System

Abstract

A system is provided.SOLUTION: A system for using a generative AI model to receive prompts from a user regarding objectives and issues and to provide appropriate supporting information based on the prompts, the system comprising: means for inputting information from the user regarding a project via a user interface; means for parsing the inputted information and formatting the supporting information into prompts for passing to the generative AI model; means for passing the formatted prompts to the generative AI model to obtain the supporting information; and means for displaying the obtained supporting information to the user via the user interface.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 programming development, beginner and intermediate developers often need to spend time finding specific solutions to project objectives and challenges. This leads to inefficiencies in the development process and reduces creativity and productivity. Furthermore, existing integrated development environments (IDEs) have limited support functions for developers, making it difficult to provide specific guidance, especially for complex problems. In addition, the lack of tools that provide specific support, such as selecting appropriate algorithms or providing code snippets, makes it difficult for developers to make the most of their skills. [Means for solving the problem]

[0005] The present invention provides a system using a generative AI model that provides appropriate support information for project-related objectives and challenges input by a user. Specifically, the system includes a means for allowing a user to input project-related information via a user interface, a means for analyzing the input information and formatting it into a prompt for passing the support information to a generative AI model, a means for passing the formatted prompt to the generative AI model and acquiring the support information, and a means for displaying the acquired support information to the user via the user interface. This allows users to quickly obtain specific solutions and code snippets tailored to their objectives and challenges, thereby improving the efficiency and creativity of the development process. Furthermore, by using natural language analysis to analyze the prompt, the system can accurately understand the user's input intent and provide more appropriate support information. Furthermore, by using a predictive model based on machine learning as the generative AI model, the system can always provide advice based on the latest technical information and best practices.

[0006] A "user interface" refers to a screen or input device that allows a user to interact with a computer system, and is a means for providing input information and displaying results.

[0007] "Information about the project" refers to specific details such as the purpose, challenges, and expected output of the software project being developed by the user.

[0008] A "prompt" refers to text data formatted to be passed to a generative AI model based on a question or request entered by a user.

[0009] A "generative AI model" is a machine learning model trained on a large dataset to generate appropriate assistance information and advice in response to input prompts.

[0010] "Natural language analysis" is a process that uses natural language processing technology to analyze text data and understand the user's intent and context.

[0011] "Support information" refers to specific information that is useful to users, such as code snippets, design patterns, and algorithm explanations generated by generative AI models.

[0012] A "machine learning-based predictive model" refers to an algorithm or model used to learn patterns from a given dataset and perform tasks such as prediction or classification on future data. [Brief explanation of the drawings]

[0013] [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

[0014] 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.

[0015] First, the terms used in the following description will be explained.

[0016] 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).

[0017] 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.

[0018] 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.

[0019] 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.

[0020] 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."

[0021] [First embodiment]

[0022] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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."

[0034] This invention is a system that uses a generative AI model to receive prompts about project objectives and issues input by the user and provide appropriate support information based on those inputs. Below, we will explain the program processing of this system in natural language and provide specific examples.

[0035] Explanation of system processing

[0036] User interface input

[0037] Terminal: When the application is launched, an input form is displayed, in which the user can enter information about the project. This input form has fields such as the project name, purpose, tasks, and expected output, and the user enters specific details into these fields. Once the information is complete, the user presses the "Submit" button to send the information.

[0038] Receiving and parsing prompts

[0039] Terminal: Receives the information entered by the user into the input form and sends it to the server as a prompt.

[0040] Server: Parses the incoming prompt and uses natural language analysis to interpret the input. Specifically, it understands the project objectives, the challenges faced, and the expected output, and then formats appropriate prompts based on that. These prompts include questions or instructions based on the user's input.

[0041] Invoking a generative AI model

[0042] Server: Passes the formatted prompt to the generative AI model, which generates assistance information in response to the prompt. This generative AI model is a predictive model based on machine learning that has been pre-trained on a large dataset, and provides highly accurate answers to natural language input.

[0043] Display of support information

[0044] Terminal: Receives assistance information obtained from the generative AI model and displays it on the user interface. The assistance information includes specific code examples, explanations of algorithms, and suggested design patterns, allowing users to use this information as a reference for their own development. Users can also ask new questions or make corrections based on the displayed assistance information.

[0045] Specific examples

[0046] Example user input

[0047] Let's say a user enters "Generating summaries for news articles" as the project name, "Generating short summaries automatically from news articles" as the objective, and "I don't know how to select and implement a summary generation algorithm in natural language processing" as the challenge they are facing. Furthermore, they enter "Sample code for generating summaries written in Python" as the desired output.

[0048] This input is formatted as a prompt and passed to the generative AI model, which then generates support information, including sample code written in Python, for generating a summary. This support information is then displayed on the device, allowing the user to proceed with their project.

[0049] The above is a specific embodiment of the present invention. By using this system, users can quickly obtain support information that is tailored to their own goals and challenges, thereby improving the efficiency and creativity of the development process.

[0050] The processing flow will be explained below.

[0051] Step 1:

[0052] User: Starts the application and enters the project name, purpose, tasks, and expected output in the input form. Once the input is complete, presses the "Submit" button.

[0053] Step 2:

[0054] Terminal: Receives the information entered by the user in the input form and formats it as a prompt. This prompt is text data including the project name, objectives, tasks, and expected output.

[0055] Step 3:

[0056] Terminal: Sends formatted prompts to the server, which then uses them as input to the generative AI model.

[0057] Step 4:

[0058] Server: Performs natural language analysis to interpret the received prompts, thereby understanding the user's intent and extracting appropriate questions and instructions based on their goals, challenges, and desired output.

[0059] Step 5:

[0060] Server: Based on the results of natural language analysis, it generates formatted prompts to be passed to the generative AI model, including specific requests for the problem to be solved and the assistance information to be provided.

[0061] Step 6:

[0062] Server: Passes the formatted prompts to a generative AI model that generates assistance information. This generative AI model is a predictive model based on machine learning and pre-trained on a large dataset.

[0063] Step 7:

[0064] Server: Receives assistance information obtained from the generative AI model, including specific code examples, algorithm explanations, and design pattern suggestions.

[0065] Step 8:

[0066] Server: Sends the assistance information to the terminal, where it is formatted into a form useful to the user.

[0067] Step 9:

[0068] Terminal: The received support information is displayed on the user interface. The user can check the displayed information and ask new questions or make corrections as necessary.

[0069] Step 10:

[0070] User: Use the displayed support information to proceed with the development of the project. Implement specific code examples and algorithm explanations to achieve the desired functionality.

[0071] Example 1

[0072] 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."

[0073] Conventional project management and support systems have struggled to quickly and accurately provide support information tailored to the specific challenges users face. Users must independently search through a vast amount of information to find the solutions they need, which is time-consuming and labor-intensive. Furthermore, there has been a lack of methods for accurately analyzing user input and providing appropriate support information based on that information. These issues often stall project progress, creating a demand for more efficient and creative development processes.

[0074] 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.

[0075] In this invention, the server includes means for inputting project-related information from a user via a user interface, means for analyzing the input information and formatting it into a prompt for passing support information to a generative AI model, and means for passing the formatted prompt to the generative AI model to obtain support information. This allows the user to quickly and accurately obtain specific support information for their own project, enabling the project to proceed smoothly.

[0076] A "user interface" is an interface through which a user interacts with a system, and is a means for input and output.

[0077] A "prompt" refers to information about a goal or task entered by a user, and is a formatted question or instruction to be passed to a generative AI model.

[0078] A "generative AI model" is a predictive model based on machine learning trained on large datasets, and is an algorithm that generates assistance information or answers in response to natural language input.

[0079] "Support information" refers to information for assistance provided by the generative AI model, including specific code examples, explanations of algorithms, and suggested design patterns.

[0080] "Analysis" is the process of interpreting and understanding the project information entered by the user using natural language processing techniques.

[0081] "Shaping" is the process of reconstructing the analyzed information into an appropriate prompt to be passed to the generative AI model.

[0082] "Acquisition" refers to the process of receiving assistance information from the generative AI model, and refers to the server receiving the generated information.

[0083] "Display" refers to the process of presenting the acquired assistance information on the user interface so that the user can visually confirm it.

[0084] The present invention is a system that uses a generative AI model to receive prompts regarding project objectives and challenges input by a user and provide appropriate support information based on the prompts. A specific embodiment of the present invention will be described below.

[0085] User interface input

[0086] Terminal: When the application is launched, an input form is displayed, allowing the user to enter information about the project. This input form includes fields such as the project name, purpose, tasks, and expected output. The user enters specific information into these fields. The input form is implemented using HTML and JavaScript. Once the input is complete, the user clicks the "Submit" button to send the information.

[0087] Receiving and parsing prompts

[0088] Terminal: The information entered by the user is converted into a data structure such as JSON and sent to the server as an HTTP request. Specifically, the data is sent using the JavaScript fetch function.

[0089] Server: Extracts project information from the received HTTP request and analyzes the data using a JSON parser or similar. The analysis results are used to interpret the user's intent and expected results using natural language processing (NLP) technology. Specifically, the input content is analyzed using Python's spaCy library or similar.

[0090] Prompt Formatting

[0091] Server: Based on the analysis results, the server formats a prompt to be passed to the generative AI model. Specifically, it creates questions and instructions based on the user's input. For example, based on the request to "automatically generate short summaries from news articles," the server formats a prompt such as "Please tell me the algorithm for generating summaries of news articles."

[0092] Invoking a generative AI model

[0093] Server: Passes the formatted prompts to the generative AI model, which is a machine learning-based predictive model pre-trained on a large dataset, and receives the responses. Specifically, it sends prompts to the model via API calls and receives responses.

[0094] Display of support information

[0095] Terminal: Analyzes the assistance information obtained from the generative AI model and formats it for display on the user interface. Specifically, the assistance information (e.g., code examples and algorithm explanations) is displayed using HTML and CSS. Users can use this information to proceed with their projects.

[0096] Specific examples

[0097] If a user enters "Generate summaries for news articles" as the project name, "Generate short summaries automatically from news articles" as the goal, "I don't know how to select and implement a summary generation algorithm in natural language processing" as the challenge they are facing, and further enters "Sample code for summary generation written in Python" as the desired output, the following prompt will be generated:

[0098] Prompt statement:

[0099] Project name: News article summary generation

[0100] Objective: Automatically generate short summaries from news articles

[0101] Problem: I don't know how to select and implement a summary generation algorithm for natural language processing.

[0102] Expected output: Summary generation example code written in Python

[0103] Based on this prompt, the generative AI model provides support information that is displayed to the user through a user interface, allowing the user to efficiently complete the project.

[0104] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0105] Step 1:

[0106] Terminal: When a user launches the application, an input form is displayed for them to enter information about the project. The input form contains fields such as the project name, purpose, tasks, and expected output. Specifically, HTML and JavaScript are used to render the form and receive user input.

[0107] Input: None (Application Launch)

[0108] Output: Project information input form

[0109] Step 2:

[0110] User: Enter specific details into fields such as project name, purpose, task, expected output, etc. Once the information is complete, the user presses the "Submit" button to send the information.

[0111] Input: Project information (project name, purpose, tasks, expected output)

[0112] Output: Submit button click event

[0113] Step 3:

[0114] Terminal: Converts the information entered by the user into JSON format and sends it to the server as an HTTP request. Specifically, it sends the data using the JavaScript fetch function.

[0115] Input: User-entered project information

[0116] Output: Project information in JSON format (HTTP request)

[0117] Step 4:

[0118] Server: Extracts project information from the received HTTP request, parses the data using a JSON parser, and then uses natural language processing techniques (e.g., Python's spaCy library) to interpret the parsed data to understand the user's intent and desired results.

[0119] Input: Project information in JSON format

[0120] Output: Interpreted project information

[0121] Step 5:

[0122] Server: Formats prompts for the generative AI model based on the analysis results. Specifically, it creates questions and instructions based on the user's input. For example, based on the content "Automatically generate short summaries from news articles," it formats a prompt such as "Please tell me the algorithm for generating summaries of news articles."

[0123] Input: Interpreted project information

[0124] Output: Formatted prompt

[0125] Step 6:

[0126] Server: Passes formatted prompts to the generative AI model and retrieves responses. It sends prompts to the generative AI model via API requests and receives responses from the model. Specifically, it accesses the generative AI model using API calls.

[0127] Input: formatted prompt text

[0128] Output: Response from the generative AI model (assistance information)

[0129] Step 7:

[0130] Server: Analyzes the assistance information obtained from the generative AI model and formats it for display on the user interface. Specifically, it uses HTML and CSS to format the assistance information (e.g., code examples and algorithm explanations) so that it is displayed in an easy-to-read format.

[0131] Input: Response from the generative AI model (assistance information)

[0132] Output: Formatted supporting information

[0133] Step 8:

[0134] Device: The formatted support information is displayed in a user interface. The user can view this information and proceed with the project as needed. Specifically, the support information is formatted using HTML and CSS and displayed on the device.

[0135] Input: Formatted support information

[0136] Output: Helpful information displayed to the user

[0137] (Application example 1)

[0138] 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."

[0139] In conventional robot management systems, it was difficult for users to easily obtain specific support information related to robot operation efficiency and production line optimization. Furthermore, selecting appropriate algorithms and implementing operation programs required extensive specialized knowledge and experience, making it difficult to make effective improvements. This can lead to a decline in production efficiency and an increase in costs.

[0140] 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.

[0141] In this invention, the server includes means for inputting project-related information from a user via a user interface, means for analyzing the input information and formatting it into a prompt for passing support information to the generative AI model, means for passing the formatted prompt to the generative AI model and acquiring the support information, means for inputting information related to robot management within a factory and generating support information related to improving the efficiency of the robot's operation, and means for displaying the acquired support information to the user via the user interface. This enables a user, even without special expertise, to quickly and easily acquire specific support information for achieving effective robot management and improving operation efficiency by utilizing the generative AI model.

[0142] A "user interface" is an interface through which a user operates or inputs data into a system and checks the output or feedback from the system.

[0143] A "project" is a set of activities or tasks designed to achieve a specific purpose.

[0144] "Analyzing information" means interpreting and understanding input data and information and performing the necessary processing or conversion.

[0145] A "prompt" is input information passed to an AI model in the form of instructions or questions generated based on user input.

[0146] A "generative AI model" is a machine learning model that is pre-trained on a large dataset and generates appropriate assistance information or answers based on natural language input.

[0147] "Support information" is information provided in the form of specific solutions or suggestions, sample code, algorithm explanations, etc. that users need.

[0148] "Robot management within factories" refers to activities to optimally manage and monitor the operation and efficiency of robots used on factory production lines and in work environments.

[0149] "Operational efficiency" means enabling robots and systems to achieve maximum results using fewer resources and less time.

[0150] This invention is a system that uses a generative AI model to receive prompts about project objectives and challenges input by a user and provide appropriate support information based on those prompts. Specifically, this system is implemented as follows.

[0151] First, the user enters information about the project through a user interface on a device (such as a smartphone or tablet). The input form contains fields for the project name, objectives, tasks, expected output, etc. Once the user enters this information and presses the submit button, the information is sent to the server.

[0152] The server analyzes the received user input using natural language processing techniques to understand the user's project objectives, the challenges they are facing, and the desired output, and then formats a prompt accordingly. The formatted prompt is then passed to a generative AI model.

[0153] Next, a generative AI model generates appropriate assistance information based on the formatted prompts. This generative AI model is based on machine learning and is pre-trained on a large dataset, allowing it to provide highly accurate answers to natural language input.

[0154] The generated support information is sent back to the terminal via the server and displayed on the user interface. The user can refer to this support information to progress with their own project. They can also ask more detailed questions about the support information they have obtained or make additional corrections.

[0155] The hardware configuration of this system includes user devices (smartphones, tablets, PCs, etc.), servers, and networks. The software configuration includes a user interface application, a library for natural language analysis (e.g., NLTK or spaCy), and a generative AI model (e.g., OpenAI API).

[0156] As a specific example, consider the case where the following project information is input.

[0157] Project Information Example

[0158] Project name: Optimization of new production line

[0159] Objective: To improve the efficiency of robot movements.

[0160] Challenge: Selecting the right algorithm and motion program

[0161] Expected output: A sample working program written in Python

[0162] This information is analyzed by the server and passed to the generative AI model as formatted prompts, which then generate assistance information that provides recommendations for specific operating programs and algorithms based on the user's requests. This information is then displayed in the user interface, allowing the user to proceed with their project.

[0163] The above is a specific embodiment for carrying out the invention. By using this system, users can quickly and easily obtain specific support information for realizing effective robot management and operational efficiency by utilizing generative AI models, even without special expertise.

[0164] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0165] Step 1:

[0166] The user opens the user interface on the terminal and enters information about the project. The input form has fields such as the project name, purpose, task, and expected output. After the user enters all of this information, he or she presses the "Submit" button. This input is sent to the server. The input data includes the following information:

[0167] Project name: Optimization of new production line

[0168] Objective: To improve the efficiency of robot movements.

[0169] Challenge: Selecting the right algorithm and operation program

[0170] Expected output: A sample of a working program written in Python

[0171] Step 2:

[0172] The server receives the information sent by the user and begins analyzing the input data. This analysis process uses natural language processing technology. Specifically, it divides the input project information and interprets and understands the meaning and relevance of each piece. As an output, structured data (prompts) are generated as shown below.

[0173] Project name: Optimization of new production line

[0174] Objective: To improve the efficiency of robot movements.

[0175] Challenge: Selecting the right algorithm and operation program

[0176] Expected output: A sample of a working program written in Python

[0177] Step 3:

[0178] The server formats the prompt based on the parsed data. The prompt is formatted to be passed to the generative AI model. This prompt formatting process converts the input data to make it easier to understand. This prompt will be passed to the generative AI model in the following text format:

[0179] Project name: Optimization of new production line

[0180] Objective: To improve the efficiency of robot movements.

[0181] Challenge: Selecting the right algorithm and motion program

[0182] Expected output: A sample working program written in Python

[0183] Step 4:

[0184] The server inputs the formatted prompt into the generative AI model. Specifically, it sends the prompt to the generative AI model using OpenAI's API, etc. Based on this prompt, the generative AI model generates appropriate assistance information. Because the generative AI model builds a predictive model based on a large-scale pre-trained dataset, it can provide highly accurate responses to user input.

