system

Abstract

We provide the system. [Solution] A means by which the user requests program generation from the system using natural language, A means by which the terminal sends user requests to the server, A means by which the server analyzes the user's request and requests program generation from a generative AI, A means by which a generative AI generates program code based on user requests, A means for the server to return the generated program code to the terminal, A means by which the terminal displays the generated program code to the user. A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, the method including: receiving a user utterance; adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot; 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In conventional program creation, it is assumed that the user has knowledge of programming languages, and it is necessary to manually write program code from scratch. Therefore, high expertise and time are required for program creation, which has been an obstacle to programming learning and practice for many users. Furthermore, it has been difficult to accurately convert user requirements into program code with existing means, resulting in problems with program quality and efficiency. The problem to be solved by this invention is to provide a system that can easily generate program code even for users with little programming knowledge.

Means for Solving the Problems

[0005] [[ID=A1]] The present invention provides a system that includes means for a user to request program generation from the system in natural language, means for a terminal to send the user's request to a server, means for the server to analyze the user's request and request program generation from a generative AI, means for the generative AI to generate program code based on the user's request, means for the server to return the generated program code to the terminal, and means for the terminal to display the generated program code to the user. Furthermore, by including means for the server to receive the user's request in JSON format and transmit it to the generative AI, means for the generative AI to return the generated program code to the server in JSON format, and interface means for the terminal to acquire the user's request in natural language and send it to the server, the system enables users to intuitively generate programs using natural language. This makes it possible to efficiently generate high-quality program code even with little programming knowledge.

[0006] ---

[0007] A "user" refers to a person who uses the system to request the generation of program code.

[0008] "Natural language" refers to the language that humans use on a daily basis, and is a form of language that does not require a specific programming language or technical knowledge.

[0009] "System" refers to a mechanism with integrated functionality consisting of multiple components, and in this invention, it includes a series of means for realizing program generation.

[0010] A "terminal" refers to a device used by a user to access a system and enter requests, and specifically includes computers, smartphones, tablets, and other similar devices.

[0011] A "server" refers to a central computer that receives requests from terminals via a network and communicates with generative AI systems.

[0012] "Generative AI" refers to artificial intelligence systems that automatically generate program code based on user requests.

[0013] "Program code" refers to a set of instructions written to perform a specific task, and more specifically, to code written in programming languages ​​such as Python, Java (registered trademark), and C++.

[0014] "JSON format" is an abbreviation for JavaScript (registered trademark) Object Notation, and refers to a text format for structuring and representing data.

[0015] "Interface means" refers to an intermediate means by which a user inputs a request into a system and sends that request to a server, and specifically includes web page forms and APIs.

[0016] A "request" refers to a user's intention to have a system perform a specific process or function.

[0017] "Analysis" refers to the process by which a server understands a user's request and extracts the necessary information.

[0018] "Transmission" refers to the act of a terminal or server passing data to another device over a network.

[0019] "Return" refers to the act of a server sending back data it has received from a generative AI or terminal.

[0020] "Display" refers to the act of a device visually presenting information or results on the user's screen.

[0021] ---

[0022] The above are definitions of the key terms included in the patent claims. [Brief explanation of the drawing]

[0023] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Modes for Carrying Out the Invention

[0024] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0025] First, let's explain the terminology used in the following explanation.

[0026] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), and APU (Accelerated Processing Unit).

[0027] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0028] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0029] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0030] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0031] [First Embodiment]

[0032] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0033] As shown in Figure 1, the 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.

[0034] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0035] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0036] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0037] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0038] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0039] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0040] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0041] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0042] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0043] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0044] The system according to the present invention provides a mechanism in which a user requests program generation in natural language, and a server and a generative AI generate program code based on that request. This allows even users with little programming knowledge to easily create and use program code.

[0045] The user accesses the system's input interface using a terminal. For example, the user might input "I want to create a simple addition program" in natural language. The terminal receives this request, generates a request to send to the server, and sends it to the server.

[0046] The server analyzes and understands the user's request received from the terminal. Based on the analysis, the server requests the generative AI to generate program code. The generative AI generates appropriate program code according to the user's request and sends the result back to the server. The generative AI understands the user's request using natural language processing technology and generates code based on the algorithm.

[0047] The server sends the program code received from the generative AI back to the terminal. The terminal displays the program code received from the server to the user. The user can copy this displayed program code as is and use it for their own purposes, or modify it as needed and execute it.

[0048] As a concrete example, if a user requests to "create a simple addition program," the generative AI would generate code using the following logical procedure: First, it extracts the keywords "addition" and "program" from the user's request, and based on these, it generates a program that takes two numbers as input and outputs their sum. The generated program code is easy for the user to understand; for example, it declares two variables, assigns numbers to them, calculates their sum, and displays it.

[0049] This system allows users to immediately utilize concrete program code without requiring specialized programming knowledge. Furthermore, the collaboration between the server and generative AI enables the rapid generation and efficient delivery of optimal code tailored to user requirements. This system can be used in a wide range of fields, including education, prototyping, and lightweight application development.

[0050] To implement this invention, since specific program code is not provided, an understanding of the underlying technologies and processes of this system is crucial. By clearly defining how each means interacts, users can efficiently generate programs.

[0051] The following describes the processing flow.

[0052] Step 1:

[0053] The user accesses the system's input interface using a terminal. For example, they might open a web browser and display a dedicated webpage.

[0054] Step 2:

[0055] The user enters what they want to achieve in natural language into the input interface and clicks the submit button. For example, they might enter, "I want to create a simple addition program."

[0056] Step 3:

[0057] The terminal retrieves the user's input and generates request data in JSON format. For example, the data format will be as follows:

[0058] json

[0059] {

[0060] "user_request": "I want to create a simple addition program."

[0061] }

[0062] Step 4:

[0063] The terminal generates request data and sends it to the server. Asynchronous communication (e.g., HTTP POST request) is performed over the network.

[0064] Step 5:

[0065] The server receives request data from the terminal and analyzes the user's request. The server understands the content of the request data and generates a request in an appropriate format for the generative AI.

[0066] Step 6:

[0067] The server requests the generative AI to generate program code. An API request is sent to the generative AI to appropriately convey the user's request.

[0068] Step 7:

[0069] A generative AI receives a request from a server and uses natural language processing techniques to understand the user's request. It then generates program code. For example, it might understand an "addition program" and generate Python code for it.

[0070] Step 8:

[0071] The generative AI sends the generated program code back to the server. For example, it sends response data containing the program code in JSON format.

[0072] Step 9:

[0073] The server receives response data from the generative AI and extracts the program code. The server then generates response data to send the extracted program code back to the terminal.

[0074] Step 10:

[0075] The server sends the generated response data to the terminal. Asynchronous communication is performed over the network to return the data to the terminal.

[0076] Step 11:

[0077] The terminal receives response data from the server and extracts the program code. For example, it extracts "generated_code" from the response data.

[0078] Step 12:

[0079] The program code received by the terminal is displayed to the user. For example, it is inserted into an HTML element that displays the program code on the user's screen.

[0080] Step 13:

[0081] The user reviews the program code displayed on the terminal, copies it as needed, and uses it in their development environment. The user can then run the generated code as is or customize it for use.

[0082] The above outlines the specific processing steps from when a user requests program generation until they actually receive the generated code. Through these steps, users can efficiently generate and utilize program code.

[0083] (Example 1)

[0084] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0085] Conventional program generation technologies have had the problem that it is difficult for users with little programming knowledge to easily generate program code. Furthermore, specialized knowledge is required to quickly generate and use specific program code, and there is a need for a system that users can operate intuitively. To solve these problems, this invention aims to provide a system that can request program generation in natural language, enabling even users with little programming knowledge to easily create and use program code.

[0086] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0087] In this invention, the server includes means for the user to request program generation from the system in natural language, means for the terminal to send the user's request to the server, means for the server to analyze the user's request and request program generation from a generative AI model, means for the generative AI model to generate program code based on the user's request, means for the server to return the generated program code to the terminal, means for the terminal to display the generated program code to the user, and means for the user to check and use the generated program code through the terminal. This makes it possible for even users with little programming expertise to intuitively request program generation using natural language and quickly obtain appropriate program code.

[0088] A "user" refers to a person or group that uses the system to request program generation.

[0089] A "terminal" refers to a device used by a user to access a system, input requests, and view generated program code.

[0090] A "server" refers to a computer system that receives and analyzes user requests and instructs the AI ​​model to generate program code.

[0091] A "generative AI model" refers to an artificial intelligence model that generates program code based on a user's requests in natural language.

[0092] "Program generation" refers to the process of automatically creating program code based on specified requirements.

[0093] "Natural language" refers to the language that humans use on a daily basis, and is used to describe requests and instructions to systems.

[0094] A "prompt statement" refers to a natural language sentence used to instruct a generative AI model to generate program code.

[0095] Modes for carrying out the invention

[0096] The system according to the present invention provides a mechanism in which a user requests program generation in natural language, and a server and a generation AI model are used to generate program code based on that request. This makes it easy for users with little programming knowledge to create and use program code.

[0097] Hardware and software details

[0098] Hardware:

[0099] Devices: PCs, smartphones, tablets, etc.

[0100] Server: A cloud server equipped with a high-performance processor (e.g., a cloud hosting service).

[0101] software:

[0102] Natural language processing technology (e.g., OpenAI's GPT model, used as a generative AI model).

[0103] Web browsers (e.g., Google Chrome®, Mozilla Firefox, etc.).

[0104] Communication protocol (e.g., HTTP / HTTPS).

[0105] System operation procedures and examples of operation

[0106] User actions

[0107] The user accesses the system's input interface using their own device. For example, they access a specific URL through a web browser and enter a request in natural language into the input field on the interface. As a concrete example, the user might enter "I want to create a simple addition program."

[0108] Terminal operation

[0109] The terminal receives user input and generates a request to send to the server. The request contains the natural language text entered by the user. This request is sent to the server using the HTTP / HTTPS protocol.

[0110] Server operation

[0111] The server analyzes the request received from the terminal and performs the necessary processing to understand its content. Based on the analysis results, it sends instructions to the generating AI model to generate program code. The instructions include prompt statements created based on the user's request. For example, in response to the request "I want to create a simple addition program," the following prompt statement will be generated.

[0112] Example of a prompt:

[0113] Please generate a Python program based on the following:

[0114] 1. Receive two numbers as input.

[0115] 2. Calculate their sum.

[0116] 3. Output the total.

[0117] How generative AI models work

[0118] The generative AI model generates program code based on prompt messages received from the server. The generative AI model uses natural language processing techniques to assemble appropriate code according to the user's request. The generated code is then returned to the server.

[0119] Server restart

[0120] The server sends the program code received from the generated AI model back to the terminal. Communication is conducted using the HTTP / HTTPS protocol.

[0121] Restarting the device

[0122] The terminal displays the program code received from the server to the user. The user can review the displayed code, copy it, and use it as is. They can also modify the code as needed and then execute it.

[0123] Specific example

[0124] If a user requests to "create a simple addition program," the AI ​​model generates the code using the following steps: First, it extracts the keywords "addition" and "program" from the user's request, and based on these, it generates a program that takes two numbers as input and outputs their sum. The generated program code is easy for the user to understand, declaring two variables, assigning numbers to them, calculating their sum, and displaying it.

[0125] This system allows users to immediately utilize concrete program code without requiring specialized programming knowledge. For example, it can be used for programming education in schools, rapid prototype creation, and everyday small programming tasks. Furthermore, the collaboration between the server and the generated AI model ensures that high-quality code tailored to the user's specific requirements is quickly provided, improving work efficiency.

[0126] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0127] Step 1:

[0128] The user enters the request in natural language.

[0129] The user accesses the system's input interface using their own device. For example, the user accesses a specific URL through a web browser and enters "I want to create a simple addition program" into the input field on the interface. This input becomes a natural language request used for the next process.

[0130] Input and output

[0131] Input: User's request in natural language (e.g., "I want to create a simple addition program")

[0132] Output: Generated natural language request

[0133] Specific actions

[0134] The user enters their request into the input field and clicks the submit button.

[0135] Step 2:

[0136] The terminal sends the user's request to the server.

[0137] The terminal receives a natural language request entered by the user and generates a request to send it to the server. This request contains the natural language text entered by the user. The request is sent to the server using the HTTP / HTTPS protocol.

[0138] Input and output

[0139] Input: User's natural language request

[0140] Output: HTTP request sent to the server

[0141] Specific actions

[0142] The device retrieves user input and sends an HTTP request to the server using the fetch API or AJAX.

[0143] Step 3:

[0144] The server analyzes the user's request and sends a prompt message to the generative AI model.

[0145] The server analyzes the request received from the terminal and performs the necessary data processing to understand the user's request. Based on the analysis results, it sends instructions to the AI ​​model to generate program code. These instructions include prompt statements created based on the user's request. For example, in response to the request "I want to create a simple addition program," the server will generate prompt statements such as "Generate a Python program based on the following: 1. Receive two numbers as input 2. Calculate their sum 3. Output the sum."

[0146] Input and output

[0147] Input: HTTP request containing the user's request

[0148] Output: Prompt message sent to the generated AI model

[0149] Specific actions

[0150] The server parses the request body, generates a prompt, and sends it to the AI ​​model.

[0151] Step 4:

[0152] The generative AI model generates program code.

[0153] The generative AI model generates program code based on prompt messages received from the server. Using natural language processing techniques, the generative AI model constructs appropriate code in response to user requests. The generated code is then returned to the server.

[0154] Input and output

[0155] Input: Prompt message sent from the server

[0156] Output: Generated program code

[0157] Specific actions

[0158] The generative AI model analyzes the prompt text, generates code based on the algorithm, and sends the result back to the server.

[0159] Step 5:

[0160] The server sends the generated program code back to the terminal.

[0161] The server sends the program code received from the generated AI model back to the terminal. This communication uses the HTTP / HTTPS protocol. The server formats the generated program code appropriately and sends it to the terminal.

[0162] Input and output

[0163] Input: Program code received from the generated AI model

[0164] Output: HTTP response sent to the terminal

[0165] Specific actions

[0166] The server formats the generated code and sends it to the terminal as an HTTP response.

[0167] Step 6:

[0168] The terminal displays the generated program code to the user.

[0169] The terminal displays the program code received from the server to the user. The user can review the displayed code, copy it, and use it as is. They can also modify the code as needed and then execute it.

[0170] Input and output

[0171] Input: HTTP response received from the server

[0172] Output: Program code displayed to the user

[0173] Specific actions

[0174] The program code received by the terminal is displayed in the web browser.

[0175] (Application Example 1)

[0176] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0177] Traditional food delivery services have the problem that users have to manually configure detailed settings when placing specific customized orders, which is time-consuming and cumbersome. Furthermore, there is a challenge in that users with little programming experience have limited means to efficiently generate and utilize programs.

[0178] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0179] In this invention, the server includes means for the user to request program generation from the system in natural language, means for the terminal to send the user's request to the server, means for a generative AI to generate program code based on the user's request, means for the user to input a request in natural language to order a customized meal, means for using a generative AI to analyze the request and automatically generate appropriate order details, and means for the server to send the appropriate order details to the restaurant based on the analysis results. This makes it possible for the user to place a customized order in natural language without any effort, and to efficiently generate and use program code without any programming knowledge.

[0180] A "user" refers to a person who uses the system to input requests in natural language.

[0181] "Natural language" refers to the linguistic expressions that humans use on a daily basis, and is not a specific programming language or command.

[0182] A "system" refers to a device or software that has a series of processes for generating programs or order details based on user requests.

[0183] "Program generation" refers to the act of automatically creating program code based on user requests.

[0184] "Customized dishes" refer to meal menus that have been adjusted according to the user's specific requests.

[0185] "Analyzing requests" refers to the process of understanding the natural language input from a user and converting it into a concrete action.

[0186] "Generative AI" refers to artificial intelligence that understands natural language and automatically generates program code or order details based on user requests.

[0187] "Order details" refers to the specific dishes and detailed settings that a user requests in food delivery.

[0188] A "server" refers to a central computer system that receives and analyzes user requests and, in cooperation with generative AI, returns the necessary data.

[0189] A "terminal" refers to a device (such as a smartphone or tablet) that a user uses to access a system and enter requests.

[0190] "Means of display" refers to functions that visually show the generated program code or order details to the user.

[0191] "Means of transmission" refers to the means of communication used to send user requests and generated data to the appropriate recipient.

[0192] The system according to this invention is a comprehensive platform that can be used by users to request program generation or customized food orders using natural language. Specific embodiments of the system are described below.

[0193] The system provides an interface where users can input requests in natural language using a device such as a smartphone. For example, a user might input a request such as, "I'd like to order chicken curry with less spice." The device receives this request and sends it to the server.

[0194] The server analyzes user requests and issues appropriate instructions to the generative AI. The generative AI uses natural language processing techniques to understand user requests and generate specific order details or program code. This analysis employs advanced natural language processing, such as generative AI models like OpenAI's GPT-3®.

[0195] The order details and program code generated by the generative AI are sent back to the terminal via the server. The terminal displays this visually to the user, who then confirms the contents. If there are no problems with the order details, the final order is automatically sent to the store.

