system

Abstract

A system is provided.SOLUTION: A system comprising means for providing answers to technical questions regarding how to use programming languages, frameworks, and libraries and how to interpret error messages by developers and engineers using generative artificial intelligence, means for suggesting best practices and design patterns to developers and engineers, means for searching and providing relevant information such as technical information, documents, API references, tutorials, and the like, means for providing code refactoring and bug identification advice, and means for supporting project management information queries and data searches and analyses such as project progress, task assignments, due dates, and resource management.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In modern system development, developers and engineers commonly face a wide variety of technical problems. These include learning how to use programming languages ​​and frameworks, interpreting error messages, and identifying optimal design patterns. However, finding quick and accurate solutions to these problems can be difficult and require a lot of time and effort. Furthermore, there is often a lack of efficient ways to search technical documentation and references, and project management makes it difficult to monitor progress and assign tasks in real time. To address these challenges, a comprehensive system is needed to support development efforts and promote high-quality software development. [Means for solving the problem]

[0005] In order to solve the above-mentioned problems, the present invention provides a system development support tool using generative artificial intelligence. This system includes the following means:

[0006] 1. A way for developers and engineers to ask technical questions about how to use programming languages, frameworks, libraries, or interpret error messages, and have generative artificial intelligence provide instant answers.

[0007] 2. A means of suggesting best practices and design patterns, which helps developers achieve high quality code and designs.

[0008] 3. A means to search and provide relevant information such as technical information, documentation, API references, tutorials, etc., allowing for fast and accurate access to information.

[0009] 4. A way to provide advice on refactoring code and identifying bugs, making it easier to improve code quality and identify problem areas.

[0010] 5. A means to support querying project management information, data retrieval, and analysis, such as project status, task assignment, deadline setting, and resource management, enabling real-time project status understanding and effective decision-making.

[0011] As claimed in the claims, this system includes a server and terminal devices that efficiently provide answers to technical questions and project management information, allowing developers and engineers to quickly and effectively address emerging technical issues and promote the development of high-quality software and systems.

[0012] "Generative AI" is an AI technology that uses natural language processing to generate appropriate answers and information in response to questions or requests entered by humans.

[0013] "Developers and engineers" are highly skilled technical personnel who design, implement, test, and maintain systems and software.

[0014] A "programming language" is a formal language for writing computer programs and is used to write source code.

[0015] A "framework" is a standardized collection of code and libraries that aids development in a particular programming language.

[0016] A "library" is a collection of code that groups together a set of functions or procedures to perform a specific task.

[0017] An "error message" is a notification containing information about an error that occurred while a program was running, which can help a developer identify the cause of the problem.

[0018] A "best practice" is the optimal way to perform a particular job or task most effectively and efficiently.

[0019] A "design pattern" is a reusable solution to a common problem encountered in the system or software design process.

[0020] "Technical information" refers to information related to the development of systems and software, including technical documents, documentation, specifications, etc.

[0021] An "API Reference" is a document that provides detailed information about a particular Application Programming Interface (API).

[0022] A "tutorial" is an instructional guide that provides step-by-step instructions on how to use a particular technique or tool.

[0023] "Code refactoring" is the process of improving the internal structure of software without changing its external behavior.

[0024] A "bug" is an error or defect in software or a system that prevents it from functioning as expected.

[0025] "Project management information" refers to information related to the progress of a project, task assignment, deadline setting, resource management, and the like.

[0026] A "server device" is a computer system that stores, processes, and distributes data over a network.

[0027] A "terminal device" is a computer system or device that is directly operated by a user and provides a means for communicating with a server. [Brief explanation of the drawings]

[0028] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8]FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0029] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0030] First, the terms used in the following description will be explained.

[0031] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0032] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0033] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0034] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0035] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0036] [First embodiment]

[0037] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0038] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0039] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0040] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0041] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0042] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0043] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0044] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0045] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0046] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0047] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0048] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0049] This invention relates to a system development support tool using generative artificial intelligence. This system is designed to quickly and efficiently address the technical challenges faced by developers and engineers.

[0050] Server configuration and processing overview

[0051] The server receives technical questions and project management information requests from the terminals and provides them to the generative AI. Specifically, it performs the following processes:

[0052] 1. Request received:

[0053] The server receives requests from the terminal using the HTTP protocol. For example, it converts the request data into JSON format and receives it.

[0054] 2. Querying Generative AI:

[0055] The server analyzes the request and makes the appropriate API calls to the generative AI model, which generates an answer based on the question.

[0056] 3. Returning the response:

[0057] The system receives the answer returned by the generative AI and sends it back to the device. The answer data is converted back to JSON format and sent as an HTTP response.

[0058] Overview of terminal configuration and processing

[0059] The terminal provides an interface for users to send technical questions and receive answers from the server. Specifically, it performs the following processes:

[0060] 1. Provide an interface:

[0061] The terminal provides a chat interface where users can enter questions, and when the user enters a question and clicks a send button, the question is sent to the server.

[0062] 2. Submit your request:

[0063] The terminal converts the user's input into JSON format and sends it to the server as an HTTP request.

[0064] 3. Show Answer:

[0065] It receives the JSON-formatted response data returned from the server, parses it, and displays it to the user, for example, as a chat bubble on the interface.

[0066] User operations and examples

[0067] Users can ask technical questions and access answers through the interface. For example:

[0068] 1. Enter your question:

[0069] The user types into the interface, "How do I read a file in Python?"

[0070] 2. Submit your request:

[0071] The device converts this question into JSON format and sends it to the server.

[0072] 3. Server-side processing:

[0073] The server receives this request and asks the generative AI, "How to read a file in Python?" The generative AI generates an appropriate answer and sends it back to the server.

[0074] 4. Receiving and Displaying Responses:

[0075] The terminal receives the response from the server and displays an answer to the user such as "In Python, you can read files using the open function. Sample code is shown below."

[0076] 5. Use of answers:

[0077] The user begins writing Python code based on the displayed answers. For example, they try to implement the file read function by using open("example.txt", "r").

[0078] This allows users to get quick and accurate answers to their technical questions, allowing them to proceed with development work efficiently. By linking the server and terminals, the system provides comprehensive technical support to developers and engineers. This configuration ensures smooth development and improved productivity.

[0079] The processing flow will be explained below.

[0080] Step 1:

[0081] The user inputs a question into the terminal interface, for example, "Please tell me how to implement asynchronous processing in JavaScript (registered trademark)."

[0082] Step 2:

[0083] The device converts the user's input into JSON format and sends it to the server. Specifically, the following JSON data { "question": "Please tell me how to implement asynchronous processing in JavaScript"} is sent as an HTTP POST request.

[0084] Step 3:

[0085] The server receives a request from the terminal and adds this data to the request processing queue.

[0086] Step 4:

[0087] The server analyzes the request and prepares an API request to query the generative AI model, for example, by setting up a POST request to an API endpoint and sending JSON data.

[0088] Step 5:

[0089] The generative AI receives questions sent from the server and analyzes them. For example, it understands "how to implement asynchronous processing in JavaScript" and generates an appropriate answer.

[0090] Step 6:

[0091] The generative AI generates an answer to the question and sends it back to the server. For example, it generates an answer such as, "In JavaScript, asynchronous processing can be implemented using the async / await keywords. Sample code is shown below."

[0092] Step 7:

[0093] The server receives the answer from the generative AI, converts it to JSON format { "answer": "In JavaScript, asynchronous processing can be implemented using the async / await keywords. Sample code is shown below."} and sends it to the device as an HTTP response.

[0094] Step 8:

[0095] The device analyzes the response received from the server and displays it to the user. Specifically, it displays the message "In JavaScript, asynchronous processing can be implemented using the async / await keywords. Sample code is shown below" in a chat bubble on the interface.

[0096] Step 9:

[0097] Users can check the displayed answers and apply them to their own development. For example, they can add sample code such as function fetchData() { const response = await fetch(url); const data = await response.json();} to their own projects to implement asynchronous processing.

[0098] Example 1

[0099] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0100] Modern engineers and developers face the complexity of programming languages, software frameworks, and libraries. Furthermore, the complexity of analyzing error messages and project management makes it difficult to work efficiently. Furthermore, the sheer volume of technical information and reference materials makes it difficult to quickly find the information you need. To address these challenges, a system is needed that can efficiently and quickly provide answers to technical questions and support project management.

[0101] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0102] In this invention, the server includes: means for using generative artificial intelligence to provide answers to technical questions developers and engineers have about how to use programming languages, software frameworks, and software libraries, and how to analyze error messages; means for suggesting best practices and design styles to developers and engineers; means for searching and providing related information such as technical information, documentation, application programming interface references, and educational materials; means for providing advice on code refactoring and fault identification; means for supporting inquiries about project management information such as project progress, task assignment, deadline setting, and resource management, as well as data search and analysis; a server device that receives technical questions from a terminal device as JSON-formatted data and provides the received data to a generative artificial intelligence model to generate answers; a server device that returns the generated answers to the terminal device as JSON-formatted data; a terminal device that provides an interface for inputting technical questions, analyzes the JSON-formatted answer data received from the server device, and displays it to the user; and a generative artificial intelligence model that generates optimal answers based on the content of the questions. This enables engineers and developers to quickly and efficiently obtain the information they need, allowing them to solve technical problems and manage projects smoothly.

[0103] "Generative AI" is AI that generates natural language text based on data, and is used to answer questions and generate sentences.

[0104] An "engineer" is an individual with specialized knowledge of software development and system design.

[0105] A "programming language" is a language used to write instructions to a computer to perform specific processes.

[0106] A "software framework" is a collection of reusable components and libraries provided to streamline software development.

[0107] A "software library" is a collection of functions or classes available to program developers that provide a specific functionality.

[0108] An "error message" is a text message that reports a problem that occurs during the operation of software or a system.

[0109] A "best practice" is a method or technique that is optimized to achieve the best results in a particular technology or task.

[0110] A "design style" is a template or pattern that provides a repeatable solution for software or system design.

[0111] "Document" means a paper or file that describes technical information or procedures.

[0112] An "Application Programming Interface Reference" is a document that describes the interfaces that software and systems use to communicate with each other and how to use them.

[0113] "Educational materials" are teaching materials for learning specific skills or knowledge.

[0114] "Refactoring" is the process of improving the internal structure of software to increase its maintainability and extensibility.

[0115] A "failure" is a problem or malfunction in the operation of a system or software.

[0116] "Project management information" is data or information regarding project progress, task assignments, deadlines, and resource allocation.

[0117] A "terminal device" is a device that allows a user to input questions and receive and display answers.

[0118] A "server device" is a computer that receives requests from terminal devices, queries the generative artificial intelligence model, and generates and returns answers.

[0119] A "generative artificial intelligence model" is an artificial intelligence algorithm that generates answers to questions based on data.

[0120] A "natural language processing model" is an artificial intelligence technology for processing, understanding, and generating human language.

[0121] This invention is a system that uses generative artificial intelligence to solve technical problems faced by engineers and developers and support project management. This system is mainly composed of a server device and a terminal device, each of which fulfills a specific role to achieve seamless technical support.

[0122] Roles and operations of server devices

[0123] The server device plays a central role in processing technical questions received from the terminal device. The server first receives a request from the terminal using the HTTP protocol. The received request is data in JSON format and is analyzed. The server then sends a prompt to the generative AI model, which generates the optimal answer. For example, the OpenAI (registered trademark) API is used as the generative AI model. This answer is then converted back into JSON format and returned to the terminal device as an HTTP response. A typical server computer is used for the specific hardware, and Python, Flask, or other software is used.

[0124] Example prompt sentence:

[0125] How do I read a file in Python?

[0126] Roles and operations of terminal devices

[0127] The terminal device provides an interface with the user. The terminal device displays a chat interface that allows the user to input technical questions. When the user inputs a question and clicks the send button, the question is converted into JSON format and sent to the server device as an HTTP request. When the terminal device receives the answer returned from the server, it analyzes it and displays it in a format that is easy for the user to view. Specifically, JavaScript, HTML, and AJAX technology are used.

[0128] User operations

[0129] A user inputs a technical question through the chat interface of the terminal device. For example, they input a question such as "How do I read a file in Python?". When they click the send button, the question is sent to the server, and an answer is returned by the generative artificial intelligence. The received answer is displayed to the user in the form of, for example, "In Python, you can read a file using the open function. Sample code is shown below."

[0130] In this way, the server and terminal devices work together to quickly and efficiently provide answers to technical questions and solve the complex problems faced by engineers and developers. Furthermore, the use of generative AI models ensures that the most appropriate answers are provided for each question, allowing users to proceed with their work based on reliable information.

[0131] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0132] Step 1:

[0133] The user enters a question and submits it

[0134] Specific behavior:

[0135] The user opens the chat interface on their device, types a question, for example, "How do I read a file in Python?", and clicks the send button.

[0136] input:

[0137] The text "How do I read a file in Python?"

[0138] output:

[0139] Text data of the question entered into the terminal device

[0140] Step 2:

[0141] The terminal device forms a request and sends it to the server

[0142] Specific behavior:

[0143] The terminal device converts the input question into JSON format and sends it to the server as an HTTP request. The transmission is asynchronous using AJAX technology.

[0144] input:

[0145] The text "How do I read a file in Python?"

[0146] Data processing:

[0147] Convert the question text to JSON format

[0148] output:

[0149] {"Question": "How do I read a file in Python?"} JSON data

[0150] Step 3:

[0151] The server receives and parses the request

[0152] Specific behavior:

[0153] The server receives the request via HTTP protocol, parses the JSON data, and extracts the question. The Flask framework is used to receive and parse the request.

[0154] input:

[0155] {"Question": "How do I read a file in Python?"} JSON data

[0156] Data Calculation:

[0157] Parse the JSON data to extract the question text

[0158] output:

[0159] The text "How do I read a file in Python?"

[0160] Step 4:

[0161] The server queries the generative AI model

[0162] Specific behavior:

[0163] The server sends the question as a prompt to the generative AI model, which then generates an answer. The server sends the prompt using the OpenAI API or similar and obtains the answer.

[0164] input:

[0165] The text "How do I read a file in Python?"

[0166] Data Calculation:

[0167] A generative AI model generates an answer based on the prompt.

[0168] output:

[0169] The text reads "In Python, you can read a file using the open function. Here is some sample code."

[0170] Step 5:

[0171] The server converts the response into JSON format and sends it back.

[0172] Specific behavior:

[0173] The server processes the answer obtained from the generative AI model into JSON format and returns it to the terminal device as an HTTP response. The response is created using a framework such as Flask.

[0174] input:

[0175] The text reads "In Python, you can read a file using the open function. Here is some sample code."

[0176] Data processing:

[0177] Convert the answer text to JSON format

[0178] output:

[0179] {"Answer": "In Python, you can read a file using the open function. Here is a sample code:"}

[0180] Step 6:

[0181] The terminal device receives and displays the response.

[0182] Specific behavior:

[0183] The terminal device receives the JSON-formatted response data returned from the server, analyzes it, and displays it to the user as a chat bubble using JavaScript DOM manipulation.

[0184] input:

[0185] {"Answer": "In Python, you can read a file using the open function. Here is a sample code:"}

[0186] Data Calculation:

[0187] Parse the JSON data to extract the answer text

[0188] output:

[0189] The text "In Python, you can read files using the open function. Here's some sample code." displayed in the chat interface

[0190] (Application example 1)

[0191] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0192] With conventional technologies, developers and engineers lack the means to quickly and efficiently respond to technical questions about programming and project management. Furthermore, when a robot encounters a technical issue in a factory, there is no support system to immediately resolve the issue, which can lead to reduced productivity and business downtime.

[0193] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0194] In this invention, the server includes: means for using generative artificial intelligence to provide answers to technical questions from developers and engineers about how to use programming languages, frameworks, and libraries and how to interpret error messages; means for suggesting best practices and design patterns to developers and engineers; means for searching and providing related information such as technical information, documentation, API references, and tutorials; means for providing advice on code refactoring and bug identification; means for supporting querying project management information such as project progress, task assignment, deadline setting, and resource management, as well as data search and analysis; means for querying technical problems in real time when they occur in the factory and presenting appropriate solutions using generative artificial intelligence; means for transmitting information on specific technical problems faced by robots to the server and receiving answers from the generative artificial intelligence; and means for the robots to execute procedures to solve the problems based on the answers received. This enables technical problems to be resolved quickly, improving the efficiency and productivity of development and factory operations.

[0195] "Generative AI" is an AI system that has the ability to generate answers in natural language in response to questions or requests.

[0196] "Technical questions" are questions about how to use programming languages, frameworks, libraries, and how to interpret error messages that developers and engineers encounter during the development process.

[0197] A "best practice" is a standard methodology or technique that is considered to be the most effective and efficient way to carry out a particular task or process.

[0198] A "design pattern" is a design template that is used repeatedly to efficiently solve a particular problem.

[0199] "Technical information" refers to knowledge and data about a specific technology, including documentation, API references, tutorials, etc.

[0200] "Refactoring" is a technique for improving the internal structure of software without changing its functionality.

[0201] "Bug identification" is the process of finding errors or defects in software or hardware and identifying where to fix them.

[0202] "Project management information" refers to information for effectively progressing a project, such as project progress, task assignment, deadline setting, and resource management.

[0203] "Technical problems in factories" are problems related to factory equipment or systems not working properly or malfunctioning.

[0204] "Real-time problem inquiry" means that the moment a technical problem occurs, that information is immediately sent to generative artificial intelligence for a solution.

[0205] "Specific technical problems faced by robots" refers to specific obstacles or error messages that factory robots encounter while operating.

[0206] A "server" is an information processing device that accepts requests from clients, queries the generative artificial intelligence, and returns a response.

[0207] A "terminal" is an information processing device that allows a user to input a question and receives and displays a response from a server.

[0208] This invention provides a system that utilizes generative artificial intelligence to quickly solve technical problems in factory robots. This system is realized with the following configuration and processing procedure.

[0209] System Program

[0210] When a factory robot encounters a technical problem, it immediately sends the information to a server, receives a response from generative artificial intelligence, and solves the problem.

[0211] Server Roles and Operations

[0212] The server receives requests from the factory robots regarding technical issues and provides them to the generative artificial intelligence. Specifically, it performs the following processes:

[0213] 1. Request received:

[0214] The server receives requests from robots using the HTTP protocol, including JSON-formatted data that contains information such as the problem description and error code.

[0215] 2. Querying Generative AI:

[0216] The server analyzes the received request and makes the appropriate API call to the generative AI model, which then generates an answer to the query.

[0217] 3. Returning the response:

[0218] It receives the answer returned by the generative AI and sends it back to the robot. The answer data is converted to JSON format and sent as an HTTP response.

[0219] Robot Roles and Processing

[0220] The robot detects technical issues during factory operations and provides an interface for querying the issue to the generative artificial intelligence. Specifically, the robot performs the following processes:

[0221] 1. Detecting the problem and submitting a request:

[0222] If the robot detects a technical problem during operation, it converts the details of the problem (e.g., error code or abnormal behavior) into JSON format and sends it to the server as an HTTP request.

[0223] 2. Receiving and implementing responses:

[0224] It receives the JSON-formatted response data returned from the server, analyzes it, and executes steps to resolve the problem, such as checking the motor connection or replacing the motor.

[0225] Hardware and software used

[0226] The following hardware and software are used in this system:

[0227] Hardware: Factory robots (e.g., Raspberry Pi), server equipment

[0228] Software: Python, Requests library, Generative AI API (e.g. OpenAI API)

[0229] Specific examples

[0230] For example, if a factory robot detects a motor abnormality while operating on a production line, it will send the following prompt sentence to the generative artificial intelligence:

[0231] Example prompt sentence:

[0232] "Error code 4040: Motor malfunction"

[0233] "timestamp: 2023-10-01T12:00:00Z"

[0234] "motor_id: MTR-001"

[0235] "status_code: 4040"

[0236] A generative artificial intelligence might respond to this with something like this:

[0237] Example answer:

[0238] "Check motor connections and ensure that the motor driver circuit is functioning correctly. If the problem persists, replace the motor."

[0239] The robot receives this response and first checks the motor connections and replaces the motor if necessary.

[0240] In this way, when a factory robot encounters a technical problem, the problem can be resolved quickly, improving productivity.

[0241] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0242] Step 1:

[0243] Problem detection and data generation

[0244] The robot detects technical issues during operation, such as abnormal motor behavior or error codes, and obtains detailed information from sensors inside the robot and system logs.

[0245] Input: Error code and related problem details

[0246] Output: JSON formatted data containing details about the issue

[0247] Specific operation: The robot detects the error message "Error code 4040: Motor malfunction" and retrieves detailed information about the error (e.g., timestamp and motor ID) from its internal log.

[0248] Step 2:

[0249] Sending data

[0250] The robot converts the detailed information of the problem it has obtained into JSON format and sends it to the server as an HTTP request.

[0251] Input: JSON formatted problem details generated in Step 1

[0252] Output: HTTP request sent to the server

[0253] Specific operation: The robot sends JSON data such as "{"issue": "Error code 4040: Motor malfunction", "timestamp": "2023-10-01T12:00:00Z", "motor_id": "MTR-001", "status_code": 4040}" as an HTTP POST request to the server's API endpoint.

[0254] Step 3:

[0255] Receiving and parsing the request

[0256] The server receives the HTTP request from the robot, analyzes its contents, and extracts the information necessary to query the generative AI.

[0257] Input: HTTP request received from the robot (detailed problem data in JSON format)

[0258] Output: Data for API calls to generative AI

[0259] What happens: The server receives the HTTP request, parses the JSON data, extracts keys and values ​​such as "issue", "timestamp", and "motor_id", and reformats them.