[0185] Step 5:

[0186] The server receives assistance information provided by the generative AI model. The assistance information includes suggestions for specific operating programs and algorithms suitable for the user's project. Specifically, it includes sample code written in Python and instructions on how to select an appropriate algorithm. An example of assistance information would be in the following format:

[0187] Python sample code to achieve efficient robot movement:

[0188] Sample Code

[0189] import some_robot_library

[0190] def optimize_robot():

[0191] Optimization algorithm description

[0192] pass

[0193] Step 6:

[0194] The server sends the support information received from the generative AI model to the user interface. The information displayed on the user interface includes the specific operation program generated and the method for selecting the algorithm. Users can refer to this information to progress their own projects. Users can also ask additional questions or make corrections.

[0195] 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.

[0196] The present invention is a system that combines a generative AI model that receives prompts about project objectives and challenges input by the user and provides appropriate support information based on those prompts with an emotion engine that recognizes the user's emotions. Below, the program processing of this system is explained in natural language, with specific examples.

[0197] Explanation of system processing

[0198] User interface input

[0199] Terminal: When the application is launched, an input form is displayed, in which the user can enter information about the project. This input form has fields such as the project name, purpose, tasks, and expected output, and the user enters specific details into these fields. Once the information is complete, the user presses the "Submit" button to send the information.

[0200] Receiving and parsing prompts

[0201] Terminal: Receives the information entered by the user in the input form and formats it as a prompt. This prompt is text data including the project name, objectives, tasks, and expected output.

[0202] Emotion engine analysis

[0203] Server: Before parsing the received prompt, the server analyzes the user's emotional state using an emotion engine. The emotion engine identifies emotional expressions in the text and determines how the user is currently feeling.

[0204] Formatting and Modifying Prompts

[0205] Server: Based on the emotions recognized by the emotion engine, the prompt is formatted and modified as needed to be passed to the generative AI model. For example, if the user is expressing negative emotions, the prompt may include a message to relax or additional support information.

[0206] Invoking a generative AI model

[0207] Server: Passes the formatted and corrected prompts to the generative AI model, which generates assistance information in response to the prompts. This generative AI model is a predictive model based on machine learning that has been pre-trained on a large dataset, and provides highly accurate answers to natural language inputs.

[0208] Display of support information

[0209] Terminal: Receives assistance information obtained from the generative AI model and displays it on the user interface. The assistance information includes specific code examples, explanations of algorithms, and suggested design patterns, allowing users to use this information as a reference for their own development. Users can also ask new questions or make corrections based on the displayed assistance information.

[0210] Specific examples

[0211] Example user input

[0212] Let's say a user enters "Generating summaries for news articles" as the project name, "Generating short summaries automatically from news articles" as the objective, and "I don't know how to select and implement a summary generation algorithm in natural language processing" as the challenge they are facing. Furthermore, they enter "Sample code for generating summaries written in Python" as the desired output.

[0213] Following this input, the emotion engine analyzes the user's emotional state from the input text and identifies that the user is expressing feelings of anxiety or confusion. Based on this information, the server formats a prompt and passes it to the generative AI model, which then generates support information based on the prompt, including sample code written in Python for generating summaries. The results are displayed on the device, allowing the user to proceed with their own project based on the information provided.

[0214] The above is a specific embodiment of the present invention. By using this system, users can quickly obtain appropriate support information that takes into account their own emotional state, making it possible to improve the efficiency of the development process and enhance creativity.

[0215] The processing flow will be explained below.

[0216] Step 1:

[0217] User: Launches the application and enters information about the project. The input form contains fields for the project name, purpose, tasks, and expected output. The user enters information in these fields and clicks the "Submit" button.

[0218] Step 2:

[0219] Terminal: Receives the information entered by the user and formats it into text data. This text data includes information such as the project name, objectives, tasks, and expected output.

[0220] Step 3:

[0221] Terminal: Sends formatted text data to the server, which is used as a prompt.

[0222] Step 4:

[0223] Server: Before parsing the received prompt, it uses an emotion engine to analyze the user's emotional state. The emotion engine identifies emotional expressions in the text data and determines how the user is currently feeling.

[0224] Step 5:

[0225] Server: Shapes prompts passed to the generative AI model based on emotions recognized by the emotion engine. For example, if the user expresses anxiety or confusion, it adds a message to relax them.

[0226] Step 6:

[0227] Server: Passes the formatted prompt to the generative AI model, which generates appropriate assistance information based on the input prompt.

[0228] Step 7:

[0229] Server: Obtains assistance information from the generative AI model, including specific code snippets, algorithm explanations, and suggested design patterns.

[0230] Step 8:

[0231] Server: Sends the acquired assistance information to the terminal, where it is formatted to be displayed to the user via the user interface.

[0232] Step 9:

[0233] Terminal: The support information received from the server is displayed on the user interface. The user can check the displayed information and ask new questions or make corrections as necessary.

[0234] Step 10:

[0235] User: Uses the displayed assistance information to further develop the project, for example, by implementing a specific functionality using the provided code snippets.

[0236] Example 2

[0237] 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."

[0238] In assistance systems using conventional generative AI models, when providing assistance information in response to prompts entered by the user, the system does not take the user's emotional state into consideration, which means that it is unable to respond appropriately to emotions such as anxiety or confusion, and therefore does not provide the assistance the user desires.In addition, information provided without considering the user's emotional state can hinder the efficiency of the user's development process and the improvement of their creativity.

[0239] 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.

[0240] In this invention, the server includes means for inputting project-related information from a user, means for analyzing the input information and recognizing the user's emotional state, means for shaping a prompt based on the recognized emotion and modifying it to a prompt to be passed to a generative AI model, means for passing the modified prompt to the generative AI model and acquiring support information, and means for displaying the acquired support information to the user via a user interface. This allows for the rapid provision of appropriate support information that takes the user's emotional state into consideration, thereby improving the efficiency and creativity of the development process.

[0241] A "user interface" is a screen or device through which a user interacts with a system and inputs information.

[0242] "Project information" refers to data such as the content, objectives, tasks, and expected output of the project the user is working on.

[0243] "Entered information" is information about a project that a user enters into the system through a user interface.

[0244] A "prompt" is text data formatted to be passed to a generative AI model, and includes information such as the project name, objectives, challenges, and expected output.

[0245] "Emotional state" refers to the psychological state of the user analyzed from the information input by the user, and includes, for example, emotions such as anxiety, confusion, and relief.

[0246] "Sentiment analysis" is a natural language processing technique for identifying the emotional state of a user from their input text.

[0247] A "generative AI model" is a predictive model trained based on machine learning that generates optimal answers or assistance information for a given prompt.

[0248] "Support information" refers to information provided by the generative AI model, such as specific advice, sample code, and algorithm explanations for the user's project.

[0249] MODE FOR CARRYING OUT THE INVENTION

[0250] The present invention is a system that provides appropriate support information using a generative AI model based on project-related information input by a user, taking into account the user's emotional state. An embodiment of this system will be described below.

[0251] System configuration

[0252] 1. User Interface: The user inputs information about the project through an application installed on the terminal. This information includes the project name, objectives, tasks, and expected outputs. The user interface is implemented as a GUI (Graphical User Interface) on, for example, a smartphone, tablet, or PC.

[0253] 2. Receiving input information: The terminal receives the information the user inputs through the user interface and formats it as a prompt.

[0254] 3. Emotion analysis by emotion engine: The server passes the content of the received prompt to the emotion engine to recognize the user's emotional state. The emotion engine analyzes emotions using a natural language processing algorithm. This emotion engine can use natural language processing technologies such as GPT-3.

[0255] 4. Prompt Shaping and Modification: The server shapes and modifies prompts to fit the generative AI model based on the user's emotional state recognized by the emotion engine. For example, if the user expresses anxiety, the prompt will include a message to help them relax.

[0256] 5. Invoke the generative AI model: The modified prompt is passed to the generative AI model, which is a machine learning model pre-trained on a large dataset to generate appropriate assistance information.

[0257] 6. Displaying Support Information: The terminal receives the generated support information and displays it to the user via a user interface. This information includes specific code examples, explanations of algorithms, and suggested design patterns.

[0258] Specific examples

[0259] The user enters "Generating summaries of news articles" as the project name, "Automatically generating short summaries from news articles" as the objective, and "I don't know how to select and implement a summary generation algorithm in natural language processing" as the challenge. Furthermore, the user enters "Sample code for generating summaries written in Python" as the desired output. Based on this input, the emotion engine identifies that the user is expressing feelings of anxiety or confusion, and the server formats the prompt and passes it to the generative AI model, including a message to relax.

[0260] Based on the prompts, the generative AI model generates sample code written in Python and specific support information for algorithm selection. The generated support information is displayed on the device, allowing users to use it as a reference to proceed with the project.

[0261] The above is a specific embodiment of the present invention. This system allows users to quickly obtain appropriate support information that takes into account their own emotional state, thereby improving the efficiency of the development process and enhancing creativity.

[0262] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0263] Step 1:

[0264] User interface input

[0265] Terminal: When the application is launched, an input form is displayed, in which the user is asked to enter information about the project. The user enters the project name, purpose, tasks, and expected output. Once the input is complete, the user presses the "Submit" button to send the information.

[0266] Input: Project name, purpose, task, expected output

[0267] Output: Input project information

[0268] Step 2:

[0269] Receiving and parsing prompts

[0270] Terminal: Receives the information entered by the user into the form and formats it as a prompt. At this time, the data from each field is combined into a single text block. Simple error checking is also performed, and if there are any omissions or errors, the user is notified.

[0271] Input: Project information entered

[0272] Output: A formatted prompt

[0273] Step 3:

[0274] Emotion engine analysis

[0275] Server: Before parsing the prompt received from the device, the server passes the prompt to the emotion engine to analyze the user's emotional state. The emotion engine uses natural language processing algorithms to identify the user's emotion from the text in the prompt. Emotions such as anxiety and confusion are identified.

[0276] Input: Formatted prompt

[0277] Output: User's emotional state

[0278] Step 4:

[0279] Formatting and Modifying Prompts

[0280] Server: Considers the emotions recognized by the emotion engine and formats and modifies the prompt to fit the generative AI model. For example, if the user expresses anxiety, it adds a message like "Don't worry, the following information may help."

[0281] Input: formatted prompts, user emotional state

[0282] Output: Modified prompt

[0283] Step 5:

[0284] Invoking a generative AI model

[0285] Server: Passes the modified prompt to the generative AI model, which generates appropriate assistance information based on the prompt, including specific sample code and algorithm suggestions. The generative AI model is a machine learning model trained on a large dataset.

[0286] Input: Corrected prompt

[0287] Output: Generated support information

[0288] Step 6:

[0289] Display of support information

[0290] Terminal: Receives the generated support information and displays it in the user interface. The user can use this information as a reference to proceed with the project. The displayed information also serves as a basis for the user to ask further questions or make corrections.

[0291] Input: Generated support information

[0292] Output: Support information displayed in the user interface

[0293] (Application example 2)

[0294] 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."

[0295] Conventional assistance systems using generative AI models were unable to consider the user's emotional state, making it difficult to provide appropriate assistance information to users who felt stressed or anxious. Furthermore, there was also the issue of users being unable to receive specific suggestions or advice to solve problems efficiently, particularly when it came to improving the efficiency of factory robot operations.

[0296] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0297] In this invention, a server is a system using a generative AI model that receives prompts regarding goals and tasks from a user and provides appropriate support information based on the prompts, and includes: means for inputting project information from the user via a user interface; means for analyzing the input information and formatting the support information into a prompt to be passed to the generative AI model; emotion recognition means for analyzing the user's emotional state during the formatting; means for modifying the prompt based on the recognized emotion and adding a message or advice for relaxation; means for passing the modified prompt to the generative AI model and acquiring support information; and means for displaying the acquired support information to the user via the user interface. This makes it possible to provide specific support information related to improving the operation efficiency of a factory robot while taking the user's emotional state into consideration.

[0298] "Project information" refers to specific information such as the content, objectives, tasks, and expected output of the project the user is working on.

[0299] A "generative AI model" is a machine learning model that has been pre-trained on a large dataset to generate assistance information based on prompts.

[0300] A "user interface" is an interface that allows a user to interact with a system, and includes input forms, display screens, and the like.

[0301] A "prompt" is text data that formats project information entered by the user and passes it to the generative AI model.

[0302] The "emotion recognition means" is a function for analyzing the user's emotional state from the text input and identifying stress or anxiety.

[0303] "Relaxation messages and advice" are additional information that provides comfort and advice depending on the user's emotional state.

[0304] "Support information" is specific suggestions, code examples, algorithm explanations, etc. generated by the generative AI model to help users solve project challenges.

[0305] "Formatting" refers to the process of analyzing user input information and converting it into a format suitable for the generative AI model.

[0306] This invention is a support system aimed at improving the efficiency of factory robot operations, and provides appropriate support information taking into account the emotional state of the user. Below, the program processing of this system is explained in natural language, with specific examples.

[0307] System configuration and program processing

[0308] Hardware and software used

[0309] Hardware:

[0310] Device: smartphone or factory robot

[0311] Server: High-performance cloud server (e.g. AWS, Google Cloud)

[0312] software:

[0313] Sentiment analysis: APIs for emotion recognition (e.g., IBM Watson Tone Analyzer API)

[0314] Generative AI models: predictive models trained on large datasets (e.g., OpenAI GPT-4 API)

[0315] User Interface: A user-friendly interface (e.g. React Native or ROS - Robot Operating System)

[0316] System Operation Procedures

[0317] 1. User interface input:

[0318] Terminal: The user uses the user interface of a smartphone or robot to input the project name, objectives, tasks, expected output, etc.

[0319] For example: "Project name: Optimization of automatic welding operations", "Objective: To improve the efficiency of welding robot operations", "Challenge: I don't know how to adjust the welding speed and improve the precision of the details", "Expected output: An algorithm for adjusting the speed and improving the precision"

[0320] 2. Receiving and parsing prompts:

[0321] Terminal: Receives input information and formats it as a prompt. The prompt is text data that includes the project name, objectives, tasks, and expected output.

[0322] 3. Emotion engine analysis:

[0323] Server: Before parsing the received prompt, the emotion engine analyzes the user's emotional state. The emotion engine identifies emotional expressions in the text and determines the user's current emotional state. For example, it uses IBM Watson Tone Analyzer.

[0324] 4. Formatting and modifying prompts:

[0325] Server: Based on the emotions recognized by the emotion engine, the server formats and optionally modifies prompts to be passed to the generative AI model. For example, if the user expresses anxiety, the server adds a message to relax or support information to the prompt.

[0326] 5. Invoke the generative AI model:

[0327] Server: Passes the formatted and corrected prompts to a generative AI model, such as OpenAI GPT-4, to generate assistance information.

[0328] 6. Display of support information:

[0329] Terminal: Receives assistance information obtained from the generative AI model and displays it on a user interface. The assistance information includes specific code examples, explanations of algorithms, and suggested design patterns.

[0330] Examples of concrete examples and prompts

[0331] Specific examples

[0332] Project name: Optimization of automated welding operations

[0333] Objective: To improve the efficiency of welding robots.

[0334] Problem: Not sure how to adjust welding speed and improve precision

[0335] Expected output: Speed ​​adjustment and accuracy improvement algorithm

[0336] Following this input, the emotion engine identifies that the user is feeling stressed. Using this information, the server formats the prompt and passes it to the generative AI model, including a message of encouragement.

[0337] Prompt Sentence Examples

[0338] Project name: Optimization of automated welding operations

[0339] Objective: To improve the efficiency of welding robots.

[0340] Problem: Not sure how to adjust welding speed and improve precision

[0341] Expected output: Speed ​​adjustment and accuracy improvement algorithm

[0342] Emotion: I'm stressed

[0343] Support information: Here are some specific algorithms for speed adjustment and accuracy improvement. I think they will be useful for setting up your welding robot. Also, I recommend taking a short break to relieve stress. You're doing great!

[0344] In this way, the present invention can provide specific support information for improving the efficiency of factory robot operations while taking into consideration the emotional state of the user, allowing the user to proceed with their work with peace of mind and achieving efficient operation of the factory robot.

[0345] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0346] Step 1:

[0347] User interface input

[0348] Terminal: The user uses the user interface of a smartphone or robot to input the project name, objectives, tasks, expected output, etc.

[0349] Input: "Project name", "Objective", "Challenge", "Expected output"

[0350] Output: The user's input data is stored in the terminal.

[0351] Specific behavior: An application starts on the device, an input form is displayed, the user fills in the input fields, and presses the submit button.

[0352] Step 2:

[0353] Receiving and parsing prompts

[0354] Terminal: Receives input information and formats it as a prompt (text data including the project name, objectives, tasks, and expected output).

[0355] Input: User-entered data

[0356] Output: Formatted prompt (text data)

[0357] Specific operation: The data analysis module in the system analyzes the input data and generates a prompt that matches the format.

[0358] Step 3:

[0359] Emotion engine analysis

[0360] Server: Analyzes the user's emotional state using the emotion engine before parsing the received prompt.

[0361] Input: Formatted prompt

[0362] Output: User's emotional state data (anxiety, stress, etc.)

[0363] Specific behavior: The server sends a prompt to an emotion recognition API (e.g., IBM Watson Tone Analyzer API) and receives the returned emotion data.

[0364] Step 4:

[0365] Formatting and Modifying Prompts

[0366] Server: Modify the prompt based on the emotions recognized by the emotion engine, adding relaxation messages and support information.

[0367] Input: Formatted prompt, user emotional state data

[0368] Output: Modified prompt

[0369] Specific behavior: The server modifies the prompt to include additional information based on the emotional state data, such as inserting a relaxation message or advice into the prompt.

[0370] Step 5:

[0371] Invoking a generative AI model

[0372] Server: Passes the modified prompt to the generative AI model to generate assistance information.

[0373] Input: Modified prompt

[0374] Output: Supporting information from the generative AI model (e.g., code examples, algorithm explanations)

[0375] Specific operation: The server calls the generated AI model API (e.g., OpenAI GPT-4 API), sends prompts, and receives relevant assistance information.

