System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving user input requirements; artificial intelligence model means for analyzing the received user input requirements and generating an appropriate technology configuration or system architecture; and means for presenting the generated technology configuration or system architecture to a user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In recent years, IT engineers have limited opportunities to comprehensively understand diverse technology stacks and system architectures because their technical knowledge is specialized in their fields and industries. Furthermore, with the evolution of cloud services and artificial intelligence, engineers are required to quickly understand and adapt to new technology patterns and design concepts. However, there is a lack of specific and useful platforms for effective learning. This situation makes it difficult for engineers to select and design the optimal technology configuration for their company's services, which can result in inefficient system designs. Therefore, there is a need for a platform that can present the optimal technology stack and system architecture in response to diverse user input requirements and expand engineers' knowledge. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for accepting user-input requirements, an artificial intelligence model means for analyzing the accepted user-input requirements and generating an appropriate technical configuration and system architecture, and a means for presenting the generated technical configuration and system architecture to the user. Specifically, when a user inputs specific requirements, the system analyzes the requirements and generates an optimal technical stack and system architecture using an artificial intelligence model trained based on past data sets. The generated technical stack and system architecture are presented to the user through a user interface. This allows engineers to learn new technical patterns and design concepts and explore optimal designs for their company's services. In the future, the system is also planned to incorporate user-generated content and expert advice, further enhancing its value as a knowledge-sharing forum.

[0006] "User-entered requirements" are data that clearly describe a particular purpose or requirement by a user.

[0007] "Means" are functional elements or processes for achieving a specific function or purpose.

[0008] "Technical configuration" refers to the combination of technical elements such as software, hardware, and networks required to realize a system or application.

[0009] "System architecture" refers to the basic structures and their interrelationships that determine the design and configuration of the entire system.

[0010] An "artificial intelligence model" is an algorithm or computational model that learns from large amounts of data and makes predictions and classifications based on the input data.

[0011] "User presentation means" refers to a device or software function that visually or otherwise notifies a user of information or results generated by the system.

[0012] "Analysis" is the process of analyzing input data or information and understanding its meaning and structure.

[0013] A "technology stack" is a set of software and technologies selected to build and operate an application or system.

[0014] A "dataset" is a collection of related data used to train a machine learning model.

[0015] "Knowledge sharing" is the act of exchanging information about a particular field or skill with others to promote learning and understanding.

[0016] A "user interface" is the set of screens and methods of operation that a user uses to interact with a system. [Brief explanation of the drawings]

[0017] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7]FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram illustrating a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0018] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0020] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0021] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0022] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0023] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0025] [First embodiment]

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

[0027] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0028] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0030] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0034] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0035] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0036] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0037] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0038] The present invention relates to a system for suggesting an appropriate technology stack or system architecture based on specific requirements input by a user, the system including means for accepting user-input requirements, artificial intelligence model means for analyzing the accepted requirements, and means for presenting the generated technology stack or system architecture to the user.

[0039] 1. System Configuration

[0040] The system includes the following major components:

[0041] 1. Front end (terminal)

[0042] It provides a web interface for users to enter requirements and view results, and is built using modern JavaScript frameworks such as React.js and Vue.js.

[0043] 2. Backend (server)

[0044] It receives user requirements and uses artificial intelligence models to generate the optimal technology stack and system architecture for those requirements, built using frameworks such as Node.js and Django.

[0045] 3. Database

[0046] It is used to store information about technology stacks and system architectures. It uses a relational database such as PostgreSQL.

[0047] 4. Artificial Intelligence Models

[0048] It includes machine learning models to analyze user requirements and generate the appropriate technology stack and system architecture, and is built using TensorFlow and PyTorch.

[0049] 2. Program Processing Overview

[0050] The system allows users to input specific requirements through a web interface, analyzes those requirements, and suggests appropriate technology stacks and system architectures.

[0051] User enters requirements:

[0052] A user accesses the system through a web browser and enters a specific requirement (e.g., "E-commerce site for startups"), and once the user has completed the entry, they click the "Submit" button to send the requirement to the system.

[0053] The device sends its requirements to the server:

[0054] When the user clicks the submit button, the terminal converts the entered requirements into JSON format and sends it to the backend server as an HTTP POST request.

[0055] The server parses the requirements:

[0056] The server analyzes the received request and extracts the requirements data, which is then passed to the artificial intelligence model.

[0057] Artificial intelligence model generates optimal tech stack:

[0058] Artificial intelligence models are trained based on historical datasets to generate the technology stack and system architecture that best suits the user's requirements.

[0059] The server returns the generated result:

[0060] The server converts the technology stack and system architecture information generated by the artificial intelligence model into JSON format and returns it to the terminal as an HTTP response.

[0061] The terminal will display the result:

[0062] The device analyzes the received data and displays the results on the user interface, allowing users to review the presented technology stack and system architecture and use it to help design their own systems.

[0063] Specific examples

[0064] For example, if a user inputs the requirement "E-commerce site for startups," the system will receive this requirement and use an artificial intelligence model to generate the optimal technology stack (e.g., React.js, Node.js, MongoDB, AWS) and system architecture (e.g., microservices architecture), providing users with reference information for specific technology selection and system construction.

[0065] As described above, the system of the present invention quickly presents appropriate technical configurations and system architectures for a variety of user requirements, greatly contributing to users' technology selection and design.

[0066] The processing flow will be explained below.

[0067] Step 1:

[0068] A user opens a web browser and accesses a web application on the system.

[0069] Step 2:

[0070] The user fills in a given form with their specific requirements (e.g., "e-commerce site for startups").

[0071] Step 3:

[0072] The user clicks the submit button on the form, which triggers the processing of the entered requirements.

[0073] Step 4:

[0074] The terminal converts the user input requirements into JSON format, which is then constructed as the body of the HTTP POST request.

[0075] Step 5:

[0076] The terminal sends an HTTP POST request to the backend server, which includes the user's input requirements.

[0077] Step 6:

[0078] The server receives an HTTP POST request from the terminal and extracts the user input requirement data from the request body.

[0079] Step 7:

[0080] The server passes the extracted requirements data to an artificial intelligence model, which takes the requirements data as input and generates the optimal technology stack and system architecture.

[0081] Step 8:

[0082] The artificial intelligence model generates technology stack and system architecture information that is sent back to the server.

[0083] Step 9:

[0084] The server converts the output of the AI ​​model into JSON format, which is then used to construct an HTTP response.

[0085] Step 10:

[0086] The server sends an HTTP response back to the device, which contains information about the generated technology stack and system architecture.

[0087] Step 11:

[0088] The device analyzes the HTTP response received from the server and extracts the generated technology stack and system architecture information from the response body.

[0089] Step 12:

[0090] The terminal displays the extracted data in a user interface, where the user can review the presented technology stack and system architecture.

[0091] Step 13:

[0092] Users can obtain reference information for their own system design based on the displayed technology stack and system architecture.

[0093] Example 1

[0094] 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."

[0095] In modern system development, selecting a technology stack and system architecture is a critical and complex process. Developers, from beginners to professionals, spend a lot of time and effort selecting the optimal technology configuration. However, making the optimal selection requires specialized knowledge, and a lack of it can reduce the project's success rate. Furthermore, incorrect technology selection can significantly increase development costs and time. Therefore, there is a need for a system that allows users to easily and quickly select the optimal technology configuration and system architecture.

[0096] 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.

[0097] In this invention, the server includes: means for accepting user-input requirements; an artificial intelligence model for analyzing the accepted user-input requirements and generating an optimal technical configuration and system architecture; means for converting the user-input requirements into JSON format and sending it to the server as an HTTP POST request; means for the server to analyze the requirements, extract requirement data, and pass it to the artificial intelligence model; means for the artificial intelligence model to generate an optimal technical configuration and system architecture based on a past dataset; means for converting the generated information on the technical configuration and system architecture into JSON format and returning it from the server to the terminal; and means for the terminal to analyze the received data and display the results on a user interface. This enables a user to quickly and easily receive an optimal technical configuration and system architecture based on specific requirements.

[0098] "User-input requirements" are functions and conditions that a user specifically desires for the system, entered in text format.

[0099] "JSON format" is an abbreviation for JavaScript Object Notation, and is a lightweight data exchange format that represents data as attribute-value pairs.

[0100] An "HTTP POST request" is a type of HTTP protocol used to send data from a web browser or client to a server.

[0101] A "server" is a computer system that provides services over a network, and in the present invention, plays a central role in receiving and analyzing requirements, and transmitting and receiving data.

[0102] An "artificial intelligence model" is a model trained by machine learning algorithms that has the ability to analyze user requirements and generate optimal technology stacks and system architectures.

[0103] A "technical configuration" is a combination of technical elements required to build a system, including frameworks, libraries, databases, etc.

[0104] "System architecture" defines the overall configuration of a system and is a concept that clarifies the interactions between components and design policies.

[0105] The "user interface" refers to a screen or operating means that is directly used by the user, and in this invention, it is a means for displaying the analysis results and allowing the user to confirm the results.

[0106] The present invention is a system that automatically generates and presents optimal technology stacks and system architectures based on specific requirements entered by a user. The system consists of major components such as terminals, servers, artificial intelligence models, and databases.

[0107] The terminal provides a user interface for users to input requirements and display the results. Specifically, it is built using modern JavaScript frameworks such as React.js or Vue.js. Users access the system through a web browser and input specific requirements (e.g., "E-commerce site for startups"). Once input is complete, users click the "Submit" button to send the requirements to the system.

[0108] The terminal converts the input requirements into JSON format and sends it as an HTTP POST request to the backend server. The server receives this HTTP POST request. The server is built using frameworks such as Node.js or Django, analyzes the request, extracts the requirements data, and passes it to the artificial intelligence model.

[0109] The artificial intelligence model is trained based on historical datasets and generates the technology stack and system architecture that best suits the user's requirements. The model is built using TensorFlow and PyTorch. For example, if a user enters the requirement "e-commerce site for startups," the model will recommend React.js, Node.js, MongoDB, and AWS.

[0110] The generated technology stack and system architecture information is converted back to JSON format and sent back to the terminal as an HTTP response from the server. The terminal analyzes this data and displays the results in the user interface. The user can then review the presented technology stack and system architecture and use it in their own system design.

[0111] For example, if the user enters the prompt text:

[0112] Example prompt sentence:

[0113] "E-commerce site for startups"

[0114] In response, the AI ​​model suggests the following optimal technology stack and system architecture:

[0115] Tech stack: React.js, Node.js, MongoDB, cloud services

[0116] System Architecture: Microservices Architecture

[0117] This allows users to quickly obtain reference information for specific technology selection and system construction. This system significantly streamlines users' technology selection and design processes, contributing to saving time and resources.

[0118] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0119] Step 1:

[0120] User enters requirements

[0121] Specific behavior:

[0122] Users access the system's front end using a web browser and fill out a requirements form to enter specific project requirements, such as "e-commerce site for startups."

[0123] input:

[0124] User requirements such as "E-commerce site for startups"

[0125] output:

[0126] Requirement data entry completed

[0127] Step 2:

[0128] The device sends its requirements to the server

[0129] Specific behavior:

[0130] When the user clicks the "Submit" button, the terminal (front end) converts the entered requirements into JSON format and sends it to the back end server as an HTTP POST request.

[0131] input:

[0132] Requirement Data

[0133] output:

[0134] An HTTP POST request containing the requirements data in JSON format

[0135] Step 3:

[0136] The server analyzes the requirements

[0137] Specific behavior:

[0138] The server analyzes the received HTTP POST request and extracts the requirements data (e.g., "E-commerce site for startups") from it.

[0139] input:

[0140] Requirements data in JSON format in an HTTP POST request

[0141] output:

[0142] Analyzed requirements data

[0143] Step 4:

[0144] The server passes the requirements data to the artificial intelligence model

[0145] Specific behavior:

[0146] In order to pass the analyzed requirements data to the artificial intelligence model, the server converts the format of the data as necessary and inputs it to the artificial intelligence model.

[0147] input:

[0148] Analyzed requirements data

[0149] output:

[0150] Requirements data in a format that can be read by artificial intelligence models

[0151] Step 5:

[0152] Artificial intelligence models generate optimal technology stacks and system architectures

[0153] Specific behavior:

[0154] Artificial intelligence models (using TensorFlow and PyTorch) utilize algorithms that learn from historical datasets to generate a technology stack and system architecture that best suits the user's requirements.

[0155] input:

[0156] Requirements data fed into an artificial intelligence model

[0157] output:

[0158] Generated technology stack and system architecture information

[0159] Step 6:

[0160] The server returns the generated results to the device.

[0161] Specific behavior:

[0162] The server converts the technology stack and system architecture information generated by the artificial intelligence model into JSON format and returns it to the terminal as an HTTP response.

[0163] input:

[0164] Generated technology stack and system architecture information

[0165] output:

[0166] HTTP response containing technology stack and system architecture information in JSON format

[0167] Step 7:

[0168] The terminal displays the results

[0169] Specific behavior:

[0170] The terminal parses the received JSON data and displays it in the user interface in an appropriate format, for example, "The recommended technology stack is React.js, Node.js, MongoDB, and AWS."

[0171] input:

[0172] Technical stack and system architecture information received as an HTTP response in JSON format

[0173] output:

[0174] Technology stack and system architecture information displayed in the user interface

[0175] This allows users to quickly obtain reference information for specific technology selection and system construction.

[0176] (Application example 1)

[0177] 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."

[0178] In recent years, demand for content distribution services has been increasing, and audio and video distribution using smart devices in particular has been rapidly expanding. However, launching these services requires selecting the optimal technology stack and system architecture, which can be difficult for users lacking technical knowledge. For this reason, there is a need for a system that allows users to easily select the optimal technology configuration and system architecture.

[0179] 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.

[0180] In this invention, the server includes means for accepting user-input requirements, artificial intelligence model means for analyzing the accepted user-input requirements and generating an appropriate technical configuration and system architecture, means for presenting the generated technical configuration and system architecture to the user, means for analyzing the user-input requirements related to content distribution and presenting an optimal technical stack and system architecture, and means for displaying the generated technical configuration and system architecture using a smart device, thereby enabling the user to easily select and use the optimal technology stack and system architecture.

[0181] - "User-input requirements" are specific requirements that users of the system input as settings or desired conditions.

[0182] An "artificial intelligence model" is an algorithm that uses technologies such as machine learning and deep learning to analyze data and make predictions and classifications.

[0183] "Technical configuration" refers to the combination of software and hardware required to realize a system.

[0184] "System architecture" is the design of the overall structure of a system and the interactions between each component.

[0185] "Analysis means" is a means for generating an appropriate technical configuration or system architecture based on user-input requirements.

[0186] A "technology stack" is a collection of technologies used to build a system or application.

[0187] A "smart device" is an electronic device that can connect to the Internet and has advanced functions.

[0188] "Content distribution" refers to the provision of digital content such as audio, video, and text to users via the Internet.

[0189] The "means for presenting to the user" refers to a means for providing the generated technical configuration and system architecture to the user.

[0190] This invention is a system that suggests appropriate technology stacks and system architectures based on specific requirements input by the user. The system mainly consists of the following elements:

[0191] 1. Frontend (terminal):

[0192] The terminal provides an interface for users to input requirements and check the results. This interface runs on smart devices such as smartphones and is built using frameworks such as React Native.

[0193] 2. Backend (server):

[0194] The server receives user requirements and uses artificial intelligence models to generate the optimal technology stack and system architecture for those requirements. This backend is built using frameworks such as Flask (Python).

[0195] 3. Database:

[0196] The database stores information about the technology stack and system architecture, and uses databases such as Firebase and DynamoDB.

[0197] 4. Artificial Intelligence Model:

[0198] The artificial intelligence model is built using machine learning techniques such as TensorFlow and trained based on historical datasets. The model analyzes user requirements and generates the optimal technology stack and system architecture.

[0199] Specific examples:

[0200] A user launches the smartphone app and inputs requirements, such as "Build a new video distribution platform." When the user clicks the "Submit" button, the device converts the input requirements into JSON format and sends it as an HTTP POST request to the backend server.

[0201] The server receives the requirements and begins analysis. The received requirements are passed to an artificial intelligence model, which generates the optimal technology stack (e.g., React Native, Node.js, Firebase) and system architecture based on historical data sets. The generated information is sent back from the server to the device and displayed in the user interface.

[0202] Users can review the proposed technology stack and system architecture and base their system design on it.

[0203] Example prompt sentence:

[0204] "Building a social media service for casual games"

[0205] This allows users to quickly obtain information on the optimal technology stack and system architecture, significantly reducing development time and effort.

[0206] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0207] Step 1:

[0208] The user launches the smartphone app, inputs their requirements, for example, "Build a new video distribution platform," and presses the submit button. The input requirements are saved on the device.

[0209] Step 2:

[0210] The terminal converts the requirements entered by the user into JSON format, converts the requirements text into the appropriate data format, and creates an HTTP POST request that includes the requirements data.

[0211] Step 3:

[0212] The terminal sends the created HTTP POST request to the backend server, which receives the request and includes the requirement data.

[0213] Step 4:

[0214] The server analyzes the received requirements data. First, it extracts the requirements data and converts it into an appropriate data format. Then, it passes the extracted requirements data to the artificial intelligence model.

[0215] Step 5:

[0216] The server-based artificial intelligence model analyzes the input requirements data using algorithms trained on past data sets, generating the optimal technology stack (e.g., React Native, Node.js, Firebase) and system architecture.

[0217] Step 6:

[0218] The server takes the technology stack and system architecture information generated by the AI ​​model, converts it into JSON format, and then creates the data to send back to the device as an HTTP response.

[0219] Step 7:

[0220] The terminal analyzes the response data received from the server and displays the analyzed data on a user interface to present the user with information about the technology stack and system architecture.

[0221] Step 8:

[0222] Users can review the presented technology stack and system architecture and use it to help with actual system design and development. For example, they can take concrete action based on a proposal such as "adopting a microservices architecture with React Native, Node.js, and Firebase."

[0223] 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.

[0224] The present invention relates to a system that proposes an appropriate technology stack or system architecture based on specific requirements input by a user, and further combines it with an emotion engine that recognizes the user's emotions. The system includes means for accepting user-input requirements, artificial intelligence model means for analyzing the accepted requirements, means for presenting the generated technology configuration or system architecture to the user, and an emotion engine that recognizes the user's emotions.

[0225] 1. System Configuration

[0226] The system includes the following major components:

[0227] 1. Front end (terminal)

[0228] It provides a web interface for users to input requirements and view results and sentiment analysis results, and is built using modern JavaScript frameworks such as React.js and Vue.js.