[0260] Step 4:

[0261] Inquiry into generative AI

[0262] Based on the analyzed data, the server makes an API call to the generative artificial intelligence to generate an appropriate answer.

[0263] Input: Parsed problem details data

[0264] Output: Answer data from generative AI

[0265] Specific operation: The server sends the extracted data to the generative artificial intelligence API, which generates a prompt in the form of, for example, "Please tell me the steps to resolve the motor's abnormal operation," and sends it to the AI.

[0266] Step 5:

[0267] Response reception and data conversion

[0268] The server receives the answer from the generative AI, converts it into JSON format, and prepares it for sending back to the robot.

[0269] Input: Answer data from generative AI

[0270] Output: JSON formatted answer data to send back to the robot

[0271] Specific operation: The generative AI receives the answer "Check motor connections and ensure the motor driver circuit is functioning correctly. If the problem persists, replace the motor." and converts this into JSON format such as "{"solution": "Check motor connections and ensure the motor driver circuit is functioning correctly. If the problem persists, replace the motor."}".

[0272] Step 6:

[0273] Returning answers and running them in a robot

[0274] The server sends the prepared answer data back to the robot, which analyzes it and executes steps to solve the problem.

[0275] Input: JSON format response data from the server

[0276] Output: Robot executes problem-solving steps

[0277] Specific behavior: The robot receives the answer, "Check motor connections and ensure the motor driver circuit is functioning correctly. If the problem persists, replace the motor." It first checks the motor connections, and if the problem persists, replaces the motor.

[0278] Through the above processing steps, when a factory robot encounters a technical problem, it can utilize generative artificial intelligence to quickly solve the problem.

[0279] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0280] This invention relates to a system development support tool that combines generative artificial intelligence and an emotion engine. This system quickly and efficiently addresses the technical challenges faced by developers and engineers, and also provides more human-like and effective support by recognizing the user's emotional state and adjusting the support content accordingly.

[0281] Server configuration and processing overview

[0282] The server receives requests from the device and works in conjunction with the generative AI and emotion engine. Specifically, it performs the following processes:

[0283] 1. Request received:

[0284] The server receives technical questions and project management information requests from the device. The received data is in JSON format.

[0285] 2. Querying Generative AI:

[0286] The server analyzes the request and prepares an API request to query the generative AI model, which generates an answer based on the question.

[0287] 3. Emotion engine recognizes user emotions:

[0288] The server simultaneously uses an emotion engine to recognize the user's emotional state, for example, by inferring the user's emotions from the tone and patterns of the text.

[0289] 4. Adjust based on responses and emotions:

[0290] The answer returned by the generative AI is combined with the results of emotion analysis by the emotion engine to tailor the answer to the user's emotional state. If the emotion is negative, a detailed and thorough explanation is added.

[0291] 5. Return of Response:

[0292] The adjusted answer is converted to JSON format and sent to the device as an HTTP response.

[0293] Overview of terminal configuration and processing

[0294] The terminal provides an interface for users to input questions and receive answers from the server. Specifically, it performs the following processes.

[0295] 1. Provide an interface:

[0296] The terminal provides a chat interface where users can enter questions, which are then sent to the server when the user clicks a send button.

[0297] 2. Submit your request:

[0298] The terminal converts the user's input into JSON format and sends it to the server as an HTTP request.

[0299] 3. Show Answer:

[0300] Parse the JSON response returned by the server and display it to the user, including responses adjusted based on emotion recognition results.

[0301] User operations and examples

[0302] Through the interface, users can ask technical questions and receive answers tailored to their emotional state.

[0303] 1. Enter your question:

[0304] The user types into the interface, "What is the interpretation of error code 1020?"

[0305] 2. Submit your request:

[0306] The device converts this question into JSON format and sends it to the server.

[0307] 3. Server-side processing:

[0308] The server receives the request and asks the generative AI for an interpretation of error code 1020. At the same time, the emotion engine analyzes the user's emotions. As a result of emotion recognition, "anxiety" is detected.

[0309] 4. Generate and refine answers:

[0310] The generative AI generates a response saying, "Error code 1020 is an authentication problem. Please check your user ID and password." Meanwhile, the emotion engine tells the server that "the user is feeling anxious." The server adds to the response, "This problem is relatively easy to solve. Please follow the next steps."

[0311] 5. Receiving and Displaying Responses:

[0312] The device analyzes the response received from the server and displays the message, "Error code 1020 is an authentication problem. Please check your user ID and password. This problem is relatively easy to resolve. Please follow the steps below."

[0313] 6. Use of Answers:

[0314] The user checks the displayed answer and follows the specific steps to solve the problem.

[0315] In this way, by combining generative AI with an emotion engine, we are able to provide not only fast and appropriate answers to technical questions, but also more effective support by taking into consideration the user's emotional state.

[0316] The processing flow will be explained below.

[0317] Step 1:

[0318] A user types a question into a terminal interface, for example, "How do I handle exceptions in Python?"

[0319] Step 2:

[0320] The terminal converts the user's input into JSON format and sends it to the server as an HTTP POST request. Specifically, it sends the data { "question": "Please tell me how to handle exceptions in Python"}.

[0321] Step 3:

[0322] The server receives the request from the terminal and analyzes the request content appropriately to add this data to the request processing queue.

[0323] Step 4:

[0324] Based on the request analyzed by the server, an API request is prepared to query the generative AI model. For example, a POST request is set up to the AI's API endpoint and the query data is sent.

[0325] Step 5:

[0326] The generative AI receives and analyzes questions sent from the server. It understands "how to handle exceptions in Python" and generates an appropriate answer. Specifically, it generates an answer such as, "Exception handling in Python is done using the try and except statements. Sample code is shown below."

[0327] Step 6:

[0328] The generative AI returns the generated answer to the server. For example, it returns JSON data containing an answer such as, "Python handles exceptions using the try and except statements. Sample code is shown below."

[0329] Step 7:

[0330] The server receives the response from the generative AI and simultaneously analyzes the user's emotional state using the emotion engine. For example, suppose the tone and expression of the input text indicate "anxiety."

[0331] Step 8:

[0332] The emotion engine sends the emotion analysis results back to the server. Specifically, it sends the analysis result that "the user is feeling anxious."

[0333] Step 9:

[0334] The server integrates the generative AI's answers with the analysis results of the emotion engine and adjusts the answer as needed. For example, if "anxiety" is detected, a detailed and polite explanation such as "This problem is relatively easy to solve. Please follow the next steps" is added.

[0335] Step 10:

[0336] The server then converts the final adjusted answer into JSON format and sends it to the device as an HTTP response.

[0337] Step 11:

[0338] The device analyzes the response received from the server and displays it to the user. Specifically, the chat interface displays the message, "Python uses the try and except statements to handle exceptions. Below is a sample code. This problem is relatively easy to solve. Please follow the steps below."

[0339] Step 12:

[0340] The user reviews the displayed answer and follows specific steps to solve the problem, for example, adding try and except statements to the Python code to implement exception handling.

[0341] In this way, the combination of generative AI and emotion engines can provide relevant answers to technical questions and personalize responses based on the user's emotional state, improving the user experience and significantly improving the efficiency of development efforts.

[0342] Example 2

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

[0344] Conventional technical consultation systems simply provide answers to technical questions without taking into account the user's emotional state. As a result, if a user is feeling anxious or stressed, their emotions are not taken into account and appropriate support is not provided. Another problem is that the quality of answers to technical questions varies, making it difficult to obtain advice that is appropriate for the content of the question or the user's background.

[0345] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0346] In this invention, the server includes means for using generative artificial intelligence to provide answers to technical questions from developers and engineers about how to use programming languages, software frameworks, and libraries and how to interpret error messages, means for suggesting best practices and design methods to developers and engineers, means for searching and providing related information such as technical information, documentation, API references, and tutorials, and means for recognizing the emotional state of a user using an emotion engine and adjusting the content of the answer based on the user's emotional state. This makes it possible to provide quick and appropriate answers to technical questions and support that takes the user's emotional state into consideration.

[0347] "Generative AI" refers to AI that automatically generates answers and suggestions in response to questions and requests from users in natural language.

[0348] "Technical questions" are questions about technical content, such as how to use programming languages, software frameworks, libraries, or interpret error messages.

[0349] An "emotion engine" is a technology for analyzing and recognizing a user's emotional state from text input and other interaction data.

[0350] "Best practices" is a concept that refers to the most efficient and effective methods and techniques in a particular technical field.

[0351] A "design method" refers to the techniques and methodologies used when designing systems and applications in software development.

[0352] "Technical information" refers to all information that developers and engineers need to perform technical work.

[0353] "Documentation" refers to documents that describe the specifications, design, and usage of software or systems.

[0354] An "API Reference" is a document that provides detailed instructions on how to use the application programming interface (API) provided by a particular program.

[0355] A "tutorial" is educational content that provides step-by-step instructions on how to use and apply a particular technology or tool.

[0356] A "terminal" is an electronic device or interface through which a user enters technical questions and receives responses from a server.

[0357] A "server" is a computer system that receives requests from users, processes them accordingly, and returns generated answers or advice to the users.

[0358] A "natural language processing model" is an algorithm for analyzing and understanding natural language text and converting it into human-readable information.

[0359] This invention is a system that combines generative artificial intelligence and an emotion engine. This system quickly and efficiently addresses the technical challenges faced by developers and engineers, and also provides more human-like and effective assistance by recognizing the user's emotional state and adjusting the assistance content accordingly.

[0360] Server configuration and processing overview

[0361] The server receives requests from the device and works in conjunction with the generative AI and emotion engine. Specifically, it performs the following processes:

[0362] Software and hardware used: The server uses "OpenAI GPT-3 (registered trademark)" as the generative AI and "Microsoft (registered trademark) Azure (registered trademark) Text Analytics API" as the emotion engine. The server itself uses a server machine equipped with a high-performance CPU and sufficient memory.

[0363] 1. Request received:

[0364] The server receives technical questions and project management information requests in JSON format from the device. For example, if a user types a question like "What is the interpretation of error code 1020?", this request is sent to the server.

[0365] 2. Querying Generative AI:

[0366] The server analyzes the received request and prepares an API request to query the generative AI model. For example, it sends a prompt message to OpenAI GPT-3: "Please tell me the interpretation of error code 1020."

[0367] 3. Emotion engine recognizes user emotions:

[0368] The server also uses Microsoft Azure's Text Analytics API to analyze the user's emotional state from the received text. For example, emotions such as "anxiety" may be recognized from the tone and patterns of the text.

[0369] 4. Adjust based on responses and emotions:

[0370] The server combines the answer returned by the generative AI with the emotion analysis results of the emotion engine to tailor the answer to the user's emotional state. For example, in response to the generative AI's answer "Error code 1020 is an authentication problem. Please check your user ID and password," the server adds additional information for anxious users, such as "This problem can be solved relatively easily. Please follow the next steps."

[0371] 5. Return of Response:

[0372] The adjusted answer is converted to JSON format and sent to the terminal as an HTTP response.

[0373] Overview of terminal configuration and processing

[0374] The terminal provides an interface through which the user can enter questions and receive answers from the server.

[0375] Hardware and software used: The device runs on a regular PC or smartphone and uses a web browser to provide the chat interface.

[0376] 1. Provide an interface:

[0377] The terminal provides a chat interface where users can enter questions. Once the user enters a question and clicks the send button, a request is sent to the server.

[0378] 2. Submit your request:

[0379] The terminal converts the user's input into JSON format and sends it to the server as an HTTP request.

[0380] 3. Show Answer:

[0381] The JSON response returned by the server is parsed and displayed to the user, with the content adjusted based on the emotion recognition results.

[0382] User operations and examples

[0383] Through the interface, users can ask technical questions and receive answers tailored to their emotional state.

[0384] 1. Enter your question:

[0385] The user types into the interface, "What is the interpretation of error code 1020?"

[0386] 2. Submit your request:

[0387] The device converts this question into JSON format and sends it to the server.

[0388] 3. Server-side processing:

[0389] The server receives the request and asks the generative AI for an interpretation of error code 1020. At the same time, the emotion engine analyzes the user's emotions. As a result of emotion recognition, "anxiety" is detected.

[0390] 4. Generate and refine answers:

[0391] The generative AI generates a response saying, "Error code 1020 is an authentication problem. Please check your user ID and password." Meanwhile, the emotion engine tells the server that "the user is feeling anxious." The server adds to the response, "This problem is relatively easy to solve. Please follow the next steps."

[0392] 5. Receiving and Displaying Responses:

[0393] The device analyzes the response received from the server and displays the message, "Error code 1020 is an authentication problem. Please check your user ID and password. This problem is relatively easy to resolve. Please follow the steps below."

[0394] 6. Use of Answers:

[0395] The user checks the displayed answer and follows the specific steps to solve the problem.

[0396] In this way, by combining generative AI with an emotion engine, it is possible to not only provide quick and appropriate answers to technical questions, but also to provide more effective support by taking into consideration the user's emotional state.

[0397] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0398] Step 1:

[0399] Entering and submitting a request

[0400] The user enters a technical question into the chat interface on the device, such as "What is the interpretation of error code 1020?", and clicks the send button. This input is converted by the device into JSON format (e.g., {"question":"What is the interpretation of error code 1020"}) and sent to the server as an HTTP request.

[0401] Step 2:

[0402] Receiving and parsing the request

[0403] The server receives an HTTP request from the device, analyzes the request, and obtains JSON data ({"question":"What is the interpretation of error code 1020?"}). Based on this data, it creates a prompt for the generative AI model.

[0404] Step 3:

[0405] Querying generative AI models

[0406] The server sends a prompt to a generative artificial intelligence model (e.g., OpenAI GPT-3) saying, "What is the interpretation of error code 1020?" The AI ​​model generates an answer based on this prompt and sends it back to the server. An example of the generated data is, "Error code 1020 is an authentication problem. Please check your user ID and password."

[0407] Step 4:

[0408] Emotion engine recognizes emotional states

[0409] The server sends the user's input text to an emotion engine (e.g., Microsoft Azure's Text Analytics API). The emotion engine performs emotion analysis on the input text and returns the results to the server. For example, an emotion such as "anxiety" is returned.

[0410] Step 5:

[0411] Emotion-based tailoring of responses

[0412] The server combines the answer obtained from the generative AI with the emotional state obtained from the emotion engine. For example, if the generated answer is "Error code 1020 is an authentication problem. Please check your user ID and password" and the emotional state is "anxious," the server adds additional information such as "This problem is relatively easy to solve. Please follow the next steps."

[0413] Step 6:

[0414] Submit your answer

[0415] The server converts the adjusted answer into JSON format (e.g., {"answer":"Error code 1020 is an authentication problem. Please check your user ID and password. This problem is relatively easy to resolve. Please follow the next steps"}) and sends it to the terminal as an HTTP response.

[0416] Step 7:

[0417] Receiving and viewing responses

[0418] The device receives the HTTP response from the server, parses the JSON data, and displays it to the user. For example, it might display a message like, "Error code 1020 is an authentication problem. Please check your user ID and password. This problem is relatively easy to resolve. Please follow the steps below."

[0419] In this way, by analyzing, generating, and adjusting based on input data at each step, we can provide appropriate answers to users' technical questions that take into account their emotional state.

[0420] (Application example 2)

[0421] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0422] Current systems that provide technical questions and solutions provide uniform answers without considering the user's emotional state, which can result in a poor user experience. Furthermore, on e-commerce sites, when users ask questions about products, it can take a long time for them to receive an appropriate answer, which can lead to lower satisfaction. This can lead to a decrease in purchasing motivation and a risk of customer attrition.

[0423] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for using generative artificial intelligence to provide answers to technical questions asked by developers and engineers about how to use programming languages, frameworks, and libraries and how to interpret error messages; means for suggesting best practices and design patterns to developers and engineers; means for searching and providing related information such as technical information, documentation, API references, and tutorials; means for providing advice on code refactoring and bug identification; means for supporting inquiries about project management information such as project progress, task assignment, deadline setting, and resource management, as well as data search and analysis; means for analyzing a user's emotional state and adjusting the content of the answer based on the user's emotions; means for providing emotion-based answers to product-related questions on an e-commerce site; and means for analyzing a user's questions and emotional state and adjusting and providing answers generated by generative artificial intelligence. This makes it possible to quickly provide answers that take emotions into consideration in response to users' technical questions and product-related concerns and doubts.

[0424] "Generative AI" is an AI model that generates new information and answers based on data such as text and images.

[0425] An "emotion engine" is an algorithm or software that analyzes and recognizes a user's emotional state from text or voice data.

[0426] "Technical questions" are questions about programming languages, frameworks, libraries, interpreting error messages, best practices, design patterns, technical information, documentation, API references, tutorials, refactoring code, identifying bugs, and related technical topics.

[0427] "Developers and engineers" are professionals who design, develop, operate, and maintain software and systems.

[0428] An "e-commerce site" is a website or application that facilitates the buying and selling of goods and services over the Internet.

[0429] The "user's emotional state" is an emotional state analyzed from the text or voice input by the user, such as anxiety, anger, relief, etc.

[0430] "Chat style" refers to an interface format in which a user inputs text and interacts with the system in response.

[0431] A "natural language processing model" is an artificial intelligence model that can understand and generate human language, and is used to generate optimal answers based on questions.

[0432] "API" stands for Application Program Interface, a set of protocols and tools that allow different software programs to communicate with each other.

[0433] A "design pattern" is a reusable solution to a common design problem in software development.

[0434] "Best practices" are the most effective and efficient methodologies and techniques established in a particular industry or field.

[0435] "Project management information" refers to information related to project progress, task assignment, deadline setting, resource management, and the like.

[0436] This invention uses a system that combines generative artificial intelligence and an emotion engine to provide emotion-based answers to technical questions and questions about products on e-commerce sites. Specific embodiments for realizing this system are described below.

[0437] System configuration

[0438] The server includes the following main functions:

[0439] 1. The ability to generate answers to technical and product questions using generative artificial intelligence models.

[0440] 2. The ability to use an emotion engine to analyze the user's emotional state and tailor responses appropriately.

[0441] 3. The function of receiving and analyzing requests from users.

[0442] 4. A function that combines emotional data obtained from the emotion engine with answers generated by generative artificial intelligence to provide the user with the most appropriate answer.

[0443] The terminal provides an interface through which the user can enter questions and receive answers from the server.

[0444] 1. Provide a chat-style interface where users can type in their questions.

[0445] 2. Send the user's input to the server.

[0446] 3. Display the answer received from the server.

[0447] Processing Details

[0448] The server receives requests from the device and analyzes their content. The analyzed information is passed to a generative AI model, which generates answers to technical and product-related questions. At the same time, an emotion engine analyzes the user's emotional state and generates emotion-based data. Finally, the generated answers are combined with the emotion data and provided in an optimized form to the user.

[0449] For example, suppose a user types "Can I return this product?" into a chat-style interface. The server passes this question to a generative AI model, which generates a standard answer: "You can return this product within 30 days of purchase." At the same time, the emotion engine analyzes the user's emotional state and determines it to be "anxious." As a result, the server adds the following statement to the answer: "Don't worry. You can return this product within 30 days of purchase. Detailed instructions are below.", providing the user with an optimized answer.

[0450] Hardware and Software

[0451] The specific hardware and software configuration required to realize this system is as follows:

[0452] Server device: A server equipped with a high-performance processor and a large amount of memory (e.g., AWS (registered trademark) EC2, Google (registered trademark) Cloud Compute Engine).

[0453] Terminal device: A smartphone or computer operated by a user.

[0454] Generative AI models: Natural language processing models (e.g., GPT-3, BERT).

[0455] Sentiment engine: Sentiment analysis algorithms (e.g., IBM Watson® Tone Analyzer, Microsoft Azure Text Analytics).

[0456] Examples of prompt statements

[0457] An example prompt for a generative AI model is:

[0458] User-submitted question: How do I get a refund if this product is broken?

[0459] Mode: Generate

[0460] Sentiment analysis results: Anxiety

[0461] Answer adjustment:

[0462] The problem is easy to solve, just follow these steps to get your refund:

[0463] Based on this prompt, the generative artificial intelligence model generates an appropriate answer and provides it to the user.

[0464] As described above, the embodiment of the present invention combines a generative artificial intelligence model and an emotion engine to realize a system that provides users with quick, emotion-sensitive answers.

[0465] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0466] Step 1:

[0467] The terminal accepts user input. The user types a question into a chat-style interface and clicks the send button. The input is in text format, and an example would be "Can I return this item?". The terminal converts this input into JSON format and sends it to the server. The input is the user question in text format, and the output is the request data in JSON format.

[0468] Step 2:

[0469] The server receives a request from the device. It analyzes the request content and prepares an API request to query the generative AI model. It analyzes the JSON formatted request data and creates a prompt to send to the generative AI model. The input is the JSON formatted request data, and the output is the prompt text to be passed to the generative AI model.

[0470] Step 3:

[0471] The server obtains the answer from the generative AI model. It sends a prompt to the generative AI model and receives the answer. The generative AI model generates an answer based on the question. The input is the prompt, and the output is the generated answer (in text format). In this example, the specific operation is to receive the answer, "This product can be returned within 30 days of purchase."

[0472] Step 4:

[0473] The server uses an emotion engine to analyze the user's emotional state. The user's input text is passed to the emotion engine for emotion analysis. The analysis result is output as an emotional state (e.g., anxiety, relief, etc.). The input is the user's question text, and the output is the emotion analysis result.