[0376] Step 6:

[0377] Display of support information

[0378] Terminal: Receives assistance information obtained from the generative AI model and displays it on the user interface.

[0379] Input: Assistance information from a generative AI model

[0380] Output: Supporting information displayed in the user interface (code examples, algorithm descriptions, etc.)

[0381] Specific operation: The device receives the support information and executes the process to display it on the user interface. Specifically, the support information is displayed on the screen in an easy-to-understand manner so that the user can refer to it.

[0382] 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.

[0383] 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.

[0384] 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.

[0385] [Second embodiment]

[0386] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0387] 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.

[0388] 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).

[0389] 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.

[0390] 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.

[0391] 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).

[0392] 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.

[0393] 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.

[0394] 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.

[0395] 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.

[0396] 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.

[0397] 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."

[0398] This invention is a system that uses a generative AI model to receive prompts about project objectives and issues input by the user and provide appropriate support information based on those inputs. Below, we will explain the program processing of this system in natural language and provide specific examples.

[0399] Explanation of system processing

[0400] User interface input

[0401] Terminal: When the application is launched, an input form is displayed, in which the user can enter information about the project. This input form has fields such as the project name, purpose, tasks, and expected output, and the user enters specific details into these fields. Once the information is complete, the user presses the "Submit" button to send the information.

[0402] Receiving and parsing prompts

[0403] Terminal: Receives the information entered by the user into the input form and sends it to the server as a prompt.

[0404] Server: Parses the incoming prompt and uses natural language analysis to interpret the input. Specifically, it understands the project objectives, the challenges faced, and the expected output, and then formats appropriate prompts based on that. These prompts include questions or instructions based on the user's input.

[0405] Invoking a generative AI model

[0406] Server: Passes the formatted prompt to the generative AI model, which generates assistance information in response to the prompt. This generative AI model is a predictive model based on machine learning that has been pre-trained on a large dataset, and provides highly accurate answers to natural language input.

[0407] Display of support information

[0408] Terminal: Receives assistance information obtained from the generative AI model and displays it on the user interface. The assistance information includes specific code examples, explanations of algorithms, and suggested design patterns, allowing users to use this information as a reference for their own development. Users can also ask new questions or make corrections based on the displayed assistance information.

[0409] Specific examples

[0410] Example user input

[0411] Let's say a user enters "Generating summaries for news articles" as the project name, "Generating short summaries automatically from news articles" as the objective, and "I don't know how to select and implement a summary generation algorithm in natural language processing" as the challenge they are facing. Furthermore, they enter "Sample code for generating summaries written in Python" as the desired output.

[0412] This input is formatted as a prompt and passed to the generative AI model, which then generates support information, including sample code written in Python, for generating a summary. This support information is then displayed on the device, allowing the user to proceed with their project.

[0413] The above is a specific embodiment of the present invention. By using this system, users can quickly obtain support information that is tailored to their own goals and challenges, thereby improving the efficiency and creativity of the development process.

[0414] The processing flow will be explained below.

[0415] Step 1:

[0416] User: Starts the application and enters the project name, purpose, tasks, and expected output in the input form. Once the input is complete, presses the "Submit" button.

[0417] Step 2:

[0418] Terminal: Receives the information entered by the user in the input form and formats it as a prompt. This prompt is text data including the project name, objectives, tasks, and expected output.

[0419] Step 3:

[0420] Terminal: Sends formatted prompts to the server, which then uses them as input to the generative AI model.

[0421] Step 4:

[0422] Server: Performs natural language analysis to interpret the received prompts, thereby understanding the user's intent and extracting appropriate questions and instructions based on their goals, challenges, and desired output.

[0423] Step 5:

[0424] Server: Based on the results of natural language analysis, it generates formatted prompts to be passed to the generative AI model, including specific requests for the problem to be solved and the assistance information to be provided.

[0425] Step 6:

[0426] Server: Passes the formatted prompts to a generative AI model that generates assistance information. This generative AI model is a predictive model based on machine learning and pre-trained on a large dataset.

[0427] Step 7:

[0428] Server: Receives assistance information obtained from the generative AI model, including specific code examples, algorithm explanations, and design pattern suggestions.

[0429] Step 8:

[0430] Server: Sends the assistance information to the terminal, where it is formatted into a form useful to the user.

[0431] Step 9:

[0432] Terminal: The received support information is displayed on the user interface. The user can check the displayed information and ask new questions or make corrections as necessary.

[0433] Step 10:

[0434] User: Use the displayed support information to proceed with the development of the project. Implement specific code examples and algorithm explanations to achieve the desired functionality.

[0435] Example 1

[0436] 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."

[0437] Conventional project management and support systems have struggled to quickly and accurately provide support information tailored to the specific challenges users face. Users must independently search through a vast amount of information to find the solutions they need, which is time-consuming and labor-intensive. Furthermore, there has been a lack of methods for accurately analyzing user input and providing appropriate support information based on that information. These issues often stall project progress, creating a demand for more efficient and creative development processes.

[0438] 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.

[0439] In this invention, the server includes means for inputting project-related information from a user via a user interface, means for analyzing the input information and formatting it into a prompt for passing support information to a generative AI model, and means for passing the formatted prompt to the generative AI model to obtain support information. This allows the user to quickly and accurately obtain specific support information for their own project, enabling the project to proceed smoothly.

[0440] A "user interface" is an interface through which a user interacts with a system, and is a means for input and output.

[0441] A "prompt" refers to information about a goal or task entered by a user, and is a formatted question or instruction to be passed to a generative AI model.

[0442] A "generative AI model" is a predictive model based on machine learning trained on large datasets, and is an algorithm that generates assistance information or answers in response to natural language input.

[0443] "Support information" refers to information for assistance provided by the generative AI model, including specific code examples, explanations of algorithms, and suggested design patterns.

[0444] "Analysis" is the process of interpreting and understanding the project information entered by the user using natural language processing techniques.

[0445] "Shaping" is the process of reconstructing the analyzed information into an appropriate prompt to be passed to the generative AI model.

[0446] "Acquisition" refers to the process of receiving assistance information from the generative AI model, and refers to the server receiving the generated information.

[0447] "Display" refers to the process of presenting the acquired assistance information on the user interface so that the user can visually confirm it.

[0448] The present invention is a system that uses a generative AI model to receive prompts regarding project objectives and challenges input by a user and provide appropriate support information based on the prompts. A specific embodiment of the present invention will be described below.

[0449] User interface input

[0450] Terminal: When the application is launched, an input form is displayed, allowing the user to enter information about the project. This input form includes fields such as the project name, purpose, tasks, and expected output. The user enters specific information into these fields. The input form is implemented using HTML and JavaScript. Once the input is complete, the user clicks the "Submit" button to send the information.

[0451] Receiving and parsing prompts

[0452] Terminal: The information entered by the user is converted into a data structure such as JSON and sent to the server as an HTTP request. Specifically, the data is sent using the JavaScript fetch function.

[0453] Server: Extracts project information from the received HTTP request and analyzes the data using a JSON parser or similar. The analysis results are used to interpret the user's intent and expected results using natural language processing (NLP) technology. Specifically, the input content is analyzed using Python's spaCy library or similar.

[0454] Prompt Formatting

[0455] Server: Based on the analysis results, the server formats a prompt to be passed to the generative AI model. Specifically, it creates questions and instructions based on the user's input. For example, based on the request to "automatically generate short summaries from news articles," the server formats a prompt such as "Please tell me the algorithm for generating summaries of news articles."

[0456] Invoking a generative AI model

[0457] Server: Passes the formatted prompts to the generative AI model, which is a machine learning-based predictive model pre-trained on a large dataset, and receives the responses. Specifically, it sends prompts to the model via API calls and receives responses.

[0458] Display of support information

[0459] Terminal: Analyzes the assistance information obtained from the generative AI model and formats it for display on the user interface. Specifically, the assistance information (e.g., code examples and algorithm explanations) is displayed using HTML and CSS. Users can use this information to proceed with their projects.

[0460] Specific examples

[0461] If a user enters "Generate summaries for news articles" as the project name, "Generate short summaries automatically from news articles" as the goal, "I don't know how to select and implement a summary generation algorithm in natural language processing" as the challenge they are facing, and further enters "Sample code for summary generation written in Python" as the desired output, the following prompt will be generated:

[0462] Prompt statement:

[0463] Project name: News article summary generation

[0464] Objective: Automatically generate short summaries from news articles

[0465] Problem: I don't know how to select and implement a summary generation algorithm for natural language processing.

[0466] Expected output: Summary generation example code written in Python

[0467] Based on this prompt, the generative AI model provides support information that is displayed to the user through a user interface, allowing the user to efficiently complete the project.

[0468] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0469] Step 1:

[0470] Terminal: When a user launches the application, an input form is displayed for them to enter information about the project. The input form contains fields such as the project name, purpose, tasks, and expected output. Specifically, HTML and JavaScript are used to render the form and receive user input.

[0471] Input: None (Application Launch)

[0472] Output: Project information input form

[0473] Step 2:

[0474] User: Enter specific details into fields such as project name, purpose, task, expected output, etc. Once the information is complete, the user presses the "Submit" button to send the information.

[0475] Input: Project information (project name, purpose, tasks, expected output)

[0476] Output: Submit button click event

[0477] Step 3:

[0478] Terminal: Converts the information entered by the user into JSON format and sends it to the server as an HTTP request. Specifically, it sends the data using the JavaScript fetch function.

[0479] Input: User-entered project information

[0480] Output: Project information in JSON format (HTTP request)

[0481] Step 4:

[0482] Server: Extracts project information from the received HTTP request, parses the data using a JSON parser, and then uses natural language processing techniques (e.g., Python's spaCy library) to interpret the parsed data to understand the user's intent and desired results.

[0483] Input: Project information in JSON format

[0484] Output: Interpreted project information

[0485] Step 5:

[0486] Server: Formats prompts for the generative AI model based on the analysis results. Specifically, it creates questions and instructions based on the user's input. For example, based on the content "Automatically generate short summaries from news articles," it formats a prompt such as "Please tell me the algorithm for generating summaries of news articles."

[0487] Input: Interpreted project information

[0488] Output: Formatted prompt

[0489] Step 6:

[0490] Server: Passes formatted prompts to the generative AI model and retrieves responses. It sends prompts to the generative AI model via API requests and receives responses from the model. Specifically, it accesses the generative AI model using API calls.

[0491] Input: formatted prompt text

[0492] Output: Response from the generative AI model (assistance information)

[0493] Step 7:

[0494] Server: Analyzes the assistance information obtained from the generative AI model and formats it for display on the user interface. Specifically, it uses HTML and CSS to format the assistance information (e.g., code examples and algorithm explanations) so that it is displayed in an easy-to-read format.

[0495] Input: Response from the generative AI model (assistance information)

[0496] Output: Formatted supporting information

[0497] Step 8:

[0498] Device: The formatted support information is displayed in a user interface. The user can view this information and proceed with the project as needed. Specifically, the support information is formatted using HTML and CSS and displayed on the device.

[0499] Input: Formatted support information

[0500] Output: Helpful information displayed to the user

[0501] (Application example 1)

[0502] 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."

[0503] In conventional robot management systems, it was difficult for users to easily obtain specific support information related to robot operation efficiency and production line optimization. Furthermore, selecting appropriate algorithms and implementing operation programs required extensive specialized knowledge and experience, making it difficult to make effective improvements. This can lead to a decline in production efficiency and an increase in costs.

[0504] 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.

[0505] In this invention, the server includes means for inputting project-related information from a user via a user interface, means for analyzing the input information and formatting it into a prompt for passing support information to the generative AI model, means for passing the formatted prompt to the generative AI model and acquiring the support information, means for inputting information related to robot management within a factory and generating support information related to improving the efficiency of the robot's operation, and means for displaying the acquired support information to the user via the user interface. This enables a user, even without special expertise, to quickly and easily acquire specific support information for achieving effective robot management and improving operation efficiency by utilizing the generative AI model.

[0506] A "user interface" is an interface through which a user operates or inputs data into a system and checks the output or feedback from the system.

[0507] A "project" is a set of activities or tasks designed to achieve a specific purpose.

[0508] "Analyzing information" means interpreting and understanding input data and information and performing the necessary processing or conversion.

[0509] A "prompt" is input information passed to an AI model in the form of instructions or questions generated based on user input.

[0510] A "generative AI model" is a machine learning model that is pre-trained on a large dataset and generates appropriate assistance information or answers based on natural language input.

[0511] "Support information" is information provided in the form of specific solutions or suggestions, sample code, algorithm explanations, etc. that users need.

[0512] "Robot management within factories" refers to activities to optimally manage and monitor the operation and efficiency of robots used on factory production lines and in work environments.

[0513] "Operational efficiency" means enabling robots and systems to achieve maximum results using fewer resources and less time.

[0514] This invention is a system that uses a generative AI model to receive prompts about project objectives and challenges input by a user and provide appropriate support information based on those prompts. Specifically, this system is implemented as follows.

[0515] First, the user enters information about the project through a user interface on a device (such as a smartphone or tablet). The input form contains fields for the project name, objectives, tasks, expected output, etc. Once the user enters this information and presses the submit button, the information is sent to the server.

[0516] The server analyzes the received user input using natural language processing techniques to understand the user's project objectives, the challenges they are facing, and the desired output, and then formats a prompt accordingly. The formatted prompt is then passed to a generative AI model.

[0517] Next, a generative AI model generates appropriate assistance information based on the formatted prompts. This generative AI model is based on machine learning and is pre-trained on a large dataset, allowing it to provide highly accurate answers to natural language input.

[0518] The generated support information is sent back to the terminal via the server and displayed on the user interface. The user can refer to this support information to progress with their own project. They can also ask more detailed questions about the support information they have obtained or make additional corrections.

[0519] The hardware configuration of this system includes user devices (smartphones, tablets, PCs, etc.), servers, and networks. The software configuration includes a user interface application, a library for natural language analysis (e.g., NLTK or spaCy), and a generative AI model (e.g., OpenAI API).

[0520] As a specific example, consider the case where the following project information is input.

[0521] Project Information Example

[0522] Project name: Optimization of new production line

[0523] Objective: To improve the efficiency of robot movements.

[0524] Challenge: Selecting the right algorithm and motion program

[0525] Expected output: A sample working program written in Python

[0526] This information is analyzed by the server and passed to the generative AI model as formatted prompts, which then generate assistance information that provides recommendations for specific operating programs and algorithms based on the user's requests. This information is then displayed in the user interface, allowing the user to proceed with their project.

[0527] The above is a specific embodiment for carrying out the invention. By using this system, users can quickly and easily obtain specific support information for realizing effective robot management and operational efficiency by utilizing generative AI models, even without special expertise.

[0528] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0529] Step 1:

[0530] The user opens the user interface on the terminal and enters information about the project. The input form has fields such as the project name, purpose, task, and expected output. After the user enters all of this information, he or she presses the "Submit" button. This input is sent to the server. The input data includes the following information:

[0531] Project name: Optimization of new production line

[0532] Objective: To improve the efficiency of robot movements.

[0533] Challenge: Selecting the right algorithm and operation program

[0534] Expected output: A sample of a working program written in Python

[0535] Step 2:

[0536] The server receives the information sent by the user and begins analyzing the input data. This analysis process uses natural language processing technology. Specifically, it divides the input project information and interprets and understands the meaning and relevance of each piece. As an output, structured data (prompts) are generated as shown below.

[0537] Project name: Optimization of new production line

[0538] Objective: To improve the efficiency of robot movements.

[0539] Challenge: Selecting the right algorithm and operation program

[0540] Expected output: A sample of a working program written in Python

[0541] Step 3:

[0542] The server formats the prompt based on the parsed data. The prompt is formatted to be passed to the generative AI model. This prompt formatting process converts the input data to make it easier to understand. This prompt will be passed to the generative AI model in the following text format:

[0543] Project name: Optimization of new production line

[0544] Objective: To improve the efficiency of robot movements.

[0545] Challenge: Selecting the right algorithm and motion program

[0546] Expected output: A sample working program written in Python

[0547] Step 4:

[0548] The server inputs the formatted prompt into the generative AI model. Specifically, it sends the prompt to the generative AI model using OpenAI's API, etc. Based on this prompt, the generative AI model generates appropriate assistance information. Because the generative AI model builds a predictive model based on a large-scale pre-trained dataset, it can provide highly accurate responses to user input.

[0549] Step 5:

[0550] The server receives assistance information provided by the generative AI model. The assistance information includes suggestions for specific operating programs and algorithms suitable for the user's project. Specifically, it includes sample code written in Python and instructions on how to select an appropriate algorithm. An example of assistance information would be in the following format:

[0551] Python sample code to achieve efficient robot movement:

[0552] Sample Code

[0553] import some_robot_library

[0554] def optimize_robot():

[0555] Optimization algorithm description

[0556] pass

[0557] Step 6:

[0558] The server sends the support information received from the generative AI model to the user interface. The information displayed on the user interface includes the specific operation program generated and the method for selecting the algorithm. Users can refer to this information to progress their own projects. Users can also ask additional questions or make corrections.

[0559] 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.

[0560] The present invention is a system that combines a generative AI model that receives prompts about project objectives and challenges input by the user and provides appropriate support information based on those prompts with an emotion engine that recognizes the user's emotions. Below, the program processing of this system is explained in natural language, with specific examples.

[0561] Explanation of system processing

[0562] User interface input

[0563] Terminal: When the application is launched, an input form is displayed, in which the user can enter information about the project. This input form has fields such as the project name, purpose, tasks, and expected output, and the user enters specific details into these fields. Once the information is complete, the user presses the "Submit" button to send the information.

[0564] Receiving and parsing prompts

[0565] Terminal: Receives the information entered by the user in the input form and formats it as a prompt. This prompt is text data including the project name, objectives, tasks, and expected output.

[0566] Emotion engine analysis

[0567] Server: Before parsing the received prompt, the server analyzes the user's emotional state using an emotion engine. The emotion engine identifies emotional expressions in the text and determines how the user is currently feeling.