[0229] 2. Backend (server)

[0230] It receives user requirements and sentiment data, analyzes them using artificial intelligence models and sentiment engines, and generates results. It is built using frameworks such as Node.js and Django.

[0231] 3. Database

[0232] It is used to store information about the technology stack and system architecture, as well as sentiment data. It uses a relational database such as PostgreSQL.

[0233] 4. Artificial Intelligence Models

[0234] It includes machine learning models to analyze user requirements and generate the appropriate technology stack and system architecture, and is built using TensorFlow and PyTorch.

[0235] 5. Emotion Engine

[0236] Recognize user emotions and incorporate them into input requirements and generated suggestions. Use machine learning models to analyze user input emotional data and use it to suggest more accurate technology stacks and system architectures.

[0237] 2. Program Processing Overview

[0238] In this system, when a user inputs specific requirements through a web interface, the system analyzes the requirements and suggests appropriate technology stacks and system architectures. The system also analyzes the user's emotional data associated with the input requirements and reflects it in the proposal results.

[0239] User enters requirements:

[0240] A user accesses the system through a web browser and inputs a specific requirement (e.g., "E-commerce site for startups"). Once the user has completed the input, they click the "Submit" button, which sends the emotion data along with the requirement to the system.

[0241] The device sends requirements and emotion data:

[0242] When the user clicks the send button, the terminal converts the input requirements and emotion data into JSON format and sends it to the backend server as an HTTP POST request.

[0243] The server parses the requirements and sentiment data:

[0244] The server analyzes the received request and extracts requirement data and emotion data, then passes the requirement data to an artificial intelligence model and the emotion data to an emotion engine for analysis.

[0245] Artificial intelligence models and emotion engines generate the optimal tech stack:

[0246] The artificial intelligence model is trained based on historical datasets to generate a technology stack and system architecture that best suits the user's requirements, and the emotion engine analyzes the user's emotion data and takes into account the user's reaction to the generated technology stack and system architecture.

[0247] The server returns the generated result:

[0248] The server converts the technology stack and system architecture information generated by the AI ​​model and emotion engine into JSON format and returns it to the terminal as an HTTP response.

[0249] The terminal will display the result:

[0250] The device analyzes the received data and displays the results in a user interface, where the user can see the proposed technology stack and system architecture, as well as the sentiment analysis results that accompany the proposal.

[0251] Specific examples

[0252] For example, if a user inputs a requirement "E-commerce site for startups" and indicates positive sentiment towards the input, the system will receive this requirement and use artificial intelligence models to generate the optimal technology stack (e.g., React.js, Node.js, MongoDB, AWS) and system architecture (e.g., microservices architecture). The sentiment engine also analyzes how the user feels about the proposed technologies, and as a result, can provide the most attractive proposal for the user.

[0253] As described above, the system of the present invention quickly presents appropriate technical configurations and system architectures in response to diverse user requirements, and furthermore, reflects the user's feelings, thereby greatly contributing to users' technology selection and design.

[0254] The processing flow will be explained below.

[0255] Step 1:

[0256] A user opens a web browser and accesses a web application on the system.

[0257] Step 2:

[0258] The user fills in a given form with their specific requirements (e.g., "e-commerce site for startups").

[0259] Step 3:

[0260] The user clicks the submit button on the form, which triggers the processing of the entered requirements and sentiment data.

[0261] Step 4:

[0262] The device converts the user input requirements into JSON format, and the emotion data is converted as well, and constructed as the body of the HTTP POST request.

[0263] Step 5:

[0264] The device sends an HTTP POST request to the backend server, which includes the user's input requirements and emotion data.

[0265] Step 6:

[0266] The server receives an HTTP POST request from the device and extracts user input requirement data and emotion data from the request body.

[0267] Step 7:

[0268] The server passes the extracted requirements data to an artificial intelligence model, which takes the requirements data as input and generates the optimal technology stack and system architecture.

[0269] Step 8:

[0270] The server passes the extracted emotion data to the emotion engine, which analyzes the emotion data and identifies the user's emotional state.

[0271] Step 9:

[0272] The emotion engine feeds the analysis results back into the artificial intelligence model, which then reflects them in optimizing the technology stack and system architecture.

[0273] Step 10:

[0274] The artificial intelligence model sends optimized technology stack and system architecture information back to the server.

[0275] Step 11:

[0276] The server converts the output of the AI ​​model and the analysis results of the emotion engine into JSON format, and the converted data is constructed as an HTTP response.

[0277] Step 12:

[0278] The server sends an HTTP response back to the device, which includes the generated technology stack and system architecture information, as well as the sentiment analysis results.

[0279] Step 13:

[0280] The device analyzes the HTTP response received from the server, extracting the generated technology stack and system architecture information and sentiment analysis results from the response body.

[0281] Step 14:

[0282] The device displays the extracted data in a user interface, where the user can view the presented technology stack, system architecture, and sentiment analysis results.

[0283] Step 15:

[0284] Users can obtain reference information for their own system design based on the displayed technology stack, system architecture, and sentiment analysis results.

[0285] Example 2

[0286] 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."

[0287] Conventional systems have limited means of providing appropriate technical configurations and system architectures for user-input requirements, making it difficult to flexibly respond to specific user requirements. Furthermore, proposals do not reflect the user's emotions, resulting in reduced user satisfaction and applicability. Therefore, there is a need for a novel system that can present system configurations that consider not only the user's input requirements but also their emotions.

[0288] 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.

[0289] In this invention, the server includes means for accepting user-input requirements, artificial intelligence model means for analyzing the accepted user-input requirements and generating an appropriate technical configuration and system architecture, means for presenting the generated technical configuration and system architecture to the user, and emotion recognition means for recognizing the user's emotions and reflecting them in the user-input requirements and the generated proposal, thereby enabling the proposal of a more personalized technical configuration and system architecture that takes into account not only the user's requirements but also their emotions.

[0290] "User input requirements" are information that specifically describes the user's requests and wishes for the system.

[0291] "Analysis means" refers to a function or device that processes input data and extracts useful information.

[0292] A "technical configuration" is a combination of technical elements or technologies used to achieve specific requirements or objectives.

[0293] "System architecture" is a representation of the interrelationships and structure of the elements that make up a system.

[0294] An "artificial intelligence model" is an algorithm or mathematical model designed to perform a specific task using techniques such as machine learning and deep learning.

[0295] "Emotion recognition means" is a function or device for analyzing a user's input or behavior and determining the user's emotional state.

[0296] A "dataset" is a set of data used to train and evaluate machine learning models.

[0297] The "means for proposing" is a function or device for presenting the optimal technical configuration or system architecture to the user based on the analysis results.

[0298] "User interface" refers to the input and output means and methods by which a user interacts with a system.

[0299] MODE FOR CARRYING OUT THE INVENTION

[0300] The present invention relates to a system that presents appropriate technical configurations and system architectures based on specific requirements input by a user, and further combines this with an emotion engine that recognizes the user's emotions. The system includes means for accepting user-input requirements, artificial intelligence model means for analyzing the accepted requirements, means for presenting the generated technical configurations and system architectures to the user, and an emotion engine that recognizes the user's emotions.

[0301] System Configuration

[0302] The system includes the following major components:

[0303] 1. Front end (terminal)

[0304] The terminal provides a web interface for users to input requirements and view results and sentiment analysis results. Specifically, it is built using modern JavaScript frameworks (e.g., React.js, Vue.js), allowing users to easily input and submit requirements using a dynamic and intuitive interface.

[0305] 2. Backend (server)

[0306] The server receives user requirements and emotion data, analyzes it using an artificial intelligence model and emotion engine, and generates results. It is built using a common backend framework (e.g., Node.js, Django). The server analyzes the received data, extracts requirement data and emotion data, and passes them to the appropriate means.

[0307] 3. Database

[0308] The database is used to store technical configuration and system architecture information, as well as sentiment data. A relational database (e.g., PostgreSQL) allows for efficient data management and querying.

[0309] 4. Artificial Intelligence Models

[0310] The artificial intelligence model analyzes user requirements and uses machine learning models to generate appropriate technology configurations and system architectures. It is built using TensorFlow and PyTorch and trained based on past datasets. This model generates the technology stack and system architecture that best suits the user's requirements.

[0311] 5. Emotion Engine

[0312] The emotion engine recognizes user emotions and reflects them in input requirements and generated suggestions. It uses machine learning models to analyze user input emotion data and determine the user's emotional state from their responses and behaviors, enabling more accurate and user-specific technical suggestions.

[0313] Specific examples

[0314] For example, if a user inputs a requirement "E-commerce site for startups" and indicates positive sentiment towards the input, the system will receive this requirement and use artificial intelligence models to generate the optimal technology stack (e.g., React.js, Node.js, MongoDB, AWS) and system architecture (e.g., microservices architecture). The sentiment engine also analyzes how the user feels about the proposed technologies, resulting in the most attractive proposal for the user.

[0315] Prompt Sentence Examples

[0316] Examples of specific prompts that users can input into a generative AI model include the following:

[0317] "Please suggest a compatible tech stack. The requirement is for an e-commerce website for a startup, and future scalability is important."

[0318] The above is a specific embodiment for carrying out the present invention.

[0319] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0320] Step 1:

[0321] User enters requirements

[0322] A user accesses a web interface and inputs specific requirements. After entering the requirements in the input fields, the user clicks the "Submit" button. A specific prompt statement (e.g., "E-commerce site for startups") is used as input. Based on this input, requirement data is generated.

[0323] Step 2:

[0324] The device sends requirements and emotion data

[0325] The device converts the requirements entered by the user along with emotional data (inferred from keyboard typing speed, mouse movements, etc.) into JSON format. The converted data is sent to the server as an HTTP POST request. The input includes the requirements data and emotional data, and the output is JSON format data. The specific operations performed by the device include formatting the data and sending the HTTP request.

[0326] Step 3:

[0327] The server analyzes the requirements and sentiment data

[0328] The server parses the received JSON data and extracts requirement data and emotion data. This analysis passes the requirement data to an artificial intelligence model and the emotion data to an emotion engine. The input contains JSON data, and the output is the parsed requirement data and emotion data. Specific operations performed by the server include data parsing and data sorting.

[0329] Step 4:

[0330] Artificial intelligence model generates optimal tech stack

[0331] The artificial intelligence model analyzes the requirements data based on past datasets and generates the optimal technology stack. The machine learning frameworks used here include TensorFlow and PyTorch. The input includes the requirements data, and the output is the optimal technology stack and system architecture. The specific operation is to execute the inference process of the machine learning model.

[0332] Step 5:

[0333] The emotion engine analyzes the emotion data

[0334] The emotion engine analyzes user emotional data and applies the results to the technology stack and system architecture. The input includes emotional data, and the output is a rating based on the emotional state. Specific operations include the execution of emotion analysis algorithms.

[0335] Step 6:

[0336] The server returns the generated results

[0337] The server converts the technology stack and system architecture information generated by the AI ​​model and emotion engine into JSON format and returns it to the terminal as an HTTP response. The input includes the generated technology stack and emotion evaluation results, and the output is JSON format data. Specific operations include formatting the data and sending the HTTP response.

[0338] Step 7:

[0339] The terminal displays the results

[0340] The terminal parses the received JSON data and displays the technology stack, system architecture, and sentiment analysis results on a user interface. The input contains JSON data, and the output provides an intuitive user interface. Specific operations include parsing the data and dynamically generating HTML.

[0341] The above is the flow of each processing step of the system.

[0342] (Application example 2)

[0343] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0344] Current proposal systems with technical configurations and system architectures make proposals without considering the user's emotions, resulting in a poor user experience. Furthermore, they are unable to appropriately control other systems or devices based on the user's emotions, resulting in a lack of responsiveness and ease of use in certain situations. Therefore, there is a need to provide systems that better suit the user's needs by analyzing the user's emotions and reflecting them in proposal results and system control.

[0345] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for accepting user-input requirements, artificial intelligence model means for analyzing the accepted user-input requirements and generating an appropriate technical configuration and system architecture, means for presenting the generated technical configuration and system architecture to the user, emotion recognition means for recognizing the user's emotions and reflecting them in the analysis results, and means for controlling other systems and devices based on the emotion recognition data. By taking emotion data into consideration when analyzing the user's input requirements, it is possible to propose more appropriate and attractive technology stacks and system architectures. Furthermore, by appropriately controlling other systems and devices, such as autonomous vehicles and entertainment providers, based on the emotion recognition data, responsiveness and ease of use can be improved.

[0346] "Means for accepting user input requirements" refers to an interface or device that the system uses to receive specific conditions or requests input by the user.

[0347] "Artificial intelligence model means" refers to a machine learning algorithm or model for analyzing received user input requirements and generating an appropriate technical configuration or system architecture based thereon.

[0348] "Means for presenting the generated technical configuration and system architecture to the user" refers to an interface or device for visually or audibly providing the user with the technical configuration and system architecture generated as a result of the analysis.

[0349] "Emotion recognition means" refers to technology or devices that recognize a user's emotions and reflect them in the analysis results. Specifically, this includes facial expression recognition and voice analysis.

[0350] "Means for controlling other systems or devices" refers to technologies or devices for appropriately controlling multiple systems or devices, such as autonomous vehicles or entertainment systems, based on recognized emotion data.

[0351] A "technology configuration" is the combination of tools and platforms used to implement a system or application, including, for example, a particular programming language, framework, database, etc.

[0352] "System architecture" refers to the basic framework or structure for the overall system configuration and design. Specifically, it includes microservice architecture and monolithic architecture.

[0353] "Emotion Recognition Data" means data about a user's emotions collected and analyzed by the emotion recognition means, which is used to improve the accuracy of suggestions and for system control.

[0354] This invention relates to a system installed in an autonomous vehicle that analyzes user input requirements and emotions, generates and presents appropriate technical configurations and system architectures based on the analysis, and controls the operation of the vehicle and related systems. To realize this system, the following programs and processing procedures are executed.

[0355] System Configuration

[0356] This system is broadly composed of the following main components:

[0357] 1. Front end (terminal)

[0358] Provide an interface for passengers to interact with the system. Specifically, a smartphone application is used. The application provides a UI for passenger input and displaying emotion recognition results. Modern JavaScript frameworks (e.g., React.js, Vue.js) are used.

[0359] 2. Backend (server)

[0360] The system receives passenger requirements and emotion data, analyzes them with artificial intelligence models and emotion engines, and generates results using server-side frameworks such as Node.js and Django. The back-end server also communicates with the autonomous vehicle and related systems.

[0361] 3. Database

[0362] Manage and store information on technical configuration and system architecture, as well as emotional data, using a relational database such as PostgreSQL.

[0363] 4. Artificial Intelligence Models

[0364] Use machine learning models to analyze passenger requirements and generate the appropriate technical configuration and system architecture, using pre-trained models based on historical datasets using TensorFlow and PyTorch.

[0365] 5. Emotion recognition means

[0366] The system recognizes passenger emotions and uses the data for analysis. It uses the smartphone's camera and microphone to perform facial expression recognition and voice analysis. Specifically, it uses toolkits such as OpenCV and TensorFlow.

[0367] 6. Means of Controlling Other Systems or Devices

[0368] Based on the recognized emotion data, autonomous vehicles and entertainment systems can be controlled, for example, by adjusting the vehicle's driving mode or the in-car environment (music, temperature, etc.) according to a specific emotion.

[0369] Program processing description

[0370] This system is constructed from a smartphone, a server, a database, an artificial intelligence model, and an emotion recognition engine. Below are specific examples of data processing and data calculation using each hardware and software.

[0371] Hardware and Software Use

[0372] Smartphone: Used to capture passengers' facial expressions and voices and generate emotion data. Uses OpenCV and the smartphone's camera and microphone.

[0373] Server: Performs data analysis and management. Uses Node.js and Django to process data and respond in real time.

[0374] Database: Stores emotion data and technical configuration information. Uses PostgreSQL.

[0375] Artificial intelligence model: Using TensorFlow or PyTorch, it suggests the best system based on passenger requirements and historical data.

[0376] Emotion Recognition Engine: Uses OpenCV and TensorFlow to recognize user emotions from captured images and audio.

[0377] Specific examples

[0378] 1. Emotion analysis: Passengers launch a smartphone application and capture emotional data through the camera and microphone. For example, if a passenger smiles, the emotion recognition engine classifies it as "happy."

[0379] 2. Driving mode adjustment: Emotion data is sent to the server, and the "happy" emotion is detected. Based on this information, the server sets the car's autonomous driving mode to "eco."

[0380] 3. Entertainment provision: The server receives the emotion data and transmits it to the entertainment system. For example, it selects a pop music playlist that best suits the emotion "happy" and starts playing it.

[0381] Prompt Sentence Examples

[0382] "If a passenger indicates a smile through facial recognition, set the vehicle's driving mode to eco-friendly Eco mode and play an upbeat pop music playlist."

[0383] The above-described embodiments of the present invention enable the proposal of flexible and appropriate technical configurations and system architectures according to the requirements and emotions of users. Furthermore, the quality of the user experience can be improved by controlling the operation of related systems in real time.

[0384] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0385] Step 1:

[0386] A user launches a smartphone application and enters their passenger requirements. These requirements include specific conditions and preferences. The input is in text format and is displayed in the application's user interface. This input data is then sent to subsequent processing steps.

[0387] Step 2:

[0388] The terminal receives the user's input requirements, converts them into JSON format, and sends them as an HTTP POST request to the backend server, where the input data is sent through a network protocol to the server and received for analysis.

[0389] Step 3:

[0390] The server receives the request and extracts the user's requirements data. This data is passed to an artificial intelligence model that uses TensorFlow or PyTorch to generate the appropriate technical configuration and system architecture.

[0391] Step 4:

[0392] The server uses emotion recognition to analyze emotion data acquired in real time from the smartphone's camera and microphone. Here, OpenCV and voice analysis technology are used to classify the emotion data. As a result, emotion labels such as "happy" and "sad" are obtained.

[0393] Step 5:

[0394] The server integrates the technical configuration and system architecture generated by the AI ​​model with the emotion data obtained by the emotion recognition means. The server then compiles the analysis results and creates data to provide to the user.

[0395] Step 6:

[0396] The server converts the integrated result data into JSON format and sends it to the terminal as an HTTP response, where the data is returned from the server to the terminal.

[0397] Step 7:

[0398] Based on the received data, the device displays the analysis results and technical proposals on the user interface. The user can check these results. Specifically, the technology stack and system architecture are illustrated on the screen.

[0399] Step 8:

[0400] The device then generates instructions for controlling the autonomous vehicle and related systems based on the emotion data and sends them to a server, which determines the driving mode and entertainment content according to the emotion.