[0474] Step 5:

[0475] The server combines the answer returned by the generative AI model with the results of sentiment analysis by the emotion engine to adjust the content of the answer according to the user's emotional state. If the sentiment is negative, a detailed and thorough explanation is added. The input is the generated answer and the sentiment analysis results, and the output is the adjusted answer. In this example, based on the sentiment analysis result of "anxiety," the server adds the words "Don't worry. This product can be returned within 30 days of purchase."

[0476] Step 6:

[0477] The server converts the adjusted answer into JSON format and sends it to the terminal as an HTTP response. The input is the adjusted answer, and the output is the JSON-formatted response data. Specifically, the server encodes the adjusted answer and sends it to the terminal.

[0478] Step 7:

[0479] The device parses the JSON formatted response received from the server and displays it to the user. The input is the JSON formatted response data received from the server, and the output is the text response to be displayed. In this example, the response displayed to the user is "Don't worry. This product can be returned within 30 days of purchase."

[0480] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0481] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0482] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0483] [Second embodiment]

[0484] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0485] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0486] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0487] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0488] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0489] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0490] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0491] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0492] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0493] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0494] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0495] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0496] This invention relates to a system development support tool using generative artificial intelligence. This system is designed to quickly and efficiently address the technical challenges faced by developers and engineers.

[0497] Server configuration and processing overview

[0498] The server receives technical questions and project management information requests from the terminals and provides them to the generative AI. Specifically, it performs the following processes:

[0499] 1. Request received:

[0500] The server receives requests from the terminal using the HTTP protocol. For example, it converts the request data into JSON format and receives it.

[0501] 2. Querying Generative AI:

[0502] The server analyzes the request and makes the appropriate API calls to the generative AI model, which generates an answer based on the question.

[0503] 3. Returning the response:

[0504] The system receives the answer returned by the generative AI and sends it back to the device. The answer data is converted back to JSON format and sent as an HTTP response.

[0505] Overview of terminal configuration and processing

[0506] The terminal provides an interface for users to send technical questions and receive answers from the server. Specifically, it performs the following processes:

[0507] 1. Provide an interface:

[0508] The terminal provides a chat interface where users can enter questions, and when the user enters a question and clicks a send button, the question is sent to the server.

[0509] 2. Submit your request:

[0510] The terminal converts the user's input into JSON format and sends it to the server as an HTTP request.

[0511] 3. Show Answer:

[0512] It receives the JSON-formatted response data returned from the server, parses it, and displays it to the user, for example, as a chat bubble on the interface.

[0513] User operations and examples

[0514] Users can ask technical questions and access answers through the interface. For example:

[0515] 1. Enter your question:

[0516] The user types into the interface, "How do I read a file in Python?"

[0517] 2. Submit your request:

[0518] The device converts this question into JSON format and sends it to the server.

[0519] 3. Server-side processing:

[0520] The server receives this request and asks the generative AI, "How to read a file in Python?" The generative AI generates an appropriate answer and sends it back to the server.

[0521] 4. Receiving and Displaying Responses:

[0522] The terminal receives the response from the server and displays an answer to the user such as "In Python, you can read files using the open function. Sample code is shown below."

[0523] 5. Use of answers:

[0524] The user begins writing Python code based on the displayed answers. For example, they try to implement the file read function by using open("example.txt", "r").

[0525] This allows users to get quick and accurate answers to their technical questions, allowing them to proceed with development work efficiently. By linking the server and terminals, the system provides comprehensive technical support to developers and engineers. This configuration ensures smooth development and improved productivity.

[0526] The processing flow will be explained below.

[0527] Step 1:

[0528] The user types a question into the device interface, for example, "How do I implement asynchronous processing in JavaScript?"

[0529] Step 2:

[0530] The device converts the user's input into JSON format and sends it to the server. Specifically, the following JSON data { "question": "Please tell me how to implement asynchronous processing in JavaScript"} is sent as an HTTP POST request.

[0531] Step 3:

[0532] The server receives a request from the terminal and adds this data to the request processing queue.

[0533] Step 4:

[0534] The server analyzes the request and prepares an API request to query the generative AI model, for example, by setting up a POST request to an API endpoint and sending JSON data.

[0535] Step 5:

[0536] The generative AI receives questions sent from the server and analyzes them. For example, it understands "how to implement asynchronous processing in JavaScript" and generates an appropriate answer.

[0537] Step 6:

[0538] The generative AI generates an answer to the question and sends it back to the server. For example, it generates an answer such as, "In JavaScript, asynchronous processing can be implemented using the async / await keywords. Sample code is shown below."

[0539] Step 7:

[0540] The server receives the answer from the generative AI, converts it to JSON format { "answer": "In JavaScript, asynchronous processing can be implemented using the async / await keywords. Sample code is shown below."} and sends it to the device as an HTTP response.

[0541] Step 8:

[0542] The device analyzes the response received from the server and displays it to the user. Specifically, it displays the message "In JavaScript, asynchronous processing can be implemented using the async / await keywords. Sample code is shown below" in a chat bubble on the interface.

[0543] Step 9:

[0544] Users can check the displayed answers and apply them to their own development. For example, they can add sample code such as function fetchData() { const response = await fetch(url); const data = await response.json();} to their own projects to implement asynchronous processing.

[0545] Example 1

[0546] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0547] Modern engineers and developers face the complexity of programming languages, software frameworks, and libraries. Furthermore, the complexity of analyzing error messages and project management makes it difficult to work efficiently. Furthermore, the sheer volume of technical information and reference materials makes it difficult to quickly find the information you need. To address these challenges, a system is needed that can efficiently and quickly provide answers to technical questions and support project management.

[0548] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0549] In this invention, the server includes: means for using generative artificial intelligence to provide answers to technical questions developers and engineers have about how to use programming languages, software frameworks, and software libraries, and how to analyze error messages; means for suggesting best practices and design styles to developers and engineers; means for searching and providing related information such as technical information, documentation, application programming interface references, and educational materials; means for providing advice on code refactoring and fault identification; means for supporting inquiries about project management information such as project progress, task assignment, deadline setting, and resource management, as well as data search and analysis; a server device that receives technical questions from a terminal device as JSON-formatted data and provides the received data to a generative artificial intelligence model to generate answers; a server device that returns the generated answers to the terminal device as JSON-formatted data; a terminal device that provides an interface for inputting technical questions, analyzes the JSON-formatted answer data received from the server device, and displays it to the user; and a generative artificial intelligence model that generates optimal answers based on the content of the questions. This enables engineers and developers to quickly and efficiently obtain the information they need, allowing them to solve technical problems and manage projects smoothly.

[0550] "Generative AI" is AI that generates natural language text based on data, and is used to answer questions and generate sentences.

[0551] An "engineer" is an individual with specialized knowledge of software development and system design.

[0552] A "programming language" is a language used to write instructions to a computer to perform specific processes.

[0553] A "software framework" is a collection of reusable components and libraries provided to streamline software development.

[0554] A "software library" is a collection of functions or classes available to program developers that provide a specific functionality.

[0555] An "error message" is a text message that reports a problem that occurs during the operation of software or a system.

[0556] A "best practice" is a method or technique that is optimized to achieve the best results in a particular technology or task.

[0557] A "design style" is a template or pattern that provides a repeatable solution for software or system design.

[0558] "Document" means a paper or file that describes technical information or procedures.

[0559] An "Application Programming Interface Reference" is a document that describes the interfaces that software and systems use to communicate with each other and how to use them.

[0560] "Educational materials" are teaching materials for learning specific skills or knowledge.

[0561] "Refactoring" is the process of improving the internal structure of software to increase its maintainability and extensibility.

[0562] A "failure" is a problem or malfunction in the operation of a system or software.

[0563] "Project management information" is data or information regarding project progress, task assignments, deadlines, and resource allocation.

[0564] A "terminal device" is a device that allows a user to input questions and receive and display answers.

[0565] A "server device" is a computer that receives requests from terminal devices, queries the generative artificial intelligence model, and generates and returns answers.

[0566] A "generative artificial intelligence model" is an artificial intelligence algorithm that generates answers to questions based on data.

[0567] A "natural language processing model" is an artificial intelligence technology for processing, understanding, and generating human language.

[0568] This invention is a system that uses generative artificial intelligence to solve technical problems faced by engineers and developers and support project management. This system is mainly composed of a server device and a terminal device, each of which fulfills a specific role to achieve seamless technical support.

[0569] Roles and operations of server devices

[0570] The server device plays a central role in processing technical questions received from the terminal device. The server first receives a request from the terminal using the HTTP protocol. The received request is data in JSON format and is analyzed. The server then sends a prompt to the generative AI model, which generates the optimal answer. An example of a generative AI model would be the OpenAI API. This answer is then converted back into JSON format and sent back to the terminal device as an HTTP response. A typical server computer is used for the specific hardware, and Python or Flask is used for the software.

[0571] Example prompt sentence:

[0572] How do I read a file in Python?

[0573] Roles and operations of terminal devices

[0574] The terminal device provides an interface with the user. The terminal device displays a chat interface that allows the user to input technical questions. When the user inputs a question and clicks the send button, the question is converted into JSON format and sent to the server device as an HTTP request. When the terminal device receives the answer returned from the server, it analyzes it and displays it in a format that is easy for the user to view. Specifically, JavaScript, HTML, and AJAX technology are used.

[0575] User operations

[0576] A user inputs a technical question through the chat interface of the terminal device. For example, they input a question such as "How do I read a file in Python?". When they click the send button, the question is sent to the server, and an answer is returned by the generative artificial intelligence. The received answer is displayed to the user in the form of, for example, "In Python, you can read a file using the open function. Sample code is shown below."

[0577] In this way, the server and terminal devices work together to quickly and efficiently provide answers to technical questions and solve the complex problems faced by engineers and developers. Furthermore, the use of generative AI models ensures that the most appropriate answers are provided for each question, allowing users to proceed with their work based on reliable information.

[0578] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0579] Step 1:

[0580] The user enters a question and submits it

[0581] Specific behavior:

[0582] The user opens the chat interface on their device, types a question, for example, "How do I read a file in Python?", and clicks the send button.

[0583] input:

[0584] The text "How do I read a file in Python?"

[0585] output:

[0586] Text data of the question entered into the terminal device

[0587] Step 2:

[0588] The terminal device forms a request and sends it to the server

[0589] Specific behavior:

[0590] The terminal device converts the input question into JSON format and sends it to the server as an HTTP request. The transmission is asynchronous using AJAX technology.

[0591] input:

[0592] The text "How do I read a file in Python?"

[0593] Data processing:

[0594] Convert the question text to JSON format

[0595] output:

[0596] {"Question": "How do I read a file in Python?"} JSON data

[0597] Step 3:

[0598] The server receives and parses the request

[0599] Specific behavior:

[0600] The server receives the request via HTTP protocol, parses the JSON data, and extracts the question. The Flask framework is used to receive and parse the request.

[0601] input:

[0602] {"Question": "How do I read a file in Python?"} JSON data

[0603] Data Calculation:

[0604] Parse the JSON data to extract the question text

[0605] output:

[0606] The text "How do I read a file in Python?"

[0607] Step 4:

[0608] The server queries the generative AI model

[0609] Specific behavior:

[0610] The server sends the question as a prompt to the generative AI model, which then generates an answer. The server sends the prompt using the OpenAI API or similar and obtains the answer.

[0611] input:

[0612] The text "How do I read a file in Python?"

[0613] Data Calculation:

[0614] A generative AI model generates an answer based on the prompt.

[0615] output:

[0616] The text reads "In Python, you can read a file using the open function. Here is some sample code."

[0617] Step 5:

[0618] The server converts the response into JSON format and sends it back.

[0619] Specific behavior:

[0620] The server processes the answer obtained from the generative AI model into JSON format and returns it to the terminal device as an HTTP response. The response is created using a framework such as Flask.

[0621] input:

[0622] The text reads "In Python, you can read a file using the open function. Here is some sample code."

[0623] Data processing:

[0624] Convert the answer text to JSON format

[0625] output:

[0626] {"Answer": "In Python, you can read a file using the open function. Here is a sample code:"}

[0627] Step 6:

[0628] The terminal device receives and displays the response.

[0629] Specific behavior:

[0630] The terminal device receives the JSON-formatted response data returned from the server, analyzes it, and displays it to the user as a chat bubble using JavaScript DOM manipulation.

[0631] input:

[0632] {"Answer": "In Python, you can read a file using the open function. Here is a sample code:"}

[0633] Data Calculation:

[0634] Parse the JSON data to extract the answer text

[0635] output:

[0636] The text "In Python, you can read files using the open function. Here's some sample code." displayed in the chat interface

[0637] (Application example 1)

[0638] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0639] With conventional technologies, developers and engineers lack the means to quickly and efficiently respond to technical questions about programming and project management. Furthermore, when a robot encounters a technical issue in a factory, there is no support system to immediately resolve the issue, which can lead to reduced productivity and business downtime.

[0640] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0641] In this invention, the server includes: means for using generative artificial intelligence to provide answers to technical questions from developers and engineers about how to use programming languages, frameworks, and libraries and how to interpret error messages; means for suggesting best practices and design patterns to developers and engineers; means for searching and providing related information such as technical information, documentation, API references, and tutorials; means for providing advice on code refactoring and bug identification; means for supporting querying project management information such as project progress, task assignment, deadline setting, and resource management, as well as data search and analysis; means for querying technical problems in real time when they occur in the factory and presenting appropriate solutions using generative artificial intelligence; means for transmitting information on specific technical problems faced by robots to the server and receiving answers from the generative artificial intelligence; and means for the robots to execute procedures to solve the problems based on the answers received. This enables technical problems to be resolved quickly, improving the efficiency and productivity of development and factory operations.

[0642] "Generative AI" is an AI system that has the ability to generate answers in natural language in response to questions or requests.

[0643] "Technical questions" are questions about how to use programming languages, frameworks, libraries, and how to interpret error messages that developers and engineers encounter during the development process.

[0644] A "best practice" is a standard methodology or technique that is considered to be the most effective and efficient way to carry out a particular task or process.

[0645] A "design pattern" is a design template that is used repeatedly to efficiently solve a particular problem.

[0646] "Technical information" refers to knowledge and data about a specific technology, including documentation, API references, tutorials, etc.

[0647] "Refactoring" is a technique for improving the internal structure of software without changing its functionality.

[0648] "Bug identification" is the process of finding errors or defects in software or hardware and identifying where to fix them.

[0649] "Project management information" refers to information for effectively progressing a project, such as project progress, task assignment, deadline setting, and resource management.

[0650] "Technical problems in factories" are problems related to factory equipment or systems not working properly or malfunctioning.

[0651] "Real-time problem inquiry" means that the moment a technical problem occurs, that information is immediately sent to generative artificial intelligence for a solution.

[0652] "Specific technical problems faced by robots" refers to specific obstacles or error messages that factory robots encounter while operating.

[0653] A "server" is an information processing device that accepts requests from clients, queries the generative artificial intelligence, and returns a response.

[0654] A "terminal" is an information processing device that allows a user to input a question and receives and displays a response from a server.

[0655] This invention provides a system that utilizes generative artificial intelligence to quickly solve technical problems in factory robots. This system is realized with the following configuration and processing procedure.

[0656] System Program

[0657] When a factory robot encounters a technical problem, it immediately sends the information to a server, receives a response from generative artificial intelligence, and solves the problem.

[0658] Server Roles and Operations

[0659] The server receives requests from the factory robots regarding technical issues and provides them to the generative artificial intelligence. Specifically, it performs the following processes:

[0660] 1. Request received:

[0661] The server receives requests from robots using the HTTP protocol, including JSON-formatted data that contains information such as the problem description and error code.

[0662] 2. Querying Generative AI:

[0663] The server analyzes the received request and makes the appropriate API call to the generative AI model, which then generates an answer to the query.

[0664] 3. Returning the response:

[0665] It receives the answer returned by the generative AI and sends it back to the robot. The answer data is converted to JSON format and sent as an HTTP response.

[0666] Robot Roles and Processing

[0667] The robot detects technical issues during factory operations and provides an interface for querying the issue to the generative artificial intelligence. Specifically, the robot performs the following processes:

[0668] 1. Detecting the problem and submitting a request:

[0669] If the robot detects a technical problem during operation, it converts the details of the problem (e.g., error code or abnormal behavior) into JSON format and sends it to the server as an HTTP request.

[0670] 2. Receiving and implementing responses:

[0671] It receives the JSON-formatted response data returned from the server, analyzes it, and executes steps to resolve the problem, such as checking the motor connection or replacing the motor.

[0672] Hardware and software used

[0673] The following hardware and software are used in this system:

[0674] Hardware: Factory robots (e.g., Raspberry Pi), server equipment

[0675] Software: Python, Requests library, Generative AI API (e.g. OpenAI API)

[0676] Specific examples

[0677] For example, if a factory robot detects a motor abnormality while operating on a production line, it will send the following prompt sentence to the generative artificial intelligence:

[0678] Example prompt sentence:

[0679] "Error code 4040: Motor malfunction"

[0680] "timestamp: 2023-10-01T12:00:00Z"

[0681] "motor_id: MTR-001"

[0682] "status_code: 4040"

[0683] A generative artificial intelligence might respond to this with something like this:

[0684] Example answer:

[0685] "Check motor connections and ensure that the motor driver circuit is functioning correctly. If the problem persists, replace the motor."

[0686] The robot receives this response and first checks the motor connections and replaces the motor if necessary.

[0687] In this way, when a factory robot encounters a technical problem, the problem can be resolved quickly, improving productivity.

[0688] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0689] Step 1:

[0690] Problem detection and data generation

[0691] The robot detects technical issues during operation, such as abnormal motor behavior or error codes, and obtains detailed information from sensors inside the robot and system logs.

[0692] Input: Error code and related problem details

[0693] Output: JSON formatted data containing details about the issue

[0694] Specific operation: The robot detects the error message "Error code 4040: Motor malfunction" and retrieves detailed information about the error (e.g., timestamp and motor ID) from its internal log.

[0695] Step 2:

[0696] Sending data

[0697] The robot converts the detailed information of the problem it has obtained into JSON format and sends it to the server as an HTTP request.

[0698] Input: JSON formatted problem details generated in Step 1

[0699] Output: HTTP request sent to the server

[0700] Specific operation: The robot sends JSON data such as "{"issue": "Error code 4040: Motor malfunction", "timestamp": "2023-10-01T12:00:00Z", "motor_id": "MTR-001", "status_code": 4040}" as an HTTP POST request to the server's API endpoint.

[0701] Step 3:

[0702] Receiving and parsing the request

[0703] The server receives the HTTP request from the robot, analyzes its contents, and extracts the information necessary to query the generative AI.

[0704] Input: HTTP request received from the robot (detailed problem data in JSON format)

[0705] Output: Data for API calls to generative AI

[0706] What happens: The server receives the HTTP request, parses the JSON data, extracts keys and values ​​such as "issue", "timestamp", and "motor_id", and reformats them.

[0707] Step 4:

[0708] Inquiry into generative AI

[0709] Based on the analyzed data, the server makes an API call to the generative artificial intelligence to generate an appropriate answer.

[0710] Input: Parsed problem details data

[0711] Output: Answer data from generative AI

[0712] Specific operation: The server sends the extracted data to the generative artificial intelligence API, which generates a prompt in the form of, for example, "Please tell me the steps to resolve the motor's abnormal operation," and sends it to the AI.

[0713] Step 5:

[0714] Response reception and data conversion

[0715] The server receives the answer from the generative AI, converts it into JSON format, and prepares it for sending back to the robot.

[0716] Input: Answer data from generative AI

[0717] Output: JSON formatted answer data to send back to the robot

[0718] Specific operation: The generative AI receives the answer "Check motor connections and ensure the motor driver circuit is functioning correctly. If the problem persists, replace the motor." and converts this into JSON format such as "{"solution": "Check motor connections and ensure the motor driver circuit is functioning correctly. If the problem persists, replace the motor."}".

[0719] Step 6:

[0720] Returning answers and running them in a robot

[0721] The server sends the prepared answer data back to the robot, which analyzes it and executes steps to solve the problem.

[0722] Input: JSON format response data from the server

[0723] Output: Robot executes problem-solving steps

[0724] Specific behavior: The robot receives the answer, "Check motor connections and ensure the motor driver circuit is functioning correctly. If the problem persists, replace the motor." It first checks the motor connections, and if the problem persists, replaces the motor.

[0725] Through the above processing steps, when a factory robot encounters a technical problem, it can utilize generative artificial intelligence to quickly solve the problem.

[0726] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0727] This invention relates to a system development support tool that combines generative artificial intelligence and an emotion engine. This system quickly and efficiently addresses the technical challenges faced by developers and engineers, and also provides more human-like and effective support by recognizing the user's emotional state and adjusting the support content accordingly.

[0728] Server configuration and processing overview

[0729] The server receives requests from the device and works in conjunction with the generative AI and emotion engine. Specifically, it performs the following processes:

[0730] 1. Request received:

[0731] The server receives technical questions and project management information requests from the device. The received data is in JSON format.

[0732] 2. Querying Generative AI:

[0733] The server analyzes the request and prepares an API request to query the generative AI model, which generates an answer based on the question.

[0734] 3. Emotion engine recognizes user emotions:

[0735] The server simultaneously uses an emotion engine to recognize the user's emotional state, for example, by inferring the user's emotions from the tone and patterns of the text.

[0736] 4. Adjust based on responses and emotions:

[0737] The answer returned by the generative AI is combined with the results of emotion analysis by the emotion engine to tailor the answer to the user's emotional state. If the emotion is negative, a detailed and thorough explanation is added.