[0568] Formatting and Modifying Prompts

[0569] Server: Based on the emotions recognized by the emotion engine, the prompt is formatted and modified as needed to be passed to the generative AI model. For example, if the user is expressing negative emotions, the prompt may include a message to relax or additional support information.

[0570] Invoking a generative AI model

[0571] Server: Passes the formatted and corrected prompts to the generative AI model, which generates assistance information in response to the prompts. This generative AI model is a predictive model based on machine learning that has been pre-trained on a large dataset, and provides highly accurate answers to natural language inputs.

[0572] Display of support information

[0573] Terminal: Receives assistance information obtained from the generative AI model and displays it on the user interface. The assistance information includes specific code examples, explanations of algorithms, and suggested design patterns, allowing users to use this information as a reference for their own development. Users can also ask new questions or make corrections based on the displayed assistance information.

[0574] Specific examples

[0575] Example user input

[0576] Let's say a user enters "Generating summaries for news articles" as the project name, "Generating short summaries automatically from news articles" as the objective, and "I don't know how to select and implement a summary generation algorithm in natural language processing" as the challenge they are facing. Furthermore, they enter "Sample code for generating summaries written in Python" as the desired output.

[0577] Following this input, the emotion engine analyzes the user's emotional state from the input text and identifies that the user is expressing feelings of anxiety or confusion. Based on this information, the server formats a prompt and passes it to the generative AI model, which then generates support information based on the prompt, including sample code written in Python for generating summaries. The results are displayed on the device, allowing the user to proceed with their own project based on the information provided.

[0578] The above is a specific embodiment of the present invention. By using this system, users can quickly obtain appropriate support information that takes into account their own emotional state, making it possible to improve the efficiency of the development process and enhance creativity.

[0579] The processing flow will be explained below.

[0580] Step 1:

[0581] User: Launches the application and enters information about the project. The input form contains fields for the project name, purpose, tasks, and expected output. The user enters information in these fields and clicks the "Submit" button.

[0582] Step 2:

[0583] Terminal: Receives the information entered by the user and formats it into text data. This text data includes information such as the project name, objectives, tasks, and expected output.

[0584] Step 3:

[0585] Terminal: Sends formatted text data to the server, which is used as a prompt.

[0586] Step 4:

[0587] Server: Before parsing the received prompt, it uses an emotion engine to analyze the user's emotional state. The emotion engine identifies emotional expressions in the text data and determines how the user is currently feeling.

[0588] Step 5:

[0589] Server: Shapes prompts passed to the generative AI model based on emotions recognized by the emotion engine. For example, if the user expresses anxiety or confusion, it adds a message to relax them.

[0590] Step 6:

[0591] Server: Passes the formatted prompt to the generative AI model, which generates appropriate assistance information based on the input prompt.

[0592] Step 7:

[0593] Server: Obtains assistance information from the generative AI model, including specific code snippets, algorithm explanations, and suggested design patterns.

[0594] Step 8:

[0595] Server: Sends the acquired assistance information to the terminal, where it is formatted to be displayed to the user via the user interface.

[0596] Step 9:

[0597] Terminal: The support information received from the server is displayed on the user interface. The user can check the displayed information and ask new questions or make corrections as necessary.

[0598] Step 10:

[0599] User: Uses the displayed assistance information to further develop the project, for example, by implementing a specific functionality using the provided code snippets.

[0600] Example 2

[0601] 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."

[0602] In assistance systems using conventional generative AI models, when providing assistance information in response to prompts entered by the user, the system does not take the user's emotional state into consideration, which means that it is unable to respond appropriately to emotions such as anxiety or confusion, and therefore does not provide the assistance the user desires.In addition, information provided without considering the user's emotional state can hinder the efficiency of the user's development process and the improvement of their creativity.

[0603] 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.

[0604] In this invention, the server includes means for inputting project-related information from a user, means for analyzing the input information and recognizing the user's emotional state, means for shaping a prompt based on the recognized emotion and modifying it to a prompt to be passed to a generative AI model, means for passing the modified prompt to the generative AI model and acquiring support information, and means for displaying the acquired support information to the user via a user interface. This allows for the rapid provision of appropriate support information that takes the user's emotional state into consideration, thereby improving the efficiency and creativity of the development process.

[0605] A "user interface" is a screen or device through which a user interacts with a system and inputs information.

[0606] "Project information" refers to data such as the content, objectives, tasks, and expected output of the project the user is working on.

[0607] "Entered information" is information about a project that a user enters into the system through a user interface.

[0608] A "prompt" is text data formatted to be passed to a generative AI model, and includes information such as the project name, objectives, challenges, and expected output.

[0609] "Emotional state" refers to the psychological state of the user analyzed from the information input by the user, and includes, for example, emotions such as anxiety, confusion, and relief.

[0610] "Sentiment analysis" is a natural language processing technique for identifying the emotional state of a user from their input text.

[0611] A "generative AI model" is a predictive model trained based on machine learning that generates optimal answers or assistance information for a given prompt.

[0612] "Support information" refers to information provided by the generative AI model, such as specific advice, sample code, and algorithm explanations for the user's project.

[0613] MODE FOR CARRYING OUT THE INVENTION

[0614] The present invention is a system that provides appropriate support information using a generative AI model based on project-related information input by a user, taking into account the user's emotional state. An embodiment of this system will be described below.

[0615] System configuration

[0616] 1. User Interface: The user inputs information about the project through an application installed on the terminal. This information includes the project name, objectives, tasks, and expected outputs. The user interface is implemented as a GUI (Graphical User Interface) on, for example, a smartphone, tablet, or PC.

[0617] 2. Receiving input information: The terminal receives the information the user inputs through the user interface and formats it as a prompt.

[0618] 3. Emotion analysis by emotion engine: The server passes the content of the received prompt to the emotion engine to recognize the user's emotional state. The emotion engine analyzes emotions using a natural language processing algorithm. This emotion engine can use natural language processing technologies such as GPT-3.

[0619] 4. Prompt Shaping and Modification: The server shapes and modifies prompts to fit the generative AI model based on the user's emotional state recognized by the emotion engine. For example, if the user expresses anxiety, the prompt will include a message to help them relax.

[0620] 5. Invoke the generative AI model: The modified prompt is passed to the generative AI model, which is a machine learning model pre-trained on a large dataset to generate appropriate assistance information.

[0621] 6. Displaying Support Information: The terminal receives the generated support information and displays it to the user via a user interface. This information includes specific code examples, explanations of algorithms, and suggested design patterns.

[0622] Specific examples

[0623] The user enters "Generating summaries of news articles" as the project name, "Automatically generating short summaries from news articles" as the objective, and "I don't know how to select and implement a summary generation algorithm in natural language processing" as the challenge. Furthermore, the user enters "Sample code for generating summaries written in Python" as the desired output. Based on this input, the emotion engine identifies that the user is expressing feelings of anxiety or confusion, and the server formats the prompt and passes it to the generative AI model, including a message to relax.

[0624] Based on the prompts, the generative AI model generates sample code written in Python and specific support information for algorithm selection. The generated support information is displayed on the device, allowing users to use it as a reference to proceed with the project.

[0625] The above is a specific embodiment of the present invention. This system allows users to quickly obtain appropriate support information that takes into account their own emotional state, thereby improving the efficiency of the development process and enhancing creativity.

[0626] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0627] Step 1:

[0628] User interface input

[0629] Terminal: When the application is launched, an input form is displayed, in which the user is asked to enter information about the project. The user enters the project name, purpose, tasks, and expected output. Once the input is complete, the user presses the "Submit" button to send the information.

[0630] Input: Project name, purpose, task, expected output

[0631] Output: Input project information

[0632] Step 2:

[0633] Receiving and parsing prompts

[0634] Terminal: Receives the information entered by the user into the form and formats it as a prompt. At this time, the data from each field is combined into a single text block. Simple error checking is also performed, and if there are any omissions or errors, the user is notified.

[0635] Input: Project information entered

[0636] Output: A formatted prompt

[0637] Step 3:

[0638] Emotion engine analysis

[0639] Server: Before parsing the prompt received from the device, the server passes the prompt to the emotion engine to analyze the user's emotional state. The emotion engine uses natural language processing algorithms to identify the user's emotion from the text in the prompt. Emotions such as anxiety and confusion are identified.

[0640] Input: Formatted prompt

[0641] Output: User's emotional state

[0642] Step 4:

[0643] Formatting and Modifying Prompts

[0644] Server: Considers the emotions recognized by the emotion engine and formats and modifies the prompt to fit the generative AI model. For example, if the user expresses anxiety, it adds a message like "Don't worry, the following information may help."

[0645] Input: formatted prompts, user emotional state

[0646] Output: Modified prompt

[0647] Step 5:

[0648] Invoking a generative AI model

[0649] Server: Passes the modified prompt to the generative AI model, which generates appropriate assistance information based on the prompt, including specific sample code and algorithm suggestions. The generative AI model is a machine learning model trained on a large dataset.

[0650] Input: Corrected prompt

[0651] Output: Generated support information

[0652] Step 6:

[0653] Display of support information

[0654] Terminal: Receives the generated support information and displays it in the user interface. The user can use this information as a reference to proceed with the project. The displayed information also serves as a basis for the user to ask further questions or make corrections.

[0655] Input: Generated support information

[0656] Output: Support information displayed in the user interface

[0657] (Application example 2)

[0658] 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."

[0659] Conventional assistance systems using generative AI models were unable to consider the user's emotional state, making it difficult to provide appropriate assistance information to users who felt stressed or anxious. Furthermore, there was also the issue of users being unable to receive specific suggestions or advice to solve problems efficiently, particularly when it came to improving the efficiency of factory robot operations.

[0660] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0661] In this invention, a server is a system using a generative AI model that receives prompts regarding goals and tasks from a user and provides appropriate support information based on the prompts, and includes: means for inputting project information from the user via a user interface; means for analyzing the input information and formatting the support information into a prompt to be passed to the generative AI model; emotion recognition means for analyzing the user's emotional state during the formatting; means for modifying the prompt based on the recognized emotion and adding a message or advice for relaxation; means for passing the modified prompt to the generative AI model and acquiring support information; and means for displaying the acquired support information to the user via the user interface. This makes it possible to provide specific support information related to improving the operation efficiency of a factory robot while taking the user's emotional state into consideration.

[0662] "Project information" refers to specific information such as the content, objectives, tasks, and expected output of the project the user is working on.

[0663] A "generative AI model" is a machine learning model that has been pre-trained on a large dataset to generate assistance information based on prompts.

[0664] A "user interface" is an interface that allows a user to interact with a system, and includes input forms, display screens, and the like.

[0665] A "prompt" is text data that formats project information entered by the user and passes it to the generative AI model.

[0666] The "emotion recognition means" is a function for analyzing the user's emotional state from the text input and identifying stress or anxiety.

[0667] "Relaxation messages and advice" are additional information that provides comfort and advice depending on the user's emotional state.

[0668] "Support information" is specific suggestions, code examples, algorithm explanations, etc. generated by the generative AI model to help users solve project challenges.

[0669] "Formatting" refers to the process of analyzing user input information and converting it into a format suitable for the generative AI model.

[0670] This invention is a support system aimed at improving the efficiency of factory robot operations, and provides appropriate support information taking into account the emotional state of the user. Below, the program processing of this system is explained in natural language, with specific examples.

[0671] System configuration and program processing

[0672] Hardware and software used

[0673] Hardware:

[0674] Device: smartphone or factory robot

[0675] Server: High-performance cloud server (e.g. AWS, Google Cloud)

[0676] software:

[0677] Sentiment analysis: APIs for emotion recognition (e.g., IBM Watson Tone Analyzer API)

[0678] Generative AI models: predictive models trained on large datasets (e.g., OpenAI GPT-4 API)

[0679] User Interface: A user-friendly interface (e.g. React Native or ROS - Robot Operating System)

[0680] System Operation Procedures

[0681] 1. User interface input:

[0682] Terminal: The user uses the user interface of a smartphone or robot to input the project name, objectives, tasks, expected output, etc.

[0683] For example: "Project name: Optimization of automatic welding operations", "Objective: To improve the efficiency of welding robot operations", "Challenge: I don't know how to adjust the welding speed and improve the precision of the details", "Expected output: An algorithm for adjusting the speed and improving the precision"

[0684] 2. Receiving and parsing prompts:

[0685] Terminal: Receives input information and formats it as a prompt. The prompt is text data that includes the project name, objectives, tasks, and expected output.

[0686] 3. Emotion engine analysis:

[0687] Server: Before parsing the received prompt, the emotion engine analyzes the user's emotional state. The emotion engine identifies emotional expressions in the text and determines the user's current emotional state. For example, it uses IBM Watson Tone Analyzer.

[0688] 4. Formatting and modifying prompts:

[0689] Server: Based on the emotions recognized by the emotion engine, the server formats and optionally modifies prompts to be passed to the generative AI model. For example, if the user expresses anxiety, the server adds a message to relax or support information to the prompt.

[0690] 5. Invoke the generative AI model:

[0691] Server: Passes the formatted and corrected prompts to a generative AI model, such as OpenAI GPT-4, to generate assistance information.

[0692] 6. Display of support information:

[0693] Terminal: Receives assistance information obtained from the generative AI model and displays it on a user interface. The assistance information includes specific code examples, explanations of algorithms, and suggested design patterns.

[0694] Examples of concrete examples and prompts

[0695] Specific examples

[0696] Project name: Optimization of automated welding operations

[0697] Objective: To improve the efficiency of welding robots.

[0698] Problem: Not sure how to adjust welding speed and improve precision

[0699] Expected output: Speed ​​adjustment and accuracy improvement algorithm

[0700] Following this input, the emotion engine identifies that the user is feeling stressed. Using this information, the server formats the prompt and passes it to the generative AI model, including a message of encouragement.

[0701] Prompt Sentence Examples

[0702] Project name: Optimization of automated welding operations

[0703] Objective: To improve the efficiency of welding robots.

[0704] Problem: Not sure how to adjust welding speed and improve precision

[0705] Expected output: Speed ​​adjustment and accuracy improvement algorithm

[0706] Emotion: I'm stressed

[0707] Support information: Here are some specific algorithms for speed adjustment and accuracy improvement. I think they will be useful for setting up your welding robot. Also, I recommend taking a short break to relieve stress. You're doing great!

[0708] In this way, the present invention can provide specific support information for improving the efficiency of factory robot operations while taking into consideration the emotional state of the user, allowing the user to proceed with their work with peace of mind and achieving efficient operation of the factory robot.

[0709] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0710] Step 1:

[0711] User interface input

[0712] Terminal: The user uses the user interface of a smartphone or robot to input the project name, objectives, tasks, expected output, etc.

[0713] Input: "Project name", "Objective", "Challenge", "Expected output"

[0714] Output: The user's input data is stored in the terminal.

[0715] Specific behavior: An application starts on the device, an input form is displayed, the user fills in the input fields, and presses the submit button.

[0716] Step 2:

[0717] Receiving and parsing prompts

[0718] Terminal: Receives input information and formats it as a prompt (text data including the project name, objectives, tasks, and expected output).

[0719] Input: User-entered data

[0720] Output: Formatted prompt (text data)

[0721] Specific operation: The data analysis module in the system analyzes the input data and generates a prompt that matches the format.

[0722] Step 3:

[0723] Emotion engine analysis

[0724] Server: Analyzes the user's emotional state using the emotion engine before parsing the received prompt.

[0725] Input: Formatted prompt

[0726] Output: User's emotional state data (anxiety, stress, etc.)

[0727] Specific behavior: The server sends a prompt to an emotion recognition API (e.g., IBM Watson Tone Analyzer API) and receives the returned emotion data.

[0728] Step 4:

[0729] Formatting and Modifying Prompts

[0730] Server: Modify the prompt based on the emotions recognized by the emotion engine, adding relaxation messages and support information.

[0731] Input: Formatted prompt, user emotional state data

[0732] Output: Modified prompt

[0733] Specific behavior: The server modifies the prompt to include additional information based on the emotional state data, such as inserting a relaxation message or advice into the prompt.

[0734] Step 5:

[0735] Invoking a generative AI model

[0736] Server: Passes the modified prompt to the generative AI model to generate assistance information.

[0737] Input: Modified prompt

[0738] Output: Supporting information from the generative AI model (e.g., code examples, algorithm explanations)

[0739] Specific operation: The server calls the generated AI model API (e.g., OpenAI GPT-4 API), sends prompts, and receives relevant assistance information.

[0740] Step 6:

[0741] Display of support information

[0742] Terminal: Receives assistance information obtained from the generative AI model and displays it on the user interface.

[0743] Input: Assistance information from a generative AI model

[0744] Output: Supporting information displayed in the user interface (code examples, algorithm descriptions, etc.)

[0745] Specific operation: The device receives the support information and executes the process to display it on the user interface. Specifically, the support information is displayed on the screen in an easy-to-understand manner so that the user can refer to it.

[0746] 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.

[0747] 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.

[0748] 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.

[0749] [Third embodiment]

[0750] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0751] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0752] 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).

[0753] 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.

[0754] 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.

[0755] 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).

[0756] 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.

[0757] 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.

[0758] 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.

[0759] 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.

[0760] 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.

[0761] 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."

[0762] This invention is a system that uses a generative AI model to receive prompts about project objectives and issues input by the user and provide appropriate support information based on those inputs. Below, we will explain the program processing of this system in natural language and provide specific examples.

[0763] Explanation of system processing

[0764] User interface input

[0765] Terminal: When the application is launched, an input form is displayed, in which the user can enter information about the project. This input form has fields such as the project name, purpose, tasks, and expected output, and the user enters specific details into these fields. Once the information is complete, the user presses the "Submit" button to send the information.

[0766] Receiving and parsing prompts

[0767] Terminal: Receives the information entered by the user into the input form and sends it to the server as a prompt.

[0768] Server: Parses the incoming prompt and uses natural language analysis to interpret the input. Specifically, it understands the project objectives, the challenges faced, and the expected output, and then formats appropriate prompts based on that. These prompts include questions or instructions based on the user's input.

[0769] Invoking a generative AI model

[0770] Server: Passes the formatted prompt to the generative AI model, which generates assistance information in response to the prompt. This generative AI model is a predictive model based on machine learning that has been pre-trained on a large dataset, and provides highly accurate answers to natural language input.

