes the source code to the review model and issues instructions for evaluation.

[0736] Step 11:

[0737] A generative AI review model evaluates and scores source code quality and functionality, based on criteria such as code efficiency, maintainability, and functional completeness.

[0738] Step 12:

[0739] The server saves the evaluation results in a database and creates a ranking. The evaluation results are saved in the form of user ID and score, and are displayed as a ranking.

[0740] Step 13:

[0741] The server will determine the winner based on the evaluation results. The user with the highest score will be selected as the winner.

[0742] Step 14:

[0743] The server will notify the winners of their prize money and employment opportunities via email and the web portal's messaging system.

[0744] Example 1

[0745] 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."

[0746] Modern system development requires the rapid and efficient generation of high-quality source code and the ability to receive fair evaluations. However, doing this manually requires a great deal of time and effort. A system is also needed to evaluate the technical capabilities of system developers and provide appropriate compensation and employment opportunities based on the evaluation results. However, traditional methods make it difficult to manage these processes in an integrated manner.

[0747] 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.

[0748] In this invention, the server includes means for saving input system requirements, means for generating source code using a generative AI model based on the saved system requirements, means for saving the generated source code, means for viewing, editing, and resaving the generated source code, means for evaluating the saved source code using the generative AI model, and means for determining and notifying a winner based on the evaluation results. This enables the system development process to be accelerated and efficient, and makes it possible to select excellent engineers through fair evaluation and provide them with appropriate compensation and employment opportunities.

[0749] "System requirements" are requirements regarding specifications such as system functions, performance, and constraints.

[0750] A "generative AI model" is a model that uses artificial intelligence technology to automatically generate source code based on specified requirements and prompts.

[0751] "User interface" refers to the interactive screens and forms through which users enter system requirements.

[0752] "Source code" is the text of a program written in a programming language to realize the functions of a system.

[0753] A "server" is a computer system that processes requests from clients (terminals) via a network, stores data, and performs calculations.

[0754] An "evaluation model" is an algorithm or program for evaluating the quality, functionality, efficiency, etc. of generated source code.

[0755] "Winner" refers to the participant who receives the best score based on the evaluation results.

[0756] "Prize" means the monetary reward offered to a winner.

[0757] "Right to join a company" refers to the right to offer outstanding candidates employment opportunities at a specific company.

[0758] A "database" is a system for efficiently storing, retrieving, and managing structured information.

[0759] The present invention provides a system that automatically generates, evaluates, and competes systems based on system requirements entered by the user using a generative AI model. The specific details of the program implementation of this system are shown below.

[0760] System requirements input phase

[0761] The user enters system requirements using a web portal. Using the user interface provided through a browser, the user enters system requirements in text boxes and list-style fields. For example, requirements such as "e-commerce site," "product list display," "cart function," and "payment function" can be entered. The entered requirements are sent from the terminal to the server, which stores them in a database. A relational database management system such as MySQL is used for the database.

[0762] System construction phase

[0763] The server provides the saved system requirements to a generative AI model (e.g., OpenAI's GPT-4 model). The generative AI model generates source code that meets the system requirements based on a prompt. An example of a prompt is "Generate Python code for an e-commerce site with product listing, cart functionality, and payment feature."

[0764] The generated source code is sent by the terminal to the server, which stores it in a database. Before saving, users are also provided with the ability to view, edit, and resave the source code. This function allows users to check the generated source code and make corrections as necessary.

[0765] Deliverables submission phase

[0766] Users upload the final source code using a web portal. The server receives the uploaded source code and stores it in a database. This process allows for centralized management of source code based on system requirements.

[0767] Review Phase

[0768] The stored source code is evaluated by a generative AI review model run by the server. The evaluation criteria consider the quality, functionality, and efficiency of the source code. The evaluation model assigns a score to each source code based on these criteria. The evaluation results are stored in a database and can later be displayed as a ranking.

[0769] Result announcement phase

[0770] The server will determine the winner based on the evaluation results. The winner will be offered a prize and the right to join a company. The server will notify the user of the results directly.

[0771] Specific examples

[0772] For example, a user may input the system requirement "e-commerce site," which includes "product listing," "cart functionality," and "payment functionality." The server sends the generative AI model a prompt: "Generate Python code for an e-commerce site with product listing, cart functionality, and payment feature." The server then receives the generated source code. The user then uploads the final source code to a web portal, and the server evaluates it. The user with the highest evaluation is selected as the winner and is offered a cash prize and employment opportunities.

[0773] This system allows for efficient system development in a short period of time, and allows for the selection of excellent engineers through fair evaluation. In this way, the present invention improves the speed and quality of system development while reducing development costs.

[0774] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0775] Step 1:

[0776] A user accesses a web portal and enters system requirements. They fill in the web portal form with details such as "e-commerce site," "product list display," "cart function," and "payment function." This becomes the input data. The entered system requirements are sent from the terminal to the server via an HTTP POST request. The server receives them and stores them in a database. A relational database management system such as MySQL is used for the database.

[0777] Input: System requirements entered by the user in a web form

[0778] Output: System requirements data sent to the server

[0779] Step 2:

[0780] The server retrieves the system requirements stored in the database and provides them to a generative AI model. The generative AI model (e.g., OpenAI's GPT-4 model) generates source code based on the system requirements, using the prompt "Generate Python code for an e-commerce site with product listing, cart functionality, and payment feature." The generated source code is sent to the terminal.

[0781] Input: System requirements stored in the database

[0782] Output: Source code generated by the generative AI model

[0783] Step 3:

[0784] The device sends the source code received from the generative AI model to the server, which receives the source code and stores it in a database. At this time, the source code is temporarily stored in the file system and its contents are stored in the database.

[0785] Input: Source code received from the generative AI model

[0786] Output: Source code stored in a database

[0787] Step 4:

[0788] Users have the ability to view, edit, and re-save source code through a web portal, and the edited source code is then sent back to the server, which then re-stores it in the database.

[0789] Input: User-edited source code

[0790] Output: Source code resaved to the database

[0791] Step 5:

[0792] Users upload the final source code to a web portal, and the server receives the uploaded source code and stores it in the database in its final form, thus keeping the final source code in the system.

[0793] Input: The final source code uploaded by the user

[0794] Output: Final source code stored in a database

[0795] Step 6:

[0796] The server then provides the final source code stored in the database to the generative AI review model for evaluation. The evaluation model evaluates the source code's quality, functionality, and efficiency, and assigns a score based on each criterion. The evaluation results are then stored in the database again.

[0797] Input: Final source code stored in the database

[0798] Output: Evaluation result score

[0799] Step 7:

[0800] The server will determine the winner based on the evaluation results. The evaluation results will be tallied and the user with the highest score will be selected as the winner. The winner will be notified directly by the server and will be offered a prize money and the right to join the company.

[0801] Input: Evaluation result score

[0802] Output: Winner determination and notification

[0803] This system improves the speed and quality of system development through a series of processing steps, and enables the selection of excellent engineers through fair evaluation.

[0804] (Application example 1)

[0805] 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."

[0806] In the past, it was difficult to quickly and efficiently develop factory automation systems and robot operation plans. In particular, there was a lack of means to design operation plans suited to individual factories and work processes and to properly evaluate their quality and efficiency. Furthermore, building such systems required a great deal of time and cost, which hindered the adoption of automation in small and medium-sized factories and sites with special needs.

[0807] 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.

[0808] In this invention, the server includes a means for saving input system requirements, a means for generating source code using a generative AI model based on the saved system requirements, and a means for saving the generated source code. This provides a means for inputting factory automation system requirements and automatically generating factory work processes and robot operation plans based on the requirements, and a means for evaluating the generated operation plans and source code and assigning scores that take efficiency and quality into consideration, enabling the rapid and high-quality construction of factory automation systems.

[0809] "System requirements" refer to the functions and characteristics that a user expects from a particular system or application.

[0810] A "generative AI model" refers to an artificial intelligence model that automatically generates source code or other output based on input data or requirements.

[0811] "Source code" refers to machine-readable program code for programming the operation of a system or application.

[0812] "Storage" refers to storing data or information in a way that allows it to be accessed at a later time.

[0813] "Evaluation" refers to judging the quality and efficiency of the generated source code and operation plan.

[0814] "Winner" refers to the user or team that receives the highest score based on the evaluation results.

[0815] "Factory automation system" refers to a system for automating manufacturing and other work processes in a factory.

[0816] An "operation plan" refers to the specific operating procedures for robots and automated equipment used in a factory.

[0817] "Score" refers to the score or rating assigned by a rating model.