[0738] 5. Return of Response:

[0739] The adjusted answer is converted to JSON format and sent to the device as an HTTP response.

[0740] Overview of terminal configuration and processing

[0741] The terminal provides an interface for users to input questions and receive answers from the server. Specifically, it performs the following processes.

[0742] 1. Provide an interface:

[0743] The terminal provides a chat interface where users can enter questions, which are then sent to the server when the user clicks a send button.

[0744] 2. Submit your request:

[0745] The terminal converts the user's input into JSON format and sends it to the server as an HTTP request.

[0746] 3. Show Answer:

[0747] Parse the JSON response returned by the server and display it to the user, including responses adjusted based on emotion recognition results.

[0748] User operations and examples

[0749] Through the interface, users can ask technical questions and receive answers tailored to their emotional state.

[0750] 1. Enter your question:

[0751] The user types into the interface, "What is the interpretation of error code 1020?"

[0752] 2. Submit your request:

[0753] The device converts this question into JSON format and sends it to the server.

[0754] 3. Server-side processing:

[0755] The server receives the request and asks the generative AI for an interpretation of error code 1020. At the same time, the emotion engine analyzes the user's emotions. As a result of emotion recognition, "anxiety" is detected.

[0756] 4. Generate and refine answers:

[0757] The generative AI generates a response saying, "Error code 1020 is an authentication problem. Please check your user ID and password." Meanwhile, the emotion engine tells the server that "the user is feeling anxious." The server adds to the response, "This problem is relatively easy to solve. Please follow the next steps."

[0758] 5. Receiving and Displaying Responses:

[0759] The device analyzes the response received from the server and displays the message, "Error code 1020 is an authentication problem. Please check your user ID and password. This problem is relatively easy to resolve. Please follow the steps below."

[0760] 6. Use of Answers:

[0761] The user checks the displayed answer and follows the specific steps to solve the problem.

[0762] In this way, by combining generative AI with an emotion engine, we are able to provide not only fast and appropriate answers to technical questions, but also more effective support by taking into consideration the user's emotional state.

[0763] The processing flow will be explained below.

[0764] Step 1:

[0765] A user types a question into a terminal interface, for example, "How do I handle exceptions in Python?"

[0766] Step 2:

[0767] The terminal converts the user's input into JSON format and sends it to the server as an HTTP POST request. Specifically, it sends the data { "question": "Please tell me how to handle exceptions in Python"}.

[0768] Step 3:

[0769] The server receives the request from the terminal and analyzes the request content appropriately to add this data to the request processing queue.

[0770] Step 4:

[0771] Based on the request analyzed by the server, an API request is prepared to query the generative AI model. For example, a POST request is set up to the AI's API endpoint and the query data is sent.

[0772] Step 5:

[0773] The generative AI receives and analyzes questions sent from the server. It understands "how to handle exceptions in Python" and generates an appropriate answer. Specifically, it generates an answer such as, "Exception handling in Python is done using the try and except statements. Sample code is shown below."

[0774] Step 6:

[0775] The generative AI returns the generated answer to the server. For example, it returns JSON data containing an answer such as, "Python handles exceptions using the try and except statements. Sample code is shown below."

[0776] Step 7:

[0777] The server receives the response from the generative AI and simultaneously analyzes the user's emotional state using the emotion engine. For example, suppose the tone and expression of the input text indicate "anxiety."

[0778] Step 8:

[0779] The emotion engine sends the emotion analysis results back to the server. Specifically, it sends the analysis result that "the user is feeling anxious."

[0780] Step 9:

[0781] The server integrates the generative AI's answers with the analysis results of the emotion engine and adjusts the answer as needed. For example, if "anxiety" is detected, a detailed and polite explanation such as "This problem is relatively easy to solve. Please follow the next steps" is added.

[0782] Step 10:

[0783] The server then converts the final adjusted answer into JSON format and sends it to the device as an HTTP response.

[0784] Step 11:

[0785] The device analyzes the response received from the server and displays it to the user. Specifically, the chat interface displays the message, "Python uses the try and except statements to handle exceptions. Below is a sample code. This problem is relatively easy to solve. Please follow the steps below."

[0786] Step 12:

[0787] The user reviews the displayed answer and follows specific steps to solve the problem, for example, adding try and except statements to the Python code to implement exception handling.

[0788] In this way, the combination of generative AI and emotion engines can provide relevant answers to technical questions and personalize responses based on the user's emotional state, improving the user experience and significantly improving the efficiency of development efforts.

[0789] Example 2

[0790] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0791] Conventional technical consultation systems simply provide answers to technical questions without taking into account the user's emotional state. As a result, if a user is feeling anxious or stressed, their emotions are not taken into account and appropriate support is not provided. Another problem is that the quality of answers to technical questions varies, making it difficult to obtain advice that is appropriate for the content of the question or the user's background.

[0792] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0793] In this invention, the server includes means for using generative artificial intelligence to provide answers to technical questions from developers and engineers about how to use programming languages, software frameworks, and libraries and how to interpret error messages, means for suggesting best practices and design methods to developers and engineers, means for searching and providing related information such as technical information, documentation, API references, and tutorials, and means for recognizing the emotional state of a user using an emotion engine and adjusting the content of the answer based on the user's emotional state. This makes it possible to provide quick and appropriate answers to technical questions and support that takes the user's emotional state into consideration.

[0794] "Generative AI" refers to AI that automatically generates answers and suggestions in response to questions and requests from users in natural language.

[0795] "Technical questions" are questions about technical content, such as how to use programming languages, software frameworks, libraries, or interpret error messages.

[0796] An "emotion engine" is a technology for analyzing and recognizing a user's emotional state from text input and other interaction data.

[0797] "Best practices" is a concept that refers to the most efficient and effective methods and techniques in a particular technical field.

[0798] A "design method" refers to the techniques and methodologies used when designing systems and applications in software development.

[0799] "Technical information" refers to all information that developers and engineers need to perform technical work.

[0800] "Documentation" refers to documents that describe the specifications, design, and usage of software or systems.

[0801] An "API Reference" is a document that provides detailed instructions on how to use the application programming interface (API) provided by a particular program.

[0802] A "tutorial" is educational content that provides step-by-step instructions on how to use and apply a particular technology or tool.

[0803] A "terminal" is an electronic device or interface through which a user enters technical questions and receives responses from a server.

[0804] A "server" is a computer system that receives requests from users, processes them accordingly, and returns generated answers or advice to the users.

[0805] A "natural language processing model" is an algorithm for analyzing and understanding natural language text and converting it into human-readable information.

[0806] This invention is a system that combines generative artificial intelligence and an emotion engine. This system quickly and efficiently addresses the technical challenges faced by developers and engineers, and also provides more human-like and effective assistance by recognizing the user's emotional state and adjusting the assistance content accordingly.

[0807] Server configuration and processing overview

[0808] The server receives requests from the device and works in conjunction with the generative AI and emotion engine. Specifically, it performs the following processes:

[0809] Software and hardware used: The server uses "OpenAI GPT-3" as the generative AI and "Microsoft Azure's Text Analytics API" as the emotion engine. The server itself uses a server machine with a high-performance CPU and sufficient memory.

[0810] 1. Request received:

[0811] The server receives technical questions and project management information requests in JSON format from the device. For example, if a user types a question like "What is the interpretation of error code 1020?", this request is sent to the server.

[0812] 2. Querying Generative AI:

[0813] The server analyzes the received request and prepares an API request to query the generative AI model. For example, it sends a prompt message to OpenAI GPT-3: "Please tell me the interpretation of error code 1020."

[0814] 3. Emotion engine recognizes user emotions:

[0815] The server also uses Microsoft Azure's Text Analytics API to analyze the user's emotional state from the received text. For example, emotions such as "anxiety" may be recognized from the tone and patterns of the text.

[0816] 4. Adjust based on responses and emotions:

[0817] The server combines the answer returned by the generative AI with the emotion analysis results of the emotion engine to tailor the answer to the user's emotional state. For example, in response to the generative AI's answer "Error code 1020 is an authentication problem. Please check your user ID and password," the server adds additional information for anxious users, such as "This problem can be solved relatively easily. Please follow the next steps."

[0818] 5. Return of Response:

[0819] The adjusted answer is converted to JSON format and sent to the terminal as an HTTP response.

[0820] Overview of terminal configuration and processing

[0821] The terminal provides an interface through which the user can enter questions and receive answers from the server.

[0822] Hardware and software used: The device runs on a regular PC or smartphone and uses a web browser to provide the chat interface.

[0823] 1. Provide an interface:

[0824] The terminal provides a chat interface where users can enter questions. Once the user enters a question and clicks the send button, a request is sent to the server.

[0825] 2. Submit your request:

[0826] The terminal converts the user's input into JSON format and sends it to the server as an HTTP request.

[0827] 3. Show Answer:

[0828] The JSON response returned by the server is parsed and displayed to the user, with the content adjusted based on the emotion recognition results.

[0829] User operations and examples

[0830] Through the interface, users can ask technical questions and receive answers tailored to their emotional state.

[0831] 1. Enter your question:

[0832] The user types into the interface, "What is the interpretation of error code 1020?"

[0833] 2. Submit your request:

[0834] The device converts this question into JSON format and sends it to the server.

[0835] 3. Server-side processing:

[0836] The server receives the request and asks the generative AI for an interpretation of error code 1020. At the same time, the emotion engine analyzes the user's emotions. As a result of emotion recognition, "anxiety" is detected.

[0837] 4. Generate and refine answers:

[0838] The generative AI generates a response saying, "Error code 1020 is an authentication problem. Please check your user ID and password." Meanwhile, the emotion engine tells the server that "the user is feeling anxious." The server adds to the response, "This problem is relatively easy to solve. Please follow the next steps."

[0839] 5. Receiving and Displaying Responses:

[0840] The device analyzes the response received from the server and displays the message, "Error code 1020 is an authentication problem. Please check your user ID and password. This problem is relatively easy to resolve. Please follow the steps below."

[0841] 6. Use of Answers:

[0842] The user checks the displayed answer and follows the specific steps to solve the problem.

[0843] In this way, by combining generative AI with an emotion engine, it is possible to not only provide quick and appropriate answers to technical questions, but also to provide more effective support by taking into consideration the user's emotional state.

[0844] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0845] Step 1:

[0846] Entering and submitting a request

[0847] The user enters a technical question into the chat interface on the device, such as "What is the interpretation of error code 1020?", and clicks the send button. This input is converted by the device into JSON format (e.g., {"question":"What is the interpretation of error code 1020"}) and sent to the server as an HTTP request.

[0848] Step 2:

[0849] Receiving and parsing the request

[0850] The server receives an HTTP request from the device, analyzes the request, and obtains JSON data ({"question":"What is the interpretation of error code 1020?"}). Based on this data, it creates a prompt for the generative AI model.

[0851] Step 3:

[0852] Querying generative AI models

[0853] The server sends a prompt to a generative artificial intelligence model (e.g., OpenAI GPT-3) saying, "What is the interpretation of error code 1020?" The AI ​​model generates an answer based on this prompt and sends it back to the server. An example of the generated data is, "Error code 1020 is an authentication problem. Please check your user ID and password."

[0854] Step 4:

[0855] Emotion engine recognizes emotional states

[0856] The server sends the user's input text to an emotion engine (e.g., Microsoft Azure's Text Analytics API). The emotion engine performs emotion analysis on the input text and returns the results to the server. For example, an emotion such as "anxiety" is returned.

[0857] Step 5:

[0858] Emotion-based tailoring of responses

[0859] The server combines the answer obtained from the generative AI with the emotional state obtained from the emotion engine. For example, if the generated answer is "Error code 1020 is an authentication problem. Please check your user ID and password" and the emotional state is "anxious," the server adds additional information such as "This problem is relatively easy to solve. Please follow the next steps."

[0860] Step 6:

[0861] Submit your answer

[0862] The server converts the adjusted answer into JSON format (e.g., {"answer":"Error code 1020 is an authentication problem. Please check your user ID and password. This problem is relatively easy to resolve. Please follow the next steps"}) and sends it to the terminal as an HTTP response.

[0863] Step 7:

[0864] Receiving and viewing responses

[0865] The device receives the HTTP response from the server, parses the JSON data, and displays it to the user. For example, it might display a message like, "Error code 1020 is an authentication problem. Please check your user ID and password. This problem is relatively easy to resolve. Please follow the steps below."

[0866] In this way, by analyzing, generating, and adjusting based on input data at each step, we can provide appropriate answers to users' technical questions that take into account their emotional state.

[0867] (Application example 2)

[0868] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0869] Current systems that provide technical questions and solutions provide uniform answers without considering the user's emotional state, which can result in a poor user experience. Furthermore, on e-commerce sites, when users ask questions about products, it can take a long time for them to receive an appropriate answer, which can lead to lower satisfaction. This can lead to a decrease in purchasing motivation and a risk of customer attrition.

[0870] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for using generative artificial intelligence to provide answers to technical questions asked by developers and engineers about how to use programming languages, frameworks, and libraries and how to interpret error messages; means for suggesting best practices and design patterns to developers and engineers; means for searching and providing related information such as technical information, documentation, API references, and tutorials; means for providing advice on code refactoring and bug identification; means for supporting inquiries about project management information such as project progress, task assignment, deadline setting, and resource management, as well as data search and analysis; means for analyzing a user's emotional state and adjusting the content of the answer based on the user's emotions; means for providing emotion-based answers to product-related questions on an e-commerce site; and means for analyzing a user's questions and emotional state and adjusting and providing answers generated by generative artificial intelligence. This makes it possible to quickly provide answers that take emotions into consideration in response to users' technical questions and product-related concerns and doubts.

[0871] "Generative AI" is an AI model that generates new information and answers based on data such as text and images.

[0872] An "emotion engine" is an algorithm or software that analyzes and recognizes a user's emotional state from text or voice data.

[0873] "Technical questions" are questions about programming languages, frameworks, libraries, interpreting error messages, best practices, design patterns, technical information, documentation, API references, tutorials, refactoring code, identifying bugs, and related technical topics.

[0874] "Developers and engineers" are professionals who design, develop, operate, and maintain software and systems.

[0875] An "e-commerce site" is a website or application that facilitates the buying and selling of goods and services over the Internet.

[0876] The "user's emotional state" is an emotional state analyzed from the text or voice input by the user, such as anxiety, anger, relief, etc.

[0877] "Chat style" refers to an interface format in which a user inputs text and interacts with the system in response.

[0878] A "natural language processing model" is an artificial intelligence model that can understand and generate human language, and is used to generate optimal answers based on questions.

[0879] "API" stands for Application Program Interface, a set of protocols and tools that allow different software programs to communicate with each other.

[0880] A "design pattern" is a reusable solution to a common design problem in software development.

[0881] "Best practices" are the most effective and efficient methodologies and techniques established in a particular industry or field.

[0882] "Project management information" refers to information related to project progress, task assignment, deadline setting, resource management, and the like.

[0883] This invention uses a system that combines generative artificial intelligence and an emotion engine to provide emotion-based answers to technical questions and questions about products on e-commerce sites. Specific embodiments for realizing this system are described below.

[0884] System configuration

[0885] The server includes the following main functions:

[0886] 1. The ability to generate answers to technical and product questions using generative artificial intelligence models.

[0887] 2. The ability to use an emotion engine to analyze the user's emotional state and tailor responses appropriately.

[0888] 3. The function of receiving and analyzing requests from users.

[0889] 4. A function that combines emotional data obtained from the emotion engine with answers generated by generative artificial intelligence to provide the user with the most appropriate answer.

[0890] The terminal provides an interface through which the user can enter questions and receive answers from the server.

[0891] 1. Provide a chat-style interface where users can type in their questions.

[0892] 2. Send the user's input to the server.

[0893] 3. Display the answer received from the server.

[0894] Processing Details

[0895] The server receives requests from the device and analyzes their content. The analyzed information is passed to a generative AI model, which generates answers to technical and product-related questions. At the same time, an emotion engine analyzes the user's emotional state and generates emotion-based data. Finally, the generated answers are combined with the emotion data and provided in an optimized form to the user.

[0896] For example, suppose a user types "Can I return this product?" into a chat-style interface. The server passes this question to a generative AI model, which generates a standard answer: "You can return this product within 30 days of purchase." At the same time, the emotion engine analyzes the user's emotional state and determines it to be "anxious." As a result, the server adds the following statement to the answer: "Don't worry. You can return this product within 30 days of purchase. Detailed instructions are below.", providing the user with an optimized answer.

[0897] Hardware and Software

[0898] The specific hardware and software configuration required to realize this system is as follows:

[0899] Server equipment: A server equipped with a powerful processor and a large amount of memory (e.g., AWS EC2, Google Cloud Compute Engine).

[0900] Terminal device: A smartphone or computer operated by a user.

[0901] Generative AI models: Natural language processing models (e.g., GPT-3, BERT).

[0902] Sentiment engine: Sentiment analysis algorithms (e.g., IBM Watson Tone Analyzer, Microsoft Azure Text Analytics).

[0903] Examples of prompt statements

[0904] An example prompt for a generative AI model is:

[0905] User-submitted question: How do I get a refund if this product is broken?

[0906] Mode: Generate

[0907] Sentiment analysis results: Anxiety

[0908] Answer adjustment:

[0909] The problem is easy to solve, just follow these steps to get your refund:

[0910] Based on this prompt, the generative artificial intelligence model generates an appropriate answer and provides it to the user.

[0911] As described above, the embodiment of the present invention combines a generative artificial intelligence model and an emotion engine to realize a system that provides users with quick, emotion-sensitive answers.

[0912] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0913] Step 1:

[0914] The terminal accepts user input. The user types a question into a chat-style interface and clicks the send button. The input is in text format, and an example would be "Can I return this item?". The terminal converts this input into JSON format and sends it to the server. The input is the user question in text format, and the output is the request data in JSON format.

[0915] Step 2:

[0916] The server receives a request from the device. It analyzes the request content and prepares an API request to query the generative AI model. It analyzes the JSON formatted request data and creates a prompt to send to the generative AI model. The input is the JSON formatted request data, and the output is the prompt text to be passed to the generative AI model.

[0917] Step 3:

[0918] The server obtains the answer from the generative AI model. It sends a prompt to the generative AI model and receives the answer. The generative AI model generates an answer based on the question. The input is the prompt, and the output is the generated answer (in text format). In this example, the specific operation is to receive the answer, "This product can be returned within 30 days of purchase."

[0919] Step 4:

[0920] The server uses an emotion engine to analyze the user's emotional state. The user's input text is passed to the emotion engine for emotion analysis. The analysis result is output as an emotional state (e.g., anxiety, relief, etc.). The input is the user's question text, and the output is the emotion analysis result.

[0921] Step 5:

[0922] The server combines the answer returned by the generative AI model with the results of sentiment analysis by the emotion engine to adjust the content of the answer according to the user's emotional state. If the sentiment is negative, a detailed and thorough explanation is added. The input is the generated answer and the sentiment analysis results, and the output is the adjusted answer. In this example, based on the sentiment analysis result of "anxiety," the server adds the words "Don't worry. This product can be returned within 30 days of purchase."

[0923] Step 6:

[0924] The server converts the adjusted answer into JSON format and sends it to the terminal as an HTTP response. The input is the adjusted answer, and the output is the JSON-formatted response data. Specifically, the server encodes the adjusted answer and sends it to the terminal.

[0925] Step 7:

[0926] The device parses the JSON formatted response received from the server and displays it to the user. The input is the JSON formatted response data received from the server, and the output is the text response to be displayed. In this example, the response displayed to the user is "Don't worry. This product can be returned within 30 days of purchase."

[0927] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0928] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0929] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0930] [Third embodiment]

[0931] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0932] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0933] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0934] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0935] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0936] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0937] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0938] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0939] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0940] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0941] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0942] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0943] This invention relates to a system development support tool using generative artificial intelligence. This system is designed to quickly and efficiently address the technical challenges faced by developers and engineers.

[0944] Server configuration and processing overview

[0945] The server receives technical questions and project management information requests from the terminals and provides them to the generative AI. Specifically, it performs the following processes:

[0946] 1. Request received:

[0947] The server receives requests from the terminal using the HTTP protocol. For example, it converts the request data into JSON format and receives it.

[0948] 2. Querying Generative AI:

[0949] The server analyzes the request and makes the appropriate API calls to the generative AI model, which generates an answer based on the question.

[0950] 3. Returning the response:

[0951] The system receives the answer returned by the generative AI and sends it back to the device. The answer data is converted back to JSON format and sent as an HTTP response.

[0952] Overview of terminal configuration and processing

[0953] The terminal provides an interface for users to send technical questions and receive answers from the server. Specifically, it performs the following processes:

[0954] 1. Provide an interface:

[0955] The terminal provides a chat interface where users can enter questions, and when the user enters a question and clicks a send button, the question is sent to the server.

[0956] 2. Submit your request:

[0957] The terminal converts the user's input into JSON format and sends it to the server as an HTTP request.

[0958] 3. Show Answer:

[0959] It receives the JSON-formatted response data returned from the server, parses it, and displays it to the user, for example, as a chat bubble on the interface.

[0960] User operations and examples

[0961] Users can ask technical questions and access answers through the interface. For example:

[0962] 1. Enter your question:

[0963] The user types into the interface, "How do I read a file in Python?"

[0964] 2. Submit your request:

[0965] The device converts this question into JSON format and sends it to the server.

[0966] 3. Server-side processing:

[0967] The server receives this request and asks the generative AI, "How to read a file in Python?" The generative AI generates an appropriate answer and sends it back to the server.

