System

Abstract

A system is provided.SOLUTION: A system comprising: means for a user to upload a state-of-the-art analysis document and a target state document; means for a server to receive and analyze the uploaded documents; means for the server to train generative artificial intelligence based on the analysis results; means for the server to receive a new state-of-the-art analysis document from the user and automatically generate a new target state document; means for the user to confirm and modify the generated target state document; and means for the server to save the final target state document and take it to the next development step.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] The following issues need to be resolved:

[0005] In current system development projects, the manual creation of current state analysis and target state documentation is cumbersome, resulting in a significant amount of work being required in upstream processes. Furthermore, when a discrepancy occurs between the current state analysis and the target state, rework is often required, significantly reducing development efficiency. Therefore, there is a need for technology that automates the creation of current state analysis and target state documentation, reducing manual errors while improving work efficiency. [Means for solving the problem]

[0006] In order to solve the above problems, the present invention provides the following means.

[0007] The system includes a means for a user to upload a current state analysis document and a target state document, a means for a server to receive and analyze the uploaded documents, a means for the server to train a generating artificial intelligence based on the analysis results, a means for the server to receive a new current state analysis document from the user and automatically generate a new target state document, a means for the user to check and modify the generated target state document, and a means for the server to save the final target state document and hand it over to the next development process.

[0008] This automates the process of documenting the target state from current state analysis, reduces manual errors, and improves work efficiency in upstream processes.

[0009] "User" refers to a person or end user who accesses and operates the System.

[0010] A "current state analysis document" is a document that describes the current state of a system or process.

[0011] A "target state document" is a document that describes the desired state of a system or process.

[0012] A "server" is a computer system that receives and processes requests from users.

[0013] "Parsing" is the process of extracting useful information from uploaded documents and organizing it into structured data.

[0014] "Generative AI" refers to artificial intelligence techniques that learn patterns in data and generate outputs based on new inputs.

[0015] A "new current situation analysis document" is a document describing the current state that a user provides based on a new project or situation.

[0016] "Automatically generating" means that the system autonomously creates the goal state document without human intervention.

[0017] "Modifying" is the process by which a user changes the content of a generated goal state document.

[0018] The "next development process" refers to the stage where actual system development and function additions are carried out based on the target state document.

[0019] "Storing" refers to recording the created or modified goal state document in a database or storage. [Brief explanation of the drawings]

[0020] [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

[0021] 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.

[0022] First, the terms used in the following description will be explained.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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."

[0028] [First embodiment]

[0029] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0030] 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.

[0031] 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).

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0037] 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.

[0038] 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.

[0039] 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.

[0040] 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."

[0041] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments of the present invention will be described in detail.

[0042] System Overview

[0043] This invention relates to an automatic generation system for current state analysis documents (AS-IS) and target state documents (TO-BE). The system is mainly composed of users, servers, and terminals, and aims to automate document creation in upstream processes.

[0044] Program processing overview

[0045] 1. User uploads a document

[0046] Users access the system using a terminal and upload current state analysis and target state documents for the project, which are then sent to the server.

[0047] 2. The server receives and parses the document

[0048] The server receives documents uploaded by users.

[0049] The server analyzes the received document using natural language processing technology, extracting important keywords and phrases and organizing the relationship between the current state analysis document and the target state document as structured data.

[0050] 3. The server trains the generative AI based on the analysis results.

[0051] The server provides the analysis results to the generative artificial intelligence (AI) and trains it based on them. The AI ​​learns the correspondence between the current state analysis document and the target state document and constructs a generative pattern based on new input.

[0052] 4. User enters new current situation analysis document

[0053] Users can upload or enter a text box for a current situation analysis document for a new project, which describes the current system status and issues.

[0054] 5. The server automatically generates a target state document based on the new current state analysis document.

[0055] The server receives a new current situation analysis document provided by the user and passes it to the generating artificial intelligence.

[0056] Based on learned patterns, generative AI automatically generates goal state documents that describe new system states and solutions.

[0057] 6. User reviews and modifies the generated goal state document

[0058] The server displays the generated goal state document to the user, who can review it and make corrections as necessary.

[0059] The user's modifications are fed back to the generation AI and reflected in the next generation.

[0060] 7. The server saves the final target state document and passes it on to the next development stage.

[0061] The server stores the final target state document confirmed by the user, and this stored data is passed on to the next development stage.

[0062] If necessary, the server will work with other development tools and systems to transfer and share data.

[0063] Specific examples

[0064] Specific examples are shown below.

[0065] For Project A

[0066] A user uploads a current situation analysis document for Project A. This document describes that the current system requires manual entry of customer information, and points out that a problem with this is that input errors are frequent.

[0067] The server generates a goal state document based on this. This goal state document describes the introduction of the automatic input system and its benefits, such as reducing input errors.

[0068] The user checks this automatically generated target state document, adds more detailed requirements and conditions, and finalizes the final version. The server saves it and hands it over to the development team to proceed to the next stage.

[0069] Effect of the invention

[0070] This system automates the process of documenting the current state and the target state, reducing the amount of work required. It also reduces manual input errors and improves work efficiency in upstream processes. As a result, it is expected to improve the efficiency and productivity of the entire system development process.

[0071] The processing flow will be explained below.

[0072] Step 1:

[0073] The user logs into the system using a terminal. After logging in, the user goes to the "Document Upload" section on the main screen, selects the current state analysis document (AS-IS) and the target state document (TO-BE), and uploads them.

[0074] Step 2:

[0075] The server receives the documents uploaded by the user, stores them in a specific folder, and prepares them for analysis.

[0076] Step 3:

[0077] The server uses natural language processing (NLP) techniques to analyze the uploaded documents, including extracting important keywords and phrases, which are then organized into structured data.

[0078] Step 4:

[0079] Based on the analysis results, the server passes the data to a generative artificial intelligence (AI) for training. The AI ​​learns the correspondence between the current state analysis document and the target state document and builds patterns.

[0080] Step 5:

[0081] The user creates a current status analysis document for a new project on their device and uploads it to the system. The document describing the current status and problems of the new system is sent to the server.

[0082] Step 6:

[0083] The server receives a new current state analysis document provided by the user. After receiving the document, it is passed to the AI, which automatically generates a goal state document based on the document.

[0084] Step 7:

[0085] The server displays the goal state document generated by the AI ​​on the user's device, and the user can review the document and modify it as needed using a text editor.

[0086] Step 8:

[0087] After the user has completed modifying the document, he / she saves the final version by clicking the Confirm button. The server saves the user-confirmed goal state document in the database.

[0088] Step 9:

[0089] The server passes the saved final target state document to the next development stage. If necessary, it connects with other development tools and systems to transfer and share data.

[0090] Example 1

[0091] 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."

[0092] Creating current state analysis documents (AS-IS) and target state documents (TO-BE) requires a lot of time and effort, and manual input and analysis is required, leading to problems of input errors and reduced efficiency. It is also not easy to accurately understand the relationships between these documents and then use them to create a new target state. To solve these issues, a system is needed that automates the process of creating documents from current state analysis to the target state, efficiently and accurately.

[0093] 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.

[0094] In this invention, the server includes means for a user to upload a current state analysis document and a goal state document, means for the server to receive the uploaded documents and analyze them using natural language processing technology, means for the server to train a generating artificial intelligence based on the analysis results, means for the generating artificial intelligence to automatically generate a goal state document based on the analysis results, means for the user to check and correct the generated goal state document, and means for the server to save the final goal state document and hand it over to the next development process. This automates the process of creating documents from the current state analysis to the goal state, enabling efficient and accurate document generation.

[0095] "User" refers to a person who accesses the system and uploads, reviews, or modifies documents.

[0096] A "current situation analysis document" refers to a document that describes the current system status and problems.

[0097] "Goal State Document" refers to a document that describes the improved system status or solution.

[0098] "Server" refers to a computer system for receiving, parsing, and storing documents uploaded by users.

[0099] "Natural language processing technology" refers to technology for understanding and analyzing human language.

[0100] "Generative artificial intelligence" refers to an AI model that learns patterns based on analyzed data and automatically generates new target state documents.

[0101] "Means for uploading" refers to a function that allows a user to send a file to a server.

[0102] "Means for receiving documents" refers to the function of the server to receive and store documents sent by users.

[0103] "Means for analyzing documents" refers to the server's ability to use natural language processing technology to analyze the content of uploaded documents and extract important information.

[0104] "Means for generating documents" refers to the function of automatically creating new target state documents based on patterns learned by the generative artificial intelligence.

[0105] "Means for checking and correcting the document" refers to a function that allows a user to check the generated goal state document and make corrections as necessary.

[0106] "Means for saving documents" refers to a function that enables the server to save the final version of the goal state document and pass it on to the next development stage.

[0107] This invention relates to an automatic generation system for current state analysis documents (AS-IS) and target state documents (TO-BE). The system is mainly composed of users, servers, and terminals, and aims to automate document creation in upstream processes.

[0108] System Overview

[0109] The user uploads the current situation analysis document and the target state document to the system using a terminal. The system then receives and analyzes the documents sent to the server. The server trains the generation AI based on the analysis results. This generation AI automatically generates a new target state document based on the analysis results. The user checks and modifies the generated target state document and confirms the final version. The final document is passed on to the next development process, improving the efficiency of the project.

[0110] Hardware and software used

[0111] The system uses the following hardware and software:

[0112] Server: A server with high-performance computing resources is used to receive, analyze, and store documents.

[0113] Terminal: A user device, such as a PC or tablet, that the user uses for access.

[0114] Natural Language Processing techniques: Use Python's NLTK and SpaCy libraries to analyze the content of uploaded documents.

[0115] Generative Artificial Intelligence (AI): Use generative AI models such as OpenAI's GPT series to automatically generate goal state documents.

[0116] How it works

[0117] Users access the system using a terminal and upload current state analysis documents and target state documents for the project. These documents are sent to the server, which receives the uploaded documents and analyzes them using natural language processing techniques such as Python's NLTK and SpaCy. Important keywords and phrases are extracted from the analyzed data, and the relationship between the current state analysis document and the target state document is organized as structured data.

[0118] The server provides the analysis results to a generative artificial intelligence (AI) for training. The AI ​​learns the correspondence between the current state analysis document and the target state document and constructs a generation pattern based on new input. The user inputs a current state analysis document for a new project, and the server uses the AI ​​to automatically generate a target state document based on this. This document describes the new system status and solutions.

[0119] The user checks the generated goal state document and makes any necessary corrections. The corrections are fed back to the generation AI and reflected in the next generation. The final goal state document is saved by the server and passed on to the next development process. The server also connects with other development tools and systems as needed to transfer and share data.

[0120] Specific examples

[0121] For example:

[0122] For Project A

[0123] The user uploads a current state analysis document for Project A. This document describes how the current system requires manual input of customer information, and cites frequent input errors as a problem. The server then uses this information to generate a goal state document. This goal state document describes the introduction of an automatic input system and its benefits, such as reduced input errors.

[0124] The user checks this automatically generated target state document, adds more detailed requirements and conditions, and finalizes the final version. The server then hands over the saved final target state document to the development team, who then proceeds to the next step.

[0125] Example prompts

[0126] Here are some examples of prompts to input to the AI:

[0127] "In the current system, customer information is entered manually, which results in many input errors. As a target state, we will introduce an automatic system for entering customer information, which will reduce input errors. Based on this, please generate a target state document detailing the necessary requirements."

[0128] The above is an embodiment of the present invention.

[0129] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0130] Step 1:

[0131] A user accesses the system using a terminal and uploads a current state analysis document and a target state document.

[0132] Input: Current State Analysis and Target State documents uploaded by the user in PDF or Word file formats.

[0133] Specific operation: The user opens a browser and accesses the system login page. After logging in, he clicks the document upload button, selects the required file, and uploads it to the system.

[0134] Step 2:

[0135] The server receives the uploaded document.

[0136] Input: User-submitted current state analysis document and target state document.

[0137] Output: The document file saved in a specific directory on the server.

[0138] What happens: The server saves the document sent by the user in a specific directory (e.g., " / uploads") and also calculates a checksum to verify the integrity of the file.

[0139] Step 3:

[0140] The server analyzes the received document using natural language processing technology.

[0141] Input: Saved current state analysis document and target state document.

[0142] Output: Keywords and phrases extracted from the parsed documents, organized structured data.

[0143] What it does: The server uses Python's NLTK and SpaCy libraries to parse the document content, extracting important keywords from the text and structuring the data based on context, then generates a data structure for mapping relationships.

[0144] Step 4:

[0145] The server trains the generative artificial intelligence (AI) based on the analysis results.

[0146] Input: Parsed structured data.

[0147] Output: The patterns and production rules learned by the neural network model (e.g., GPT-3).

[0148] Specific operation: The server passes the analysis results to the generation AI and performs the training process. The AI ​​uses the provided data to learn the correspondence between the current state analysis document and the target state document. As a result, a generation pattern is built, allowing it to generate a target state document based on new input.

[0149] Step 5:

[0150] The user inputs a new current situation analysis document.

[0151] Input: A new current situation analysis document (e.g., project current situation information and issues entered into text boxes).

[0152] Output: The new current situation analysis document uploaded or entered.

[0153] What it does: The user enters a current situation analysis document for the new project into the text box or uploads it as a file, which includes the current system status and current issues.

[0154] Step 6:

[0155] The server automatically generates a target state document based on the new current state analysis document.

[0156] Input: The newly provided current situation analysis document.

[0157] Output: An automatically generated goal state document.

[0158] Specific operation: The server receives a new current state analysis document and passes it to the generation AI. The AI ​​automatically generates a goal state document based on the learned patterns. This generation process may include, for example, a system design or improvement plan to solve the current problem.

[0159] Step 7:

[0160] The user reviews and modifies the generated goal state document.

[0161] Input: An automatically generated goal state document.

[0162] Output: A final target state document that reflects the user's confirmation and correction results.

[0163] Specific operation: The server displays the generated goal state document to the user. The user checks the document and makes corrections as necessary. The corrections are sent back to the server and fed back into the AI's learning data.

[0164] Step 8:

[0165] The server saves the final target state document and passes it on to the next development stage.

[0166] Input: The final goal state document as confirmed by the user.

[0167] Output: The final data used in the next development process.

[0168] Specific operation: The server saves the finalized goal state document in a specific directory (e.g., " / final_documents"), and then transfers the file to other development tools or systems as needed to share and integrate data.

[0169] The above is the specific flow of program processing for this system.

[0170] (Application example 1)

[0171] 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."

[0172] The challenges are to reduce the man-hours and time required to create current state analysis information and target state information, and to reduce errors that occur when manually entering information. In particular, factory manufacturing processes require processing large amounts of information and data in real time and quickly deriving the optimal manufacturing process, so these processes need to be automated.

[0173] 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.

[0174] In this invention, the server includes means for a user to input current state analysis information and target state information, means for the server to receive the input information and analyze it using natural language processing technology, means for the server to train a generative machine learning algorithm based on the analysis results, means for the server to receive new current state analysis information from the user and automatically generate new target state information, means for the user to confirm and correct the generated target state information, and means for the server to save the final target state information and hand it over to the next process. This automates the process of creating current state analysis information and target state information, reducing the man-hours and time required for creation and reducing manual input errors.

[0175] "Current status analysis information" is information that describes in detail the current state and problems of a manufacturing process or system.

[0176] "Target state information" is information that describes in detail the ideal system state or solution to be achieved in the future, which is set based on the current situation analysis information.

[0177] An "input device" is any hardware or software that allows a user to provide information to a system.

[0178] A "server" is a computer that provides multiple functions such as receiving, analyzing, storing, and generating information.

[0179] "Natural language processing technology" is a computer technology for analyzing, understanding, and generating human language.

[0180] "Analysis results" include keywords, phrases, and structured data extracted from current analysis information using natural language processing technology.

[0181] A "generative machine learning algorithm" is an algorithm that learns from large amounts of data and automatically generates new information and patterns.

[0182] "Training" is the process by which a generative machine learning algorithm learns from data and improves its accuracy.

[0183] "Automatic generation" is the process by which a system creates new documents or information without human intervention.

[0184] The "next step" is a subsequent work process or procedure in which the generated goal state information is used.

[0185] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The embodiments for carrying out the present invention will be described in detail below.

[0186] System Overview

[0187] The system mainly consists of a user, a server, and a terminal. The user accesses the system using a terminal and inputs current analysis information and target state information. The server receives and analyzes this information, trains the generative machine learning algorithm, and automatically generates new target state information.

[0188] Program Overview

[0189] 1. User input: The user inputs the current situation analysis information into the input device via a terminal. For example, the current situation analysis information may be input such as, "The process of joining part A to part B is being done manually, and each process takes 20 minutes."

[0190] 2. Data Reception and Analysis: The server receives the input current situation analysis information. The received information is analyzed using natural language processing techniques. Specifically, important keywords and phrases are extracted using open source libraries (e.g., spacy and nltk).

[0191] 3. Training a generative machine learning algorithm: The analysis results are fed into a generative machine learning algorithm for training, using an advanced generative model such as OpenAI's GPT-3.

[0192] 4. Automatic generation: When the user inputs new current situation analysis information, the server automatically generates new target state information based on the learned generative machine learning algorithm. The generated target state information might be, for example, "We will aim to reduce time by introducing an automatic joining system."

[0193] 5. Confirmation and Correction: The generated goal state information is provided to the user, who confirms it and makes corrections as necessary.

[0194] 6. Data storage and handover: The final goal state information is stored on the server and passed on to the next process.

[0195] Examples of specific examples and prompts

[0196] For example, if a user enters the following current status information:

[0197] "The process of joining part A to part B is done manually, and it takes 20 minutes per process. I would like to automate this process and reduce the time."

[0198] Example prompts for generative AI models:

[0199] "The process of joining part A to part B is done manually, and it takes 20 minutes per step. I would like to automate this process and reduce the time. Please generate a target state based on this current state."

[0200] In this way, the present invention automates the process of creating current state analysis information and target state information, reducing the number of steps and time required for creation, and reducing manual input errors.

[0201] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0202] Step 1:

[0203] The user uses a terminal to input information for analyzing the current situation. Text data about the current manufacturing process and problems is provided as input. For example, the user might enter information such as, "The process of joining part A to part B is done manually, and each process takes 20 minutes."