[0401] Step 9:

[0402] The server receives these instructions and calls the appropriate APIs to control the autonomous vehicle's driving mode and entertainment system. For example, if the passenger is recognized as "happy," it can set the vehicle's driving mode to "eco" and play a pop music playlist.

[0403] Step 10:

[0404] The end result is an in-car environment that matches the user's emotions, which the system monitors in real time and adjusts as needed, ensuring a comfortable riding experience for passengers.

[0405] 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.

[0406] 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.

[0407] 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.

[0408] [Second embodiment]

[0409] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0410] 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.

[0411] 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).

[0412] 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.

[0413] 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.

[0414] 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).

[0415] 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.

[0416] 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.

[0417] 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.

[0418] 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.

[0419] 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.

[0420] 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."

[0421] The present invention relates to a system for suggesting an appropriate technology stack or system architecture based on specific requirements input by a user, the system including means for accepting user-input requirements, artificial intelligence model means for analyzing the accepted requirements, and means for presenting the generated technology stack or system architecture to the user.

[0422] 1. System Configuration

[0423] The system includes the following major components:

[0424] 1. Front end (terminal)

[0425] It provides a web interface for users to enter requirements and view results, and is built using modern JavaScript frameworks such as React.js and Vue.js.

[0426] 2. Backend (server)

[0427] It receives user requirements and uses artificial intelligence models to generate the optimal technology stack and system architecture for those requirements, built using frameworks such as Node.js and Django.

[0428] 3. Database

[0429] It is used to store information about technology stacks and system architectures. It uses a relational database such as PostgreSQL.

[0430] 4. Artificial Intelligence Models

[0431] It includes machine learning models to analyze user requirements and generate the appropriate technology stack and system architecture, and is built using TensorFlow and PyTorch.

[0432] 2. Program Processing Overview

[0433] The system allows users to input specific requirements through a web interface, analyzes those requirements, and suggests appropriate technology stacks and system architectures.

[0434] User enters requirements:

[0435] A user accesses the system through a web browser and enters a specific requirement (e.g., "E-commerce site for startups"), and once the user has completed the entry, they click the "Submit" button to send the requirement to the system.

[0436] The device sends its requirements to the server:

[0437] When the user clicks the submit button, the terminal converts the entered requirements into JSON format and sends it to the backend server as an HTTP POST request.

[0438] The server parses the requirements:

[0439] The server analyzes the received request and extracts the requirements data, which is then passed to the artificial intelligence model.

[0440] Artificial intelligence model generates optimal tech stack:

[0441] Artificial intelligence models are trained based on historical datasets to generate the technology stack and system architecture that best suits the user's requirements.

[0442] The server returns the generated result:

[0443] The server converts the technology stack and system architecture information generated by the artificial intelligence model into JSON format and returns it to the terminal as an HTTP response.

[0444] The terminal will display the result:

[0445] The device analyzes the received data and displays the results on the user interface, allowing users to review the presented technology stack and system architecture and use it to help design their own systems.

[0446] Specific examples

[0447] For example, if a user inputs the requirement "E-commerce site for startups," the system will receive this requirement and use an artificial intelligence model to generate the optimal technology stack (e.g., React.js, Node.js, MongoDB, AWS) and system architecture (e.g., microservices architecture), providing users with reference information for specific technology selection and system construction.

[0448] As described above, the system of the present invention quickly presents appropriate technical configurations and system architectures for a variety of user requirements, greatly contributing to users' technology selection and design.

[0449] The processing flow will be explained below.

[0450] Step 1:

[0451] A user opens a web browser and accesses a web application on the system.

[0452] Step 2:

[0453] The user fills in a given form with their specific requirements (e.g., "e-commerce site for startups").

[0454] Step 3:

[0455] The user clicks the submit button on the form, which triggers the processing of the entered requirements.

[0456] Step 4:

[0457] The terminal converts the user input requirements into JSON format, which is then constructed as the body of the HTTP POST request.

[0458] Step 5:

[0459] The terminal sends an HTTP POST request to the backend server, which includes the user's input requirements.

[0460] Step 6:

[0461] The server receives an HTTP POST request from the terminal and extracts the user input requirement data from the request body.

[0462] Step 7:

[0463] The server passes the extracted requirements data to an artificial intelligence model, which takes the requirements data as input and generates the optimal technology stack and system architecture.

[0464] Step 8:

[0465] The artificial intelligence model generates technology stack and system architecture information that is sent back to the server.

[0466] Step 9:

[0467] The server converts the output of the AI ​​model into JSON format, which is then used to construct an HTTP response.

[0468] Step 10:

[0469] The server sends an HTTP response back to the device, which includes information about the generated technology stack and system architecture.

[0470] Step 11:

[0471] The device analyzes the HTTP response received from the server and extracts the generated technology stack and system architecture information from the response body.

[0472] Step 12:

[0473] The terminal displays the extracted data in a user interface, where the user can review the presented technology stack and system architecture.

[0474] Step 13:

[0475] Users can obtain reference information for their own system design based on the displayed technology stack and system architecture.

[0476] Example 1

[0477] 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."

[0478] In modern system development, selecting a technology stack and system architecture is a critical and complex process. Developers, from beginners to professionals, spend a great deal of time and effort selecting the optimal technology configuration. However, making the optimal selection requires specialized knowledge, and a lack of it can reduce the project's success rate. Furthermore, incorrect technology selection can significantly increase development costs and time. Therefore, there is a need for a system that allows users to easily and quickly select the optimal technology configuration and system architecture.

[0479] 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.

[0480] In this invention, the server includes: means for accepting user-input requirements; an artificial intelligence model for analyzing the accepted user-input requirements and generating an optimal technical configuration and system architecture; means for converting the user-input requirements into JSON format and sending it to the server as an HTTP POST request; means for the server to analyze the requirements, extract requirement data, and pass it to the artificial intelligence model; means for the artificial intelligence model to generate an optimal technical configuration and system architecture based on a past dataset; means for converting the generated information on the technical configuration and system architecture into JSON format and returning it from the server to the terminal; and means for the terminal to analyze the received data and display the results on a user interface. This enables a user to quickly and easily receive an optimal technical configuration and system architecture based on specific requirements.

[0481] "User-input requirements" are functions and conditions that a user specifically desires for the system, entered in text format.

[0482] "JSON format" is an abbreviation for JavaScript Object Notation, and is a lightweight data exchange format that represents data as attribute-value pairs.

[0483] An "HTTP POST request" is a type of HTTP protocol used to send data from a web browser or client to a server.

[0484] A "server" is a computer system that provides services over a network, and in this invention, plays a central role in receiving and analyzing requirements, and transmitting and receiving data.

[0485] An "artificial intelligence model" is a model trained by machine learning algorithms that has the ability to analyze user requirements and generate optimal technology stacks and system architectures.

[0486] A "technical configuration" is a combination of technical elements required to build a system, including frameworks, libraries, databases, etc.

[0487] "System architecture" defines the overall configuration of a system and is a concept that clarifies the interactions between components and design policies.

[0488] The "user interface" refers to a screen or operating means that is directly used by the user, and in this invention, it is a means for displaying the analysis results and allowing the user to confirm the results.

[0489] The present invention is a system that automatically generates and presents optimal technology stacks and system architectures based on specific requirements entered by a user. The system consists of major components such as terminals, servers, artificial intelligence models, and databases.

[0490] The terminal provides a user interface for users to input requirements and display the results. Specifically, it is built using modern JavaScript frameworks such as React.js or Vue.js. Users access the system through a web browser and input specific requirements (e.g., "E-commerce site for startups"). Once input is complete, users click the "Submit" button to send the requirements to the system.

[0491] The terminal converts the input requirements into JSON format and sends it as an HTTP POST request to the backend server. The server receives this HTTP POST request. The server is built using frameworks such as Node.js or Django, analyzes the request, extracts the requirements data, and passes it to the artificial intelligence model.

[0492] The artificial intelligence model is trained based on historical datasets and generates the technology stack and system architecture that best suits the user's requirements. The model is built using TensorFlow and PyTorch. For example, if a user enters the requirement "e-commerce site for startups," the model will recommend React.js, Node.js, MongoDB, and AWS.

[0493] The generated technology stack and system architecture information is converted back to JSON format and sent back to the terminal as an HTTP response from the server. The terminal analyzes this data and displays the results in the user interface. The user can then review the presented technology stack and system architecture and use it in their own system design.

[0494] For example, if the user enters the prompt text:

[0495] Example prompt sentence:

[0496] "E-commerce site for startups"

[0497] In response, the AI ​​model suggests the following optimal technology stack and system architecture:

[0498] Tech stack: React.js, Node.js, MongoDB, cloud services

[0499] System Architecture: Microservices Architecture

[0500] This allows users to quickly obtain reference information for specific technology selection and system construction. This system significantly streamlines users' technology selection and design processes, contributing to saving time and resources.

[0501] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0502] Step 1:

[0503] User enters requirements

[0504] Specific behavior:

[0505] Users access the system's front end using a web browser and fill out a requirements form to enter specific project requirements, such as "e-commerce site for startups."

[0506] input:

[0507] User requirements such as "E-commerce site for startups"

[0508] output:

[0509] Requirement data entry completed

[0510] Step 2:

[0511] The device sends its requirements to the server

[0512] Specific behavior:

[0513] When the user clicks the "Submit" button, the terminal (front end) converts the entered requirements into JSON format and sends it to the back end server as an HTTP POST request.

[0514] input:

[0515] Requirement Data

[0516] output:

[0517] An HTTP POST request containing the requirements data in JSON format

[0518] Step 3:

[0519] The server analyzes the requirements

[0520] Specific behavior:

[0521] The server analyzes the received HTTP POST request and extracts the requirements data (e.g., "E-commerce site for startups") from it.

[0522] input:

[0523] Requirements data in JSON format in an HTTP POST request

[0524] output:

[0525] Analyzed requirements data

[0526] Step 4:

[0527] The server passes the requirements data to the artificial intelligence model

[0528] Specific behavior:

[0529] In order to pass the analyzed requirements data to the artificial intelligence model, the server converts the format of the data as necessary and inputs it to the artificial intelligence model.

[0530] input:

[0531] Analyzed requirements data

[0532] output:

[0533] Requirements data in a format that can be read by artificial intelligence models

[0534] Step 5:

[0535] Artificial intelligence models generate optimal technology stacks and system architectures

[0536] Specific behavior:

[0537] Artificial intelligence models (using TensorFlow and PyTorch) utilize algorithms that learn from historical datasets to generate a technology stack and system architecture that best suits the user's requirements.

[0538] input:

[0539] Requirements data fed into an artificial intelligence model

[0540] output:

[0541] Generated technology stack and system architecture information

[0542] Step 6:

[0543] The server returns the generated results to the device.

[0544] Specific behavior:

[0545] The server converts the technology stack and system architecture information generated by the artificial intelligence model into JSON format and returns it to the terminal as an HTTP response.

[0546] input:

[0547] Generated technology stack and system architecture information

[0548] output:

[0549] HTTP response containing technology stack and system architecture information in JSON format

[0550] Step 7:

[0551] The terminal displays the results

[0552] Specific behavior:

[0553] The terminal parses the received JSON data and displays it in the user interface in an appropriate format, for example, "The recommended technology stack is React.js, Node.js, MongoDB, and AWS."

[0554] input:

[0555] Technical stack and system architecture information received as an HTTP response in JSON format

[0556] output:

[0557] Technology stack and system architecture information displayed in the user interface

[0558] This allows users to quickly obtain reference information for specific technology selection and system construction.

[0559] (Application example 1)

[0560] 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."

[0561] In recent years, demand for content distribution services has been increasing, and audio and video distribution using smart devices in particular has been rapidly expanding. However, launching these services requires selecting the optimal technology stack and system architecture, which can be difficult for users lacking technical knowledge. For this reason, there is a need for a system that allows users to easily select the optimal technology configuration and system architecture.

[0562] 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.

[0563] In this invention, the server includes means for accepting user-input requirements, artificial intelligence model means for analyzing the accepted user-input requirements and generating an appropriate technical configuration and system architecture, means for presenting the generated technical configuration and system architecture to the user, means for analyzing the user-input requirements related to content distribution and presenting an optimal technical stack and system architecture, and means for displaying the generated technical configuration and system architecture using a smart device, thereby enabling the user to easily select and use the optimal technology stack and system architecture.

[0564] - "User-input requirements" are specific requirements that users of the system input as settings or desired conditions.

[0565] An "artificial intelligence model" is an algorithm that uses technologies such as machine learning and deep learning to analyze data and make predictions and classifications.

[0566] "Technical configuration" refers to the combination of software and hardware required to realize a system.

[0567] "System architecture" is the design of the overall structure of a system and the interactions between its components.

[0568] "Analysis means" is a means for generating an appropriate technical configuration or system architecture based on user-input requirements.

[0569] A "technology stack" is a collection of technologies used to build a system or application.

[0570] A "smart device" is an electronic device that can connect to the Internet and has advanced functions.

[0571] "Content distribution" refers to the provision of digital content such as audio, video, and text to users via the Internet.

[0572] The "means for presenting to the user" refers to a means for providing the generated technical configuration and system architecture to the user.

[0573] This invention is a system that suggests appropriate technology stacks and system architectures based on specific requirements input by the user. The system mainly consists of the following elements:

[0574] 1. Frontend (terminal):

[0575] The terminal provides an interface for users to input requirements and check the results. This interface runs on smart devices such as smartphones and is built using frameworks such as React Native.

[0576] 2. Backend (server):

[0577] The server receives user requirements and uses artificial intelligence models to generate the optimal technology stack and system architecture for those requirements. This backend is built using frameworks such as Flask (Python).

[0578] 3. Database:

[0579] The database stores information about the technology stack and system architecture, and uses databases such as Firebase and DynamoDB.

[0580] 4. Artificial Intelligence Model:

[0581] The artificial intelligence model is built using machine learning techniques such as TensorFlow and trained based on historical datasets. The model analyzes user requirements and generates the optimal technology stack and system architecture.

[0582] Specific examples:

[0583] A user launches the smartphone app and inputs requirements, such as "Build a new video distribution platform." When the user clicks the "Submit" button, the device converts the input requirements into JSON format and sends it as an HTTP POST request to the backend server.

[0584] The server receives the requirements and begins analysis. The received requirements are passed to an artificial intelligence model, which generates the optimal technology stack (e.g., React Native, Node.js, Firebase) and system architecture based on historical data sets. The generated information is sent back from the server to the device and displayed in the user interface.

[0585] Users can review the proposed technology stack and system architecture and base their system design on it.

[0586] Example prompt sentence:

[0587] "Building a social media service for casual games"

[0588] This allows users to quickly obtain information on the optimal technology stack and system architecture, significantly reducing development time and effort.

[0589] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0590] Step 1:

[0591] The user launches the smartphone app, inputs their requirements, for example, "Build a new video distribution platform," and presses the submit button. The input requirements are saved on the device.

[0592] Step 2:

[0593] The terminal converts the requirements entered by the user into JSON format, converts the requirements text into the appropriate data format, and creates an HTTP POST request that includes the requirements data.

[0594] Step 3:

[0595] The terminal sends the created HTTP POST request to the backend server, which receives the request and includes the requirement data.

[0596] Step 4:

[0597] The server analyzes the received requirements data. First, it extracts the requirements data and converts it into an appropriate data format. Then, it passes the extracted requirements data to the artificial intelligence model.

[0598] Step 5:

[0599] The server-based artificial intelligence model analyzes the input requirements data using algorithms trained on past data sets, generating the optimal technology stack (e.g., React Native, Node.js, Firebase) and system architecture.

[0600] Step 6:

[0601] The server takes the technology stack and system architecture information generated by the AI ​​model, converts it into JSON format, and then creates the data to send back to the device as an HTTP response.

[0602] Step 7:

[0603] The terminal analyzes the response data received from the server and displays the analyzed data on a user interface to present the user with information about the technology stack and system architecture.

[0604] Step 8:

[0605] Users can review the presented technology stack and system architecture and use it to help with actual system design and development. For example, they can take concrete action based on a proposal such as "adopting a microservices architecture with React Native, Node.js, and Firebase."

[0606] 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.

[0607] The present invention relates to a system that proposes an appropriate technology stack or system architecture based on specific requirements input by a user, and further combines it with an emotion engine that recognizes the user's emotions. The system includes means for accepting user-input requirements, artificial intelligence model means for analyzing the accepted requirements, means for presenting the generated technology configuration or system architecture to the user, and an emotion engine that recognizes the user's emotions.

[0608] 1. System Configuration

[0609] The system includes the following major components:

[0610] 1. Front end (terminal)

[0611] It provides a web interface for users to input requirements and view results and sentiment analysis results, and is built using modern JavaScript frameworks such as React.js and Vue.js.

[0612] 2. Backend (server)

[0613] It receives user requirements and sentiment data, analyzes them using artificial intelligence models and sentiment engines, and generates results. It is built using frameworks such as Node.js and Django.

[0614] 3. Database

[0615] It is used to store information about the technology stack and system architecture, as well as sentiment data. It uses a relational database such as PostgreSQL.

[0616] 4. Artificial Intelligence Models

[0617] It includes machine learning models to analyze user requirements and generate the appropriate technology stack and system architecture, and is built using TensorFlow and PyTorch.

[0618] 5. Emotion Engine

[0619] Recognize user emotions and incorporate them into input requirements and generated suggestions. Use machine learning models to analyze user input emotional data and use it to suggest more accurate technology stacks and system architectures.

[0620] 2. Program Processing Overview

[0621] In this system, when a user inputs specific requirements through a web interface, the system analyzes the requirements and suggests appropriate technology stacks and system architectures. The system also analyzes the user's emotional data associated with the input requirements and reflects it in the proposal results.

[0622] User enters requirements:

[0623] A user accesses the system through a web browser and inputs a specific requirement (e.g., "E-commerce site for startups"). Once the user has completed the input, they click the "Submit" button, which sends the emotion data along with the requirement to the system.

[0624] The device sends requirements and emotion data:

[0625] When the user clicks the send button, the terminal converts the input requirements and emotion data into JSON format and sends it to the backend server as an HTTP POST request.

[0626] The server parses the requirements and sentiment data:

[0627] The server analyzes the received request and extracts requirement data and emotion data, then passes the requirement data to an artificial intelligence model and the emotion data to an emotion engine for analysis.

[0628] Artificial intelligence models and emotion engines generate the optimal tech stack:

[0629] The artificial intelligence model is trained based on historical datasets to generate a technology stack and system architecture that best suits the user's requirements, and the emotion engine analyzes the user's emotion data and takes into account the user's reaction to the generated technology stack and system architecture.