[0968] 4. Receiving and Displaying Responses:

[0969] The terminal receives the response from the server and displays an answer to the user such as "In Python, you can read files using the open function. Sample code is shown below."

[0970] 5. Use of answers:

[0971] The user begins writing Python code based on the displayed answers. For example, they try to implement the file read function by using open("example.txt", "r").

[0972] This allows users to get quick and accurate answers to their technical questions, allowing them to proceed with development work efficiently. By linking the server and terminals, the system provides comprehensive technical support to developers and engineers. This configuration ensures smooth development and improved productivity.

[0973] The processing flow will be explained below.

[0974] Step 1:

[0975] The user types a question into the device interface, for example, "How do I implement asynchronous processing in JavaScript?"

[0976] Step 2:

[0977] The device converts the user's input into JSON format and sends it to the server. Specifically, the following JSON data { "question": "Please tell me how to implement asynchronous processing in JavaScript"} is sent as an HTTP POST request.

[0978] Step 3:

[0979] The server receives a request from the terminal and adds this data to the request processing queue.

[0980] Step 4:

[0981] The server analyzes the request and prepares an API request to query the generative AI model, for example, by setting up a POST request to an API endpoint and sending JSON data.

[0982] Step 5:

[0983] The generative AI receives questions sent from the server and analyzes them. For example, it understands "how to implement asynchronous processing in JavaScript" and generates an appropriate answer.

[0984] Step 6:

[0985] The generative AI generates an answer to the question and sends it back to the server. For example, it generates an answer such as, "In JavaScript, asynchronous processing can be implemented using the async / await keywords. Sample code is shown below."

[0986] Step 7:

[0987] The server receives the answer from the generative AI, converts it to JSON format { "answer": "In JavaScript, asynchronous processing can be implemented using the async / await keywords. Sample code is shown below."} and sends it to the device as an HTTP response.

[0988] Step 8:

[0989] The device analyzes the response received from the server and displays it to the user. Specifically, it displays the message "In JavaScript, asynchronous processing can be implemented using the async / await keywords. Sample code is shown below" in a chat bubble on the interface.

[0990] Step 9:

[0991] Users can check the displayed answers and apply them to their own development. For example, they can add sample code such as function fetchData() { const response = await fetch(url); const data = await response.json();} to their own projects to implement asynchronous processing.

[0992] Example 1

[0993] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0994] Modern engineers and developers face the complexity of programming languages, software frameworks, and libraries. Furthermore, the complexity of analyzing error messages and project management makes it difficult to work efficiently. Furthermore, the sheer volume of technical information and reference materials makes it difficult to quickly find the information you need. To address these challenges, a system is needed that can efficiently and quickly provide answers to technical questions and support project management.

[0995] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0996] In this invention, the server includes: means for using generative artificial intelligence to provide answers to technical questions developers and engineers have about how to use programming languages, software frameworks, and software libraries, and how to analyze error messages; means for suggesting best practices and design styles to developers and engineers; means for searching and providing related information such as technical information, documentation, application programming interface references, and educational materials; means for providing advice on code refactoring and fault identification; means for supporting inquiries about project management information such as project progress, task assignment, deadline setting, and resource management, as well as data search and analysis; a server device that receives technical questions from a terminal device as JSON-formatted data and provides the received data to a generative artificial intelligence model to generate answers; a server device that returns the generated answers to the terminal device as JSON-formatted data; a terminal device that provides an interface for inputting technical questions, analyzes the JSON-formatted answer data received from the server device, and displays it to the user; and a generative artificial intelligence model that generates optimal answers based on the content of the questions. This enables engineers and developers to quickly and efficiently obtain the information they need, allowing them to solve technical problems and manage projects smoothly.

[0997] "Generative AI" is AI that generates natural language text based on data, and is used to answer questions and generate sentences.

[0998] An "engineer" is an individual with specialized knowledge of software development and system design.

[0999] A "programming language" is a language used to write instructions to a computer to perform specific processes.

[1000] A "software framework" is a collection of reusable components and libraries provided to streamline software development.

[1001] A "software library" is a collection of functions or classes available to program developers that provide a specific functionality.

[1002] An "error message" is a text message that reports a problem that occurs during the operation of software or a system.

[1003] A "best practice" is a method or technique that is optimized to achieve the best results in a particular technology or task.

[1004] A "design style" is a template or pattern that provides a repeatable solution for software or system design.

[1005] "Document" means a paper or file that describes technical information or procedures.

[1006] An "Application Programming Interface Reference" is a document that describes the interfaces that software and systems use to communicate with each other and how to use them.

[1007] "Educational materials" are teaching materials for learning specific skills or knowledge.

[1008] "Refactoring" is the process of improving the internal structure of software to increase its maintainability and extensibility.

[1009] A "failure" is a problem or malfunction in the operation of a system or software.

[1010] "Project management information" is data or information regarding project progress, task assignments, deadlines, and resource allocation.

[1011] A "terminal device" is a device that allows a user to input questions and receive and display answers.

[1012] A "server device" is a computer that receives requests from terminal devices, queries the generative artificial intelligence model, and generates and returns answers.

[1013] A "generative artificial intelligence model" is an artificial intelligence algorithm that generates answers to questions based on data.

[1014] A "natural language processing model" is an artificial intelligence technology for processing, understanding, and generating human language.

[1015] This invention is a system that uses generative artificial intelligence to solve technical problems faced by engineers and developers and support project management. This system is mainly composed of a server device and a terminal device, each of which fulfills a specific role to achieve seamless technical support.

[1016] Roles and operations of server devices

[1017] The server device plays a central role in processing technical questions received from the terminal device. The server first receives a request from the terminal using the HTTP protocol. The received request is data in JSON format and is analyzed. The server then sends a prompt to the generative AI model, which generates the optimal answer. An example of a generative AI model would be the OpenAI API. This answer is then converted back into JSON format and sent back to the terminal device as an HTTP response. A typical server computer is used for the specific hardware, and Python or Flask is used for the software.

[1018] Example prompt sentence:

[1019] How do I read a file in Python?

[1020] Roles and operations of terminal devices

[1021] The terminal device provides an interface with the user. The terminal device displays a chat interface that allows the user to input technical questions. When the user inputs a question and clicks the send button, the question is converted into JSON format and sent to the server device as an HTTP request. When the terminal device receives the answer returned from the server, it analyzes it and displays it in a format that is easy for the user to view. Specifically, JavaScript, HTML, and AJAX technology are used.

[1022] User operations

[1023] A user inputs a technical question through the chat interface of the terminal device. For example, they input a question such as "How do I read a file in Python?". When they click the send button, the question is sent to the server, and an answer is returned by the generative artificial intelligence. The received answer is displayed to the user in the form of, for example, "In Python, you can read a file using the open function. Sample code is shown below."

[1024] In this way, the server and terminal devices work together to quickly and efficiently provide answers to technical questions and solve the complex problems faced by engineers and developers. Furthermore, the use of generative AI models ensures that the most appropriate answers are provided for each question, allowing users to proceed with their work based on reliable information.

[1025] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1026] Step 1:

[1027] The user enters a question and submits it

[1028] Specific behavior:

[1029] The user opens the chat interface on their device, types a question, for example, "How do I read a file in Python?", and clicks the send button.

[1030] input:

[1031] The text "How do I read a file in Python?"

[1032] output:

[1033] Text data of the question entered into the terminal device

[1034] Step 2:

[1035] The terminal device forms a request and sends it to the server

[1036] Specific behavior:

[1037] The terminal device converts the input question into JSON format and sends it to the server as an HTTP request. The transmission is asynchronous using AJAX technology.

[1038] input:

[1039] The text "How do I read a file in Python?"

[1040] Data processing:

[1041] Convert the question text to JSON format

[1042] output:

[1043] {"Question": "How do I read a file in Python?"} JSON data

[1044] Step 3:

[1045] The server receives and parses the request

[1046] Specific behavior:

[1047] The server receives the request via HTTP protocol, parses the JSON data, and extracts the question. The Flask framework is used to receive and parse the request.

[1048] input:

[1049] {"Question": "How do I read a file in Python?"} JSON data

[1050] Data Calculation:

[1051] Parse the JSON data to extract the question text

[1052] output:

[1053] The text "How do I read a file in Python?"

[1054] Step 4:

[1055] The server queries the generative AI model

[1056] Specific behavior:

[1057] The server sends the question as a prompt to the generative AI model, which then generates an answer. The server sends the prompt using the OpenAI API or similar and obtains the answer.

[1058] input:

[1059] The text "How do I read a file in Python?"

[1060] Data Calculation:

[1061] A generative AI model generates an answer based on the prompt.

[1062] output:

[1063] The text reads "In Python, you can read a file using the open function. Here is some sample code."

[1064] Step 5:

[1065] The server converts the response into JSON format and sends it back.

[1066] Specific behavior:

[1067] The server processes the answer obtained from the generative AI model into JSON format and returns it to the terminal device as an HTTP response. The response is created using a framework such as Flask.

[1068] input:

[1069] The text reads "In Python, you can read a file using the open function. Here is some sample code."

[1070] Data processing:

[1071] Convert the answer text to JSON format

[1072] output:

[1073] {"Answer": "In Python, you can read a file using the open function. Here is a sample code:"}

[1074] Step 6:

[1075] The terminal device receives and displays the response.

[1076] Specific behavior:

[1077] The terminal device receives the JSON-formatted response data returned from the server, analyzes it, and displays it to the user as a chat bubble using JavaScript DOM manipulation.

[1078] input:

[1079] {"Answer": "In Python, you can read a file using the open function. Here is a sample code:"}

[1080] Data Calculation:

[1081] Parse the JSON data to extract the answer text

[1082] output:

[1083] The text "In Python, you can read files using the open function. Here's some sample code." displayed in the chat interface

[1084] (Application example 1)

[1085] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1086] With conventional technologies, developers and engineers lack the means to quickly and efficiently respond to technical questions about programming and project management. Furthermore, when a robot encounters a technical issue in a factory, there is no support system to immediately resolve the issue, which can lead to reduced productivity and business downtime.

[1087] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1088] In this invention, the server includes: means for using generative artificial intelligence to provide answers to technical questions from developers and engineers about how to use programming languages, frameworks, and libraries and how to interpret error messages; means for suggesting best practices and design patterns to developers and engineers; means for searching and providing related information such as technical information, documentation, API references, and tutorials; means for providing advice on code refactoring and bug identification; means for supporting querying project management information such as project progress, task assignment, deadline setting, and resource management, as well as data search and analysis; means for querying technical problems in real time when they occur in the factory and presenting appropriate solutions using generative artificial intelligence; means for transmitting information on specific technical problems faced by robots to the server and receiving answers from the generative artificial intelligence; and means for the robots to execute procedures to solve the problems based on the answers received. This enables technical problems to be resolved quickly, improving the efficiency and productivity of development and factory operations.

[1089] "Generative AI" is an AI system that has the ability to generate answers in natural language in response to questions or requests.

[1090] "Technical questions" are questions about how to use programming languages, frameworks, libraries, and how to interpret error messages that developers and engineers encounter during the development process.

[1091] A "best practice" is a standard methodology or technique that is considered to be the most effective and efficient way to carry out a particular task or process.

[1092] A "design pattern" is a design template that is used repeatedly to efficiently solve a particular problem.

[1093] "Technical information" refers to knowledge and data about a specific technology, including documentation, API references, tutorials, etc.

[1094] "Refactoring" is a technique for improving the internal structure of software without changing its functionality.

[1095] "Bug identification" is the process of finding errors or defects in software or hardware and identifying where to fix them.

[1096] "Project management information" refers to information for effectively progressing a project, such as project progress, task assignment, deadline setting, and resource management.

[1097] "Technical problems in factories" are problems related to factory equipment or systems not working properly or malfunctioning.

[1098] "Real-time problem inquiry" means that the moment a technical problem occurs, that information is immediately sent to generative artificial intelligence for a solution.

[1099] "Specific technical problems faced by robots" refers to specific obstacles or error messages that factory robots encounter while operating.

[1100] A "server" is an information processing device that accepts requests from clients, queries the generative artificial intelligence, and returns a response.

[1101] A "terminal" is an information processing device that allows a user to input a question and receives and displays a response from a server.

[1102] This invention provides a system that utilizes generative artificial intelligence to quickly solve technical problems in factory robots. This system is realized with the following configuration and processing procedure.

[1103] System Program

[1104] When a factory robot encounters a technical problem, it immediately sends the information to a server, receives a response from generative artificial intelligence, and solves the problem.

[1105] Server Roles and Operations

[1106] The server receives requests from the factory robots regarding technical issues and provides them to the generative artificial intelligence. Specifically, it performs the following processes:

[1107] 1. Request received:

[1108] The server receives requests from robots using the HTTP protocol, including JSON-formatted data that contains information such as the problem description and error code.

[1109] 2. Querying Generative AI:

[1110] The server analyzes the received request and makes the appropriate API call to the generative AI model, which then generates an answer to the query.

[1111] 3. Returning the response:

[1112] It receives the answer returned by the generative AI and sends it back to the robot. The answer data is converted to JSON format and sent as an HTTP response.

[1113] Robot Roles and Processing

[1114] The robot detects technical issues during factory operations and provides an interface for querying the issue to the generative artificial intelligence. Specifically, the robot performs the following processes:

[1115] 1. Detecting the problem and submitting a request:

[1116] If the robot detects a technical problem during operation, it converts the details of the problem (e.g., error code or abnormal behavior) into JSON format and sends it to the server as an HTTP request.

[1117] 2. Receiving and implementing responses:

[1118] It receives the JSON-formatted response data returned from the server, analyzes it, and executes steps to resolve the problem, such as checking the motor connection or replacing the motor.

[1119] Hardware and software used

[1120] The following hardware and software are used in this system:

[1121] Hardware: Factory robots (e.g., Raspberry Pi), server equipment

[1122] Software: Python, Requests library, Generative AI API (e.g. OpenAI API)

[1123] Specific examples

[1124] For example, if a factory robot detects a motor abnormality while operating on a production line, it will send the following prompt sentence to the generative artificial intelligence:

[1125] Example prompt sentence:

[1126] "Error code 4040: Motor malfunction"

[1127] "timestamp: 2023-10-01T12:00:00Z"

[1128] "motor_id: MTR-001"

[1129] "status_code: 4040"

[1130] A generative artificial intelligence might respond to this with something like this:

[1131] Example answer:

[1132] "Check motor connections and ensure that the motor driver circuit is functioning correctly. If the problem persists, replace the motor."

[1133] The robot receives this response and first checks the motor connections and replaces the motor if necessary.

[1134] In this way, when a factory robot encounters a technical problem, the problem can be resolved quickly, improving productivity.

[1135] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1136] Step 1:

[1137] Problem detection and data generation

[1138] The robot detects technical issues during operation, such as abnormal motor behavior or error codes, and obtains detailed information from sensors inside the robot and system logs.

[1139] Input: Error code and related problem details

[1140] Output: JSON formatted data containing details about the issue

[1141] Specific operation: The robot detects the error message "Error code 4040: Motor malfunction" and retrieves detailed information about the error (e.g., timestamp and motor ID) from its internal log.

[1142] Step 2:

[1143] Sending data

[1144] The robot converts the detailed information of the problem it has obtained into JSON format and sends it to the server as an HTTP request.

[1145] Input: JSON formatted problem details generated in Step 1

[1146] Output: HTTP request sent to the server

[1147] Specific operation: The robot sends JSON data such as "{"issue": "Error code 4040: Motor malfunction", "timestamp": "2023-10-01T12:00:00Z", "motor_id": "MTR-001", "status_code": 4040}" as an HTTP POST request to the server's API endpoint.

[1148] Step 3:

[1149] Receiving and parsing the request

[1150] The server receives the HTTP request from the robot, analyzes its contents, and extracts the information necessary to query the generative AI.

[1151] Input: HTTP request received from the robot (detailed problem data in JSON format)

[1152] Output: Data for API calls to generative AI

[1153] What happens: The server receives the HTTP request, parses the JSON data, extracts keys and values ​​such as "issue", "timestamp", and "motor_id", and reformats them.

[1154] Step 4:

[1155] Inquiry into generative AI

[1156] Based on the analyzed data, the server makes an API call to the generative artificial intelligence to generate an appropriate answer.

[1157] Input: Parsed problem details data

[1158] Output: Answer data from generative AI

[1159] Specific operation: The server sends the extracted data to the generative artificial intelligence API, which generates a prompt in the form of, for example, "Please tell me the steps to resolve the motor's abnormal operation," and sends it to the AI.

[1160] Step 5:

[1161] Response reception and data conversion

[1162] The server receives the answer from the generative AI, converts it into JSON format, and prepares it for sending back to the robot.

[1163] Input: Answer data from generative AI

[1164] Output: JSON formatted answer data to send back to the robot

[1165] Specific operation: The generative AI receives the answer "Check motor connections and ensure the motor driver circuit is functioning correctly. If the problem persists, replace the motor." and converts this into JSON format such as "{"solution": "Check motor connections and ensure the motor driver circuit is functioning correctly. If the problem persists, replace the motor."}".

[1166] Step 6:

[1167] Returning answers and running them in a robot

[1168] The server sends the prepared answer data back to the robot, which analyzes it and executes steps to solve the problem.

[1169] Input: JSON format response data from the server

[1170] Output: Robot executes problem-solving steps

[1171] Specific behavior: The robot receives the answer, "Check motor connections and ensure the motor driver circuit is functioning correctly. If the problem persists, replace the motor." It first checks the motor connections, and if the problem persists, replaces the motor.

[1172] Through the above processing steps, when a factory robot encounters a technical problem, it can utilize generative artificial intelligence to quickly solve the problem.

[1173] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1174] This invention relates to a system development support tool that combines generative artificial intelligence and an emotion engine. This system quickly and efficiently addresses the technical challenges faced by developers and engineers, and also provides more human-like and effective support by recognizing the user's emotional state and adjusting the support content accordingly.

[1175] Server configuration and processing overview

[1176] The server receives requests from the device and works in conjunction with the generative AI and emotion engine. Specifically, it performs the following processes:

[1177] 1. Request received:

[1178] The server receives technical questions and project management information requests from the device. The received data is in JSON format.

[1179] 2. Querying Generative AI:

[1180] The server analyzes the request and prepares an API request to query the generative AI model, which generates an answer based on the question.

[1181] 3. Emotion engine recognizes user emotions:

[1182] The server simultaneously uses an emotion engine to recognize the user's emotional state, for example, by inferring the user's emotions from the tone and patterns of the text.

[1183] 4. Adjust based on responses and emotions:

[1184] The answer returned by the generative AI is combined with the results of emotion analysis by the emotion engine to tailor the answer to the user's emotional state. If the emotion is negative, a detailed and thorough explanation is added.

[1185] 5. Return of Response:

[1186] The adjusted answer is converted to JSON format and sent to the device as an HTTP response.

[1187] Overview of terminal configuration and processing

[1188] The terminal provides an interface for users to input questions and receive answers from the server. Specifically, it performs the following processes.

[1189] 1. Provide an interface:

[1190] The terminal provides a chat interface where users can enter questions, which are then sent to the server when the user clicks a send button.

[1191] 2. Submit your request:

[1192] The terminal converts the user's input into JSON format and sends it to the server as an HTTP request.

[1193] 3. Show Answer:

[1194] Parse the JSON response returned by the server and display it to the user, including responses adjusted based on emotion recognition results.

[1195] User operations and examples

[1196] Through the interface, users can ask technical questions and receive answers tailored to their emotional state.

[1197] 1. Enter your question:

[1198] The user types into the interface, "What is the interpretation of error code 1020?"

[1199] 2. Submit your request:

[1200] The device converts this question into JSON format and sends it to the server.

[1201] 3. Server-side processing:

[1202] The server receives the request and asks the generative AI for an interpretation of error code 1020. At the same time, the emotion engine analyzes the user's emotions. As a result of emotion recognition, "anxiety" is detected.

[1203] 4. Generate and refine answers:

[1204] The generative AI generates a response saying, "Error code 1020 is an authentication problem. Please check your user ID and password." Meanwhile, the emotion engine tells the server that "the user is feeling anxious." The server adds to the response, "This problem is relatively easy to solve. Please follow the next steps."

[1205] 5. Receiving and Displaying Responses:

[1206] The device analyzes the response received from the server and displays the message, "Error code 1020 is an authentication problem. Please check your user ID and password. This problem is relatively easy to resolve. Please follow the steps below."

[1207] 6. Use of Answers:

[1208] The user checks the displayed answer and follows the specific steps to solve the problem.

[1209] In this way, by combining generative AI with an emotion engine, we are able to provide not only fast and appropriate answers to technical questions, but also more effective support by taking into consideration the user's emotional state.

[1210] The processing flow will be explained below.

[1211] Step 1:

[1212] A user types a question into a terminal interface, for example, "How do I handle exceptions in Python?"

[1213] Step 2:

[1214] The terminal converts the user's input into JSON format and sends it to the server as an HTTP POST request. Specifically, it sends the data { "question": "Please tell me how to handle exceptions in Python"}.

[1215] Step 3:

[1216] The server receives the request from the terminal and analyzes the request content appropriately to add this data to the request processing queue.

[1217] Step 4:

[1218] Based on the request analyzed by the server, an API request is prepared to query the generative AI model. For example, a POST request is set up to the AI's API endpoint and the query data is sent.

[1219] Step 5:

[1220] The generative AI receives and analyzes questions sent from the server. It understands "how to handle exceptions in Python" and generates an appropriate answer. Specifically, it generates an answer such as, "Exception handling in Python is done using the try and except statements. Sample code is shown below."