[0771] Display of support information

[0772] Terminal: Receives assistance information obtained from the generative AI model and displays it on the user interface. The assistance information includes specific code examples, explanations of algorithms, and suggested design patterns, allowing users to use this information as a reference for their own development. Users can also ask new questions or make corrections based on the displayed assistance information.

[0773] Specific examples

[0774] Example user input

[0775] Let's say a user enters "Generating summaries for news articles" as the project name, "Generating short summaries automatically from news articles" as the objective, and "I don't know how to select and implement a summary generation algorithm in natural language processing" as the challenge they are facing. Furthermore, they enter "Sample code for generating summaries written in Python" as the desired output.

[0776] This input is formatted as a prompt and passed to the generative AI model, which then generates support information, including sample code written in Python, for generating a summary. This support information is then displayed on the device, allowing the user to proceed with their project.

[0777] The above is a specific embodiment of the present invention. By using this system, users can quickly obtain support information that is tailored to their own goals and challenges, thereby improving the efficiency and creativity of the development process.

[0778] The processing flow will be explained below.

[0779] Step 1:

[0780] User: Starts the application and enters the project name, purpose, tasks, and expected output in the input form. Once the input is complete, presses the "Submit" button.

[0781] Step 2:

[0782] Terminal: Receives the information entered by the user in the input form and formats it as a prompt. This prompt is text data including the project name, objectives, tasks, and expected output.

[0783] Step 3:

[0784] Terminal: Sends formatted prompts to the server, which then uses them as input to the generative AI model.

[0785] Step 4:

[0786] Server: Performs natural language analysis to interpret the received prompts, thereby understanding the user's intent and extracting appropriate questions and instructions based on their goals, challenges, and desired output.

[0787] Step 5:

[0788] Server: Based on the results of natural language analysis, it generates formatted prompts to be passed to the generative AI model, including specific requests for the problem to be solved and the assistance information to be provided.

[0789] Step 6:

[0790] Server: Passes the formatted prompts to a generative AI model that generates assistance information. This generative AI model is a predictive model based on machine learning and pre-trained on a large dataset.

[0791] Step 7:

[0792] Server: Receives assistance information obtained from the generative AI model, including specific code examples, algorithm explanations, and design pattern suggestions.

[0793] Step 8:

[0794] Server: Sends the assistance information to the terminal, where it is formatted into a form useful to the user.

[0795] Step 9:

[0796] Terminal: The received support information is displayed on the user interface. The user can check the displayed information and ask new questions or make corrections as necessary.

[0797] Step 10:

[0798] User: Use the displayed support information to proceed with the development of the project. Implement specific code examples and algorithm explanations to achieve the desired functionality.

[0799] Example 1

[0800] 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."

[0801] Conventional project management and support systems have struggled to quickly and accurately provide support information tailored to the specific challenges users face. Users must independently search through a vast amount of information to find the solutions they need, which is time-consuming and labor-intensive. Furthermore, there has been a lack of methods for accurately analyzing user input and providing appropriate support information based on that information. These issues often stall project progress, creating a demand for more efficient and creative development processes.

[0802] 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.

[0803] In this invention, the server includes means for inputting project-related information from a user via a user interface, means for analyzing the input information and formatting it into a prompt for passing support information to a generative AI model, and means for passing the formatted prompt to the generative AI model to obtain support information. This allows the user to quickly and accurately obtain specific support information for their own project, enabling the project to proceed smoothly.

[0804] A "user interface" is an interface through which a user interacts with a system, and is a means for input and output.

[0805] A "prompt" refers to information about a goal or task entered by a user, and is a formatted question or instruction to be passed to a generative AI model.

[0806] A "generative AI model" is a predictive model based on machine learning trained on large datasets, and is an algorithm that generates assistance information or answers in response to natural language input.

[0807] "Support information" refers to information for assistance provided by the generative AI model, including specific code examples, explanations of algorithms, and suggested design patterns.

[0808] "Analysis" is the process of interpreting and understanding the project information entered by the user using natural language processing techniques.

[0809] "Shaping" is the process of reconstructing the analyzed information into an appropriate prompt to be passed to the generative AI model.

[0810] "Acquisition" refers to the process of receiving assistance information from the generative AI model, and refers to the server receiving the generated information.

[0811] "Display" refers to the process of presenting the acquired assistance information on the user interface so that the user can visually confirm it.

[0812] The present invention is a system that uses a generative AI model to receive prompts regarding project objectives and challenges input by a user and provide appropriate support information based on the prompts. A specific embodiment of the present invention will be described below.

[0813] User interface input

[0814] Terminal: When the application is launched, an input form is displayed, allowing the user to enter information about the project. This input form includes fields such as the project name, purpose, tasks, and expected output. The user enters specific information into these fields. The input form is implemented using HTML and JavaScript. Once the input is complete, the user clicks the "Submit" button to send the information.

[0815] Receiving and parsing prompts

[0816] Terminal: The information entered by the user is converted into a data structure such as JSON and sent to the server as an HTTP request. Specifically, the data is sent using the JavaScript fetch function.

[0817] Server: Extracts project information from the received HTTP request and analyzes the data using a JSON parser or similar. The analysis results are used to interpret the user's intent and expected results using natural language processing (NLP) technology. Specifically, the input content is analyzed using Python's spaCy library or similar.

[0818] Prompt Formatting

[0819] Server: Based on the analysis results, the server formats a prompt to be passed to the generative AI model. Specifically, it creates questions and instructions based on the user's input. For example, based on the request to "automatically generate short summaries from news articles," the server formats a prompt such as "Please tell me the algorithm for generating summaries of news articles."

[0820] Invoking a generative AI model

[0821] Server: Passes the formatted prompts to the generative AI model, which is a machine learning-based predictive model pre-trained on a large dataset, and receives the responses. Specifically, it sends prompts to the model via API calls and receives responses.

[0822] Display of support information

[0823] Terminal: Analyzes the assistance information obtained from the generative AI model and formats it for display on the user interface. Specifically, the assistance information (e.g., code examples and algorithm explanations) is displayed using HTML and CSS. Users can use this information to proceed with their projects.

[0824] Specific examples

[0825] If a user enters "Generate summaries for news articles" as the project name, "Generate short summaries automatically from news articles" as the goal, "I don't know how to select and implement a summary generation algorithm in natural language processing" as the challenge they are facing, and further enters "Sample code for summary generation written in Python" as the desired output, the following prompt will be generated:

[0826] Prompt statement:

[0827] Project name: News article summary generation

[0828] Objective: Automatically generate short summaries from news articles

[0829] Problem: I don't know how to select and implement a summary generation algorithm for natural language processing.

[0830] Expected output: Summary generation example code written in Python

[0831] Based on this prompt, the generative AI model provides support information that is displayed to the user through a user interface, allowing the user to efficiently complete the project.

[0832] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0833] Step 1:

[0834] Terminal: When a user launches the application, an input form is displayed for them to enter information about the project. The input form contains fields such as the project name, purpose, tasks, and expected output. Specifically, HTML and JavaScript are used to render the form and receive user input.

[0835] Input: None (Application Launch)

[0836] Output: Project information input form

[0837] Step 2:

[0838] User: Enter specific details into fields such as project name, purpose, task, expected output, etc. Once the information is complete, the user presses the "Submit" button to send the information.

[0839] Input: Project information (project name, purpose, tasks, expected output)

[0840] Output: Submit button click event

[0841] Step 3:

[0842] Terminal: Converts the information entered by the user into JSON format and sends it to the server as an HTTP request. Specifically, it sends the data using the JavaScript fetch function.

[0843] Input: User-entered project information

[0844] Output: Project information in JSON format (HTTP request)

[0845] Step 4:

[0846] Server: Extracts project information from the received HTTP request, parses the data using a JSON parser, and then uses natural language processing techniques (e.g., Python's spaCy library) to interpret the parsed data to understand the user's intent and desired results.

[0847] Input: Project information in JSON format

[0848] Output: Interpreted project information

[0849] Step 5:

[0850] Server: Formats prompts for the generative AI model based on the analysis results. Specifically, it creates questions and instructions based on the user's input. For example, based on the content "Automatically generate short summaries from news articles," it formats a prompt such as "Please tell me the algorithm for generating summaries of news articles."

[0851] Input: Interpreted project information

[0852] Output: Formatted prompt

[0853] Step 6:

[0854] Server: Passes formatted prompts to the generative AI model and retrieves responses. It sends prompts to the generative AI model via API requests and receives responses from the model. Specifically, it accesses the generative AI model using API calls.

[0855] Input: formatted prompt text

[0856] Output: Response from the generative AI model (assistance information)

[0857] Step 7:

[0858] Server: Analyzes the assistance information obtained from the generative AI model and formats it for display on the user interface. Specifically, it uses HTML and CSS to format the assistance information (e.g., code examples and algorithm explanations) so that it is displayed in an easy-to-read format.

[0859] Input: Response from the generative AI model (assistance information)

[0860] Output: Formatted supporting information

[0861] Step 8:

[0862] Device: The formatted support information is displayed in a user interface. The user can view this information and proceed with the project as needed. Specifically, the support information is formatted using HTML and CSS and displayed on the device.

[0863] Input: Formatted support information

[0864] Output: Helpful information displayed to the user

[0865] (Application example 1)

[0866] 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."

[0867] In conventional robot management systems, it was difficult for users to easily obtain specific support information related to robot operation efficiency and production line optimization. Furthermore, selecting appropriate algorithms and implementing operation programs required extensive specialized knowledge and experience, making it difficult to make effective improvements. This can lead to a decline in production efficiency and an increase in costs.

[0868] 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.

[0869] In this invention, the server includes means for inputting project-related information from a user via a user interface, means for analyzing the input information and formatting it into a prompt for passing support information to the generative AI model, means for passing the formatted prompt to the generative AI model and acquiring the support information, means for inputting information related to robot management within a factory and generating support information related to improving the efficiency of the robot's operation, and means for displaying the acquired support information to the user via the user interface. This enables a user, even without special expertise, to quickly and easily acquire specific support information for achieving effective robot management and improving operation efficiency by utilizing the generative AI model.

[0870] A "user interface" is an interface through which a user operates or inputs data into a system and checks the output or feedback from the system.

[0871] A "project" is a set of activities or tasks designed to achieve a specific purpose.

[0872] "Analyzing information" means interpreting and understanding input data and information and performing the necessary processing or conversion.

[0873] A "prompt" is input information passed to an AI model in the form of instructions or questions generated based on user input.

[0874] A "generative AI model" is a machine learning model that is pre-trained on a large dataset and generates appropriate assistance information or answers based on natural language input.

[0875] "Support information" is information provided in the form of specific solutions or suggestions, sample code, algorithm explanations, etc. that users need.

[0876] "Robot management within factories" refers to activities to optimally manage and monitor the operation and efficiency of robots used on factory production lines and in work environments.

[0877] "Operational efficiency" means enabling robots and systems to achieve maximum results using fewer resources and less time.

[0878] This invention is a system that uses a generative AI model to receive prompts about project objectives and challenges input by a user and provide appropriate support information based on those prompts. Specifically, this system is implemented as follows.

[0879] First, the user enters information about the project through a user interface on a device (such as a smartphone or tablet). The input form contains fields for the project name, objectives, tasks, expected output, etc. Once the user enters this information and presses the submit button, the information is sent to the server.

[0880] The server analyzes the received user input using natural language processing techniques to understand the user's project objectives, the challenges they are facing, and the desired output, and then formats a prompt accordingly. The formatted prompt is then passed to a generative AI model.

[0881] Next, a generative AI model generates appropriate assistance information based on the formatted prompts. This generative AI model is based on machine learning and is pre-trained on a large dataset, allowing it to provide highly accurate answers to natural language input.

[0882] The generated support information is sent back to the terminal via the server and displayed on the user interface. The user can refer to this support information to progress with their own project. They can also ask more detailed questions about the support information they have obtained or make additional corrections.

[0883] The hardware configuration of this system includes user devices (smartphones, tablets, PCs, etc.), servers, and networks. The software configuration includes a user interface application, a library for natural language analysis (e.g., NLTK or spaCy), and a generative AI model (e.g., OpenAI API).

[0884] As a specific example, consider the case where the following project information is input.

[0885] Project Information Example

[0886] Project name: Optimization of new production line

[0887] Objective: To improve the efficiency of robot movements.

[0888] Challenge: Selecting the right algorithm and motion program

[0889] Expected output: A sample working program written in Python

[0890] This information is analyzed by the server and passed to the generative AI model as formatted prompts, which then generate assistance information that provides recommendations for specific operating programs and algorithms based on the user's requests. This information is then displayed in the user interface, allowing the user to proceed with their project.

[0891] The above is a specific embodiment for carrying out the invention. By using this system, users can quickly and easily obtain specific support information for realizing effective robot management and operational efficiency by utilizing generative AI models, even without special expertise.

[0892] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0893] Step 1:

[0894] The user opens the user interface on the terminal and enters information about the project. The input form has fields such as the project name, purpose, task, and expected output. After the user enters all of this information, he or she presses the "Submit" button. This input is sent to the server. The input data includes the following information:

[0895] Project name: Optimization of new production line

[0896] Objective: To improve the efficiency of robot movements.

[0897] Challenge: Selecting the right algorithm and operation program

[0898] Expected output: A sample of a working program written in Python

[0899] Step 2:

[0900] The server receives the information sent by the user and begins analyzing the input data. This analysis process uses natural language processing technology. Specifically, it divides the input project information and interprets and understands the meaning and relevance of each piece. As an output, structured data (prompts) are generated as shown below.

[0901] Project name: Optimization of new production line

[0902] Objective: To improve the efficiency of robot movements.

[0903] Challenge: Selecting the right algorithm and operation program

[0904] Expected output: A sample of a working program written in Python

[0905] Step 3:

[0906] The server formats the prompt based on the parsed data. The prompt is formatted to be passed to the generative AI model. This prompt formatting process converts the input data to make it easier to understand. This prompt will be passed to the generative AI model in the following text format:

[0907] Project name: Optimization of new production line

[0908] Objective: To improve the efficiency of robot movements.

[0909] Challenge: Selecting the right algorithm and motion program

[0910] Expected output: A sample working program written in Python

[0911] Step 4:

[0912] The server inputs the formatted prompt into the generative AI model. Specifically, it sends the prompt to the generative AI model using OpenAI's API, etc. Based on this prompt, the generative AI model generates appropriate assistance information. Because the generative AI model builds a predictive model based on a large-scale pre-trained dataset, it can provide highly accurate responses to user input.

[0913] Step 5:

[0914] The server receives assistance information provided by the generative AI model. The assistance information includes suggestions for specific operating programs and algorithms suitable for the user's project. Specifically, it includes sample code written in Python and instructions on how to select an appropriate algorithm. An example of assistance information would be in the following format:

[0915] Python sample code to achieve efficient robot movement:

[0916] Sample Code

[0917] import some_robot_library

[0918] def optimize_robot():

[0919] Optimization algorithm description

[0920] pass

[0921] Step 6:

[0922] The server sends the support information received from the generative AI model to the user interface. The information displayed on the user interface includes the specific operation program generated and the method for selecting the algorithm. Users can refer to this information to progress their own projects. Users can also ask additional questions or make corrections.

[0923] 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.

[0924] The present invention is a system that combines a generative AI model that receives prompts about project objectives and challenges input by the user and provides appropriate support information based on those prompts with an emotion engine that recognizes the user's emotions. Below, the program processing of this system is explained in natural language, with specific examples.

[0925] Explanation of system processing

[0926] User interface input

[0927] Terminal: When the application is launched, an input form is displayed, in which the user can enter information about the project. This input form has fields such as the project name, purpose, tasks, and expected output, and the user enters specific details into these fields. Once the information is complete, the user presses the "Submit" button to send the information.

[0928] Receiving and parsing prompts

[0929] Terminal: Receives the information entered by the user in the input form and formats it as a prompt. This prompt is text data including the project name, objectives, tasks, and expected output.

[0930] Emotion engine analysis

[0931] Server: Before parsing the received prompt, the server analyzes the user's emotional state using an emotion engine. The emotion engine identifies emotional expressions in the text and determines how the user is currently feeling.

[0932] Formatting and Modifying Prompts

[0933] Server: Based on the emotions recognized by the emotion engine, the prompt is formatted and modified as needed to be passed to the generative AI model. For example, if the user is expressing negative emotions, the prompt may include a message to relax or additional support information.

[0934] Invoking a generative AI model

[0935] Server: Passes the formatted and corrected prompts to the generative AI model, which generates assistance information in response to the prompts. This generative AI model is a predictive model based on machine learning that has been pre-trained on a large dataset, and provides highly accurate answers to natural language inputs.

[0936] Display of support information

[0937] Terminal: Receives assistance information obtained from the generative AI model and displays it on the user interface. The assistance information includes specific code examples, explanations of algorithms, and suggested design patterns, allowing users to use this information as a reference for their own development. Users can also ask new questions or make corrections based on the displayed assistance information.

[0938] Specific examples

[0939] Example user input

[0940] Let's say a user enters "Generating summaries for news articles" as the project name, "Generating short summaries automatically from news articles" as the objective, and "I don't know how to select and implement a summary generation algorithm in natural language processing" as the challenge they are facing. Furthermore, they enter "Sample code for generating summaries written in Python" as the desired output.

[0941] Following this input, the emotion engine analyzes the user's emotional state from the input text and identifies that the user is expressing feelings of anxiety or confusion. Based on this information, the server formats a prompt and passes it to the generative AI model, which then generates support information based on the prompt, including sample code written in Python for generating summaries. The results are displayed on the device, allowing the user to proceed with their own project based on the information provided.

[0942] The above is a specific embodiment of the present invention. By using this system, users can quickly obtain appropriate support information that takes into account their own emotional state, making it possible to improve the efficiency of the development process and enhance creativity.

[0943] The processing flow will be explained below.

[0944] Step 1:

[0945] User: Launches the application and enters information about the project. The input form contains fields for the project name, purpose, tasks, and expected output. The user enters information in these fields and clicks the "Submit" button.

[0946] Step 2:

[0947] Terminal: Receives the information entered by the user and formats it into text data. This text data includes information such as the project name, objectives, tasks, and expected output.