[0196] Hardware and software to be used:

[0197] Smartphone: Used as a user interface (UI), it provides functionality for inputting requests in natural language.

[0198] Server: The central system that receives and analyzes user requests, and returns results in cooperation with the generated AI model.

[0199] Generative AI models: These models understand natural language and generate specific order details or program code based on user requests. For example, OpenAI GPT-3 is used.

[0200] Flask: A framework for managing server-side processing and API endpoints.

[0201] As a concrete example, if a user requests "I want to order chicken curry with less spice," the prompt text would be input to the generating AI model as follows:

[0202] Examples of input prompts for a generative AI model:

[0203] text

[0204] Please generate an order for a food delivery app where a user says, "I'd like to order chicken curry with less spice."

[0205] Based on this prompt, the generating AI model generates the following order:

[0206] Example of generated order details:

[0207] text

[0208] Order details:

[0209] Chicken Curry

[0210] Mildly spiced

[0211] Large serving of rice

[0212] Comes with salad

[0213] Special note: Use half the usual amount of spices.

[0214] This system allows users to place customized orders using natural language without any hassle, and enables them to efficiently generate and utilize program code even without programming knowledge.

[0215] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0216] Step 1:

[0217] Users input requests in natural language through a smartphone application. For example, a request might be, "I'd like to order chicken curry with less spice." This input data is collected through the device's interface.

[0218] Step 2:

[0219] The device receives the user's request in natural language as text data and sends that data to the server. The data sent will be in JSON format. For example, the format could be {"request": "I would like to order chicken curry with less spice"}.

[0220] Step 3:

[0221] The server analyzes the user request it receives. This analysis uses natural language processing techniques to generate prompts for a generative AI model (e.g., OpenAI GPT-3). Input data: "I want to order chicken curry with less spice." The resulting prompt is: "Generate the order details for when a user says 'I want to order chicken curry with less spice' in a food delivery app."

[0222] Step 4:

[0223] Based on the analysis results, the system requests the generative AI to generate a program. The server then sends an appropriate API request to the generative AI based on the prompt. For example, the system might send a prompt to the generative AI model instructing it to "generate an order for a food delivery app when a user says, 'I want to order chicken curry with less spice.'"

[0224] Step 5:

[0225] The generative AI generates program code and order details based on the prompt text. The generated data is sent back to the server, and for example, a JSON file in the format {"order": "Chicken curry, less spice, large portion of rice, with salad, special note: Half the usual amount of spice"} is returned.

[0226] Step 6:

[0227] The server receives the generated program code and order details and sends them to the terminal. It may also include logs of the processes required for analysis and generation in its response.

[0228] Step 7:

[0229] The terminal displays the data received from the server through the user interface. The user reviews this, and if there are no problems, the order details are automatically sent to the restaurant. Specifically, the order details displayed might be: "Chicken curry, less spice, large portion of rice, with salad, special note: use half the usual amount of spice."

[0230] Step 8:

[0231] After final user confirmation, the order details are automatically sent to the restaurant. The restaurant then prepares the food according to the user's customized order. At this point, the ordering process is complete, and the user receives a notification. For example, the user may be notified of their order ID and be able to track the delivery status.

[0232] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0233] The system according to the present invention not only allows users to request program generation in natural language, but also uses an emotion engine to recognize the user's emotional state and adjusts the operation of the generative AI based on that emotional state to provide a more customized program code.

[0234] The user accesses the system's input interface using a terminal. For example, they might open a web browser and access a dedicated webpage. At this point, the user might input in natural language, "I want to create a simple addition program." The terminal has an emotion engine built in that infers the user's emotional state from their facial expressions, voice, and input speed during the input process.

[0235] The emotion engine analyzes the user's emotions and notifies the device of the results. The device sends the emotion data to the server in JSON format along with the user's request. For example, data indicating the user's emotional state, such as "feeling a little irritated," may be added.

[0236] The server receives and analyzes user requests and emotion data from the terminal. Based on the analysis results, the server requests the generative AI to generate program code. At this time, the user's emotion data is also provided to the generative AI.

[0237] Generative AI generates program code based on requests from the server and user emotion data. For example, if the AI ​​analyzes that the user is "a little irritated," it selects concise and quickly generated code and provides it in a way that does not cause the user stress.

[0238] The program code generated by the generative AI is sent back to the server. The server sends the received program code back to the terminal, which then displays it to the user. The user can review the generated program code, copy it as needed, and use it in their own development environment.

[0239] As a concrete example, if a user requests to "create a simple addition program" and is perceived to be in a "slightly irritated" emotional state, the generative AI would generate code using the following logical steps: First, it extracts the keywords "addition" and "program" from the user's request, and based on that, it generates a program that takes two numbers as input and outputs their sum. Furthermore, the code is written simply and clearly so as not to stress the user.

[0240] The advantage of this system lies in its ability to improve user satisfaction by generating program code that takes into account the user's current emotional state. For example, it can be customized to the situation, providing quick solutions when the user is anxious and providing code with detailed explanations when the user is relaxed.

[0241] For the present invention to be implemented, it is crucial that the emotion engine recognizes the user's emotions, and that the server and generative AI operate based on that information. This allows the user to efficiently generate and utilize program code that meets their specific needs.

[0242] The following describes the processing flow.

[0243] Step 1:

[0244] The user accesses the system's input interface using a terminal. For example, the user opens a web browser and displays a dedicated web page.

[0245] Step 2:

[0246] The user enters what they want to achieve in natural language into the input interface. For example, they might enter, "I want to create a simple addition program."

[0247] Step 3:

[0248] The emotion engine analyzes the user's facial expressions, voice, and typing speed during input to recognize the user's emotional state. For example, it might determine that the user is "a little irritated."

[0249] Step 4:

[0250] The device converts the user's request and recognized emotional state into JSON-formatted request data. For example, the data format will be as follows:

[0251] json

[0252] {

[0253] "user_request": "I want to create a simple addition program",

[0254] "user_emotion": "A little irritated"

[0255] }

[0256] Step 5:

[0257] The terminal generates request data and sends it to the server. Asynchronous communication (e.g., HTTP POST request) is performed over the network.

[0258] Step 6:

[0259] The server receives request data from the terminal and analyzes the user's requests and sentiment data. The server understands the content of the request data and converts it into an appropriate format for forwarding the request to the generative AI.

[0260] Step 7:

[0261] The server requests the generative AI to generate program code. It also sends an API request to the generative AI to appropriately convey the user's request and emotional data.

[0262] Step 8:

[0263] A generative AI receives a request from a server and uses natural language processing techniques to understand the user's request. It then considers emotional data when generating program code. For example, if the user is "a little irritated," the generative AI will create concise and quickly executable program code.

[0264] Step 9:

[0265] The generative AI sends the generated program code back to the server in JSON format. The data format includes the generated program code.

[0266] Step 10:

[0267] The server receives response data from the generative AI and extracts the program code. The server then generates response data to send the extracted program code back to the terminal.

[0268] Step 11:

[0269] The server sends the generated response data to the terminal. It then sends the data back to the terminal via asynchronous communication over the network.

[0270] Step 12:

[0271] The terminal receives response data from the server and extracts the program code. For example, it extracts "generated_code" from the response data.

[0272] Step 13:

[0273] The program code received by the terminal is displayed to the user. For example, it is inserted into an HTML element that displays the program code on the user's screen.

[0274] Step 14:

[0275] The user reviews the program code displayed on the terminal, copies it as needed, and uses it in their development environment. The user can then run the generated code as is or further customize it for use.

[0276] The above outlines the specific processing steps involved in a user requesting program generation using the emotion engine and receiving the generated code. Through these steps, users can efficiently generate and utilize optimal program code tailored to their own emotional state.

[0277] (Example 2)

[0278] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0279] Traditional program generation systems fail to adequately improve user satisfaction because they provide standardized program code without considering the user's emotional state. Furthermore, some users experienced problems with the rapid generation of appropriate code in stressful or urgent situations. This can hinder efficient program generation, highlighting the need for improved user experience.

[0280] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving user requests and emotional data in JSON format and transmitting them to the generative AI, means for sending the program code generated by the generative AI back to the server in JSON format, and means for sending the generated program code back to the terminal. This makes it possible to generate customized program code that takes into account the user's emotional state.

[0281] A "user" is someone who requests program generation from the system using natural language.

[0282] A "system" is a mechanism that performs a series of processes, generating and delivering customized program code based on the user's requests and emotional state.

[0283] The "terminal" is a device through which a user accesses the system, inputs requests, and recognizes emotional states.

[0284] The "server" is a device that analyzes the user's requests and emotional data, requests the generation of program code from the generative AI, and returns the generated code to the terminal.

[0285] The "emotion engine" is a software or hardware component that analyzes the user's expressions, voice, input speed, etc., and recognizes the user's emotional state.

[0286] The "generative AI" is an artificial intelligence model that generates appropriate program code based on the user's requests and emotional states.

[0287] A "request" is what the user hopes to generate specific program code for the system in natural language.

[0288] "Emotional data" is data in which the emotion engine recognizes the user's emotional state and represents that information in JSON format.

[0289] "Program code" is the source code generated by the generative AI based on the user's requests and emotional states.

[0290] "JSON format" is the abbreviation of JavaScript Object Notation, which is a way to structure and represent data in a lightweight text format.

[0291] The system according to the present invention starts with the user accessing the input interface of the system using the terminal. The user, for example, opens a web browser, accesses a dedicated web page, and inputs in natural language "want to create a simple addition program".

[0292] The device incorporates an emotion engine that infers the user's emotional state from their facial expressions, voice, and input speed during input. This emotion engine uses facial recognition software, voice analysis software, and other tools to analyze the user's emotional state in real time and obtain the results. For example, if the device detects that the user is "a little irritated," that information is sent to the device as emotion data.

[0293] Next, the terminal sends the user's request along with emotional data in JSON format to the server. The server analyzes the received user request and emotional data and requests the generative AI to generate program code. The generative AI generates appropriate program code based on the request from the server and the user's emotional data.

[0294] Generative AI, for example, if it analyzes that a user is "a little irritated," will select a program code that is concise and can be executed quickly, and deliver it in a way that does not cause the user stress. If the user is relaxed, it can also provide code with detailed explanations.

[0295] The generated program code is sent back to the server, which then sends the code to the terminal. The terminal displays the received program code to the user. The user can review the generated program code and, if necessary, copy it for use in their own development environment.

[0296] As a concrete example, if a user requests to "create a simple addition program" and is in a "slightly irritated" emotional state, the generative AI will generate concise code as follows. An example prompt would be, "Generate Python code for a user who requests to 'create a simple addition program' and is slightly irritated." In this way, it becomes possible to generate customized program code that takes the user's emotional state into account.

[0297] As described above, the present invention improves user satisfaction and achieves efficient program generation by generating program code while taking into account the user's emotional state.

[0298] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0299] Step 1:

[0300] The user accesses a dedicated webpage and enters "I want to create a simple addition program" in natural language. The input is entered into the text field on the webpage via the keyboard, and the system is sent when the submit button is clicked. The input here is the user's request, and the output becomes the data sent to the terminal.

[0301] Step 2:

[0302] The device incorporates an emotion engine that recognizes the user's facial expressions, voice, and input speed in real time. The emotion engine uses a dedicated camera and microphone to collect data and processes it to infer the user's emotions. For example, if the voice is sharp and fast, it might be interpreted as "slightly irritated." The input for this step is the user's biometric data, and the output is emotion data.

[0303] Step 3:

[0304] The terminal sends user requests and sentiment data to the server in JSON format. Specifically, it serializes the user's requests (e.g., "I want to create a simple addition program") and sentiment data (e.g., "I'm a little annoyed") as a JSON object and sends it to the server over the network. The input for this step is the user's requests and sentiment data, and the output is the JSON data containing them.

[0305] Step 4:

[0306] The server analyzes the received JSON data. First, the server deserializes the JSON data and extracts the user's request content and sentiment data. Then, it analyzes the request content and creates an appropriate prompt sentence for the generative AI. For example, it generates a prompt sentence like "Please generate Python code when the user requests 'I want to create a simple addition program' and is a bit irritated." The input for this step is JSON data, and the output is the prompt sentence for the generative AI.

[0307] Step 5:

[0308] The server sends the prompt sentence to the generative AI. Based on the received prompt sentence, the generative AI generates appropriate program code considering the user's request and emotional state. For example, it generates Python code that is concise and can be executed quickly. The input for this step is the prompt sentence, and the output is the generated program code.

[0309] Step 6:

[0310] The generated program code is sent back to the server. The server converts the received program code into JSON format and sends it to the terminal. The input for this step is the program code from the generative AI, and the output is the program code data in JSON format.

[0311] Step 7:

[0312] The terminal analyzes the program code received from the server and displays it to the user. The display is done using a text area on a web page or another dedicated viewer. The user can view the displayed program code, copy it if necessary, and use it in their own development environment. The input for this step is the program code data in JSON format, and the output is the program code displayed on the user's screen.

[0313] Through the steps described above, the present invention can generate and provide customized program code based on natural language requests while taking into account the user's emotional state.

[0314] (Application Example 2)

[0315] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0316] Conventional systems can process program generation requests from users using natural language, but they fail to adequately enhance user satisfaction because they do not consider the user's emotional state. Furthermore, they struggle to mitigate the stress users experience in specific situations. Therefore, there is a need to provide more effective and comfortable program generation that takes user emotions into account.

[0317] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for receiving user requests in JSON format and transmitting them to the generative AI, means for sending the program code generated by the generative AI back to the server in JSON format, and means for the terminal to send data in JSON format, including the user's emotional data, to the server. This makes it possible to generate optimized program code that takes the user's emotional state into consideration.

[0318] A "terminal" is a device that a user directly operates, and its role is to input user requests and data and send them to the server.

[0319] A "server" is a device that receives and processes user requests and data, and transmits necessary information and program code to a generative AI.

[0320] A "user" is someone who uses the system to request the generation of program code.

[0321] "Natural language" refers to the words and sentences that humans use in everyday life, and is the format used to input program generation requests into a terminal.

[0322] "Program code" refers to text that describes a series of instructions executed by a computer, and is generated by a generative AI based on user requests.

[0323] "Generative AI" refers to artificial intelligence that analyzes user requests and generates appropriate program code based on those requests.

[0324] "Emotional data" refers to information that indicates the user's emotional state, which is recognized from facial expressions, voice, etc., and sent to the server in JSON format.

[0325] The system according to this invention provides a more customized program code by allowing the user to request program generation in natural language and recognizing the user's emotional state using an emotion engine. Specifically, the user accesses the system using a terminal and inputs a request. The terminal collects the user's emotional data along with the request and sends it to the server. The server analyzes the request and emotional data and requests the generative AI to generate program code.

[0326] The emotion engine analyzes the user's facial expressions, voice, and input speed to infer their emotional state. The emotional data analyzed by the emotion engine is sent from the terminal to the server. The server receives this emotional data in JSON format and provides it to the generative AI. The generative AI generates program code based on the request and emotional data, and sends the generated program code back to the server. The server sends this code to the terminal, which then displays it to the user.

[0327] As a concrete example of this system, consider a smart glasses application for a physical store that supports customer service. For example, a store employee wears smart glasses and captures the customer's facial image and voice using a camera and microphone. An emotion engine analyzes the customer's emotional state in real time and sends the analysis results to a server. Based on this emotion data, a generative AI generates a customer service response method appropriate to the customer's emotions and displays it on the smart glasses' display. This allows the store employee to provide the optimal response according to the customer's emotional state.

[0328] For example, if a generative AI detects that a customer is in a "slightly irritated" emotional state, it will suggest a quick and concise way to address the situation. For instance, a message like, "The customer appears angry. Please remain calm and assess the situation," might be generated and displayed on the employee's screen.

[0329] Examples of input prompts for a generative AI model:

[0330] Generate code to recognize customer emotions and suggest appropriate customer service responses. Output a Python program that analyzes image and voice input and returns a response based on the emotion.

[0331] As described above, this system improves user satisfaction by considering the user's emotional state and generating optimal program code. Furthermore, a variety of applications are possible, such as supporting customer service in physical stores.

[0332] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0333] Step 1: The user enters the request in natural language.

[0334] The user uses the terminal interface to input a program generation request in natural language. For example, the user's input might be, "I want to create a simple addition program."

[0335] Step 2: The device recognizes the user's emotions.

[0336] The emotion engine built into the device infers the user's emotional state from their facial expressions, voice, and input speed. For example, it analyzes facial images captured by the camera and audio data recorded by the microphone to recognize an emotional state such as "slightly irritated."

[0337] Step 3: The device sends the request and sentiment data to the server.

[0338] The device sends the user's natural language request and recognized emotion data to the server in JSON format. For example, it sends data in the format {"request": "I want to create a simple addition program", "emotion": "I'm a little annoyed"}.

[0339] Step 4: The server analyzes the data and transmits it to the generative AI.

[0340] The server analyzes the JSON data received from the terminal and extracts user requests and sentiment data. It then provides this data to a generative AI and requests the generation of program code.