[0630] The server returns the generated result:

[0631] The server converts the technology stack and system architecture information generated by the AI ​​model and emotion engine into JSON format and returns it to the terminal as an HTTP response.

[0632] The terminal will display the result:

[0633] The device analyzes the received data and displays the results in a user interface, where the user can see the proposed technology stack and system architecture, as well as the sentiment analysis results that accompany the proposal.

[0634] Specific examples

[0635] For example, if a user inputs a requirement "E-commerce site for startups" and indicates positive sentiment towards the input, the system will receive this requirement and use artificial intelligence models to generate the optimal technology stack (e.g., React.js, Node.js, MongoDB, AWS) and system architecture (e.g., microservices architecture). The sentiment engine also analyzes how the user feels about the proposed technologies, and as a result, can provide the most attractive proposal for the user.

[0636] As described above, the system of the present invention quickly presents appropriate technical configurations and system architectures in response to diverse user requirements, and furthermore, reflects the user's feelings, thereby greatly contributing to users' technology selection and design.

[0637] The processing flow will be explained below.

[0638] Step 1:

[0639] A user opens a web browser and accesses a web application on the system.

[0640] Step 2:

[0641] The user fills in a given form with their specific requirements (e.g., "e-commerce site for startups").

[0642] Step 3:

[0643] The user clicks the submit button on the form, which triggers the processing of the entered requirements and sentiment data.

[0644] Step 4:

[0645] The device converts the user input requirements into JSON format, and the emotion data is converted as well, and constructed as the body of the HTTP POST request.

[0646] Step 5:

[0647] The device sends an HTTP POST request to the backend server, which includes the user's input requirements and emotion data.

[0648] Step 6:

[0649] The server receives an HTTP POST request from the device and extracts user input requirement data and emotion data from the request body.

[0650] Step 7:

[0651] The server passes the extracted requirements data to an artificial intelligence model, which takes the requirements data as input and generates the optimal technology stack and system architecture.

[0652] Step 8:

[0653] The server passes the extracted emotion data to the emotion engine, which analyzes the emotion data and identifies the user's emotional state.

[0654] Step 9:

[0655] The emotion engine feeds the analysis results back into the artificial intelligence model, which then reflects them in optimizing the technology stack and system architecture.

[0656] Step 10:

[0657] The artificial intelligence model sends optimized technology stack and system architecture information back to the server.

[0658] Step 11:

[0659] The server converts the output of the AI ​​model and the analysis results of the emotion engine into JSON format, and the converted data is constructed as an HTTP response.

[0660] Step 12:

[0661] The server sends an HTTP response back to the device, which includes the generated technology stack and system architecture information, as well as the sentiment analysis results.

[0662] Step 13:

[0663] The device analyzes the HTTP response received from the server, extracting the generated technology stack and system architecture information and sentiment analysis results from the response body.

[0664] Step 14:

[0665] The device displays the extracted data in a user interface, where the user can view the presented technology stack, system architecture, and sentiment analysis results.

[0666] Step 15:

[0667] Users can obtain reference information for their own system design based on the displayed technology stack, system architecture, and sentiment analysis results.

[0668] Example 2

[0669] 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."

[0670] Conventional systems have limited means of providing appropriate technical configurations and system architectures for user-input requirements, making it difficult to flexibly respond to specific user requirements. Furthermore, proposals do not reflect the user's emotions, resulting in reduced user satisfaction and applicability. Therefore, there is a need for a novel system that can present system configurations that consider not only the user's input requirements but also their emotions.

[0671] 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.

[0672] In this invention, the server includes means for accepting user-input requirements, artificial intelligence model means for analyzing the accepted user-input requirements and generating an appropriate technical configuration and system architecture, means for presenting the generated technical configuration and system architecture to the user, and emotion recognition means for recognizing the user's emotions and reflecting them in the user-input requirements and the generated proposal, thereby enabling the proposal of a more personalized technical configuration and system architecture that takes into account not only the user's requirements but also their emotions.

[0673] "User input requirements" are information that specifically describes the user's requests and wishes for the system.

[0674] "Analysis means" refers to a function or device that processes input data and extracts useful information.

[0675] A "technical configuration" is a combination of technical elements or technologies used to achieve specific requirements or objectives.

[0676] "System architecture" is a representation of the interrelationships and structure of the elements that make up a system.

[0677] An "artificial intelligence model" is an algorithm or mathematical model designed to perform a specific task using techniques such as machine learning and deep learning.

[0678] "Emotion recognition means" is a function or device for analyzing a user's input or behavior and determining the user's emotional state.

[0679] A "dataset" is a set of data used to train and evaluate machine learning models.

[0680] The "means for proposing" is a function or device for presenting the optimal technical configuration or system architecture to the user based on the analysis results.

[0681] "User interface" refers to the input and output means and methods by which a user interacts with a system.

[0682] MODE FOR CARRYING OUT THE INVENTION

[0683] The present invention relates to a system that presents appropriate technical configurations and system architectures based on specific requirements input by a user, and further combines this with an emotion engine that recognizes the user's emotions. The system includes means for accepting user-input requirements, artificial intelligence model means for analyzing the accepted requirements, means for presenting the generated technical configurations and system architectures to the user, and an emotion engine that recognizes the user's emotions.

[0684] System Configuration

[0685] The system includes the following major components:

[0686] 1. Front end (terminal)

[0687] The terminal provides a web interface for users to input requirements and view results and sentiment analysis results. Specifically, it is built using modern JavaScript frameworks (e.g., React.js, Vue.js), allowing users to easily input and submit requirements using a dynamic and intuitive interface.

[0688] 2. Backend (server)

[0689] The server receives user requirements and emotion data, analyzes it using an artificial intelligence model and emotion engine, and generates results. It is built using a common backend framework (e.g., Node.js, Django). The server analyzes the received data, extracts requirement data and emotion data, and passes them to the appropriate means.

[0690] 3. Database

[0691] The database is used to store technical configuration and system architecture information, as well as sentiment data. A relational database (e.g., PostgreSQL) allows for efficient data management and querying.

[0692] 4. Artificial Intelligence Models

[0693] The artificial intelligence model analyzes user requirements and uses machine learning models to generate appropriate technology configurations and system architectures. It is built using TensorFlow and PyTorch and trained based on past datasets. This model generates the technology stack and system architecture that best suits the user's requirements.

[0694] 5. Emotion Engine

[0695] The emotion engine recognizes user emotions and reflects them in input requirements and generated suggestions. It uses machine learning models to analyze user input emotion data and determine the user's emotional state from their responses and behaviors, enabling more accurate and user-specific technical suggestions.

[0696] Specific examples

[0697] For example, if a user inputs a requirement "E-commerce site for startups" and indicates positive sentiment towards the input, the system will receive this requirement and use artificial intelligence models to generate the optimal technology stack (e.g., React.js, Node.js, MongoDB, AWS) and system architecture (e.g., microservices architecture). The sentiment engine also analyzes how the user feels about the proposed technologies, resulting in the most attractive proposal for the user.

[0698] Prompt Sentence Examples

[0699] Examples of specific prompts that users can input into a generative AI model include the following:

[0700] "Please suggest a compatible tech stack. The requirement is for an e-commerce website for a startup, and future scalability is important."

[0701] The above is a specific embodiment for carrying out the present invention.

[0702] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0703] Step 1:

[0704] User enters requirements

[0705] A user accesses a web interface and inputs specific requirements. After entering the requirements in the input fields, the user clicks the "Submit" button. A specific prompt statement (e.g., "E-commerce site for startups") is used as input. Based on this input, requirement data is generated.

[0706] Step 2:

[0707] The device sends requirements and emotion data

[0708] The device converts the requirements entered by the user along with emotional data (inferred from keyboard typing speed, mouse movements, etc.) into JSON format. The converted data is sent to the server as an HTTP POST request. The input includes the requirements data and emotional data, and the output is JSON format data. The specific operations performed by the device include formatting the data and sending the HTTP request.

[0709] Step 3:

[0710] The server analyzes the requirements and sentiment data

[0711] The server parses the received JSON data and extracts requirement data and emotion data. This analysis passes the requirement data to an artificial intelligence model and the emotion data to an emotion engine. The input contains JSON data, and the output is the parsed requirement data and emotion data. Specific operations performed by the server include data parsing and data sorting.

[0712] Step 4:

[0713] Artificial intelligence model generates optimal tech stack

[0714] The artificial intelligence model analyzes the requirements data based on past datasets and generates the optimal technology stack. The machine learning frameworks used here include TensorFlow and PyTorch. The input includes the requirements data, and the output is the optimal technology stack and system architecture. The specific operation is to execute the inference process of the machine learning model.

[0715] Step 5:

[0716] The emotion engine analyzes the emotion data

[0717] The emotion engine analyzes user emotional data and applies the results to the technology stack and system architecture. The input includes emotional data, and the output is a rating based on the emotional state. Specific operations include the execution of emotion analysis algorithms.

[0718] Step 6:

[0719] The server returns the generated results

[0720] The server converts the technology stack and system architecture information generated by the AI ​​model and emotion engine into JSON format and returns it to the terminal as an HTTP response. The input includes the generated technology stack and emotion evaluation results, and the output is JSON format data. Specific operations include formatting the data and sending the HTTP response.

[0721] Step 7:

[0722] The terminal displays the results

[0723] The terminal parses the received JSON data and displays the technology stack, system architecture, and sentiment analysis results on a user interface. The input contains JSON data, and the output provides an intuitive user interface. Specific operations include parsing the data and dynamically generating HTML.

[0724] The above is the flow of each processing step of the system.

[0725] (Application example 2)

[0726] 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."

[0727] Current proposal systems with technical configurations and system architectures make proposals without considering the user's emotions, resulting in a poor user experience. Furthermore, they are unable to appropriately control other systems or devices based on the user's emotions, resulting in a lack of responsiveness and ease of use in certain situations. Therefore, there is a need to provide systems that better suit the user's needs by analyzing the user's emotions and reflecting them in proposal results and system control.

[0728] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for accepting user-input requirements, artificial intelligence model means for analyzing the accepted user-input requirements and generating an appropriate technical configuration and system architecture, means for presenting the generated technical configuration and system architecture to the user, emotion recognition means for recognizing the user's emotions and reflecting them in the analysis results, and means for controlling other systems and devices based on the emotion recognition data. By taking emotion data into consideration when analyzing the user's input requirements, it is possible to propose more appropriate and attractive technology stacks and system architectures. Furthermore, by appropriately controlling other systems and devices, such as autonomous vehicles and entertainment providers, based on the emotion recognition data, responsiveness and ease of use can be improved.

[0729] "Means for accepting user input requirements" refers to an interface or device that the system uses to receive specific conditions or requests input by the user.

[0730] "Artificial intelligence model means" refers to a machine learning algorithm or model for analyzing received user input requirements and generating an appropriate technical configuration or system architecture based thereon.

[0731] "Means for presenting the generated technical configuration and system architecture to the user" refers to an interface or device for visually or audibly providing the user with the technical configuration and system architecture generated as a result of the analysis.

[0732] "Emotion recognition means" refers to technology or devices that recognize a user's emotions and reflect them in the analysis results. Specifically, this includes facial expression recognition and voice analysis.

[0733] "Means for controlling other systems or devices" refers to technologies or devices for appropriately controlling multiple systems or devices, such as autonomous vehicles or entertainment systems, based on recognized emotion data.

[0734] A "technology configuration" is the combination of tools and platforms used to implement a system or application, including, for example, a particular programming language, framework, database, etc.

[0735] "System architecture" refers to the basic framework or structure for the overall system configuration and design. Specifically, it includes microservice architecture and monolithic architecture.

[0736] "Emotion Recognition Data" means data about a user's emotions collected and analyzed by the emotion recognition means, which is used to improve the accuracy of suggestions and for system control.

[0737] This invention relates to a system installed in an autonomous vehicle that analyzes user input requirements and emotions, generates and presents appropriate technical configurations and system architectures based on the analysis, and controls the operation of the vehicle and related systems. To realize this system, the following programs and processing procedures are executed.

[0738] System Configuration

[0739] This system is broadly composed of the following main components:

[0740] 1. Front end (terminal)

[0741] Provide an interface for passengers to interact with the system. Specifically, a smartphone application is used. The application provides a UI for passenger input and displaying emotion recognition results. Modern JavaScript frameworks (e.g., React.js, Vue.js) are used.

[0742] 2. Backend (server)

[0743] The system receives passenger requirements and emotion data, analyzes them with artificial intelligence models and emotion engines, and generates results using server-side frameworks such as Node.js and Django. The back-end server also communicates with the autonomous vehicle and related systems.

[0744] 3. Database

[0745] Manage and store information on technical configuration and system architecture, as well as emotional data, using a relational database such as PostgreSQL.

[0746] 4. Artificial Intelligence Models

[0747] Use machine learning models to analyze passenger requirements and generate the appropriate technical configuration and system architecture, using pre-trained models based on historical datasets using TensorFlow and PyTorch.

[0748] 5. Emotion recognition means

[0749] The system recognizes passenger emotions and uses the data for analysis. It uses the smartphone's camera and microphone to perform facial expression recognition and voice analysis. Specifically, it uses toolkits such as OpenCV and TensorFlow.

[0750] 6. Means of Controlling Other Systems or Devices

[0751] Based on the recognized emotion data, autonomous vehicles and entertainment systems can be controlled, for example, by adjusting the vehicle's driving mode or the in-car environment (music, temperature, etc.) according to a specific emotion.

[0752] Program processing description

[0753] This system is constructed from a smartphone, a server, a database, an artificial intelligence model, and an emotion recognition engine. Below are specific examples of data processing and data calculation using each hardware and software.

[0754] Hardware and Software Use

[0755] Smartphone: Used to capture passengers' facial expressions and voices and generate emotion data. Uses OpenCV and the smartphone's camera and microphone.

[0756] Server: Performs data analysis and management. Uses Node.js and Django to process data and respond in real time.

[0757] Database: Stores emotion data and technical configuration information. Uses PostgreSQL.

[0758] Artificial intelligence model: Using TensorFlow or PyTorch, it suggests the best system based on passenger requirements and historical data.

[0759] Emotion Recognition Engine: Uses OpenCV and TensorFlow to recognize user emotions from captured images and audio.

[0760] Specific examples

[0761] 1. Emotion analysis: Passengers launch a smartphone application and capture emotional data through the camera and microphone. For example, if a passenger smiles, the emotion recognition engine classifies it as "happy."

[0762] 2. Driving mode adjustment: Emotion data is sent to the server, and the "happy" emotion is detected. Based on this information, the server sets the car's autonomous driving mode to "eco."

[0763] 3. Entertainment provision: The server receives the emotion data and transmits it to the entertainment system. For example, it selects a pop music playlist that best suits the emotion "happy" and starts playing it.

[0764] Prompt Sentence Examples

[0765] "If a passenger indicates a smile through facial recognition, set the vehicle's driving mode to eco-friendly Eco mode and play an upbeat pop music playlist."

[0766] The above-described embodiments of the present invention enable the proposal of flexible and appropriate technical configurations and system architectures according to the requirements and emotions of users. Furthermore, the quality of the user experience can be improved by controlling the operation of related systems in real time.

[0767] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0768] Step 1:

[0769] A user launches a smartphone application and enters their passenger requirements. These requirements include specific conditions and preferences. The input is in text format and is displayed on the application's user interface. This input data is then sent to subsequent processing steps.

[0770] Step 2:

[0771] The terminal receives the user's input requirements, converts them into JSON format, and sends them as an HTTP POST request to the backend server, where the input data is sent through a network protocol to the server and received for analysis.

[0772] Step 3:

[0773] The server receives the request and extracts the user's requirements data. This data is passed to an artificial intelligence model that uses TensorFlow or PyTorch to generate the appropriate technical configuration and system architecture.

[0774] Step 4:

[0775] The server uses emotion recognition to analyze emotion data acquired in real time from the smartphone's camera and microphone. Here, OpenCV and voice analysis technology are used to classify the emotion data. As a result, emotion labels such as "happy" and "sad" are obtained.

[0776] Step 5:

[0777] The server integrates the technical configuration and system architecture generated by the AI ​​model with the emotion data obtained by the emotion recognition means. The server then compiles the analysis results and creates data to provide to the user.

[0778] Step 6:

[0779] The server converts the integrated result data into JSON format and sends it to the terminal as an HTTP response, where the data is returned from the server to the terminal.

[0780] Step 7:

[0781] Based on the received data, the device displays the analysis results and technical proposals on the user interface. The user can check these results. Specifically, the technology stack and system architecture are illustrated on the screen.

[0782] Step 8:

[0783] The device then generates instructions for controlling the autonomous vehicle and related systems based on the emotion data and sends them to a server, which determines the driving mode and entertainment content according to the emotion.

[0784] Step 9:

[0785] The server receives these instructions and calls the appropriate APIs to control the autonomous vehicle's driving mode and entertainment system. For example, if the passenger is recognized as "happy," the server can set the vehicle's driving mode to "eco" and play a pop music playlist.

[0786] Step 10:

[0787] The end result is an in-car environment that matches the user's emotions, which the system monitors in real time and adjusts as needed, ensuring a comfortable riding experience for passengers.

[0788] 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.

[0789] 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.

[0790] 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.

[0791] [Third embodiment]

[0792] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0793] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0794] 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).

[0795] 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.

[0796] 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.

[0797] 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).

[0798] 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.

[0799] 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.

[0800] 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.

[0801] 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.

[0802] 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.

[0803] 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."

[0804] The present invention relates to a system for suggesting an appropriate technology stack or system architecture based on specific requirements input by a user, the system including means for accepting user-input requirements, artificial intelligence model means for analyzing the accepted requirements, and means for presenting the generated technology stack or system architecture to the user.

[0805] 1. System Configuration

[0806] The system includes the following major components:

[0807] 1. Front end (terminal)

[0808] It provides a web interface for users to enter requirements and view results, and is built using modern JavaScript frameworks such as React.js and Vue.js.

[0809] 2. Backend (server)

[0810] It receives user requirements and uses artificial intelligence models to generate the optimal technology stack and system architecture for those requirements, built using frameworks such as Node.js and Django.

[0811] 3. Database

[0812] It is used to store information about technology stacks and system architectures. It uses a relational database such as PostgreSQL.

[0813] 4. Artificial Intelligence Models

[0814] It includes machine learning models to analyze user requirements and generate the appropriate technology stack and system architecture, and is built using TensorFlow and PyTorch.