[0204] Step 2:

[0205] The terminal sends the entered current situation analysis information to the server. The input data is transferred to the server in text format, and the server receives it. As a result, the current situation analysis information provided by the user is aggregated on the server.

[0206] Step 3:

[0207] The server analyzes the received current situation analysis information using natural language processing technology. Specifically, it uses open source libraries (e.g., spacy and nltk) to tokenize the text data and extract important keywords and phrases. The current situation analysis information is used as input, and the analysis results are obtained as output.

[0208] Step 4:

[0209] The server provides the analysis results to a generative machine learning algorithm to train the algorithm. The analysis results are input as training data, and the generative machine learning algorithm (e.g., OpenAI's GPT-3) learns from them. The output is the algorithm's ability to generate target state information from new data.

[0210] Step 5:

[0211] The user inputs new current situation analysis information from the terminal. The input process is the same as in step 1, and information on new projects and manufacturing processes is provided.

[0212] Step 6:

[0213] The server uses a trained generative machine learning algorithm to automatically generate target state information based on new current situation analysis information. The new current situation analysis information is used as input, and generated target state information is obtained as output. For example, the generated content is "We aim to reduce time by introducing an automatic joining system."

[0214] Step 7:

[0215] The user checks the generated goal state information and corrects it if necessary. The device displays the generated goal state information, and the user checks it and provides feedback. The user's suggestions for correction are added as input, and the information is output as the final goal state information.

[0216] Step 8:

[0217] The server saves the final goal state information and passes it on to the next process. The saved data is used for future reference and for linking with other systems. The finalized goal state information is saved as input, and data that can be applied to the next process is obtained as output.

[0218] Through the above steps, the system creates and automatically generates current state analysis information and target state information, and can optimize the manufacturing process based on the information provided by the user.

[0219] 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.

[0220] The following describes in detail the embodiments of the present invention. The present invention combines an emotion engine that recognizes user emotions with an automatic generation system for current state analysis documents (AS-IS) and goal state documents (TO-BE). This system is primarily composed of users, servers, and terminals, and aims to automate document creation in upstream processes and make adjustments based on emotions.

[0221] System Overview

[0222] The system is configured as follows:

[0223] 1. User Device

[0224] An interface for users to upload current state analysis and target state documents.

[0225] The user inputs a new current situation analysis document and the emotion engine recognizes emotions.

[0226] 2. Server

[0227] It receives documents, analyzes them, trains the AI, and automatically generates and saves goal state documents.

[0228] The emotion engine analyzes the user's emotions and adjusts the system's behavior accordingly.

[0229] 3. Emotion Engine

[0230] Recognize user emotions from user input and uploaded documents.

[0231] Program processing overview

[0232] 1. User uploads a document

[0233] A user logs into the system using a terminal and uploads a current state analysis document and a target state document.

[0234] 2. The server receives and parses the document

[0235] The server receives the uploaded documents and analyzes them using natural language processing techniques, extracting important keywords and phrases and organizing them into structured data.

[0236] 3. The server trains the generative AI based on the analysis results.

[0237] The server provides the analysis results to the AI ​​and performs training. The AI ​​learns the correspondence between the current state analysis document and the target state document and constructs a generation pattern.

[0238] 4. User enters new current situation analysis document

[0239] Users upload a new current situation analysis document or enter it into a text box, and the emotion engine recognizes emotions.

[0240] 5. Emotion engine analyzes emotions

[0241] The emotion engine analyzes the user's input and identifies the user's emotion, and adjustments are made to the goal state document based on the emotion.

[0242] 6. The server automatically generates a target state document based on the new current state analysis document.

[0243] The server receives the new current state analysis document and passes it to the AI. The AI ​​automatically generates a goal state document based on the learned patterns. The analysis results of the emotion engine are also taken into account during generation.

[0244] 7. User reviews and modifies the generated goal state document

[0245] The server displays the generated goal state document on the user's device. The user checks the contents and makes corrections as necessary. The corrections are fed back to the AI.

[0246] 8. The server saves the final target state document and passes it on to the next development stage.

[0247] The server stores the final target state document and passes it on to the next development stage. Data is transferred and shared as needed.

[0248] Specific examples

[0249] Specific examples are shown below.

[0250] For Project A

[0251] A user uploads a current situation analysis document for Project A. This document describes that the current system requires manual entry of customer information, and points out that a problem with this is that input errors are frequent.

[0252] The server generates a goal state document based on this. The generated goal state document describes the introduction of the automatic input system and its benefits, such as reducing input errors.

[0253] If the emotion engine detects stress when the user reviews the document and adds specific requirements, the system displays appropriate support messages to the user, thus reducing the burden on the user and finalizing the document.

[0254] The saved goal state document is passed on to the next development process and implemented by the development team. The introduction of the emotion engine enables flexible responses according to the user's emotional state, improving the system's accuracy and user satisfaction.

[0255] The processing flow will be explained below.

[0256] Step 1:

[0257] The user logs in to the system using a terminal. After logging in, the user selects and uploads the current state analysis document and the target state document from the "Document Upload" section displayed on the main screen.

[0258] Step 2:

[0259] The server receives the uploaded documents and stores them in a specific folder, ready to be passed on to the analysis process.

[0260] Step 3:

[0261] The server uses natural language processing (NLP) techniques to analyze the text of the uploaded document, extracting keywords and phrases and organizing them into structured data, which is then used as input for the subsequent AI learning process.

[0262] Step 4:

[0263] The server provides the analysis results as training data to the generative artificial intelligence (AI). The AI ​​performs training based on the provided data and learns the correspondence between the current state analysis document and the target state document.

[0264] Step 5:

[0265] The user creates a current situation analysis document for a new project on the terminal and enters it into the text box. After completing the input, the user clicks the "Upload" button to send the document to the server.

[0266] Step 6:

[0267] The server receives a newly uploaded current situation analysis document, which describes the current system status and problems.

[0268] Step 7:

[0269] The emotion engine analyzes the newly uploaded current situation analysis document and recognizes the user's emotions. Specifically, it infers the user's emotions (e.g., stress or satisfaction) from the vocabulary and context contained in the text.

[0270] Step 8:

[0271] The server inputs the analyzed current state analysis document into the artificial intelligence generator, which then automatically generates a new target state document. The generation process also takes into account emotional data from the emotion engine.

[0272] Step 9:

[0273] The server displays the AI-generated goal state document on the user's device, and the user can review the document and modify it as needed using a text editor.

[0274] Step 10:

[0275] The user completes the document modification and clicks the Confirm button. The server saves the final target state document confirmed by the user to the database.

[0276] Step 11:

[0277] The server passes the saved final target state document to the next development stage. If necessary, it connects with other development tools and systems to transfer and share data.

[0278] Specific examples

[0279] The user inputs a current situation analysis document for Project B. This document states that "the current system manages inventory manually" and "it is difficult to grasp inventory status in real time." When the server receives and analyzes this document, the emotion engine detects stress from the user's text. As a result, the system generates a goal state document that includes elements such as "introduce an automated inventory management system" and "a low-stress interface." The user reviews this document, makes corrections, and then finalizes the version to move on to the next process.

[0280] Example 2

[0281] 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."

[0282] There are problems with the automation of the creation of current state analysis documents and goal state documents, and the lack of adjustments that take user emotions into account.In addition, there is a lack of a system that can effectively learn and automatically generate correspondences between current state analysis documents and goal state documents.

[0283] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for receiving an uploaded document and analyzing it using natural language processing technology, means for training a machine learning model based on the analysis results, means for receiving a new current situation analysis document and automatically generating a new goal state document, and means for analyzing a user's emotions using emotion recognition technology and reflecting the emotions in the goal state document. This enables automation of document creation and flexible adjustment based on the user's emotions.

[0284] A "current situation analysis document" is a document that details the current status of business operations and systems.

[0285] A "target state document" is a document that details the ideal state of a future business or system.

[0286] "Upload" is the act of a user transferring data or files from a terminal to a server.

[0287] "Natural language processing technology" is a technology that enables computers to understand, analyze, and generate human language.

[0288] "Analysis" is the act of breaking down data or information and understanding its structure and meaning.

[0289] A "machine learning model" is an algorithm that learns patterns and rules from data and makes predictions and classifications.

[0290] "Auto-generation" is the act of a system using specific algorithms to create new data or information without human intervention.

[0291] "Emotion recognition technology" is a technology for identifying emotions from user input and behavior.

[0292] "Storage" is the act of recording data or information for later reference.

[0293] "Next step" refers to the series of tasks or processes that follow the current phase.

[0294] The following describes a specific embodiment of the present invention. The present invention combines a system for automatically generating a current state analysis document and a goal state document with an emotion engine that recognizes the user's emotions. This system consists of a user, a server, and a terminal.

[0295] System Overview

[0296] The system is configured as follows:

[0297] 1. User Device

[0298] Provides an interface for users to upload current state analysis documents and target state documents.

[0299] The user inputs a new current situation analysis document and the emotion engine recognizes emotions.

[0300] 2. Server

[0301] It receives documents, analyzes them, uses AI to learn, and automatically generates and saves goal state documents.

[0302] The emotion engine analyzes the user's emotions and adjusts the system's behavior accordingly.

[0303] Specific software used includes natural language processing libraries "NLTK" and "spaCy," and machine learning libraries "TensorFlow" and "PyTorch."

[0304] 3. Emotion Engine

[0305] The app recognizes user emotions from user input and uploaded documents using IBM Watson Emotion Analysis and Microsoft Azure Emotion API.

[0306] Program processing overview

[0307] Users log in to the system using their terminals and upload their current state analysis document and target state document. The server receives these and analyzes them using natural language processing technology. Important keywords and phrases are extracted and organized as structured data.

[0308] The server provides the analysis results to the AI ​​and performs training. The AI ​​learns the correspondence between the current state analysis document and the target state document and constructs a generation pattern.

[0309] The user inputs a new current state analysis document, and the emotion engine recognizes emotions from this input. The emotion engine analyzes the user's input in real time to identify the user's emotions. Based on the emotions, adjustments are made to the goal state document.

[0310] The server receives the new current state analysis document and passes it to the AI. The AI ​​automatically generates a goal state document based on the learned patterns. The analysis results of the emotion engine are also taken into account when generating the document.

[0311] The server displays the generated goal state document on the user's device. The user checks the contents and makes corrections as necessary. The corrections are fed back to the AI.

[0312] The server saves the final target state document and passes it on to the next process, transferring and sharing data as needed.

[0313] Specific examples

[0314] For Project A

[0315] The user uploads a current state analysis document for Project A. This document describes the current situation where customer information is manually entered, resulting in frequent input errors. The server performs analysis based on this and generates a target state document. The generated target state document describes the introduction of an automatic input system and its benefits, which include reducing input errors.

[0316] If the emotion engine detects stress in the user as they review this document and add specific requests, the system will display a support message to the user, such as "Would you like some tips to help you with this task?"

[0317] The saved goal state document is passed on to the next process and implemented by the development team. The introduction of the emotion engine enables flexible responses according to the user's emotional state, improving the system's accuracy and user satisfaction.

[0318] Prompt Sentence Examples

[0319] "I have uploaded a current situation analysis document for Project A. It states that frequent input errors are a problem with the current manual data entry system. Please generate a target state document based on this. In the generated document, please state the introduction of an automated data entry system and its benefits, such as reducing input errors."

[0320] The above is a specific embodiment for carrying out the invention.

[0321] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0322] Step 1:

[0323] A user uploads a document

[0324] The user logs into the system using a terminal and selects the current state analysis document (AS-IS) and the target state document (TO-BE) in the document upload section through the web interface. Then, he clicks the "Upload" button to send these documents to the server. The current state analysis document and the target state document are the inputs, and these are sent to the server as the outputs.

[0325] Step 2:

[0326] The server receives and parses the document

[0327] The server receives documents uploaded by users. These documents are then analyzed using natural language processing (NLP) techniques. Specifically, the Python natural language processing libraries "NLTK" and "spaCy" are used to tokenize the text, extract keywords, and perform noun phrase analysis. The input is the uploaded document, and the output is structured data with keywords and important phrases extracted.

[0328] Step 3:

[0329] The server trains the generative AI based on the analysis results.

[0330] The server trains a machine learning model based on the structured data obtained through the analysis. During this process, the analysis results are provided to the AI ​​model using libraries such as TensorFlow and PyTorch for training. The input is the structured data from the analysis results, and the output is an AI model that has learned the correspondence between the current state analysis document and the target state document.

[0331] Step 4:

[0332] User enters a new current situation analysis document

[0333] The user uploads a new current situation analysis document through the system's input interface or enters it directly into a text box. The emotion engine analyzes the emotions in real time based on this input. The input is the new current situation analysis document, and the output is emotion data.

[0334] Step 5:

[0335] Emotion engine analyzes emotions

[0336] The emotion engine analyzes the user's input and identifies emotions. This analysis is performed using IBM Watson Emotion Analysis and Microsoft Azure Emotion API. Specifically, it sends text data to the API and analyzes the returned emotion data. The input is the user's text data, and the output is analyzed emotion data.

[0337] Step 6:

[0338] The server automatically generates a target state document based on the new current state analysis document.

[0339] The server passes the newly received current situation analysis document and the analysis results of the emotion engine to the AI ​​model, which then automatically generates a target state document. Using an AI model (e.g., GPT-4), the server generates a target state document that takes into account the content of the current situation analysis document and the user's emotions. The input is the new current situation analysis document and emotion data, and the output is an automatically generated target state document.

[0340] Step 7:

[0341] User reviews and modifies the generated goal state document

[0342] The server displays the generated goal state document on the user's device. The user checks the contents and makes any necessary corrections. The corrections are sent back to the server and fed back to the AI ​​model. The input is the generated goal state document and the user's corrections, and the output is the final goal state document.

[0343] Step 8:

[0344] The server saves the final goal state document and passes it on to the next process.

[0345] The server securely stores the final modified target state document. The saved document is kept in a format that can be freely used for the next process, for example, for the progress of a development project. The input is the final target state document, and the output is the saved document.

[0346] (Application example 2)

[0347] 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."

[0348] Current document creation systems simply generate and manage documents without considering the user's emotions, which means they are unable to reduce user stress and dissatisfaction. Furthermore, even in virtual stores, there is a lack of technology to analyze customer emotions in real time and respond accordingly, limiting the improvement of customer experience.

[0349] 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.

[0350] In this invention, the server includes a means for recognizing a user's emotions and providing suggestions and support based on the emotions, a means for analyzing the user's emotions in the virtual store and providing product suggestions and support messages according to the emotions, and a means for receiving and analyzing documents uploaded by the server. This enables flexible responses according to the user's emotional state, improving the accuracy of the system, user satisfaction, and the customer experience in the virtual store.

[0351] A "user" is a person who uses the system to upload, review, and modify current state analysis and / or target state documents.

[0352] The "server" is a device that receives uploaded documents, analyzes them, and performs artificial intelligence learning, automatic generation of new goal state documents, and even emotion recognition.

[0353] A "current situation analysis document" is a document that analyzes and describes the current situation and problems.

[0354] A "goal state document" is a document that describes a desired future state or goal.

[0355] "Emotion recognition" is a technology that analyzes a user's facial expressions, tone of voice, and text to identify the user's emotions.

[0356] A "virtual store" is a simulation of a store that operates on the Internet and allows users to browse and purchase products in a virtual environment.

[0357] "Product suggestion" is the act of recommending a specific product based on the user's interests and emotional state.

[0358] "Support messages" are messages that are displayed to the user for hints or assistance.

[0359] "Analysis results" are data or information obtained as a result of the server analyzing a document.

[0360] "Automatic generation" is the process by which a system uses AI technology to automatically create documents and data without manual intervention.

[0361] "Training" is the process by which the server trains the artificial intelligence based on the analysis results and improves its performance.

[0362] "Flexible response" refers to the ability of the system to adapt its behavior according to the user's emotions and circumstances.

[0363] The present invention combines an emotion engine that recognizes a user's emotions with a system for automatically generating a current state analysis document and a goal state document, and particularly provides an example of application to a virtual store.

[0364] System Configuration

[0365] The system consists of several main components:

[0366] 1. User Device

[0367] Users use devices such as smart glasses or head-mounted displays, equipped with emotion-recognition cameras and sensors.

[0368] This allows the system to sense the user's facial expressions and tone of voice in real time and transmit them as emotional data to the server.

[0369] 2. Server

[0370] The server receives the uploaded current state analysis document and target state document and analyzes them using natural language processing techniques.

[0371] The AI ​​model learns based on important keywords and phrases extracted through analysis.

[0372] By incorporating the analysis results of the user's emotions by the emotion engine, the generated goal state document is adjusted according to the user's emotions.

[0373] 3. Emotion Engine

[0374] Analyzes emotions from the user's facial expressions, tone of voice, and input text.

[0375] The analysis results are sent to the server and reflected in the document generation process and product suggestions in the virtual store.

[0376] 4. Virtual Store

[0377] The virtual store system provides appropriate product suggestions and support messages based on emotion recognition results when users browse and purchase products in a virtual space.

[0378] If the user's stress or discomfort is detected, the system will display suggestions for relaxing products and support messages.

[0379] Program processing overview

[0380] 1. Emotion recognition

[0381] The emotion engine detects and analyzes facial expressions and tone of voice through cameras and sensors installed on the user's device, using software such as OpenCV, TensorFlow, and Keras.

[0382] 2. Document Analysis and Generation

[0383] Using conventional natural language processing techniques, the current state analysis document and the target state document are analyzed and trained into an AI model. Here, key data processing techniques such as keyword extraction and phrase analysis are performed.

[0384] 3. Emotion-Based Adjustment

[0385] The server adjusts the goal state document based on the emotion analysis data provided by the emotion engine. Specifically, if the user is feeling stressed, the server displays a support message and adjusts the goal state document accordingly.

[0386] Specific examples

[0387] If a user feels "stressed" while browsing a specific product in a virtual store, the system will suggest relaxing products or play music. For example, if the emotion analysis results indicate "stress," the system will suggest "play relaxing music" or display a "discount coupon for your next purchase."

[0388] Prompt Sentence Examples

[0389] If a user is experiencing frustration while viewing the details of a particular product:

[0390] Product category: relaxation-related items

[0391] Recommended products include aroma diffusers, relaxing music CDs, and stress balls.