[0341] Step 5: The generative AI generates the program code.

[0342] Generative AI generates program code based on requests and emotional data provided by a server. For example, based on the request "I want to create a simple addition program" and the emotional data "I'm a little irritated," it generates concise program code.

[0343] Step 6: The program code generated by the generative AI is sent back to the server.

[0344] The generative AI returns the generated program code to the server in JSON format. For example, it returns data in the format {"code": "def add(a, b): return a + b"}.

[0345] Step 7: The server sends the program code to the terminal.

[0346] The server sends the program code received from the generative AI to the terminal. The terminal converts the received program code into data for display to the user and displays it.

[0347] Step 8: The terminal displays the program code to the user.

[0348] The terminal displays the program code sent from the server to the user. The user can review the displayed program code and use it in their own development environment as needed. At this time, the user confirms that the generated code is concise and easy to understand.

[0349] The above steps enable the generation and display of program code that takes the user's emotional state into consideration.

[0350] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0351] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0352] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0353] [Second Embodiment]

[0354] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0355] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0356] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0357] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0358] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0359] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0360] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0361] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0362] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0363] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0364] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0365] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0366] The system according to the present invention provides a mechanism in which a user requests program generation in natural language, and a server and a generative AI generate program code based on that request. This allows even users with little programming knowledge to easily create and use program code.

[0367] The user accesses the system's input interface using a terminal. For example, the user might input "I want to create a simple addition program" in natural language. The terminal receives this request, generates a request to send to the server, and sends it to the server.

[0368] The server analyzes and understands the user's request received from the terminal. Based on the analysis, the server requests the generative AI to generate program code. The generative AI generates appropriate program code according to the user's request and sends the result back to the server. The generative AI understands the user's request using natural language processing technology and generates code based on the algorithm.

[0369] The server sends the program code received from the generative AI back to the terminal. The terminal displays the program code received from the server to the user. The user can copy this displayed program code as is and use it for their own purposes, or modify it as needed and execute it.

[0370] As a concrete example, if a user requests to "create a simple addition program," the generative AI would generate code using the following logical procedure: First, it extracts the keywords "addition" and "program" from the user's request, and based on these, it generates a program that takes two numbers as input and outputs their sum. The generated program code is easy for the user to understand; for example, it declares two variables, assigns numbers to them, calculates their sum, and displays it.

[0371] This system allows users to immediately utilize concrete program code without requiring specialized programming knowledge. Furthermore, the collaboration between the server and generative AI enables the rapid generation and efficient delivery of optimal code tailored to user requirements. This system can be used in a wide range of fields, including education, prototyping, and lightweight application development.

[0372] To implement this invention, since specific program code is not provided, an understanding of the underlying technologies and processes of this system is crucial. By clearly defining how each means interacts, users can efficiently generate programs.

[0373] The following describes the processing flow.

[0374] Step 1:

[0375] The user accesses the system's input interface using a terminal. For example, they might open a web browser and display a dedicated webpage.

[0376] Step 2:

[0377] The user enters what they want to achieve in natural language into the input interface and clicks the submit button. For example, they might enter, "I want to create a simple addition program."

[0378] Step 3:

[0379] The terminal retrieves the user's input and generates request data in JSON format. For example, the data format will be as follows:

[0380] json

[0381] {

[0382] "user_request": "I want to create a simple addition program."

[0383] }

[0384] Step 4:

[0385] The terminal generates request data and sends it to the server. Asynchronous communication (e.g., HTTP POST request) is performed over the network.

[0386] Step 5:

[0387] The server receives request data from the terminal and analyzes the user's request. The server understands the content of the request data and generates a request in an appropriate format for the generative AI.

[0388] Step 6:

[0389] The server requests the generative AI to generate program code. An API request is sent to the generative AI to appropriately convey the user's request.

[0390] Step 7:

[0391] A generative AI receives a request from a server and uses natural language processing techniques to understand the user's request. It then generates program code. For example, it might understand an "addition program" and generate Python code for it.

[0392] Step 8:

[0393] The generative AI sends the generated program code back to the server. For example, it sends response data containing the program code in JSON format.

[0394] Step 9:

[0395] The server receives response data from the generative AI and extracts the program code. The server then generates response data to send the extracted program code back to the terminal.

[0396] Step 10:

[0397] The server sends the generated response data to the terminal. Asynchronous communication is performed over the network to return the data to the terminal.

[0398] Step 11:

[0399] The terminal receives response data from the server and extracts the program code. For example, it extracts "generated_code" from the response data.

[0400] Step 12:

[0401] The program code received by the terminal is displayed to the user. For example, it is inserted into an HTML element that displays the program code on the user's screen.

[0402] Step 13:

[0403] The user reviews the program code displayed on the terminal, copies it as needed, and uses it in their development environment. The user can then run the generated code as is or customize it for use.

[0404] The above outlines the specific processing steps from when a user requests program generation until they actually receive the generated code. Through these steps, users can efficiently generate and utilize program code.

[0405] (Example 1)

[0406] Next, we will describe Example 1. 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".

[0407] Conventional program generation technologies have had the problem that it is difficult for users with little programming knowledge to easily generate program code. Furthermore, specialized knowledge is required to quickly generate and use specific program code, and there is a need for a system that users can operate intuitively. To solve these problems, this invention aims to provide a system that can request program generation in natural language, enabling even users with little programming knowledge to easily create and use program code.

[0408] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0409] In this invention, the server includes means for the user to request program generation from the system in natural language, means for the terminal to send the user's request to the server, means for the server to analyze the user's request and request program generation from a generative AI model, means for the generative AI model to generate program code based on the user's request, means for the server to return the generated program code to the terminal, means for the terminal to display the generated program code to the user, and means for the user to check and use the generated program code through the terminal. This makes it possible for even users with little programming expertise to intuitively request program generation using natural language and quickly obtain appropriate program code.

[0410] A "user" refers to a person or group that uses the system to request program generation.

[0411] A "terminal" refers to a device used by a user to access a system, input requests, and view generated program code.

[0412] A "server" refers to a computer system that receives and analyzes user requests and instructs the AI ​​model to generate program code.

[0413] A "generative AI model" refers to an artificial intelligence model that generates program code based on a user's requests in natural language.

[0414] "Program generation" refers to the process of automatically creating program code based on specified requirements.

[0415] "Natural language" refers to the language that humans use on a daily basis, and is used to describe requests and instructions to systems.

[0416] A "prompt statement" refers to a natural language sentence used to instruct a generative AI model to generate program code.

[0417] Modes for carrying out the invention

[0418] The system according to the present invention provides a mechanism in which a user requests program generation in natural language, and a server and a generation AI model are used to generate program code based on that request. This makes it easy for users with little programming knowledge to create and use program code.

[0419] Hardware and software details

[0420] Hardware:

[0421] Devices: PCs, smartphones, tablets, etc.

[0422] Server: A cloud server equipped with a high-performance processor (e.g., a cloud hosting service).

[0423] software:

[0424] Natural language processing technology (e.g., OpenAI's GPT model used as a generative AI model).

[0425] Web browsers (e.g., Google Chrome, Mozilla Firefox, etc.).

[0426] Communication protocol (e.g., HTTP / HTTPS).

[0427] System operation procedures and examples of operation

[0428] User actions

[0429] The user accesses the system's input interface using their own device. For example, they access a specific URL through a web browser and enter a request in natural language into the input field on the interface. As a concrete example, the user might enter "I want to create a simple addition program."

[0430] Terminal operation

[0431] The terminal receives user input and generates a request to send to the server. The request contains the natural language text entered by the user. This request is sent to the server using the HTTP / HTTPS protocol.

[0432] Server operation

[0433] The server analyzes the request received from the terminal and performs the necessary processing to understand its content. Based on the analysis results, it sends instructions to the generating AI model to generate program code. The instructions include prompt statements created based on the user's request. For example, in response to the request "I want to create a simple addition program," the following prompt statement will be generated.

[0434] Example of a prompt:

[0435] Please generate a Python program based on the following:

[0436] 1. Receive two numbers as input.

[0437] 2. Calculate their sum.

[0438] 3. Output the total.

[0439] How generative AI models work

[0440] The generative AI model generates program code based on prompt messages received from the server. The generative AI model uses natural language processing techniques to assemble appropriate code according to the user's request. The generated code is then returned to the server.

[0441] Server restart

[0442] The server sends the program code received from the generated AI model back to the terminal. Communication is conducted using the HTTP / HTTPS protocol.

[0443] Restarting the device

[0444] The terminal displays the program code received from the server to the user. The user can review the displayed code, copy it, and use it as is. They can also modify the code as needed and then execute it.

[0445] Specific example

[0446] If a user requests to "create a simple addition program," the AI ​​model generates the code using the following steps: First, it extracts the keywords "addition" and "program" from the user's request, and based on these, it generates a program that takes two numbers as input and outputs their sum. The generated program code is easy for the user to understand, declaring two variables, assigning numbers to them, calculating their sum, and displaying it.

[0447] This system allows users to immediately utilize concrete program code without requiring specialized programming knowledge. For example, it can be used for programming education in schools, rapid prototype creation, and everyday small programming tasks. Furthermore, the collaboration between the server and the generated AI model ensures that high-quality code tailored to the user's specific requirements is quickly provided, improving work efficiency.

[0448] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0449] Step 1:

[0450] The user enters the request in natural language.

[0451] The user accesses the system's input interface using their own device. For example, the user accesses a specific URL through a web browser and enters "I want to create a simple addition program" into the input field on the interface. This input becomes a natural language request used for the next process.

[0452] Input and output

[0453] Input: User's request in natural language (e.g., "I want to create a simple addition program")

[0454] Output: Generated natural language request

[0455] Specific actions

[0456] The user enters their request into the input field and clicks the submit button.

[0457] Step 2:

[0458] The terminal sends the user's request to the server.

[0459] The terminal receives a natural language request entered by the user and generates a request to send it to the server. This request contains the natural language text entered by the user. The request is sent to the server using the HTTP / HTTPS protocol.

[0460] Input and output

[0461] Input: User's natural language request

[0462] Output: HTTP request sent to the server

[0463] Specific actions

[0464] The device retrieves user input and sends an HTTP request to the server using the fetch API or AJAX.

[0465] Step 3:

[0466] The server analyzes the user's request and sends a prompt message to the generative AI model.

[0467] The server analyzes the request received from the terminal and performs the necessary data processing to understand the user's request. Based on the analysis results, it sends instructions to the AI ​​model to generate program code. These instructions include prompt statements created based on the user's request. For example, in response to the request "I want to create a simple addition program," the server will generate prompt statements such as "Generate a Python program based on the following: 1. Receive two numbers as input 2. Calculate their sum 3. Output the sum."

[0468] Input and output

[0469] Input: HTTP request containing the user's request

[0470] Output: Prompt message sent to the generated AI model

[0471] Specific actions

[0472] The server parses the request body, generates a prompt, and sends it to the AI ​​model.

[0473] Step 4:

[0474] The generative AI model generates program code.

[0475] The generative AI model generates program code based on prompt messages received from the server. Using natural language processing techniques, the generative AI model constructs appropriate code in response to user requests. The generated code is then returned to the server.

[0476] Input and output

[0477] Input: Prompt message sent from the server

[0478] Output: Generated program code

[0479] Specific actions

[0480] The generative AI model analyzes the prompt text, generates code based on the algorithm, and sends the result back to the server.

[0481] Step 5:

[0482] The server sends the generated program code back to the terminal.

[0483] The server sends the program code received from the generated AI model back to the terminal. This communication uses the HTTP / HTTPS protocol. The server formats the generated program code appropriately and sends it to the terminal.

[0484] Input and output

[0485] Input: Program code received from the generated AI model

[0486] Output: HTTP response sent to the terminal

[0487] Specific actions

[0488] The server formats the generated code and sends it to the terminal as an HTTP response.

[0489] Step 6:

[0490] The terminal displays the generated program code to the user.

[0491] The terminal displays the program code received from the server to the user. The user can review the displayed code, copy it, and use it as is. They can also modify the code as needed and then execute it.

[0492] Input and output

[0493] Input: HTTP response received from the server

[0494] Output: Program code displayed to the user

[0495] Specific actions

[0496] The program code received by the terminal is displayed in the web browser.

[0497] (Application Example 1)

[0498] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0499] Traditional food delivery services have the problem that users have to manually configure detailed settings when placing specific customized orders, which is time-consuming and cumbersome. Furthermore, there is a challenge in that users with little programming experience have limited means to efficiently generate and utilize programs.

[0500] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0501] In this invention, the server includes means for the user to request program generation from the system in natural language, means for the terminal to send the user's request to the server, means for a generative AI to generate program code based on the user's request, means for the user to input a request in natural language to order a customized meal, means for using a generative AI to analyze the request and automatically generate appropriate order details, and means for the server to send the appropriate order details to the restaurant based on the analysis results. This makes it possible for the user to place a customized order in natural language without any effort, and to efficiently generate and use program code without any programming knowledge.

[0502] A "user" refers to a person who uses the system to input requests in natural language.

[0503] "Natural language" refers to the linguistic expressions that humans use on a daily basis, and is not a specific programming language or command.

[0504] A "system" refers to a device or software that has a series of processes for generating programs or order details based on user requests.

[0505] "Program generation" refers to the act of automatically creating program code based on user requests.

[0506] "Customized dishes" refer to meal menus that have been adjusted according to the user's specific requests.

[0507] "Analyzing requests" refers to the process of understanding the natural language input from a user and converting it into a concrete action.

[0508] "Generative AI" refers to artificial intelligence that understands natural language and automatically generates program code or order details based on user requests.

[0509] "Order details" refers to the specific dishes and detailed settings that a user requests in food delivery.

[0510] A "server" refers to a central computer system that receives and analyzes user requests and, in cooperation with generative AI, returns the necessary data.

[0511] A "terminal" refers to a device (such as a smartphone or tablet) that a user uses to access a system and enter requests.

[0512] "Means of display" refers to functions that visually show the generated program code or order details to the user.

[0513] "Means of transmission" refers to the means of communication used to send user requests and generated data to the appropriate recipient.

[0514] The system according to this invention is a comprehensive platform that can be used by users to request program generation or customized food orders using natural language. Specific embodiments of the system are described below.

[0515] The system provides an interface where users can input requests in natural language using a device such as a smartphone. For example, a user might input a request such as, "I'd like to order chicken curry with less spice." The device receives this request and sends it to the server.

[0516] The server analyzes user requests and issues appropriate instructions to the generative AI. The generative AI uses natural language processing techniques to understand user requests and generate specific order details or program code. This analysis employs advanced natural language processing, such as generative AI models like OpenAI's GPT-3.

[0517] The order details and program code generated by the generative AI are sent back to the terminal via the server. The terminal displays this visually to the user, who then confirms the contents. If there are no problems with the order details, the final order is automatically sent to the store.

[0518] Hardware and software to be used:

[0519] Smartphone: Used as a user interface (UI), it provides functionality for inputting requests in natural language.

[0520] Server: The central system that receives and analyzes user requests, and returns results in cooperation with the generated AI model.

[0521] Generative AI models: These models understand natural language and generate specific order details or program code based on user requests. For example, OpenAI GPT-3 is used.

[0522] Flask: A framework for managing server-side processing and API endpoints.

[0523] As a concrete example, if a user requests "I want to order chicken curry with less spice," the prompt text would be input to the generating AI model as follows:

[0524] Examples of input prompts for a generative AI model:

[0525] text

[0526] Please generate an order for a food delivery app where a user says, "I'd like to order chicken curry with less spice."

[0527] Based on this prompt, the generating AI model generates the following order:

[0528] Example of generated order details:

[0529] text

[0530] Order details:

[0531] Chicken Curry

[0532] Mildly spiced

[0533] Large serving of rice

[0534] Comes with salad

[0535] Special note: Use half the usual amount of spices.

[0536] This system allows users to place customized orders using natural language without any hassle, and enables them to efficiently generate and utilize program code even without programming knowledge.

[0537] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0538] Step 1:

[0539] Users input requests in natural language through a smartphone application. For example, a request might be, "I'd like to order chicken curry with less spice." This input data is collected through the device's interface.

[0540] Step 2:

[0541] The device receives the user's request in natural language as text data and sends that data to the server. The data sent will be in JSON format. For example, the format could be {"request": "I would like to order chicken curry with less spice"}.

[0542] Step 3:

[0543] The server analyzes the user request it receives. This analysis uses natural language processing techniques to generate prompts for a generative AI model (e.g., OpenAI GPT-3). Input data: "I want to order chicken curry with less spice." The resulting prompt is: "Generate the order details for when a user says 'I want to order chicken curry with less spice' in a food delivery app."

[0544] Step 4:

[0545] Based on the analysis results, the system requests the generative AI to generate a program. The server then sends an appropriate API request to the generative AI based on the prompt. For example, the system might send a prompt to the generative AI model instructing it to "generate an order for a food delivery app when a user says, 'I want to order chicken curry with less spice.'"