[0815] 2. Program Processing Overview

[0816] The system allows users to input specific requirements through a web interface, analyzes those requirements, and suggests appropriate technology stacks and system architectures.

[0817] User enters requirements:

[0818] A user accesses the system through a web browser and enters a specific requirement (e.g., "E-commerce site for startups"), and once the user has completed the entry, they click the "Submit" button to send the requirement to the system.

[0819] The device sends its requirements to the server:

[0820] When the user clicks the submit button, the terminal converts the entered requirements into JSON format and sends it to the backend server as an HTTP POST request.

[0821] The server parses the requirements:

[0822] The server analyzes the received request and extracts the requirements data, which is then passed to the artificial intelligence model.

[0823] Artificial intelligence model generates optimal tech stack:

[0824] Artificial intelligence models are trained based on historical datasets to generate the technology stack and system architecture that best suits the user's requirements.

[0825] The server returns the generated result:

[0826] The server converts the technology stack and system architecture information generated by the artificial intelligence model into JSON format and returns it to the terminal as an HTTP response.

[0827] The terminal will display the result:

[0828] The device analyzes the received data and displays the results on the user interface, allowing users to review the presented technology stack and system architecture and use it to help design their own systems.

[0829] Specific examples

[0830] For example, if a user inputs the requirement "E-commerce site for startups," the system will receive this requirement and use an artificial intelligence model to generate the optimal technology stack (e.g., React.js, Node.js, MongoDB, AWS) and system architecture (e.g., microservices architecture), providing users with reference information for specific technology selection and system construction.

[0831] As described above, the system of the present invention quickly presents appropriate technical configurations and system architectures for a variety of user requirements, greatly contributing to users' technology selection and design.

[0832] The processing flow will be explained below.

[0833] Step 1:

[0834] A user opens a web browser and accesses a web application on the system.

[0835] Step 2:

[0836] The user fills in a given form with their specific requirements (e.g., "e-commerce site for startups").

[0837] Step 3:

[0838] The user clicks the submit button on the form, which triggers the processing of the entered requirements.

[0839] Step 4:

[0840] The terminal converts the user input requirements into JSON format, which is then constructed as the body of the HTTP POST request.

[0841] Step 5:

[0842] The terminal sends an HTTP POST request to the backend server, which includes the user's input requirements.

[0843] Step 6:

[0844] The server receives an HTTP POST request from the terminal and extracts the user input requirement data from the request body.

[0845] Step 7:

[0846] The server passes the extracted requirements data to an artificial intelligence model, which takes the requirements data as input and generates the optimal technology stack and system architecture.

[0847] Step 8:

[0848] The artificial intelligence model generates technology stack and system architecture information that is sent back to the server.

[0849] Step 9:

[0850] The server converts the output of the AI ​​model into JSON format, which is then used to construct an HTTP response.

[0851] Step 10:

[0852] The server sends an HTTP response back to the device, which includes information about the generated technology stack and system architecture.

[0853] Step 11:

[0854] The device analyzes the HTTP response received from the server and extracts the generated technology stack and system architecture information from the response body.

[0855] Step 12:

[0856] The terminal displays the extracted data in a user interface, where the user can review the presented technology stack and system architecture.

[0857] Step 13:

[0858] Users can obtain reference information for their own system design based on the displayed technology stack and system architecture.

[0859] Example 1

[0860] 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."

[0861] In modern system development, selecting a technology stack and system architecture is a critical and complex process. Developers, from beginners to professionals, spend a lot of time and effort selecting the optimal technology configuration. However, making the optimal selection requires specialized knowledge, and a lack of it can reduce the project's success rate. Furthermore, incorrect technology selection can significantly increase development costs and time. Therefore, there is a need for a system that allows users to easily and quickly select the optimal technology configuration and system architecture.

[0862] 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.

[0863] In this invention, the server includes: means for accepting user-input requirements; an artificial intelligence model for analyzing the accepted user-input requirements and generating an optimal technical configuration and system architecture; means for converting the user-input requirements into JSON format and sending it to the server as an HTTP POST request; means for the server to analyze the requirements, extract requirement data, and pass it to the artificial intelligence model; means for the artificial intelligence model to generate an optimal technical configuration and system architecture based on a past dataset; means for converting the generated information on the technical configuration and system architecture into JSON format and returning it from the server to the terminal; and means for the terminal to analyze the received data and display the results on a user interface. This enables a user to quickly and easily receive an optimal technical configuration and system architecture based on specific requirements.

[0864] "User-input requirements" are functions and conditions that a user specifically desires for the system, entered in text format.

[0865] "JSON format" is an abbreviation for JavaScript Object Notation, and is a lightweight data exchange format that represents data as attribute-value pairs.

[0866] An "HTTP POST request" is a type of HTTP protocol used to send data from a web browser or client to a server.

[0867] A "server" is a computer system that provides services over a network, and in this invention, plays a central role in receiving and analyzing requirements, and transmitting and receiving data.

[0868] An "artificial intelligence model" is a model trained by machine learning algorithms that has the ability to analyze user requirements and generate optimal technology stacks and system architectures.

[0869] A "technical configuration" is a combination of technical elements required to build a system, including frameworks, libraries, databases, etc.

[0870] "System architecture" defines the overall configuration of a system and is a concept that clarifies the interactions between components and design policies.

[0871] The "user interface" refers to a screen or operating means that is directly used by the user, and in this invention, it is a means for displaying the analysis results and allowing the user to confirm the results.

[0872] The present invention is a system that automatically generates and presents optimal technology stacks and system architectures based on specific requirements entered by a user. The system consists of major components such as terminals, servers, artificial intelligence models, and databases.

[0873] The terminal provides a user interface for users to input requirements and display the results. Specifically, it is built using modern JavaScript frameworks such as React.js or Vue.js. Users access the system through a web browser and input specific requirements (e.g., "E-commerce site for startups"). Once input is complete, users click the "Submit" button to send the requirements to the system.

[0874] The terminal converts the input requirements into JSON format and sends it as an HTTP POST request to the backend server. The server receives this HTTP POST request. The server is built using frameworks such as Node.js or Django, analyzes the request, extracts the requirements data, and passes it to the artificial intelligence model.

[0875] The artificial intelligence model is trained based on historical datasets and generates the technology stack and system architecture that best suits the user's requirements. The model is built using TensorFlow and PyTorch. For example, if a user enters the requirement "e-commerce site for startups," the model will recommend React.js, Node.js, MongoDB, and AWS.

[0876] The generated technology stack and system architecture information is converted back to JSON format and sent back to the terminal as an HTTP response from the server. The terminal analyzes this data and displays the results in the user interface. The user can then review the presented technology stack and system architecture and use it in their own system design.

[0877] For example, if the user enters the prompt text:

[0878] Example prompt sentence:

[0879] "E-commerce site for startups"

[0880] In response, the AI ​​model suggests the following optimal technology stack and system architecture:

[0881] Tech stack: React.js, Node.js, MongoDB, cloud services

[0882] System Architecture: Microservices Architecture

[0883] This allows users to quickly obtain reference information for specific technology selection and system construction. This system significantly streamlines users' technology selection and design processes, contributing to saving time and resources.

[0884] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0885] Step 1:

[0886] User enters requirements

[0887] Specific behavior:

[0888] Users access the system's front end using a web browser and fill out a requirements form to enter specific project requirements, such as "e-commerce site for startups."

[0889] input:

[0890] User requirements such as "E-commerce site for startups"

[0891] output:

[0892] Requirement data entry completed

[0893] Step 2:

[0894] The device sends its requirements to the server

[0895] Specific behavior:

[0896] When the user clicks the "Submit" button, the terminal (front end) converts the entered requirements into JSON format and sends it to the back end server as an HTTP POST request.

[0897] input:

[0898] Requirement Data

[0899] output:

[0900] An HTTP POST request containing the requirements data in JSON format

[0901] Step 3:

[0902] The server analyzes the requirements

[0903] Specific behavior:

[0904] The server analyzes the received HTTP POST request and extracts the requirements data (e.g., "E-commerce site for startups") from it.

[0905] input:

[0906] Requirements data in JSON format in an HTTP POST request

[0907] output:

[0908] Analyzed requirements data

[0909] Step 4:

[0910] The server passes the requirements data to the artificial intelligence model

[0911] Specific behavior:

[0912] In order to pass the analyzed requirements data to the artificial intelligence model, the server converts the format of the data as necessary and inputs it to the artificial intelligence model.

[0913] input:

[0914] Analyzed requirements data

[0915] output:

[0916] Requirements data in a format that can be read by artificial intelligence models

[0917] Step 5:

[0918] Artificial intelligence models generate optimal technology stacks and system architectures

[0919] Specific behavior:

[0920] Artificial intelligence models (using TensorFlow and PyTorch) utilize algorithms that learn from historical datasets to generate a technology stack and system architecture that best suits the user's requirements.

[0921] input:

[0922] Requirements data fed into an artificial intelligence model

[0923] output:

[0924] Generated technology stack and system architecture information

[0925] Step 6:

[0926] The server returns the generated results to the device.

[0927] Specific behavior:

[0928] The server converts the technology stack and system architecture information generated by the artificial intelligence model into JSON format and returns it to the terminal as an HTTP response.

[0929] input:

[0930] Generated technology stack and system architecture information

[0931] output:

[0932] HTTP response containing technology stack and system architecture information in JSON format

[0933] Step 7:

[0934] The terminal displays the results

[0935] Specific behavior:

[0936] The terminal parses the received JSON data and displays it in the user interface in an appropriate format, for example, "The recommended technology stack is React.js, Node.js, MongoDB, and AWS."

[0937] input:

[0938] Technical stack and system architecture information received as an HTTP response in JSON format

[0939] output:

[0940] Technology stack and system architecture information displayed in the user interface

[0941] This allows users to quickly obtain reference information for specific technology selection and system construction.

[0942] (Application example 1)

[0943] 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."

[0944] In recent years, demand for content distribution services has been increasing, and audio and video distribution using smart devices in particular has been rapidly expanding. However, launching these services requires selecting the optimal technology stack and system architecture, which can be difficult for users lacking technical knowledge. For this reason, there is a need for a system that allows users to easily select the optimal technology configuration and system architecture.

[0945] 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.

[0946] In this invention, the server includes means for accepting user-input requirements, artificial intelligence model means for analyzing the accepted user-input requirements and generating an appropriate technical configuration and system architecture, means for presenting the generated technical configuration and system architecture to the user, means for analyzing the user-input requirements related to content distribution and presenting an optimal technical stack and system architecture, and means for displaying the generated technical configuration and system architecture using a smart device, thereby enabling the user to easily select and use the optimal technology stack and system architecture.

[0947] - "User-input requirements" are specific requirements that users of the system input as settings or desired conditions.

[0948] An "artificial intelligence model" is an algorithm that uses technologies such as machine learning and deep learning to analyze data and make predictions and classifications.

[0949] "Technical configuration" refers to the combination of software and hardware required to realize a system.

[0950] "System architecture" is the design of the overall structure of a system and the interactions between its components.

[0951] "Analysis means" is a means for generating an appropriate technical configuration or system architecture based on user-input requirements.

[0952] A "technology stack" is a collection of technologies used to build a system or application.

[0953] A "smart device" is an electronic device that can connect to the Internet and has advanced functions.

[0954] "Content distribution" refers to the provision of digital content such as audio, video, and text to users via the Internet.

[0955] The "means for presenting to the user" refers to a means for providing the generated technical configuration and system architecture to the user.

[0956] This invention is a system that suggests appropriate technology stacks and system architectures based on specific requirements input by the user. The system mainly consists of the following elements:

[0957] 1. Frontend (terminal):

[0958] The terminal provides an interface for users to input requirements and check the results. This interface runs on smart devices such as smartphones and is built using frameworks such as React Native.

[0959] 2. Backend (server):

[0960] The server receives user requirements and uses artificial intelligence models to generate the optimal technology stack and system architecture for those requirements. This backend is built using frameworks such as Flask (Python).

[0961] 3. Database:

[0962] The database stores information about the technology stack and system architecture, and uses databases such as Firebase and DynamoDB.

[0963] 4. Artificial Intelligence Model:

[0964] The artificial intelligence model is built using machine learning techniques such as TensorFlow and trained based on historical datasets. The model analyzes user requirements and generates the optimal technology stack and system architecture.

[0965] Specific examples:

[0966] A user launches the smartphone app and inputs requirements, such as "Build a new video distribution platform." When the user clicks the "Submit" button, the device converts the input requirements into JSON format and sends it as an HTTP POST request to the backend server.

[0967] The server receives the requirements and begins analysis. The received requirements are passed to an artificial intelligence model, which generates the optimal technology stack (e.g., React Native, Node.js, Firebase) and system architecture based on historical data sets. The generated information is sent back from the server to the device and displayed in the user interface.

[0968] Users can review the proposed technology stack and system architecture and base their system design on it.

[0969] Example prompt sentence:

[0970] "Building a social media service for casual games"

[0971] This allows users to quickly obtain information on the optimal technology stack and system architecture, significantly reducing development time and effort.

[0972] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0973] Step 1:

[0974] The user launches the smartphone app, inputs their requirements, for example, "Build a new video distribution platform," and presses the submit button. The input requirements are saved on the device.

[0975] Step 2:

[0976] The terminal converts the requirements entered by the user into JSON format, converts the requirements text into the appropriate data format, and creates an HTTP POST request that includes the requirements data.

[0977] Step 3:

[0978] The terminal sends the created HTTP POST request to the backend server, which receives the request and includes the requirement data.

[0979] Step 4:

[0980] The server analyzes the received requirements data. First, it extracts the requirements data and converts it into an appropriate data format. Then, it passes the extracted requirements data to the artificial intelligence model.

[0981] Step 5:

[0982] The server-based artificial intelligence model analyzes the input requirements data using algorithms trained on past data sets, generating the optimal technology stack (e.g., React Native, Node.js, Firebase) and system architecture.

[0983] Step 6:

[0984] The server takes the technology stack and system architecture information generated by the AI ​​model, converts it into JSON format, and then creates the data to send back to the device as an HTTP response.

[0985] Step 7:

[0986] The terminal analyzes the response data received from the server and displays the analyzed data on a user interface to present the user with information about the technology stack and system architecture.

[0987] Step 8:

[0988] Users can review the presented technology stack and system architecture and use it to help with actual system design and development. For example, they can take concrete action based on a proposal such as "adopting a microservices architecture with React Native, Node.js, and Firebase."

[0989] 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.

[0990] The present invention relates to a system that proposes an appropriate technology stack or system architecture based on specific requirements input by a user, and further combines it with an emotion engine that recognizes the user's emotions. The system includes means for accepting user-input requirements, artificial intelligence model means for analyzing the accepted requirements, means for presenting the generated technology configuration or system architecture to the user, and an emotion engine that recognizes the user's emotions.

[0991] 1. System Configuration

[0992] The system includes the following major components:

[0993] 1. Front end (terminal)

[0994] It provides a web interface for users to input requirements and view results and sentiment analysis results, and is built using modern JavaScript frameworks such as React.js and Vue.js.

[0995] 2. Backend (server)

[0996] It receives user requirements and sentiment data, analyzes them using artificial intelligence models and sentiment engines, and generates results. It is built using frameworks such as Node.js and Django.

[0997] 3. Database

[0998] It is used to store information about the technology stack and system architecture, as well as sentiment data. It uses a relational database such as PostgreSQL.

[0999] 4. Artificial Intelligence Models

[1000] It includes machine learning models to analyze user requirements and generate the appropriate technology stack and system architecture, and is built using TensorFlow and PyTorch.

[1001] 5. Emotion Engine

[1002] Recognize user emotions and incorporate them into input requirements and generated suggestions. Use machine learning models to analyze user input emotional data to help propose more accurate technology stacks and system architectures.

[1003] 2. Program Processing Overview

[1004] In this system, when a user inputs specific requirements through a web interface, the system analyzes the requirements and suggests appropriate technology stacks and system architectures. The system also analyzes the user's emotional data associated with the input requirements and reflects it in the proposal results.

[1005] User enters requirements:

[1006] A user accesses the system through a web browser and inputs a specific requirement (e.g., "E-commerce site for startups"). Once the user has completed the input, they click the "Submit" button, which sends the requirement along with the emotion data to the system.

[1007] The device sends requirements and emotion data:

[1008] When the user clicks the send button, the terminal converts the input requirements and emotion data into JSON format and sends it to the backend server as an HTTP POST request.

[1009] The server parses the requirements and sentiment data:

[1010] The server analyzes the received request and extracts requirement data and emotion data, then passes the requirement data to an artificial intelligence model and the emotion data to an emotion engine for analysis.

[1011] Artificial intelligence models and emotion engines generate the optimal tech stack:

[1012] The artificial intelligence model is trained based on historical datasets to generate a technology stack and system architecture that best suits the user's requirements, and the emotion engine analyzes the user's emotion data and takes into account the user's reaction to the generated technology stack and system architecture.

[1013] The server returns the generated result:

[1014] The server converts the technology stack and system architecture information generated by the AI ​​model and emotion engine into JSON format and returns it to the terminal as an HTTP response.

[1015] The terminal will display the result:

[1016] The device analyzes the received data and displays the results in a user interface, where the user can see the proposed technology stack and system architecture, as well as the sentiment analysis results that accompany the proposal.

[1017] Specific examples

[1018] For example, if a user inputs a requirement "E-commerce site for startups" and indicates positive sentiment towards the input, the system will receive this requirement and use artificial intelligence models to generate the optimal technology stack (e.g., React.js, Node.js, MongoDB, AWS) and system architecture (e.g., microservices architecture). The sentiment engine also analyzes how the user feels about the proposed technologies, and as a result, can provide the most attractive proposal for the user.

[1019] As described above, the system of the present invention quickly presents appropriate technical configurations and system architectures in response to diverse user requirements, and furthermore, reflects the user's feelings, thereby greatly contributing to users' technology selection and design.

[1020] The processing flow will be explained below.

[1021] Step 1:

[1022] A user opens a web browser and accesses a web application on the system.

[1023] Step 2:

[1024] The user fills in a given form with their specific requirements (e.g., "e-commerce site for startups").

[1025] Step 3:

[1026] The user clicks the submit button on the form, which triggers the processing of the entered requirements and sentiment data.

[1027] Step 4:

[1028] The device converts the user input requirements into JSON format, and the emotion data is converted as well, and constructed as the body of the HTTP POST request.

[1029] Step 5:

[1030] The device sends an HTTP POST request to the backend server, which includes the user's input requirements and emotion data.