[1221] Step 6:

[1222] The generative AI returns the generated answer to the server. For example, it returns JSON data containing an answer such as, "Python handles exceptions using the try and except statements. Sample code is shown below."

[1223] Step 7:

[1224] The server receives the response from the generative AI and simultaneously analyzes the user's emotional state using the emotion engine. For example, suppose the tone and expression of the input text indicate "anxiety."

[1225] Step 8:

[1226] The emotion engine sends the emotion analysis results back to the server. Specifically, it sends the analysis result that "the user is feeling anxious."

[1227] Step 9:

[1228] The server integrates the generative AI's answers with the analysis results of the emotion engine and adjusts the answer as needed. For example, if "anxiety" is detected, a detailed and polite explanation such as "This problem is relatively easy to solve. Please follow the next steps" is added.

[1229] Step 10:

[1230] The server then converts the final adjusted answer into JSON format and sends it to the device as an HTTP response.

[1231] Step 11:

[1232] The device analyzes the response received from the server and displays it to the user. Specifically, the chat interface displays the message, "Python uses the try and except statements to handle exceptions. Below is a sample code. This problem is relatively easy to solve. Please follow the steps below."

[1233] Step 12:

[1234] The user reviews the displayed answer and follows specific steps to solve the problem, for example, adding try and except statements to the Python code to implement exception handling.

[1235] In this way, the combination of generative AI and emotion engines can provide relevant answers to technical questions and personalize responses based on the user's emotional state, improving the user experience and significantly improving the efficiency of development efforts.

[1236] Example 2

[1237] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1238] Conventional technical consultation systems simply provide answers to technical questions without taking into account the user's emotional state. As a result, if a user is feeling anxious or stressed, their emotions are not taken into account and appropriate support is not provided. Another problem is that the quality of answers to technical questions varies, making it difficult to obtain advice that is appropriate for the content of the question or the user's background.

[1239] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1240] In this invention, the server includes means for using generative artificial intelligence to provide answers to technical questions from developers and engineers about how to use programming languages, software frameworks, and libraries and how to interpret error messages, means for suggesting best practices and design methods to developers and engineers, means for searching and providing related information such as technical information, documentation, API references, and tutorials, and means for recognizing the emotional state of a user using an emotion engine and adjusting the content of the answer based on the user's emotional state. This makes it possible to provide quick and appropriate answers to technical questions and support that takes the user's emotional state into consideration.

[1241] "Generative AI" refers to AI that automatically generates answers and suggestions in response to questions and requests from users in natural language.

[1242] "Technical questions" are questions about technical content, such as how to use programming languages, software frameworks, libraries, or interpret error messages.

[1243] An "emotion engine" is a technology for analyzing and recognizing a user's emotional state from text input and other interaction data.

[1244] "Best practices" is a concept that refers to the most efficient and effective methods and techniques in a particular technical field.

[1245] A "design method" refers to the techniques and methodologies used when designing systems and applications in software development.

[1246] "Technical information" refers to all information that developers and engineers need to perform technical work.

[1247] "Documentation" refers to documents that describe the specifications, design, and usage of software or systems.

[1248] An "API Reference" is a document that provides detailed instructions on how to use the application programming interface (API) provided by a particular program.

[1249] A "tutorial" is educational content that provides step-by-step instructions on how to use and apply a particular technology or tool.

[1250] A "terminal" is an electronic device or interface through which a user enters technical questions and receives responses from a server.

[1251] A "server" is a computer system that receives requests from users, processes them accordingly, and returns generated answers or advice to the users.

[1252] A "natural language processing model" is an algorithm for analyzing and understanding natural language text and converting it into human-readable information.

[1253] This invention is a system that combines generative artificial intelligence and an emotion engine. This system quickly and efficiently addresses the technical challenges faced by developers and engineers, and also provides more human-like and effective assistance by recognizing the user's emotional state and adjusting the assistance content accordingly.

[1254] Server configuration and processing overview

[1255] The server receives requests from the device and works in conjunction with the generative AI and emotion engine. Specifically, it performs the following processes:

[1256] Software and hardware used: The server uses "OpenAI GPT-3" as the generative AI and "Microsoft Azure's Text Analytics API" as the emotion engine. The server itself uses a server machine with a high-performance CPU and sufficient memory.

[1257] 1. Request received:

[1258] The server receives technical questions and project management information requests in JSON format from the device. For example, if a user types a question like "What is the interpretation of error code 1020?", this request is sent to the server.

[1259] 2. Querying Generative AI:

[1260] The server analyzes the received request and prepares an API request to query the generative AI model. For example, it sends a prompt message to OpenAI GPT-3: "Please tell me the interpretation of error code 1020."

[1261] 3. Emotion engine recognizes user emotions:

[1262] The server also uses Microsoft Azure's Text Analytics API to analyze the user's emotional state from the received text. For example, emotions such as "anxiety" may be recognized from the tone and patterns of the text.

[1263] 4. Adjust based on responses and emotions:

[1264] The server combines the answer returned by the generative AI with the emotion analysis results of the emotion engine to tailor the answer to the user's emotional state. For example, in response to the generative AI's answer "Error code 1020 is an authentication problem. Please check your user ID and password," the server adds additional information for anxious users, such as "This problem can be solved relatively easily. Please follow the next steps."

[1265] 5. Return of Response:

[1266] The adjusted answer is converted to JSON format and sent to the terminal as an HTTP response.

[1267] Overview of terminal configuration and processing

[1268] The terminal provides an interface through which the user can enter questions and receive answers from the server.

[1269] Hardware and software used: The device runs on a regular PC or smartphone and uses a web browser to provide the chat interface.

[1270] 1. Provide an interface:

[1271] The terminal provides a chat interface where users can enter questions. Once the user enters a question and clicks the send button, a request is sent to the server.

[1272] 2. Submit your request:

[1273] The terminal converts the user's input into JSON format and sends it to the server as an HTTP request.

[1274] 3. Show Answer:

[1275] The JSON response returned by the server is parsed and displayed to the user, with the content adjusted based on the emotion recognition results.

[1276] User operations and examples

[1277] Through the interface, users can ask technical questions and receive answers tailored to their emotional state.

[1278] 1. Enter your question:

[1279] The user types into the interface, "What is the interpretation of error code 1020?"

[1280] 2. Submit your request:

[1281] The device converts this question into JSON format and sends it to the server.

[1282] 3. Server-side processing:

[1283] The server receives the request and asks the generative AI for an interpretation of error code 1020. At the same time, the emotion engine analyzes the user's emotions. As a result of emotion recognition, "anxiety" is detected.

[1284] 4. Generate and refine answers:

[1285] The generative AI generates a response saying, "Error code 1020 is an authentication problem. Please check your user ID and password." Meanwhile, the emotion engine tells the server that "the user is feeling anxious." The server adds to the response, "This problem is relatively easy to solve. Please follow the next steps."

[1286] 5. Receiving and Displaying Responses:

[1287] The device analyzes the response received from the server and displays the message, "Error code 1020 is an authentication problem. Please check your user ID and password. This problem is relatively easy to resolve. Please follow the steps below."

[1288] 6. Use of Answers:

[1289] The user checks the displayed answer and follows the specific steps to solve the problem.

[1290] In this way, by combining generative AI with an emotion engine, it is possible to not only provide quick and appropriate answers to technical questions, but also to provide more effective support by taking into consideration the user's emotional state.

[1291] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1292] Step 1:

[1293] Entering and submitting a request

[1294] The user enters a technical question into the chat interface on the device, such as "What is the interpretation of error code 1020?", and clicks the send button. This input is converted by the device into JSON format (e.g., {"question":"What is the interpretation of error code 1020"}) and sent to the server as an HTTP request.

[1295] Step 2:

[1296] Receiving and parsing the request

[1297] The server receives an HTTP request from the device, analyzes the request, and obtains JSON data ({"question":"What is the interpretation of error code 1020?"}). Based on this data, it creates a prompt for the generative AI model.

[1298] Step 3:

[1299] Querying generative AI models

[1300] The server sends a prompt to a generative artificial intelligence model (e.g., OpenAI GPT-3) saying, "What is the interpretation of error code 1020?" The AI ​​model generates an answer based on this prompt and sends it back to the server. An example of the generated data is, "Error code 1020 is an authentication problem. Please check your user ID and password."

[1301] Step 4:

[1302] Emotion engine recognizes emotional states

[1303] The server sends the user's input text to an emotion engine (e.g., Microsoft Azure's Text Analytics API). The emotion engine performs emotion analysis on the input text and returns the results to the server. For example, an emotion such as "anxiety" is returned.

[1304] Step 5:

[1305] Emotion-based tailoring of responses

[1306] The server combines the answer obtained from the generative AI with the emotional state obtained from the emotion engine. For example, if the generated answer is "Error code 1020 is an authentication problem. Please check your user ID and password" and the emotional state is "anxious," the server adds additional information such as "This problem is relatively easy to solve. Please follow the next steps."

[1307] Step 6:

[1308] Submit your answer

[1309] The server converts the adjusted answer into JSON format (e.g., {"answer":"Error code 1020 is an authentication problem. Please check your user ID and password. This problem is relatively easy to resolve. Please follow the next steps"}) and sends it to the terminal as an HTTP response.

[1310] Step 7:

[1311] Receiving and viewing responses

[1312] The device receives the HTTP response from the server, parses the JSON data, and displays it to the user. For example, it might display a message like, "Error code 1020 is an authentication problem. Please check your user ID and password. This problem is relatively easy to resolve. Please follow the steps below."

[1313] In this way, by analyzing, generating, and adjusting based on input data at each step, we can provide appropriate answers to users' technical questions that take into account their emotional state.

[1314] (Application example 2)

[1315] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1316] Current systems that provide technical questions and solutions provide uniform answers without considering the user's emotional state, which can result in a poor user experience. Furthermore, on e-commerce sites, when users ask questions about products, it can take a long time for them to receive an appropriate answer, which can lead to lower satisfaction. This can lead to a decrease in purchasing motivation and a risk of customer attrition.

[1317] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for using generative artificial intelligence to provide answers to technical questions asked by developers and engineers about how to use programming languages, frameworks, and libraries and how to interpret error messages; means for suggesting best practices and design patterns to developers and engineers; means for searching and providing related information such as technical information, documentation, API references, and tutorials; means for providing advice on code refactoring and bug identification; means for supporting inquiries about project management information such as project progress, task assignment, deadline setting, and resource management, as well as data search and analysis; means for analyzing a user's emotional state and adjusting the content of the answer based on the user's emotions; means for providing emotion-based answers to product-related questions on an e-commerce site; and means for analyzing a user's questions and emotional state and adjusting and providing answers generated by generative artificial intelligence. This makes it possible to quickly provide answers that take emotions into consideration in response to users' technical questions and product-related concerns and doubts.

[1318] "Generative AI" is an AI model that generates new information and answers based on data such as text and images.

[1319] An "emotion engine" is an algorithm or software that analyzes and recognizes a user's emotional state from text or voice data.

[1320] "Technical questions" are questions about programming languages, frameworks, libraries, interpreting error messages, best practices, design patterns, technical information, documentation, API references, tutorials, refactoring code, identifying bugs, and related technical topics.

[1321] "Developers and engineers" are professionals who design, develop, operate, and maintain software and systems.

[1322] An "e-commerce site" is a website or application that facilitates the buying and selling of goods and services over the Internet.

[1323] The "user's emotional state" is an emotional state analyzed from the text or voice input by the user, such as anxiety, anger, relief, etc.

[1324] "Chat style" refers to an interface format in which a user inputs text and interacts with the system in response.

[1325] A "natural language processing model" is an artificial intelligence model that can understand and generate human language, and is used to generate optimal answers based on questions.

[1326] "API" stands for Application Program Interface, a set of protocols and tools that allow different software programs to communicate with each other.

[1327] A "design pattern" is a reusable solution to a common design problem in software development.

[1328] "Best practices" are the most effective and efficient methodologies and techniques established in a particular industry or field.

[1329] "Project management information" refers to information related to project progress, task assignment, deadline setting, resource management, and the like.

[1330] This invention uses a system that combines generative artificial intelligence and an emotion engine to provide emotion-based answers to technical questions and questions about products on e-commerce sites. Specific embodiments for realizing this system are described below.

[1331] System configuration

[1332] The server includes the following main functions:

[1333] 1. The ability to generate answers to technical and product questions using generative artificial intelligence models.

[1334] 2. The ability to use an emotion engine to analyze the user's emotional state and tailor responses appropriately.

[1335] 3. The function of receiving and analyzing requests from users.

[1336] 4. A function that combines emotional data obtained from the emotion engine with answers generated by generative artificial intelligence to provide the user with the most appropriate answer.

[1337] The terminal provides an interface through which the user can enter questions and receive answers from the server.

[1338] 1. Provide a chat-style interface where users can type in their questions.

[1339] 2. Send the user's input to the server.

[1340] 3. Display the answer received from the server.

[1341] Processing Details

[1342] The server receives requests from the device and analyzes their content. The analyzed information is passed to a generative AI model, which generates answers to technical and product-related questions. At the same time, an emotion engine analyzes the user's emotional state and generates emotion-based data. Finally, the generated answers are combined with the emotion data and provided in an optimized form to the user.

[1343] For example, suppose a user types "Can I return this product?" into a chat-style interface. The server passes this question to a generative AI model, which generates a standard answer: "You can return this product within 30 days of purchase." At the same time, the emotion engine analyzes the user's emotional state and determines it to be "anxious." As a result, the server adds the following statement to the answer: "Don't worry. You can return this product within 30 days of purchase. Detailed instructions are below.", providing the user with an optimized answer.

[1344] Hardware and Software

[1345] The specific hardware and software configuration required to realize this system is as follows:

[1346] Server equipment: A server equipped with a powerful processor and a large amount of memory (e.g., AWS EC2, Google Cloud Compute Engine).

[1347] Terminal device: A smartphone or computer operated by a user.

[1348] Generative AI models: Natural language processing models (e.g., GPT-3, BERT).

[1349] Sentiment engine: Sentiment analysis algorithms (e.g., IBM Watson Tone Analyzer, Microsoft Azure Text Analytics).

[1350] Examples of prompt statements

[1351] An example prompt for a generative AI model is:

[1352] User-submitted question: How do I get a refund if this product is broken?

[1353] Mode: Generate

[1354] Sentiment analysis results: Anxiety

[1355] Answer adjustment:

[1356] The problem is easy to solve, just follow these steps to get your refund:

[1357] Based on this prompt, the generative artificial intelligence model generates an appropriate answer and provides it to the user.

[1358] As described above, the embodiment of the present invention combines a generative artificial intelligence model and an emotion engine to realize a system that provides users with quick, emotion-sensitive answers.

[1359] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1360] Step 1:

[1361] The terminal accepts user input. The user types a question into a chat-style interface and clicks the send button. The input is in text format, and an example would be "Can I return this item?". The terminal converts this input into JSON format and sends it to the server. The input is the user question in text format, and the output is the request data in JSON format.

[1362] Step 2:

[1363] The server receives a request from the device. It analyzes the request content and prepares an API request to query the generative AI model. It analyzes the JSON formatted request data and creates a prompt to send to the generative AI model. The input is the JSON formatted request data, and the output is the prompt text to be passed to the generative AI model.

[1364] Step 3:

[1365] The server obtains the answer from the generative AI model. It sends a prompt to the generative AI model and receives the answer. The generative AI model generates an answer based on the question. The input is the prompt, and the output is the generated answer (in text format). In this example, the specific operation is to receive the answer, "This product can be returned within 30 days of purchase."

[1366] Step 4:

[1367] The server uses an emotion engine to analyze the user's emotional state. The user's input text is passed to the emotion engine for emotion analysis. The analysis result is output as an emotional state (e.g., anxiety, relief, etc.). The input is the user's question text, and the output is the emotion analysis result.

[1368] Step 5:

[1369] The server combines the answer returned by the generative AI model with the results of sentiment analysis by the emotion engine to adjust the content of the answer according to the user's emotional state. If the sentiment is negative, a detailed and thorough explanation is added. The input is the generated answer and the sentiment analysis results, and the output is the adjusted answer. In this example, based on the sentiment analysis result of "anxiety," the server adds the words "Don't worry. This product can be returned within 30 days of purchase."

[1370] Step 6:

[1371] The server converts the adjusted answer into JSON format and sends it to the terminal as an HTTP response. The input is the adjusted answer, and the output is the JSON-formatted response data. Specifically, the server encodes the adjusted answer and sends it to the terminal.

[1372] Step 7:

[1373] The device parses the JSON formatted response received from the server and displays it to the user. The input is the JSON formatted response data received from the server, and the output is the text response to be displayed. In this example, the response displayed to the user is "Don't worry. This product can be returned within 30 days of purchase."

[1374] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1375] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1376] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1377] [Fourth embodiment]

[1378] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1379] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1380] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1381] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1382] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1383] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1384] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1385] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1386] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1387] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1388] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1389] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1390] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1391] This invention relates to a system development support tool using generative artificial intelligence. This system is designed to quickly and efficiently address the technical challenges faced by developers and engineers.

[1392] Server configuration and processing overview

[1393] The server receives technical questions and project management information requests from the terminals and provides them to the generative AI. Specifically, it performs the following processes:

[1394] 1. Request received:

[1395] The server receives requests from the terminal using the HTTP protocol. For example, it converts the request data into JSON format and receives it.

[1396] 2. Querying Generative AI:

[1397] The server analyzes the request and makes the appropriate API calls to the generative AI model, which generates an answer based on the question.

[1398] 3. Returning the response:

[1399] The system receives the answer returned by the generative AI and sends it back to the device. The answer data is converted back to JSON format and sent as an HTTP response.

[1400] Overview of terminal configuration and processing

[1401] The terminal provides an interface for users to send technical questions and receive answers from the server. Specifically, it performs the following processes:

[1402] 1. Provide an interface:

[1403] The terminal provides a chat interface where users can enter questions, and when the user enters a question and clicks a send button, the question is sent to the server.

[1404] 2. Submit your request:

[1405] The terminal converts the user's input into JSON format and sends it to the server as an HTTP request.

[1406] 3. Show Answer:

[1407] It receives the JSON-formatted response data returned from the server, parses it, and displays it to the user, for example, as a chat bubble on the interface.

[1408] User operations and examples

[1409] Users can ask technical questions and access answers through the interface. For example:

[1410] 1. Enter your question:

[1411] The user types into the interface, "How do I read a file in Python?"

[1412] 2. Submit your request:

[1413] The device converts this question into JSON format and sends it to the server.

[1414] 3. Server-side processing:

[1415] The server receives this request and asks the generative AI, "How to read a file in Python?" The generative AI generates an appropriate answer and sends it back to the server.

[1416] 4. Receiving and Displaying Responses:

[1417] The terminal receives the response from the server and displays an answer to the user such as "In Python, you can read files using the open function. Sample code is shown below."

[1418] 5. Use of answers:

[1419] The user begins writing Python code based on the displayed answers. For example, they try to implement the file read function by using open("example.txt", "r").

[1420] This allows users to get quick and accurate answers to their technical questions, allowing them to proceed with development work efficiently. By linking the server and terminals, the system provides comprehensive technical support to developers and engineers. This configuration ensures smooth development and improved productivity.

[1421] The processing flow will be explained below.

[1422] Step 1:

[1423] The user types a question into the device interface, for example, "How do I implement asynchronous processing in JavaScript?"

[1424] Step 2:

[1425] The device converts the user's input into JSON format and sends it to the server. Specifically, the following JSON data { "question": "Please tell me how to implement asynchronous processing in JavaScript"} is sent as an HTTP POST request.

[1426] Step 3:

[1427] The server receives a request from the terminal and adds this data to the request processing queue.

[1428] Step 4:

[1429] The server analyzes the request and prepares an API request to query the generative AI model, for example, by setting up a POST request to an API endpoint and sending JSON data.

[1430] Step 5:

[1431] The generative AI receives questions sent from the server and analyzes them. For example, it understands "how to implement asynchronous processing in JavaScript" and generates an appropriate answer.

[1432] Step 6:

[1433] The generative AI generates an answer to the question and sends it back to the server. For example, it generates an answer such as, "In JavaScript, asynchronous processing can be implemented using the async / await keywords. Sample code is shown below."

[1434] Step 7:

[1435] The server receives the answer from the generative AI, converts it to JSON format { "answer": "In JavaScript, asynchronous processing can be implemented using the async / await keywords. Sample code is shown below."} and sends it to the device as an HTTP response.

[1436] Step 8:

[1437] The device analyzes the response received from the server and displays it to the user. Specifically, it displays the message "In JavaScript, asynchronous processing can be implemented using the async / await keywords. Sample code is shown below" in a chat bubble on the interface.

[1438] Step 9:

[1439] Users can check the displayed answers and apply them to their own development. For example, they can add sample code such as function fetchData() { const response = await fetch(url); const data = await response.json();} to their own projects to implement asynchronous processing.

[1440] Example 1

[1441] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1442] Modern engineers and developers face the complexity of programming languages, software frameworks, and libraries. Furthermore, the complexity of analyzing error messages and project management makes it difficult to work efficiently. Furthermore, the sheer volume of technical information and reference materials makes it difficult to quickly find the information you need. To address these challenges, a system is needed that can efficiently and quickly provide answers to technical questions and support project management.