[0392] Message to display: 10% off coupon for your next purchase

[0393] Music to play: Classical music

[0394] The present invention enables flexible responses that are in line with the user's emotional state, contributing to improved system accuracy and user satisfaction. In particular, it is expected to significantly improve the customer experience in virtual stores.

[0395] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0396] Step 1:

[0397] Provide a means for users to upload current state analysis documents and target state documents.

[0398] Input: The user provides the current state analysis document and the target state document to the system through a file upload interface.

[0399] Output: The uploaded document is sent to the server.

[0400] Specific operation: The user operates the interface in the virtual store, selects a document, and presses the upload button. The server receives the document and stores it in the database.

[0401] Step 2:

[0402] The server receives and parses the uploaded document.

[0403] Inputs: Uploaded current state analysis document and target state document.

[0404] Output: Structured data that analyzes the document, especially extracting important keywords and phrases.

[0405] What it does: The server uses natural language processing techniques (e.g., NLTK or spaCy) to analyze the text in the document and extract keywords and related phrases.

[0406] Step 3:

[0407] The server trains the AI ​​model based on the analysis results.

[0408] Input: Document analysis results, keywords and phrases.

[0409] Output: A trained AI model.

[0410] How it works: The server feeds the extracted keywords and phrases to the AI ​​model and trains it using a machine learning algorithm (e.g., TensorFlow or PyTorch). The model learns the correspondence between the current state analysis document and the goal state document.

[0411] Step 4:

[0412] The user inputs a new current situation analysis document.

[0413] Input: The new current situation analysis document entered by the user.

[0414] Output: A new current situation analysis document sent to the server.

[0415] Specific operation: The user uses the text box in the virtual store to input a new current situation analysis document, and the input is sent to the server in real time.

[0416] Step 5:

[0417] The emotion engine recognizes emotions from user input and uploaded documents.

[0418] Input: User text input and uploaded documents.

[0419] Output: The user's emotional state (e.g., stress, joy, frustration).

[0420] Specific operation: An emotion engine (using, for example, OpenCV or Keras) analyzes the user's input text and facial expressions captured by the camera to identify emotions.

[0421] Step 6:

[0422] The server automatically generates a target state document based on the new current state analysis document.

[0423] Input: New current situation analysis document, sentiment engine analysis results, trained AI model.

[0424] Output: A goal state document.

[0425] Specific operation: The server inputs a new current situation analysis document into the AI ​​model, and then automatically generates an optimal target state document, taking into account the analysis results of the emotion engine.

[0426] Step 7:

[0427] The user reviews and modifies the generated goal state document.

[0428] Input: Generated goal state document, user review and revision.

[0429] Output: The revised goal state document.

[0430] Specific operation: The user reviews the generated goal state document and enters corrections as needed. This feedback is sent to the server, and the AI ​​model is updated.

[0431] Step 8:

[0432] The server saves the final target state document and passes it on to the next development stage.

[0433] Input: The modified goal state document.

[0434] Output: Final goal state document.

[0435] Specific operation: The server saves the final modified target state document, exports it in the format required for the next development phase, and shares it with other systems as needed.

[0436] 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.

[0437] 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.

[0438] 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.

[0439] [Second embodiment]

[0440] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0441] 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.

[0442] 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).

[0443] 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.

[0444] 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.

[0445] 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).

[0446] 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.

[0447] 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.

[0448] 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.

[0449] 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.

[0450] 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.

[0451] 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."

[0452] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments of the present invention will be described in detail.

[0453] System Overview

[0454] This invention relates to an automatic generation system for current state analysis documents (AS-IS) and target state documents (TO-BE). The system is mainly composed of users, servers, and terminals, and aims to automate document creation in upstream processes.

[0455] Program processing overview

[0456] 1. User uploads a document

[0457] Users access the system using a terminal and upload current state analysis and target state documents for the project, which are then sent to the server.

[0458] 2. The server receives and parses the document

[0459] The server receives documents uploaded by users.

[0460] The server analyzes the received document using natural language processing technology, extracting important keywords and phrases and organizing the relationship between the current state analysis document and the target state document as structured data.

[0461] 3. The server trains the generative AI based on the analysis results.

[0462] The server provides the analysis results to the generative artificial intelligence (AI) and trains it based on them. The AI ​​learns the correspondence between the current state analysis document and the target state document and constructs a generative pattern based on new input.

[0463] 4. User enters new current situation analysis document

[0464] Users can upload or enter a text box for a current situation analysis document for a new project, which describes the current system status and issues.

[0465] 5. The server automatically generates a target state document based on the new current state analysis document.

[0466] The server receives a new current situation analysis document provided by the user and passes it to the generating artificial intelligence.

[0467] Based on learned patterns, generative AI automatically generates goal state documents that describe new system states and solutions.

[0468] 6. User reviews and modifies the generated goal state document

[0469] The server displays the generated goal state document to the user, who can review it and make corrections as necessary.

[0470] The user's modifications are fed back to the generation AI and reflected in the next generation.

[0471] 7. The server saves the final target state document and passes it on to the next development stage.

[0472] The server stores the final target state document confirmed by the user, and this stored data is passed on to the next development stage.

[0473] If necessary, the server will work with other development tools and systems to transfer and share data.

[0474] Specific examples

[0475] Specific examples are shown below.

[0476] For Project A

[0477] A user uploads a current situation analysis document for Project A. This document describes that the current system requires manual entry of customer information, and points out that a problem with this is that input errors are frequent.

[0478] The server generates a goal state document based on this. This goal state document describes the introduction of the automatic input system and its benefits, such as reducing input errors.

[0479] The user checks this automatically generated target state document, adds more detailed requirements and conditions, and finalizes the final version. The server saves it and hands it over to the development team to proceed to the next stage.

[0480] Effect of the invention

[0481] This system automates the process of documenting the current state and the target state, reducing the amount of work required. It also reduces manual input errors and improves work efficiency in upstream processes. As a result, it is expected to improve the efficiency and productivity of the entire system development process.

[0482] The processing flow will be explained below.

[0483] Step 1:

[0484] The user logs into the system using a terminal. After logging in, the user goes to the "Document Upload" section on the main screen, selects the current state analysis document (AS-IS) and the target state document (TO-BE), and uploads them.

[0485] Step 2:

[0486] The server receives the documents uploaded by the user, stores them in a specific folder, and prepares them for analysis.

[0487] Step 3:

[0488] The server uses natural language processing (NLP) techniques to analyze the uploaded documents, including extracting important keywords and phrases, which are then organized into structured data.

[0489] Step 4:

[0490] Based on the analysis results, the server passes the data to a generative artificial intelligence (AI) for training. The AI ​​learns the correspondence between the current state analysis document and the target state document and builds patterns.

[0491] Step 5:

[0492] The user creates a current status analysis document for a new project on their device and uploads it to the system. The document describing the current status and problems of the new system is sent to the server.

[0493] Step 6:

[0494] The server receives a new current state analysis document provided by the user. After receiving the document, it is passed to the AI, which automatically generates a goal state document based on the document.

[0495] Step 7:

[0496] The server displays the goal state document generated by the AI ​​on the user's device, and the user can review the document and modify it as needed using a text editor.

[0497] Step 8:

[0498] After the user has completed modifying the document, he / she saves the final version by clicking the Confirm button. The server saves the user-confirmed goal state document in the database.

[0499] Step 9:

[0500] The server passes the saved final target state document to the next development stage. If necessary, it connects with other development tools and systems to transfer and share data.

[0501] Example 1

[0502] 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."

[0503] Creating current state analysis documents (AS-IS) and target state documents (TO-BE) requires a lot of time and effort, and manual input and analysis is required, leading to problems of input errors and reduced efficiency. It is also not easy to accurately understand the relationships between these documents and then use them to create a new target state. To solve these issues, a system is needed that automates the process of creating documents from current state analysis to the target state, efficiently and accurately.

[0504] 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.

[0505] In this invention, the server includes means for a user to upload a current state analysis document and a goal state document, means for the server to receive the uploaded documents and analyze them using natural language processing technology, means for the server to train a generating artificial intelligence based on the analysis results, means for the generating artificial intelligence to automatically generate a goal state document based on the analysis results, means for the user to check and correct the generated goal state document, and means for the server to save the final goal state document and hand it over to the next development process. This automates the process of creating documents from the current state analysis to the goal state, enabling efficient and accurate document generation.

[0506] "User" refers to a person who accesses the system and uploads, reviews, or modifies documents.

[0507] A "current situation analysis document" refers to a document that describes the current system status and problems.

[0508] "Goal State Document" refers to a document that describes the improved system status or solution.

[0509] "Server" refers to a computer system for receiving, parsing, and storing documents uploaded by users.

[0510] "Natural language processing technology" refers to technology for understanding and analyzing human language.

[0511] "Generative artificial intelligence" refers to an AI model that learns patterns based on analyzed data and automatically generates new target state documents.

[0512] "Means for uploading" refers to a function that allows a user to send a file to a server.

[0513] "Means for receiving documents" refers to the function of the server to receive and store documents sent by users.

[0514] "Means for analyzing documents" refers to the server's ability to use natural language processing technology to analyze the content of uploaded documents and extract important information.

[0515] "Means for generating documents" refers to the function of automatically creating new target state documents based on patterns learned by the generative artificial intelligence.

[0516] "Means for checking and correcting the document" refers to a function that allows a user to check the generated goal state document and make corrections as necessary.

[0517] "Means for saving documents" refers to a function that enables the server to save the final version of the goal state document and pass it on to the next development stage.

[0518] This invention relates to an automatic generation system for current state analysis documents (AS-IS) and target state documents (TO-BE). The system is mainly composed of users, servers, and terminals, and aims to automate document creation in upstream processes.

[0519] System Overview

[0520] The user uploads the current situation analysis document and the target state document to the system using a terminal. The system then receives and analyzes the documents sent to the server. The server trains the generation AI based on the analysis results. This generation AI automatically generates a new target state document based on the analysis results. The user checks and modifies the generated target state document and confirms the final version. The final document is passed on to the next development process, improving the efficiency of the project.

[0521] Hardware and software used

[0522] The system uses the following hardware and software:

[0523] Server: A server with high-performance computing resources is used to receive, analyze, and store documents.

[0524] Terminal: A user device, such as a PC or tablet, that the user uses for access.

[0525] Natural Language Processing techniques: Use Python's NLTK and SpaCy libraries to analyze the content of uploaded documents.

[0526] Generative Artificial Intelligence (AI): Use generative AI models such as OpenAI's GPT series to automatically generate goal state documents.

[0527] How it works

[0528] Users access the system using a terminal and upload current state analysis documents and target state documents for the project. These documents are sent to the server, which receives the uploaded documents and analyzes them using natural language processing techniques such as Python's NLTK and SpaCy. Important keywords and phrases are extracted from the analyzed data, and the relationship between the current state analysis document and the target state document is organized as structured data.

[0529] The server provides the analysis results to a generative artificial intelligence (AI) for training. The AI ​​learns the correspondence between the current state analysis document and the target state document and constructs a generation pattern based on new input. The user inputs a current state analysis document for a new project, and the server uses the AI ​​to automatically generate a target state document based on this. This document describes the new system status and solutions.

[0530] The user checks the generated goal state document and makes any necessary corrections. The corrections are fed back to the generation AI and reflected in the next generation. The final goal state document is saved by the server and passed on to the next development process. The server also connects with other development tools and systems as needed to transfer and share data.

[0531] Specific examples

[0532] For example:

[0533] For Project A

[0534] The user uploads a current state analysis document for Project A. This document describes how the current system requires manual input of customer information, and cites frequent input errors as a problem. The server then uses this information to generate a goal state document. This goal state document describes the introduction of an automatic input system and its benefits, such as reduced input errors.

[0535] The user checks this automatically generated target state document, adds more detailed requirements and conditions, and finalizes the final version. The server then hands over the saved final target state document to the development team, who then proceeds to the next step.

[0536] Example prompts

[0537] Here are some examples of prompts to input to the AI:

[0538] "In the current system, customer information is entered manually, which results in many input errors. As a target state, we will introduce an automatic system for entering customer information, which will reduce input errors. Based on this, please generate a target state document detailing the necessary requirements."

[0539] The above is an embodiment of the present invention.

[0540] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0541] Step 1:

[0542] A user accesses the system using a terminal and uploads a current state analysis document and a target state document.

[0543] Input: Current State Analysis and Target State documents uploaded by the user in PDF or Word file formats.

[0544] Specific operation: The user opens a browser and accesses the system login page. After logging in, he clicks the document upload button, selects the required file, and uploads it to the system.

[0545] Step 2:

[0546] The server receives the uploaded document.

[0547] Input: User-submitted current state analysis document and target state document.

[0548] Output: The document file saved in a specific directory on the server.

[0549] What happens: The server saves the document sent by the user in a specific directory (e.g., " / uploads") and also calculates a checksum to verify the integrity of the file.

[0550] Step 3:

[0551] The server analyzes the received document using natural language processing technology.

[0552] Input: Saved current state analysis document and target state document.

[0553] Output: Keywords and phrases extracted from the parsed documents, organized structured data.

[0554] What it does: The server uses Python's NLTK and SpaCy libraries to parse the document content, extracting important keywords from the text and structuring the data based on context, then generates a data structure for mapping relationships.

[0555] Step 4:

[0556] The server trains the generative artificial intelligence (AI) based on the analysis results.

[0557] Input: Parsed structured data.

[0558] Output: The patterns and production rules learned by the neural network model (e.g., GPT-3).

[0559] Specific operation: The server passes the analysis results to the generation AI and performs the training process. The AI ​​uses the provided data to learn the correspondence between the current state analysis document and the target state document. As a result, a generation pattern is built, allowing it to generate a target state document based on new input.

[0560] Step 5:

[0561] The user inputs a new current situation analysis document.

[0562] Input: A new current situation analysis document (e.g., project current situation information and issues entered into text boxes).

[0563] Output: The new current situation analysis document uploaded or entered.

[0564] What it does: The user enters a current situation analysis document for the new project into the text box or uploads it as a file, which includes the current system status and current issues.

[0565] Step 6:

[0566] The server automatically generates a target state document based on the new current state analysis document.

[0567] Input: The newly provided current situation analysis document.

[0568] Output: An automatically generated goal state document.

[0569] Specific operation: The server receives a new current state analysis document and passes it to the generation AI. The AI ​​automatically generates a goal state document based on the learned patterns. This generation process may include, for example, a system design or improvement plan to solve the current problem.

[0570] Step 7:

[0571] The user reviews and modifies the generated goal state document.

[0572] Input: An automatically generated goal state document.

[0573] Output: A final target state document that reflects the user's confirmation and correction results.

[0574] Specific operation: The server displays the generated goal state document to the user. The user checks the document and makes corrections as necessary. The corrections are sent back to the server and fed back into the AI's learning data.

[0575] Step 8:

[0576] The server saves the final target state document and passes it on to the next development stage.

[0577] Input: The final goal state document as confirmed by the user.

[0578] Output: The final data used in the next development process.

[0579] Specific operation: The server saves the finalized goal state document in a specific directory (e.g., " / final_documents"), and then transfers the file to other development tools or systems as needed to share and integrate data.

[0580] The above is the specific flow of program processing for this system.

[0581] (Application example 1)

[0582] 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."

[0583] The challenges are to reduce the man-hours and time required to create current state analysis information and target state information, and to reduce errors that occur when manually entering information. In particular, factory manufacturing processes require processing large amounts of information and data in real time and quickly deriving the optimal manufacturing process, so these processes need to be automated.

[0584] 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.

[0585] In this invention, the server includes means for a user to input current state analysis information and target state information, means for the server to receive the input information and analyze it using natural language processing technology, means for the server to train a generative machine learning algorithm based on the analysis results, means for the server to receive new current state analysis information from the user and automatically generate new target state information, means for the user to confirm and correct the generated target state information, and means for the server to save the final target state information and hand it over to the next process. This automates the process of creating current state analysis information and target state information, reducing the man-hours and time required for creation and reducing manual input errors.

[0586] "Current status analysis information" is information that describes in detail the current state and problems of a manufacturing process or system.

[0587] "Target state information" is information that describes in detail the ideal system state or solution to be achieved in the future, which is set based on the current situation analysis information.

[0588] An "input device" is any hardware or software that allows a user to provide information to a system.

[0589] A "server" is a computer that provides multiple functions such as receiving, analyzing, storing, and generating information.

[0590] "Natural language processing technology" is a computer technology for analyzing, understanding, and generating human language.

[0591] "Analysis results" include keywords, phrases, and structured data extracted from current analysis information using natural language processing technology.

[0592] A "generative machine learning algorithm" is an algorithm that learns from large amounts of data and automatically generates new information and patterns.

[0593] "Training" is the process by which a generative machine learning algorithm learns from data and improves its accuracy.

[0594] "Automatic generation" is the process by which a system creates new documents or information without human intervention.

[0595] The "next step" is a subsequent work process or procedure in which the generated goal state information is used.

[0596] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The embodiments for carrying out the present invention will be described in detail below.

[0597] System Overview

[0598] The system mainly consists of a user, a server, and a terminal. The user accesses the system using a terminal and inputs current analysis information and target state information. The server receives and analyzes this information, trains the generative machine learning algorithm, and automatically generates new target state information.

[0599] Program Overview

[0600] 1. User input: The user inputs the current situation analysis information into the input device via a terminal. For example, the current situation analysis information may be input such as, "The process of joining part A to part B is being done manually, and each process takes 20 minutes."

[0601] 2. Data Reception and Analysis: The server receives the input current situation analysis information. The received information is analyzed using natural language processing techniques. Specifically, important keywords and phrases are extracted using open source libraries (e.g., spacy and nltk).

[0602] 3. Training a generative machine learning algorithm: The analysis results are fed into a generative machine learning algorithm for training, using an advanced generative model such as OpenAI's GPT-3.

[0603] 4. Automatic generation: When the user inputs new current situation analysis information, the server automatically generates new target state information based on the learned generative machine learning algorithm. The generated target state information might be, for example, "We will aim to reduce time by introducing an automatic joining system."

[0604] 5. Confirmation and Correction: The generated goal state information is provided to the user, who confirms it and makes corrections as necessary.

[0605] 6. Data storage and handover: The final goal state information is stored on the server and passed on to the next process.