[0546] Step 5:

[0547] The generative AI generates program code and order details based on the prompt text. The generated data is sent back to the server, and for example, a JSON file in the format {"order": "Chicken curry, less spice, large portion of rice, with salad, special note: Half the usual amount of spice"} is returned.

[0548] Step 6:

[0549] The server receives the generated program code and order details and sends them to the terminal. It may also include logs of the processes required for analysis and generation in its response.

[0550] Step 7:

[0551] The terminal displays the data received from the server through the user interface. The user reviews this, and if there are no problems, the order details are automatically sent to the restaurant. Specifically, the order details displayed might be: "Chicken curry, less spice, large portion of rice, with salad, special note: use half the usual amount of spice."

[0552] Step 8:

[0553] After final user confirmation, the order details are automatically sent to the restaurant. The restaurant then prepares the food according to the user's customized order. At this point, the ordering process is complete, and the user receives a notification. For example, the user may be notified of their order ID and be able to track the delivery status.

[0554] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0555] The system according to the present invention not only allows users to request program generation in natural language, but also uses an emotion engine to recognize the user's emotional state and adjusts the operation of the generative AI based on that emotional state to provide a more customized program code.

[0556] The user accesses the system's input interface using a terminal. For example, they might open a web browser and access a dedicated webpage. At this point, the user might input in natural language, "I want to create a simple addition program." The terminal has an emotion engine built in that infers the user's emotional state from their facial expressions, voice, and input speed during the input process.

[0557] The emotion engine analyzes the user's emotions and notifies the device of the results. The device sends the emotion data to the server in JSON format along with the user's request. For example, data indicating the user's emotional state, such as "feeling a little irritated," may be added.

[0558] The server receives and analyzes user requests and emotion data from the terminal. Based on the analysis results, the server requests the generative AI to generate program code. At this time, the user's emotion data is also provided to the generative AI.

[0559] Generative AI generates program code based on requests from the server and user emotion data. For example, if the AI ​​analyzes that the user is "a little irritated," it selects concise and quickly generated code and provides it in a way that does not cause the user stress.

[0560] The program code generated by the generative AI is sent back to the server. The server sends the received program code back to the terminal, which then displays it to the user. The user can review the generated program code, copy it as needed, and use it in their own development environment.

[0561] As a concrete example, if a user requests to "create a simple addition program" and is perceived to be in a "slightly irritated" emotional state, the generative AI would generate code using the following logical steps: First, it extracts the keywords "addition" and "program" from the user's request, and based on that, it generates a program that takes two numbers as input and outputs their sum. Furthermore, the code is written simply and clearly so as not to stress the user.

[0562] The advantage of this system lies in its ability to improve user satisfaction by generating program code that takes into account the user's current emotional state. For example, it can be customized to the situation, providing quick solutions when the user is anxious and providing code with detailed explanations when the user is relaxed.

[0563] For the present invention to be implemented, it is crucial that the emotion engine recognizes the user's emotions, and that the server and generative AI operate based on that information. This allows the user to efficiently generate and utilize program code that meets their specific needs.

[0564] The following describes the processing flow.

[0565] Step 1:

[0566] The user accesses the system's input interface using a terminal. For example, the user opens a web browser and displays a dedicated web page.

[0567] Step 2:

[0568] The user enters what they want to achieve in natural language into the input interface. For example, they might enter, "I want to create a simple addition program."

[0569] Step 3:

[0570] The emotion engine analyzes the user's facial expressions, voice, and typing speed during input to recognize the user's emotional state. For example, it might determine that the user is "a little irritated."

[0571] Step 4:

[0572] The device converts the user's request and recognized emotional state into JSON-formatted request data. For example, the data format will be as follows:

[0573] json

[0574] {

[0575] "user_request": "I want to create a simple addition program",

[0576] "user_emotion": "A little irritated"

[0577] }

[0578] Step 5:

[0579] The terminal generates request data and sends it to the server. Asynchronous communication (e.g., HTTP POST request) is performed over the network.

[0580] Step 6:

[0581] The server receives request data from the terminal and analyzes the user's requests and sentiment data. The server understands the content of the request data and converts it into an appropriate format for forwarding the request to the generative AI.

[0582] Step 7:

[0583] The server requests the generative AI to generate program code. It also sends an API request to the generative AI to appropriately convey the user's request and emotional data.

[0584] Step 8:

[0585] A generative AI receives a request from a server and uses natural language processing techniques to understand the user's request. It then considers emotional data when generating program code. For example, if the user is "a little irritated," the generative AI will create concise and quickly executable program code.

[0586] Step 9:

[0587] The generative AI sends the generated program code back to the server in JSON format. The data format includes the generated program code.

[0588] Step 10:

[0589] The server receives response data from the generative AI and extracts the program code. The server then generates response data to send the extracted program code back to the terminal.

[0590] Step 11:

[0591] The server sends the generated response data to the terminal. It then sends the data back to the terminal via asynchronous communication over the network.

[0592] Step 12:

[0593] The terminal receives response data from the server and extracts the program code. For example, it extracts "generated_code" from the response data.

[0594] Step 13:

[0595] The program code received by the terminal is displayed to the user. For example, it is inserted into an HTML element that displays the program code on the user's screen.

[0596] Step 14:

[0597] The user reviews the program code displayed on the terminal, copies it as needed, and uses it in their development environment. The user can then run the generated code as is or further customize it for use.

[0598] The above outlines the specific processing steps involved in a user requesting program generation using the emotion engine and receiving the generated code. Through these steps, users can efficiently generate and utilize optimal program code tailored to their own emotional state.

[0599] (Example 2)

[0600] Next, we will describe Example 2. 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".

[0601] Traditional program generation systems fail to adequately improve user satisfaction because they provide standardized program code without considering the user's emotional state. Furthermore, some users experienced problems with the rapid generation of appropriate code in stressful or urgent situations. This can hinder efficient program generation, highlighting the need for improved user experience.

[0602] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving user requests and emotional data in JSON format and transmitting them to the generative AI, means for sending the program code generated by the generative AI back to the server in JSON format, and means for sending the generated program code back to the terminal. This makes it possible to generate customized program code that takes into account the user's emotional state.

[0603] A "user" is someone who requests program generation from the system using natural language.

[0604] A "system" is a mechanism that performs a series of processes, generating and delivering customized program code based on the user's requests and emotional state.

[0605] A "terminal" is a device through which a user accesses a system, inputs requests, and recognizes their emotional state.

[0606] A "server" is a device that analyzes user requests and emotional data, requests the generative AI to generate program code, and sends the generated code back to the terminal.

[0607] An "emotion engine" is a software or hardware component that analyzes the user's facial expressions, voice, input speed, etc., to recognize the user's emotional state.

[0608] "Generative AI" refers to artificial intelligence models that generate appropriate program code based on the user's requests and emotional state.

[0609] A "request" is a user's request in natural language for the system to generate specific program code.

[0610] "Emotional data" refers to data that the emotion engine recognizes the user's emotional state and expresses in JSON format.

[0611] "Program code" refers to the source code generated by a generative AI based on the user's requests and emotional state.

[0612] "JSON format" is an abbreviation for JavaScript Object Notation, and it is a method of representing data in a lightweight text format.

[0613] The system according to the present invention begins with the user accessing the system's input interface using a terminal. For example, the user opens a web browser, accesses a dedicated web page, and inputs in natural language, "I want to create a simple addition program."

[0614] The device incorporates an emotion engine that infers the user's emotional state from their facial expressions, voice, and input speed during input. This emotion engine uses facial recognition software, voice analysis software, and other tools to analyze the user's emotional state in real time and obtain the results. For example, if the device detects that the user is "a little irritated," that information is sent to the device as emotion data.

[0615] Next, the terminal sends the user's request along with emotional data in JSON format to the server. The server analyzes the received user request and emotional data and requests the generative AI to generate program code. The generative AI generates appropriate program code based on the request from the server and the user's emotional data.

[0616] Generative AI, for example, if it analyzes that a user is "a little irritated," will select a program code that is concise and can be executed quickly, and deliver it in a way that does not cause the user stress. If the user is relaxed, it can also provide code with detailed explanations.

[0617] The generated program code is sent back to the server, which then sends the code to the terminal. The terminal displays the received program code to the user. The user can review the generated program code and, if necessary, copy it for use in their own development environment.

[0618] As a concrete example, if a user requests to "create a simple addition program" and is in a "slightly irritated" emotional state, the generative AI will generate concise code as follows. An example prompt would be, "Generate Python code for a user who requests to 'create a simple addition program' and is slightly irritated." In this way, it becomes possible to generate customized program code that takes the user's emotional state into account.

[0619] As described above, the present invention improves user satisfaction and achieves efficient program generation by generating program code while taking into account the user's emotional state.

[0620] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0621] Step 1:

[0622] The user accesses a dedicated webpage and enters "I want to create a simple addition program" in natural language. The input is entered into the text field on the webpage via the keyboard, and the system is sent when the submit button is clicked. The input here is the user's request, and the output becomes the data sent to the terminal.

[0623] Step 2:

[0624] The device incorporates an emotion engine that recognizes the user's facial expressions, voice, and input speed in real time. The emotion engine uses a dedicated camera and microphone to collect data and processes it to infer the user's emotions. For example, if the voice is sharp and fast, it might be interpreted as "slightly irritated." The input for this step is the user's biometric data, and the output is emotion data.

[0625] Step 3:

[0626] The terminal sends user requests and sentiment data to the server in JSON format. Specifically, it serializes the user's requests (e.g., "I want to create a simple addition program") and sentiment data (e.g., "I'm a little annoyed") as a JSON object and sends it to the server over the network. The input for this step is the user's requests and sentiment data, and the output is the JSON data containing them.

[0627] Step 4:

[0628] The server parses the received JSON data. First, the server deserializes the JSON data and extracts the user's request and sentiment data. Then, it analyzes the request and creates an appropriate prompt for the generative AI. For example, it might generate a prompt such as, "Generate Python code for a user who requests to 'create a simple addition program' and is slightly frustrated." The input for this step is JSON data, and the output is a prompt for the generative AI.

[0629] Step 5:

[0630] The server sends a prompt to the generative AI. Based on the received prompt, the generative AI generates appropriate program code, taking into account the user's request and emotional state. For example, it might generate concise and quickly executable Python code. The input for this step is the prompt, and the output is the generated program code.

[0631] Step 6:

[0632] The generated program code is sent back to the server. The server converts the received program code into JSON format and sends it to the terminal. The input for this step is program code from a generative AI, and the output is program code data in JSON format.

[0633] Step 7:

[0634] The terminal parses the program code received from the server and displays it to the user. The display is done using a text area on a web page or a separate dedicated viewer. The user can review this displayed program code and, if necessary, copy it for use in their development environment. The input for this step is program code data in JSON format, and the output is the program code displayed on the user's screen.

[0635] Through the steps described above, the present invention can generate and provide customized program code based on natural language requests while taking into account the user's emotional state.

[0636] (Application Example 2)

[0637] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0638] Conventional systems can process program generation requests from users using natural language, but they fail to adequately enhance user satisfaction because they do not consider the user's emotional state. Furthermore, they struggle to mitigate the stress users experience in specific situations. Therefore, there is a need to provide more effective and comfortable program generation that takes user emotions into account.

[0639] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for receiving user requests in JSON format and transmitting them to the generative AI, means for sending the program code generated by the generative AI back to the server in JSON format, and means for the terminal to send data in JSON format, including the user's emotional data, to the server. This makes it possible to generate optimized program code that takes the user's emotional state into consideration.

[0640] A "terminal" is a device that a user directly operates, and its role is to input user requests and data and send them to the server.

[0641] A "server" is a device that receives and processes user requests and data, and transmits necessary information and program code to a generative AI.

[0642] A "user" is someone who uses the system to request the generation of program code.

[0643] "Natural language" refers to the words and sentences that humans use in everyday life, and is the format used to input program generation requests into a terminal.

[0644] "Program code" refers to text that describes a series of instructions executed by a computer, and is generated by a generative AI based on user requests.

[0645] "Generative AI" refers to artificial intelligence that analyzes user requests and generates appropriate program code based on those requests.

[0646] "Emotional data" refers to information that indicates the user's emotional state, which is recognized from facial expressions, voice, etc., and sent to the server in JSON format.

[0647] The system according to this invention provides a more customized program code by allowing the user to request program generation in natural language and recognizing the user's emotional state using an emotion engine. Specifically, the user accesses the system using a terminal and inputs a request. The terminal collects the user's emotional data along with the request and sends it to the server. The server analyzes the request and emotional data and requests the generative AI to generate program code.

[0648] The emotion engine analyzes the user's facial expressions, voice, and input speed to infer their emotional state. The emotional data analyzed by the emotion engine is sent from the terminal to the server. The server receives this emotional data in JSON format and provides it to the generative AI. The generative AI generates program code based on the request and emotional data, and sends the generated program code back to the server. The server sends this code to the terminal, which then displays it to the user.

[0649] As a concrete example of this system, consider a smart glasses application for a physical store that supports customer service. For example, a store employee wears smart glasses and captures the customer's facial image and voice using a camera and microphone. An emotion engine analyzes the customer's emotional state in real time and sends the analysis results to a server. Based on this emotion data, a generative AI generates a customer service response method appropriate to the customer's emotions and displays it on the smart glasses' display. This allows the store employee to provide the optimal response according to the customer's emotional state.

[0650] For example, if a generative AI detects that a customer is in a "slightly irritated" emotional state, it will suggest a quick and concise way to address the situation. For instance, a message like, "The customer appears angry. Please remain calm and assess the situation," might be generated and displayed on the employee's screen.

[0651] Examples of input prompts for a generative AI model:

[0652] Generate code to recognize customer emotions and suggest appropriate customer service responses. Output a Python program that analyzes image and voice input and returns a response based on the emotion.

[0653] As described above, this system improves user satisfaction by considering the user's emotional state and generating optimal program code. Furthermore, a variety of applications are possible, such as supporting customer service in physical stores.

[0654] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0655] Step 1: The user enters the request in natural language.

[0656] The user uses the terminal interface to input a program generation request in natural language. For example, the user's input might be, "I want to create a simple addition program."

[0657] Step 2: The device recognizes the user's emotions.

[0658] The emotion engine built into the device infers the user's emotional state from their facial expressions, voice, and input speed. For example, it analyzes facial images captured by the camera and audio data recorded by the microphone to recognize an emotional state such as "slightly irritated."

[0659] Step 3: The device sends the request and sentiment data to the server.

[0660] The device sends the user's natural language request and recognized emotion data to the server in JSON format. For example, it sends data in the format {"request": "I want to create a simple addition program", "emotion": "I'm a little annoyed"}.

[0661] Step 4: The server analyzes the data and transmits it to the generative AI.

[0662] The server analyzes the JSON data received from the terminal and extracts user requests and sentiment data. It then provides this data to a generative AI and requests the generation of program code.

[0663] Step 5: The generative AI generates the program code.

[0664] Generative AI generates program code based on requests and emotional data provided by a server. For example, based on the request "I want to create a simple addition program" and the emotional data "I'm a little irritated," it generates concise program code.

[0665] Step 6: The program code generated by the generative AI is sent back to the server.

[0666] The generative AI returns the generated program code to the server in JSON format. For example, it returns data in the format {"code": "def add(a, b): return a + b"}.

[0667] Step 7: The server sends the program code to the terminal.

[0668] The server sends the program code received from the generative AI to the terminal. The terminal converts the received program code into data for display to the user and displays it.

[0669] Step 8: The terminal displays the program code to the user.

[0670] The terminal displays the program code sent from the server to the user. The user can review the displayed program code and use it in their own development environment as needed. At this time, the user confirms that the generated code is concise and easy to understand.

[0671] The above steps enable the generation and display of program code that takes the user's emotional state into consideration.

[0672] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0673] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0674] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0675] [Third Embodiment]

[0676] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0677] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0678] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0679] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0680] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0681] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0682] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0683] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0684] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0685] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0686] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0687] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0688] The system according to the present invention provides a mechanism in which a user requests program generation in natural language, and a server and a generative AI generate program code based on that request. This allows even users with little programming knowledge to easily create and use program code.

[0689] The user accesses the system's input interface using a terminal. For example, the user might input "I want to create a simple addition program" in natural language. The terminal receives this request, generates a request to send to the server, and sends it to the server.

[0690] The server analyzes and understands the user's request received from the terminal. Based on the analysis, the server requests the generative AI to generate program code. The generative AI generates appropriate program code according to the user's request and sends the result back to the server. The generative AI understands the user's request using natural language processing technology and generates code based on the algorithm.

[0691] The server sends the program code received from the generative AI back to the terminal. The terminal displays the program code received from the server to the user. The user can copy this displayed program code as is and use it for their own purposes, or modify it as needed and execute it.

[0692] As a concrete example, if a user requests to "create a simple addition program," the generative AI would generate code using the following logical procedure: First, it extracts the keywords "addition" and "program" from the user's request, and based on these, it generates a program that takes two numbers as input and outputs their sum. The generated program code is easy for the user to understand; for example, it declares two variables, assigns numbers to them, calculates their sum, and displays it.