[0818] This invention is a system for quickly and efficiently constructing factory automation systems and robot operation plans. Specifically, the system automatically generates systems based on user input system requirements using a generative AI model, evaluates them, and then selects the best system through a competition.

[0819] First, a user inputs system requirements, such as a factory automation system or a robot's operation plan, via a web portal. These requirements are sent to a server and stored in a database. The server then provides the stored system requirements to a generative AI model, which the user's device uses to generate optimal source code and an operation plan. The generated source code is then sent back to the server and stored in the database.

[0820] Next, the user uploads the generated source code and operation plan to a web portal. The server receives the uploaded source code and operation plan and evaluates its quality, functionality, efficiency, etc. using a generative AI evaluation model. The scores assigned by the evaluation model are stored in a database and later displayed as a ranking.

[0821] Based on the evaluation results, the server will determine the user with the highest evaluation as the winner and notify them. The winner will be offered a reward and the opportunity to join the company. This system makes it possible to efficiently build high-quality factory automation systems and robot operation plans in a short period of time.

[0822] The specific hardware and software used will include servers, smartphones, and tablets. The software will use Flask as a web application framework and JSON as the data storage format. Advanced generative AI models such as GPT-4 are expected to be used.

[0823] For example, if a factory engineer inputs a requirement such as "a motion plan for a package sorting robot," the generative AI model will generate an optimal motion plan and corresponding source code based on this requirement, which will then be implemented in the factory robot, resulting in a 30% improvement in the robot's operating efficiency.

[0824] Example prompt sentence:

[0825] The user has entered a requirement: "Action plan for a package sorting robot." Based on this requirement, generate and evaluate the optimal logic and source code. Also, provide a plan that takes into account efficiency and safety. The generated source code should look like this:

[0826] In this way, the present invention makes it possible to quickly and efficiently construct and evaluate operation plans for factory automation systems and robots.

[0827] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0828] Step 1:

[0829] The user enters system requirements through a web portal. Specifically, the user uses the user interface to enter detailed requirements for the factory automation system and robot operation plans. The input data is sent to the server in JSON format. Input: System requirements entered by the user. Output: System requirements sent to the server and saved.

[0830] Step 2:

[0831] The server receives the system requirements and stores them in a database. Specifically, it parses the received data and stores it in the database in the correct format. Input: Received system requirements in JSON format. Output: System requirements stored in the database.

[0832] Step 3:

[0833] The server retrieves system requirements from the database and provides them to the generative AI model. Specifically, it converts the data retrieved from the database into a format that the generative AI model can understand and inputs it into the model. Input: System requirements stored in the database. Output: System requirements input into the generative AI model.

[0834] Step 4:

[0835] A generative AI model generates source code based on system requirements. Specifically, a generative AI model (e.g., GPT-4) generates optimal source code based on the provided requirements. Input: System requirements. Output: Generated source code.

[0836] Step 5:

[0837] The generated source code is sent to the server and stored in the database. Specifically, the source code output from the generative AI model is sent to the server and stored in the database in an appropriate format. Input: Source code generated by the generative AI model. Output: Source code stored in the database.

[0838] Step 6:

[0839] The user uploads the generated source code and action plan to the web portal. Specifically, the user selects the generated source code from the user interface and clicks the upload button. Input: Generated source code. Output: Source code uploaded to the server.

[0840] Step 7:

[0841] The server receives the uploaded source code and action plan and evaluates it using a generative AI evaluation model. Specifically, the source code is input into the evaluation model, and a score is calculated based on the evaluation of quality, efficiency, functionality, etc. Input: Uploaded source code. Output: Score calculated by the evaluation model.

[0842] Step 8:

[0843] The evaluation results are stored in a database, and the server determines and notifies the winner based on the results. Specifically, it compares the scores of each source code, selects the user with the highest score as the winner, and notifies the result. Input: Evaluation result score. Output: Determination and notification of the winner.

[0844] Through the above processing steps, this system is able to quickly and efficiently generate and evaluate operation plans for factory automation systems and robots.

[0845] 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.

[0846] This invention combines an emotion engine that recognizes the user's emotions with a system that automatically generates, evaluates, and competes systems based on user input system requirements using a generative AI model. The specific processing flow for the program implementation of this system is described below.

[0847] System requirements input phase

[0848] A user enters system requirements using a web portal. The requirements are sent from the device to a server, which stores them in a database.

[0849] In this phase, the emotion engine analyzes the user's emotional state in real time. The emotion data entered by the user is sent to the server and stored in a database along with the system requirements.

[0850] System construction phase

[0851] The server provides the stored system requirements to the generative AI model. The device uses the generative AI model to automatically generate source code based on the system requirements. This source code is sent from the device to the server, which stores it in a database.

[0852] The emotion engine also monitors the user's emotions during this phase, for example, recording the stress or satisfaction the user feels during the code generation process and sending this data to the server.

[0853] Deliverables submission phase

[0854] Users upload the generated source code to a web portal, and the server receives the uploaded source code and stores it in a database.

[0855] Review Phase

[0856] The stored source code is evaluated by a generative AI review model running on a server. The evaluation model assigns a score based on criteria such as the quality, functionality, and efficiency of the source code. This score is stored in a database and later displayed as a ranking.

[0857] Emotion data obtained from the emotion engine is also reflected in the evaluation process. For example, high-quality source code under low stress conditions can earn additional evaluation points.

[0858] Result announcement phase

[0859] The server will determine the winner based on the evaluation results. The winner will be offered a prize and the right to join the company. The server will then notify the user of the results.

[0860] Specific examples

[0861] For example, suppose a user inputs the system requirements for an "e-commerce website." These requirements include displaying a product list, a cart function, and a payment function. The terminal uses a generative AI model to generate source code containing these functions and sends the source code to the server. During this process, an emotion engine monitors the user's emotions. For example, if the user expresses high satisfaction during this process, the emotion data is also saved. The user then uploads the source code to a web portal, where the server evaluates it. The emotion data is reflected in the evaluation results, and the user with the highest evaluation is selected as the winner and offered a cash prize and employment opportunities.

[0862] This system enables efficient system development in a short period of time and selects excellent engineers through fair evaluation. Furthermore, by incorporating user emotional data into the evaluation process, a more human-centered evaluation becomes possible, leading to improved user satisfaction and experience.

[0863] The processing flow will be explained below.

[0864] Step 1:

[0865] A user enters their system requirements using a web portal. The user enters the required features and specifications into the input boxes and clicks the submit button.

[0866] Step 2:

[0867] The device sends the system requirements entered by the user to the server. The system requirements are transferred in a data format such as JSON.

[0868] Step 3:

[0869] The server stores the received system requirements in a database, where the user ID and the requirements information are stored as associated records.

[0870] Step 4:

[0871] The device's built-in emotion engine analyzes the user's emotions in real time while they are entering system requirements, detecting stress, excitement, and satisfaction from the user's facial expressions, voice, and input speed.

[0872] Step 5:

[0873] The device transmits the analyzed emotion data along with the system requirements to the server, where the emotion data is stored together with the requirements data.

[0874] Step 6:

[0875] The server provides the stored system requirements to the generative AI model, which then passes the requirements to the generative AI model through an appropriate API or interface.

[0876] Step 7:

[0877] The device automatically generates source code based on the system requirements using a generative AI model, which analyzes the stored requirements and generates program code accordingly.

[0878] Step 8:

[0879] The terminal sends the generated source code to the server, which transfers the source code in text format or in an archive file format.

[0880] Step 9:

[0881] The server stores the received source code in a database. The generated source code is stored in association with the user ID.

[0882] Step 10:

[0883] The user uploads the generated source code using a web portal. The user attaches the generated source code file to an upload form and submits it to the server.

[0884] Step 11:

[0885] The server receives the uploaded source code and stores it in a database along with the user ID.

[0886] Step 12:

[0887] The server provides the stored source code to the generated AI review model, which then passes the source code to the review model and issues instructions for evaluation.

[0888] Step 13:

[0889] A generative AI review model evaluates and scores source code quality and functionality, based on criteria such as code efficiency, maintainability, and functional completeness.

[0890] Step 14:

[0891] The server saves the evaluation results in a database and creates a ranking. The evaluation results are saved in the form of user ID and score, and are displayed as a ranking.

[0892] Step 15:

[0893] Emotion data obtained from the emotion engine is also reflected in the evaluation process. For example, high-quality source code under low stress conditions can earn additional evaluation points.

[0894] Step 16:

[0895] The server will determine the winner based on the evaluation results. The user with the highest score will be selected as the winner.