[0606] Examples of specific examples and prompts

[0607] For example, if a user enters the following current status information:

[0608] "The process of joining part A to part B is done manually, and it takes 20 minutes per process. I would like to automate this process and reduce the time."

[0609] Example prompts for generative AI models:

[0610] "The process of joining part A to part B is done manually, and it takes 20 minutes per step. I would like to automate this process and reduce the time. Please generate a target state based on this current state."

[0611] In this way, the present invention automates the process of creating current state analysis information and target state information, reducing the number of steps and time required for creation, and reducing manual input errors.

[0612] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0613] Step 1:

[0614] The user uses a terminal to input information for analyzing the current situation. Text data about the current manufacturing process and problems is provided as input. For example, the user might enter information such as, "The process of joining part A to part B is done manually, and each process takes 20 minutes."

[0615] Step 2:

[0616] The terminal sends the entered current situation analysis information to the server. The input data is transferred to the server in text format, and the server receives it. As a result, the current situation analysis information provided by the user is aggregated on the server.

[0617] Step 3:

[0618] The server analyzes the received current situation analysis information using natural language processing technology. Specifically, it uses open source libraries (e.g., spacy and nltk) to tokenize the text data and extract important keywords and phrases. The current situation analysis information is used as input, and the analysis results are obtained as output.

[0619] Step 4:

[0620] The server provides the analysis results to a generative machine learning algorithm to train the algorithm. The analysis results are input as training data, and the generative machine learning algorithm (e.g., OpenAI's GPT-3) learns from them. The output is the algorithm's ability to generate target state information from new data.

[0621] Step 5:

[0622] The user inputs new current situation analysis information from the terminal. The input process is the same as in step 1, and information on new projects and manufacturing processes is provided.

[0623] Step 6:

[0624] The server uses a trained generative machine learning algorithm to automatically generate target state information based on new current situation analysis information. The new current situation analysis information is used as input, and generated target state information is obtained as output. For example, the generated content is "We aim to reduce time by introducing an automatic joining system."

[0625] Step 7:

[0626] The user checks the generated goal state information and corrects it if necessary. The device displays the generated goal state information, and the user checks it and provides feedback. The user's suggestions for correction are added as input, and the information is output as the final goal state information.

[0627] Step 8:

[0628] The server saves the final goal state information and passes it on to the next process. The saved data is used for future reference and for linking with other systems. The finalized goal state information is saved as input, and data that can be applied to the next process is obtained as output.

[0629] Through the above steps, the system creates and automatically generates current state analysis information and target state information, and can optimize the manufacturing process based on the information provided by the user.

[0630] 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.

[0631] The following describes in detail the embodiments of the present invention. The present invention combines an emotion engine that recognizes user emotions with an automatic generation system for current state analysis documents (AS-IS) and goal state documents (TO-BE). This system is primarily composed of users, servers, and terminals, and aims to automate document creation in upstream processes and make adjustments based on emotions.

[0632] System Overview

[0633] The system is configured as follows:

[0634] 1. User Device

[0635] An interface for users to upload current state analysis and target state documents.

[0636] The user inputs a new current situation analysis document and the emotion engine recognizes emotions.

[0637] 2. Server

[0638] It receives documents, analyzes them, trains the AI, and automatically generates and saves goal state documents.

[0639] The emotion engine analyzes the user's emotions and adjusts the system's behavior accordingly.

[0640] 3. Emotion Engine

[0641] Recognize user emotions from user input and uploaded documents.

[0642] Program processing overview

[0643] 1. User uploads a document

[0644] A user logs into the system using a terminal and uploads a current state analysis document and a target state document.

[0645] 2. The server receives and parses the document

[0646] The server receives the uploaded documents and analyzes them using natural language processing techniques, extracting important keywords and phrases and organizing them into structured data.

[0647] 3. The server trains the generative AI based on the analysis results.

[0648] The server provides the analysis results to the AI ​​and performs training. The AI ​​learns the correspondence between the current state analysis document and the target state document and constructs a generation pattern.

[0649] 4. User enters new current situation analysis document

[0650] Users upload a new current situation analysis document or enter it into a text box, and the emotion engine recognizes emotions.

[0651] 5. Emotion engine analyzes emotions

[0652] The emotion engine analyzes the user's input and identifies the user's emotion, and adjustments are made to the goal state document based on the emotion.

[0653] 6. The server automatically generates a target state document based on the new current state analysis document.

[0654] The server receives the new current state analysis document and passes it to the AI. The AI ​​automatically generates a goal state document based on the learned patterns. The analysis results of the emotion engine are also taken into account during generation.

[0655] 7. User reviews and modifies the generated goal state document

[0656] The server displays the generated goal state document on the user's device. The user checks the contents and makes corrections as necessary. The corrections are fed back to the AI.

[0657] 8. The server saves the final target state document and passes it on to the next development stage.

[0658] The server stores the final target state document and passes it on to the next development stage. Data is transferred and shared as needed.

[0659] Specific examples

[0660] Specific examples are shown below.

[0661] For Project A

[0662] A user uploads a current situation analysis document for Project A. This document describes that the current system requires manual entry of customer information, and points out that a problem with this is that input errors are frequent.

[0663] The server generates a goal state document based on this. The generated goal state document describes the introduction of the automatic input system and its benefits, such as reducing input errors.

[0664] If the emotion engine detects stress when the user reviews the document and adds specific requirements, the system displays appropriate support messages to the user, thus reducing the burden on the user and finalizing the document.

[0665] The saved goal state document is passed on to the next development process and implemented by the development team. The introduction of the emotion engine enables flexible responses according to the user's emotional state, improving the system's accuracy and user satisfaction.

[0666] The processing flow will be explained below.

[0667] Step 1:

[0668] The user logs in to the system using a terminal. After logging in, the user selects and uploads the current state analysis document and the target state document from the "Document Upload" section displayed on the main screen.

[0669] Step 2:

[0670] The server receives the uploaded documents and stores them in a specific folder, ready to be passed on to the analysis process.

[0671] Step 3:

[0672] The server uses natural language processing (NLP) techniques to analyze the text of the uploaded document, extracting keywords and phrases and organizing them into structured data, which is then used as input for the subsequent AI learning process.

[0673] Step 4:

[0674] The server provides the analysis results as training data to the generative artificial intelligence (AI). The AI ​​performs training based on the provided data and learns the correspondence between the current state analysis document and the target state document.

[0675] Step 5:

[0676] The user creates a current situation analysis document for a new project on the terminal and enters it into the text box. After completing the input, the user clicks the "Upload" button to send the document to the server.

[0677] Step 6:

[0678] The server receives a newly uploaded current situation analysis document, which describes the current system status and problems.

[0679] Step 7:

[0680] The emotion engine analyzes the newly uploaded current situation analysis document and recognizes the user's emotions. Specifically, it infers the user's emotions (e.g., stress or satisfaction) from the vocabulary and context contained in the text.

[0681] Step 8:

[0682] The server inputs the analyzed current state analysis document into the artificial intelligence generator, which then automatically generates a new target state document. The generation process also takes into account emotional data from the emotion engine.

[0683] Step 9:

[0684] The server displays the AI-generated goal state document on the user's device, and the user can review the document and modify it as needed using a text editor.

[0685] Step 10:

[0686] The user completes the document modification and clicks the Confirm button. The server saves the final target state document confirmed by the user to the database.

[0687] Step 11:

[0688] The server passes the saved final target state document to the next development stage. If necessary, it connects with other development tools and systems to transfer and share data.

[0689] Specific examples

[0690] The user inputs a current situation analysis document for Project B. This document states that "the current system manages inventory manually" and "it is difficult to grasp inventory status in real time." When the server receives and analyzes this document, the emotion engine detects stress from the user's text. As a result, the system generates a goal state document that includes elements such as "introduce an automated inventory management system" and "a low-stress interface." The user reviews this document, makes corrections, and then finalizes the version to move on to the next process.

[0691] Example 2

[0692] 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."

[0693] There are problems with the automation of the creation of current state analysis documents and goal state documents, and the lack of adjustments that take user emotions into account.In addition, there is a lack of a system that can effectively learn and automatically generate correspondences between current state analysis documents and goal state documents.

[0694] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for receiving an uploaded document and analyzing it using natural language processing technology, means for training a machine learning model based on the analysis results, means for receiving a new current situation analysis document and automatically generating a new goal state document, and means for analyzing a user's emotions using emotion recognition technology and reflecting the emotions in the goal state document. This enables automation of document creation and flexible adjustment based on the user's emotions.

[0695] A "current situation analysis document" is a document that details the current status of business operations and systems.

[0696] A "target state document" is a document that details the ideal state of a future business or system.

[0697] "Upload" is the act of a user transferring data or files from a terminal to a server.

[0698] "Natural language processing technology" is a technology that enables computers to understand, analyze, and generate human language.

[0699] "Analysis" is the act of breaking down data or information and understanding its structure and meaning.

[0700] A "machine learning model" is an algorithm that learns patterns and rules from data and makes predictions and classifications.

[0701] "Auto-generation" is the act of a system using specific algorithms to create new data or information without human intervention.

[0702] "Emotion recognition technology" is a technology for identifying emotions from user input and behavior.

[0703] "Storage" is the act of recording data or information for later reference.

[0704] "Next step" refers to the series of tasks or processes that follow the current phase.

[0705] The following describes a specific embodiment of the present invention. The present invention combines a system for automatically generating a current state analysis document and a goal state document with an emotion engine that recognizes the user's emotions. This system consists of a user, a server, and a terminal.

[0706] System Overview

[0707] The system is configured as follows:

[0708] 1. User Device

[0709] Provides an interface for users to upload current state analysis documents and target state documents.

[0710] The user inputs a new current situation analysis document and the emotion engine recognizes emotions.

[0711] 2. Server

[0712] It receives documents, analyzes them, uses AI to learn, and automatically generates and saves goal state documents.

[0713] The emotion engine analyzes the user's emotions and adjusts the system's behavior accordingly.

[0714] Specific software used includes natural language processing libraries "NLTK" and "spaCy," and machine learning libraries "TensorFlow" and "PyTorch."

[0715] 3. Emotion Engine

[0716] The app recognizes user emotions from user input and uploaded documents using IBM Watson Emotion Analysis and Microsoft Azure Emotion API.

[0717] Program processing overview

[0718] Users log in to the system using their terminals and upload their current state analysis document and target state document. The server receives these and analyzes them using natural language processing technology. Important keywords and phrases are extracted and organized as structured data.

[0719] The server provides the analysis results to the AI ​​and performs training. The AI ​​learns the correspondence between the current state analysis document and the target state document and constructs a generation pattern.

[0720] The user inputs a new current state analysis document, and the emotion engine recognizes emotions from this input. The emotion engine analyzes the user's input in real time to identify the user's emotions. Based on the emotions, adjustments are made to the goal state document.

[0721] The server receives the new current state analysis document and passes it to the AI. The AI ​​automatically generates a goal state document based on the learned patterns. The analysis results of the emotion engine are also taken into account when generating the document.

[0722] The server displays the generated goal state document on the user's device. The user checks the contents and makes corrections as necessary. The corrections are fed back to the AI.

[0723] The server saves the final target state document and passes it on to the next process, transferring and sharing data as needed.

[0724] Specific examples

[0725] For Project A

[0726] The user uploads a current state analysis document for Project A. This document describes the current situation where customer information is manually entered, resulting in frequent input errors. The server performs analysis based on this and generates a target state document. The generated target state document describes the introduction of an automatic input system and its benefits, which include reducing input errors.

[0727] If the emotion engine detects stress in the user as they review this document and add specific requests, the system will display a support message to the user, such as "Would you like some tips to help you with this task?"

[0728] The saved goal state document is passed on to the next process and implemented by the development team. The introduction of the emotion engine enables flexible responses according to the user's emotional state, improving the system's accuracy and user satisfaction.

[0729] Prompt Sentence Examples

[0730] "I have uploaded a current situation analysis document for Project A. It states that frequent input errors are a problem with the current manual data entry system. Please generate a target state document based on this. In the generated document, please state the introduction of an automated data entry system and its benefits, such as reducing input errors."

[0731] The above is a specific embodiment for carrying out the invention.

[0732] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0733] Step 1:

[0734] A user uploads a document

[0735] The user logs into the system using a terminal and selects the current state analysis document (AS-IS) and the target state document (TO-BE) in the document upload section through the web interface. Then, he clicks the "Upload" button to send these documents to the server. The current state analysis document and the target state document are the inputs, and these are sent to the server as the outputs.

[0736] Step 2:

[0737] The server receives and parses the document

[0738] The server receives documents uploaded by users. These documents are then analyzed using natural language processing (NLP) techniques. Specifically, the Python natural language processing libraries "NLTK" and "spaCy" are used to tokenize the text, extract keywords, and perform noun phrase analysis. The input is the uploaded document, and the output is structured data with keywords and important phrases extracted.

[0739] Step 3:

[0740] The server trains the generative AI based on the analysis results.

[0741] The server trains a machine learning model based on the structured data obtained through the analysis. During this process, the analysis results are provided to the AI ​​model using libraries such as TensorFlow and PyTorch for training. The input is the structured data from the analysis results, and the output is an AI model that has learned the correspondence between the current state analysis document and the target state document.

[0742] Step 4:

[0743] User enters a new current situation analysis document

[0744] The user uploads a new current situation analysis document through the system's input interface or enters it directly into a text box. The emotion engine analyzes the emotions in real time based on this input. The input is the new current situation analysis document, and the output is emotion data.

[0745] Step 5:

[0746] Emotion engine analyzes emotions

[0747] The emotion engine analyzes the user's input and identifies emotions. This analysis is performed using IBM Watson Emotion Analysis and Microsoft Azure Emotion API. Specifically, it sends text data to the API and analyzes the returned emotion data. The input is the user's text data, and the output is analyzed emotion data.

[0748] Step 6:

[0749] The server automatically generates a target state document based on the new current state analysis document.

[0750] The server passes the newly received current situation analysis document and the analysis results of the emotion engine to the AI ​​model, which then automatically generates a target state document. Using an AI model (e.g., GPT-4), the server generates a target state document that takes into account the content of the current situation analysis document and the user's emotions. The input is the new current situation analysis document and emotion data, and the output is an automatically generated target state document.

[0751] Step 7:

[0752] User reviews and modifies the generated goal state document

[0753] The server displays the generated goal state document on the user's device. The user checks the contents and makes any necessary corrections. The corrections are sent back to the server and fed back to the AI ​​model. The input is the generated goal state document and the user's corrections, and the output is the final goal state document.

[0754] Step 8:

[0755] The server saves the final goal state document and passes it on to the next process.

[0756] The server securely stores the final modified target state document. The saved document is kept in a format that can be freely used for the next process, for example, for the progress of a development project. The input is the final target state document, and the output is the saved document.

[0757] (Application example 2)

[0758] 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."

[0759] Current document creation systems simply generate and manage documents without considering the user's emotions, which means they are unable to reduce user stress and dissatisfaction. Furthermore, even in virtual stores, there is a lack of technology to analyze customer emotions in real time and respond accordingly, limiting the improvement of customer experience.

[0760] 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.

[0761] In this invention, the server includes a means for recognizing a user's emotions and providing suggestions and support based on the emotions, a means for analyzing the user's emotions in the virtual store and providing product suggestions and support messages according to the emotions, and a means for receiving and analyzing documents uploaded by the server. This enables flexible responses according to the user's emotional state, improving the accuracy of the system, user satisfaction, and the customer experience in the virtual store.

[0762] A "user" is a person who uses the system to upload, review, and modify current state analysis and / or target state documents.

[0763] The "server" is a device that receives uploaded documents, analyzes them, and performs artificial intelligence learning, automatic generation of new goal state documents, and even emotion recognition.

[0764] A "current situation analysis document" is a document that analyzes and describes the current situation and problems.

[0765] A "goal state document" is a document that describes a desired future state or goal.

[0766] "Emotion recognition" is a technology that analyzes a user's facial expressions, tone of voice, and text to identify the user's emotions.

[0767] A "virtual store" is a simulation of a store that operates on the Internet and allows users to browse and purchase products in a virtual environment.

[0768] "Product suggestion" is the act of recommending a specific product based on the user's interests and emotional state.

[0769] "Support messages" are messages that are displayed to the user for hints or assistance.

[0770] "Analysis results" are data or information obtained as a result of the server analyzing a document.

[0771] "Automatic generation" is the process by which a system uses AI technology to automatically create documents and data without manual intervention.

[0772] "Training" is the process by which the server trains the artificial intelligence based on the analysis results and improves its performance.

[0773] "Flexible response" refers to the ability of the system to adapt its behavior according to the user's emotions and circumstances.

[0774] The present invention combines an emotion engine that recognizes a user's emotions with a system for automatically generating a current state analysis document and a goal state document, and particularly provides an example of application to a virtual store.

[0775] System Configuration

[0776] The system consists of several main components:

[0777] 1. User Device

[0778] Users use devices such as smart glasses or head-mounted displays, equipped with emotion-recognition cameras and sensors.

[0779] This allows the system to sense the user's facial expressions and tone of voice in real time and transmit them as emotional data to the server.

[0780] 2. Server

[0781] The server receives the uploaded current state analysis document and target state document and analyzes them using natural language processing techniques.

[0782] The AI ​​model learns based on important keywords and phrases extracted through analysis.

[0783] By incorporating the analysis results of the user's emotions by the emotion engine, the generated goal state document is adjusted according to the user's emotions.

[0784] 3. Emotion Engine

[0785] Analyzes emotions from the user's facial expressions, tone of voice, and input text.

[0786] The analysis results are sent to the server and reflected in the document generation process and product suggestions in the virtual store.

[0787] 4. Virtual Store

[0788] The virtual store system provides appropriate product suggestions and support messages based on emotion recognition results when users browse and purchase products in a virtual space.

[0789] If the user's stress or discomfort is detected, the system will display suggestions for relaxing products and support messages.

[0790] Program processing overview

[0791] 1. Emotion recognition

[0792] The emotion engine detects and analyzes facial expressions and tone of voice through cameras and sensors installed on the user's device, using software such as OpenCV, TensorFlow, and Keras.