[0693] This system allows users to immediately utilize concrete program code without requiring specialized programming knowledge. Furthermore, the collaboration between the server and generative AI enables the rapid generation and efficient delivery of optimal code tailored to user requirements. This system can be used in a wide range of fields, including education, prototyping, and lightweight application development.

[0694] To implement this invention, since specific program code is not provided, an understanding of the underlying technologies and processes of this system is crucial. By clearly defining how each means interacts, users can efficiently generate programs.

[0695] The following describes the processing flow.

[0696] Step 1:

[0697] The user accesses the system's input interface using a terminal. For example, they might open a web browser and display a dedicated webpage.

[0698] Step 2:

[0699] The user enters what they want to achieve in natural language into the input interface and clicks the submit button. For example, they might enter, "I want to create a simple addition program."

[0700] Step 3:

[0701] The terminal retrieves the user's input and generates request data in JSON format. For example, the data format will be as follows:

[0702] json

[0703] {

[0704] "user_request": "I want to create a simple addition program."

[0705] }

[0706] Step 4:

[0707] The terminal generates request data and sends it to the server. Asynchronous communication (e.g., HTTP POST request) is performed over the network.

[0708] Step 5:

[0709] The server receives request data from the terminal and analyzes the user's request. The server understands the content of the request data and generates a request in an appropriate format for the generative AI.

[0710] Step 6:

[0711] The server requests the generative AI to generate program code. An API request is sent to the generative AI to appropriately convey the user's request.

[0712] Step 7:

[0713] A generative AI receives a request from a server and uses natural language processing techniques to understand the user's request. It then generates program code. For example, it might understand an "addition program" and generate Python code for it.

[0714] Step 8:

[0715] The generative AI sends the generated program code back to the server. For example, it sends response data containing the program code in JSON format.

[0716] Step 9:

[0717] The server receives response data from the generative AI and extracts the program code. The server then generates response data to send the extracted program code back to the terminal.

[0718] Step 10:

[0719] The server sends the generated response data to the terminal. Asynchronous communication is performed over the network to return the data to the terminal.

[0720] Step 11:

[0721] The terminal receives response data from the server and extracts the program code. For example, it extracts "generated_code" from the response data.

[0722] Step 12:

[0723] The program code received by the terminal is displayed to the user. For example, it is inserted into an HTML element that displays the program code on the user's screen.

[0724] Step 13:

[0725] The user reviews the program code displayed on the terminal, copies it as needed, and uses it in their development environment. The user can then run the generated code as is or customize it for use.

[0726] The above outlines the specific processing steps from when a user requests program generation until they actually receive the generated code. Through these steps, users can efficiently generate and utilize program code.

[0727] (Example 1)

[0728] Next, we will describe Example 1. 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."

[0729] Conventional program generation technologies have had the problem that it is difficult for users with little programming knowledge to easily generate program code. Furthermore, specialized knowledge is required to quickly generate and use specific program code, and there is a need for a system that users can operate intuitively. To solve these problems, this invention aims to provide a system that can request program generation in natural language, enabling even users with little programming knowledge to easily create and use program code.

[0730] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0731] In this invention, the server includes means for the user to request program generation from the system in natural language, means for the terminal to send the user's request to the server, means for the server to analyze the user's request and request program generation from a generative AI model, means for the generative AI model to generate program code based on the user's request, means for the server to return the generated program code to the terminal, means for the terminal to display the generated program code to the user, and means for the user to check and use the generated program code through the terminal. This makes it possible for even users with little programming expertise to intuitively request program generation using natural language and quickly obtain appropriate program code.

[0732] A "user" refers to a person or group that uses the system to request program generation.

[0733] A "terminal" refers to a device used by a user to access a system, input requests, and view generated program code.

[0734] A "server" refers to a computer system that receives and analyzes user requests and instructs the AI ​​model to generate program code.

[0735] A "generative AI model" refers to an artificial intelligence model that generates program code based on a user's requests in natural language.

[0736] "Program generation" refers to the process of automatically creating program code based on specified requirements.

[0737] "Natural language" refers to the language that humans use on a daily basis, and is used to describe requests and instructions to systems.

[0738] A "prompt statement" refers to a natural language sentence used to instruct a generative AI model to generate program code.

[0739] Modes for carrying out the invention

[0740] The system according to the present invention provides a mechanism in which a user requests program generation in natural language, and a server and a generation AI model are used to generate program code based on that request. This makes it easy for users with little programming knowledge to create and use program code.

[0741] Hardware and software details

[0742] Hardware:

[0743] Devices: PCs, smartphones, tablets, etc.

[0744] Server: A cloud server equipped with a high-performance processor (e.g., a cloud hosting service).

[0745] software:

[0746] Natural language processing technology (e.g., OpenAI's GPT model used as a generative AI model).

[0747] A web browser (e.g., Google Chrome, Mozilla Firefox, etc.).

[0748] Communication protocol (e.g., HTTP / HTTPS).

[0749] System operation procedures and examples of operation

[0750] User actions

[0751] The user accesses the system's input interface using their own device. For example, they access a specific URL through a web browser and enter a request in natural language into the input field on the interface. As a concrete example, the user might enter "I want to create a simple addition program."

[0752] Terminal operation

[0753] The terminal receives user input and generates a request to send to the server. The request contains the natural language text entered by the user. This request is sent to the server using the HTTP / HTTPS protocol.

[0754] Server operation

[0755] The server analyzes the request received from the terminal and performs the necessary processing to understand its content. Based on the analysis results, it sends instructions to the generating AI model to generate program code. The instructions include prompt statements created based on the user's request. For example, in response to the request "I want to create a simple addition program," the following prompt statement will be generated.

[0756] Example of a prompt:

[0757] Please generate a Python program based on the following:

[0758] 1. Receive two numbers as input.

[0759] 2. Calculate their sum.

[0760] 3. Output the total.

[0761] How generative AI models work

[0762] The generative AI model generates program code based on prompt messages received from the server. The generative AI model uses natural language processing techniques to assemble appropriate code according to the user's request. The generated code is then returned to the server.

[0763] Server restart

[0764] The server sends the program code received from the generated AI model back to the terminal. Communication is conducted using the HTTP / HTTPS protocol.

[0765] Restarting the device

[0766] The terminal displays the program code received from the server to the user. The user can review the displayed code, copy it, and use it as is. They can also modify the code as needed and then execute it.

[0767] Specific example

[0768] If a user requests to "create a simple addition program," the AI ​​model generates the code using the following steps: First, it extracts the keywords "addition" and "program" from the user's request, and based on these, it generates a program that takes two numbers as input and outputs their sum. The generated program code is easy for the user to understand, declaring two variables, assigning numbers to them, calculating their sum, and displaying it.

[0769] This system allows users to immediately utilize concrete program code without requiring specialized programming knowledge. For example, it can be used for programming education in schools, rapid prototype creation, and everyday small programming tasks. Furthermore, the collaboration between the server and the generated AI model ensures that high-quality code tailored to the user's specific requirements is quickly provided, improving work efficiency.

[0770] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0771] Step 1:

[0772] The user enters the request in natural language.

[0773] The user accesses the system's input interface using their own device. For example, the user accesses a specific URL through a web browser and enters "I want to create a simple addition program" into the input field on the interface. This input becomes a natural language request used for the next process.

[0774] Input and output

[0775] Input: User's request in natural language (e.g., "I want to create a simple addition program")

[0776] Output: Generated natural language request

[0777] Specific actions

[0778] The user enters their request into the input field and clicks the submit button.

[0779] Step 2:

[0780] The terminal sends the user's request to the server.

[0781] The terminal receives a natural language request entered by the user and generates a request to send it to the server. This request contains the natural language text entered by the user. The request is sent to the server using the HTTP / HTTPS protocol.

[0782] Input and output

[0783] Input: User's natural language request

[0784] Output: HTTP request sent to the server

[0785] Specific actions

[0786] The device retrieves user input and sends an HTTP request to the server using the fetch API or AJAX.

[0787] Step 3:

[0788] The server analyzes the user's request and sends a prompt message to the generative AI model.

[0789] The server analyzes the request received from the terminal and performs the necessary data processing to understand the user's request. Based on the analysis results, it sends instructions to the AI ​​model to generate program code. These instructions include prompt statements created based on the user's request. For example, in response to the request "I want to create a simple addition program," the server will generate prompt statements such as "Generate a Python program based on the following: 1. Receive two numbers as input 2. Calculate their sum 3. Output the sum."

[0790] Input and output

[0791] Input: HTTP request containing the user's request

[0792] Output: Prompt message sent to the generated AI model

[0793] Specific actions

[0794] The server parses the request body, generates a prompt, and sends it to the AI ​​model.

[0795] Step 4:

[0796] The generative AI model generates program code.

[0797] The generative AI model generates program code based on prompt messages received from the server. Using natural language processing techniques, the generative AI model constructs appropriate code in response to user requests. The generated code is then returned to the server.

[0798] Input and output

[0799] Input: Prompt message sent from the server

[0800] Output: Generated program code

[0801] Specific actions

[0802] The generative AI model analyzes the prompt text, generates code based on the algorithm, and sends the result back to the server.

[0803] Step 5:

[0804] The server sends the generated program code back to the terminal.

[0805] The server sends the program code received from the generated AI model back to the terminal. This communication uses the HTTP / HTTPS protocol. The server formats the generated program code appropriately and sends it to the terminal.

[0806] Input and output

[0807] Input: Program code received from the generated AI model

[0808] Output: HTTP response sent to the terminal

[0809] Specific actions

[0810] The server formats the generated code and sends it to the terminal as an HTTP response.

[0811] Step 6:

[0812] The terminal displays the generated program code to the user.

[0813] The terminal displays the program code received from the server to the user. The user can review the displayed code, copy it, and use it as is. They can also modify the code as needed and then execute it.

[0814] Input and output

[0815] Input: HTTP response received from the server

[0816] Output: Program code displayed to the user

[0817] Specific actions

[0818] The program code received by the terminal is displayed in the web browser.

[0819] (Application Example 1)

[0820] Next, we will explain Application Example 1. In the following explanation, 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."

[0821] Traditional food delivery services have the problem that users have to manually configure detailed settings when placing specific customized orders, which is time-consuming and cumbersome. Furthermore, there is a challenge in that users with little programming experience have limited means to efficiently generate and utilize programs.

[0822] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0823] In this invention, the server includes means for the user to request program generation from the system in natural language, means for the terminal to send the user's request to the server, means for a generative AI to generate program code based on the user's request, means for the user to input a request in natural language to order a customized meal, means for using a generative AI to analyze the request and automatically generate appropriate order details, and means for the server to send the appropriate order details to the restaurant based on the analysis results. This makes it possible for the user to place a customized order in natural language without any effort, and to efficiently generate and use program code without any programming knowledge.

[0824] A "user" refers to a person who uses the system to input requests in natural language.

[0825] "Natural language" refers to the linguistic expressions that humans use on a daily basis, and is not a specific programming language or command.

[0826] A "system" refers to a device or software that has a series of processes for generating programs or order details based on user requests.

[0827] "Program generation" refers to the act of automatically creating program code based on user requests.

[0828] "Customized dishes" refer to meal menus that have been adjusted according to the user's specific requests.

[0829] "Analyzing requests" refers to the process of understanding the natural language input from a user and converting it into a concrete action.

[0830] "Generative AI" refers to artificial intelligence that understands natural language and automatically generates program code or order details based on user requests.

[0831] "Order details" refers to the specific dishes and detailed settings that a user requests in food delivery.

[0832] A "server" refers to a central computer system that receives and analyzes user requests and, in cooperation with generative AI, returns the necessary data.

[0833] A "terminal" refers to a device (such as a smartphone or tablet) that a user uses to access a system and enter requests.

[0834] "Means of display" refers to functions that visually show the generated program code or order details to the user.

[0835] "Means of transmission" refers to the means of communication used to send user requests and generated data to the appropriate recipient.

[0836] The system according to this invention is a comprehensive platform that can be used by users to request program generation or customized food orders using natural language. Specific embodiments of the system are described below.

[0837] The system provides an interface where users can input requests in natural language using a device such as a smartphone. For example, a user might input a request such as, "I'd like to order chicken curry with less spice." The device receives this request and sends it to the server.

[0838] The server analyzes user requests and issues appropriate instructions to the generative AI. The generative AI uses natural language processing techniques to understand user requests and generate specific order details or program code. This analysis employs advanced natural language processing, such as generative AI models like OpenAI's GPT-3.

[0839] The order details and program code generated by the generative AI are sent back to the terminal via the server. The terminal displays this visually to the user, who then confirms the contents. If there are no problems with the order details, the final order is automatically sent to the store.

[0840] Hardware and software to be used:

[0841] Smartphone: Used as a user interface (UI), it provides functionality for inputting requests in natural language.

[0842] Server: The central system that receives and analyzes user requests, and returns results in cooperation with the generated AI model.

[0843] Generative AI models: These models understand natural language and generate specific order details or program code based on user requests. For example, OpenAI GPT-3 is used.

[0844] Flask: A framework for managing server-side processing and API endpoints.

[0845] As a concrete example, if a user requests "I want to order chicken curry with less spice," the prompt text would be input to the generating AI model as follows:

[0846] Examples of input prompts for a generative AI model:

[0847] text

[0848] Please generate an order for a food delivery app where a user says, "I'd like to order chicken curry with less spice."

[0849] Based on this prompt, the generating AI model generates the following order:

[0850] Example of generated order details:

[0851] text

[0852] Order details:

[0853] Chicken Curry

[0854] Mildly spiced

[0855] Large serving of rice

[0856] Comes with salad

[0857] Special note: Use half the usual amount of spices.

[0858] This system allows users to place customized orders using natural language without any hassle, and enables them to efficiently generate and utilize program code even without programming knowledge.

[0859] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0860] Step 1:

[0861] Users input requests in natural language through a smartphone application. For example, a request might be, "I'd like to order chicken curry with less spice." This input data is collected through the device's interface.

[0862] Step 2:

[0863] The device receives the user's request in natural language as text data and sends that data to the server. The data sent will be in JSON format. For example, the format could be {"request": "I would like to order chicken curry with less spice"}.

[0864] Step 3:

[0865] The server analyzes the user request it receives. This analysis uses natural language processing techniques to generate prompts for a generative AI model (e.g., OpenAI GPT-3). Input data: "I want to order chicken curry with less spice." The resulting prompt is: "Generate the order details for when a user says 'I want to order chicken curry with less spice' in a food delivery app."

[0866] Step 4:

[0867] Based on the analysis results, the system requests the generative AI to generate a program. The server then sends an appropriate API request to the generative AI based on the prompt. For example, the system might send a prompt to the generative AI model instructing it to "generate an order for a food delivery app when a user says, 'I want to order chicken curry with less spice.'"

[0868] Step 5:

[0869] The generative AI generates program code and order details based on the prompt text. The generated data is sent back to the server, and for example, a JSON file in the format {"order": "Chicken curry, less spice, large portion of rice, with salad, special note: Half the usual amount of spice"} is returned.

[0870] Step 6:

[0871] The server receives the generated program code and order details and sends them to the terminal. It may also include logs of the processes required for analysis and generation in its response.

[0872] Step 7:

[0873] The terminal displays the data received from the server through the user interface. The user reviews this, and if there are no problems, the order details are automatically sent to the restaurant. Specifically, the order details displayed might be: "Chicken curry, less spice, large portion of rice, with salad, special note: use half the usual amount of spice."

[0874] Step 8:

[0875] After final user confirmation, the order details are automatically sent to the restaurant. The restaurant then prepares the food according to the user's customized order. At this point, the ordering process is complete, and the user receives a notification. For example, the user may be notified of their order ID and be able to track the delivery status.

[0876] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0877] The system according to the present invention not only allows users to request program generation in natural language, but also uses an emotion engine to recognize the user's emotional state and adjusts the operation of the generative AI based on that emotional state to provide a more customized program code.

[0878] The user accesses the system's input interface using a terminal. For example, they might open a web browser and access a dedicated webpage. At this point, the user might input in natural language, "I want to create a simple addition program." The terminal has an emotion engine built in that infers the user's emotional state from their facial expressions, voice, and input speed during the input process.

[0879] The emotion engine analyzes the user's emotions and notifies the device of the results. The device sends the emotion data to the server in JSON format along with the user's request. For example, data indicating the user's emotional state, such as "feeling a little irritated," may be added.

[0880] The server receives and analyzes user requests and emotion data from the terminal. Based on the analysis results, the server requests the generative AI to generate program code. At this time, the user's emotion data is also provided to the generative AI.

[0881] Generative AI generates program code based on requests from the server and user emotion data. For example, if the AI ​​analyzes that the user is "a little irritated," it selects concise and quickly generated code and provides it in a way that does not cause the user stress.

[0882] The program code generated by the generative AI is sent back to the server. The server sends the received program code back to the terminal, which then displays it to the user. The user can review the generated program code, copy it as needed, and use it in their own development environment.