[1031] Step 6:

[1032] The server receives an HTTP POST request from the device and extracts user input requirement data and emotion data from the request body.

[1033] Step 7:

[1034] The server passes the extracted requirements data to an artificial intelligence model, which takes the requirements data as input and generates the optimal technology stack and system architecture.

[1035] Step 8:

[1036] The server passes the extracted emotion data to the emotion engine, which analyzes the emotion data and identifies the user's emotional state.

[1037] Step 9:

[1038] The emotion engine feeds the analysis results back into the artificial intelligence model, which then reflects them in optimizing the technology stack and system architecture.

[1039] Step 10:

[1040] The artificial intelligence model sends optimized technology stack and system architecture information back to the server.

[1041] Step 11:

[1042] The server converts the output of the AI ​​model and the analysis results of the emotion engine into JSON format, and the converted data is constructed as an HTTP response.

[1043] Step 12:

[1044] The server sends an HTTP response back to the device, which includes the generated technology stack and system architecture information, as well as the sentiment analysis results.

[1045] Step 13:

[1046] The device analyzes the HTTP response received from the server, extracting the generated technology stack and system architecture information and sentiment analysis results from the response body.

[1047] Step 14:

[1048] The device displays the extracted data in a user interface, where the user can view the presented technology stack, system architecture, and sentiment analysis results.

[1049] Step 15:

[1050] Users can obtain reference information for their own system design based on the displayed technology stack, system architecture, and sentiment analysis results.

[1051] Example 2

[1052] 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."

[1053] Conventional systems have limited means of providing appropriate technical configurations and system architectures for user-input requirements, making it difficult to flexibly respond to specific user requirements. Furthermore, proposals do not reflect the user's emotions, resulting in reduced user satisfaction and applicability. Therefore, there is a need for a novel system that can present system configurations that consider not only the user's input requirements but also their emotions.

[1054] 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.

[1055] In this invention, the server includes means for accepting user-input requirements, artificial intelligence model means for analyzing the accepted user-input requirements and generating an appropriate technical configuration and system architecture, means for presenting the generated technical configuration and system architecture to the user, and emotion recognition means for recognizing the user's emotions and reflecting them in the user-input requirements and the generated proposal, thereby enabling the proposal of a more personalized technical configuration and system architecture that takes into account not only the user's requirements but also their emotions.

[1056] "User input requirements" are information that specifically describes the user's requests and wishes for the system.

[1057] "Analysis means" refers to a function or device that processes input data and extracts useful information.

[1058] A "technical configuration" is a combination of technical elements or technologies used to achieve specific requirements or objectives.

[1059] "System architecture" is a representation of the interrelationships and structure of the elements that make up a system.

[1060] An "artificial intelligence model" is an algorithm or mathematical model designed to perform a specific task using techniques such as machine learning and deep learning.

[1061] "Emotion recognition means" is a function or device for analyzing a user's input or behavior and determining the user's emotional state.

[1062] A "dataset" is a set of data used to train and evaluate machine learning models.

[1063] The "means for proposing" is a function or device for presenting the optimal technical configuration or system architecture to the user based on the analysis results.

[1064] "User interface" refers to the input and output means and methods by which a user interacts with a system.

[1065] MODE FOR CARRYING OUT THE INVENTION

[1066] The present invention relates to a system that presents appropriate technical configurations and system architectures based on specific requirements input by a user, and further combines this with an emotion engine that recognizes the user's emotions. The system includes means for accepting user-input requirements, artificial intelligence model means for analyzing the accepted requirements, means for presenting the generated technical configurations and system architectures to the user, and an emotion engine that recognizes the user's emotions.

[1067] System Configuration

[1068] The system includes the following major components:

[1069] 1. Front end (terminal)

[1070] The terminal provides a web interface for users to input requirements and view results and sentiment analysis results. Specifically, it is built using modern JavaScript frameworks (e.g., React.js, Vue.js), allowing users to easily input and submit requirements using a dynamic and intuitive interface.

[1071] 2. Backend (server)

[1072] The server receives user requirements and emotion data, analyzes it using an artificial intelligence model and emotion engine, and generates results. It is built using a common backend framework (e.g., Node.js, Django). The server analyzes the received data, extracts requirement data and emotion data, and passes them to the appropriate means.

[1073] 3. Database

[1074] The database is used to store technical configuration and system architecture information, as well as sentiment data. A relational database (e.g., PostgreSQL) allows for efficient data management and querying.

[1075] 4. Artificial Intelligence Models

[1076] The artificial intelligence model analyzes user requirements and uses machine learning models to generate appropriate technology configurations and system architectures. It is built using TensorFlow and PyTorch and trained based on past datasets. This model generates the technology stack and system architecture that best suits the user's requirements.

[1077] 5. Emotion Engine

[1078] The emotion engine recognizes user emotions and reflects them in input requirements and generated suggestions. It uses machine learning models to analyze user input emotion data and determine the user's emotional state from their responses and behaviors, enabling more accurate and user-specific technical suggestions.

[1079] Specific examples

[1080] For example, if a user inputs a requirement "E-commerce site for startups" and indicates positive sentiment towards the input, the system will receive this requirement and use artificial intelligence models to generate the optimal technology stack (e.g., React.js, Node.js, MongoDB, AWS) and system architecture (e.g., microservices architecture). The sentiment engine also analyzes how the user feels about the proposed technologies, resulting in the most attractive proposal for the user.

[1081] Prompt Sentence Examples

[1082] Examples of specific prompts that users can input into a generative AI model include the following:

[1083] "Please suggest a compatible tech stack. The requirement is for an e-commerce website for a startup, and future scalability is important."

[1084] The above is a specific embodiment for carrying out the present invention.

[1085] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1086] Step 1:

[1087] User enters requirements

[1088] A user accesses a web interface and inputs specific requirements. After entering the requirements in the input fields, the user clicks the "Submit" button. A specific prompt statement (e.g., "E-commerce site for startups") is used as input. Based on this input, requirement data is generated.

[1089] Step 2:

[1090] The device sends requirements and emotion data

[1091] The device converts the requirements entered by the user along with emotional data (inferred from keyboard typing speed, mouse movements, etc.) into JSON format. The converted data is sent to the server as an HTTP POST request. The input includes the requirements data and emotional data, and the output is JSON format data. The specific operations performed by the device include formatting the data and sending the HTTP request.

[1092] Step 3:

[1093] The server analyzes the requirements and sentiment data

[1094] The server parses the received JSON data and extracts requirement data and emotion data. This analysis passes the requirement data to an artificial intelligence model and the emotion data to an emotion engine. The input contains JSON data, and the output is the parsed requirement data and emotion data. Specific operations performed by the server include data parsing and data sorting.

[1095] Step 4:

[1096] Artificial intelligence model generates optimal tech stack

[1097] The artificial intelligence model analyzes the requirements data based on past datasets and generates the optimal technology stack. The machine learning frameworks used here include TensorFlow and PyTorch. The input includes the requirements data, and the output is the optimal technology stack and system architecture. The specific operation is to execute the inference process of the machine learning model.

[1098] Step 5:

[1099] The emotion engine analyzes the emotion data

[1100] The emotion engine analyzes user emotional data and applies the results to the technology stack and system architecture. The input includes emotional data, and the output is an evaluation result based on the emotional state. Specific operations include the execution of emotion analysis algorithms.

[1101] Step 6:

[1102] The server returns the generated results

[1103] The server converts the technology stack and system architecture information generated by the AI ​​model and emotion engine into JSON format and returns it to the terminal as an HTTP response. The input includes the generated technology stack and emotion evaluation results, and the output is JSON format data. Specific operations include formatting the data and sending the HTTP response.

[1104] Step 7:

[1105] The terminal displays the results

[1106] The terminal parses the received JSON data and displays the technology stack, system architecture, and sentiment analysis results on a user interface. The input contains JSON data, and the output provides an intuitive user interface. Specific operations include parsing the data and dynamically generating HTML.

[1107] The above is the flow of each processing step of the system.

[1108] (Application example 2)

[1109] 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."

[1110] Current proposal systems with technical configurations and system architectures make proposals without considering the user's emotions, resulting in a poor user experience. Furthermore, they are unable to appropriately control other systems or devices based on the user's emotions, resulting in a lack of responsiveness and ease of use in certain situations. Therefore, there is a need to provide systems that better suit the user's needs by analyzing the user's emotions and reflecting them in proposal results and system control.

[1111] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for accepting user-input requirements, artificial intelligence model means for analyzing the accepted user-input requirements and generating an appropriate technical configuration and system architecture, means for presenting the generated technical configuration and system architecture to the user, emotion recognition means for recognizing the user's emotions and reflecting them in the analysis results, and means for controlling other systems and devices based on the emotion recognition data. By taking emotion data into consideration when analyzing the user's input requirements, it is possible to propose more appropriate and attractive technology stacks and system architectures. Furthermore, by appropriately controlling other systems and devices, such as autonomous vehicles and entertainment providers, based on the emotion recognition data, responsiveness and ease of use can be improved.

[1112] "Means for accepting user input requirements" refers to an interface or device that the system uses to receive specific conditions or requests input by the user.

[1113] "Artificial intelligence model means" refers to a machine learning algorithm or model for analyzing received user input requirements and generating an appropriate technical configuration or system architecture based thereon.

[1114] "Means for presenting the generated technical configuration and system architecture to the user" refers to an interface or device for visually or audibly providing the user with the technical configuration and system architecture generated as a result of the analysis.

[1115] "Emotion recognition means" refers to technology or devices that recognize a user's emotions and reflect them in the analysis results. Specifically, this includes facial expression recognition and voice analysis.

[1116] "Means for controlling other systems or devices" refers to technologies or devices for appropriately controlling multiple systems or devices, such as autonomous vehicles or entertainment systems, based on recognized emotion data.

[1117] A "technology configuration" is the combination of tools and platforms used to implement a system or application, including, for example, a specific programming language, framework, database, etc.

[1118] "System architecture" refers to the basic framework or structure for the overall system configuration and design. Specifically, it includes microservice architecture and monolithic architecture.

[1119] "Emotion Recognition Data" means data about a user's emotions collected and analyzed by the emotion recognition means, which is used to improve the accuracy of suggestions and for system control.

[1120] This invention relates to a system installed in an autonomous vehicle that analyzes user input requirements and emotions, generates and presents appropriate technical configurations and system architectures based on the analysis, and controls the operation of the vehicle and related systems. To realize this system, the following programs and processing procedures are executed.

[1121] System Configuration

[1122] This system is broadly composed of the following main components:

[1123] 1. Front end (terminal)

[1124] Provide an interface for passengers to interact with the system. Specifically, a smartphone application is used. The application provides a UI for passenger input and displaying emotion recognition results. Modern JavaScript frameworks (e.g., React.js, Vue.js) are used.

[1125] 2. Backend (server)

[1126] The system receives passenger requirements and emotion data, analyzes them with artificial intelligence models and emotion engines, and generates results using server-side frameworks such as Node.js and Django. The back-end server also communicates with the autonomous vehicle and related systems.

[1127] 3. Database

[1128] Manage and store information on technical configuration and system architecture, as well as emotional data, using a relational database such as PostgreSQL.

[1129] 4. Artificial Intelligence Models

[1130] Use machine learning models to analyze passenger requirements and generate the appropriate technical configuration and system architecture, using pre-trained models based on historical datasets using TensorFlow and PyTorch.

[1131] 5. Emotion recognition means

[1132] The system recognizes passenger emotions and uses the data for analysis. It uses the smartphone's camera and microphone to perform facial expression recognition and voice analysis. Specifically, it uses toolkits such as OpenCV and TensorFlow.

[1133] 6. Means of Controlling Other Systems or Devices

[1134] Based on the recognized emotion data, autonomous vehicles and entertainment systems can be controlled, for example, by adjusting the vehicle's driving mode or the in-car environment (music, temperature, etc.) according to a specific emotion.

[1135] Program processing description

[1136] This system is constructed from a smartphone, a server, a database, an artificial intelligence model, and an emotion recognition engine. Below are specific examples of data processing and data calculation using each hardware and software.

[1137] Hardware and Software Use

[1138] Smartphone: Used to capture passengers' facial expressions and voices and generate emotion data. Uses OpenCV and the smartphone's camera and microphone.

[1139] Server: Performs data analysis and management. Uses Node.js and Django to process data and respond in real time.

[1140] Database: Stores emotion data and technical configuration information. Uses PostgreSQL.

[1141] Artificial intelligence model: Using TensorFlow or PyTorch, it suggests the best system based on passenger requirements and historical data.

[1142] Emotion Recognition Engine: Uses OpenCV and TensorFlow to recognize user emotions from captured images and audio.

[1143] Specific examples

[1144] 1. Emotion analysis: Passengers launch a smartphone application and capture emotional data through the camera and microphone. For example, if a passenger smiles, the emotion recognition engine classifies it as "happy."

[1145] 2. Driving mode adjustment: Emotion data is sent to the server, and the "happy" emotion is detected. Based on this information, the server sets the car's autonomous driving mode to "eco."

[1146] 3. Entertainment provision: The server receives the emotion data and transmits it to the entertainment system. For example, it selects a pop music playlist that best suits the emotion "happy" and starts playing it.

[1147] Prompt Sentence Examples

[1148] "If a passenger indicates a smile through facial recognition, set the vehicle's driving mode to eco-friendly Eco mode and play an upbeat pop music playlist."

[1149] The above-described embodiments of the present invention enable the proposal of flexible and appropriate technical configurations and system architectures according to the requirements and emotions of users. Furthermore, the quality of the user experience can be improved by controlling the operation of related systems in real time.

[1150] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1151] Step 1:

[1152] A user launches a smartphone application and enters their passenger requirements. These requirements include specific conditions and preferences. The input is in text format and is displayed in the application's user interface. This input data is then sent to subsequent processing steps.

[1153] Step 2:

[1154] The terminal receives the user's input requirements, converts them into JSON format, and sends them as an HTTP POST request to the backend server, where the input data is sent through a network protocol to the server and received for analysis.

[1155] Step 3:

[1156] The server receives the request and extracts the user's requirements data. This data is passed to an artificial intelligence model that uses TensorFlow or PyTorch to generate the appropriate technical configuration and system architecture.

[1157] Step 4:

[1158] The server uses emotion recognition to analyze emotion data acquired in real time from the smartphone's camera and microphone. Here, OpenCV and voice analysis technology are used to classify the emotion data. As a result, emotion labels such as "happy" and "sad" are obtained.

[1159] Step 5:

[1160] The server integrates the technical configuration and system architecture generated by the AI ​​model with the emotion data obtained by the emotion recognition means. The server then compiles the analysis results and creates data to provide to the user.

[1161] Step 6:

[1162] The server converts the integrated result data into JSON format and sends it to the terminal as an HTTP response, where the data is returned from the server to the terminal.

[1163] Step 7:

[1164] Based on the received data, the device displays the analysis results and technical proposals on the user interface. The user can check these results. Specifically, the technology stack and system architecture are illustrated on the screen.

[1165] Step 8:

[1166] The device then generates instructions for controlling the autonomous vehicle and related systems based on the emotion data and sends them to a server, which determines the driving mode and entertainment content according to the emotion.

[1167] Step 9:

[1168] The server receives these instructions and calls the appropriate APIs to control the autonomous vehicle's driving mode and entertainment system. For example, if the passenger is recognized as "happy," it can set the vehicle's driving mode to "eco" and play a pop music playlist.

[1169] Step 10:

[1170] The end result is an in-car environment that matches the user's emotions, which the system monitors in real time and adjusts as needed, ensuring a comfortable riding experience for passengers.

[1171] 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.

[1172] 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.

[1173] 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.

[1174] [Fourth embodiment]

[1175] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1176] 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.

[1177] 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).

[1178] 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.

[1179] 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.

[1180] 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).

[1181] 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.

[1182] 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.

[1183] 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.

[1184] 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.

[1185] 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.

[1186] 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.

[1187] 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."

[1188] The present invention relates to a system for suggesting an appropriate technology stack or system architecture based on specific requirements input by a user, the system including means for accepting user-input requirements, artificial intelligence model means for analyzing the accepted requirements, and means for presenting the generated technology stack or system architecture to the user.

[1189] 1. System Configuration

[1190] The system includes the following major components:

[1191] 1. Front end (terminal)

[1192] It provides a web interface for users to enter requirements and view results, and is built using modern JavaScript frameworks such as React.js and Vue.js.

[1193] 2. Backend (server)

[1194] It receives user requirements and uses artificial intelligence models to generate the optimal technology stack and system architecture for those requirements, built using frameworks such as Node.js and Django.

[1195] 3. Database

[1196] It is used to store information about technology stacks and system architectures. It uses a relational database such as PostgreSQL.

[1197] 4. Artificial Intelligence Models

[1198] It includes machine learning models to analyze user requirements and generate the appropriate technology stack and system architecture, and is built using TensorFlow and PyTorch.

[1199] 2. Program Processing Overview

[1200] The system allows users to input specific requirements through a web interface, analyzes those requirements, and suggests appropriate technology stacks and system architectures.

[1201] User enters requirements:

[1202] A user accesses the system through a web browser and enters a specific requirement (e.g., "E-commerce site for startups"), and once the user has completed the entry, they click the "Submit" button to send the requirement to the system.

[1203] The device sends its requirements to the server:

[1204] When the user clicks the submit button, the terminal converts the entered requirements into JSON format and sends it to the backend server as an HTTP POST request.

[1205] The server parses the requirements:

[1206] The server analyzes the received request and extracts the requirements data, which is then passed to the artificial intelligence model.

[1207] Artificial intelligence model generates optimal tech stack:

[1208] Artificial intelligence models are trained based on historical datasets to generate the technology stack and system architecture that best suits the user's requirements.

[1209] The server returns the generated result:

[1210] The server converts the technology stack and system architecture information generated by the artificial intelligence model into JSON format and returns it to the terminal as an HTTP response.

[1211] The terminal will display the result:

[1212] The device analyzes the received data and displays the results on the user interface, allowing users to review the presented technology stack and system architecture and use it to help design their own systems.

[1213] Specific examples

[1214] For example, if a user inputs the requirement "E-commerce site for startups," the system will receive this requirement and use an artificial intelligence model to generate the optimal technology stack (e.g., React.js, Node.js, MongoDB, AWS) and system architecture (e.g., microservices architecture), providing users with reference information for specific technology selection and system construction.

[1215] As described above, the system of the present invention quickly presents appropriate technical configurations and system architectures for a variety of user requirements, greatly contributing to users' technology selection and design.

[1216] The processing flow will be explained below.