[0793] 2. Document Analysis and Generation

[0794] Using conventional natural language processing techniques, the current state analysis document and the target state document are analyzed and trained into an AI model. Here, key data processing techniques such as keyword extraction and phrase analysis are performed.

[0795] 3. Emotion-Based Adjustment

[0796] The server adjusts the goal state document based on the emotion analysis data provided by the emotion engine. Specifically, if the user is feeling stressed, the server displays a support message and adjusts the goal state document accordingly.

[0797] Specific examples

[0798] If a user feels "stressed" while browsing a specific product in a virtual store, the system will suggest relaxing products or play music. For example, if the emotion analysis results indicate "stress," the system will suggest "play relaxing music" or display a "discount coupon for your next purchase."

[0799] Prompt Sentence Examples

[0800] If a user is experiencing frustration while viewing the details of a particular product:

[0801] Product category: relaxation-related items

[0802] Recommended products include aroma diffusers, relaxing music CDs, and stress balls.

[0803] Message to display: 10% off coupon for your next purchase

[0804] Music to play: Classical music

[0805] The present invention enables flexible responses that are in line with the user's emotional state, contributing to improved system accuracy and user satisfaction. In particular, it is expected to significantly improve the customer experience in virtual stores.

[0806] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0807] Step 1:

[0808] Provide a means for users to upload current state analysis documents and target state documents.

[0809] Input: The user provides the current state analysis document and the target state document to the system through a file upload interface.

[0810] Output: The uploaded document is sent to the server.

[0811] Specific operation: The user operates the interface in the virtual store, selects a document, and presses the upload button. The server receives the document and stores it in the database.

[0812] Step 2:

[0813] The server receives and parses the uploaded document.

[0814] Inputs: Uploaded current state analysis document and target state document.

[0815] Output: Structured data that analyzes the document, especially extracting important keywords and phrases.

[0816] What it does: The server uses natural language processing techniques (e.g., NLTK or spaCy) to analyze the text in the document and extract keywords and related phrases.

[0817] Step 3:

[0818] The server trains the AI ​​model based on the analysis results.

[0819] Input: Document analysis results, keywords and phrases.

[0820] Output: A trained AI model.

[0821] How it works: The server feeds the extracted keywords and phrases to the AI ​​model and trains it using a machine learning algorithm (e.g., TensorFlow or PyTorch). The model learns the correspondence between the current state analysis document and the goal state document.

[0822] Step 4:

[0823] The user inputs a new current situation analysis document.

[0824] Input: The new current situation analysis document entered by the user.

[0825] Output: A new current situation analysis document sent to the server.

[0826] Specific operation: The user uses the text box in the virtual store to input a new current situation analysis document, and the input is sent to the server in real time.

[0827] Step 5:

[0828] The emotion engine recognizes emotions from user input and uploaded documents.

[0829] Input: User text input and uploaded documents.

[0830] Output: The user's emotional state (e.g., stress, joy, frustration).

[0831] Specific operation: An emotion engine (using, for example, OpenCV or Keras) analyzes the user's input text and facial expressions captured by the camera to identify emotions.

[0832] Step 6:

[0833] The server automatically generates a target state document based on the new current state analysis document.

[0834] Input: New current situation analysis document, sentiment engine analysis results, trained AI model.

[0835] Output: A goal state document.

[0836] Specific operation: The server inputs a new current situation analysis document into the AI ​​model, and then automatically generates an optimal target state document, taking into account the analysis results of the emotion engine.

[0837] Step 7:

[0838] The user reviews and modifies the generated goal state document.

[0839] Input: Generated goal state document, user review and revision.

[0840] Output: The revised goal state document.

[0841] Specific operation: The user reviews the generated goal state document and enters corrections as needed. This feedback is sent to the server, and the AI ​​model is updated.

[0842] Step 8:

[0843] The server saves the final target state document and passes it on to the next development stage.

[0844] Input: The modified goal state document.

[0845] Output: Final goal state document.

[0846] Specific operation: The server saves the final modified target state document, exports it in the format required for the next development phase, and shares it with other systems as needed.

[0847] 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.

[0848] 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.

[0849] 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.

[0850] [Third embodiment]

[0851] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0852] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0853] 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).

[0854] 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.

[0855] 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.

[0856] 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).

[0857] 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.

[0858] 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.

[0859] 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.

[0860] 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.

[0861] 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.

[0862] 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."

[0863] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments of the present invention will be described in detail.

[0864] System Overview

[0865] This invention relates to an automatic generation system for current state analysis documents (AS-IS) and target state documents (TO-BE). The system is mainly composed of users, servers, and terminals, and aims to automate document creation in upstream processes.

[0866] Program processing overview

[0867] 1. User uploads a document

[0868] Users access the system using a terminal and upload current state analysis and target state documents for the project, which are then sent to the server.

[0869] 2. The server receives and parses the document

[0870] The server receives documents uploaded by users.

[0871] The server analyzes the received document using natural language processing technology, extracting important keywords and phrases and organizing the relationship between the current state analysis document and the target state document as structured data.

[0872] 3. The server trains the generative AI based on the analysis results.

[0873] The server provides the analysis results to the generative artificial intelligence (AI) and trains it based on them. The AI ​​learns the correspondence between the current state analysis document and the target state document and constructs a generative pattern based on new input.

[0874] 4. User enters new current situation analysis document

[0875] Users can upload or enter a text box for a current situation analysis document for a new project, which describes the current system status and issues.

[0876] 5. The server automatically generates a target state document based on the new current state analysis document.

[0877] The server receives a new current situation analysis document provided by the user and passes it to the generating artificial intelligence.

[0878] Based on learned patterns, generative AI automatically generates goal state documents that describe new system states and solutions.

[0879] 6. User reviews and modifies the generated goal state document

[0880] The server displays the generated goal state document to the user, who can review it and make corrections as necessary.

[0881] The user's modifications are fed back to the generation AI and reflected in the next generation.

[0882] 7. The server saves the final target state document and passes it on to the next development stage.

[0883] The server stores the final target state document confirmed by the user, and this stored data is passed on to the next development stage.

[0884] If necessary, the server will work with other development tools and systems to transfer and share data.

[0885] Specific examples

[0886] Specific examples are shown below.

[0887] For Project A

[0888] A user uploads a current situation analysis document for Project A. This document describes that the current system requires manual entry of customer information, and points out that a problem with this is that input errors are frequent.

[0889] The server generates a goal state document based on this. This goal state document describes the introduction of the automatic input system and its benefits, such as reducing input errors.

[0890] The user checks this automatically generated target state document, adds more detailed requirements and conditions, and finalizes the final version. The server saves it and hands it over to the development team to proceed to the next stage.

[0891] Effect of the invention

[0892] This system automates the process of documenting the current state and the target state, reducing the amount of work required. It also reduces manual input errors and improves work efficiency in upstream processes. As a result, it is expected to improve the efficiency and productivity of the entire system development process.

[0893] The processing flow will be explained below.

[0894] Step 1:

[0895] The user logs into the system using a terminal. After logging in, the user goes to the "Document Upload" section on the main screen, selects the current state analysis document (AS-IS) and the target state document (TO-BE), and uploads them.

[0896] Step 2:

[0897] The server receives the documents uploaded by the user, stores them in a specific folder, and prepares them for analysis.

[0898] Step 3:

[0899] The server uses natural language processing (NLP) techniques to analyze the uploaded documents, including extracting important keywords and phrases, which are then organized into structured data.

[0900] Step 4:

[0901] Based on the analysis results, the server passes the data to a generative artificial intelligence (AI) for training. The AI ​​learns the correspondence between the current state analysis document and the target state document and builds patterns.

[0902] Step 5:

[0903] The user creates a current status analysis document for a new project on their device and uploads it to the system. The document describing the current status and problems of the new system is sent to the server.

[0904] Step 6:

[0905] The server receives a new current state analysis document provided by the user. After receiving the document, it is passed to the AI, which automatically generates a goal state document based on the document.

[0906] Step 7:

[0907] The server displays the goal state document generated by the AI ​​on the user's device, and the user can review the document and modify it as needed using a text editor.

[0908] Step 8:

[0909] After the user has completed modifying the document, he / she saves the final version by clicking the Confirm button. The server saves the user-confirmed goal state document in the database.

[0910] Step 9:

[0911] The server passes the saved final target state document to the next development stage. If necessary, it connects with other development tools and systems to transfer and share data.

[0912] Example 1

[0913] 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."

[0914] Creating current state analysis documents (AS-IS) and target state documents (TO-BE) requires a lot of time and effort, and manual input and analysis is required, leading to problems of input errors and reduced efficiency. It is also not easy to accurately understand the relationships between these documents and then use them to create a new target state. To solve these issues, a system is needed that automates the process of creating documents from current state analysis to the target state, efficiently and accurately.

[0915] 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.

[0916] In this invention, the server includes means for a user to upload a current state analysis document and a goal state document, means for the server to receive the uploaded documents and analyze them using natural language processing technology, means for the server to train a generating artificial intelligence based on the analysis results, means for the generating artificial intelligence to automatically generate a goal state document based on the analysis results, means for the user to check and correct the generated goal state document, and means for the server to save the final goal state document and hand it over to the next development process. This automates the process of creating documents from the current state analysis to the goal state, enabling efficient and accurate document generation.

[0917] "User" refers to a person who accesses the system and uploads, reviews, or modifies documents.

[0918] A "current situation analysis document" refers to a document that describes the current system status and problems.

[0919] "Goal State Document" refers to a document that describes the improved system status or solution.

[0920] "Server" refers to a computer system for receiving, parsing, and storing documents uploaded by users.

[0921] "Natural language processing technology" refers to technology for understanding and analyzing human language.

[0922] "Generative artificial intelligence" refers to an AI model that learns patterns based on analyzed data and automatically generates new target state documents.

[0923] "Means for uploading" refers to a function that allows a user to send a file to a server.

[0924] "Means for receiving documents" refers to the function of the server to receive and store documents sent by users.

[0925] "Means for analyzing documents" refers to the server's ability to use natural language processing technology to analyze the content of uploaded documents and extract important information.

[0926] "Means for generating documents" refers to the function of automatically creating new target state documents based on patterns learned by the generative artificial intelligence.

[0927] "Means for checking and correcting the document" refers to a function that allows a user to check the generated goal state document and make corrections as necessary.

[0928] "Means for saving documents" refers to a function that enables the server to save the final version of the goal state document and pass it on to the next development stage.

[0929] This invention relates to an automatic generation system for current state analysis documents (AS-IS) and target state documents (TO-BE). The system is mainly composed of users, servers, and terminals, and aims to automate document creation in upstream processes.

[0930] System Overview

[0931] The user uploads the current situation analysis document and the target state document to the system using a terminal. The system then receives and analyzes the documents sent to the server. The server trains the generation AI based on the analysis results. This generation AI automatically generates a new target state document based on the analysis results. The user checks and modifies the generated target state document and confirms the final version. The final document is passed on to the next development process, improving the efficiency of the project.

[0932] Hardware and software used

[0933] The system uses the following hardware and software:

[0934] Server: A server with high-performance computing resources is used to receive, analyze, and store documents.

[0935] Terminal: A user device, such as a PC or tablet, that the user uses for access.

[0936] Natural Language Processing techniques: Use Python's NLTK and SpaCy libraries to analyze the content of uploaded documents.

[0937] Generative Artificial Intelligence (AI): Use generative AI models such as OpenAI's GPT series to automatically generate goal state documents.

[0938] How it works

[0939] Users access the system using a terminal and upload current state analysis documents and target state documents for the project. These documents are sent to the server, which receives the uploaded documents and analyzes them using natural language processing techniques such as Python's NLTK and SpaCy. Important keywords and phrases are extracted from the analyzed data, and the relationship between the current state analysis document and the target state document is organized as structured data.

[0940] The server provides the analysis results to a generative artificial intelligence (AI) for training. The AI ​​learns the correspondence between the current state analysis document and the target state document and constructs a generation pattern based on new input. The user inputs a current state analysis document for a new project, and the server uses the AI ​​to automatically generate a target state document based on this. This document describes the new system status and solutions.

[0941] The user checks the generated goal state document and makes any necessary corrections. The corrections are fed back to the generation AI and reflected in the next generation. The final goal state document is saved by the server and passed on to the next development process. The server also connects with other development tools and systems as needed to transfer and share data.

[0942] Specific examples

[0943] For example:

[0944] For Project A

[0945] The user uploads a current state analysis document for Project A. This document describes how the current system requires manual input of customer information, and cites frequent input errors as a problem. The server then uses this information to generate a goal state document. This goal state document describes the introduction of an automatic input system and its benefits, such as reduced input errors.

[0946] The user checks this automatically generated target state document, adds more detailed requirements and conditions, and finalizes the final version. The server then hands over the saved final target state document to the development team, who then proceeds to the next step.

[0947] Example prompts

[0948] Here are some examples of prompts to input to the AI:

[0949] "In the current system, customer information is entered manually, which results in many input errors. As a target state, we will introduce an automatic system for entering customer information, which will reduce input errors. Based on this, please generate a target state document detailing the necessary requirements."

[0950] The above is an embodiment of the present invention.

[0951] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0952] Step 1:

[0953] A user accesses the system using a terminal and uploads a current state analysis document and a target state document.

[0954] Input: Current State Analysis and Target State documents uploaded by the user in PDF or Word file formats.

[0955] Specific operation: The user opens a browser and accesses the system login page. After logging in, he clicks the document upload button, selects the required file, and uploads it to the system.

[0956] Step 2:

[0957] The server receives the uploaded document.

[0958] Input: User-submitted current state analysis document and target state document.

[0959] Output: The document file saved in a specific directory on the server.

[0960] What happens: The server saves the document sent by the user in a specific directory (e.g., " / uploads") and also calculates a checksum to verify the integrity of the file.

[0961] Step 3:

[0962] The server analyzes the received document using natural language processing technology.

[0963] Input: Saved current state analysis document and target state document.

[0964] Output: Keywords and phrases extracted from the parsed documents, organized structured data.

[0965] What it does: The server uses Python's NLTK and SpaCy libraries to parse the document content, extracting important keywords from the text and structuring the data based on context, then generates a data structure for mapping relationships.

[0966] Step 4:

[0967] The server trains the generative artificial intelligence (AI) based on the analysis results.

[0968] Input: Parsed structured data.

[0969] Output: The patterns and production rules learned by the neural network model (e.g., GPT-3).

[0970] Specific operation: The server passes the analysis results to the generation AI and performs the training process. The AI ​​uses the provided data to learn the correspondence between the current state analysis document and the target state document. As a result, a generation pattern is built, allowing it to generate a target state document based on new input.

[0971] Step 5:

[0972] The user inputs a new current situation analysis document.

[0973] Input: A new current situation analysis document (e.g., project current situation information and issues entered into text boxes).

[0974] Output: The new current situation analysis document uploaded or entered.

[0975] What it does: The user enters a current situation analysis document for the new project into the text box or uploads it as a file, which includes the current system status and current issues.

[0976] Step 6:

[0977] The server automatically generates a target state document based on the new current state analysis document.

[0978] Input: The newly provided current situation analysis document.

[0979] Output: An automatically generated goal state document.

[0980] Specific operation: The server receives a new current state analysis document and passes it to the generation AI. The AI ​​automatically generates a goal state document based on the learned patterns. This generation process may include, for example, a system design or improvement plan to solve the current problem.

[0981] Step 7:

[0982] The user reviews and modifies the generated goal state document.

[0983] Input: An automatically generated goal state document.

[0984] Output: A final target state document that reflects the user's confirmation and correction results.

[0985] Specific operation: The server displays the generated goal state document to the user. The user checks the document and makes corrections as necessary. The corrections are sent back to the server and fed back into the AI's learning data.

[0986] Step 8:

[0987] The server saves the final target state document and passes it on to the next development stage.

[0988] Input: The final goal state document as confirmed by the user.

[0989] Output: The final data used in the next development process.

[0990] Specific operation: The server saves the finalized goal state document in a specific directory (e.g., " / final_documents"), and then transfers the file to other development tools or systems as needed to share and integrate data.

[0991] The above is the specific flow of program processing for this system.

[0992] (Application example 1)

[0993] 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."

[0994] The challenges are to reduce the man-hours and time required to create current state analysis information and target state information, and to reduce errors that occur when manually entering information. In particular, factory manufacturing processes require processing large amounts of information and data in real time and quickly deriving the optimal manufacturing process, so these processes need to be automated.

[0995] 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.

[0996] In this invention, the server includes means for a user to input current state analysis information and target state information, means for the server to receive the input information and analyze it using natural language processing technology, means for the server to train a generative machine learning algorithm based on the analysis results, means for the server to receive new current state analysis information from the user and automatically generate new target state information, means for the user to confirm and correct the generated target state information, and means for the server to save the final target state information and hand it over to the next process. This automates the process of creating current state analysis information and target state information, reducing the man-hours and time required for creation and reducing manual input errors.

[0997] "Current status analysis information" is information that describes in detail the current state and problems of a manufacturing process or system.

[0998] "Target state information" is information that describes in detail the ideal system state or solution to be achieved in the future, which is set based on the current situation analysis information.

[0999] An "input device" is any hardware or software that allows a user to provide information to a system.

[1000] A "server" is a computer that provides multiple functions such as receiving, analyzing, storing, and generating information.

[1001] "Natural language processing technology" is a computer technology for analyzing, understanding, and generating human language.

[1002] "Analysis results" include keywords, phrases, and structured data extracted from current analysis information using natural language processing technology.

[1003] A "generative machine learning algorithm" is an algorithm that learns from large amounts of data and automatically generates new information and patterns.

[1004] "Training" is the process by which a generative machine learning algorithm learns from data and improves its accuracy.

[1005] "Automatic generation" is the process by which a system creates new documents or information without human intervention.

[1006] The "next step" is a subsequent work process or procedure in which the generated goal state information is used.

[1007] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The embodiments for carrying out the present invention will be described in detail below.

[1008] System Overview

[1009] The system mainly consists of a user, a server, and a terminal. The user accesses the system using a terminal and inputs current analysis information and target state information. The server receives and analyzes this information, trains the generative machine learning algorithm, and automatically generates new target state information.

[1010] Program Overview

[1011] 1. User input: The user inputs the current situation analysis information into the input device via a terminal. For example, the current situation analysis information may be input such as, "The process of joining part A to part B is being done manually, and each process takes 20 minutes."