[0883] As a concrete example, if a user requests to "create a simple addition program" and is perceived to be in a "slightly irritated" emotional state, the generative AI would generate code using the following logical steps: First, it extracts the keywords "addition" and "program" from the user's request, and based on that, it generates a program that takes two numbers as input and outputs their sum. Furthermore, the code is written simply and clearly so as not to stress the user.

[0884] The advantage of this system lies in its ability to improve user satisfaction by generating program code that takes into account the user's current emotional state. For example, it can be customized to the situation, providing quick solutions when the user is anxious and providing code with detailed explanations when the user is relaxed.

[0885] For the present invention to be implemented, it is crucial that the emotion engine recognizes the user's emotions, and that the server and generative AI operate based on that information. This allows the user to efficiently generate and utilize program code that meets their specific needs.

[0886] The following describes the processing flow.

[0887] Step 1:

[0888] The user accesses the system's input interface using a terminal. For example, the user opens a web browser and displays a dedicated web page.

[0889] Step 2:

[0890] The user enters what they want to achieve in natural language into the input interface. For example, they might enter, "I want to create a simple addition program."

[0891] Step 3:

[0892] The emotion engine analyzes the user's facial expressions, voice, and typing speed during input to recognize the user's emotional state. For example, it might determine that the user is "a little irritated."

[0893] Step 4:

[0894] The device converts the user's request and recognized emotional state into JSON-formatted request data. For example, the data format will be as follows:

[0895] json

[0896] {

[0897] "user_request": "I want to create a simple addition program",

[0898] "user_emotion": "A little irritated"

[0899] }

[0900] Step 5:

[0901] The terminal generates request data and sends it to the server. Asynchronous communication (e.g., HTTP POST request) is performed over the network.

[0902] Step 6:

[0903] The server receives request data from the terminal and analyzes the user's requests and sentiment data. The server understands the content of the request data and converts it into an appropriate format for forwarding the request to the generative AI.

[0904] Step 7:

[0905] The server requests the generative AI to generate program code. It also sends an API request to the generative AI to appropriately convey the user's request and emotional data.

[0906] Step 8:

[0907] A generative AI receives a request from a server and uses natural language processing techniques to understand the user's request. It then considers emotional data when generating program code. For example, if the user is "a little irritated," the generative AI will create concise and quickly executable program code.

[0908] Step 9:

[0909] The generative AI sends the generated program code back to the server in JSON format. The data format includes the generated program code.

[0910] Step 10:

[0911] The server receives response data from the generative AI and extracts the program code. The server then generates response data to send the extracted program code back to the terminal.

[0912] Step 11:

[0913] The server sends the generated response data to the terminal. It then sends the data back to the terminal via asynchronous communication over the network.

[0914] Step 12:

[0915] The terminal receives response data from the server and extracts the program code. For example, it extracts "generated_code" from the response data.

[0916] Step 13:

[0917] The program code received by the terminal is displayed to the user. For example, it is inserted into an HTML element that displays the program code on the user's screen.

[0918] Step 14:

[0919] The user reviews the program code displayed on the terminal, copies it as needed, and uses it in their development environment. The user can then run the generated code as is or further customize it for use.

[0920] The above outlines the specific processing steps involved in a user requesting program generation using the emotion engine and receiving the generated code. Through these steps, users can efficiently generate and utilize optimal program code tailored to their own emotional state.

[0921] (Example 2)

[0922] Next, we will describe Example 2. 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."

[0923] Traditional program generation systems fail to adequately improve user satisfaction because they provide standardized program code without considering the user's emotional state. Furthermore, some users experienced problems with the rapid generation of appropriate code in stressful or urgent situations. This can hinder efficient program generation, highlighting the need for improved user experience.

[0924] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving user requests and emotional data in JSON format and transmitting them to the generative AI, means for sending the program code generated by the generative AI back to the server in JSON format, and means for sending the generated program code back to the terminal. This makes it possible to generate customized program code that takes into account the user's emotional state.

[0925] A "user" is someone who requests program generation from the system using natural language.

[0926] A "system" is a mechanism that performs a series of processes, generating and delivering customized program code based on the user's requests and emotional state.

[0927] A "terminal" is a device through which a user accesses a system, inputs requests, and recognizes their emotional state.

[0928] A "server" is a device that analyzes user requests and emotional data, requests the generative AI to generate program code, and sends the generated code back to the terminal.

[0929] An "emotion engine" is a software or hardware component that analyzes the user's facial expressions, voice, input speed, etc., to recognize the user's emotional state.

[0930] "Generative AI" refers to artificial intelligence models that generate appropriate program code based on the user's requests and emotional state.

[0931] A "request" is a user's request in natural language for the system to generate specific program code.

[0932] "Emotional data" refers to data that the emotion engine recognizes the user's emotional state and expresses in JSON format.

[0933] "Program code" refers to the source code generated by a generative AI based on the user's requests and emotional state.

[0934] "JSON format" is an abbreviation for JavaScript Object Notation, and it is a method of representing data in a lightweight text format.

[0935] The system according to the present invention begins with the user accessing the system's input interface using a terminal. For example, the user opens a web browser, accesses a dedicated web page, and inputs in natural language, "I want to create a simple addition program."

[0936] The device incorporates an emotion engine that infers the user's emotional state from their facial expressions, voice, and input speed during input. This emotion engine uses facial recognition software, voice analysis software, and other tools to analyze the user's emotional state in real time and obtain the results. For example, if the device detects that the user is "a little irritated," that information is sent to the device as emotion data.

[0937] Next, the terminal sends the user's request along with emotional data in JSON format to the server. The server analyzes the received user request and emotional data and requests the generative AI to generate program code. The generative AI generates appropriate program code based on the request from the server and the user's emotional data.

[0938] Generative AI, for example, if it analyzes that a user is "a little irritated," will select a program code that is concise and can be executed quickly, and deliver it in a way that does not cause the user stress. If the user is relaxed, it can also provide code with detailed explanations.

[0939] The generated program code is sent back to the server, which then sends the code to the terminal. The terminal displays the received program code to the user. The user can review the generated program code and, if necessary, copy it for use in their own development environment.

[0940] As a concrete example, if a user requests to "create a simple addition program" and is in a "slightly irritated" emotional state, the generative AI will generate concise code as follows. An example prompt would be, "Generate Python code for a user who requests to 'create a simple addition program' and is slightly irritated." In this way, it becomes possible to generate customized program code that takes the user's emotional state into account.

[0941] As described above, the present invention improves user satisfaction and achieves efficient program generation by generating program code while taking into account the user's emotional state.

[0942] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0943] Step 1:

[0944] The user accesses a dedicated webpage and enters "I want to create a simple addition program" in natural language. The input is entered into the text field on the webpage via the keyboard, and the system is sent when the submit button is clicked. The input here is the user's request, and the output becomes the data sent to the terminal.

[0945] Step 2:

[0946] The device incorporates an emotion engine that recognizes the user's facial expressions, voice, and input speed in real time. The emotion engine uses a dedicated camera and microphone to collect data and processes it to infer the user's emotions. For example, if the voice is sharp and fast, it might be interpreted as "slightly irritated." The input for this step is the user's biometric data, and the output is emotion data.

[0947] Step 3:

[0948] The terminal sends user requests and sentiment data to the server in JSON format. Specifically, it serializes the user's requests (e.g., "I want to create a simple addition program") and sentiment data (e.g., "I'm a little annoyed") as a JSON object and sends it to the server over the network. The input for this step is the user's requests and sentiment data, and the output is the JSON data containing them.

[0949] Step 4:

[0950] The server parses the received JSON data. First, the server deserializes the JSON data and extracts the user's request and sentiment data. Then, it analyzes the request and creates an appropriate prompt for the generative AI. For example, it might generate a prompt such as, "Generate Python code for a user who requests to 'create a simple addition program' and is slightly frustrated." The input for this step is JSON data, and the output is a prompt for the generative AI.

[0951] Step 5:

[0952] The server sends a prompt to the generative AI. Based on the received prompt, the generative AI generates appropriate program code, taking into account the user's request and emotional state. For example, it might generate concise and quickly executable Python code. The input for this step is the prompt, and the output is the generated program code.

[0953] Step 6:

[0954] The generated program code is sent back to the server. The server converts the received program code into JSON format and sends it to the terminal. The input for this step is program code from a generative AI, and the output is program code data in JSON format.

[0955] Step 7:

[0956] The terminal parses the program code received from the server and displays it to the user. The display is done using a text area on a web page or a separate dedicated viewer. The user can review this displayed program code and, if necessary, copy it for use in their development environment. The input for this step is program code data in JSON format, and the output is the program code displayed on the user's screen.

[0957] Through the steps described above, the present invention can generate and provide customized program code based on natural language requests while taking into account the user's emotional state.

[0958] (Application Example 2)

[0959] Next, we will explain application example 2. In the following explanation, 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."

[0960] Conventional systems can process program generation requests from users using natural language, but they fail to adequately enhance user satisfaction because they do not consider the user's emotional state. Furthermore, they struggle to mitigate the stress users experience in specific situations. Therefore, there is a need to provide more effective and comfortable program generation that takes user emotions into account.

[0961] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for receiving user requests in JSON format and transmitting them to the generative AI, means for sending the program code generated by the generative AI back to the server in JSON format, and means for the terminal to send data in JSON format, including the user's emotional data, to the server. This makes it possible to generate optimized program code that takes the user's emotional state into consideration.

[0962] A "terminal" is a device that a user directly operates, and its role is to input user requests and data and send them to the server.

[0963] A "server" is a device that receives and processes user requests and data, and transmits necessary information and program code to a generative AI.

[0964] A "user" is someone who uses the system to request the generation of program code.

[0965] "Natural language" refers to the words and sentences that humans use in everyday life, and is the format used to input program generation requests into a terminal.

[0966] "Program code" refers to text that describes a series of instructions executed by a computer, and is generated by a generative AI based on user requests.

[0967] "Generative AI" refers to artificial intelligence that analyzes user requests and generates appropriate program code based on those requests.

[0968] "Emotional data" refers to information that indicates the user's emotional state, which is recognized from facial expressions, voice, etc., and sent to the server in JSON format.

[0969] The system according to this invention provides a more customized program code by allowing the user to request program generation in natural language and recognizing the user's emotional state using an emotion engine. Specifically, the user accesses the system using a terminal and inputs a request. The terminal collects the user's emotional data along with the request and sends it to the server. The server analyzes the request and emotional data and requests the generative AI to generate program code.

[0970] The emotion engine analyzes the user's facial expressions, voice, and input speed to infer their emotional state. The emotional data analyzed by the emotion engine is sent from the terminal to the server. The server receives this emotional data in JSON format and provides it to the generative AI. The generative AI generates program code based on the request and emotional data, and sends the generated program code back to the server. The server sends this code to the terminal, which then displays it to the user.

[0971] As a concrete example of this system, consider a smart glasses application for a physical store that supports customer service. For example, a store employee wears smart glasses and captures the customer's facial image and voice using a camera and microphone. An emotion engine analyzes the customer's emotional state in real time and sends the analysis results to a server. Based on this emotion data, a generative AI generates a customer service response method appropriate to the customer's emotions and displays it on the smart glasses' display. This allows the store employee to provide the optimal response according to the customer's emotional state.

[0972] For example, if a generative AI detects that a customer is in a "slightly irritated" emotional state, it will suggest a quick and concise way to address the situation. For instance, a message like, "The customer appears angry. Please remain calm and assess the situation," might be generated and displayed on the employee's screen.

[0973] Examples of input prompts for a generative AI model:

[0974] Generate code to recognize customer emotions and suggest appropriate customer service responses. Output a Python program that analyzes image and voice input and returns a response based on the emotion.

[0975] As described above, this system improves user satisfaction by considering the user's emotional state and generating optimal program code. Furthermore, a variety of applications are possible, such as supporting customer service in physical stores.

[0976] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0977] Step 1: The user enters the request in natural language.

[0978] The user uses the terminal interface to input a program generation request in natural language. For example, the user's input might be, "I want to create a simple addition program."

[0979] Step 2: The device recognizes the user's emotions.

[0980] The emotion engine built into the device infers the user's emotional state from their facial expressions, voice, and input speed. For example, it analyzes facial images captured by the camera and audio data recorded by the microphone to recognize an emotional state such as "slightly irritated."

[0981] Step 3: The device sends the request and sentiment data to the server.

[0982] The device sends the user's natural language request and recognized emotion data to the server in JSON format. For example, it sends data in the format {"request": "I want to create a simple addition program", "emotion": "I'm a little annoyed"}.

[0983] Step 4: The server analyzes the data and transmits it to the generative AI.

[0984] The server analyzes the JSON data received from the terminal and extracts user requests and sentiment data. It then provides this data to a generative AI and requests the generation of program code.

[0985] Step 5: The generative AI generates the program code.

[0986] Generative AI generates program code based on requests and emotional data provided by a server. For example, based on the request "I want to create a simple addition program" and the emotional data "I'm a little irritated," it generates concise program code.

[0987] Step 6: The program code generated by the generative AI is sent back to the server.

[0988] The generative AI returns the generated program code to the server in JSON format. For example, it returns data in the format {"code": "def add(a, b): return a + b"}.

[0989] Step 7: The server sends the program code to the terminal.

[0990] The server sends the program code received from the generative AI to the terminal. The terminal converts the received program code into data for display to the user and displays it.

[0991] Step 8: The terminal displays the program code to the user.

[0992] The terminal displays the program code sent from the server to the user. The user can review the displayed program code and use it in their own development environment as needed. At this time, the user confirms that the generated code is concise and easy to understand.

[0993] The above steps enable the generation and display of program code that takes the user's emotional state into consideration.

[0994] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0995] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0996] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0997] [Fourth Embodiment]

[0998] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0999] As shown in Figure 7, the 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.

[1000] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1001] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1002] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1003] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1004] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1005] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1006] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1007] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[1008] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1009] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1010] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1011] The system according to the present invention provides a mechanism in which a user requests program generation in natural language, and a server and a generative AI generate program code based on that request. This allows even users with little programming knowledge to easily create and use program code.

[1012] The user accesses the system's input interface using a terminal. For example, the user might input "I want to create a simple addition program" in natural language. The terminal receives this request, generates a request to send to the server, and sends it to the server.

[1013] The server analyzes and understands the user's request received from the terminal. Based on the analysis, the server requests the generative AI to generate program code. The generative AI generates appropriate program code according to the user's request and sends the result back to the server. The generative AI understands the user's request using natural language processing technology and generates code based on the algorithm.

[1014] The server sends the program code received from the generative AI back to the terminal. The terminal displays the program code received from the server to the user. The user can copy this displayed program code as is and use it for their own purposes, or modify it as needed and execute it.

[1015] As a concrete example, if a user requests to "create a simple addition program," the generative AI would generate code using the following logical procedure: First, it extracts the keywords "addition" and "program" from the user's request, and based on these, it generates a program that takes two numbers as input and outputs their sum. The generated program code is easy for the user to understand; for example, it declares two variables, assigns numbers to them, calculates their sum, and displays it.

[1016] This system allows users to immediately utilize concrete program code without requiring specialized programming knowledge. Furthermore, the collaboration between the server and generative AI enables the rapid generation and efficient delivery of optimal code tailored to user requirements. This system can be used in a wide range of fields, including education, prototyping, and lightweight application development.

[1017] To implement this invention, since specific program code is not provided, an understanding of the underlying technologies and processes of this system is crucial. By clearly defining how each means interacts, users can efficiently generate programs.

[1018] The following describes the processing flow.

[1019] Step 1:

[1020] The user accesses the system's input interface using a terminal. For example, they might open a web browser and display a dedicated webpage.

[1021] Step 2:

[1022] The user enters what they want to achieve in natural language into the input interface and clicks the submit button. For example, they might enter, "I want to create a simple addition program."

[1023] Step 3:

[1024] The terminal retrieves the user's input and generates request data in JSON format. For example, the data format will be as follows:

[1025] json

[1026] {

[1027] "user_request": "I want to create a simple addition program."

[1028] }

[1029] Step 4:

[1030] The terminal generates request data and sends it to the server. Asynchronous communication (e.g., HTTP POST request) is performed over the network.

[1031] Step 5:

[1032] The server receives request data from the terminal and analyzes the user's request. The server understands the content of the request data and generates a request in an appropriate format for the generative AI.

[1033] Step 6:

[1034] The server requests the generative AI to generate program code. An API request is sent to the generative AI to appropriately convey the user's request.

[1035] Step 7:

[1036] A generative AI receives a request from a server and uses natural language processing techniques to understand the user's request. It then generates program code. For example, it might understand an "addition program" and generate Python code for it.

[1037] Step 8:

[1038] The generative AI sends the generated program code back to the server. For example, it sends response data containing the program code in JSON format.

[1039] Step 9:

[1040] The server receives response data from the generative AI and extracts the program code. The server then generates response data to send the extracted program code back to the terminal.

[1041] Step 10:

[1042] The server sends the generated response data to the terminal. Asynchronous communication is performed over the network to return the data to the terminal.

[1043] Step 11:

[1044] The terminal receives response data from the server and extracts the program code. For example, it extracts "generated_code" from the response data.