[1217] Step 1:

[1218] A user opens a web browser and accesses a web application on the system.

[1219] Step 2:

[1220] The user fills in a given form with their specific requirements (e.g., "e-commerce site for startups").

[1221] Step 3:

[1222] The user clicks the submit button on the form, which triggers the processing of the entered requirements.

[1223] Step 4:

[1224] The terminal converts the user input requirements into JSON format, which is then constructed as the body of the HTTP POST request.

[1225] Step 5:

[1226] The terminal sends an HTTP POST request to the backend server, which includes the user's input requirements.

[1227] Step 6:

[1228] The server receives an HTTP POST request from the terminal and extracts the user input requirement data from the request body.

[1229] Step 7:

[1230] The server passes the extracted requirements data to an artificial intelligence model, which takes the requirements data as input and generates the optimal technology stack and system architecture.

[1231] Step 8:

[1232] The artificial intelligence model generates technology stack and system architecture information that is sent back to the server.

[1233] Step 9:

[1234] The server converts the output of the AI ​​model into JSON format, which is then used to construct an HTTP response.

[1235] Step 10:

[1236] The server sends an HTTP response back to the device, which includes information about the generated technology stack and system architecture.

[1237] Step 11:

[1238] The device analyzes the HTTP response received from the server and extracts the generated technology stack and system architecture information from the response body.

[1239] Step 12:

[1240] The terminal displays the extracted data in a user interface, where the user can review the presented technology stack and system architecture.

[1241] Step 13:

[1242] Users can obtain reference information for their own system design based on the displayed technology stack and system architecture.

[1243] Example 1

[1244] 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."

[1245] In modern system development, selecting a technology stack and system architecture is a critical and complex process. Developers, from beginners to professionals, spend a lot of time and effort selecting the optimal technology configuration. However, making the optimal selection requires specialized knowledge, and a lack of it can reduce the project's success rate. Furthermore, incorrect technology selection can significantly increase development costs and time. Therefore, there is a need for a system that allows users to easily and quickly select the optimal technology configuration and system architecture.

[1246] 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.

[1247] In this invention, the server includes: means for accepting user-input requirements; an artificial intelligence model for analyzing the accepted user-input requirements and generating an optimal technical configuration and system architecture; means for converting the user-input requirements into JSON format and sending it to the server as an HTTP POST request; means for the server to analyze the requirements, extract requirement data, and pass it to the artificial intelligence model; means for the artificial intelligence model to generate an optimal technical configuration and system architecture based on a past dataset; means for converting the generated information on the technical configuration and system architecture into JSON format and returning it from the server to the terminal; and means for the terminal to analyze the received data and display the results on a user interface. This enables a user to quickly and easily receive an optimal technical configuration and system architecture based on specific requirements.

[1248] "User-input requirements" are functions and conditions that a user specifically desires for the system, entered in text format.

[1249] "JSON format" is an abbreviation for JavaScript Object Notation, and is a lightweight data exchange format that represents data as attribute-value pairs.

[1250] An "HTTP POST request" is a type of HTTP protocol used to send data from a web browser or client to a server.

[1251] A "server" is a computer system that provides services over a network, and in the present invention, plays a central role in receiving and analyzing requirements, and transmitting and receiving data.

[1252] An "artificial intelligence model" is a model trained by machine learning algorithms that has the ability to analyze user requirements and generate optimal technology stacks and system architectures.

[1253] A "technical configuration" is a combination of technical elements required to build a system, including frameworks, libraries, databases, etc.

[1254] "System architecture" defines the overall configuration of a system and is a concept that clarifies the interactions between components and design policies.

[1255] The "user interface" refers to a screen or operating means that is directly used by the user, and in this invention, it is a means for displaying the analysis results and allowing the user to confirm the results.

[1256] The present invention is a system that automatically generates and presents optimal technology stacks and system architectures based on specific requirements entered by a user. The system consists of major components such as terminals, servers, artificial intelligence models, and databases.

[1257] The terminal provides a user interface for users to input requirements and display the results. Specifically, it is built using modern JavaScript frameworks such as React.js or Vue.js. Users access the system through a web browser and input specific requirements (e.g., "E-commerce site for startups"). Once input is complete, users click the "Submit" button to send the requirements to the system.

[1258] The terminal converts the input requirements into JSON format and sends it as an HTTP POST request to the backend server. The server receives this HTTP POST request. The server is built using frameworks such as Node.js or Django, analyzes the request, extracts the requirements data, and passes it to the artificial intelligence model.

[1259] The artificial intelligence model is trained based on historical datasets and generates the technology stack and system architecture that best suits the user's requirements. The model is built using TensorFlow and PyTorch. For example, if a user enters the requirement "e-commerce site for startups," the model will recommend React.js, Node.js, MongoDB, and AWS.

[1260] The generated technology stack and system architecture information is converted back to JSON format and sent back to the terminal as an HTTP response from the server. The terminal analyzes this data and displays the results in the user interface. The user can then review the presented technology stack and system architecture and use it in their own system design.

[1261] For example, if the user enters the prompt text:

[1262] Example prompt sentence:

[1263] "E-commerce site for startups"

[1264] In response, the AI ​​model suggests the following optimal technology stack and system architecture:

[1265] Tech stack: React.js, Node.js, MongoDB, cloud services

[1266] System Architecture: Microservices Architecture

[1267] This allows users to quickly obtain reference information for specific technology selection and system construction. This system significantly streamlines users' technology selection and design processes, contributing to saving time and resources.

[1268] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1269] Step 1:

[1270] User enters requirements

[1271] Specific behavior:

[1272] Users access the system's front end using a web browser and fill out a requirements form to enter specific project requirements, such as "e-commerce site for startups."

[1273] input:

[1274] User requirements such as "E-commerce site for startups"

[1275] output:

[1276] Requirement data entry completed

[1277] Step 2:

[1278] The device sends its requirements to the server

[1279] Specific behavior:

[1280] When the user clicks the "Submit" button, the terminal (front end) converts the entered requirements into JSON format and sends it to the back end server as an HTTP POST request.

[1281] input:

[1282] Requirement Data

[1283] output:

[1284] An HTTP POST request containing the requirements data in JSON format

[1285] Step 3:

[1286] The server analyzes the requirements

[1287] Specific behavior:

[1288] The server analyzes the received HTTP POST request and extracts the requirements data (e.g., "E-commerce site for startups") from it.

[1289] input:

[1290] Requirements data in JSON format in an HTTP POST request

[1291] output:

[1292] Analyzed requirements data

[1293] Step 4:

[1294] The server passes the requirements data to the artificial intelligence model

[1295] Specific behavior:

[1296] In order to pass the analyzed requirements data to the artificial intelligence model, the server converts the format of the data as necessary and inputs it to the artificial intelligence model.

[1297] input:

[1298] Analyzed requirements data

[1299] output:

[1300] Requirements data in a format that can be read by artificial intelligence models

[1301] Step 5:

[1302] Artificial intelligence models generate optimal technology stacks and system architectures

[1303] Specific behavior:

[1304] Artificial intelligence models (using TensorFlow and PyTorch) utilize algorithms that learn from historical datasets to generate a technology stack and system architecture that best suits the user's requirements.

[1305] input:

[1306] Requirements data fed into an artificial intelligence model

[1307] output:

[1308] Generated technology stack and system architecture information

[1309] Step 6:

[1310] The server returns the generated results to the device.

[1311] Specific behavior:

[1312] The server converts the technology stack and system architecture information generated by the artificial intelligence model into JSON format and returns it to the terminal as an HTTP response.

[1313] input:

[1314] Generated technology stack and system architecture information

[1315] output:

[1316] HTTP response containing technology stack and system architecture information in JSON format

[1317] Step 7:

[1318] The terminal displays the results

[1319] Specific behavior:

[1320] The terminal parses the received JSON data and displays it in the user interface in an appropriate format, for example, "The recommended technology stack is React.js, Node.js, MongoDB, and AWS."

[1321] input:

[1322] Technical stack and system architecture information received as an HTTP response in JSON format

[1323] output:

[1324] Technology stack and system architecture information displayed in the user interface

[1325] This allows users to quickly obtain reference information for specific technology selection and system construction.

[1326] (Application example 1)

[1327] 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."

[1328] In recent years, demand for content distribution services has been increasing, and audio and video distribution using smart devices in particular has been rapidly expanding. However, launching these services requires selecting the optimal technology stack and system architecture, which can be difficult for users with limited technical knowledge. For this reason, there is a need for a system that allows users to easily select the optimal technology configuration and system architecture.

[1329] 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.

[1330] In this invention, the server includes means for accepting user-input requirements, artificial intelligence model means for analyzing the accepted user-input requirements and generating an appropriate technical configuration and system architecture, means for presenting the generated technical configuration and system architecture to the user, means for analyzing the user-input requirements related to content distribution and presenting an optimal technical stack and system architecture, and means for displaying the generated technical configuration and system architecture using a smart device, thereby enabling the user to easily select and use the optimal technology stack and system architecture.

[1331] - "User-input requirements" are specific requirements that users of the system input as settings or desired conditions.

[1332] An "artificial intelligence model" is an algorithm that uses technologies such as machine learning and deep learning to analyze data and make predictions and classifications.

[1333] "Technical configuration" refers to the combination of software and hardware required to realize a system.

[1334] "System architecture" is the design of the overall structure of a system and the interactions between its components.

[1335] "Analysis means" is a means for generating an appropriate technical configuration or system architecture based on user-input requirements.

[1336] A "technology stack" is a collection of technologies used to build a system or application.

[1337] A "smart device" is an electronic device that can connect to the Internet and has advanced functions.

[1338] "Content distribution" refers to the provision of digital content such as audio, video, and text to users via the Internet.

[1339] The "means for presenting to the user" refers to a means for providing the generated technical configuration and system architecture to the user.

[1340] This invention is a system that suggests appropriate technology stacks and system architectures based on specific requirements input by the user. The system mainly consists of the following elements:

[1341] 1. Frontend (terminal):

[1342] The terminal provides an interface for users to input requirements and check the results. This interface runs on smart devices such as smartphones and is built using frameworks such as React Native.

[1343] 2. Backend (server):

[1344] The server receives user requirements and uses artificial intelligence models to generate the optimal technology stack and system architecture for those requirements. This backend is built using frameworks such as Flask (Python).

[1345] 3. Database:

[1346] The database stores information about the technology stack and system architecture, and uses databases such as Firebase and DynamoDB.

[1347] 4. Artificial Intelligence Model:

[1348] The artificial intelligence model is built using machine learning techniques such as TensorFlow and trained based on historical datasets. The model analyzes user requirements and generates the optimal technology stack and system architecture.

[1349] Specific examples:

[1350] A user launches the smartphone app and inputs requirements, such as "Build a new video distribution platform." When the user clicks the "Submit" button, the device converts the input requirements into JSON format and sends it as an HTTP POST request to the backend server.

[1351] The server receives the requirements and begins analysis. The received requirements are passed to an artificial intelligence model, which generates the optimal technology stack (e.g., React Native, Node.js, Firebase) and system architecture based on historical data sets. The generated information is sent back from the server to the device and displayed on the user interface.

[1352] Users can review the proposed technology stack and system architecture and base their system design on it.

[1353] Example prompt sentence:

[1354] "Building a social media service for casual games"

[1355] This allows users to quickly obtain information on the optimal technology stack and system architecture, significantly reducing development time and effort.

[1356] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1357] Step 1:

[1358] The user launches the smartphone app, inputs their requirements, for example, "Build a new video distribution platform," and presses the submit button. The input requirements are saved on the device.

[1359] Step 2:

[1360] The terminal converts the requirements entered by the user into JSON format, converts the requirements text into the appropriate data format, and creates an HTTP POST request that includes the requirements data.

[1361] Step 3:

[1362] The terminal sends the created HTTP POST request to the backend server, which receives the request and includes the requirement data.

[1363] Step 4:

[1364] The server analyzes the received requirements data. First, it extracts the requirements data and converts it into an appropriate data format. Then, it passes the extracted requirements data to the artificial intelligence model.

[1365] Step 5:

[1366] The server-based artificial intelligence model analyzes the input requirements data using algorithms trained on past data sets, generating the optimal technology stack (e.g., React Native, Node.js, Firebase) and system architecture.

[1367] Step 6:

[1368] The server takes the technology stack and system architecture information generated by the AI ​​model, converts it into JSON format, and then creates the data to send back to the device as an HTTP response.

[1369] Step 7:

[1370] The terminal analyzes the response data received from the server and displays the analyzed data on a user interface to present the user with information about the technology stack and system architecture.

[1371] Step 8:

[1372] Users can review the presented technology stack and system architecture and use it to help with actual system design and development. For example, they can take concrete action based on a proposal such as "adopting a microservices architecture with React Native, Node.js, and Firebase."

[1373] 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.

[1374] The present invention relates to a system that proposes an appropriate technology stack or system architecture based on specific requirements input by a user, and further combines it with an emotion engine that recognizes the user's emotions. The system includes means for accepting user-input requirements, artificial intelligence model means for analyzing the accepted requirements, means for presenting the generated technology configuration or system architecture to the user, and an emotion engine that recognizes the user's emotions.

[1375] 1. System Configuration

[1376] The system includes the following major components:

[1377] 1. Front end (terminal)

[1378] It provides a web interface for users to input requirements and view results and sentiment analysis results, and is built using modern JavaScript frameworks such as React.js and Vue.js.

[1379] 2. Backend (server)

[1380] It receives user requirements and sentiment data, analyzes them using artificial intelligence models and sentiment engines, and generates results. It is built using frameworks such as Node.js and Django.

[1381] 3. Database

[1382] It is used to store information about the technology stack and system architecture, as well as sentiment data. It uses a relational database such as PostgreSQL.

[1383] 4. Artificial Intelligence Models

[1384] It includes machine learning models to analyze user requirements and generate the appropriate technology stack and system architecture, and is built using TensorFlow and PyTorch.

[1385] 5. Emotion Engine

[1386] Recognize user emotions and incorporate them into input requirements and generated suggestions. Use machine learning models to analyze user input emotional data and use it to suggest more accurate technology stacks and system architectures.

[1387] 2. Program Processing Overview

[1388] In this system, when a user inputs specific requirements through a web interface, the system analyzes the requirements and suggests appropriate technology stacks and system architectures. The system also analyzes the user's emotional data associated with the input requirements and reflects it in the proposal results.

[1389] User enters requirements:

[1390] A user accesses the system through a web browser and inputs a specific requirement (e.g., "E-commerce site for startups"). Once the user has completed the input, they click the "Submit" button, which sends the emotion data along with the requirement to the system.

[1391] The device sends requirements and emotion data:

[1392] When the user clicks the send button, the terminal converts the input requirements and emotion data into JSON format and sends it to the backend server as an HTTP POST request.

[1393] The server parses the requirements and sentiment data:

[1394] The server analyzes the received request and extracts requirement data and emotion data, then passes the requirement data to an artificial intelligence model and the emotion data to an emotion engine for analysis.

[1395] Artificial intelligence models and emotion engines generate the optimal tech stack:

[1396] The artificial intelligence model is trained based on historical datasets to generate a technology stack and system architecture that best suits the user's requirements, and the emotion engine analyzes the user's emotion data and takes into account the user's reaction to the generated technology stack and system architecture.

[1397] The server returns the generated result:

[1398] The server converts the technology stack and system architecture information generated by the AI ​​model and emotion engine into JSON format and returns it to the terminal as an HTTP response.

[1399] The terminal will display the result:

[1400] The device analyzes the received data and displays the results in a user interface, where the user can see the proposed technology stack and system architecture, as well as the sentiment analysis results that accompany the proposal.

[1401] Specific examples

[1402] For example, if a user inputs a requirement "E-commerce site for startups" and indicates positive sentiment towards the input, the system will receive this requirement and use artificial intelligence models to generate the optimal technology stack (e.g., React.js, Node.js, MongoDB, AWS) and system architecture (e.g., microservices architecture). The sentiment engine also analyzes how the user feels about the proposed technologies, and as a result, can provide the most attractive proposal for the user.

[1403] As described above, the system of the present invention quickly presents appropriate technical configurations and system architectures in response to diverse user requirements, and furthermore, reflects the user's feelings, thereby greatly contributing to users' technology selection and design.

[1404] The processing flow will be explained below.

[1405] Step 1:

[1406] A user opens a web browser and accesses a web application on the system.

[1407] Step 2:

[1408] The user fills in a given form with their specific requirements (e.g., "e-commerce site for startups").

[1409] Step 3:

[1410] The user clicks the submit button on the form, which triggers the processing of the entered requirements and sentiment data.

[1411] Step 4:

[1412] The device converts the user input requirements into JSON format, and the emotion data is converted as well, and constructed as the body of the HTTP POST request.

[1413] Step 5:

[1414] The device sends an HTTP POST request to the backend server, which includes the user's input requirements and emotion data.

[1415] Step 6:

[1416] The server receives an HTTP POST request from the device and extracts user input requirement data and emotion data from the request body.

[1417] Step 7:

[1418] The server passes the extracted requirements data to an artificial intelligence model, which takes the requirements data as input and generates the optimal technology stack and system architecture.

[1419] Step 8:

[1420] The server passes the extracted emotion data to the emotion engine, which analyzes the emotion data and identifies the user's emotional state.

[1421] Step 9:

[1422] The emotion engine feeds the analysis results back into the artificial intelligence model, which then reflects them in optimizing the technology stack and system architecture.

[1423] Step 10:

[1424] The artificial intelligence model sends optimized technology stack and system architecture information back to the server.

[1425] Step 11:

[1426] The server converts the output of the AI ​​model and the analysis results of the emotion engine into JSON format, and the converted data is constructed as an HTTP response.

[1427] Step 12:

[1428] The server sends an HTTP response back to the device, which includes the generated technology stack and system architecture information, as well as the sentiment analysis results.

[1429] Step 13:

[1430] The device analyzes the HTTP response received from the server, extracting the generated technology stack and system architecture information and sentiment analysis results from the response body.

[1431] Step 14:

[1432] The device displays the extracted data in a user interface, where the user can view the presented technology stack, system architecture, and sentiment analysis results.

[1433] Step 15:

[1434] Users can obtain reference information for their own system design based on the displayed technology stack, system architecture, and sentiment analysis results.

[1435] Example 2

[1436] 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."

[1437] Conventional systems have limited means of providing appropriate technical configurations and system architectures for user-input requirements, making it difficult to flexibly respond to specific user requirements. Furthermore, proposals do not reflect the user's emotions, resulting in reduced user satisfaction and applicability. Therefore, there is a need for a novel system that can present system configurations that consider not only the user's input requirements but also their emotions.