[1012] 2. Data Reception and Analysis: The server receives the input current situation analysis information. The received information is analyzed using natural language processing techniques. Specifically, important keywords and phrases are extracted using open source libraries (e.g., spacy and nltk).

[1013] 3. Training a generative machine learning algorithm: The analysis results are fed into a generative machine learning algorithm for training, using an advanced generative model such as OpenAI's GPT-3.

[1014] 4. Automatic generation: When the user inputs new current situation analysis information, the server automatically generates new target state information based on the learned generative machine learning algorithm. The generated target state information might be, for example, "We will aim to reduce time by introducing an automatic joining system."

[1015] 5. Confirmation and Correction: The generated goal state information is provided to the user, who confirms it and makes corrections as necessary.

[1016] 6. Data storage and handover: The final goal state information is stored on the server and passed on to the next process.

[1017] Examples of specific examples and prompts

[1018] For example, if a user enters the following current status information:

[1019] "The process of joining part A to part B is done manually, and it takes 20 minutes per process. I would like to automate this process and reduce the time."

[1020] Example prompts for generative AI models:

[1021] "The process of joining part A to part B is done manually, and it takes 20 minutes per step. I would like to automate this process and reduce the time. Please generate a target state based on this current state."

[1022] In this way, the present invention automates the process of creating current state analysis information and target state information, reducing the number of steps and time required for creation, and reducing manual input errors.

[1023] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1024] Step 1:

[1025] The user uses a terminal to input information for analyzing the current situation. Text data about the current manufacturing process and problems is provided as input. For example, the user might enter information such as, "The process of joining part A to part B is done manually, and each process takes 20 minutes."

[1026] Step 2:

[1027] The terminal sends the entered current situation analysis information to the server. The input data is transferred to the server in text format, and the server receives it. As a result, the current situation analysis information provided by the user is aggregated on the server.

[1028] Step 3:

[1029] The server analyzes the received current situation analysis information using natural language processing technology. Specifically, it uses open source libraries (e.g., spacy and nltk) to tokenize the text data and extract important keywords and phrases. The current situation analysis information is used as input, and the analysis results are obtained as output.

[1030] Step 4:

[1031] The server provides the analysis results to a generative machine learning algorithm to train the algorithm. The analysis results are input as training data, and the generative machine learning algorithm (e.g., OpenAI's GPT-3) learns from them. The output is the algorithm's ability to generate target state information from new data.

[1032] Step 5:

[1033] The user inputs new current situation analysis information from the terminal. The input process is the same as in step 1, and information on new projects and manufacturing processes is provided.

[1034] Step 6:

[1035] The server uses a trained generative machine learning algorithm to automatically generate target state information based on new current situation analysis information. The new current situation analysis information is used as input, and generated target state information is obtained as output. For example, the generated content is "We aim to reduce time by introducing an automatic joining system."

[1036] Step 7:

[1037] The user checks the generated goal state information and corrects it if necessary. The device displays the generated goal state information, and the user checks it and provides feedback. The user's suggestions for correction are added as input, and the information is output as the final goal state information.

[1038] Step 8:

[1039] The server saves the final goal state information and passes it on to the next process. The saved data is used for future reference and for linking with other systems. The finalized goal state information is saved as input, and data that can be applied to the next process is obtained as output.

[1040] Through the above steps, the system creates and automatically generates current state analysis information and target state information, and can optimize the manufacturing process based on the information provided by the user.

[1041] 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.

[1042] The following describes in detail the embodiments of the present invention. The present invention combines an emotion engine that recognizes user emotions with an automatic generation system for current state analysis documents (AS-IS) and goal state documents (TO-BE). This system is primarily composed of users, servers, and terminals, and aims to automate document creation in upstream processes and make adjustments based on emotions.

[1043] System Overview

[1044] The system is configured as follows:

[1045] 1. User Device

[1046] An interface for users to upload current state analysis and target state documents.

[1047] The user inputs a new current situation analysis document and the emotion engine recognizes emotions.

[1048] 2. Server

[1049] It receives documents, analyzes them, trains the AI, and automatically generates and saves goal state documents.

[1050] The emotion engine analyzes the user's emotions and adjusts the system's behavior accordingly.

[1051] 3. Emotion Engine

[1052] Recognize user emotions from user input and uploaded documents.

[1053] Program processing overview

[1054] 1. User uploads a document

[1055] A user logs into the system using a terminal and uploads a current state analysis document and a target state document.

[1056] 2. The server receives and parses the document

[1057] The server receives the uploaded documents and analyzes them using natural language processing techniques, extracting important keywords and phrases and organizing them into structured data.

[1058] 3. The server trains the generative AI based on the analysis results.

[1059] The server provides the analysis results to the AI ​​and performs training. The AI ​​learns the correspondence between the current state analysis document and the target state document and constructs a generation pattern.

[1060] 4. User enters new current situation analysis document

[1061] Users upload a new current situation analysis document or enter it into a text box, and the emotion engine recognizes emotions.

[1062] 5. Emotion engine analyzes emotions

[1063] The emotion engine analyzes the user's input and identifies the user's emotion, and adjustments are made to the goal state document based on the emotion.

[1064] 6. The server automatically generates a target state document based on the new current state analysis document.

[1065] The server receives the new current state analysis document and passes it to the AI. The AI ​​automatically generates a goal state document based on the learned patterns. The analysis results of the emotion engine are also taken into account during generation.

[1066] 7. User reviews and modifies the generated goal state document

[1067] The server displays the generated goal state document on the user's device. The user checks the contents and makes corrections as necessary. The corrections are fed back to the AI.

[1068] 8. The server saves the final target state document and passes it on to the next development stage.

[1069] The server stores the final target state document and passes it on to the next development stage. Data is transferred and shared as needed.

[1070] Specific examples

[1071] Specific examples are shown below.

[1072] For Project A

[1073] A user uploads a current situation analysis document for Project A. This document describes that the current system requires manual entry of customer information, and points out that a problem with this is that input errors are frequent.

[1074] The server generates a goal state document based on this. The generated goal state document describes the introduction of the automatic input system and its benefits, such as reducing input errors.

[1075] If the emotion engine detects stress when the user reviews the document and adds specific requirements, the system displays appropriate support messages to the user, thus reducing the burden on the user and finalizing the document.

[1076] The saved goal state document is passed on to the next development process and implemented by the development team. The introduction of the emotion engine enables flexible responses according to the user's emotional state, improving the system's accuracy and user satisfaction.

[1077] The processing flow will be explained below.

[1078] Step 1:

[1079] The user logs in to the system using a terminal. After logging in, the user selects and uploads the current state analysis document and the target state document from the "Document Upload" section displayed on the main screen.

[1080] Step 2:

[1081] The server receives the uploaded documents and stores them in a specific folder, ready to be passed on to the analysis process.

[1082] Step 3:

[1083] The server uses natural language processing (NLP) techniques to analyze the text of the uploaded document, extracting keywords and phrases and organizing them into structured data, which is then used as input for the subsequent AI learning process.

[1084] Step 4:

[1085] The server provides the analysis results as training data to the generative artificial intelligence (AI). The AI ​​performs training based on the provided data and learns the correspondence between the current state analysis document and the target state document.

[1086] Step 5:

[1087] The user creates a current situation analysis document for a new project on the terminal and enters it into the text box. After completing the input, the user clicks the "Upload" button to send the document to the server.

[1088] Step 6:

[1089] The server receives a newly uploaded current situation analysis document, which describes the current system status and problems.

[1090] Step 7:

[1091] The emotion engine analyzes the newly uploaded current situation analysis document and recognizes the user's emotions. Specifically, it infers the user's emotions (e.g., stress or satisfaction) from the vocabulary and context contained in the text.

[1092] Step 8:

[1093] The server inputs the analyzed current state analysis document into the artificial intelligence generator, which then automatically generates a new target state document. The generation process also takes into account emotional data from the emotion engine.

[1094] Step 9:

[1095] The server displays the AI-generated goal state document on the user's device, and the user can review the document and modify it as needed using a text editor.

[1096] Step 10:

[1097] The user completes the document modification and clicks the Confirm button. The server saves the final target state document confirmed by the user to the database.

[1098] Step 11:

[1099] The server passes the saved final target state document to the next development stage. If necessary, it connects with other development tools and systems to transfer and share data.

[1100] Specific examples

[1101] The user inputs a current situation analysis document for Project B. This document states that "the current system manages inventory manually" and "it is difficult to grasp inventory status in real time." When the server receives and analyzes this document, the emotion engine detects stress from the user's text. As a result, the system generates a goal state document that includes elements such as "introduce an automated inventory management system" and "a low-stress interface." The user reviews this document, makes corrections, and then finalizes the version to move on to the next process.

[1102] Example 2

[1103] 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."

[1104] There are problems with the automation of the creation of current state analysis documents and goal state documents, and the lack of adjustments that take user emotions into account.In addition, there is a lack of a system that can effectively learn and automatically generate correspondences between current state analysis documents and goal state documents.

[1105] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for receiving an uploaded document and analyzing it using natural language processing technology, means for training a machine learning model based on the analysis results, means for receiving a new current situation analysis document and automatically generating a new goal state document, and means for analyzing a user's emotions using emotion recognition technology and reflecting the emotions in the goal state document. This enables automation of document creation and flexible adjustment based on the user's emotions.

[1106] A "current situation analysis document" is a document that details the current status of business operations and systems.

[1107] A "target state document" is a document that details the ideal state of a future business or system.

[1108] "Upload" is the act of a user transferring data or files from a terminal to a server.

[1109] "Natural language processing technology" is a technology that enables computers to understand, analyze, and generate human language.

[1110] "Analysis" is the act of breaking down data or information and understanding its structure and meaning.

[1111] A "machine learning model" is an algorithm that learns patterns and rules from data and makes predictions and classifications.

[1112] "Auto-generation" is the act of a system using specific algorithms to create new data or information without human intervention.

[1113] "Emotion recognition technology" is a technology for identifying emotions from user input and behavior.

[1114] "Storage" is the act of recording data or information for later reference.

[1115] "Next step" refers to the series of tasks or processes that follow the current phase.

[1116] The following describes a specific embodiment of the present invention. The present invention combines a system for automatically generating a current state analysis document and a goal state document with an emotion engine that recognizes the user's emotions. This system consists of a user, a server, and a terminal.

[1117] System Overview

[1118] The system is configured as follows:

[1119] 1. User Device

[1120] Provides an interface for users to upload current state analysis documents and target state documents.

[1121] The user inputs a new current situation analysis document and the emotion engine recognizes emotions.

[1122] 2. Server

[1123] It receives documents, analyzes them, uses AI to learn, and automatically generates and saves goal state documents.

[1124] The emotion engine analyzes the user's emotions and adjusts the system's behavior accordingly.

[1125] Specific software used includes natural language processing libraries "NLTK" and "spaCy," and machine learning libraries "TensorFlow" and "PyTorch."

[1126] 3. Emotion Engine

[1127] The app recognizes user emotions from user input and uploaded documents using IBM Watson Emotion Analysis and Microsoft Azure Emotion API.

[1128] Program processing overview

[1129] Users log in to the system using their terminals and upload their current state analysis document and target state document. The server receives these and analyzes them using natural language processing technology. Important keywords and phrases are extracted and organized as structured data.

[1130] The server provides the analysis results to the AI ​​and performs training. The AI ​​learns the correspondence between the current state analysis document and the target state document and constructs a generation pattern.

[1131] The user inputs a new current state analysis document, and the emotion engine recognizes emotions from this input. The emotion engine analyzes the user's input in real time to identify the user's emotions. Based on the emotions, adjustments are made to the goal state document.

[1132] The server receives the new current state analysis document and passes it to the AI. The AI ​​automatically generates a goal state document based on the learned patterns. The analysis results of the emotion engine are also taken into account when generating the document.

[1133] The server displays the generated goal state document on the user's device. The user checks the contents and makes corrections as necessary. The corrections are fed back to the AI.

[1134] The server saves the final target state document and passes it on to the next process, transferring and sharing data as needed.

[1135] Specific examples

[1136] For Project A

[1137] The user uploads a current state analysis document for Project A. This document describes the current situation where customer information is manually entered, resulting in frequent input errors. The server performs analysis based on this and generates a target state document. The generated target state document describes the introduction of an automatic input system and its benefits, which include reducing input errors.

[1138] If the emotion engine detects stress in the user as they review this document and add specific requests, the system will display a support message to the user, such as "Would you like some tips to help you with this task?"

[1139] The saved goal state document is passed on to the next process and implemented by the development team. The introduction of the emotion engine enables flexible responses according to the user's emotional state, improving the system's accuracy and user satisfaction.

[1140] Prompt Sentence Examples

[1141] "I have uploaded a current situation analysis document for Project A. It states that frequent input errors are a problem with the current manual data entry system. Please generate a target state document based on this. In the generated document, please state the introduction of an automated data entry system and its benefits, such as reducing input errors."

[1142] The above is a specific embodiment for carrying out the invention.

[1143] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1144] Step 1:

[1145] A user uploads a document

[1146] The user logs into the system using a terminal and selects the current state analysis document (AS-IS) and the target state document (TO-BE) in the document upload section through the web interface. Then, he clicks the "Upload" button to send these documents to the server. The current state analysis document and the target state document are the inputs, and these are sent to the server as the outputs.

[1147] Step 2:

[1148] The server receives and parses the document

[1149] The server receives documents uploaded by users. These documents are then analyzed using natural language processing (NLP) techniques. Specifically, the Python natural language processing libraries "NLTK" and "spaCy" are used to tokenize the text, extract keywords, and perform noun phrase analysis. The input is the uploaded document, and the output is structured data with keywords and important phrases extracted.

[1150] Step 3:

[1151] The server trains the generative AI based on the analysis results.

[1152] The server trains a machine learning model based on the structured data obtained through the analysis. During this process, the analysis results are provided to the AI ​​model using libraries such as TensorFlow and PyTorch for training. The input is the structured data from the analysis results, and the output is an AI model that has learned the correspondence between the current state analysis document and the target state document.

[1153] Step 4:

[1154] User enters a new current situation analysis document

[1155] The user uploads a new current situation analysis document through the system's input interface or enters it directly into a text box. The emotion engine analyzes the emotions in real time based on this input. The input is the new current situation analysis document, and the output is emotion data.

[1156] Step 5:

[1157] Emotion engine analyzes emotions

[1158] The emotion engine analyzes the user's input and identifies emotions. This analysis is performed using IBM Watson Emotion Analysis and Microsoft Azure Emotion API. Specifically, it sends text data to the API and analyzes the returned emotion data. The input is the user's text data, and the output is analyzed emotion data.

[1159] Step 6:

[1160] The server automatically generates a target state document based on the new current state analysis document.

[1161] The server passes the newly received current situation analysis document and the analysis results of the emotion engine to the AI ​​model, which then automatically generates a target state document. Using an AI model (e.g., GPT-4), the server generates a target state document that takes into account the content of the current situation analysis document and the user's emotions. The input is the new current situation analysis document and emotion data, and the output is an automatically generated target state document.

[1162] Step 7:

[1163] User reviews and modifies the generated goal state document

[1164] The server displays the generated goal state document on the user's device. The user checks the contents and makes any necessary corrections. The corrections are sent back to the server and fed back to the AI ​​model. The input is the generated goal state document and the user's corrections, and the output is the final goal state document.

[1165] Step 8:

[1166] The server saves the final goal state document and passes it on to the next process.

[1167] The server securely stores the final modified target state document. The saved document is kept in a format that can be freely used for the next process, for example, for the progress of a development project. The input is the final target state document, and the output is the saved document.

[1168] (Application example 2)

[1169] 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."

[1170] Current document creation systems simply generate and manage documents without considering the user's emotions, which means they are unable to reduce user stress and dissatisfaction. Furthermore, even in virtual stores, there is a lack of technology to analyze customer emotions in real time and respond accordingly, limiting the improvement of customer experience.

[1171] 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.

[1172] In this invention, the server includes a means for recognizing a user's emotions and providing suggestions and support based on the emotions, a means for analyzing the user's emotions in the virtual store and providing product suggestions and support messages according to the emotions, and a means for receiving and analyzing documents uploaded by the server. This enables flexible responses according to the user's emotional state, improving the accuracy of the system, user satisfaction, and the customer experience in the virtual store.

[1173] A "user" is a person who uses the system to upload, review, and modify current state analysis and / or target state documents.

[1174] The "server" is a device that receives uploaded documents, analyzes them, and performs artificial intelligence learning, automatic generation of new goal state documents, and even emotion recognition.

[1175] A "current situation analysis document" is a document that analyzes and describes the current situation and problems.

[1176] A "goal state document" is a document that describes a desired future state or goal.

[1177] "Emotion recognition" is a technology that analyzes a user's facial expressions, tone of voice, and text to identify the user's emotions.

[1178] A "virtual store" is a simulation of a store that operates on the Internet and allows users to browse and purchase products in a virtual environment.

[1179] "Product suggestion" is the act of recommending a specific product based on the user's interests and emotional state.

[1180] "Support messages" are messages that are displayed to the user for hints or assistance.

[1181] "Analysis results" are data or information obtained as a result of the server analyzing a document.

[1182] "Automatic generation" is the process by which a system uses AI technology to automatically create documents and data without manual intervention.

[1183] "Training" is the process by which the server trains the artificial intelligence based on the analysis results and improves its performance.

[1184] "Flexible response" refers to the ability of the system to adapt its behavior according to the user's emotions and circumstances.

[1185] The present invention combines an emotion engine that recognizes a user's emotions with a system for automatically generating a current state analysis document and a goal state document, and particularly provides an example of application to a virtual store.

[1186] System Configuration

[1187] The system consists of several main components:

[1188] 1. User Device

[1189] Users use devices such as smart glasses or head-mounted displays, equipped with emotion-recognition cameras and sensors.

[1190] This allows the system to sense the user's facial expressions and tone of voice in real time and transmit them as emotional data to the server.

[1191] 2. Server

[1192] The server receives the uploaded current state analysis document and target state document and analyzes them using natural language processing techniques.

[1193] The AI ​​model learns based on important keywords and phrases extracted through analysis.

[1194] By incorporating the analysis results of the user's emotions by the emotion engine, the generated goal state document is adjusted according to the user's emotions.