[1045] Step 12:

[1046] The program code received by the terminal is displayed to the user. For example, it is inserted into an HTML element that displays the program code on the user's screen.

[1047] Step 13:

[1048] The user reviews the program code displayed on the terminal, copies it as needed, and uses it in their development environment. The user can then run the generated code as is or customize it for use.

[1049] The above outlines the specific processing steps from when a user requests program generation until they actually receive the generated code. Through these steps, users can efficiently generate and utilize program code.

[1050] (Example 1)

[1051] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1052] Conventional program generation technologies have had the problem that it is difficult for users with little programming knowledge to easily generate program code. Furthermore, specialized knowledge is required to quickly generate and use specific program code, and there is a need for a system that users can operate intuitively. To solve these problems, this invention aims to provide a system that can request program generation in natural language, enabling even users with little programming knowledge to easily create and use program code.

[1053] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1054] In this invention, the server includes means for the user to request program generation from the system in natural language, means for the terminal to send the user's request to the server, means for the server to analyze the user's request and request program generation from a generative AI model, means for the generative AI model to generate program code based on the user's request, means for the server to return the generated program code to the terminal, means for the terminal to display the generated program code to the user, and means for the user to check and use the generated program code through the terminal. This makes it possible for even users with little programming expertise to intuitively request program generation using natural language and quickly obtain appropriate program code.

[1055] A "user" refers to a person or group that uses the system to request program generation.

[1056] A "terminal" refers to a device used by a user to access a system, input requests, and view generated program code.

[1057] A "server" refers to a computer system that receives and analyzes user requests and instructs the AI ​​model to generate program code.

[1058] A "generative AI model" refers to an artificial intelligence model that generates program code based on a user's requests in natural language.

[1059] "Program generation" refers to the process of automatically creating program code based on specified requirements.

[1060] "Natural language" refers to the language that humans use on a daily basis, and is used to describe requests and instructions to systems.

[1061] A "prompt statement" refers to a natural language sentence used to instruct a generative AI model to generate program code.

[1062] Modes for carrying out the invention

[1063] The system according to the present invention provides a mechanism in which a user requests program generation in natural language, and a server and a generation AI model are used to generate program code based on that request. This makes it easy for users with little programming knowledge to create and use program code.

[1064] Hardware and software details

[1065] Hardware:

[1066] Devices: PCs, smartphones, tablets, etc.

[1067] Server: A cloud server equipped with a high-performance processor (e.g., a cloud hosting service).

[1068] software:

[1069] Natural language processing technology (e.g., OpenAI's GPT model used as a generative AI model).

[1070] A web browser (e.g., Google Chrome, Mozilla Firefox, etc.).

[1071] Communication protocol (e.g., HTTP / HTTPS).

[1072] System operation procedures and examples of operation

[1073] User actions

[1074] The user accesses the system's input interface using their own device. For example, they access a specific URL through a web browser and enter a request in natural language into the input field on the interface. As a concrete example, the user might enter "I want to create a simple addition program."

[1075] Terminal operation

[1076] The terminal receives user input and generates a request to send to the server. The request contains the natural language text entered by the user. This request is sent to the server using the HTTP / HTTPS protocol.

[1077] Server operation

[1078] The server analyzes the request received from the terminal and performs the necessary processing to understand its content. Based on the analysis results, it sends instructions to the generating AI model to generate program code. The instructions include prompt statements created based on the user's request. For example, in response to the request "I want to create a simple addition program," the following prompt statement will be generated.

[1079] Example of a prompt:

[1080] Please generate a Python program based on the following:

[1081] 1. Receive two numbers as input.

[1082] 2. Calculate their sum.

[1083] 3. Output the total.

[1084] How generative AI models work

[1085] The generative AI model generates program code based on prompt messages received from the server. The generative AI model uses natural language processing techniques to assemble appropriate code according to the user's request. The generated code is then returned to the server.

[1086] Server restart

[1087] The server sends the program code received from the generated AI model back to the terminal. Communication is conducted using the HTTP / HTTPS protocol.

[1088] Restarting the device

[1089] The terminal displays the program code received from the server to the user. The user can review the displayed code, copy it, and use it as is. They can also modify the code as needed and then execute it.

[1090] Specific example

[1091] If a user requests to "create a simple addition program," the AI ​​model generates the code using the following steps: First, it extracts the keywords "addition" and "program" from the user's request, and based on these, it generates a program that takes two numbers as input and outputs their sum. The generated program code is easy for the user to understand, declaring two variables, assigning numbers to them, calculating their sum, and displaying it.

[1092] This system allows users to immediately utilize concrete program code without requiring specialized programming knowledge. For example, it can be used for programming education in schools, rapid prototype creation, and everyday small programming tasks. Furthermore, the collaboration between the server and the generated AI model ensures that high-quality code tailored to the user's specific requirements is quickly provided, improving work efficiency.

[1093] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1094] Step 1:

[1095] The user enters the request in natural language.

[1096] The user accesses the system's input interface using their own device. For example, the user accesses a specific URL through a web browser and enters "I want to create a simple addition program" into the input field on the interface. This input becomes a natural language request used for the next process.

[1097] Input and output

[1098] Input: User's request in natural language (e.g., "I want to create a simple addition program")

[1099] Output: Generated natural language request

[1100] Specific actions

[1101] The user enters their request into the input field and clicks the submit button.

[1102] Step 2:

[1103] The terminal sends the user's request to the server.

[1104] The terminal receives a natural language request entered by the user and generates a request to send it to the server. This request contains the natural language text entered by the user. The request is sent to the server using the HTTP / HTTPS protocol.

[1105] Input and output

[1106] Input: User's natural language request

[1107] Output: HTTP request sent to the server

[1108] Specific actions

[1109] The device retrieves user input and sends an HTTP request to the server using the fetch API or AJAX.

[1110] Step 3:

[1111] The server analyzes the user's request and sends a prompt message to the generative AI model.

[1112] The server analyzes the request received from the terminal and performs the necessary data processing to understand the user's request. Based on the analysis results, it sends instructions to the AI ​​model to generate program code. These instructions include prompt statements created based on the user's request. For example, in response to the request "I want to create a simple addition program," the server will generate prompt statements such as "Generate a Python program based on the following: 1. Receive two numbers as input 2. Calculate their sum 3. Output the sum."

[1113] Input and output

[1114] Input: HTTP request containing the user's request

[1115] Output: Prompt message sent to the generated AI model

[1116] Specific actions

[1117] The server parses the request body, generates a prompt, and sends it to the AI ​​model.

[1118] Step 4:

[1119] The generative AI model generates program code.

[1120] The generative AI model generates program code based on prompt messages received from the server. Using natural language processing techniques, the generative AI model constructs appropriate code in response to user requests. The generated code is then returned to the server.

[1121] Input and output

[1122] Input: Prompt message sent from the server

[1123] Output: Generated program code

[1124] Specific actions

[1125] The generative AI model analyzes the prompt text, generates code based on the algorithm, and sends the result back to the server.

[1126] Step 5:

[1127] The server sends the generated program code back to the terminal.

[1128] The server sends the program code received from the generated AI model back to the terminal. This communication uses the HTTP / HTTPS protocol. The server formats the generated program code appropriately and sends it to the terminal.

[1129] Input and output

[1130] Input: Program code received from the generated AI model

[1131] Output: HTTP response sent to the terminal

[1132] Specific actions

[1133] The server formats the generated code and sends it to the terminal as an HTTP response.

[1134] Step 6:

[1135] The terminal displays the generated program code to the user.

[1136] The terminal displays the program code received from the server to the user. The user can review the displayed code, copy it, and use it as is. They can also modify the code as needed and then execute it.

[1137] Input and output

[1138] Input: HTTP response received from the server

[1139] Output: Program code displayed to the user

[1140] Specific actions

[1141] The program code received by the terminal is displayed in the web browser.

[1142] (Application Example 1)

[1143] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1144] Traditional food delivery services have the problem that users have to manually configure detailed settings when placing specific customized orders, which is time-consuming and cumbersome. Furthermore, there is a challenge in that users with little programming experience have limited means to efficiently generate and utilize programs.

[1145] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1146] In this invention, the server includes means for the user to request program generation from the system in natural language, means for the terminal to send the user's request to the server, means for a generative AI to generate program code based on the user's request, means for the user to input a request in natural language to order a customized meal, means for using a generative AI to analyze the request and automatically generate appropriate order details, and means for the server to send the appropriate order details to the restaurant based on the analysis results. This makes it possible for the user to place a customized order in natural language without any effort, and to efficiently generate and use program code without any programming knowledge.

[1147] A "user" refers to a person who uses the system to input requests in natural language.

[1148] "Natural language" refers to the linguistic expressions that humans use on a daily basis, and is not a specific programming language or command.

[1149] A "system" refers to a device or software that has a series of processes for generating programs or order details based on user requests.

[1150] "Program generation" refers to the act of automatically creating program code based on user requests.

[1151] "Customized dishes" refer to meal menus that have been adjusted according to the user's specific requests.

[1152] "Analyzing requests" refers to the process of understanding the natural language input from a user and converting it into a concrete action.

[1153] "Generative AI" refers to artificial intelligence that understands natural language and automatically generates program code or order details based on user requests.

[1154] "Order details" refers to the specific dishes and detailed settings that a user requests in food delivery.

[1155] A "server" refers to a central computer system that receives and analyzes user requests and, in cooperation with generative AI, returns the necessary data.

[1156] A "terminal" refers to a device (such as a smartphone or tablet) that a user uses to access a system and enter requests.

[1157] "Means of display" refers to functions that visually show the generated program code or order details to the user.

[1158] "Means of transmission" refers to the means of communication used to send user requests and generated data to the appropriate recipient.

[1159] The system according to this invention is a comprehensive platform that can be used by users to request program generation or customized food orders using natural language. Specific embodiments of the system are described below.

[1160] The system provides an interface where users can input requests in natural language using a device such as a smartphone. For example, a user might input a request such as, "I'd like to order chicken curry with less spice." The device receives this request and sends it to the server.

[1161] The server analyzes user requests and issues appropriate instructions to the generative AI. The generative AI uses natural language processing techniques to understand user requests and generate specific order details or program code. This analysis employs advanced natural language processing, such as generative AI models like OpenAI's GPT-3.

[1162] The order details and program code generated by the generative AI are sent back to the terminal via the server. The terminal displays this visually to the user, who then confirms the contents. If there are no problems with the order details, the final order is automatically sent to the store.

[1163] Hardware and software to be used:

[1164] Smartphone: Used as a user interface (UI), it provides functionality for inputting requests in natural language.

[1165] Server: The central system that receives and analyzes user requests, and returns results in cooperation with the generated AI model.

[1166] Generative AI models: These models understand natural language and generate specific order details or program code based on user requests. For example, OpenAI GPT-3 is used.

[1167] Flask: A framework for managing server-side processing and API endpoints.

[1168] As a concrete example, if a user requests "I want to order chicken curry with less spice," the prompt text would be input to the generating AI model as follows:

[1169] Examples of input prompts for a generative AI model:

[1170] text

[1171] Please generate an order for a food delivery app where a user says, "I'd like to order chicken curry with less spice."

[1172] Based on this prompt, the generating AI model generates the following order:

[1173] Example of generated order details:

[1174] text

[1175] Order details:

[1176] Chicken Curry

[1177] Mildly spiced

[1178] Large serving of rice

[1179] Comes with salad

[1180] Special note: Use half the usual amount of spices.

[1181] This system allows users to place customized orders using natural language without any hassle, and enables them to efficiently generate and utilize program code even without programming knowledge.

[1182] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1183] Step 1:

[1184] Users input requests in natural language through a smartphone application. For example, a request might be, "I'd like to order chicken curry with less spice." This input data is collected through the device's interface.

[1185] Step 2:

[1186] The device receives the user's request in natural language as text data and sends that data to the server. The data sent will be in JSON format. For example, the format could be {"request": "I would like to order chicken curry with less spice"}.

[1187] Step 3:

[1188] The server analyzes the user request it receives. This analysis uses natural language processing techniques to generate prompts for a generative AI model (e.g., OpenAI GPT-3). Input data: "I want to order chicken curry with less spice." The resulting prompt is: "Generate the order details for when a user says 'I want to order chicken curry with less spice' in a food delivery app."

[1189] Step 4:

[1190] Based on the analysis results, the system requests the generative AI to generate a program. The server then sends an appropriate API request to the generative AI based on the prompt. For example, the system might send a prompt to the generative AI model instructing it to "generate an order for a food delivery app when a user says, 'I want to order chicken curry with less spice.'"

[1191] Step 5:

[1192] The generative AI generates program code and order details based on the prompt text. The generated data is sent back to the server, and for example, a JSON file in the format {"order": "Chicken curry, less spice, large portion of rice, with salad, special note: Half the usual amount of spice"} is returned.

[1193] Step 6:

[1194] The server receives the generated program code and order details and sends them to the terminal. It may also include logs of the processes required for analysis and generation in its response.

[1195] Step 7:

[1196] The terminal displays the data received from the server through the user interface. The user reviews this, and if there are no problems, the order details are automatically sent to the restaurant. Specifically, the order details displayed might be: "Chicken curry, less spice, large portion of rice, with salad, special note: use half the usual amount of spice."

[1197] Step 8:

[1198] After final user confirmation, the order details are automatically sent to the restaurant. The restaurant then prepares the food according to the user's customized order. At this point, the ordering process is complete, and the user receives a notification. For example, the user may be notified of their order ID and be able to track the delivery status.

[1199] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1200] The system according to the present invention not only allows users to request program generation in natural language, but also uses an emotion engine to recognize the user's emotional state and adjusts the operation of the generative AI based on that emotional state to provide a more customized program code.

[1201] The user accesses the system's input interface using a terminal. For example, they might open a web browser and access a dedicated webpage. At this point, the user might input in natural language, "I want to create a simple addition program." The terminal has an emotion engine built in that infers the user's emotional state from their facial expressions, voice, and input speed during the input process.

[1202] The emotion engine analyzes the user's emotions and notifies the device of the results. The device sends the emotion data to the server in JSON format along with the user's request. For example, data indicating the user's emotional state, such as "feeling a little irritated," may be added.

[1203] The server receives and analyzes user requests and emotion data from the terminal. Based on the analysis results, the server requests the generative AI to generate program code. At this time, the user's emotion data is also provided to the generative AI.

[1204] Generative AI generates program code based on requests from the server and user emotion data. For example, if the AI ​​analyzes that the user is "a little irritated," it selects concise and quickly generated code and provides it in a way that does not cause the user stress.

[1205] The program code generated by the generative AI is sent back to the server. The server sends the received program code back to the terminal, which then displays it to the user. The user can review the generated program code, copy it as needed, and use it in their own development environment.

[1206] As a concrete example, if a user requests to "create a simple addition program" and is perceived to be in a "slightly irritated" emotional state, the generative AI would generate code using the following logical steps: First, it extracts the keywords "addition" and "program" from the user's request, and based on that, it generates a program that takes two numbers as input and outputs their sum. Furthermore, the code is written simply and clearly so as not to stress the user.

[1207] The advantage of this system lies in its ability to improve user satisfaction by generating program code that takes into account the user's current emotional state. For example, it can be customized to the situation, providing quick solutions when the user is anxious and providing code with detailed explanations when the user is relaxed.

[1208] For the present invention to be implemented, it is crucial that the emotion engine recognizes the user's emotions, and that the server and generative AI operate based on that information. This allows the user to efficiently generate and utilize program code that meets their specific needs.

[1209] The following describes the processing flow.

[1210] Step 1:

[1211] The user accesses the system's input interface using a terminal. For example, the user opens a web browser and displays a dedicated web page.

[1212] Step 2:

[1213] The user enters what they want to achieve in natural language into the input interface. For example, they might enter, "I want to create a simple addition program."

[1214] Step 3:

[1215] The emotion engine analyzes the user's facial expressions, voice, and typing speed during input to recognize the user's emotional state. For example, it might determine that the user is "a little irritated."

[1216] Step 4:

[1217] The device converts the user's request and recognized emotional state into JSON-formatted request data. For example, the data format will be as follows:

[1218] json

[1219] {

[1220] "user_request": "I want to create a simple addition program",

[1221] "user_emotion": "A little irritated"

[1222] }

[1223] Step 5:

[1224] The terminal generates request data and sends it to the server. Asynchronous communication (e.g., HTTP POST request) is performed over the network.

[1225] Step 6:

[1226] The server receives request data from the terminal and analyzes the user's requests and sentiment data. The server understands the content of the request data and converts it into an appropriate format for forwarding the request to the generative AI.

[1227] Step 7:

[1228] The server requests the generative AI to generate program code. It also sends an API request to the generative AI to appropriately convey the user's request and emotional data.

[1229] Step 8:

[1230] A generative AI receives a request from a server and uses natural language processing techniques to understand the user's request. It then considers emotional data when generating program code. For example, if the user is "a little irritated," the generative AI will create concise and quickly executable program code.

[1231] Step 9:

[1232] The generative AI sends the generated program code back to the server in JSON format. The data format includes the generated program code.