[1443] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1444] In this invention, the server includes: means for using generative artificial intelligence to provide answers to technical questions developers and engineers have about how to use programming languages, software frameworks, and software libraries, and how to analyze error messages; means for suggesting best practices and design styles to developers and engineers; means for searching and providing related information such as technical information, documentation, application programming interface references, and educational materials; means for providing advice on code refactoring and fault identification; means for supporting inquiries about project management information such as project progress, task assignment, deadline setting, and resource management, as well as data search and analysis; a server device that receives technical questions from a terminal device as JSON-formatted data and provides the received data to a generative artificial intelligence model to generate answers; a server device that returns the generated answers to the terminal device as JSON-formatted data; a terminal device that provides an interface for inputting technical questions, analyzes the JSON-formatted answer data received from the server device, and displays it to the user; and a generative artificial intelligence model that generates optimal answers based on the content of the questions. This enables engineers and developers to quickly and efficiently obtain the information they need, allowing them to solve technical problems and manage projects smoothly.

[1445] "Generative AI" is AI that generates natural language text based on data, and is used to answer questions and generate sentences.

[1446] An "engineer" is an individual with specialized knowledge of software development and system design.

[1447] A "programming language" is a language used to write instructions to a computer to perform specific processes.

[1448] A "software framework" is a collection of reusable components and libraries provided to streamline software development.

[1449] A "software library" is a collection of functions or classes available to program developers that provide a specific functionality.

[1450] An "error message" is a text message that reports a problem that occurs during the operation of software or a system.

[1451] A "best practice" is a method or technique that is optimized to achieve the best results in a particular technology or task.

[1452] A "design style" is a template or pattern that provides a repeatable solution for software or system design.

[1453] "Document" means a paper or file that describes technical information or procedures.

[1454] An "Application Programming Interface Reference" is a document that describes the interfaces that software and systems use to communicate with each other and how to use them.

[1455] "Educational materials" are teaching materials for learning specific skills or knowledge.

[1456] "Refactoring" is the process of improving the internal structure of software to increase its maintainability and extensibility.

[1457] A "failure" is a problem or malfunction in the operation of a system or software.

[1458] "Project management information" is data or information regarding project progress, task assignments, deadlines, and resource allocation.

[1459] A "terminal device" is a device that allows a user to input questions and receive and display answers.

[1460] A "server device" is a computer that receives requests from terminal devices, queries the generative artificial intelligence model, and generates and returns answers.

[1461] A "generative artificial intelligence model" is an artificial intelligence algorithm that generates answers to questions based on data.

[1462] A "natural language processing model" is an artificial intelligence technology for processing, understanding, and generating human language.

[1463] This invention is a system that uses generative artificial intelligence to solve technical problems faced by engineers and developers and support project management. This system is mainly composed of a server device and a terminal device, each of which fulfills a specific role to achieve seamless technical support.

[1464] Roles and operations of server devices

[1465] The server device plays a central role in processing technical questions received from the terminal device. The server first receives a request from the terminal using the HTTP protocol. The received request is data in JSON format and is analyzed. The server then sends a prompt to the generative AI model, which generates the optimal answer. An example of a generative AI model would be the OpenAI API. This answer is then converted back into JSON format and sent back to the terminal device as an HTTP response. A typical server computer is used for the specific hardware, and Python or Flask is used for the software.

[1466] Example prompt sentence:

[1467] How do I read a file in Python?

[1468] Roles and operations of terminal devices

[1469] The terminal device provides an interface with the user. The terminal device displays a chat interface that allows the user to input technical questions. When the user inputs a question and clicks the send button, the question is converted into JSON format and sent to the server device as an HTTP request. When the terminal device receives the answer returned from the server, it analyzes it and displays it in a format that is easy for the user to view. Specifically, JavaScript, HTML, and AJAX technology are used.

[1470] User operations

[1471] A user inputs a technical question through the chat interface of the terminal device. For example, they input a question such as "How do I read a file in Python?". When they click the send button, the question is sent to the server, and an answer is returned by the generative artificial intelligence. The received answer is displayed to the user in the form of, for example, "In Python, you can read a file using the open function. Sample code is shown below."

[1472] In this way, the server and terminal devices work together to quickly and efficiently provide answers to technical questions and solve the complex problems faced by engineers and developers. Furthermore, the use of generative AI models ensures that the most appropriate answers are provided for each question, allowing users to proceed with their work based on reliable information.

[1473] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1474] Step 1:

[1475] The user enters a question and submits it

[1476] Specific behavior:

[1477] The user opens the chat interface on their device, types a question, for example, "How do I read a file in Python?", and clicks the send button.

[1478] input:

[1479] The text "How do I read a file in Python?"

[1480] output:

[1481] Text data of the question entered into the terminal device

[1482] Step 2:

[1483] The terminal device forms a request and sends it to the server

[1484] Specific behavior:

[1485] The terminal device converts the input question into JSON format and sends it to the server as an HTTP request. The transmission is asynchronous using AJAX technology.

[1486] input:

[1487] The text "How do I read a file in Python?"

[1488] Data processing:

[1489] Convert the question text to JSON format

[1490] output:

[1491] {"Question": "How do I read a file in Python?"} JSON data

[1492] Step 3:

[1493] The server receives and parses the request

[1494] Specific behavior:

[1495] The server receives the request via HTTP protocol, parses the JSON data, and extracts the question. The Flask framework is used to receive and parse the request.

[1496] input:

[1497] {"Question": "How do I read a file in Python?"} JSON data

[1498] Data Calculation:

[1499] Parse the JSON data to extract the question text

[1500] output:

[1501] The text "How do I read a file in Python?"

[1502] Step 4:

[1503] The server queries the generative AI model

[1504] Specific behavior:

[1505] The server sends the question as a prompt to the generative AI model, which then generates an answer. The server sends the prompt using the OpenAI API or similar and obtains the answer.

[1506] input:

[1507] The text "How do I read a file in Python?"

[1508] Data Calculation:

[1509] A generative AI model generates an answer based on the prompt.

[1510] output:

[1511] The text reads "In Python, you can read a file using the open function. Here is some sample code."

[1512] Step 5:

[1513] The server converts the response into JSON format and sends it back.

[1514] Specific behavior:

[1515] The server processes the answer obtained from the generative AI model into JSON format and returns it to the terminal device as an HTTP response. The response is created using a framework such as Flask.

[1516] input:

[1517] The text reads "In Python, you can read a file using the open function. Here is some sample code."

[1518] Data processing:

[1519] Convert the answer text to JSON format

[1520] output:

[1521] {"Answer": "In Python, you can read a file using the open function. Here is a sample code:"}

[1522] Step 6:

[1523] The terminal device receives and displays the response.

[1524] Specific behavior:

[1525] The terminal device receives the JSON-formatted response data returned from the server, analyzes it, and displays it to the user as a chat bubble using JavaScript DOM manipulation.

[1526] input:

[1527] {"Answer": "In Python, you can read a file using the open function. Here is a sample code:"}

[1528] Data Calculation:

[1529] Parse the JSON data to extract the answer text

[1530] output:

[1531] The text "In Python, you can read files using the open function. Here's some sample code." displayed in the chat interface

[1532] (Application example 1)

[1533] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1534] With conventional technologies, developers and engineers lack the means to quickly and efficiently respond to technical questions about programming and project management. Furthermore, when a robot encounters a technical issue in a factory, there is no support system to immediately resolve the issue, which can lead to reduced productivity and business downtime.

[1535] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1536] In this invention, the server includes: means for using generative artificial intelligence to provide answers to technical questions from developers and engineers about how to use programming languages, frameworks, and libraries and how to interpret error messages; means for suggesting best practices and design patterns to developers and engineers; means for searching and providing related information such as technical information, documentation, API references, and tutorials; means for providing advice on code refactoring and bug identification; means for supporting querying project management information such as project progress, task assignment, deadline setting, and resource management, as well as data search and analysis; means for querying technical problems in real time when they occur in the factory and presenting appropriate solutions using generative artificial intelligence; means for transmitting information on specific technical problems faced by robots to the server and receiving answers from the generative artificial intelligence; and means for the robots to execute procedures to solve the problems based on the answers received. This enables technical problems to be resolved quickly, improving the efficiency and productivity of development and factory operations.

[1537] "Generative AI" is an AI system that has the ability to generate answers in natural language in response to questions or requests.

[1538] "Technical questions" are questions about how to use programming languages, frameworks, libraries, and how to interpret error messages that developers and engineers encounter during the development process.

[1539] A "best practice" is a standard methodology or technique that is considered to be the most effective and efficient way to carry out a particular task or process.

[1540] A "design pattern" is a design template that is used repeatedly to efficiently solve a particular problem.

[1541] "Technical information" refers to knowledge and data about a specific technology, including documentation, API references, tutorials, etc.

[1542] "Refactoring" is a technique for improving the internal structure of software without changing its functionality.

[1543] "Bug identification" is the process of finding errors or defects in software or hardware and identifying where to fix them.

[1544] "Project management information" refers to information for effectively progressing a project, such as project progress, task assignment, deadline setting, and resource management.

[1545] "Technical problems in factories" are problems related to factory equipment or systems not working properly or malfunctioning.

[1546] "Real-time problem inquiry" means that the moment a technical problem occurs, that information is immediately sent to generative artificial intelligence for a solution.

[1547] "Specific technical problems faced by robots" refers to specific obstacles or error messages that factory robots encounter while operating.

[1548] A "server" is an information processing device that accepts requests from clients, queries the generative artificial intelligence, and returns a response.

[1549] A "terminal" is an information processing device that allows a user to input a question and receives and displays a response from a server.

[1550] This invention provides a system that utilizes generative artificial intelligence to quickly solve technical problems in factory robots. This system is realized with the following configuration and processing procedure.

[1551] System Program

[1552] When a factory robot encounters a technical problem, it immediately sends the information to a server, receives a response from generative artificial intelligence, and solves the problem.

[1553] Server Roles and Operations

[1554] The server receives requests from the factory robots regarding technical issues and provides them to the generative artificial intelligence. Specifically, it performs the following processes:

[1555] 1. Request received:

[1556] The server receives requests from robots using the HTTP protocol, including JSON-formatted data that contains information such as the problem description and error code.

[1557] 2. Querying Generative AI:

[1558] The server analyzes the received request and makes the appropriate API call to the generative AI model, which then generates an answer to the query.

[1559] 3. Returning the response:

[1560] It receives the answer returned by the generative AI and sends it back to the robot. The answer data is converted to JSON format and sent as an HTTP response.

[1561] Robot Roles and Processing

[1562] The robot detects technical issues during factory operations and provides an interface for querying the issue to the generative artificial intelligence. Specifically, the robot performs the following processes:

[1563] 1. Detecting the problem and submitting a request:

[1564] If the robot detects a technical problem during operation, it converts the details of the problem (e.g., error code or abnormal behavior) into JSON format and sends it to the server as an HTTP request.

[1565] 2. Receiving and implementing responses:

[1566] It receives the JSON-formatted response data returned from the server, analyzes it, and executes steps to resolve the problem, such as checking the motor connection or replacing the motor.

[1567] Hardware and software used

[1568] The following hardware and software are used in this system:

[1569] Hardware: Factory robots (e.g., Raspberry Pi), server equipment

[1570] Software: Python, Requests library, Generative AI API (e.g. OpenAI API)

[1571] Specific examples

[1572] For example, if a factory robot detects a motor abnormality while operating on a production line, it will send the following prompt sentence to the generative artificial intelligence:

[1573] Example prompt sentence:

[1574] "Error code 4040: Motor malfunction"

[1575] "timestamp: 2023-10-01T12:00:00Z"

[1576] "motor_id: MTR-001"

[1577] "status_code: 4040"

[1578] A generative artificial intelligence might respond to this with something like this:

[1579] Example answer:

[1580] "Check motor connections and ensure that the motor driver circuit is functioning correctly. If the problem persists, replace the motor."

[1581] The robot receives this response and first checks the motor connections and replaces the motor if necessary.

[1582] In this way, when a factory robot encounters a technical problem, the problem can be resolved quickly, improving productivity.

[1583] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1584] Step 1:

[1585] Problem detection and data generation

[1586] The robot detects technical issues during operation, such as abnormal motor behavior or error codes, and obtains detailed information from sensors inside the robot and system logs.

[1587] Input: Error code and related problem details

[1588] Output: JSON formatted data containing details about the issue

[1589] Specific operation: The robot detects the error message "Error code 4040: Motor malfunction" and retrieves detailed information about the error (e.g., timestamp and motor ID) from its internal log.

[1590] Step 2:

[1591] Sending data

[1592] The robot converts the detailed information of the problem it has obtained into JSON format and sends it to the server as an HTTP request.

[1593] Input: JSON formatted problem details generated in Step 1

[1594] Output: HTTP request sent to the server

[1595] Specific operation: The robot sends JSON data such as "{"issue": "Error code 4040: Motor malfunction", "timestamp": "2023-10-01T12:00:00Z", "motor_id": "MTR-001", "status_code": 4040}" as an HTTP POST request to the server's API endpoint.

[1596] Step 3:

[1597] Receiving and parsing the request

[1598] The server receives the HTTP request from the robot, analyzes its contents, and extracts the information necessary to query the generative AI.

[1599] Input: HTTP request received from the robot (detailed problem data in JSON format)

[1600] Output: Data for API calls to generative AI

[1601] What happens: The server receives the HTTP request, parses the JSON data, extracts keys and values ​​such as "issue", "timestamp", and "motor_id", and reformats them.

[1602] Step 4:

[1603] Inquiry into generative AI

[1604] Based on the analyzed data, the server makes an API call to the generative artificial intelligence to generate an appropriate answer.

[1605] Input: Parsed problem details data

[1606] Output: Answer data from generative AI

[1607] Specific operation: The server sends the extracted data to the generative artificial intelligence API, which generates a prompt in the form of, for example, "Please tell me the steps to resolve the motor's abnormal operation," and sends it to the AI.

[1608] Step 5:

[1609] Response reception and data conversion

[1610] The server receives the answer from the generative AI, converts it into JSON format, and prepares it for sending back to the robot.

[1611] Input: Answer data from generative AI

[1612] Output: JSON formatted answer data to send back to the robot

[1613] Specific operation: The generative AI receives the answer "Check motor connections and ensure the motor driver circuit is functioning correctly. If the problem persists, replace the motor." and converts this into JSON format such as "{"solution": "Check motor connections and ensure the motor driver circuit is functioning correctly. If the problem persists, replace the motor."}".

[1614] Step 6:

[1615] Returning answers and running them in a robot

[1616] The server sends the prepared answer data back to the robot, which analyzes it and executes steps to solve the problem.

[1617] Input: JSON format response data from the server

[1618] Output: Robot executes problem-solving steps

[1619] Specific behavior: The robot receives the answer, "Check motor connections and ensure the motor driver circuit is functioning correctly. If the problem persists, replace the motor." It first checks the motor connections, and if the problem persists, replaces the motor.

[1620] Through the above processing steps, when a factory robot encounters a technical problem, it can utilize generative artificial intelligence to quickly solve the problem.

[1621] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1622] This invention relates to a system development support tool that combines generative artificial intelligence and an emotion engine. This system quickly and efficiently addresses the technical challenges faced by developers and engineers, and also provides more human-like and effective support by recognizing the user's emotional state and adjusting the support content accordingly.

[1623] Server configuration and processing overview

[1624] The server receives requests from the device and works in conjunction with the generative AI and emotion engine. Specifically, it performs the following processes:

[1625] 1. Request received:

[1626] The server receives technical questions and project management information requests from the device. The received data is in JSON format.

[1627] 2. Querying Generative AI:

[1628] The server analyzes the request and prepares an API request to query the generative AI model, which generates an answer based on the question.

[1629] 3. Emotion engine recognizes user emotions:

[1630] The server simultaneously uses an emotion engine to recognize the user's emotional state, for example, by inferring the user's emotions from the tone and patterns of the text.

[1631] 4. Adjust based on responses and emotions:

[1632] The answer returned by the generative AI is combined with the results of emotion analysis by the emotion engine to tailor the answer to the user's emotional state. If the emotion is negative, a detailed and thorough explanation is added.

[1633] 5. Return of Response:

[1634] The adjusted answer is converted to JSON format and sent to the device as an HTTP response.

[1635] Overview of terminal configuration and processing

[1636] The terminal provides an interface for users to input questions and receive answers from the server. Specifically, it performs the following processes.

[1637] 1. Provide an interface:

[1638] The terminal provides a chat interface where users can enter questions, which are then sent to the server when the user clicks a send button.

[1639] 2. Submit your request:

[1640] The terminal converts the user's input into JSON format and sends it to the server as an HTTP request.

[1641] 3. Show Answer:

[1642] Parse the JSON response returned by the server and display it to the user, including responses adjusted based on emotion recognition results.

[1643] User operations and examples

[1644] Through the interface, users can ask technical questions and receive answers tailored to their emotional state.

[1645] 1. Enter your question:

[1646] The user types into the interface, "What is the interpretation of error code 1020?"

[1647] 2. Submit your request:

[1648] The device converts this question into JSON format and sends it to the server.

[1649] 3. Server-side processing:

[1650] The server receives the request and asks the generative AI for an interpretation of error code 1020. At the same time, the emotion engine analyzes the user's emotions. As a result of emotion recognition, "anxiety" is detected.

[1651] 4. Generate and refine answers:

[1652] The generative AI generates a response saying, "Error code 1020 is an authentication problem. Please check your user ID and password." Meanwhile, the emotion engine tells the server that "the user is feeling anxious." The server adds to the response, "This problem is relatively easy to solve. Please follow the next steps."

[1653] 5. Receiving and Displaying Responses:

[1654] The device analyzes the response received from the server and displays the message, "Error code 1020 is an authentication problem. Please check your user ID and password. This problem is relatively easy to resolve. Please follow the steps below."

[1655] 6. Use of Answers:

[1656] The user checks the displayed answer and follows the specific steps to solve the problem.

[1657] In this way, by combining generative AI with an emotion engine, we are able to provide not only fast and appropriate answers to technical questions, but also more effective support by taking into consideration the user's emotional state.

[1658] The processing flow will be explained below.

[1659] Step 1:

[1660] A user types a question into a terminal interface, for example, "How do I handle exceptions in Python?"

[1661] Step 2:

[1662] The terminal converts the user's input into JSON format and sends it to the server as an HTTP POST request. Specifically, it sends the data { "question": "Please tell me how to handle exceptions in Python"}.

[1663] Step 3:

[1664] The server receives the request from the terminal and analyzes the request content appropriately to add this data to the request processing queue.

[1665] Step 4:

[1666] Based on the request analyzed by the server, an API request is prepared to query the generative AI model. For example, a POST request is set up to the AI's API endpoint and the query data is sent.

[1667] Step 5:

[1668] The generative AI receives and analyzes questions sent from the server. It understands "how to handle exceptions in Python" and generates an appropriate answer. Specifically, it generates an answer such as, "Exception handling in Python is done using the try and except statements. Sample code is shown below."

[1669] Step 6:

[1670] The generative AI returns the generated answer to the server. For example, it returns JSON data containing an answer such as, "Python handles exceptions using the try and except statements. Sample code is shown below."

[1671] Step 7:

[1672] The server receives the response from the generative AI and simultaneously analyzes the user's emotional state using the emotion engine. For example, suppose the tone and expression of the input text indicate "anxiety."

[1673] Step 8:

[1674] The emotion engine sends the emotion analysis results back to the server. Specifically, it sends the analysis result that "the user is feeling anxious."

[1675] Step 9:

[1676] The server integrates the generative AI's answers with the analysis results of the emotion engine and adjusts the answer as needed. For example, if "anxiety" is detected, a detailed and polite explanation such as "This problem is relatively easy to solve. Please follow the next steps" is added.

[1677] Step 10:

[1678] The server then converts the final adjusted answer into JSON format and sends it to the device as an HTTP response.

[1679] Step 11:

[1680] The device analyzes the response received from the server and displays it to the user. Specifically, the chat interface displays the message, "Python uses the try and except statements to handle exceptions. Below is a sample code. This problem is relatively easy to solve. Please follow the steps below."

[1681] Step 12:

[1682] The user reviews the displayed answer and follows specific steps to solve the problem, for example, adding try and except statements to the Python code to implement exception handling.

[1683] In this way, the combination of generative AI and emotion engines can provide relevant answers to technical questions and personalize responses based on the user's emotional state, improving the user experience and significantly improving the efficiency of development efforts.

[1684] Example 2

[1685] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1686] Conventional technical consultation systems simply provide answers to technical questions without taking into account the user's emotional state. As a result, if a user is feeling anxious or stressed, their emotions are not taken into account and appropriate support is not provided. Another problem is that the quality of answers to technical questions varies, making it difficult to obtain advice that is appropriate for the content of the question or the user's background.

[1687] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1688] In this invention, the server includes means for using generative artificial intelligence to provide answers to technical questions from developers and engineers about how to use programming languages, software frameworks, and libraries and how to interpret error messages, means for suggesting best practices and design methods to developers and engineers, means for searching and providing related information such as technical information, documentation, API references, and tutorials, and means for recognizing the emotional state of a user using an emotion engine and adjusting the content of the answer based on the user's emotional state. This makes it possible to provide quick and appropriate answers to technical questions and support that takes the user's emotional state into consideration.

[1689] "Generative AI" refers to AI that automatically generates answers and suggestions in response to questions and requests from users in natural language.

[1690] "Technical questions" are questions about technical content, such as how to use programming languages, software frameworks, libraries, or interpret error messages.

[1691] An "emotion engine" is a technology for analyzing and recognizing a user's emotional state from text input and other interaction data.

[1692] "Best practices" is a concept that refers to the most efficient and effective methods and techniques in a particular technical field.