[1195] 3. Emotion Engine

[1196] Analyzes emotions from the user's facial expressions, tone of voice, and input text.

[1197] The analysis results are sent to the server and reflected in the document generation process and product suggestions in the virtual store.

[1198] 4. Virtual Store

[1199] The virtual store system provides appropriate product suggestions and support messages based on emotion recognition results when users browse and purchase products in a virtual space.

[1200] If the user's stress or discomfort is detected, the system will display suggestions for relaxing products and support messages.

[1201] Program processing overview

[1202] 1. Emotion recognition

[1203] The emotion engine detects and analyzes facial expressions and tone of voice through cameras and sensors installed on the user's device, using software such as OpenCV, TensorFlow, and Keras.

[1204] 2. Document Analysis and Generation

[1205] Using conventional natural language processing techniques, the current state analysis document and the target state document are analyzed and trained into an AI model. Here, key data processing techniques such as keyword extraction and phrase analysis are performed.

[1206] 3. Emotion-Based Adjustment

[1207] The server adjusts the goal state document based on the emotion analysis data provided by the emotion engine. Specifically, if the user is feeling stressed, the server displays a support message and adjusts the goal state document accordingly.

[1208] Specific examples

[1209] If a user feels "stressed" while browsing a specific product in a virtual store, the system will suggest relaxing products or play music. For example, if the emotion analysis results indicate "stress," the system will suggest "play relaxing music" or display a "discount coupon for your next purchase."

[1210] Prompt Sentence Examples

[1211] If a user is experiencing frustration while viewing the details of a particular product:

[1212] Product category: relaxation-related items

[1213] Recommended products include aroma diffusers, relaxing music CDs, and stress balls.

[1214] Message to display: 10% off coupon for your next purchase

[1215] Music to play: Classical music

[1216] The present invention enables flexible responses that are in line with the user's emotional state, contributing to improved system accuracy and user satisfaction. In particular, it is expected to significantly improve the customer experience in virtual stores.

[1217] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1218] Step 1:

[1219] Provide a means for users to upload current state analysis documents and target state documents.

[1220] Input: The user provides the current state analysis document and the target state document to the system through a file upload interface.

[1221] Output: The uploaded document is sent to the server.

[1222] Specific operation: The user operates the interface in the virtual store, selects a document, and presses the upload button. The server receives the document and stores it in the database.

[1223] Step 2:

[1224] The server receives and parses the uploaded document.

[1225] Inputs: Uploaded current state analysis document and target state document.

[1226] Output: Structured data that analyzes the document, especially extracting important keywords and phrases.

[1227] What it does: The server uses natural language processing techniques (e.g., NLTK or spaCy) to analyze the text in the document and extract keywords and related phrases.

[1228] Step 3:

[1229] The server trains the AI ​​model based on the analysis results.

[1230] Input: Document analysis results, keywords and phrases.

[1231] Output: A trained AI model.

[1232] How it works: The server feeds the extracted keywords and phrases to the AI ​​model and trains it using a machine learning algorithm (e.g., TensorFlow or PyTorch). The model learns the correspondence between the current state analysis document and the goal state document.

[1233] Step 4:

[1234] The user inputs a new current situation analysis document.

[1235] Input: The new current situation analysis document entered by the user.

[1236] Output: A new current situation analysis document sent to the server.

[1237] Specific operation: The user uses the text box in the virtual store to input a new current situation analysis document, and the input is sent to the server in real time.

[1238] Step 5:

[1239] The emotion engine recognizes emotions from user input and uploaded documents.

[1240] Input: User text input and uploaded documents.

[1241] Output: The user's emotional state (e.g., stress, joy, frustration).

[1242] Specific operation: An emotion engine (using, for example, OpenCV or Keras) analyzes the user's input text and facial expressions captured by the camera to identify emotions.

[1243] Step 6:

[1244] The server automatically generates a target state document based on the new current state analysis document.

[1245] Input: New current situation analysis document, sentiment engine analysis results, trained AI model.

[1246] Output: A goal state document.

[1247] Specific operation: The server inputs a new current situation analysis document into the AI ​​model, and then automatically generates an optimal target state document, taking into account the analysis results of the emotion engine.

[1248] Step 7:

[1249] The user reviews and modifies the generated goal state document.

[1250] Input: Generated goal state document, user review and revision.

[1251] Output: The revised goal state document.

[1252] Specific operation: The user reviews the generated goal state document and enters corrections as needed. This feedback is sent to the server, and the AI ​​model is updated.

[1253] Step 8:

[1254] The server saves the final target state document and passes it on to the next development stage.

[1255] Input: The modified goal state document.

[1256] Output: Final goal state document.

[1257] Specific operation: The server saves the final modified target state document, exports it in the format required for the next development phase, and shares it with other systems as needed.

[1258] 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.

[1259] 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.

[1260] 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.

[1261] [Fourth embodiment]

[1262] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1263] 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.

[1264] 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).

[1265] 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.

[1266] 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.

[1267] 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).

[1268] 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.

[1269] 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.

[1270] 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.

[1271] 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.

[1272] 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.

[1273] 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.

[1274] 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."

[1275] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments of the present invention will be described in detail.

[1276] System Overview

[1277] This invention relates to an automatic generation system for current state analysis documents (AS-IS) and target state documents (TO-BE). The system is mainly composed of users, servers, and terminals, and aims to automate document creation in upstream processes.

[1278] Program processing overview

[1279] 1. User uploads a document

[1280] Users access the system using a terminal and upload current state analysis and target state documents for the project, which are then sent to the server.

[1281] 2. The server receives and parses the document

[1282] The server receives documents uploaded by users.

[1283] The server analyzes the received document using natural language processing technology, extracting important keywords and phrases and organizing the relationship between the current state analysis document and the target state document as structured data.

[1284] 3. The server trains the generative AI based on the analysis results.

[1285] The server provides the analysis results to the generative artificial intelligence (AI) and trains it based on them. The AI ​​learns the correspondence between the current state analysis document and the target state document and constructs a generative pattern based on new input.

[1286] 4. User enters new current situation analysis document

[1287] Users can upload or enter a text box for a current situation analysis document for a new project, which describes the current system status and issues.

[1288] 5. The server automatically generates a target state document based on the new current state analysis document.

[1289] The server receives a new current situation analysis document provided by the user and passes it to the generating artificial intelligence.

[1290] Based on learned patterns, generative AI automatically generates goal state documents that describe new system states and solutions.

[1291] 6. User reviews and modifies the generated goal state document

[1292] The server displays the generated goal state document to the user, who can review it and make corrections as necessary.

[1293] The user's modifications are fed back to the generation AI and reflected in the next generation.

[1294] 7. The server saves the final target state document and passes it on to the next development stage.

[1295] The server stores the final target state document confirmed by the user, and this stored data is passed on to the next development stage.

[1296] If necessary, the server will work with other development tools and systems to transfer and share data.

[1297] Specific examples

[1298] Specific examples are shown below.

[1299] For Project A

[1300] A user uploads a current situation analysis document for Project A. This document describes that the current system requires manual entry of customer information, and points out that a problem with this is that input errors are frequent.

[1301] The server generates a goal state document based on this. This goal state document describes the introduction of the automatic input system and its benefits, such as reducing input errors.

[1302] The user checks this automatically generated target state document, adds more detailed requirements and conditions, and finalizes the final version. The server saves it and hands it over to the development team to proceed to the next stage.

[1303] Effect of the invention

[1304] This system automates the process of documenting the current state and the target state, reducing the amount of work required. It also reduces manual input errors and improves work efficiency in upstream processes. As a result, it is expected to improve the efficiency and productivity of the entire system development process.

[1305] The processing flow will be explained below.

[1306] Step 1:

[1307] The user logs into the system using a terminal. After logging in, the user goes to the "Document Upload" section on the main screen, selects the current state analysis document (AS-IS) and the target state document (TO-BE), and uploads them.

[1308] Step 2:

[1309] The server receives the documents uploaded by the user, stores them in a specific folder, and prepares them for analysis.

[1310] Step 3:

[1311] The server uses natural language processing (NLP) techniques to analyze the uploaded documents, including extracting important keywords and phrases, which are then organized into structured data.

[1312] Step 4:

[1313] Based on the analysis results, the server passes the data to a generative artificial intelligence (AI) for training. The AI ​​learns the correspondence between the current state analysis document and the target state document and builds patterns.

[1314] Step 5:

[1315] The user creates a current status analysis document for a new project on their device and uploads it to the system. The document describing the current status and problems of the new system is sent to the server.

[1316] Step 6:

[1317] The server receives a new current state analysis document provided by the user. After receiving the document, it is passed to the AI, which automatically generates a goal state document based on the document.

[1318] Step 7:

[1319] The server displays the goal state document generated by the AI ​​on the user's device, and the user can review the document and modify it as needed using a text editor.

[1320] Step 8:

[1321] After the user has completed modifying the document, he / she saves the final version by clicking the Confirm button. The server saves the user-confirmed goal state document in the database.

[1322] Step 9:

[1323] The server passes the saved final target state document to the next development stage. If necessary, it connects with other development tools and systems to transfer and share data.

[1324] Example 1

[1325] 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."

[1326] Creating current state analysis documents (AS-IS) and target state documents (TO-BE) requires a lot of time and effort, and manual input and analysis is required, leading to problems of input errors and reduced efficiency. It is also not easy to accurately understand the relationships between these documents and then use them to create a new target state. To solve these issues, a system is needed that automates the process of creating documents from current state analysis to the target state, efficiently and accurately.

[1327] 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.

[1328] In this invention, the server includes means for a user to upload a current state analysis document and a goal state document, means for the server to receive the uploaded documents and analyze them using natural language processing technology, means for the server to train a generating artificial intelligence based on the analysis results, means for the generating artificial intelligence to automatically generate a goal state document based on the analysis results, means for the user to check and correct the generated goal state document, and means for the server to save the final goal state document and hand it over to the next development process. This automates the process of creating documents from the current state analysis to the goal state, enabling efficient and accurate document generation.

[1329] "User" refers to a person who accesses the system and uploads, reviews, or modifies documents.

[1330] A "current situation analysis document" refers to a document that describes the current system status and problems.

[1331] "Goal State Document" refers to a document that describes the improved system status or solution.

[1332] "Server" refers to a computer system for receiving, parsing, and storing documents uploaded by users.

[1333] "Natural language processing technology" refers to technology for understanding and analyzing human language.

[1334] "Generative artificial intelligence" refers to an AI model that learns patterns based on analyzed data and automatically generates new target state documents.

[1335] "Means for uploading" refers to a function that allows a user to send a file to a server.

[1336] "Means for receiving documents" refers to the function of the server to receive and store documents sent by users.

[1337] "Means for analyzing documents" refers to the server's ability to use natural language processing technology to analyze the content of uploaded documents and extract important information.

[1338] "Means for generating documents" refers to the function of automatically creating new target state documents based on patterns learned by the generative artificial intelligence.

[1339] "Means for checking and correcting the document" refers to a function that allows a user to check the generated goal state document and make corrections as necessary.

[1340] "Means for saving documents" refers to a function that enables the server to save the final version of the goal state document and pass it on to the next development stage.

[1341] This invention relates to an automatic generation system for current state analysis documents (AS-IS) and target state documents (TO-BE). The system is mainly composed of users, servers, and terminals, and aims to automate document creation in upstream processes.

[1342] System Overview

[1343] The user uploads the current situation analysis document and the target state document to the system using a terminal. The system then receives and analyzes the documents sent to the server. The server trains the generation AI based on the analysis results. This generation AI automatically generates a new target state document based on the analysis results. The user checks and modifies the generated target state document and confirms the final version. The final document is passed on to the next development process, improving the efficiency of the project.

[1344] Hardware and software used

[1345] The system uses the following hardware and software:

[1346] Server: A server with high-performance computing resources is used to receive, analyze, and store documents.

[1347] Terminal: A user device, such as a PC or tablet, that the user uses for access.

[1348] Natural Language Processing techniques: Use Python's NLTK and SpaCy libraries to analyze the content of uploaded documents.

[1349] Generative Artificial Intelligence (AI): Use generative AI models such as OpenAI's GPT series to automatically generate goal state documents.

[1350] How it works

[1351] Users access the system using a terminal and upload current state analysis documents and target state documents for the project. These documents are sent to the server, which receives the uploaded documents and analyzes them using natural language processing techniques such as Python's NLTK and SpaCy. Important keywords and phrases are extracted from the analyzed data, and the relationship between the current state analysis document and the target state document is organized as structured data.

[1352] The server provides the analysis results to a generative artificial intelligence (AI) for training. The AI ​​learns the correspondence between the current state analysis document and the target state document and constructs a generation pattern based on new input. The user inputs a current state analysis document for a new project, and the server uses the AI ​​to automatically generate a target state document based on this. This document describes the new system status and solutions.

[1353] The user checks the generated goal state document and makes any necessary corrections. The corrections are fed back to the generation AI and reflected in the next generation. The final goal state document is saved by the server and passed on to the next development process. The server also connects with other development tools and systems as needed to transfer and share data.

[1354] Specific examples

[1355] For example:

[1356] For Project A

[1357] The user uploads a current state analysis document for Project A. This document describes how the current system requires manual input of customer information, and cites frequent input errors as a problem. The server then uses this information to generate a goal state document. This goal state document describes the introduction of an automatic input system and its benefits, such as reduced input errors.

[1358] The user checks this automatically generated target state document, adds more detailed requirements and conditions, and finalizes the final version. The server then hands over the saved final target state document to the development team, who then proceeds to the next step.

[1359] Example prompts

[1360] Here are some examples of prompts to input to the AI:

[1361] "In the current system, customer information is entered manually, which results in many input errors. As a target state, we will introduce an automatic system for entering customer information, which will reduce input errors. Based on this, please generate a target state document detailing the necessary requirements."

[1362] The above is an embodiment of the present invention.

[1363] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1364] Step 1:

[1365] A user accesses the system using a terminal and uploads a current state analysis document and a target state document.

[1366] Input: Current State Analysis and Target State documents uploaded by the user in PDF or Word file formats.

[1367] Specific operation: The user opens a browser and accesses the system login page. After logging in, he clicks the document upload button, selects the required file, and uploads it to the system.

[1368] Step 2:

[1369] The server receives the uploaded document.

[1370] Input: User-submitted current state analysis document and target state document.

[1371] Output: The document file saved in a specific directory on the server.

[1372] What happens: The server saves the document sent by the user in a specific directory (e.g., " / uploads") and also calculates a checksum to verify the integrity of the file.

[1373] Step 3:

[1374] The server analyzes the received document using natural language processing technology.

[1375] Input: Saved current state analysis document and target state document.

[1376] Output: Keywords and phrases extracted from the parsed documents, organized structured data.

[1377] What it does: The server uses Python's NLTK and SpaCy libraries to parse the document content, extracting important keywords from the text and structuring the data based on context, then generates a data structure for mapping relationships.

[1378] Step 4:

[1379] The server trains the generative artificial intelligence (AI) based on the analysis results.

[1380] Input: Parsed structured data.

[1381] Output: The patterns and production rules learned by the neural network model (e.g., GPT-3).

[1382] Specific operation: The server passes the analysis results to the generation AI and performs the training process. The AI ​​uses the provided data to learn the correspondence between the current state analysis document and the target state document. As a result, a generation pattern is built, allowing it to generate a target state document based on new input.

[1383] Step 5:

[1384] The user inputs a new current situation analysis document.

[1385] Input: A new current situation analysis document (e.g., project current situation information and issues entered into text boxes).

[1386] Output: The new current situation analysis document uploaded or entered.

[1387] What it does: The user enters a current situation analysis document for the new project into the text box or uploads it as a file, which includes the current system status and current issues.

[1388] Step 6:

[1389] The server automatically generates a target state document based on the new current state analysis document.

[1390] Input: The newly provided current situation analysis document.

[1391] Output: An automatically generated goal state document.

[1392] Specific operation: The server receives a new current state analysis document and passes it to the generation AI. The AI ​​automatically generates a goal state document based on the learned patterns. This generation process may include, for example, a system design or improvement plan to solve the current problem.

[1393] Step 7:

[1394] The user reviews and modifies the generated goal state document.

[1395] Input: An automatically generated goal state document.

[1396] Output: A final target state document that reflects the user's confirmation and correction results.

[1397] Specific operation: The server displays the generated goal state document to the user. The user checks the document and makes corrections as necessary. The corrections are sent back to the server and fed back into the AI's learning data.

[1398] Step 8:

[1399] The server saves the final target state document and passes it on to the next development stage.

[1400] Input: The final goal state document as confirmed by the user.

[1401] Output: The final data used in the next development process.

[1402] Specific operation: The server saves the finalized goal state document in a specific directory (e.g., " / final_documents"), and then transfers the file to other development tools or systems as needed to share and integrate data.

[1403] The above is the specific flow of program processing for this system.

[1404] (Application example 1)

[1405] 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."

[1406] The challenges are to reduce the man-hours and time required to create current state analysis information and target state information, and to reduce errors that occur when manually entering information. In particular, factory manufacturing processes require processing large amounts of information and data in real time and quickly deriving the optimal manufacturing process, so these processes need to be automated.

[1407] 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.

[1408] In this invention, the server includes means for a user to input current state analysis information and target state information, means for the server to receive the input information and analyze it using natural language processing technology, means for the server to train a generative machine learning algorithm based on the analysis results, means for the server to receive new current state analysis information from the user and automatically generate new target state information, means for the user to confirm and correct the generated target state information, and means for the server to save the final target state information and hand it over to the next process. This automates the process of creating current state analysis information and target state information, reducing the man-hours and time required for creation and reducing manual input errors.

[1409] "Current status analysis information" is information that describes in detail the current state and problems of a manufacturing process or system.

[1410] "Target state information" is information that describes in detail the ideal system state or solution to be achieved in the future, which is set based on the current situation analysis information.

[1411] An "input device" is any hardware or software that allows a user to provide information to a system.

[1412] A "server" is a computer that provides multiple functions such as receiving, analyzing, storing, and generating information.

[1413] "Natural language processing technology" is a computer technology for analyzing, understanding, and generating human language.

[1414] "Analysis results" include keywords, phrases, and structured data extracted from current analysis information using natural language processing technology.