[1233] Step 10:

[1234] The server receives response data from the generative AI and extracts the program code. The server then generates response data to send the extracted program code back to the terminal.

[1235] Step 11:

[1236] The server sends the generated response data to the terminal. It then sends the data back to the terminal via asynchronous communication over the network.

[1237] Step 12:

[1238] The terminal receives response data from the server and extracts the program code. For example, it extracts "generated_code" from the response data.

[1239] Step 13:

[1240] The program code received by the terminal is displayed to the user. For example, it is inserted into an HTML element that displays the program code on the user's screen.

[1241] Step 14:

[1242] The user reviews the program code displayed on the terminal, copies it as needed, and uses it in their development environment. The user can then run the generated code as is or further customize it for use.

[1243] The above outlines the specific processing steps involved in a user requesting program generation using the emotion engine and receiving the generated code. Through these steps, users can efficiently generate and utilize optimal program code tailored to their own emotional state.

[1244] (Example 2)

[1245] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1246] Traditional program generation systems fail to adequately improve user satisfaction because they provide standardized program code without considering the user's emotional state. Furthermore, some users experienced problems with the rapid generation of appropriate code in stressful or urgent situations. This can hinder efficient program generation, highlighting the need for improved user experience.

[1247] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving user requests and emotional data in JSON format and transmitting them to the generative AI, means for sending the program code generated by the generative AI back to the server in JSON format, and means for sending the generated program code back to the terminal. This makes it possible to generate customized program code that takes into account the user's emotional state.

[1248] A "user" is someone who requests program generation from the system using natural language.

[1249] A "system" is a mechanism that performs a series of processes, generating and delivering customized program code based on the user's requests and emotional state.

[1250] A "terminal" is a device through which a user accesses a system, inputs requests, and recognizes their emotional state.

[1251] A "server" is a device that analyzes user requests and emotional data, requests the generative AI to generate program code, and sends the generated code back to the terminal.

[1252] An "emotion engine" is a software or hardware component that analyzes the user's facial expressions, voice, input speed, etc., to recognize the user's emotional state.

[1253] "Generative AI" refers to artificial intelligence models that generate appropriate program code based on the user's requests and emotional state.

[1254] A "request" is a user's request in natural language for the system to generate specific program code.

[1255] "Emotional data" refers to data that the emotion engine recognizes the user's emotional state and expresses in JSON format.

[1256] "Program code" refers to the source code generated by a generative AI based on the user's requests and emotional state.

[1257] "JSON format" is an abbreviation for JavaScript Object Notation, and it is a method of representing data in a lightweight text format.

[1258] The system according to the present invention begins with the user accessing the system's input interface using a terminal. For example, the user opens a web browser, accesses a dedicated web page, and inputs in natural language, "I want to create a simple addition program."

[1259] The device incorporates an emotion engine that infers the user's emotional state from their facial expressions, voice, and input speed during input. This emotion engine uses facial recognition software, voice analysis software, and other tools to analyze the user's emotional state in real time and obtain the results. For example, if the device detects that the user is "a little irritated," that information is sent to the device as emotion data.

[1260] Next, the terminal sends the user's request along with emotional data in JSON format to the server. The server analyzes the received user request and emotional data and requests the generative AI to generate program code. The generative AI generates appropriate program code based on the request from the server and the user's emotional data.

[1261] Generative AI, for example, if it analyzes that a user is "a little irritated," will select a program code that is concise and can be executed quickly, and deliver it in a way that does not cause the user stress. If the user is relaxed, it can also provide code with detailed explanations.

[1262] The generated program code is sent back to the server, which then sends the code to the terminal. The terminal displays the received program code to the user. The user can review the generated program code and, if necessary, copy it for use in their own development environment.

[1263] As a concrete example, if a user requests to "create a simple addition program" and is in a "slightly irritated" emotional state, the generative AI will generate concise code as follows. An example prompt would be, "Generate Python code for a user who requests to 'create a simple addition program' and is slightly irritated." In this way, it becomes possible to generate customized program code that takes the user's emotional state into account.

[1264] As described above, the present invention improves user satisfaction and achieves efficient program generation by generating program code while taking into account the user's emotional state.

[1265] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1266] Step 1:

[1267] The user accesses a dedicated webpage and enters "I want to create a simple addition program" in natural language. The input is entered into the text field on the webpage via the keyboard, and the system is sent when the submit button is clicked. The input here is the user's request, and the output becomes the data sent to the terminal.

[1268] Step 2:

[1269] The device incorporates an emotion engine that recognizes the user's facial expressions, voice, and input speed in real time. The emotion engine uses a dedicated camera and microphone to collect data and processes it to infer the user's emotions. For example, if the voice is sharp and fast, it might be interpreted as "slightly irritated." The input for this step is the user's biometric data, and the output is emotion data.

[1270] Step 3:

[1271] The terminal sends user requests and sentiment data to the server in JSON format. Specifically, it serializes the user's requests (e.g., "I want to create a simple addition program") and sentiment data (e.g., "I'm a little annoyed") as a JSON object and sends it to the server over the network. The input for this step is the user's requests and sentiment data, and the output is the JSON data containing them.

[1272] Step 4:

[1273] The server parses the received JSON data. First, the server deserializes the JSON data and extracts the user's request and sentiment data. Then, it analyzes the request and creates an appropriate prompt for the generative AI. For example, it might generate a prompt such as, "Generate Python code for a user who requests to 'create a simple addition program' and is slightly frustrated." The input for this step is JSON data, and the output is a prompt for the generative AI.

[1274] Step 5:

[1275] The server sends a prompt to the generative AI. Based on the received prompt, the generative AI generates appropriate program code, taking into account the user's request and emotional state. For example, it might generate concise and quickly executable Python code. The input for this step is the prompt, and the output is the generated program code.

[1276] Step 6:

[1277] The generated program code is sent back to the server. The server converts the received program code into JSON format and sends it to the terminal. The input for this step is program code from a generative AI, and the output is program code data in JSON format.

[1278] Step 7:

[1279] The terminal parses the program code received from the server and displays it to the user. The display is done using a text area on a web page or a separate dedicated viewer. The user can review this displayed program code and, if necessary, copy it for use in their development environment. The input for this step is program code data in JSON format, and the output is the program code displayed on the user's screen.

[1280] Through the steps described above, the present invention can generate and provide customized program code based on natural language requests while taking into account the user's emotional state.

[1281] (Application Example 2)

[1282] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1283] Conventional systems can process program generation requests from users using natural language, but they fail to adequately enhance user satisfaction because they do not consider the user's emotional state. Furthermore, they struggle to mitigate the stress users experience in specific situations. Therefore, there is a need to provide more effective and comfortable program generation that takes user emotions into account.

[1284] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for receiving user requests in JSON format and transmitting them to the generative AI, means for sending the program code generated by the generative AI back to the server in JSON format, and means for the terminal to send data in JSON format, including the user's emotional data, to the server. This makes it possible to generate optimized program code that takes the user's emotional state into consideration.

[1285] A "terminal" is a device that a user directly operates, and its role is to input user requests and data and send them to the server.

[1286] A "server" is a device that receives and processes user requests and data, and transmits necessary information and program code to a generative AI.

[1287] A "user" is someone who uses the system to request the generation of program code.

[1288] "Natural language" refers to the words and sentences that humans use in everyday life, and is the format used to input program generation requests into a terminal.

[1289] "Program code" refers to text that describes a series of instructions executed by a computer, and is generated by a generative AI based on user requests.

[1290] "Generative AI" refers to artificial intelligence that analyzes user requests and generates appropriate program code based on those requests.

[1291] "Emotional data" refers to information that indicates the user's emotional state, which is recognized from facial expressions, voice, etc., and sent to the server in JSON format.

[1292] The system according to this invention provides a more customized program code by allowing the user to request program generation in natural language and recognizing the user's emotional state using an emotion engine. Specifically, the user accesses the system using a terminal and inputs a request. The terminal collects the user's emotional data along with the request and sends it to the server. The server analyzes the request and emotional data and requests the generative AI to generate program code.

[1293] The emotion engine analyzes the user's facial expressions, voice, and input speed to infer their emotional state. The emotional data analyzed by the emotion engine is sent from the terminal to the server. The server receives this emotional data in JSON format and provides it to the generative AI. The generative AI generates program code based on the request and emotional data, and sends the generated program code back to the server. The server sends this code to the terminal, which then displays it to the user.

[1294] As a concrete example of this system, consider a smart glasses application for a physical store that supports customer service. For example, a store employee wears smart glasses and captures the customer's facial image and voice using a camera and microphone. An emotion engine analyzes the customer's emotional state in real time and sends the analysis results to a server. Based on this emotion data, a generative AI generates a customer service response method appropriate to the customer's emotions and displays it on the smart glasses' display. This allows the store employee to provide the optimal response according to the customer's emotional state.

[1295] For example, if a generative AI detects that a customer is in a "slightly irritated" emotional state, it will suggest a quick and concise way to address the situation. For instance, a message like, "The customer appears angry. Please remain calm and assess the situation," might be generated and displayed on the employee's screen.

[1296] Examples of input prompts for a generative AI model:

[1297] Generate code to recognize customer emotions and suggest appropriate customer service responses. Output a Python program that analyzes image and voice input and returns a response based on the emotion.

[1298] As described above, this system improves user satisfaction by considering the user's emotional state and generating optimal program code. Furthermore, a variety of applications are possible, such as supporting customer service in physical stores.

[1299] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1300] Step 1: The user enters the request in natural language.

[1301] The user uses the terminal interface to input a program generation request in natural language. For example, the user's input might be, "I want to create a simple addition program."

[1302] Step 2: The device recognizes the user's emotions.

[1303] The emotion engine built into the device infers the user's emotional state from their facial expressions, voice, and input speed. For example, it analyzes facial images captured by the camera and audio data recorded by the microphone to recognize an emotional state such as "slightly irritated."

[1304] Step 3: The device sends the request and sentiment data to the server.

[1305] The device sends the user's natural language request and recognized emotion data to the server in JSON format. For example, it sends data in the format {"request": "I want to create a simple addition program", "emotion": "I'm a little annoyed"}.

[1306] Step 4: The server analyzes the data and transmits it to the generative AI.

[1307] The server analyzes the JSON data received from the terminal and extracts user requests and sentiment data. It then provides this data to a generative AI and requests the generation of program code.

[1308] Step 5: The generative AI generates the program code.

[1309] Generative AI generates program code based on requests and emotional data provided by a server. For example, based on the request "I want to create a simple addition program" and the emotional data "I'm a little irritated," it generates concise program code.

[1310] Step 6: The program code generated by the generative AI is sent back to the server.

[1311] The generative AI returns the generated program code to the server in JSON format. For example, it returns data in the format {"code": "def add(a, b): return a + b"}.

[1312] Step 7: The server sends the program code to the terminal.

[1313] The server sends the program code received from the generative AI to the terminal. The terminal converts the received program code into data for display to the user and displays it.

[1314] Step 8: The terminal displays the program code to the user.

[1315] The terminal displays the program code sent from the server to the user. The user can review the displayed program code and use it in their own development environment as needed. At this time, the user confirms that the generated code is concise and easy to understand.

[1316] The above steps enable the generation and display of program code that takes the user's emotional state into consideration.

[1317] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1318] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1319] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1320] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1321] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1322] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1323] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1324] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1325] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1326] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1327] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1328] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1329] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1330] 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.

[1331] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1332] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1333] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1334] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1335] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1336] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1337] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[1338] The following is further disclosed regarding the embodiments described above.

[1339] (Claim 1)

[1340] A means by which the user requests program generation from the system using natural language,

[1341] A means by which the terminal sends user requests to the server,

[1342] A means by which the server analyzes the user's request and requests program generation from a generative AI,

[1343] A means by which a generative AI generates program code based on user requests,

[1344] A means for the server to return the generated program code to the terminal,

[1345] A means by which the terminal displays the generated program code to the user.

[1346] A system that includes this.

[1347] (Claim 2)

[1348] A means by which the server receives user requests in JSON format and transmits them to a generative AI,

[1349] A method for returning program code generated by a generative AI to the server in JSON format.

[1350] The system according to claim 1, including the following:

[1351] (Claim 3)

[1352] The system according to claim 1, comprising an interface means for a terminal to obtain a user's request in natural language and transmit it to a server.

[1353] "Example 1"

[1354] (Claim 1)

[1355] A means by which the user requests program generation from the system using natural language,

[1356] A means by which the terminal sends user requests to the server,

[1357] A means by which the server analyzes the user's request and requests program generation from the generated AI model,

[1358] A means by which a generative AI model generates program code based on user requests,

[1359] A means for the server to return the generated program code to the terminal,

[1360] A means by which the terminal displays the generated program code to the user,

[1361] A means by which users can view and use program code generated through their terminals.

[1362] A system that includes this.

[1363] (Claim 2)

[1364] A means by which the server receives user requests in JSON format and transmits them to the generated AI model,

[1365] A method for returning the program code generated by the generation AI model to the server in JSON format.

[1366] The system according to claim 1, including the following:

[1367] (Claim 3)

[1368] The system according to claim 1, comprising an interface means for a terminal to obtain a user's request in natural language and transmit it to a server.

[1369] "Application Example 1"

[1370] (Claim 1)

[1371] A means by which the user requests program generation from the system using natural language,

[1372] A means by which the terminal sends user requests to the server,

[1373] A means by which the server analyzes the user's request and requests program generation from a generative AI,

[1374] A means by which a generative AI generates program code based on user requests,

[1375] A means for the server to return the generated program code to the terminal,

[1376] A means by which the terminal displays the generated program code to the user,

[1377] A means for users to input requests for ordering customized dishes using natural language,

[1378] A means of using a generative AI to analyze requests and automatically generate appropriate order details,

[1379] A method by which the server sends appropriate order details to the store based on the analysis results.

[1380] A system that includes this.

[1381] (Claim 2)

[1382] A means by which the server receives user requests in JSON format and transmits them to a generative AI,

[1383] A method for returning program code generated by a generative AI and customized order details to the server in JSON format.

[1384] The system according to claim 1, including the following:

[1385] (Claim 3)

[1386] An interface means for the terminal to obtain a user's request in natural language and send it to the server,

[1387] Includes a means to display the generated order details to the user and automatically send them to the store after confirmation.

[1388] The system according to claim 1.

[1389] "Example 2 of combining an emotion engine"

[1390] (Claim 1)

[1391] A means by which the user requests program generation from the system using natural language,

[1392] A means by which the terminal sends user requests to the server,

[1393] The means by which the emotion engine recognizes the user's emotional state,

[1394] A means for the terminal to send data including the recognized emotional state to a server,

[1395] A means by which the server analyzes user requests and emotional data and requests program generation from a generative AI,

[1396] A means by which a generative AI generates program code based on user requests and emotional data,

[1397] A means for the server to return the generated program code to the terminal,

[1398] A means by which the terminal displays the generated program code to the user.

[1399] A system that includes this.

[1400] (Claim 2)

[1401] A means by which the server receives user requests and sentiment data in JSON format and transmits them to a generative AI,

[1402] A method for returning program code generated by a generative AI to the server in JSON format.

[1403] The system according to claim 1, including the following:

[1404] (Claim 3)

[1405] The system according to claim 1, comprising an interface means for the terminal to recognize the user's natural language requests and the user's emotional state and transmit them to a server.

[1406] "Application example 2 when combining with an emotional engine"

[1407] (Claim 1)

[1408] A means by which the user requests program generation from the system using natural language,

[1409] A means by which the terminal sends user requests to the server,

[1410] A means by which the server analyzes the user's request and requests program generation from a generative AI,

[1411] A means by which a generative AI generates program code based on user requests,

[1412] A means for the server to return the generated program code to the terminal,

[1413] A means by which the terminal displays the generated program code to the user,

[1414] A means by which the device recognizes the user's emotions and sends emotion data to a server,

[1415] A means by which generative AI adjusts the generation of program code based on emotional data.

[1416] A system that includes this.

[1417] (Claim 2)

[1418] A means by which the server receives user requests in JSON format and transmits them to a generative AI,

[1419] A method for sending the program code generated by a generative AI back to the server in JSON format,

[1420] A method for a device to send JSON-formatted data, including user sentiment data, to a server.

[1421] The system according to claim 1, including the following:

[1422] (Claim 3)

[1423] An interface means for the terminal to obtain a user's request in natural language and send it to the server,

[1424] A method by which a device recognizes emotional data through the user's facial expressions and voice and transmits it to a server.

[1425] The system according to claim 1, including the following: [Explanation of Symbols]

[1426] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means by which the user requests program generation from the system using natural language, A means by which the terminal sends user requests to the server, A means by which the server analyzes the user's request and requests program generation from a generative AI, A means by which a generative AI generates program code based on user requests, A means for the server to return the generated program code to the terminal, A means by which the terminal displays the generated program code to the user. A system that includes this.

2. A means by which the server receives user requests in JSON format and transmits them to a generative AI, A method for returning program code generated by a generative AI to the server in JSON format. The system according to claim 1, including the following:

3. The system according to claim 1, comprising an interface means for a terminal to obtain a user's request in natural language and transmit it to a server.

Images