[0896] Step 17:

[0897] The server will notify the winners of their prize money and employment opportunities via email and the web portal's messaging system.

[0898] Example 2

[0899] 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."

[0900] In recent years, there has been a demand for more efficient system development, but conventional methods often involve manual processes, from inputting system requirements to generating source code and evaluating it. This tends to depend on the skills and experience of the developer, making fair and efficient evaluation difficult. Furthermore, there is no established evaluation method that takes into account the emotional state of the developer during the development process, making it difficult to fully improve user satisfaction and experience. Therefore, a system that automates system development and performs evaluations that take into account the developer's emotional data is needed.

[0901] 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.

[0902] In this invention, the server includes means for saving input system requirements, means for generating source code using a generative AI model based on the saved system requirements, means for saving the generated source code, means for analyzing users' emotional states in real time and saving emotional data, means for reflecting the emotional data in the evaluation process, and means for determining and notifying a winner based on the evaluation results. This makes it possible to efficiently and automatically develop systems and to perform fair evaluations that take users' emotional states into account.

[0903] "System requirements" indicate the specific functions, performance, constraints, etc. required for the system to be developed.

[0904] A "generative AI model" is an algorithm or program that uses artificial intelligence technology to automatically generate source code.

[0905] "Source code" means a set of program instructions written in a programming language that can be executed by a computer.

[0906] A "server" is a computer system that stores, processes, and manages data, and provides necessary services in response to requests from clients.

[0907] A "terminal" is a device operated by a user to communicate with a server, such as a PC or smartphone.

[0908] An "emotion engine" is software or hardware that analyzes a user's emotional state and outputs the analysis results as data.

[0909] "Evaluation" is the act of analyzing the quality, functionality, efficiency, etc. of the generated source code and assigning it a score or ranking.

[0910] The "Winner" is the participant who receives the highest score based on the evaluation results.

[0911] "Notification" is the act of transmitting results or information from the server to the user, usually via email or a messaging system.

[0912] "Emotion data" refers to data that indicates the user's emotional state analyzed by the emotion engine, and includes stress level, satisfaction level, and the like.

[0913] The "evaluation process" refers to a series of steps to conduct a fair and objective evaluation based on the generated source code and emotional data.

[0914] The present invention combines an emotion engine that recognizes the user's emotions with a system in which a user inputs system requirements and a generative AI model is used to automatically generate and evaluate a system based on those requirements.

[0915] System requirements input phase

[0916] Users use a web portal to enter system requirements, which are then sent from their devices to a server, which stores them in a database. The web portal runs in a standard web browser and uses HTML and JavaScript to create the user interface.

[0917] Using data from the webcam and keyboard input speed, the emotion engine analyzes the user's emotional state in real time, and this emotion data, along with the system requirements, is sent to the server and stored in a database.

[0918] System construction phase

[0919] The server retrieves the stored system requirements and provides them to a generative AI model, which is built using the latest AI technologies, including natural language processing techniques and machine learning algorithms.

[0920] The device uses a generative AI model to automatically generate source code based on system requirements. The generated source code is written in a common programming language (e.g., Python or JavaScript). The generated source code is sent from the device to a server, which stores it in a database.

[0921] During this phase, the emotion engine also monitors the user's emotions and sends the data to the server for storage, including the level of stress and satisfaction the user feels during code generation.

[0922] Deliverables submission phase

[0923] Users upload the generated source code through a web portal, which is then received by the server and stored in a database.

[0924] Review Phase

[0925] The server provides the stored source code to a generative AI review model, which evaluates and scores the source code based on its quality, functionality, efficiency, etc. The evaluation results are stored in a database and later displayed as a ranking.

[0926] Emotional data is also taken into account in this evaluation process: for example, users who generate high-quality source code under low stress conditions are awarded additional evaluation points.

[0927] Result announcement phase

[0928] The server will determine the winner based on the evaluation results. The winner will be given rewards, employment opportunities, etc. The server will then send a notification of the results to the user.

[0929] Specific examples

[0930] For example, if a user inputs the system requirement "e-commerce site," this requirement includes "displaying a product list," "cart function," and "payment function." The terminal uses a generative AI model to generate source code including these functions and sends the source code to the server. During this process, an emotion engine monitors the user's emotions, and if the user expresses high satisfaction with the process, the emotion data is also saved. The user then uploads the source code to a web portal, and the server evaluates it. The emotion data is reflected in the evaluation results, and the user with the highest evaluation is selected as the winner and offered rewards and employment opportunities.

[0931] Prompt Sentence Examples

[0932] "The system requirements for an e-commerce site include product listing, shopping cart functionality, and payment functionality. Please generate source code using a generative AI model based on these requirements."

[0933] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0934] System processing flow

[0935] Step 1:

[0936] A user opens a web portal and inputs system requirements. The user inputs "Build an e-commerce site," and the requirements include "Display a product list," "Cart function," and "Payment function." The input system requirements are sent to the server by the terminal. At this point, the input data are the system requirements, and the output data are the system requirements sent to the server.

[0937] Operation details:

[0938] Using a web browser, the user enters the system requirements into a form on the web portal and clicks the "Submit" button.

[0939] Step 2:

[0940] The server stores the received system requirements in a database. The server checks the integrity of the entered data and ensures that all required fields are present. At this point, the input data are the system requirements sent from the terminal, and the output data are the system requirements stored in the database.

[0941] Operation details:

[0942] The server receives the HTTP request and stores it in a database.

[0943] Step 3:

[0944] The emotion engine analyzes the user's emotional state in real time. Data such as webcam and keyboard input speed are used for the analysis. This emotion data, along with system requirements, is sent to the server and stored in a database. The input data is raw emotion data, and the output data is analyzed emotion data.

[0945] Operation details:

[0946] The emotion engine analyzes webcam footage and infers emotions from the user's facial expressions and eye movements.

[0947] Step 4:

[0948] The server provides the saved system requirements to the generative AI model, which receives the prompt and generates source code based on it. The input data are the system requirements and the prompt, and the output data is the generated source code.

[0949] Operation details:

[0950] The server sends a prompt to the generative AI model, such as "Please generate source code based on the following system requirements: product list display, cart function, and payment function."

[0951] Step 5:

[0952] The terminal uses the generative AI model to automatically generate source code based on the system requirements. The generated source code is sent from the terminal to the server and stored in a database. The input data is the prompt provided to the generative AI model, and the output data is the generated source code.

[0953] Operation details:

[0954] The device inputs a prompt into the generative AI model, receives the generated source code, and uploads it to the server.

[0955] Step 6:

[0956] The server saves the generated source code in a database. When saving, it checks the data consistency and confirms the format of the required files. The input data is the source code sent from the terminal, and the output data is the source code saved in the database.

[0957] Operation details:

[0958] The server receives the source code uploaded via HTTP request and stores it in a database.

[0959] Step 7:

[0960] The emotion engine monitors the user's emotions even while generating source code. Emotion data is periodically sent to the server and stored in a database in association with system requirements. The input data is raw data of the user's emotions, and the output data is analyzed emotion data.

[0961] Operation details:

[0962] The emotion engine sequentially analyzes the user's facial expressions and behavior during the generation process and transmits the emotional state to the server in real time.

[0963] Step 8:

[0964] The user uploads the generated source code to the server through a web portal. At this point, the input data is the generated source code, and the output data is the source code sent to the server.

[0965] Operation details:

[0966] The user accesses the web portal and uploads the generated source code file by selecting the file using the file specification button and clicking the "Upload" button.

[0967] Step 9:

[0968] The server provides the stored source code to the generative AI review model for evaluation. The evaluation results also reflect emotional data. The input data are the source code and emotional data, and the output data is the evaluation score.

[0969] Operation details:

[0970] The server sends the source code file to the generative AI review model along with a prompt saying, "Please rate this source code for quality, functionality, and efficiency."

[0971] Step 10:

[0972] The server determines the winner based on the evaluation results and notifies the user of the result. The winner will be offered rewards and employment opportunities. The input data is the evaluation score, and the output data is the winner notification and reward information.

[0973] Operation details:

[0974] The server tally the evaluation scores, determine the user with the highest score, and notify the user of the result via email or internal message.

[0975] (Application example 2)

[0976] 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."

[0977] In conventional systems, after users input system requirements, the system is automatically generated and evaluated, but the user's emotional data is not reflected in the process, making it difficult to conduct efficient, human-centered evaluations. Furthermore, there was a lack of efficient means for generating high-quality source code for factory robot control systems. This resulted in poor user satisfaction and experience, making appropriate evaluations difficult.