[1693] A "design method" refers to the techniques and methodologies used when designing systems and applications in software development.

[1694] "Technical information" refers to all information that developers and engineers need to perform technical work.

[1695] "Documentation" refers to documents that describe the specifications, design, and usage of software or systems.

[1696] An "API Reference" is a document that provides detailed instructions on how to use the application programming interface (API) provided by a particular program.

[1697] A "tutorial" is educational content that provides step-by-step instructions on how to use and apply a particular technology or tool.

[1698] A "terminal" is an electronic device or interface through which a user enters technical questions and receives responses from a server.

[1699] A "server" is a computer system that receives requests from users, processes them accordingly, and returns generated answers or advice to the users.

[1700] A "natural language processing model" is an algorithm for analyzing and understanding natural language text and converting it into human-readable information.

[1701] This invention is a system that combines generative artificial intelligence and an emotion engine. This system quickly and efficiently addresses the technical challenges faced by developers and engineers, and also provides more human-like and effective assistance by recognizing the user's emotional state and adjusting the assistance content accordingly.

[1702] Server configuration and processing overview

[1703] The server receives requests from the device and works in conjunction with the generative AI and emotion engine. Specifically, it performs the following processes:

[1704] Software and hardware used: The server uses "OpenAI GPT-3" as the generative AI and "Microsoft Azure's Text Analytics API" as the emotion engine. The server itself uses a server machine with a high-performance CPU and sufficient memory.

[1705] 1. Request received:

[1706] The server receives technical questions and project management information requests in JSON format from the device. For example, if a user types a question like "What is the interpretation of error code 1020?", this request is sent to the server.

[1707] 2. Querying Generative AI:

[1708] The server analyzes the received request and prepares an API request to query the generative AI model. For example, it sends a prompt message to OpenAI GPT-3: "Please tell me the interpretation of error code 1020."

[1709] 3. Emotion engine recognizes user emotions:

[1710] The server also uses Microsoft Azure's Text Analytics API to analyze the user's emotional state from the received text. For example, emotions such as "anxiety" may be recognized from the tone and patterns of the text.

[1711] 4. Adjust based on responses and emotions:

[1712] The server combines the answer returned by the generative AI with the emotion analysis results of the emotion engine to tailor the answer to the user's emotional state. For example, in response to the generative AI's answer "Error code 1020 is an authentication problem. Please check your user ID and password," the server adds additional information for anxious users, such as "This problem can be solved relatively easily. Please follow the next steps."

[1713] 5. Return of Response:

[1714] The adjusted answer is converted to JSON format and sent to the terminal as an HTTP response.

[1715] Overview of terminal configuration and processing

[1716] The terminal provides an interface through which the user can enter questions and receive answers from the server.

[1717] Hardware and software used: The device runs on a regular PC or smartphone and uses a web browser to provide the chat interface.

[1718] 1. Provide an interface:

[1719] The terminal provides a chat interface where users can enter questions. Once the user enters a question and clicks the send button, a request is sent to the server.

[1720] 2. Submit your request:

[1721] The terminal converts the user's input into JSON format and sends it to the server as an HTTP request.

[1722] 3. Show Answer:

[1723] The JSON response returned by the server is parsed and displayed to the user, with the content adjusted based on the emotion recognition results.

[1724] User operations and examples

[1725] Through the interface, users can ask technical questions and receive answers tailored to their emotional state.

[1726] 1. Enter your question:

[1727] The user types into the interface, "What is the interpretation of error code 1020?"

[1728] 2. Submit your request:

[1729] The device converts this question into JSON format and sends it to the server.

[1730] 3. Server-side processing:

[1731] The server receives the request and asks the generative AI for an interpretation of error code 1020. At the same time, the emotion engine analyzes the user's emotions. As a result of emotion recognition, "anxiety" is detected.

[1732] 4. Generate and refine answers:

[1733] The generative AI generates a response saying, "Error code 1020 is an authentication problem. Please check your user ID and password." Meanwhile, the emotion engine tells the server that "the user is feeling anxious." The server adds to the response, "This problem is relatively easy to solve. Please follow the next steps."

[1734] 5. Receiving and Displaying Responses:

[1735] The device analyzes the response received from the server and displays the message, "Error code 1020 is an authentication problem. Please check your user ID and password. This problem is relatively easy to resolve. Please follow the steps below."

[1736] 6. Use of Answers:

[1737] The user checks the displayed answer and follows the specific steps to solve the problem.

[1738] In this way, by combining generative AI with an emotion engine, it is possible to not only provide quick and appropriate answers to technical questions, but also to provide more effective support by taking into consideration the user's emotional state.

[1739] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1740] Step 1:

[1741] Entering and submitting a request

[1742] The user enters a technical question into the chat interface on the device, such as "What is the interpretation of error code 1020?", and clicks the send button. This input is converted by the device into JSON format (e.g., {"question":"What is the interpretation of error code 1020"}) and sent to the server as an HTTP request.

[1743] Step 2:

[1744] Receiving and parsing the request

[1745] The server receives an HTTP request from the device, analyzes the request, and obtains JSON data ({"question":"What is the interpretation of error code 1020?"}). Based on this data, it creates a prompt for the generative AI model.

[1746] Step 3:

[1747] Querying generative AI models

[1748] The server sends a prompt to a generative artificial intelligence model (e.g., OpenAI GPT-3) saying, "What is the interpretation of error code 1020?" The AI ​​model generates an answer based on this prompt and sends it back to the server. An example of the generated data is, "Error code 1020 is an authentication problem. Please check your user ID and password."

[1749] Step 4:

[1750] Emotion engine recognizes emotional states

[1751] The server sends the user's input text to an emotion engine (e.g., Microsoft Azure's Text Analytics API). The emotion engine performs emotion analysis on the input text and returns the results to the server. For example, an emotion such as "anxiety" is returned.

[1752] Step 5:

[1753] Emotion-based tailoring of responses

[1754] The server combines the answer obtained from the generative AI with the emotional state obtained from the emotion engine. For example, if the generated answer is "Error code 1020 is an authentication problem. Please check your user ID and password" and the emotional state is "anxious," the server adds additional information such as "This problem is relatively easy to solve. Please follow the next steps."

[1755] Step 6:

[1756] Submit your answer

[1757] The server converts the adjusted answer into JSON format (e.g., {"answer":"Error code 1020 is an authentication problem. Please check your user ID and password. This problem is relatively easy to resolve. Please follow the next steps"}) and sends it to the terminal as an HTTP response.

[1758] Step 7:

[1759] Receiving and viewing responses

[1760] The device receives the HTTP response from the server, parses the JSON data, and displays it to the user. For example, it might display a message like, "Error code 1020 is an authentication problem. Please check your user ID and password. This problem is relatively easy to resolve. Please follow the steps below."

[1761] In this way, by analyzing, generating, and adjusting based on input data at each step, we can provide appropriate answers to users' technical questions that take into account their emotional state.

[1762] (Application example 2)

[1763] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1764] Current systems that provide technical questions and solutions provide uniform answers without considering the user's emotional state, which can result in a poor user experience. Furthermore, on e-commerce sites, when users ask questions about products, it can take a long time for them to receive an appropriate answer, which can lead to lower satisfaction. This can lead to a decrease in purchasing motivation and a risk of customer attrition.

[1765] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for using generative artificial intelligence to provide answers to technical questions asked by developers and engineers about how to use programming languages, frameworks, and libraries and how to interpret error messages; means for suggesting best practices and design patterns to developers and engineers; means for searching and providing related information such as technical information, documentation, API references, and tutorials; means for providing advice on code refactoring and bug identification; means for supporting inquiries about project management information such as project progress, task assignment, deadline setting, and resource management, as well as data search and analysis; means for analyzing a user's emotional state and adjusting the content of the answer based on the user's emotions; means for providing emotion-based answers to product-related questions on an e-commerce site; and means for analyzing a user's questions and emotional state and adjusting and providing answers generated by generative artificial intelligence. This makes it possible to quickly provide answers that take emotions into consideration in response to users' technical questions and product-related concerns and doubts.

[1766] "Generative AI" is an AI model that generates new information and answers based on data such as text and images.

[1767] An "emotion engine" is an algorithm or software that analyzes and recognizes a user's emotional state from text or voice data.

[1768] "Technical questions" are questions about programming languages, frameworks, libraries, interpreting error messages, best practices, design patterns, technical information, documentation, API references, tutorials, refactoring code, identifying bugs, and related technical topics.

[1769] "Developers and engineers" are professionals who design, develop, operate, and maintain software and systems.

[1770] An "e-commerce site" is a website or application that facilitates the buying and selling of goods and services over the Internet.

[1771] The "user's emotional state" is an emotional state analyzed from the text or voice input by the user, such as anxiety, anger, relief, etc.

[1772] "Chat style" refers to an interface format in which a user inputs text and interacts with the system in response.

[1773] A "natural language processing model" is an artificial intelligence model that can understand and generate human language, and is used to generate optimal answers based on questions.

[1774] "API" stands for Application Program Interface, a set of protocols and tools that allow different software programs to communicate with each other.

[1775] A "design pattern" is a reusable solution to a common design problem in software development.

[1776] "Best practices" are the most effective and efficient methodologies and techniques established in a particular industry or field.

[1777] "Project management information" refers to information related to project progress, task assignment, deadline setting, resource management, and the like.

[1778] This invention uses a system that combines generative artificial intelligence and an emotion engine to provide emotion-based answers to technical questions and questions about products on e-commerce sites. Specific embodiments for realizing this system are described below.

[1779] System configuration

[1780] The server includes the following main functions:

[1781] 1. The ability to generate answers to technical and product questions using generative artificial intelligence models.

[1782] 2. The ability to use an emotion engine to analyze the user's emotional state and tailor responses appropriately.

[1783] 3. The function of receiving and analyzing requests from users.

[1784] 4. A function that combines emotional data obtained from the emotion engine with answers generated by generative artificial intelligence to provide the user with the most appropriate answer.

[1785] The terminal provides an interface through which the user can enter questions and receive answers from the server.

[1786] 1. Provide a chat-style interface where users can type in their questions.

[1787] 2. Send the user's input to the server.

[1788] 3. Display the answer received from the server.

[1789] Processing Details

[1790] The server receives requests from the device and analyzes their content. The analyzed information is passed to a generative AI model, which generates answers to technical and product-related questions. At the same time, an emotion engine analyzes the user's emotional state and generates emotion-based data. Finally, the generated answers are combined with the emotion data and provided in an optimized form to the user.

[1791] For example, suppose a user types "Can I return this product?" into a chat-style interface. The server passes this question to a generative AI model, which generates a standard answer: "You can return this product within 30 days of purchase." At the same time, the emotion engine analyzes the user's emotional state and determines it to be "anxious." As a result, the server adds the following statement to the answer: "Don't worry. You can return this product within 30 days of purchase. Detailed instructions are below.", providing the user with an optimized answer.

[1792] Hardware and Software

[1793] The specific hardware and software configuration required to realize this system is as follows:

[1794] Server equipment: A server equipped with a powerful processor and a large amount of memory (e.g., AWS EC2, Google Cloud Compute Engine).

[1795] Terminal device: A smartphone or computer operated by a user.

[1796] Generative AI models: Natural language processing models (e.g., GPT-3, BERT).

[1797] Sentiment engine: Sentiment analysis algorithms (e.g., IBM Watson Tone Analyzer, Microsoft Azure Text Analytics).

[1798] Examples of prompt statements

[1799] An example prompt for a generative AI model is:

[1800] User-submitted question: How do I get a refund if this product is broken?

[1801] Mode: Generate

[1802] Sentiment analysis results: Anxiety

[1803] Answer adjustment:

[1804] The problem is easy to solve, just follow these steps to get your refund:

[1805] Based on this prompt, the generative artificial intelligence model generates an appropriate answer and provides it to the user.

[1806] As described above, the embodiment of the present invention combines a generative artificial intelligence model and an emotion engine to realize a system that provides users with quick, emotion-sensitive answers.

[1807] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1808] Step 1:

[1809] The terminal accepts user input. The user types a question into a chat-style interface and clicks the send button. The input is in text format, and an example would be "Can I return this item?". The terminal converts this input into JSON format and sends it to the server. The input is the user question in text format, and the output is the request data in JSON format.

[1810] Step 2:

[1811] The server receives a request from the device. It analyzes the request content and prepares an API request to query the generative AI model. It analyzes the JSON formatted request data and creates a prompt to send to the generative AI model. The input is the JSON formatted request data, and the output is the prompt text to be passed to the generative AI model.

[1812] Step 3:

[1813] The server obtains the answer from the generative AI model. It sends a prompt to the generative AI model and receives the answer. The generative AI model generates an answer based on the question. The input is the prompt, and the output is the generated answer (in text format). In this example, the specific operation is to receive the answer, "This product can be returned within 30 days of purchase."

[1814] Step 4:

[1815] The server uses an emotion engine to analyze the user's emotional state. The user's input text is passed to the emotion engine for emotion analysis. The analysis result is output as an emotional state (e.g., anxiety, relief, etc.). The input is the user's question text, and the output is the emotion analysis result.

[1816] Step 5:

[1817] The server combines the answer returned by the generative AI model with the results of sentiment analysis by the emotion engine to adjust the content of the answer according to the user's emotional state. If the sentiment is negative, a detailed and thorough explanation is added. The input is the generated answer and the sentiment analysis results, and the output is the adjusted answer. In this example, based on the sentiment analysis result of "anxiety," the server adds the words "Don't worry. This product can be returned within 30 days of purchase."

[1818] Step 6:

[1819] The server converts the adjusted answer into JSON format and sends it to the terminal as an HTTP response. The input is the adjusted answer, and the output is the JSON-formatted response data. Specifically, the server encodes the adjusted answer and sends it to the terminal.

[1820] Step 7:

[1821] The device parses the JSON formatted response received from the server and displays it to the user. The input is the JSON formatted response data received from the server, and the output is the text response to be displayed. In this example, the response displayed to the user is "Don't worry. This product can be returned within 30 days of purchase."

[1822] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1823] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1824] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1825] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1826] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1827] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1828] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1829] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1830] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1831] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1832] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1833] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1834] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1835] 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.

[1836] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1837] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1838] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1839] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1840] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1841] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1842] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1843] The following is further disclosed regarding the above embodiment.

[1844] (Claim 1)

[1845] A way for developers and engineers to use generative artificial intelligence to provide answers to technical questions about how to use programming languages, frameworks, libraries, and interpret error messages; and

[1846] A means to suggest best practices and design patterns to developers and engineers,

[1847] A means to find and provide related information such as technical information, documentation, API references, tutorials, etc.;

[1848] A means of providing advice on refactoring code and identifying bugs, and

[1849] A system that includes the means to query project management information, such as project status, task assignment, deadline setting, and resource management, as well as the means to search and analyze data.

[1850] (Claim 2)

[1851] a server device that obtains answers to technical questions from the generative artificial intelligence model and returns the answers to developers and engineers;

[1852] 2. The system according to claim 1, further comprising a terminal device that inputs a technical question from a user, transmits the question to the server device, and displays the answer received from the server device.

[1853] (Claim 3)

[1854] The system according to claim 1, characterized in that, in generating and providing an answer, it includes a natural language processing model that generates an optimal answer based on the content of the question.

[1855] "Example 1"

[1856] (Claim 1)

[1857] A means to use generative artificial intelligence to provide developers and engineers with answers to technical questions about how to use programming languages, software frameworks, software libraries, and to analyze error messages; and

[1858] A means to suggest best practices and design styles to developers and engineers,

[1859] A means for retrieving and providing related information, such as technical information, documentation, application programming interface references, and educational materials; and

[1860] A means of providing advice on refactoring code and identifying bottlenecks,

[1861] A means to support querying project management information such as project progress, task assignment, deadline setting, and resource management, as well as data search and analysis.

[1862] a server device that receives technical questions from a terminal device as JSON format data and provides the data to a generative artificial intelligence model to generate answers;

[1863] a server device that returns the generated response to the terminal device as JSON format data;

[1864] a terminal device that provides an interface for inputting technical questions, analyzes JSON formatted answer data received from the server device, and displays the data to the user;

[1865] A generative artificial intelligence model that generates optimal answers based on the content of questions;

[1866] A system including:

[1867] (Claim 2)

[1868] a server device that obtains answers to technical questions from the generative artificial intelligence model and returns the answers to developers and engineers;

[1869] 2. The system according to claim 1, further comprising a terminal device that inputs a technical question from a user, transmits the question to the server device, and displays the answer received from the server device.

[1870] (Claim 3)

[1871] The system according to claim 1, characterized in that, in generating and providing an answer, it includes a natural language processing model that generates an optimal answer based on the content of the question.

[1872] "Application Example 1"

[1873] (Claim 1)

[1874] A way for developers and engineers to use generative artificial intelligence to provide answers to technical questions about how to use programming languages, frameworks, libraries, and interpret error messages; and

[1875] A means to suggest best practices and design patterns to developers and engineers,

[1876] A means to find and provide related information such as technical information, documentation, API references, tutorials, etc.;

[1877] A means of providing advice on refactoring code and identifying bugs, and

[1878] A means to support querying project management information such as project status, task assignment, deadline setting, and resource management, as well as data search and analysis;

[1879] When technical problems occur in factories, there is a way to query the problem in real time and provide appropriate solutions using generative artificial intelligence.

[1880] a means for transmitting information about specific technical problems faced by the robot to a server and receiving answers from the generative artificial intelligence;

[1881] The system includes a means for the robot to execute steps to solve the problem based on the answers received.

[1882] (Claim 2)

[1883] a server device that obtains answers to technical questions from the generative artificial intelligence model and returns the answers to developers and engineers;

[1884] 2. The system according to claim 1, further comprising a terminal device that inputs a technical question from a user, transmits the question to the server device, and displays the answer received from the server device.

[1885] (Claim 3)

[1886] The system according to claim 1, characterized in that, in generating and providing an answer, it includes a natural language processing model that generates an optimal answer based on the content of the question.

[1887] "Example 2: Combining Emotion Engines"

[1888] (Claim 1)

[1889] A means to use generative artificial intelligence to provide answers to technical questions developers and engineers have about how to use programming languages, software frameworks, libraries, and interpret error messages; and

[1890] A means to suggest best practices and design methods to developers and engineers,

[1891] A means to find and provide related information such as technical information, documentation, API references, tutorials, etc.;

[1892] A means of providing advice on optimizing source code and identifying defects;

[1893] A means to support querying and data retrieval and analysis of plan management information such as plan progress, task assignment, deadline setting, and resource management;

[1894] means for recognizing a user's emotional state using an emotion engine and adjusting the content of the response based on the user's emotional state;

[1895] A means for combining answers from the generative artificial intelligence with emotion analysis results to provide answers that take into account the user's emotional state; and

[1896] A system including:

[1897] (Claim 2)

[1898] a server device that obtains answers to technical questions from the generative artificial intelligence model and returns the answers to developers and engineers;

[1899] 2. The system according to claim 1, further comprising a terminal device that inputs a technical question from a user, transmits the question to the server device, and displays the answer received from the server device.

[1900] (Claim 3)

[1901] The system according to claim 1, characterized in that, in generating and providing an answer, it includes a natural language processing model that generates an optimal answer based on the content of the question.

[1902] "Application example 2 when combining emotion engines"

[1903] (Claim 1)

[1904] A way for developers and engineers to use generative artificial intelligence to provide answers to technical questions about how to use programming languages, frameworks, libraries, and interpret error messages; and

[1905] A means to suggest best practices and design patterns to developers and engineers,

[1906] A means to find and provide related information such as technical information, documentation, API references, tutorials, etc.;

[1907] A means of providing advice on refactoring code and identifying bugs, and

[1908] A means to support querying project management information such as project status, task assignment, deadline setting, and resource management, as well as data search and analysis;

[1909] means for analyzing the emotional state of the user and adjusting the content of the response in accordance with the emotional state;

[1910] A means for providing emotion-based answers to product questions on an e-commerce site;

[1911] A means for analyzing questions and emotional states from users and adjusting and providing answers using generative artificial intelligence;

[1912] A system including:

[1913] (Claim 2)

[1914] a server device that obtains answers to technical questions from the generative artificial intelligence model and returns the answers to developers and engineers;

[1915] a terminal device that inputs technical questions from users, transmits the questions to the server device, and displays the answers received from the server device;

[1916] 2. The system according to claim 1, further comprising a server device that adjusts responses according to emotional states.

[1917] (Claim 3)

[1918] A natural language processing model that generates an optimal answer based on the question content in generating and providing an answer;

[1919] 2. The system of claim 1, further comprising means for analyzing the user's emotional state and adjusting responses based on the results of the analysis. [Explanation of symbols]

[1920] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A way for developers and engineers to use generative artificial intelligence to provide answers to technical questions about how to use programming languages, frameworks, libraries, and interpret error messages; and A means to suggest best practices and design patterns to developers and engineers, A means to find and provide related information such as technical information, documentation, API references, tutorials, etc.; A means of providing advice on refactoring code and identifying bugs, and A system that includes the means to support querying project management information, such as project status, task assignment, deadline setting, and resource management, as well as data retrieval and analysis.

2. a server device that obtains answers to technical questions from the generative artificial intelligence model and returns the answers to developers and engineers; 2. The system according to claim 1, further comprising a terminal device for inputting technical questions from a user, transmitting the questions to the server device, and displaying answers received from the server device.

3. 2. The system according to claim 1, further comprising a natural language processing model for generating an optimal answer based on the content of a question in generating and providing an answer.

Images