[0948] Step 3:

[0949] Terminal: Sends formatted text data to the server, which is used as a prompt.

[0950] Step 4:

[0951] Server: Before parsing the received prompt, it uses an emotion engine to analyze the user's emotional state. The emotion engine identifies emotional expressions in the text data and determines how the user is currently feeling.

[0952] Step 5:

[0953] Server: Shapes prompts passed to the generative AI model based on emotions recognized by the emotion engine. For example, if the user expresses anxiety or confusion, it adds a message to relax them.

[0954] Step 6:

[0955] Server: Passes the formatted prompt to the generative AI model, which generates appropriate assistance information based on the input prompt.

[0956] Step 7:

[0957] Server: Obtains assistance information from the generative AI model, including specific code snippets, algorithm explanations, and suggested design patterns.

[0958] Step 8:

[0959] Server: Sends the acquired assistance information to the terminal, where it is formatted to be displayed to the user via the user interface.

[0960] Step 9:

[0961] Terminal: The support information received from the server is displayed on the user interface. The user can check the displayed information and ask new questions or make corrections as necessary.

[0962] Step 10:

[0963] User: Uses the displayed assistance information to further develop the project, for example, by implementing a specific functionality using the provided code snippets.

[0964] Example 2

[0965] 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."

[0966] In assistance systems using conventional generative AI models, when providing assistance information in response to prompts entered by the user, the system does not take the user's emotional state into consideration, which means that it is unable to respond appropriately to emotions such as anxiety or confusion, and therefore does not provide the assistance the user desires.In addition, information provided without considering the user's emotional state can hinder the efficiency of the user's development process and the improvement of their creativity.

[0967] 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.

[0968] In this invention, the server includes means for inputting project-related information from a user, means for analyzing the input information and recognizing the user's emotional state, means for shaping a prompt based on the recognized emotion and modifying it to a prompt to be passed to a generative AI model, means for passing the modified prompt to the generative AI model and acquiring support information, and means for displaying the acquired support information to the user via a user interface. This allows for the rapid provision of appropriate support information that takes the user's emotional state into consideration, thereby improving the efficiency and creativity of the development process.

[0969] A "user interface" is a screen or device through which a user interacts with a system and inputs information.

[0970] "Project information" refers to data such as the content, objectives, tasks, and expected output of the project the user is working on.

[0971] "Entered information" is information about a project that a user enters into the system through a user interface.

[0972] A "prompt" is text data formatted to be passed to a generative AI model, and includes information such as the project name, objectives, challenges, and expected output.

[0973] "Emotional state" refers to the psychological state of the user analyzed from the information input by the user, and includes, for example, emotions such as anxiety, confusion, and relief.

[0974] "Sentiment analysis" is a natural language processing technique for identifying the emotional state of a user from their input text.

[0975] A "generative AI model" is a predictive model trained based on machine learning that generates optimal answers or assistance information for a given prompt.

[0976] "Support information" refers to information provided by the generative AI model, such as specific advice, sample code, and algorithm explanations for the user's project.

[0977] MODE FOR CARRYING OUT THE INVENTION

[0978] The present invention is a system that provides appropriate support information using a generative AI model based on project-related information input by a user, taking into account the user's emotional state. An embodiment of this system will be described below.

[0979] System configuration

[0980] 1. User Interface: The user inputs information about the project through an application installed on the terminal. This information includes the project name, objectives, tasks, and expected outputs. The user interface is implemented as a GUI (Graphical User Interface) on, for example, a smartphone, tablet, or PC.

[0981] 2. Receiving input information: The terminal receives the information the user inputs through the user interface and formats it as a prompt.

[0982] 3. Emotion analysis by emotion engine: The server passes the content of the received prompt to the emotion engine to recognize the user's emotional state. The emotion engine analyzes emotions using a natural language processing algorithm. This emotion engine can use natural language processing technologies such as GPT-3.

[0983] 4. Prompt Shaping and Modification: The server shapes and modifies prompts to fit the generative AI model based on the user's emotional state recognized by the emotion engine. For example, if the user expresses anxiety, the prompt will include a message to help them relax.

[0984] 5. Invoke the generative AI model: The modified prompt is passed to the generative AI model, which is a machine learning model pre-trained on a large dataset to generate appropriate assistance information.

[0985] 6. Displaying Support Information: The terminal receives the generated support information and displays it to the user via a user interface. This information includes specific code examples, explanations of algorithms, and suggested design patterns.

[0986] Specific examples

[0987] The user enters "Generating summaries of news articles" as the project name, "Automatically generating short summaries from news articles" as the objective, and "I don't know how to select and implement a summary generation algorithm in natural language processing" as the challenge. Furthermore, the user enters "Sample code for generating summaries written in Python" as the desired output. Based on this input, the emotion engine identifies that the user is expressing feelings of anxiety or confusion, and the server formats the prompt and passes it to the generative AI model, including a message to relax.

[0988] Based on the prompts, the generative AI model generates sample code written in Python and specific support information for algorithm selection. The generated support information is displayed on the device, allowing users to use it as a reference to proceed with the project.

[0989] The above is a specific embodiment of the present invention. This system allows users to quickly obtain appropriate support information that takes into account their own emotional state, thereby improving the efficiency of the development process and enhancing creativity.

[0990] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0991] Step 1:

[0992] User interface input

[0993] Terminal: When the application is launched, an input form is displayed, in which the user is asked to enter information about the project. The user enters the project name, purpose, tasks, and expected output. Once the input is complete, the user presses the "Submit" button to send the information.

[0994] Input: Project name, purpose, task, expected output

[0995] Output: Input project information

[0996] Step 2:

[0997] Receiving and parsing prompts

[0998] Terminal: Receives the information entered by the user into the form and formats it as a prompt. At this time, the data from each field is combined into a single text block. Simple error checking is also performed, and if there are any omissions or errors, the user is notified.

[0999] Input: Project information entered

[1000] Output: A formatted prompt

[1001] Step 3:

[1002] Emotion engine analysis

[1003] Server: Before parsing the prompt received from the device, the server passes the prompt to the emotion engine to analyze the user's emotional state. The emotion engine uses natural language processing algorithms to identify the user's emotion from the text in the prompt. Emotions such as anxiety and confusion are identified.

[1004] Input: Formatted prompt

[1005] Output: User's emotional state

[1006] Step 4:

[1007] Formatting and Modifying Prompts

[1008] Server: Considers the emotions recognized by the emotion engine and formats and modifies the prompt to fit the generative AI model. For example, if the user expresses anxiety, it adds a message like "Don't worry, the following information may help."

[1009] Input: formatted prompts, user emotional state

[1010] Output: Modified prompt

[1011] Step 5:

[1012] Invoking a generative AI model

[1013] Server: Passes the modified prompt to the generative AI model, which generates appropriate assistance information based on the prompt, including specific sample code and algorithm suggestions. The generative AI model is a machine learning model trained on a large dataset.

[1014] Input: Corrected prompt

[1015] Output: Generated support information

[1016] Step 6:

[1017] Display of support information

[1018] Terminal: Receives the generated support information and displays it in the user interface. The user can use this information as a reference to proceed with the project. The displayed information also serves as a basis for the user to ask further questions or make corrections.

[1019] Input: Generated support information

[1020] Output: Support information displayed in the user interface

[1021] (Application example 2)

[1022] 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."

[1023] Conventional assistance systems using generative AI models were unable to consider the user's emotional state, making it difficult to provide appropriate assistance information to users who felt stressed or anxious. Furthermore, there was also the issue of users being unable to receive specific suggestions or advice to solve problems efficiently, particularly when it came to improving the efficiency of factory robot operations.

[1024] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1025] In this invention, a server is a system using a generative AI model that receives prompts regarding goals and tasks from a user and provides appropriate support information based on the prompts, and includes: means for inputting project information from the user via a user interface; means for analyzing the input information and formatting the support information into a prompt to be passed to the generative AI model; emotion recognition means for analyzing the user's emotional state during the formatting; means for modifying the prompt based on the recognized emotion and adding a message or advice for relaxation; means for passing the modified prompt to the generative AI model and acquiring support information; and means for displaying the acquired support information to the user via the user interface. This makes it possible to provide specific support information related to improving the operation efficiency of a factory robot while taking the user's emotional state into consideration.

[1026] "Project information" refers to specific information such as the content, objectives, tasks, and expected output of the project the user is working on.

[1027] A "generative AI model" is a machine learning model that has been pre-trained on a large dataset to generate assistance information based on prompts.

[1028] A "user interface" is an interface that allows a user to interact with a system, and includes input forms, display screens, and the like.

[1029] A "prompt" is text data that formats project information entered by the user and passes it to the generative AI model.

[1030] The "emotion recognition means" is a function for analyzing the user's emotional state from the text input and identifying stress or anxiety.

[1031] "Relaxation messages and advice" are additional information that provides comfort and advice depending on the user's emotional state.

[1032] "Support information" is specific suggestions, code examples, algorithm explanations, etc. generated by the generative AI model to help users solve project challenges.

[1033] "Formatting" refers to the process of analyzing user input information and converting it into a format suitable for the generative AI model.

[1034] This invention is a support system aimed at improving the efficiency of factory robot operations, and provides appropriate support information taking into account the emotional state of the user. Below, the program processing of this system is explained in natural language, with specific examples.

[1035] System configuration and program processing

[1036] Hardware and software used

[1037] Hardware:

[1038] Device: smartphone or factory robot

[1039] Server: High-performance cloud server (e.g. AWS, Google Cloud)

[1040] software:

[1041] Sentiment analysis: APIs for emotion recognition (e.g., IBM Watson Tone Analyzer API)

[1042] Generative AI models: predictive models trained on large datasets (e.g., OpenAI GPT-4 API)

[1043] User Interface: A user-friendly interface (e.g. React Native or ROS - Robot Operating System)

[1044] System Operation Procedures

[1045] 1. User interface input:

[1046] Terminal: The user uses the user interface of a smartphone or robot to input the project name, objectives, tasks, expected output, etc.

[1047] For example: "Project name: Optimization of automatic welding operations", "Objective: To improve the efficiency of welding robot operations", "Challenge: I don't know how to adjust the welding speed and improve the precision of the details", "Expected output: An algorithm for adjusting the speed and improving the precision"

[1048] 2. Receiving and parsing prompts:

[1049] Terminal: Receives input information and formats it as a prompt. The prompt is text data that includes the project name, objectives, tasks, and expected output.

[1050] 3. Emotion engine analysis:

[1051] Server: Before parsing the received prompt, the emotion engine analyzes the user's emotional state. The emotion engine identifies emotional expressions in the text and determines the user's current emotional state. For example, it uses IBM Watson Tone Analyzer.

[1052] 4. Formatting and modifying prompts:

[1053] Server: Based on the emotions recognized by the emotion engine, the server formats and optionally modifies prompts to be passed to the generative AI model. For example, if the user expresses anxiety, the server adds a message to relax or support information to the prompt.

[1054] 5. Invoke the generative AI model:

[1055] Server: Passes the formatted and corrected prompts to a generative AI model, such as OpenAI GPT-4, to generate assistance information.

[1056] 6. Display of support information:

[1057] Terminal: Receives assistance information obtained from the generative AI model and displays it on a user interface. The assistance information includes specific code examples, explanations of algorithms, and suggested design patterns.

[1058] Examples of concrete examples and prompts

[1059] Specific examples

[1060] Project name: Optimization of automated welding operations

[1061] Objective: To improve the efficiency of welding robots.

[1062] Problem: Not sure how to adjust welding speed and improve precision

[1063] Expected output: Speed ​​adjustment and accuracy improvement algorithm

[1064] Following this input, the emotion engine identifies that the user is feeling stressed. Using this information, the server formats the prompt and passes it to the generative AI model, including a message of encouragement.

[1065] Prompt Sentence Examples

[1066] Project name: Optimization of automated welding operations

[1067] Objective: To improve the efficiency of welding robots.

[1068] Problem: Not sure how to adjust welding speed and improve precision

[1069] Expected output: Speed ​​adjustment and accuracy improvement algorithm

[1070] Emotion: I'm stressed

[1071] Support information: Here are some specific algorithms for speed adjustment and accuracy improvement. I think they will be useful for setting up your welding robot. Also, I recommend taking a short break to relieve stress. You're doing great!

[1072] In this way, the present invention can provide specific support information for improving the efficiency of factory robot operations while taking into consideration the emotional state of the user, allowing the user to proceed with their work with peace of mind and achieving efficient operation of the factory robot.

[1073] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1074] Step 1:

[1075] User interface input

[1076] Terminal: The user uses the user interface of a smartphone or robot to input the project name, objectives, tasks, expected output, etc.

[1077] Input: "Project name", "Objective", "Challenge", "Expected output"

[1078] Output: The user's input data is stored in the terminal.

[1079] Specific behavior: An application starts on the device, an input form is displayed, the user fills in the input fields, and presses the submit button.

[1080] Step 2:

[1081] Receiving and parsing prompts

[1082] Terminal: Receives input information and formats it as a prompt (text data including the project name, objectives, tasks, and expected output).

[1083] Input: User-entered data

[1084] Output: Formatted prompt (text data)

[1085] Specific operation: The data analysis module in the system analyzes the input data and generates a prompt that matches the format.

[1086] Step 3:

[1087] Emotion engine analysis

[1088] Server: Analyzes the user's emotional state using the emotion engine before parsing the received prompt.

[1089] Input: Formatted prompt

[1090] Output: User's emotional state data (anxiety, stress, etc.)

[1091] Specific behavior: The server sends a prompt to an emotion recognition API (e.g., IBM Watson Tone Analyzer API) and receives the returned emotion data.

[1092] Step 4:

[1093] Formatting and Modifying Prompts

[1094] Server: Modify the prompt based on the emotions recognized by the emotion engine, adding relaxation messages and support information.

[1095] Input: Formatted prompt, user emotional state data

[1096] Output: Modified prompt

[1097] Specific behavior: The server modifies the prompt to include additional information based on the emotional state data, such as inserting a relaxation message or advice into the prompt.

[1098] Step 5:

[1099] Invoking a generative AI model

[1100] Server: Passes the modified prompt to the generative AI model to generate assistance information.

[1101] Input: Modified prompt

[1102] Output: Supporting information from the generative AI model (e.g., code examples, algorithm explanations)

[1103] Specific operation: The server calls the generated AI model API (e.g., OpenAI GPT-4 API), sends prompts, and receives relevant assistance information.

[1104] Step 6:

[1105] Display of support information

[1106] Terminal: Receives assistance information obtained from the generative AI model and displays it on the user interface.

[1107] Input: Assistance information from a generative AI model

[1108] Output: Supporting information displayed in the user interface (code examples, algorithm descriptions, etc.)

[1109] Specific operation: The device receives the support information and executes the process to display it on the user interface. Specifically, the support information is displayed on the screen in an easy-to-understand manner so that the user can refer to it.

[1110] 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.

[1111] 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.

[1112] 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.

[1113] [Fourth embodiment]

[1114] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1115] 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.

[1116] 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).

[1117] 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.

[1118] 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.

[1119] 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).

[1120] 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.

[1121] 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.

[1122] 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.

[1123] 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.

[1124] 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.

[1125] 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.

[1126] 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."

[1127] This invention is a system that uses a generative AI model to receive prompts about project objectives and issues input by the user and provide appropriate support information based on those inputs. Below, we will explain the program processing of this system in natural language and provide specific examples.

[1128] Explanation of system processing

[1129] User interface input

[1130] Terminal: When the application is launched, an input form is displayed, in which the user can enter information about the project. This input form has fields such as the project name, purpose, tasks, and expected output, and the user enters specific details into these fields. Once the information is complete, the user presses the "Submit" button to send the information.

[1131] Receiving and parsing prompts

[1132] Terminal: Receives the information entered by the user into the input form and sends it to the server as a prompt.

[1133] Server: Parses the incoming prompt and uses natural language analysis to interpret the input. Specifically, it understands the project objectives, the challenges faced, and the expected output, and then formats appropriate prompts based on that. These prompts include questions or instructions based on the user's input.

[1134] Invoking a generative AI model

[1135] Server: Passes the formatted prompt to the generative AI model, which generates assistance information in response to the prompt. This generative AI model is a predictive model based on machine learning that has been pre-trained on a large dataset, and provides highly accurate answers to natural language input.

[1136] Display of support information

[1137] Terminal: Receives assistance information obtained from the generative AI model and displays it on the user interface. The assistance information includes specific code examples, explanations of algorithms, and suggested design patterns, allowing users to use this information as a reference for their own development. Users can also ask new questions or make corrections based on the displayed assistance information.

[1138] Specific examples

[1139] Example user input

[1140] Let's say a user enters "Generating summaries for news articles" as the project name, "Generating short summaries automatically from news articles" as the objective, and "I don't know how to select and implement a summary generation algorithm in natural language processing" as the challenge they are facing. Furthermore, they enter "Sample code for generating summaries written in Python" as the desired output.

[1141] This input is formatted as a prompt and passed to the generative AI model, which then generates support information, including sample code written in Python, for generating a summary. This support information is then displayed on the device, allowing the user to proceed with their project.

[1142] The above is a specific embodiment of the present invention. By using this system, users can quickly obtain support information that is tailored to their own goals and challenges, thereby improving the efficiency and creativity of the development process.

[1143] The processing flow will be explained below.

[1144] Step 1:

[1145] User: Starts the application and enters the project name, purpose, tasks, and expected output in the input form. Once the input is complete, presses the "Submit" button.

[1146] Step 2:

[1147] Terminal: Receives the information entered by the user in the input form and formats it as a prompt. This prompt is text data including the project name, objectives, tasks, and expected output.

[1148] Step 3:

[1149] Terminal: Sends formatted prompts to the server, which then uses them as input to the generative AI model.

[1150] Step 4:

[1151] Server: Performs natural language analysis to interpret the received prompts, thereby understanding the user's intent and extracting appropriate questions and instructions based on their goals, challenges, and desired output.

[1152] Step 5:

[1153] Server: Based on the results of natural language analysis, it generates formatted prompts to be passed to the generative AI model, including specific requests for the problem to be solved and the assistance information to be provided.