[0978] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0979] In this invention, the server includes means for saving input system requirements and emotion data, means for generating source code using a generative AI model based on the saved system requirements, and means for saving the generated source code, thereby enabling automatic generation and evaluation of high-quality source code based on the system requirements while reflecting the user's emotion data.

[0980] "System requirements" refers to specific requirements or conditions regarding the operation or functionality of a system.

[0981] "Emotion data" is data that reflects the user's mental state, and includes information such as stress level and satisfaction level.

[0982] "Storage means" refers to a function for temporarily or permanently storing input data and generated source code.

[0983] A "generative AI model" refers to an artificial intelligence algorithm that automatically generates source code or other output based on given requirements or conditions.

[0984] "Evaluation means" refers to functions for evaluating the quality, functionality, efficiency, etc. of the generated source code and system.

[0985] "User interface" refers to the interactive screens and components that allow a user to interact with a system and input data.

[0986] "Notification means" refers to a function for conveying information such as evaluation results and winner selection to users.

[0987] "Benefits" refers to any rewards or rights provided as a result of an evaluation.

[0988] The hardware required to realize this application example includes a server, a user device, and sensors (camera, microphone, etc.) for acquiring emotion data. The software includes the Python programming language, a generative AI model library (AIModel), an emotion recognition library (EmotionEngine), and a database operation library (Database).

[0989] Overall system flow

[0990] The server first receives the system requirements and emotion data entered by the user through the terminal and stores them in a database. Next, it generates source code using a generative AI model based on the stored system requirements. The generated source code is then stored in the database by the server.

[0991] The server then evaluates the stored source code. This evaluation takes into account the generative AI model as well as the user's emotional data. For example, if the user's stress level while entering the system requirements is low, the evaluation score will increase. The server then determines and notifies the winner based on the evaluation results.

[0992] Step-by-step details

[0993] 1. System requirements input:

[0994] When a user inputs system requirements using the terminal's user interface, the emotion engine analyzes emotions in real time, and these data are sent to the server and stored in a database.

[0995] 2. System construction:

[0996] The server retrieves the saved system requirements and uses the generative AI model to generate source code based on the requirements. During this generation process, the emotion engine continues to analyze the user's emotions, which are also stored in the database.

[0997] 3. Evaluation:

[0998] The server evaluates the generated source code, using the generative AI model and user emotion data to calculate an overall score.

[0999] 4. Result notification:

[1000] The server will determine and notify the winner based on the evaluation results, and the winner will receive a prize.

[1001] Specific examples

[1002] For example, consider the case where a user inputs a system requirement such as "a robot control system that can assemble parts at high speed." As the user inputs the requirement, the emotion engine analyzes the user's emotion data, and the server stores this data in a database. Next, a generative AI model generates source code for controlling the robot based on the requirement. The generated source code and emotion data are again stored in the database. The server then uses the generative AI model to evaluate the source code, and determines and notifies the winner based on the evaluation results and emotion data.

[1003] Example prompts to input to the generative AI model

[1004] "Generate source code for a robotic control system that assembles parts at high speed. Requirements are: high speed, high accuracy."

[1005] By inputting this prompt into the AI ​​model, the appropriate source code is generated.

[1006] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1007] Step 1:

[1008] The user inputs system requirements using the user interface of the device. The input system requirements are sent from the device to the server. At that time, the emotion engine analyzes the user's emotion data in real time, and this emotion data is also sent to the server. The server stores the system requirements and emotion data in a database.

[1009] Step 2:

[1010] The server retrieves the system requirements stored in the database. It provides the retrieved system requirements to the generation AI model, which then generates source code based on the system requirements. During this generation process, the emotion engine continues to analyze the user's emotions, which are also sent to the server and stored in the database. The server then stores the generated source code in the database.

[1011] Step 3:

[1012] The server retrieves the generated source code from the database and uses a generative AI model to evaluate the quality, functionality, efficiency, etc. of the source code. The evaluation uses information about the source code itself and stored emotional data. For example, if the user's stress level is low based on the emotional data, the server increases the evaluation score. The evaluation results are stored in the database by the server.

[1013] Step 4:

[1014] The server determines the winner based on the evaluation results stored in the database. When determining the winner, the evaluation results and emotional data are taken into consideration comprehensively. For example, the winner will be the user who generates high-quality source code while working with low stress. After the winner is determined, the server will notify the user.

[1015] Step 5:

[1016] The server processes the delivery of prizes and rewards to winners, including using a management system to arrange and deliver physical and digital rewards, and winners receive notifications and details via email and a user interface.

[1017] Through these steps, the system operates smoothly and enables efficient and human-centered evaluation.

[1018] 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.

[1019] 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.

[1020] 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.

[1021] [Fourth embodiment]

[1022] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1023] 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.

[1024] 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).

[1025] 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.

[1026] 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.

[1027] 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).

[1028] 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.

[1029] 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.

[1030] 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.

[1031] 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.

[1032] 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.

[1033] 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.

[1034] 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."

[1035] The present invention provides a system that automatically generates, evaluates, and competes systems based on system requirements entered by the user using a generative AI model. The specific process flow for the program implementation of this system is described below.

[1036] System requirements input phase

[1037] A user enters system requirements using a web portal. The requirements are sent from the device to a server, which stores them in a database.

[1038] System construction phase

[1039] The server provides the stored system requirements to the generative AI model. The device uses the generative AI model to automatically generate source code based on the system requirements. This source code is sent from the device to the server, which stores it in a database.

[1040] Deliverables submission phase

[1041] Users upload the generated source code to a web portal, and the server receives the uploaded source code and stores it in a database.

[1042] Review Phase

[1043] The stored source code is evaluated by a generative AI review model running on a server. The evaluation model assigns a score based on criteria such as the quality, functionality, and efficiency of the source code. This score is stored in a database and later displayed as a ranking.

[1044] Result announcement phase

[1045] The server will determine the winner based on the evaluation results. The winner will be offered a prize and the right to join the company. The server will then notify the user of the results.

[1046] Specific examples

[1047] For example, suppose a user inputs the system requirement "e-commerce website," which includes "displaying a product list," "cart function," and "payment function." The terminal uses a generative AI model to generate source code containing these functions and sends the source code to the server. The user then uploads the source code to a web portal, and the server evaluates it. Based on the evaluation results, the user with the highest evaluation is selected as the winner and offered a prize and employment opportunities.

[1048] This system enables efficient system development in a short period of time, and allows the selection of excellent engineers through fair evaluation. In this way, the present invention improves the speed and quality of system development while reducing development costs.

[1049] The processing flow will be explained below.

[1050] Step 1:

[1051] A user enters their system requirements using a web portal. The user enters the required features and specifications into the input boxes and clicks the submit button.

[1052] Step 2:

[1053] The device sends the system requirements entered by the user to the server. The system requirements are transferred in a data format such as JSON.

[1054] Step 3:

[1055] The server stores the received system requirements in a database, where the user ID and the requirements information are stored as associated records.

[1056] Step 4:

[1057] The server provides the stored system requirements to the generative AI model, which then passes the requirements to the generative AI model through an appropriate API or interface.

[1058] Step 5:

[1059] The device automatically generates source code based on the system requirements using a generative AI model, which analyzes the stored requirements and generates program code accordingly.

[1060] Step 6:

[1061] The terminal sends the generated source code to the server, which transfers the source code in text format or in an archive file format.

[1062] Step 7:

[1063] The server stores the received source code in a database. The generated source code is stored in association with the user ID.

[1064] Step 8:

[1065] The user uploads the generated source code using a web portal. The user attaches the generated source code file to an upload form and submits it to the server.

[1066] Step 9:

[1067] The server receives the uploaded source code and stores it in a database along with the user ID.

[1068] Step 10:

[1069] The server provides the stored source code to the generated AI review model, which then passes the source code to the review model and issues instructions for evaluation.

[1070] Step 11:

[1071] A generative AI review model evaluates and scores source code quality and functionality, based on criteria such as code efficiency, maintainability, and functional completeness.

[1072] Step 12:

[1073] The server saves the evaluation results in a database and creates a ranking. The evaluation results are saved in the form of user ID and score, and are displayed as a ranking.

[1074] Step 13:

[1075] The server will determine the winner based on the evaluation results. The user with the highest score will be selected as the winner.

[1076] Step 14:

[1077] The server will notify the winners of their prize money and employment opportunities via email and the web portal's messaging system.

[1078] Example 1

[1079] 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."