[1438] 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.

[1439] In this invention, the server includes means for accepting user-input requirements, artificial intelligence model means for analyzing the accepted user-input requirements and generating an appropriate technical configuration and system architecture, means for presenting the generated technical configuration and system architecture to the user, and emotion recognition means for recognizing the user's emotions and reflecting them in the user-input requirements and the generated proposal, thereby enabling the proposal of a more personalized technical configuration and system architecture that takes into account not only the user's requirements but also their emotions.

[1440] "User input requirements" are information that specifically describes the user's requests and wishes for the system.

[1441] "Analysis means" refers to a function or device that processes input data and extracts useful information.

[1442] A "technical configuration" is a combination of technical elements or technologies used to achieve specific requirements or objectives.

[1443] "System architecture" is a representation of the interrelationships and structure of the elements that make up a system.

[1444] An "artificial intelligence model" is an algorithm or mathematical model designed to perform a specific task using techniques such as machine learning and deep learning.

[1445] "Emotion recognition means" is a function or device for analyzing a user's input or behavior and determining the user's emotional state.

[1446] A "dataset" is a set of data used to train and evaluate machine learning models.

[1447] The "means for proposing" is a function or device for presenting the optimal technical configuration or system architecture to the user based on the analysis results.

[1448] "User interface" refers to the input and output means and methods by which a user interacts with a system.

[1449] MODE FOR CARRYING OUT THE INVENTION

[1450] The present invention relates to a system that presents appropriate technical configurations and system architectures based on specific requirements input by a user, and further combines this with an emotion engine that recognizes the user's emotions. The system includes means for accepting user-input requirements, artificial intelligence model means for analyzing the accepted requirements, means for presenting the generated technical configurations and system architectures to the user, and an emotion engine that recognizes the user's emotions.

[1451] System Configuration

[1452] The system includes the following major components:

[1453] 1. Front end (terminal)

[1454] The terminal provides a web interface for users to input requirements and view results and sentiment analysis results. Specifically, it is built using modern JavaScript frameworks (e.g., React.js, Vue.js), allowing users to easily input and submit requirements using a dynamic and intuitive interface.

[1455] 2. Backend (server)

[1456] The server receives user requirements and emotion data, analyzes it using an artificial intelligence model and emotion engine, and generates results. It is built using a common backend framework (e.g., Node.js, Django). The server analyzes the received data, extracts requirement data and emotion data, and passes them to the appropriate means.

[1457] 3. Database

[1458] The database is used to store technical configuration and system architecture information, as well as sentiment data. A relational database (e.g., PostgreSQL) allows for efficient data management and querying.

[1459] 4. Artificial Intelligence Models

[1460] The artificial intelligence model analyzes user requirements and uses machine learning models to generate appropriate technology configurations and system architectures. It is built using TensorFlow and PyTorch and trained based on past datasets. This model generates the technology stack and system architecture that best suits the user's requirements.

[1461] 5. Emotion Engine

[1462] The emotion engine recognizes user emotions and reflects them in input requirements and generated suggestions. It uses machine learning models to analyze user input emotion data and determine the user's emotional state from their responses and behaviors, enabling more accurate and user-specific technical suggestions.

[1463] Specific examples

[1464] For example, if a user inputs a requirement "E-commerce site for startups" and indicates positive sentiment towards the input, the system will receive this requirement and use artificial intelligence models to generate the optimal technology stack (e.g., React.js, Node.js, MongoDB, AWS) and system architecture (e.g., microservices architecture). The sentiment engine also analyzes how the user feels about the proposed technologies, resulting in the most attractive proposal for the user.

[1465] Prompt Sentence Examples

[1466] Examples of specific prompts that users can input into a generative AI model include the following:

[1467] "Please suggest a compatible tech stack. The requirement is for an e-commerce website for a startup, and future scalability is important."

[1468] The above is a specific embodiment for carrying out the present invention.

[1469] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1470] Step 1:

[1471] User enters requirements

[1472] A user accesses a web interface and inputs specific requirements. After entering the requirements in the input fields, the user clicks the "Submit" button. A specific prompt statement (e.g., "E-commerce site for startups") is used as input. Based on this input, requirement data is generated.

[1473] Step 2:

[1474] The device sends requirements and emotion data

[1475] The device converts the requirements entered by the user along with emotional data (inferred from keyboard typing speed, mouse movements, etc.) into JSON format. The converted data is sent to the server as an HTTP POST request. The input includes the requirements data and emotional data, and the output is JSON format data. The specific operations performed by the device include formatting the data and sending the HTTP request.

[1476] Step 3:

[1477] The server analyzes the requirements and sentiment data

[1478] The server parses the received JSON data and extracts requirement data and emotion data. This analysis passes the requirement data to an artificial intelligence model and the emotion data to an emotion engine. The input contains JSON data, and the output is the parsed requirement data and emotion data. Specific operations performed by the server include data parsing and data sorting.

[1479] Step 4:

[1480] Artificial intelligence model generates optimal tech stack

[1481] The artificial intelligence model analyzes the requirements data based on past datasets and generates the optimal technology stack. The machine learning frameworks used here include TensorFlow and PyTorch. The input includes the requirements data, and the output is the optimal technology stack and system architecture. The specific operation is to execute the inference process of the machine learning model.

[1482] Step 5:

[1483] The emotion engine analyzes the emotion data

[1484] The emotion engine analyzes user emotional data and applies the results to the technology stack and system architecture. The input includes emotional data, and the output is an evaluation result based on the emotional state. Specific operations include the execution of emotion analysis algorithms.

[1485] Step 6:

[1486] The server returns the generated results

[1487] The server converts the technology stack and system architecture information generated by the AI ​​model and emotion engine into JSON format and returns it to the terminal as an HTTP response. The input includes the generated technology stack and emotion evaluation results, and the output is JSON format data. Specific operations include formatting the data and sending the HTTP response.

[1488] Step 7:

[1489] The terminal displays the results

[1490] The terminal parses the received JSON data and displays the technology stack, system architecture, and sentiment analysis results on a user interface. The input contains JSON data, and the output provides an intuitive user interface. Specific operations include parsing the data and dynamically generating HTML.

[1491] The above is the flow of each processing step of the system.

[1492] (Application example 2)

[1493] 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."

[1494] Current proposal systems with technical configurations and system architectures make proposals without considering the user's emotions, resulting in a poor user experience. Furthermore, they are unable to appropriately control other systems or devices based on the user's emotions, resulting in a lack of responsiveness and ease of use in certain situations. Therefore, there is a need to provide systems that better suit the user's needs by analyzing the user's emotions and reflecting them in proposal results and system control.

[1495] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for accepting user-input requirements, artificial intelligence model means for analyzing the accepted user-input requirements and generating an appropriate technical configuration and system architecture, means for presenting the generated technical configuration and system architecture to the user, emotion recognition means for recognizing the user's emotions and reflecting them in the analysis results, and means for controlling other systems and devices based on the emotion recognition data. By taking emotion data into consideration when analyzing the user's input requirements, it is possible to propose more appropriate and attractive technology stacks and system architectures. Furthermore, by appropriately controlling other systems and devices, such as autonomous vehicles and entertainment providers, based on the emotion recognition data, responsiveness and ease of use can be improved.

[1496] "Means for accepting user input requirements" refers to an interface or device that the system uses to receive specific conditions or requests input by the user.

[1497] "Artificial intelligence model means" refers to a machine learning algorithm or model for analyzing received user input requirements and generating an appropriate technical configuration or system architecture based thereon.

[1498] "Means for presenting the generated technical configuration and system architecture to the user" refers to an interface or device for visually or audibly providing the user with the technical configuration and system architecture generated as a result of the analysis.

[1499] "Emotion recognition means" refers to technology or devices that recognize a user's emotions and reflect them in the analysis results. Specifically, this includes facial expression recognition and voice analysis.

[1500] "Means for controlling other systems or devices" refers to technologies or devices for appropriately controlling multiple systems or devices, such as autonomous vehicles or entertainment systems, based on recognized emotion data.

[1501] A "technology configuration" is the combination of tools and platforms used to implement a system or application, including, for example, a specific programming language, framework, database, etc.

[1502] "System architecture" refers to the basic framework or structure for the overall system configuration and design. Specifically, it includes microservice architecture and monolithic architecture.

[1503] "Emotion Recognition Data" means data about a user's emotions collected and analyzed by the emotion recognition means, which is used to improve the accuracy of suggestions and for system control.

[1504] This invention relates to a system installed in an autonomous vehicle that analyzes user input requirements and emotions, generates and presents appropriate technical configurations and system architectures based on the analysis, and controls the operation of the vehicle and related systems. To realize this system, the following programs and processing procedures are executed.

[1505] System Configuration

[1506] This system is broadly composed of the following main components:

[1507] 1. Front end (terminal)

[1508] Provide an interface for passengers to interact with the system. Specifically, a smartphone application is used. The application provides a UI for passenger input and displaying emotion recognition results. Modern JavaScript frameworks (e.g., React.js, Vue.js) are used.

[1509] 2. Backend (server)

[1510] The system receives passenger requirements and emotion data, analyzes them with artificial intelligence models and emotion engines, and generates results using server-side frameworks such as Node.js and Django. The back-end server also communicates with the autonomous vehicle and related systems.

[1511] 3. Database

[1512] Manage and store information on technical configuration and system architecture, as well as emotional data, using a relational database such as PostgreSQL.

[1513] 4. Artificial Intelligence Models

[1514] Use machine learning models to analyze passenger requirements and generate the appropriate technical configuration and system architecture, using pre-trained models based on historical datasets using TensorFlow and PyTorch.

[1515] 5. Emotion recognition means

[1516] The system recognizes passenger emotions and uses the data for analysis. It uses the smartphone's camera and microphone to perform facial expression recognition and voice analysis. Specifically, it uses toolkits such as OpenCV and TensorFlow.

[1517] 6. Means of Controlling Other Systems or Devices

[1518] Based on the recognized emotion data, autonomous vehicles and entertainment systems can be controlled, for example, by adjusting the vehicle's driving mode or the in-car environment (music, temperature, etc.) according to a specific emotion.

[1519] Program processing description

[1520] This system is constructed from a smartphone, a server, a database, an artificial intelligence model, and an emotion recognition engine. Below are specific examples of data processing and data calculation using each hardware and software.

[1521] Hardware and Software Use

[1522] Smartphone: Used to capture passengers' facial expressions and voices and generate emotion data. Uses OpenCV and the smartphone's camera and microphone.

[1523] Server: Performs data analysis and management. Uses Node.js and Django to process data and respond in real time.

[1524] Database: Stores emotion data and technical configuration information. Uses PostgreSQL.

[1525] Artificial intelligence model: Using TensorFlow or PyTorch, it suggests the best system based on passenger requirements and historical data.

[1526] Emotion Recognition Engine: Uses OpenCV and TensorFlow to recognize user emotions from captured images and audio.

[1527] Specific examples

[1528] 1. Emotion analysis: Passengers launch a smartphone application and capture emotional data through the camera and microphone. For example, if a passenger smiles, the emotion recognition engine classifies it as "happy."

[1529] 2. Driving mode adjustment: Emotion data is sent to the server, and the "happy" emotion is detected. Based on this information, the server sets the car's autonomous driving mode to "eco."

[1530] 3. Entertainment provision: The server receives the emotion data and transmits it to the entertainment system. For example, it selects a pop music playlist that best suits the emotion "happy" and starts playing it.

[1531] Prompt Sentence Examples

[1532] "If a passenger indicates a smile through facial recognition, set the vehicle's driving mode to eco-friendly Eco mode and play an upbeat pop music playlist."

[1533] The above-described embodiments of the present invention enable the proposal of flexible and appropriate technical configurations and system architectures according to the requirements and emotions of users. Furthermore, the quality of the user experience can be improved by controlling the operation of related systems in real time.

[1534] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1535] Step 1:

[1536] A user launches a smartphone application and enters their passenger requirements. These requirements include specific conditions and preferences. The input is in text format and is displayed in the application's user interface. This input data is then sent to subsequent processing steps.

[1537] Step 2:

[1538] The terminal receives the user's input requirements, converts them into JSON format, and sends them as an HTTP POST request to the backend server, where the input data is sent through a network protocol to the server and received for analysis.

[1539] Step 3:

[1540] The server receives the request and extracts the user's requirements data. This data is passed to an artificial intelligence model that uses TensorFlow or PyTorch to generate the appropriate technical configuration and system architecture.

[1541] Step 4:

[1542] The server uses emotion recognition to analyze emotion data acquired in real time from the smartphone's camera and microphone. Here, OpenCV and voice analysis technology are used to classify the emotion data. As a result, emotion labels such as "happy" and "sad" are obtained.

[1543] Step 5:

[1544] The server integrates the technical configuration and system architecture generated by the AI ​​model with the emotion data obtained by the emotion recognition means. The server then compiles the analysis results and creates data to provide to the user.

[1545] Step 6:

[1546] The server converts the integrated result data into JSON format and sends it to the terminal as an HTTP response, where the data is returned from the server to the terminal.

[1547] Step 7:

[1548] Based on the received data, the device displays the analysis results and technical proposals on the user interface. The user can check these results. Specifically, the technology stack and system architecture are illustrated on the screen.

[1549] Step 8:

[1550] The device then generates instructions for controlling the autonomous vehicle and related systems based on the emotion data and sends them to a server, which determines the driving mode and entertainment content according to the emotion.

[1551] Step 9:

[1552] The server receives these instructions and calls the appropriate APIs to control the autonomous vehicle's driving mode and entertainment system. For example, if the passenger is recognized as "happy," it can set the vehicle's driving mode to "eco" and play a pop music playlist.

[1553] Step 10:

[1554] The end result is an in-car environment that matches the user's emotions, which the system monitors in real time and adjusts as needed, ensuring a comfortable riding experience for passengers.

[1555] 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.

[1556] 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.

[1557] 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.

[1558] 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.

[1559] 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.

[1560] 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.

[1561] 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).

[1562] 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.

[1563] 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."

[1564] 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.

[1565] 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).

[1566] 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.

[1567] 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.

[1568] 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.

[1569] 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.

[1570] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1571] 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.

[1572] 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.

[1573] 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.

[1574] 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.

[1575] 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.

[1576] The following is further disclosed regarding the above embodiment.

[1577] (Claim 1)

[1578] means for accepting user input requirements;

[1579] an artificial intelligence model means for analyzing the received user input requirements and generating an appropriate technical configuration or system architecture;

[1580] A means for presenting the generated technical configuration and system architecture to a user;

[1581] A system including:

[1582] (Claim 2)

[1583] 10. The system of claim 1,

[1584] The system wherein the analyzing means further comprises means for suggesting an optimal technology stack based on user input requirements.

[1585] (Claim 3)

[1586] 10. The system of claim 1,

[1587] The system includes means for training the artificial intelligence model based on historical data sets.

[1588] "Example 1"

[1589] (Claim 1)

[1590] means for accepting user input requirements;

[1591] an artificial intelligence model means for analyzing the received user input requirements and generating an optimal technical configuration and system architecture;

[1592] A means to convert the requirements entered by the user into JSON format and send it to the server as an HTTP POST request,

[1593] A means for the server to analyze the requirements, extract the requirements data, and pass it to the artificial intelligence model;

[1594] A means by which an artificial intelligence model generates optimal technology configurations and system architectures based on historical data sets; and

[1595] A means for converting the generated technical configuration and system architecture information into JSON format and returning it from the server to the terminal;

[1596] means for analyzing the data received by the terminal and displaying the results on a user interface;

[1597] A system including:

[1598] (Claim 2)

[1599] 10. The system of claim 1, further comprising: means for suggesting an optimal technology stack based on user-input requirements.

[1600] (Claim 3)

[1601] 10. The system of claim 1, wherein the artificial intelligence model means comprises means that is trained based on historical data sets.

[1602] "Application Example 1"

[1603] (Claim 1)

[1604] means for accepting user input requirements;

[1605] an artificial intelligence model means for analyzing the received user input requirements and generating an appropriate technical configuration or system architecture;

[1606] A means for presenting the generated technical configuration and system architecture to a user;

[1607] A means for analyzing user-input requirements for content delivery and suggesting optimal technology stacks and system architectures;

[1608] A means for displaying the generated technical configuration or system architecture using a smart device;

[1609] A system including:

[1610] (Claim 2)

[1611] 10. The system of claim 1, wherein the analyzing means further comprises: means for suggesting an optimal technology stack based on user-input requirements.

[1612] (Claim 3)

[1613] 10. The system of claim 1, wherein the artificial intelligence model means includes means that is trained based on historical data sets.

[1614] "Example 2: Combining Emotion Engines"

[1615] (Claim 1)

[1616] means for accepting user input requirements;

[1617] an artificial intelligence model means for analyzing the received user input requirements and generating an appropriate technical configuration or system architecture;

[1618] A means for presenting the generated technical configuration and system architecture to a user;

[1619] An emotion recognition means for recognizing a user's emotion and reflecting it in the user input requirements and generated suggestions;

[1620] A system including:

[1621] (Claim 2)

[1622] The system wherein the analyzing means further includes means for suggesting an optimal technology stack based on user-input requirements.

[1623] 10. The system of claim 1.

[1624] (Claim 3)

[1625] The system includes means for training the artificial intelligence model based on a past data set.

[1626] 10. The system of claim 1.

[1627] "Application example 2 when combining emotion engines"

[1628] (Claim 1)

[1629] means for accepting user input requirements;

[1630] an artificial intelligence model means for analyzing the received user input requirements and generating an appropriate technical configuration or system architecture;

[1631] A means for presenting the generated technical configuration and system architecture to a user;

[1632] An emotion recognition means for recognizing a user's emotion and reflecting it in an analysis result;

[1633] means for controlling other systems or devices based on the emotion recognition data;

[1634] A system including:

[1635] (Claim 2)

[1636] 10. The system of claim 1, wherein the analyzing means further comprises: means for suggesting an optimal technology stack based on user-input requirements.

[1637] (Claim 3)

[1638] 10. The system of claim 1, wherein the artificial intelligence model means includes means that is trained based on historical data sets. [Explanation of symbols]

[1639] 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 accepting user input requirements; an artificial intelligence model means for analyzing the received user input requirements and generating an appropriate technical configuration or system architecture; A means for presenting the generated technical configuration and system architecture to a user; A system including:

2. 10. The system of claim 1, The system wherein the analyzing means further comprises means for suggesting an optimal technology stack based on user input requirements.

3. 10. The system of claim 1, The system includes means for training the artificial intelligence model based on historical data sets.

Images