[1154] Step 6:

[1155] Server: Passes the formatted prompts to a generative AI model that generates assistance information. This generative AI model is a predictive model based on machine learning and pre-trained on a large dataset.

[1156] Step 7:

[1157] Server: Receives assistance information obtained from the generative AI model, including specific code examples, algorithm explanations, and design pattern suggestions.

[1158] Step 8:

[1159] Server: Sends the assistance information to the terminal, where it is formatted into a form useful to the user.

[1160] Step 9:

[1161] Terminal: The received support information is displayed on the user interface. The user can check the displayed information and ask new questions or make corrections as necessary.

[1162] Step 10:

[1163] User: Use the displayed support information to proceed with the development of the project. Implement specific code examples and algorithm explanations to achieve the desired functionality.

[1164] Example 1

[1165] 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."

[1166] Conventional project management and support systems have struggled to quickly and accurately provide support information tailored to the specific challenges users face. Users must independently search through a vast amount of information to find the solutions they need, which is time-consuming and labor-intensive. Furthermore, there has been a lack of methods for accurately analyzing user input and providing appropriate support information based on that information. These issues often stall project progress, creating a demand for more efficient and creative development processes.

[1167] 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.

[1168] In this invention, the server includes means for inputting project-related information from a user via a user interface, means for analyzing the input information and formatting it into a prompt for passing support information to a generative AI model, and means for passing the formatted prompt to the generative AI model to obtain support information. This allows the user to quickly and accurately obtain specific support information for their own project, enabling the project to proceed smoothly.

[1169] A "user interface" is an interface through which a user interacts with a system, and is a means for input and output.

[1170] A "prompt" refers to information about a goal or task entered by a user, and is a formatted question or instruction to be passed to a generative AI model.

[1171] A "generative AI model" is a predictive model based on machine learning trained on large datasets, and is an algorithm that generates assistance information or answers in response to natural language input.

[1172] "Support information" refers to information for assistance provided by the generative AI model, including specific code examples, explanations of algorithms, and suggested design patterns.

[1173] "Analysis" is the process of interpreting and understanding the project information entered by the user using natural language processing techniques.

[1174] "Shaping" is the process of reconstructing the analyzed information into an appropriate prompt to be passed to the generative AI model.

[1175] "Acquisition" refers to the process of receiving assistance information from the generative AI model, and refers to the server receiving the generated information.

[1176] "Display" refers to the process of presenting the acquired assistance information on the user interface so that the user can visually confirm it.

[1177] The present invention is a system that uses a generative AI model to receive prompts regarding project objectives and challenges input by a user and provide appropriate support information based on the prompts. A specific embodiment of the present invention will be described below.

[1178] User interface input

[1179] Terminal: When the application is launched, an input form is displayed, allowing the user to enter information about the project. This input form includes fields such as the project name, purpose, tasks, and expected output. The user enters specific information into these fields. The input form is implemented using HTML and JavaScript. Once the input is complete, the user clicks the "Submit" button to send the information.

[1180] Receiving and parsing prompts

[1181] Terminal: The information entered by the user is converted into a data structure such as JSON and sent to the server as an HTTP request. Specifically, the data is sent using the JavaScript fetch function.

[1182] Server: Extracts project information from the received HTTP request and analyzes the data using a JSON parser or similar. The analysis results are used to interpret the user's intent and expected results using natural language processing (NLP) technology. Specifically, the input content is analyzed using Python's spaCy library or similar.

[1183] Prompt Formatting

[1184] Server: Based on the analysis results, the server formats a prompt to be passed to the generative AI model. Specifically, it creates questions and instructions based on the user's input. For example, based on the request to "automatically generate short summaries from news articles," the server formats a prompt such as "Please tell me the algorithm for generating summaries of news articles."

[1185] Invoking a generative AI model

[1186] Server: Passes the formatted prompts to the generative AI model, which is a machine learning-based predictive model pre-trained on a large dataset, and receives the responses. Specifically, it sends prompts to the model via API calls and receives responses.

[1187] Display of support information

[1188] Terminal: Analyzes the assistance information obtained from the generative AI model and formats it for display on the user interface. Specifically, the assistance information (e.g., code examples and algorithm explanations) is displayed using HTML and CSS. Users can use this information to proceed with their projects.

[1189] Specific examples

[1190] If a user enters "Generate summaries for news articles" as the project name, "Generate short summaries automatically from news articles" as the goal, "I don't know how to select and implement a summary generation algorithm in natural language processing" as the challenge they are facing, and further enters "Sample code for summary generation written in Python" as the desired output, the following prompt will be generated:

[1191] Prompt statement:

[1192] Project name: News article summary generation

[1193] Objective: Automatically generate short summaries from news articles

[1194] Problem: I don't know how to select and implement a summary generation algorithm for natural language processing.

[1195] Expected output: Summary generation example code written in Python

[1196] Based on this prompt, the generative AI model provides support information that is displayed to the user through a user interface, allowing the user to efficiently complete the project.

[1197] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1198] Step 1:

[1199] Terminal: When a user launches the application, an input form is displayed for them to enter information about the project. The input form contains fields such as the project name, purpose, tasks, and expected output. Specifically, HTML and JavaScript are used to render the form and receive user input.

[1200] Input: None (Application Launch)

[1201] Output: Project information input form

[1202] Step 2:

[1203] User: Enter specific details into fields such as project name, purpose, task, expected output, etc. Once the information is complete, the user presses the "Submit" button to send the information.

[1204] Input: Project information (project name, purpose, tasks, expected output)

[1205] Output: Submit button click event

[1206] Step 3:

[1207] Terminal: Converts the information entered by the user into JSON format and sends it to the server as an HTTP request. Specifically, it sends the data using the JavaScript fetch function.

[1208] Input: User-entered project information

[1209] Output: Project information in JSON format (HTTP request)

[1210] Step 4:

[1211] Server: Extracts project information from the received HTTP request, parses the data using a JSON parser, and then uses natural language processing techniques (e.g., Python's spaCy library) to interpret the parsed data to understand the user's intent and desired results.

[1212] Input: Project information in JSON format

[1213] Output: Interpreted project information

[1214] Step 5:

[1215] Server: Formats prompts for the generative AI model based on the analysis results. Specifically, it creates questions and instructions based on the user's input. For example, based on the content "Automatically generate short summaries from news articles," it formats a prompt such as "Please tell me the algorithm for generating summaries of news articles."

[1216] Input: Interpreted project information

[1217] Output: Formatted prompt

[1218] Step 6:

[1219] Server: Passes formatted prompts to the generative AI model and retrieves responses. It sends prompts to the generative AI model via API requests and receives responses from the model. Specifically, it accesses the generative AI model using API calls.

[1220] Input: formatted prompt text

[1221] Output: Response from the generative AI model (assistance information)

[1222] Step 7:

[1223] Server: Analyzes the assistance information obtained from the generative AI model and formats it for display on the user interface. Specifically, it uses HTML and CSS to format the assistance information (e.g., code examples and algorithm explanations) so that it is displayed in an easy-to-read format.

[1224] Input: Response from the generative AI model (assistance information)

[1225] Output: Formatted supporting information

[1226] Step 8:

[1227] Device: The formatted support information is displayed in a user interface. The user can view this information and proceed with the project as needed. Specifically, the support information is formatted using HTML and CSS and displayed on the device.

[1228] Input: Formatted support information

[1229] Output: Helpful information displayed to the user

[1230] (Application example 1)

[1231] 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."

[1232] In conventional robot management systems, it was difficult for users to easily obtain specific support information related to robot operation efficiency and production line optimization. Furthermore, selecting appropriate algorithms and implementing operation programs required extensive specialized knowledge and experience, making it difficult to make effective improvements. This can lead to a decline in production efficiency and an increase in costs.

[1233] 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.

[1234] In this invention, the server includes means for inputting project-related information from a user via a user interface, means for analyzing the input information and formatting it into a prompt for passing support information to the generative AI model, means for passing the formatted prompt to the generative AI model and acquiring the support information, means for inputting information related to robot management within a factory and generating support information related to improving the efficiency of the robot's operation, and means for displaying the acquired support information to the user via the user interface. This enables a user, even without special expertise, to quickly and easily acquire specific support information for achieving effective robot management and improving operation efficiency by utilizing the generative AI model.

[1235] A "user interface" is an interface through which a user operates or inputs data into a system and checks the output or feedback from the system.

[1236] A "project" is a set of activities or tasks designed to achieve a specific purpose.

[1237] "Analyzing information" means interpreting and understanding input data and information and performing the necessary processing or conversion.

[1238] A "prompt" is input information passed to an AI model in the form of instructions or questions generated based on user input.

[1239] A "generative AI model" is a machine learning model that is pre-trained on a large dataset and generates appropriate assistance information or answers based on natural language input.

[1240] "Support information" is information provided in the form of specific solutions or suggestions, sample code, algorithm explanations, etc. that users need.

[1241] "Robot management within factories" refers to activities to optimally manage and monitor the operation and efficiency of robots used on factory production lines and in work environments.

[1242] "Operational efficiency" means enabling robots and systems to achieve maximum results using fewer resources and less time.

[1243] This invention is a system that uses a generative AI model to receive prompts about project objectives and challenges input by a user and provide appropriate support information based on those prompts. Specifically, this system is implemented as follows.

[1244] First, the user enters information about the project through a user interface on a device (such as a smartphone or tablet). The input form contains fields for the project name, objectives, tasks, expected output, etc. Once the user enters this information and presses the submit button, the information is sent to the server.

[1245] The server analyzes the received user input using natural language processing techniques to understand the user's project objectives, the challenges they are facing, and the desired output, and then formats a prompt accordingly. The formatted prompt is then passed to a generative AI model.

[1246] Next, a generative AI model generates appropriate assistance information based on the formatted prompts. This generative AI model is based on machine learning and is pre-trained on a large dataset, allowing it to provide highly accurate answers to natural language input.

[1247] The generated support information is sent back to the terminal via the server and displayed on the user interface. The user can refer to this support information to progress with their own project. They can also ask more detailed questions about the support information they have obtained or make additional corrections.

[1248] The hardware configuration of this system includes user devices (smartphones, tablets, PCs, etc.), servers, and networks. The software configuration includes a user interface application, a library for natural language analysis (e.g., NLTK or spaCy), and a generative AI model (e.g., OpenAI API).

[1249] As a specific example, consider the case where the following project information is input.

[1250] Project Information Example

[1251] Project name: Optimization of new production line

[1252] Objective: To improve the efficiency of robot movements.

[1253] Challenge: Selecting the right algorithm and motion program

[1254] Expected output: A sample working program written in Python

[1255] This information is analyzed by the server and passed to the generative AI model as formatted prompts, which then generate assistance information that provides recommendations for specific operating programs and algorithms based on the user's requests. This information is then displayed in the user interface, allowing the user to proceed with their project.

[1256] The above is a specific embodiment for carrying out the invention. By using this system, users can quickly and easily obtain specific support information for realizing effective robot management and operational efficiency by utilizing generative AI models, even without special expertise.

[1257] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1258] Step 1:

[1259] The user opens the user interface on the terminal and enters information about the project. The input form has fields such as the project name, purpose, task, and expected output. After the user enters all of this information, he or she presses the "Submit" button. This input is sent to the server. The input data includes the following information:

[1260] Project name: Optimization of new production line

[1261] Objective: To improve the efficiency of robot movements.

[1262] Challenge: Selecting the right algorithm and operation program

[1263] Expected output: A sample of a working program written in Python

[1264] Step 2:

[1265] The server receives the information sent by the user and begins analyzing the input data. This analysis process uses natural language processing technology. Specifically, it divides the input project information and interprets and understands the meaning and relevance of each piece. As an output, structured data (prompts) are generated as shown below.

[1266] Project name: Optimization of new production line

[1267] Objective: To improve the efficiency of robot movements.

[1268] Challenge: Selecting the right algorithm and operation program

[1269] Expected output: A sample of a working program written in Python

[1270] Step 3:

[1271] The server formats the prompt based on the parsed data. The prompt is formatted to be passed to the generative AI model. This prompt formatting process converts the input data to make it easier to understand. This prompt will be passed to the generative AI model in the following text format:

[1272] Project name: Optimization of new production line

[1273] Objective: To improve the efficiency of robot movements.

[1274] Challenge: Selecting the right algorithm and motion program

[1275] Expected output: A sample working program written in Python

[1276] Step 4:

[1277] The server inputs the formatted prompt into the generative AI model. Specifically, it sends the prompt to the generative AI model using OpenAI's API, etc. Based on this prompt, the generative AI model generates appropriate assistance information. Because the generative AI model builds a predictive model based on a large-scale pre-trained dataset, it can provide highly accurate responses to user input.

[1278] Step 5:

[1279] The server receives assistance information provided by the generative AI model. The assistance information includes suggestions for specific operating programs and algorithms suitable for the user's project. Specifically, it includes sample code written in Python and instructions on how to select an appropriate algorithm. An example of assistance information would be in the following format:

[1280] Python sample code to achieve efficient robot movement:

[1281] Sample Code

[1282] import some_robot_library

[1283] def optimize_robot():

[1284] Optimization algorithm description

[1285] pass

[1286] Step 6:

[1287] The server sends the support information received from the generative AI model to the user interface. The information displayed on the user interface includes the specific operation program generated and the method for selecting the algorithm. Users can refer to this information to progress their own projects. Users can also ask additional questions or make corrections.

[1288] 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.

[1289] The present invention is a system that combines a generative AI model that receives prompts about project objectives and challenges input by the user and provides appropriate support information based on those prompts with an emotion engine that recognizes the user's emotions. Below, the program processing of this system is explained in natural language, with specific examples.

[1290] Explanation of system processing

[1291] User interface input

[1292] Terminal: When the application is launched, an input form is displayed, in which the user can enter information about the project. This input form has fields such as the project name, purpose, tasks, and expected output, and the user enters specific details into these fields. Once the information is complete, the user presses the "Submit" button to send the information.

[1293] Receiving and parsing prompts

[1294] Terminal: Receives the information entered by the user in the input form and formats it as a prompt. This prompt is text data including the project name, objectives, tasks, and expected output.

[1295] Emotion engine analysis

[1296] Server: Before parsing the received prompt, the server analyzes the user's emotional state using an emotion engine. The emotion engine identifies emotional expressions in the text and determines how the user is currently feeling.

[1297] Formatting and Modifying Prompts

[1298] Server: Based on the emotions recognized by the emotion engine, the prompt is formatted and modified as needed to be passed to the generative AI model. For example, if the user is expressing negative emotions, the prompt may include a message to relax or additional support information.

[1299] Invoking a generative AI model

[1300] Server: Passes the formatted and corrected prompts to the generative AI model, which generates assistance information in response to the prompts. This generative AI model is a predictive model based on machine learning that has been pre-trained on a large dataset, and provides highly accurate answers to natural language inputs.

[1301] Display of support information

[1302] Terminal: Receives assistance information obtained from the generative AI model and displays it on the user interface. The assistance information includes specific code examples, explanations of algorithms, and suggested design patterns, allowing users to use this information as a reference for their own development. Users can also ask new questions or make corrections based on the displayed assistance information.

[1303] Specific examples

[1304] Example user input

[1305] Let's say a user enters "Generating summaries for news articles" as the project name, "Generating short summaries automatically from news articles" as the objective, and "I don't know how to select and implement a summary generation algorithm in natural language processing" as the challenge they are facing. Furthermore, they enter "Sample code for generating summaries written in Python" as the desired output.

[1306] Following this input, the emotion engine analyzes the user's emotional state from the input text and identifies that the user is expressing feelings of anxiety or confusion. Based on this information, the server formats a prompt and passes it to the generative AI model, which then generates support information based on the prompt, including sample code written in Python for generating summaries. The results are displayed on the device, allowing the user to proceed with their own project based on the information provided.

[1307] The above is a specific embodiment of the present invention. By using this system, users can quickly obtain appropriate support information that takes into account their own emotional state, making it possible to improve the efficiency of the development process and enhance creativity.

[1308] The processing flow will be explained below.

[1309] Step 1:

[1310] User: Launches the application and enters information about the project. The input form contains fields for the project name, purpose, tasks, and expected output. The user enters information in these fields and clicks the "Submit" button.

[1311] Step 2:

[1312] Terminal: Receives the information entered by the user and formats it into text data. This text data includes information such as the project name, objectives, tasks, and expected output.

[1313] Step 3:

[1314] Terminal: Sends formatted text data to the server, which is used as a prompt.

[1315] Step 4:

[1316] Server: Before parsing the received prompt, it uses an emotion engine to analyze the user's emotional state. The emotion engine identifies emotional expressions in the text data and determines how the user is currently feeling.

[1317] Step 5:

[1318] Server: Shapes prompts passed to the generative AI model based on emotions recognized by the emotion engine. For example, if the user expresses anxiety or confusion, it adds a message to relax them.

[1319] Step 6:

[1320] Server: Passes the formatted prompt to the generative AI model, which generates appropriate assistance information based on the input prompt.

[1321] Step 7:

[1322] Server: Obtains assistance information from the generative AI model, including specific code snippets, algorithm explanations, and suggested design patterns.

[1323] Step 8:

[1324] Server: Sends the acquired assistance information to the terminal, where it is formatted to be displayed to the user via the user interface.

[1325] Step 9:

[1326] Terminal: The support information received from the server is displayed on the user interface. The user can check the displayed information and ask new questions or make corrections as necessary.

[1327] Step 10:

[1328] User: Uses the displayed assistance information to further develop the project, for example, by implementing a specific functionality using the provided code snippets.

[1329] Example 2

[1330] 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."

[1331] In assistance systems using conventional generative AI models, when providing assistance information in response to prompts entered by the user, the system does not take the user's emotional state into consideration, which means that it is unable to respond appropriately to emotions such as anxiety or confusion, and therefore does not provide the assistance the user desires.In addition, information provided without considering the user's emotional state can hinder the efficiency of the user's development process and the improvement of their creativity.

[1332] 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.