[1080] Modern system development requires the rapid and efficient generation of high-quality source code and the ability to receive fair evaluations. However, doing this manually requires a great deal of time and effort. A system is also needed to evaluate the technical capabilities of system developers and provide appropriate compensation and employment opportunities based on the evaluation results. However, traditional methods make it difficult to manage these processes in an integrated manner.

[1081] 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.

[1082] In this invention, the server includes means for saving input system requirements, means for generating source code using a generative AI model based on the saved system requirements, means for saving the generated source code, means for viewing, editing, and resaving the generated source code, means for evaluating the saved source code using the generative AI model, and means for determining and notifying a winner based on the evaluation results. This enables the system development process to be accelerated and efficient, and makes it possible to select excellent engineers through fair evaluation and provide them with appropriate compensation and employment opportunities.

[1083] "System requirements" are requirements regarding specifications such as system functions, performance, and constraints.

[1084] A "generative AI model" is a model that uses artificial intelligence technology to automatically generate source code based on specified requirements and prompts.

[1085] "User interface" refers to the interactive screens and forms through which users enter system requirements.

[1086] "Source code" is the text of a program written in a programming language to realize the functions of a system.

[1087] A "server" is a computer system that processes requests from clients (terminals) via a network, stores data, and performs calculations.

[1088] An "evaluation model" is an algorithm or program for evaluating the quality, functionality, efficiency, etc. of generated source code.

[1089] "Winner" refers to the participant who receives the best score based on the evaluation results.

[1090] "Prize" means the monetary reward offered to a winner.

[1091] "Right to join a company" refers to the right to offer outstanding candidates employment opportunities at a specific company.

[1092] A "database" is a system for efficiently storing, retrieving, and managing structured information.

[1093] The present invention provides a system that automatically generates, evaluates, and competes systems based on system requirements entered by the user using a generative AI model. The specific details of the program implementation of this system are shown below.

[1094] System requirements input phase

[1095] The user enters system requirements using a web portal. Using the user interface provided through a browser, the user enters system requirements in text boxes and list-style fields. For example, requirements such as "e-commerce site," "product list display," "cart function," and "payment function" can be entered. The entered requirements are sent from the terminal to the server, which stores them in a database. A relational database management system such as MySQL is used for the database.

[1096] System construction phase

[1097] The server provides the saved system requirements to a generative AI model (e.g., OpenAI's GPT-4 model). The generative AI model generates source code that meets the system requirements based on a prompt. An example of a prompt is "Generate Python code for an e-commerce site with product listing, cart functionality, and payment feature."

[1098] The generated source code is sent by the terminal to the server, which stores it in a database. Before saving, users are also provided with the ability to view, edit, and resave the source code. This function allows users to check the generated source code and make corrections as necessary.

[1099] Deliverables submission phase

[1100] Users upload the final source code using a web portal. The server receives the uploaded source code and stores it in a database. This process allows for centralized management of source code based on system requirements.

[1101] Review Phase

[1102] The stored source code is evaluated by a generative AI review model run by the server. The evaluation criteria consider the quality, functionality, and efficiency of the source code. The evaluation model assigns a score to each source code based on these criteria. The evaluation results are stored in a database and can later be displayed as a ranking.

[1103] Result announcement phase

[1104] The server will determine the winner based on the evaluation results. The winner will be offered a prize and the right to join a company. The server will notify the user of the results directly.

[1105] Specific examples

[1106] For example, a user may input the system requirement "e-commerce site," which includes "product listing," "cart functionality," and "payment functionality." The server sends the generative AI model a prompt: "Generate Python code for an e-commerce site with product listing, cart functionality, and payment feature." The server then receives the generated source code. The user then uploads the final source code to a web portal, and the server evaluates it. The user with the highest evaluation is selected as the winner and is offered a cash prize and employment opportunities.

[1107] This system allows for efficient system development in a short period of time, and allows for the selection of excellent engineers through fair evaluation. In this way, the present invention improves the speed and quality of system development while reducing development costs.

[1108] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1109] Step 1:

[1110] A user accesses a web portal and enters system requirements. They fill in the web portal form with details such as "e-commerce site," "product list display," "cart function," and "payment function." This becomes the input data. The entered system requirements are sent from the terminal to the server via an HTTP POST request. The server receives them and stores them in a database. A relational database management system such as MySQL is used for the database.

[1111] Input: System requirements entered by the user in a web form

[1112] Output: System requirements data sent to the server

[1113] Step 2:

[1114] The server retrieves the system requirements stored in the database and provides them to a generative AI model. The generative AI model (e.g., OpenAI's GPT-4 model) generates source code based on the system requirements, using the prompt "Generate Python code for an e-commerce site with product listing, cart functionality, and payment feature." The generated source code is sent to the terminal.

[1115] Input: System requirements stored in the database

[1116] Output: Source code generated by the generative AI model

[1117] Step 3:

[1118] The device sends the source code received from the generative AI model to the server, which receives the source code and stores it in a database. At this time, the source code is temporarily stored in the file system and its contents are stored in the database.

[1119] Input: Source code received from the generative AI model

[1120] Output: Source code stored in a database

[1121] Step 4:

[1122] Users have the ability to view, edit, and re-save source code through a web portal, and the edited source code is then sent back to the server, which then re-stores it in the database.

[1123] Input: User-edited source code

[1124] Output: Source code resaved to the database

[1125] Step 5:

[1126] Users upload the final source code to a web portal, and the server receives the uploaded source code and stores it in the database in its final form, thus keeping the final source code in the system.

[1127] Input: The final source code uploaded by the user

[1128] Output: Final source code stored in a database

[1129] Step 6:

[1130] The server then provides the final source code stored in the database to the generative AI review model for evaluation. The evaluation model evaluates the source code's quality, functionality, and efficiency, and assigns a score based on each criterion. The evaluation results are then stored in the database again.

[1131] Input: Final source code stored in the database

[1132] Output: Evaluation result score

[1133] Step 7:

[1134] The server will determine the winner based on the evaluation results. The evaluation results will be tallied and the user with the highest score will be selected as the winner. The winner will be notified directly by the server and will be offered a prize money and the right to join the company.

[1135] Input: Evaluation result score

[1136] Output: Winner determination and notification

[1137] This system improves the speed and quality of system development through a series of processing steps, and enables the selection of excellent engineers through fair evaluation.

[1138] (Application example 1)

[1139] 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."

[1140] In the past, it was difficult to quickly and efficiently develop factory automation systems and robot operation plans. In particular, there was a lack of means to design operation plans suited to individual factories and work processes and to properly evaluate their quality and efficiency. Furthermore, building such systems required a great deal of time and cost, which hindered the adoption of automation in small and medium-sized factories and sites with special needs.

[1141] 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.

[1142] In this invention, the server includes a means for saving input system requirements, a means for generating source code using a generative AI model based on the saved system requirements, and a means for saving the generated source code. This provides a means for inputting factory automation system requirements and automatically generating factory work processes and robot operation plans based on the requirements, and a means for evaluating the generated operation plans and source code and assigning scores that take efficiency and quality into consideration, enabling the rapid and high-quality construction of factory automation systems.

[1143] "System requirements" refer to the functions and characteristics that a user expects from a particular system or application.

[1144] A "generative AI model" refers to an artificial intelligence model that automatically generates source code or other output based on input data or requirements.

[1145] "Source code" refers to machine-readable program code for programming the operation of a system or application.

[1146] "Storage" refers to storing data or information in a way that allows it to be accessed at a later time.

[1147] "Evaluation" refers to judging the quality and efficiency of the generated source code and operation plan.

[1148] "Winner" refers to the user or team that receives the highest score based on the evaluation results.

[1149] "Factory automation system" refers to a system for automating manufacturing and other work processes in a factory.

[1150] An "operation plan" refers to the specific operating procedures for robots and automated equipment used in a factory.

[1151] "Score" refers to the score or rating assigned by a rating model.

[1152] This invention is a system for quickly and efficiently constructing factory automation systems and robot operation plans. Specifically, the system automatically generates systems based on user input system requirements using a generative AI model, evaluates them, and then selects the best system through a competition.

[1153] First, a user inputs system requirements, such as a factory automation system or a robot's operation plan, via a web portal. These requirements are sent to a server and stored in a database. The server then provides the stored system requirements to a generative AI model, which the user's device uses to generate optimal source code and an operation plan. The generated source code is then sent back to the server and stored in the database.

[1154] Next, the user uploads the generated source code and operation plan to a web portal. The server receives the uploaded source code and operation plan and evaluates its quality, functionality, efficiency, etc. using a generative AI evaluation model. The scores assigned by the evaluation model are stored in a database and later displayed as a ranking.

[1155] Based on the evaluation results, the server will determine the user with the highest evaluation as the winner and notify them. The winner will be offered a reward and the opportunity to join the company. This system makes it possible to efficiently build high-quality factory automation systems and robot operation plans in a short period of time.

[1156] The specific hardware and software used will include servers, smartphones, and tablets. The software will use Flask as a web application framework and JSON as the data storage format. Advanced generative AI models such as GPT-4 are expected to be used.

[1157] For example, if a factory engineer inputs a requirement such as "a motion plan for a package sorting robot," the generative AI model will generate an optimal motion plan and corresponding source code based on this requirement, which will then be implemented in the factory robot, resulting in a 30% improvement in the robot's operating efficiency.

[1158] Example prompt sentence:

[1159] The user has entered a requirement: "Action plan for a package sorting robot." Based on this requirement, generate and evaluate the optimal logic and source code. Also, provide a plan that takes into account efficiency and safety. The generated source code should look like this:

[1160] In this way, the present invention makes it possible to quickly and efficiently construct and evaluate operation plans for factory automation systems and robots.

[1161] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1162] Step 1:

[1163] The user enters system requirements through a web portal. Specifically, the user uses the user interface to enter detailed requirements for the factory automation system and robot operation plans. The input data is sent to the server in JSON format. Input: System requirements entered by the user. Output: System requirements sent to the server and saved.

[1164] Step 2:

[1165] The server receives the system requirements and stores them in a database. Specifically, it parses the received data and stores it in the database in the correct format. Input: Received system requirements in JSON format. Output: System requirements stored in the database.

[1166] Step 3:

[1167] The server retrieves system requirements from the database and provides them to the generative AI model. Specifically, it converts the data retrieved from the database into a format that the generative AI model can understand and inputs it into the model. Input: System requirements stored in the database. Output: System requirements input into the generative AI model.

[1168] Step 4:

[1169] A generative AI model generates source code based on system requirements. Specifically, a generative AI model (e.g., GPT-4) generates optimal source code based on the provided requirements. Input: System requirements. Output: Generated source code.

[1170] Step 5:

[1171] The generated source code is sent to the server and stored in the database. Specifically, the source code output from the generative AI model is sent to the server and stored in the database in an appropriate format. Input: Source code generated by the generative AI model. Output: Source code stored in the database.

[1172] Step 6:

[1173] The user uploads the generated source code and action plan to the web portal. Specifically, the user selects the generated source code from the user interface and clicks the upload button. Input: Generated source code. Output: Source code uploaded to the server.

[1174] Step 7:

[1175] The server receives the uploaded source code and action plan and evaluates it using a generative AI evaluation model. Specifically, the source code is input into the evaluation model, and a score is calculated based on the evaluation of quality, efficiency, functionality, etc. Input: Uploaded source code. Output: Score calculated by the evaluation model.

[1176] Step 8:

[1177] The evaluation results are stored in a database, and the server determines and notifies the winner based on the results. Specifically, it compares the scores of each source code, selects the user with the highest score as the winner, and notifies the result. Input: Evaluation result score. Output: Determination and notification of the winner.

[1178] Through the above processing steps, this system is able to quickly and efficiently generate and evaluate operation plans for factory automation systems and robots.

[1179] 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.

[1180] This invention combines an emotion engine that recognizes the user's emotions with a system that automatically generates, evaluates, and competes systems based on user input system requirements using a generative AI model. The specific processing flow for the program implementation of this system is described below.

[1181] System requirements input phase

[1182] A user enters system requirements using a web portal. The requirements are sent from the device to a server, which stores them in a database.

[1183] In this phase, the emotion engine analyzes the user's emotional state in real time. The emotion data entered by the user is sent to the server and stored in a database along with the system requirements.

[1184] System construction phase

[1185] The server provides the stored system requirements to the generative AI model. The device uses the generative AI model to automatically generate source code based on the system requirements. This source code is sent from the device to the server, which stores it in a database.

[1186] The emotion engine also monitors the user's emotions during this phase, for example, recording the stress or satisfaction the user feels during the code generation process and sending this data to the server.

[1187] Deliverables submission phase

[1188] Users upload the generated source code to a web portal, and the server receives the uploaded source code and stores it in a database.

[1189] Review Phase

[1190] The stored source code is evaluated by a generative AI review model running on a server. The evaluation model assigns a score based on criteria such as the quality, functionality, and efficiency of the source code. This score is stored in a database and later displayed as a ranking.

[1191] Emotion data obtained from the emotion engine is also reflected in the evaluation process. For example, high-quality source code under low stress conditions can earn additional evaluation points.

[1192] Result announcement phase

[1193] The server will determine the winner based on the evaluation results. The winner will be offered a prize and the right to join the company. The server will then notify the user of the results.

[1194] Specific examples

[1195] For example, suppose a user inputs the system requirements for an "e-commerce website." These requirements include displaying a product list, a cart function, and a payment function. The terminal uses a generative AI model to generate source code containing these functions and sends the source code to the server. During this process, an emotion engine monitors the user's emotions. For example, if the user expresses high satisfaction during this process, the emotion data is also saved. The user then uploads the source code to a web portal, where the server evaluates it. The emotion data is reflected in the evaluation results, and the user with the highest evaluation is selected as the winner and offered a cash prize and employment opportunities.

[1196] This system enables efficient system development in a short period of time and selects excellent engineers through fair evaluation. Furthermore, by incorporating user emotional data into the evaluation process, a more human-centered evaluation becomes possible, leading to improved user satisfaction and experience.

[1197] The processing flow will be explained below.

[1198] Step 1:

[1199] A user enters their system requirements using a web portal. The user enters the required features and specifications into the input boxes and clicks the submit button.

[1200] Step 2:

[1201] The device sends the system requirements entered by the user to the server. The system requirements are transferred in a data format such as JSON.

[1202] Step 3:

[1203] The server stores the received system requirements in a database, where the user ID and the requirements information are stored as associated records.

[1204] Step 4:

[1205] The device's built-in emotion engine analyzes the user's emotions in real time while they are entering system requirements, detecting stress, excitement, and satisfaction from the user's facial expressions, voice, and input speed.

[1206] Step 5:

[1207] The device transmits the analyzed emotion data along with the system requirements to the server, where the emotion data is stored together with the requirements data.

[1208] Step 6:

[1209] The server provides the stored system requirements to the generative AI model, which then passes the requirements to the generative AI model through an appropriate API or interface.

[1210] Step 7:

[1211] The device automatically generates source code based on the system requirements using a generative AI model, which analyzes the stored requirements and generates program code accordingly.

[1212] Step 8:

[1213] The terminal sends the generated source code to the server, which transfers the source code in text format or in an archive file format.

[1214] Step 9:

[1215] The server stores the received source code in a database. The generated source code is stored in association with the user ID.

[1216] Step 10:

[1217] The user uploads the generated source code using a web portal. The user attaches the generated source code file to an upload form and submits it to the server.

[1218] Step 11:

[1219] The server receives the uploaded source code and stores it in a database along with the user ID.

[1220] Step 12:

[1221] The server provides the stored source code to the generated AI review model, which then passes the source code to the review model and issues instructions for evaluation.

[1222] Step 13:

[1223] A generative AI review model evaluates and scores source code quality and functionality, based on criteria such as code efficiency, maintainability, and functional completeness.

[1224] Step 14:

[1225] The server saves the evaluation results in a database and creates a ranking. The evaluation results are saved in the form of user ID and score, and are displayed as a ranking.

[1226] Step 15:

[1227] Emotion data obtained from the emotion engine is also reflected in the evaluation process. For example, high-quality source code under low stress conditions can earn additional evaluation points.

[1228] Step 16:

[1229] The server will determine the winner based on the evaluation results. The user with the highest score will be selected as the winner.

[1230] Step 17:

[1231] The server will notify the winners of their prize money and employment opportunities via email and the web portal's messaging system.

[1232] Example 2

[1233] 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."

[1234] In recent years, there has been a demand for more efficient system development, but conventional methods often involve manual processes, from inputting system requirements to generating source code and evaluating it. This tends to depend on the skills and experience of the developer, making fair and efficient evaluation difficult. Furthermore, there is no established evaluation method that takes into account the emotional state of the developer during the development process, making it difficult to fully improve user satisfaction and experience. Therefore, a system that automates system development and performs evaluations that take into account the developer's emotional data is needed.

[1235] 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.