[1333] In this invention, the server includes means for inputting project-related information from a user, means for analyzing the input information and recognizing the user's emotional state, means for shaping a prompt based on the recognized emotion and modifying it to a prompt to be passed to a generative AI model, means for passing the modified prompt to the generative AI model and acquiring support information, and means for displaying the acquired support information to the user via a user interface. This allows for the rapid provision of appropriate support information that takes the user's emotional state into consideration, thereby improving the efficiency and creativity of the development process.

[1334] A "user interface" is a screen or device through which a user interacts with a system and inputs information.

[1335] "Project information" refers to data such as the content, objectives, tasks, and expected output of the project the user is working on.

[1336] "Entered information" is information about a project that a user enters into the system through a user interface.

[1337] A "prompt" is text data formatted to be passed to a generative AI model, and includes information such as the project name, objectives, challenges, and expected output.

[1338] "Emotional state" refers to the psychological state of the user analyzed from the information input by the user, and includes, for example, emotions such as anxiety, confusion, and relief.

[1339] "Sentiment analysis" is a natural language processing technique for identifying the emotional state of a user from their input text.

[1340] A "generative AI model" is a predictive model trained based on machine learning that generates optimal answers or assistance information for a given prompt.

[1341] "Support information" refers to information provided by the generative AI model, such as specific advice, sample code, and algorithm explanations for the user's project.

[1342] MODE FOR CARRYING OUT THE INVENTION

[1343] The present invention is a system that provides appropriate support information using a generative AI model based on project-related information input by a user, taking into account the user's emotional state. An embodiment of this system will be described below.

[1344] System configuration

[1345] 1. User Interface: The user inputs information about the project through an application installed on the terminal. This information includes the project name, objectives, tasks, and expected outputs. The user interface is implemented as a GUI (Graphical User Interface) on, for example, a smartphone, tablet, or PC.

[1346] 2. Receiving input information: The terminal receives the information the user inputs through the user interface and formats it as a prompt.

[1347] 3. Emotion analysis by emotion engine: The server passes the content of the received prompt to the emotion engine to recognize the user's emotional state. The emotion engine analyzes emotions using a natural language processing algorithm. This emotion engine can use natural language processing technologies such as GPT-3.

[1348] 4. Prompt Shaping and Modification: The server shapes and modifies prompts to fit the generative AI model based on the user's emotional state recognized by the emotion engine. For example, if the user expresses anxiety, the prompt will include a message to help them relax.

[1349] 5. Invoke the generative AI model: The modified prompt is passed to the generative AI model, which is a machine learning model pre-trained on a large dataset to generate appropriate assistance information.

[1350] 6. Displaying Support Information: The terminal receives the generated support information and displays it to the user via a user interface. This information includes specific code examples, explanations of algorithms, and suggested design patterns.

[1351] Specific examples

[1352] The user enters "Generating summaries of news articles" as the project name, "Automatically generating short summaries from news articles" as the objective, and "I don't know how to select and implement a summary generation algorithm in natural language processing" as the challenge. Furthermore, the user enters "Sample code for generating summaries written in Python" as the desired output. Based on this input, the emotion engine identifies that the user is expressing feelings of anxiety or confusion, and the server formats the prompt and passes it to the generative AI model, including a message to relax.

[1353] Based on the prompts, the generative AI model generates sample code written in Python and specific support information for algorithm selection. The generated support information is displayed on the device, allowing users to use it as a reference to proceed with the project.

[1354] The above is a specific embodiment of the present invention. This system allows users to quickly obtain appropriate support information that takes into account their own emotional state, thereby improving the efficiency of the development process and enhancing creativity.

[1355] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1356] Step 1:

[1357] User interface input

[1358] Terminal: When the application is launched, an input form is displayed, in which the user is asked to enter information about the project. The user enters the project name, purpose, tasks, and expected output. Once the input is complete, the user presses the "Submit" button to send the information.

[1359] Input: Project name, purpose, task, expected output

[1360] Output: Input project information

[1361] Step 2:

[1362] Receiving and parsing prompts

[1363] Terminal: Receives the information entered by the user into the form and formats it as a prompt. At this time, the data from each field is combined into a single text block. Simple error checking is also performed, and if there are any omissions or errors, the user is notified.

[1364] Input: Project information entered

[1365] Output: A formatted prompt

[1366] Step 3:

[1367] Emotion engine analysis

[1368] Server: Before parsing the prompt received from the device, the server passes the prompt to the emotion engine to analyze the user's emotional state. The emotion engine uses natural language processing algorithms to identify the user's emotion from the text in the prompt. Emotions such as anxiety and confusion are identified.

[1369] Input: Formatted prompt

[1370] Output: User's emotional state

[1371] Step 4:

[1372] Formatting and Modifying Prompts

[1373] Server: Considers the emotions recognized by the emotion engine and formats and modifies the prompt to fit the generative AI model. For example, if the user expresses anxiety, it adds a message like "Don't worry, the following information may help."

[1374] Input: formatted prompts, user emotional state

[1375] Output: Modified prompt

[1376] Step 5:

[1377] Invoking a generative AI model

[1378] Server: Passes the modified prompt to the generative AI model, which generates appropriate assistance information based on the prompt, including specific sample code and algorithm suggestions. The generative AI model is a machine learning model trained on a large dataset.

[1379] Input: Corrected prompt

[1380] Output: Generated support information

[1381] Step 6:

[1382] Display of support information

[1383] Terminal: Receives the generated support information and displays it in the user interface. The user can use this information as a reference to proceed with the project. The displayed information also serves as a basis for the user to ask further questions or make corrections.

[1384] Input: Generated support information

[1385] Output: Support information displayed in the user interface

[1386] (Application example 2)

[1387] 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."

[1388] Conventional assistance systems using generative AI models were unable to consider the user's emotional state, making it difficult to provide appropriate assistance information to users who felt stressed or anxious. Furthermore, there was also the issue of users being unable to receive specific suggestions or advice to solve problems efficiently, particularly when it came to improving the efficiency of factory robot operations.

[1389] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1390] In this invention, a server is a system using a generative AI model that receives prompts regarding goals and tasks from a user and provides appropriate support information based on the prompts, and includes: means for inputting project information from the user via a user interface; means for analyzing the input information and formatting the support information into a prompt to be passed to the generative AI model; emotion recognition means for analyzing the user's emotional state during the formatting; means for modifying the prompt based on the recognized emotion and adding a message or advice for relaxation; means for passing the modified prompt to the generative AI model and acquiring support information; and means for displaying the acquired support information to the user via the user interface. This makes it possible to provide specific support information related to improving the operation efficiency of a factory robot while taking the user's emotional state into consideration.

[1391] "Project information" refers to specific information such as the content, objectives, tasks, and expected output of the project the user is working on.

[1392] A "generative AI model" is a machine learning model that has been pre-trained on a large dataset to generate assistance information based on prompts.

[1393] A "user interface" is an interface that allows a user to interact with a system, and includes input forms, display screens, and the like.

[1394] A "prompt" is text data that formats project information entered by the user and passes it to the generative AI model.

[1395] The "emotion recognition means" is a function for analyzing the user's emotional state from the text input and identifying stress or anxiety.

[1396] "Relaxation messages and advice" are additional information that provides comfort and advice depending on the user's emotional state.

[1397] "Support information" is specific suggestions, code examples, algorithm explanations, etc. generated by the generative AI model to help users solve project challenges.

[1398] "Formatting" refers to the process of analyzing user input information and converting it into a format suitable for the generative AI model.

[1399] This invention is a support system aimed at improving the efficiency of factory robot operations, and provides appropriate support information taking into account the emotional state of the user. Below, the program processing of this system is explained in natural language, with specific examples.

[1400] System configuration and program processing

[1401] Hardware and software used

[1402] Hardware:

[1403] Device: smartphone or factory robot

[1404] Server: High-performance cloud server (e.g. AWS, Google Cloud)

[1405] software:

[1406] Sentiment analysis: APIs for emotion recognition (e.g., IBM Watson Tone Analyzer API)

[1407] Generative AI models: predictive models trained on large datasets (e.g., OpenAI GPT-4 API)

[1408] User Interface: A user-friendly interface (e.g. React Native or ROS - Robot Operating System)

[1409] System Operation Procedures

[1410] 1. User interface input:

[1411] Terminal: The user uses the user interface of a smartphone or robot to input the project name, objectives, tasks, expected output, etc.

[1412] For example: "Project name: Optimization of automatic welding operations", "Objective: To improve the efficiency of welding robot operations", "Challenge: I don't know how to adjust the welding speed and improve the precision of the details", "Expected output: An algorithm for adjusting the speed and improving the precision"

[1413] 2. Receiving and parsing prompts:

[1414] Terminal: Receives input information and formats it as a prompt. The prompt is text data that includes the project name, objectives, tasks, and expected output.

[1415] 3. Emotion engine analysis:

[1416] Server: Before parsing the received prompt, the emotion engine analyzes the user's emotional state. The emotion engine identifies emotional expressions in the text and determines the user's current emotional state. For example, it uses IBM Watson Tone Analyzer.

[1417] 4. Formatting and modifying prompts:

[1418] Server: Based on the emotions recognized by the emotion engine, the server formats and optionally modifies prompts to be passed to the generative AI model. For example, if the user expresses anxiety, the server adds a message to relax or support information to the prompt.

[1419] 5. Invoke the generative AI model:

[1420] Server: Passes the formatted and corrected prompts to a generative AI model, such as OpenAI GPT-4, to generate assistance information.

[1421] 6. Display of support information:

[1422] Terminal: Receives assistance information obtained from the generative AI model and displays it on a user interface. The assistance information includes specific code examples, explanations of algorithms, and suggested design patterns.

[1423] Examples of concrete examples and prompts

[1424] Specific examples

[1425] Project name: Optimization of automated welding operations

[1426] Objective: To improve the efficiency of welding robots.

[1427] Problem: Not sure how to adjust welding speed and improve precision

[1428] Expected output: Speed ​​adjustment and accuracy improvement algorithm

[1429] Following this input, the emotion engine identifies that the user is feeling stressed. Using this information, the server formats the prompt and passes it to the generative AI model, including a message of encouragement.

[1430] Prompt Sentence Examples

[1431] Project name: Optimization of automated welding operations

[1432] Objective: To improve the efficiency of welding robots.

[1433] Problem: Not sure how to adjust welding speed and improve precision

[1434] Expected output: Speed ​​adjustment and accuracy improvement algorithm

[1435] Emotion: I'm stressed

[1436] Support information: Here are some specific algorithms for speed adjustment and accuracy improvement. I think they will be useful for setting up your welding robot. Also, I recommend taking a short break to relieve stress. You're doing great!

[1437] In this way, the present invention can provide specific support information for improving the efficiency of factory robot operations while taking into consideration the emotional state of the user, allowing the user to proceed with their work with peace of mind and achieving efficient operation of the factory robot.

[1438] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1439] Step 1:

[1440] User interface input

[1441] Terminal: The user uses the user interface of a smartphone or robot to input the project name, objectives, tasks, expected output, etc.

[1442] Input: "Project name", "Objective", "Challenge", "Expected output"

[1443] Output: The user's input data is stored in the terminal.

[1444] Specific behavior: An application starts on the device, an input form is displayed, the user fills in the input fields, and presses the submit button.

[1445] Step 2:

[1446] Receiving and parsing prompts

[1447] Terminal: Receives input information and formats it as a prompt (text data including the project name, objectives, tasks, and expected output).

[1448] Input: User-entered data

[1449] Output: Formatted prompt (text data)

[1450] Specific operation: The data analysis module in the system analyzes the input data and generates a prompt that matches the format.

[1451] Step 3:

[1452] Emotion engine analysis

[1453] Server: Analyzes the user's emotional state using the emotion engine before parsing the received prompt.

[1454] Input: Formatted prompt

[1455] Output: User's emotional state data (anxiety, stress, etc.)

[1456] Specific behavior: The server sends a prompt to an emotion recognition API (e.g., IBM Watson Tone Analyzer API) and receives the returned emotion data.

[1457] Step 4:

[1458] Formatting and Modifying Prompts

[1459] Server: Modify the prompt based on the emotions recognized by the emotion engine, adding relaxation messages and support information.

[1460] Input: Formatted prompt, user emotional state data

[1461] Output: Modified prompt

[1462] Specific behavior: The server modifies the prompt to include additional information based on the emotional state data, such as inserting a relaxation message or advice into the prompt.

[1463] Step 5:

[1464] Invoking a generative AI model

[1465] Server: Passes the modified prompt to the generative AI model to generate assistance information.

[1466] Input: Modified prompt

[1467] Output: Supporting information from the generative AI model (e.g., code examples, algorithm explanations)

[1468] Specific operation: The server calls the generated AI model API (e.g., OpenAI GPT-4 API), sends prompts, and receives relevant assistance information.

[1469] Step 6:

[1470] Display of support information

[1471] Terminal: Receives assistance information obtained from the generative AI model and displays it on the user interface.

[1472] Input: Assistance information from a generative AI model

[1473] Output: Supporting information displayed in the user interface (code examples, algorithm descriptions, etc.)

[1474] Specific operation: The device receives the support information and executes the process to display it on the user interface. Specifically, the support information is displayed on the screen in an easy-to-understand manner so that the user can refer to it.

[1475] 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.

[1476] 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.

[1477] 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.

[1478] 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.

[1479] FIG. 9 illustrates 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 behaviors 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.

[1480] 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.

[1481] 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).

[1482] 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.

[1483] 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."

[1484] 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.

[1485] 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).

[1486] 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.

[1487] 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.

[1488] 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.

[1489] 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.

[1490] 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.

[1491] 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.

[1492] 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.

[1493] 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.

[1494] 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.

[1495] 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.

[1496] The following is further disclosed regarding the above embodiment.

[1497] (Claim 1)

[1498] A system using a generative AI model that receives prompts from a user regarding goals and tasks and provides appropriate support information based on the prompts,

[1499] means for inputting information about the project from a user via a user interface;

[1500] A means for analyzing the input information and formatting the assistance information into a prompt for passing it to a generative AI model;

[1501] means for passing the formatted prompt to a generative AI model to obtain assistance information;

[1502] means for displaying the acquired assistance information to a user via a user interface;

[1503] A system including:

[1504] (Claim 2)

[1505] 10. The system of claim 1, wherein the prompt analysis uses natural language analysis.

[1506] (Claim 3)

[1507] The system of claim 1, wherein the generative AI model uses a predictive model based on machine learning.

[1508] "Example 1"

[1509] (Claim 1)

[1510] A system using a generative AI model that receives prompts from a user regarding goals and tasks and provides appropriate support information based on the prompts,

[1511] means for inputting information about the project from a user via a user interface;

[1512] A means for analyzing the input information and formatting the assistance information into a prompt for passing it to a generative AI model;

[1513] means for passing the formatted prompt to a generative AI model to obtain assistance information;

[1514] means for displaying the acquired assistance information to a user via a user interface;

[1515] A system including:

[1516] (Claim 2)

[1517] 10. The system of claim 1, wherein the prompt analysis uses natural language analysis.

[1518] (Claim 3)

[1519] The system of claim 1, wherein the generative AI model uses a predictive model based on machine learning.

[1520] "Application Example 1"

[1521] (Claim 1)

[1522] A system using a generative AI model that receives prompts from a user regarding goals and tasks and provides appropriate support information based on the prompts,

[1523] means for inputting information about the project from a user via a user interface;

[1524] A means for analyzing the input information and formatting the assistance information into a prompt for passing it to a generative AI model;

[1525] means for passing the formatted prompt to a generative AI model to obtain assistance information;

[1526] a means for inputting information relating to robot management within a factory and generating support information relating to improving the efficiency of the robot's operation;

[1527] means for displaying the acquired assistance information to a user via a user interface;

[1528] A system including:

[1529] (Claim 2)

[1530] 10. The system of claim 1, wherein the prompt analysis uses natural language analysis.

[1531] (Claim 3)

[1532] The system of claim 1, wherein the generative AI model uses a predictive model based on machine learning.

[1533] "Example 2: Combining Emotion Engines"

[1534] (Claim 1)

[1535] A system using a generative AI model that receives prompts from a user regarding goals and tasks and provides appropriate support information based on the prompts,

[1536] means for inputting information about the project from a user via a user interface;

[1537] means for analyzing the input information and recognizing the emotional state of the user;

[1538] means for shaping prompts based on the recognized emotions and modifying the prompts to be passed to a generative AI model;

[1539] means for passing the modified prompt to a generative AI model to obtain assistance information;

[1540] means for displaying the acquired assistance information to a user via a user interface;

[1541] A system including:

[1542] (Claim 2)

[1543] 10. The system of claim 1, wherein the prompt analysis uses natural language analysis and sentiment analysis.

[1544] (Claim 3)

[1545] The system of claim 1, wherein the generative AI model uses a predictive model based on machine learning.

[1546] "Application example 2 when combining emotion engines"

[1547] (Claim 1)

[1548] A system using a generative AI model that receives prompts from a user regarding goals and tasks and provides appropriate support information based on the prompts,

[1549] means for inputting information about the project from a user via a user interface;

[1550] A means for analyzing the input information and formatting the assistance information into a prompt for passing it to a generative AI model;

[1551] emotion recognition means for analyzing the user's emotional state during the shaping process;

[1552] means for modifying the prompt based on the recognized emotion to add a message or advice for relaxation;

[1553] means for passing the modified prompt to a generative AI model to obtain assistance information;

[1554] means for displaying the acquired assistance information to a user via a user interface;

[1555] A system including:

[1556] (Claim 2)

[1557] 10. The system of claim 1, wherein the prompt analysis and emotional state recognition utilize natural language analysis.

[1558] (Claim 3)

[1559] The system of claim 1, wherein the generative AI model uses a predictive model based on machine learning. [Explanation of symbols]

[1560] 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 system using a generative AI model that receives prompts from a user regarding goals and tasks and provides appropriate support information based on the prompts, means for inputting information about the project from a user via a user interface; A means for analyzing the input information and formatting the assistance information into a prompt for passing it to a generative AI model; means for passing the formatted prompt to a generative AI model to obtain assistance information; a means for displaying the acquired assistance information to a user via a user interface; A system including:

2. 10. The system of claim 1, wherein the prompt analysis uses natural language analysis.

3. The system of claim 1 , wherein the generative AI model uses a predictive model based on machine learning.

Images