[1236] In this invention, the server includes means for saving input system requirements, means for generating source code using a generative AI model based on the saved system requirements, means for saving the generated source code, means for analyzing users' emotional states in real time and saving emotional data, means for reflecting the emotional data in the evaluation process, and means for determining and notifying a winner based on the evaluation results. This makes it possible to efficiently and automatically develop systems and to perform fair evaluations that take users' emotional states into account.

[1237] "System requirements" indicate the specific functions, performance, constraints, etc. required for the system to be developed.

[1238] A "generative AI model" is an algorithm or program that uses artificial intelligence technology to automatically generate source code.

[1239] "Source code" means a set of program instructions written in a programming language that can be executed by a computer.

[1240] A "server" is a computer system that stores, processes, and manages data, and provides necessary services in response to requests from clients.

[1241] A "terminal" is a device operated by a user to communicate with a server, such as a PC or smartphone.

[1242] An "emotion engine" is software or hardware that analyzes a user's emotional state and outputs the analysis results as data.

[1243] "Evaluation" is the act of analyzing the quality, functionality, efficiency, etc. of the generated source code and assigning it a score or ranking.

[1244] The "Winner" is the participant who receives the highest score based on the evaluation results.

[1245] "Notification" is the act of transmitting results or information from the server to the user, usually via email or a messaging system.

[1246] "Emotion data" refers to data that indicates the user's emotional state analyzed by the emotion engine, and includes stress level, satisfaction level, and the like.

[1247] The "evaluation process" refers to a series of steps to conduct a fair and objective evaluation based on the generated source code and emotional data.

[1248] The present invention combines an emotion engine that recognizes the user's emotions with a system in which a user inputs system requirements and a generative AI model is used to automatically generate and evaluate a system based on those requirements.

[1249] System requirements input phase

[1250] Users use a web portal to enter system requirements, which are then sent from their devices to a server, which stores them in a database. The web portal runs in a standard web browser and uses HTML and JavaScript to create the user interface.

[1251] Using data from the webcam, keyboard input speed, etc., the emotion engine analyzes the user's emotional state in real time. This emotion data, along with the system requirements, is also sent to the server and stored in a database.

[1252] System construction phase

[1253] The server retrieves the stored system requirements and provides them to a generative AI model, which is built using the latest AI technologies, including natural language processing techniques and machine learning algorithms.

[1254] The device uses a generative AI model to automatically generate source code based on system requirements. The generated source code is written in a common programming language (e.g., Python or JavaScript). The generated source code is sent from the device to a server, which stores it in a database.

[1255] During this phase, the emotion engine also monitors the user's emotions and sends the data to the server for storage, including the level of stress and satisfaction the user feels during code generation.

[1256] Deliverables submission phase

[1257] Users upload the generated source code through a web portal, which is then received by the server and stored in a database.

[1258] Review Phase

[1259] The server provides the stored source code to a generative AI review model, which evaluates and scores the source code based on its quality, functionality, efficiency, etc. The evaluation results are stored in a database and later displayed as a ranking.

[1260] Emotional data is also taken into account in this evaluation process: for example, users who generate high-quality source code under low stress conditions are awarded additional evaluation points.

[1261] Result announcement phase

[1262] The server will determine the winner based on the evaluation results. The winner will be given rewards, employment opportunities, etc. The server will then send a notification of the results to the user.

[1263] Specific examples

[1264] For example, if a user inputs the system requirement "e-commerce site," this requirement includes "displaying a product list," "cart function," and "payment function." The terminal uses a generative AI model to generate source code including these functions and sends the source code to the server. During this process, an emotion engine monitors the user's emotions, and if the user expresses high satisfaction with the process, the emotion data is also saved. The user then uploads the source code to a web portal, and the server evaluates it. The emotion data is reflected in the evaluation results, and the user with the highest evaluation is selected as the winner and offered rewards and employment opportunities.

[1265] Prompt Sentence Examples

[1266] "The system requirements for an e-commerce site include product listing, shopping cart functionality, and payment functionality. Please generate source code using a generative AI model based on these requirements."

[1267] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1268] System processing flow

[1269] Step 1:

[1270] A user opens a web portal and inputs system requirements. The user inputs "Build an e-commerce site," and the requirements include "Display a product list," "Cart function," and "Payment function." The input system requirements are sent to the server by the terminal. At this point, the input data are the system requirements, and the output data are the system requirements sent to the server.

[1271] Operation details:

[1272] Using a web browser, the user enters the system requirements into a form on the web portal and clicks the "Submit" button.

[1273] Step 2:

[1274] The server stores the received system requirements in a database. The server checks the integrity of the entered data and ensures that all required fields are present. At this point, the input data are the system requirements sent from the terminal, and the output data are the system requirements stored in the database.

[1275] Operation details:

[1276] The server receives the HTTP request and stores it in a database.

[1277] Step 3:

[1278] The emotion engine analyzes the user's emotional state in real time. Data such as webcam and keyboard input speed are used for the analysis. This emotion data, along with system requirements, is sent to the server and stored in a database. The input data is raw emotion data, and the output data is analyzed emotion data.

[1279] Operation details:

[1280] The emotion engine analyzes webcam footage and infers emotions from the user's facial expressions and eye movements.

[1281] Step 4:

[1282] The server provides the saved system requirements to the generative AI model, which receives the prompt and generates source code based on it. The input data are the system requirements and the prompt, and the output data is the generated source code.

[1283] Operation details:

[1284] The server sends a prompt to the generative AI model, such as "Please generate source code based on the following system requirements: product list display, cart function, and payment function."

[1285] Step 5:

[1286] The terminal uses the generative AI model to automatically generate source code based on the system requirements. The generated source code is sent from the terminal to the server and stored in a database. The input data is the prompt provided to the generative AI model, and the output data is the generated source code.

[1287] Operation details:

[1288] The device inputs a prompt into the generative AI model, receives the generated source code, and uploads it to the server.

[1289] Step 6:

[1290] The server saves the generated source code in a database. When saving, it checks the data consistency and confirms the format of the required files. The input data is the source code sent from the terminal, and the output data is the source code saved in the database.

[1291] Operation details:

[1292] The server receives the source code uploaded via HTTP request and stores it in a database.

[1293] Step 7:

[1294] The emotion engine monitors the user's emotions even while generating source code. Emotion data is periodically sent to the server and stored in a database in association with system requirements. The input data is raw data of the user's emotions, and the output data is analyzed emotion data.

[1295] Operation details:

[1296] The emotion engine sequentially analyzes the user's facial expressions and behavior during the generation process and transmits the emotional state to the server in real time.

[1297] Step 8:

[1298] The user uploads the generated source code to the server through a web portal. At this point, the input data is the generated source code, and the output data is the source code sent to the server.

[1299] Operation details:

[1300] The user accesses the web portal and uploads the generated source code file by selecting the file using the file specification button and clicking the "Upload" button.

[1301] Step 9:

[1302] The server provides the stored source code to the generative AI review model for evaluation. The evaluation results also reflect emotional data. The input data are the source code and emotional data, and the output data is the evaluation score.

[1303] Operation details:

[1304] The server sends the source code file to the generative AI review model along with a prompt saying, "Please rate this source code for quality, functionality, and efficiency."

[1305] Step 10:

[1306] The server determines the winner based on the evaluation results and notifies the user of the result. The winner will be offered rewards and employment opportunities. The input data is the evaluation score, and the output data is the winner notification and reward information.

[1307] Operation details:

[1308] The server tally the evaluation scores, determine the user with the highest score, and notify the user of the result via email or internal message.

[1309] (Application example 2)

[1310] 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."

[1311] In conventional systems, after users input system requirements, the system is automatically generated and evaluated, but the user's emotional data is not reflected in the process, making it difficult to conduct efficient, human-centered evaluations. Furthermore, there was a lack of efficient means for generating high-quality source code for factory robot control systems. This resulted in poor user satisfaction and experience, making appropriate evaluations difficult.

[1312] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1313] In this invention, the server includes means for saving input system requirements and emotion data, means for generating source code using a generative AI model based on the saved system requirements, and means for saving the generated source code, thereby enabling automatic generation and evaluation of high-quality source code based on the system requirements while reflecting the user's emotion data.

[1314] "System requirements" refers to specific requirements or conditions regarding the operation or functionality of a system.

[1315] "Emotion data" is data that reflects the user's mental state, and includes information such as stress level and satisfaction level.

[1316] "Storage means" refers to a function for temporarily or permanently storing input data and generated source code.

[1317] A "generative AI model" refers to an artificial intelligence algorithm that automatically generates source code or other output based on given requirements or conditions.

[1318] "Evaluation means" refers to functions for evaluating the quality, functionality, efficiency, etc. of the generated source code and system.

[1319] "User interface" refers to the interactive screens and components that allow a user to interact with a system and input data.

[1320] "Notification means" refers to a function for conveying information such as evaluation results and winner selection to users.

[1321] "Benefits" refers to any rewards or rights provided as a result of an evaluation.

[1322] The hardware required to realize this application example includes a server, a user device, and sensors (camera, microphone, etc.) for acquiring emotion data. The software includes the Python programming language, a generative AI model library (AIModel), an emotion recognition library (EmotionEngine), and a database operation library (Database).

[1323] Overall system flow

[1324] The server first receives the system requirements and emotion data entered by the user through the terminal and stores them in a database. Next, it generates source code using a generative AI model based on the stored system requirements. The generated source code is then stored in the database by the server.

[1325] The server then evaluates the stored source code. This evaluation takes into account the generative AI model as well as the user's emotional data. For example, if the user's stress level while entering the system requirements is low, the evaluation score will increase. The server then determines and notifies the winner based on the evaluation results.

[1326] Step-by-step details

[1327] 1. System requirements input:

[1328] When a user inputs system requirements using the terminal's user interface, the emotion engine analyzes emotions in real time, and these data are sent to the server and stored in a database.

[1329] 2. System construction:

[1330] The server retrieves the saved system requirements and uses the generative AI model to generate source code based on the requirements. During this generation process, the emotion engine continues to analyze the user's emotions, which are also stored in the database.

[1331] 3. Evaluation:

[1332] The server evaluates the generated source code, using the generative AI model and user emotion data to calculate an overall score.

[1333] 4. Result notification:

[1334] The server will determine and notify the winner based on the evaluation results, and the winner will receive a prize.

[1335] Specific examples

[1336] For example, consider the case where a user inputs a system requirement such as "a robot control system that can assemble parts at high speed." As the user inputs the requirement, the emotion engine analyzes the user's emotion data, and the server stores this data in a database. Next, a generative AI model generates source code for controlling the robot based on the requirement. The generated source code and emotion data are again stored in the database. The server then uses the generative AI model to evaluate the source code, and determines and notifies the winner based on the evaluation results and emotion data.

[1337] Example prompts to input to the generative AI model

[1338] "Generate source code for a robotic control system that assembles parts at high speed. Requirements are: high speed, high accuracy."

[1339] By inputting this prompt into the AI ​​model, the appropriate source code is generated.

[1340] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1341] Step 1:

[1342] The user inputs system requirements using the user interface of the device. The input system requirements are sent from the device to the server. At that time, the emotion engine analyzes the user's emotion data in real time, and this emotion data is also sent to the server. The server stores the system requirements and emotion data in a database.

[1343] Step 2:

[1344] The server retrieves the system requirements stored in the database. It provides the retrieved system requirements to the generation AI model, which then generates source code based on the system requirements. During this generation process, the emotion engine continues to analyze the user's emotions, which are also sent to the server and stored in the database. The server then stores the generated source code in the database.

[1345] Step 3:

[1346] The server retrieves the generated source code from the database and uses a generative AI model to evaluate the quality, functionality, efficiency, etc. of the source code. The evaluation uses information about the source code itself and stored emotional data. For example, if the user's stress level is low based on the emotional data, the server increases the evaluation score. The evaluation results are stored in the database by the server.

[1347] Step 4:

[1348] The server determines the winner based on the evaluation results stored in the database. When determining the winner, the evaluation results and emotional data are taken into consideration comprehensively. For example, the winner will be the user who generates high-quality source code while working with low stress. After the winner is determined, the server will notify the user.

[1349] Step 5:

[1350] The server processes the delivery of prizes and rewards to winners, including using a management system to arrange and deliver physical and digital rewards, and winners receive notifications and details via email and a user interface.

[1351] Through these steps, the system operates smoothly and enables efficient and human-centered evaluation.

[1352] 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.

[1353] 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.

[1354] 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.

[1355] 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.

[1356] 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.

[1357] 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.

[1358] 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).

[1359] 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.

[1360] 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."

[1361] 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.

[1362] 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).

[1363] 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.

[1364] 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.

[1365] 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.

[1366] 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.

[1367] The hardware resource for executing a specific process can be any of the following processors: A CPU is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A dedicated electrical circuit, such as a field-programmable gate array (FPGA), a programmable logic device (PLD), or an application-specific integrated circuit (ASIC), is a processor with a circuit configuration specifically designed to execute a specific process. Each processor has built-in or connected memory, and uses the memory to execute the specific process.

[1368] 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.

[1369] 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.

[1370] 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.

[1371] 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.

[1372] 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.

[1373] The following is further disclosed regarding the above embodiment.

[1374] (Claim 1)

[1375] means for saving the entered system requirements;

[1376] means for generating source code using the generative AI model based on the stored system requirements;

[1377] a means for storing the generated source code;

[1378] means for evaluating the stored source code using a generative AI model;

[1379] The system includes a means for determining and notifying a winner based on the evaluation results.

[1380] (Claim 2)

[1381] 10. The system of claim 1, further comprising means for providing a user interface for inputting system requirements.

[1382] (Claim 3)

[1383] 10. The system of claim 1, further comprising means for providing a winner with a prize and the right to join a company.

[1384] "Example 1"

[1385] (Claim 1)

[1386] means for saving the entered system requirements;

[1387] means for generating source code using the generative AI model based on the stored system requirements;

[1388] a means for storing the generated source code;

[1389] a means to view, edit, and resave the generated source code;

[1390] means for evaluating the stored source code using a generative AI model;

[1391] The system includes a means for determining and notifying a winner based on the evaluation results.

[1392] (Claim 2)

[1393] 10. The system of claim 1, further comprising means for providing a user interface for inputting system requirements.

[1394] (Claim 3)

[1395] 10. The system of claim 1, further comprising means for providing a winner with a prize and the right to join a company.

[1396] "Application Example 1"

[1397] (Claim 1)

[1398] means for saving the entered system requirements;

[1399] means for generating source code using the generative AI model based on the stored system requirements;

[1400] a means for storing the generated source code;

[1401] means for evaluating the stored source code using a generative AI model;

[1402] a means for determining and notifying a winner based on the evaluation results;

[1403] A means for inputting requirements for a factory automation system and automatically generating factory work processes and robot operation plans based on the requirements;

[1404] The system includes a means for evaluating the generated action plan and source code and assigning a score that takes into account efficiency and quality.

[1405] (Claim 2)

[1406] 10. The system of claim 1, further comprising means for providing a user interface for inputting system requirements.

[1407] (Claim 3)

[1408] 10. The system of claim 1, further comprising means for providing rewards and employment opportunities to winners.

[1409] "Example 2: Combining Emotion Engines"

[1410] (Claim 1)

[1411] means for saving the entered system requirements;

[1412] means for generating source code using the generative AI model based on the stored system requirements;

[1413] a means for storing the generated source code;

[1414] means for evaluating the stored source code using a generative AI model;

[1415] a means for determining and notifying a winner based on the evaluation results;

[1416] a means for analyzing the user's emotional state in real time and storing the emotional data;

[1417] A system including a means for incorporating emotional data into the evaluation process.

[1418] (Claim 2)

[1419] 2. The system according to claim 1, further comprising: means for providing a user interface for inputting system requirements; and means for transmitting the input system requirements and the user's emotion data to the server.

[1420] (Claim 3)

[1421] 10. The system of claim 1, further comprising means for providing rewards and employment opportunities to winners.

[1422] "Application example 2 when combining emotion engines"

[1423] (Claim 1)

[1424] a means for storing the input system requirements and emotion data;

[1425] means for generating source code using the generative AI model based on the stored system requirements;

[1426] a means for storing the generated source code;

[1427] means for evaluating the stored source code using a generative AI model;

[1428] The system includes a means for determining and notifying a winner based on the evaluation results and sentiment data.

[1429] (Claim 2)

[1430] 10. The system of claim 1, further comprising means for providing a user interface for inputting system requirements and emotion data.

[1431] (Claim 3)

[1432] 10. The system of claim 1, further comprising means for providing prizes and benefits to winners. [Explanation of symbols]

[1433] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for saving the entered system requirements; means for generating source code using the generative AI model based on the stored system requirements; a means for storing the generated source code; means for evaluating the stored source code using a generative AI model; The system includes a means for determining and notifying a winner based on the evaluation results.

2. The system of claim 1 further comprising means for providing a user interface for inputting system requirements.

3. 10. The system of claim 1, further comprising means for providing a winner with a prize and the right to join a company.

Images