[1415] A "generative machine learning algorithm" is an algorithm that learns from large amounts of data and automatically generates new information and patterns.

[1416] "Training" is the process by which a generative machine learning algorithm learns from data and improves its accuracy.

[1417] "Automatic generation" is the process by which a system creates new documents or information without human intervention.

[1418] The "next step" is a subsequent work process or procedure in which the generated goal state information is used.

[1419] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The embodiments for carrying out the present invention will be described in detail below.

[1420] System Overview

[1421] The system mainly consists of a user, a server, and a terminal. The user accesses the system using a terminal and inputs current analysis information and target state information. The server receives and analyzes this information, trains the generative machine learning algorithm, and automatically generates new target state information.

[1422] Program Overview

[1423] 1. User input: The user inputs the current situation analysis information into the input device via a terminal. For example, the current situation analysis information may be input such as, "The process of joining part A to part B is being done manually, and each process takes 20 minutes."

[1424] 2. Data Reception and Analysis: The server receives the input current situation analysis information. The received information is analyzed using natural language processing techniques. Specifically, important keywords and phrases are extracted using open source libraries (e.g., spacy and nltk).

[1425] 3. Training a generative machine learning algorithm: The analysis results are fed into a generative machine learning algorithm for training, using an advanced generative model such as OpenAI's GPT-3.

[1426] 4. Automatic generation: When the user inputs new current situation analysis information, the server automatically generates new target state information based on the learned generative machine learning algorithm. The generated target state information might be, for example, "We will aim to reduce time by introducing an automatic joining system."

[1427] 5. Confirmation and Correction: The generated goal state information is provided to the user, who confirms it and makes corrections as necessary.

[1428] 6. Data storage and handover: The final goal state information is stored on the server and passed on to the next process.

[1429] Examples of specific examples and prompts

[1430] For example, if a user enters the following current status information:

[1431] "The process of joining part A to part B is done manually, and it takes 20 minutes per process. I would like to automate this process and reduce the time."

[1432] Example prompts for generative AI models:

[1433] "The process of joining part A to part B is done manually, and it takes 20 minutes per step. I would like to automate this process and reduce the time. Please generate a target state based on this current state."

[1434] In this way, the present invention automates the process of creating current state analysis information and target state information, reducing the number of steps and time required for creation, and reducing manual input errors.

[1435] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1436] Step 1:

[1437] The user uses a terminal to input information for analyzing the current situation. Text data about the current manufacturing process and problems is provided as input. For example, the user might enter information such as, "The process of joining part A to part B is done manually, and each process takes 20 minutes."

[1438] Step 2:

[1439] The terminal sends the entered current situation analysis information to the server. The input data is transferred to the server in text format, and the server receives it. As a result, the current situation analysis information provided by the user is aggregated on the server.

[1440] Step 3:

[1441] The server analyzes the received current situation analysis information using natural language processing technology. Specifically, it uses open source libraries (e.g., spacy and nltk) to tokenize the text data and extract important keywords and phrases. The current situation analysis information is used as input, and the analysis results are obtained as output.

[1442] Step 4:

[1443] The server provides the analysis results to a generative machine learning algorithm to train the algorithm. The analysis results are input as training data, and the generative machine learning algorithm (e.g., OpenAI's GPT-3) learns from them. The output is the algorithm's ability to generate target state information from new data.

[1444] Step 5:

[1445] The user inputs new current situation analysis information from the terminal. The input process is the same as in step 1, and information on new projects and manufacturing processes is provided.

[1446] Step 6:

[1447] The server uses a trained generative machine learning algorithm to automatically generate target state information based on new current situation analysis information. The new current situation analysis information is used as input, and generated target state information is obtained as output. For example, the generated content is "We aim to reduce time by introducing an automatic joining system."

[1448] Step 7:

[1449] The user checks the generated goal state information and corrects it if necessary. The device displays the generated goal state information, and the user checks it and provides feedback. The user's suggestions for correction are added as input, and the information is output as the final goal state information.

[1450] Step 8:

[1451] The server saves the final goal state information and passes it on to the next process. The saved data is used for future reference and for linking with other systems. The finalized goal state information is saved as input, and data that can be applied to the next process is obtained as output.

[1452] Through the above steps, the system creates and automatically generates current state analysis information and target state information, and can optimize the manufacturing process based on the information provided by the user.

[1453] 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.

[1454] The following describes in detail the embodiments of the present invention. The present invention combines an emotion engine that recognizes user emotions with an automatic generation system for current state analysis documents (AS-IS) and goal state documents (TO-BE). This system is primarily composed of users, servers, and terminals, and aims to automate document creation in upstream processes and make adjustments based on emotions.

[1455] System Overview

[1456] The system is configured as follows:

[1457] 1. User Device

[1458] An interface for users to upload current state analysis and target state documents.

[1459] The user inputs a new current situation analysis document and the emotion engine recognizes emotions.

[1460] 2. Server

[1461] It receives documents, analyzes them, trains the AI, and automatically generates and saves goal state documents.

[1462] The emotion engine analyzes the user's emotions and adjusts the system's behavior accordingly.

[1463] 3. Emotion Engine

[1464] Recognize user emotions from user input and uploaded documents.

[1465] Program processing overview

[1466] 1. User uploads a document

[1467] A user logs into the system using a terminal and uploads a current state analysis document and a target state document.

[1468] 2. The server receives and parses the document

[1469] The server receives the uploaded documents and analyzes them using natural language processing techniques, extracting important keywords and phrases and organizing them into structured data.

[1470] 3. The server trains the generative AI based on the analysis results.

[1471] The server provides the analysis results to the AI ​​and performs training. The AI ​​learns the correspondence between the current state analysis document and the target state document and constructs a generation pattern.

[1472] 4. User enters new current situation analysis document

[1473] Users upload a new current situation analysis document or enter it into a text box, and the emotion engine recognizes emotions.

[1474] 5. Emotion engine analyzes emotions

[1475] The emotion engine analyzes the user's input and identifies the user's emotion, and adjustments are made to the goal state document based on the emotion.

[1476] 6. The server automatically generates a target state document based on the new current state analysis document.

[1477] The server receives the new current state analysis document and passes it to the AI. The AI ​​automatically generates a goal state document based on the learned patterns. The analysis results of the emotion engine are also taken into account during generation.

[1478] 7. User reviews and modifies the generated goal state document

[1479] The server displays the generated goal state document on the user's device. The user checks the contents and makes corrections as necessary. The corrections are fed back to the AI.

[1480] 8. The server saves the final target state document and passes it on to the next development stage.

[1481] The server stores the final target state document and passes it on to the next development stage. Data is transferred and shared as needed.

[1482] Specific examples

[1483] Specific examples are shown below.

[1484] For Project A

[1485] A user uploads a current situation analysis document for Project A. This document describes that the current system requires manual entry of customer information, and points out that a problem with this is that input errors are frequent.

[1486] The server generates a goal state document based on this. The generated goal state document describes the introduction of the automatic input system and its benefits, such as reducing input errors.

[1487] If the emotion engine detects stress when the user reviews the document and adds specific requirements, the system displays appropriate support messages to the user, thus reducing the burden on the user and finalizing the document.

[1488] The saved goal state document is passed on to the next development process and implemented by the development team. The introduction of the emotion engine enables flexible responses according to the user's emotional state, improving the system's accuracy and user satisfaction.

[1489] The processing flow will be explained below.

[1490] Step 1:

[1491] The user logs in to the system using a terminal. After logging in, the user selects and uploads the current state analysis document and the target state document from the "Document Upload" section displayed on the main screen.

[1492] Step 2:

[1493] The server receives the uploaded documents and stores them in a specific folder, ready to be passed on to the analysis process.

[1494] Step 3:

[1495] The server uses natural language processing (NLP) techniques to analyze the text of the uploaded document, extracting keywords and phrases and organizing them into structured data, which is then used as input for the subsequent AI learning process.

[1496] Step 4:

[1497] The server provides the analysis results as training data to the generative artificial intelligence (AI). The AI ​​performs training based on the provided data and learns the correspondence between the current state analysis document and the target state document.

[1498] Step 5:

[1499] The user creates a current situation analysis document for a new project on the terminal and enters it into the text box. After completing the input, the user clicks the "Upload" button to send the document to the server.

[1500] Step 6:

[1501] The server receives a newly uploaded current situation analysis document, which describes the current system status and problems.

[1502] Step 7:

[1503] The emotion engine analyzes the newly uploaded current situation analysis document and recognizes the user's emotions. Specifically, it infers the user's emotions (e.g., stress or satisfaction) from the vocabulary and context contained in the text.

[1504] Step 8:

[1505] The server inputs the analyzed current state analysis document into the artificial intelligence generator, which then automatically generates a new target state document. The generation process also takes into account emotional data from the emotion engine.

[1506] Step 9:

[1507] The server displays the AI-generated goal state document on the user's device, and the user can review the document and modify it as needed using a text editor.

[1508] Step 10:

[1509] The user completes the document modification and clicks the Confirm button. The server saves the final target state document confirmed by the user to the database.

[1510] Step 11:

[1511] The server passes the saved final target state document to the next development stage. If necessary, it connects with other development tools and systems to transfer and share data.

[1512] Specific examples

[1513] The user inputs a current situation analysis document for Project B. This document states that "the current system manages inventory manually" and "it is difficult to grasp inventory status in real time." When the server receives and analyzes this document, the emotion engine detects stress from the user's text. As a result, the system generates a goal state document that includes elements such as "introduce an automated inventory management system" and "a low-stress interface." The user reviews this document, makes corrections, and then finalizes the version to move on to the next process.

[1514] Example 2

[1515] 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."

[1516] There are problems with the automation of the creation of current state analysis documents and goal state documents, and the lack of adjustments that take user emotions into account.In addition, there is a lack of a system that can effectively learn and automatically generate correspondences between current state analysis documents and goal state documents.

[1517] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for receiving an uploaded document and analyzing it using natural language processing technology, means for training a machine learning model based on the analysis results, means for receiving a new current situation analysis document and automatically generating a new goal state document, and means for analyzing a user's emotions using emotion recognition technology and reflecting the emotions in the goal state document. This enables automation of document creation and flexible adjustment based on the user's emotions.

[1518] A "current situation analysis document" is a document that details the current status of business operations and systems.

[1519] A "target state document" is a document that details the ideal state of a future business or system.

[1520] "Upload" is the act of a user transferring data or files from a terminal to a server.

[1521] "Natural language processing technology" is a technology that enables computers to understand, analyze, and generate human language.

[1522] "Analysis" is the act of breaking down data or information and understanding its structure and meaning.

[1523] A "machine learning model" is an algorithm that learns patterns and rules from data and makes predictions and classifications.

[1524] "Auto-generation" is the act of a system using specific algorithms to create new data or information without human intervention.

[1525] "Emotion recognition technology" is a technology for identifying emotions from user input and behavior.

[1526] "Storage" is the act of recording data or information for later reference.

[1527] "Next step" refers to the series of tasks or processes that follow the current phase.

[1528] The following describes a specific embodiment of the present invention. The present invention combines a system for automatically generating a current state analysis document and a goal state document with an emotion engine that recognizes the user's emotions. This system consists of a user, a server, and a terminal.

[1529] System Overview

[1530] The system is configured as follows:

[1531] 1. User Device

[1532] Provides an interface for users to upload current state analysis documents and target state documents.

[1533] The user inputs a new current situation analysis document and the emotion engine recognizes emotions.

[1534] 2. Server

[1535] It receives documents, analyzes them, uses AI to learn, and automatically generates and saves goal state documents.

[1536] The emotion engine analyzes the user's emotions and adjusts the system's behavior accordingly.

[1537] Specific software used includes natural language processing libraries "NLTK" and "spaCy," and machine learning libraries "TensorFlow" and "PyTorch."

[1538] 3. Emotion Engine

[1539] The app recognizes user emotions from user input and uploaded documents using IBM Watson Emotion Analysis and Microsoft Azure Emotion API.

[1540] Program processing overview

[1541] Users log in to the system using their terminals and upload their current state analysis document and target state document. The server receives these and analyzes them using natural language processing technology. Important keywords and phrases are extracted and organized as structured data.

[1542] The server provides the analysis results to the AI ​​and performs training. The AI ​​learns the correspondence between the current state analysis document and the target state document and constructs a generation pattern.

[1543] The user inputs a new current state analysis document, and the emotion engine recognizes emotions from this input. The emotion engine analyzes the user's input in real time to identify the user's emotions. Based on the emotions, adjustments are made to the goal state document.

[1544] The server receives the new current state analysis document and passes it to the AI. The AI ​​automatically generates a goal state document based on the learned patterns. The analysis results of the emotion engine are also taken into account when generating the document.

[1545] The server displays the generated goal state document on the user's device. The user checks the contents and makes corrections as necessary. The corrections are fed back to the AI.

[1546] The server saves the final target state document and passes it on to the next process, transferring and sharing data as needed.

[1547] Specific examples

[1548] For Project A

[1549] The user uploads a current state analysis document for Project A. This document describes the current situation where customer information is manually entered, resulting in frequent input errors. The server performs analysis based on this and generates a target state document. The generated target state document describes the introduction of an automatic input system and its benefits, which include reducing input errors.

[1550] If the emotion engine detects stress in the user as they review this document and add specific requests, the system will display a support message to the user, such as "Would you like some tips to help you with this task?"

[1551] The saved goal state document is passed on to the next process and implemented by the development team. The introduction of the emotion engine enables flexible responses according to the user's emotional state, improving the system's accuracy and user satisfaction.

[1552] Prompt Sentence Examples

[1553] "I have uploaded a current situation analysis document for Project A. It states that frequent input errors are a problem with the current manual data entry system. Please generate a target state document based on this. In the generated document, please state the introduction of an automated data entry system and its benefits, such as reducing input errors."

[1554] The above is a specific embodiment for carrying out the invention.

[1555] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1556] Step 1:

[1557] A user uploads a document

[1558] The user logs into the system using a terminal and selects the current state analysis document (AS-IS) and the target state document (TO-BE) in the document upload section through the web interface. Then, he clicks the "Upload" button to send these documents to the server. The current state analysis document and the target state document are the inputs, and these are sent to the server as the outputs.

[1559] Step 2:

[1560] The server receives and parses the document

[1561] The server receives documents uploaded by users. These documents are then analyzed using natural language processing (NLP) techniques. Specifically, the Python natural language processing libraries "NLTK" and "spaCy" are used to tokenize the text, extract keywords, and perform noun phrase analysis. The input is the uploaded document, and the output is structured data with keywords and important phrases extracted.

[1562] Step 3:

[1563] The server trains the generative AI based on the analysis results.

[1564] The server trains a machine learning model based on the structured data obtained through the analysis. During this process, the analysis results are provided to the AI ​​model using libraries such as TensorFlow and PyTorch for training. The input is the structured data from the analysis results, and the output is an AI model that has learned the correspondence between the current state analysis document and the target state document.

[1565] Step 4:

[1566] User enters a new current situation analysis document

[1567] The user uploads a new current situation analysis document through the system's input interface or enters it directly into a text box. The emotion engine analyzes the emotions in real time based on this input. The input is the new current situation analysis document, and the output is emotion data.

[1568] Step 5:

[1569] Emotion engine analyzes emotions

[1570] The emotion engine analyzes the user's input and identifies emotions. This analysis is performed using IBM Watson Emotion Analysis and Microsoft Azure Emotion API. Specifically, it sends text data to the API and analyzes the returned emotion data. The input is the user's text data, and the output is analyzed emotion data.

[1571] Step 6:

[1572] The server automatically generates a target state document based on the new current state analysis document.

[1573] The server passes the newly received current situation analysis document and the analysis results of the emotion engine to the AI ​​model, which then automatically generates a target state document. Using an AI model (e.g., GPT-4), the server generates a target state document that takes into account the content of the current situation analysis document and the user's emotions. The input is the new current situation analysis document and emotion data, and the output is an automatically generated target state document.

[1574] Step 7:

[1575] User reviews and modifies the generated goal state document

[1576] The server displays the generated goal state document on the user's device. The user checks the contents and makes any necessary corrections. The corrections are sent back to the server and fed back to the AI ​​model. The input is the generated goal state document and the user's corrections, and the output is the final goal state document.

[1577] Step 8:

[1578] The server saves the final goal state document and passes it on to the next process.

[1579] The server securely stores the final modified target state document. The saved document is kept in a format that can be freely used for the next process, for example, for the progress of a development project. The input is the final target state document, and the output is the saved document.

[1580] (Application example 2)

[1581] 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."

[1582] Current document creation systems simply generate and manage documents without considering the user's emotions, which means they are unable to reduce user stress and dissatisfaction. Furthermore, even in virtual stores, there is a lack of technology to analyze customer emotions in real time and respond accordingly, limiting the improvement of customer experience.

[1583] 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.

[1584] In this invention, the server includes a means for recognizing a user's emotions and providing suggestions and support based on the emotions, a means for analyzing the user's emotions in the virtual store and providing product suggestions and support messages according to the emotions, and a means for receiving and analyzing documents uploaded by the server. This enables flexible responses according to the user's emotional state, improving the accuracy of the system, user satisfaction, and the customer experience in the virtual store.

[1585] A "user" is a person who uses the system to upload, review, and modify current state analysis and / or target state documents.

[1586] The "server" is a device that receives uploaded documents, analyzes them, and performs artificial intelligence learning, automatic generation of new goal state documents, and even emotion recognition.

[1587] A "current situation analysis document" is a document that analyzes and describes the current situation and problems.

[1588] A "goal state document" is a document that describes a desired future state or goal.

[1589] "Emotion recognition" is a technology that analyzes a user's facial expressions, tone of voice, and text to identify the user's emotions.

[1590] A "virtual store" is a simulation of a store that operates on the Internet and allows users to browse and purchase products in a virtual environment.

[1591] "Product suggestion" is the act of recommending a specific product based on the user's interests and emotional state.

[1592] "Support messages" are messages that are displayed to the user for hints or assistance.

[1593] "Analysis results" are data or information obtained as a result of the server analyzing a document.

[1594] "Automatic generation" is the process by which a system uses AI technology to automatically create documents and data without manual intervention.

[1595] "Training" is the process by which the server trains the artificial intelligence based on the analysis results and improves its performance.

[1596] "Flexible response" refers to the ability of the system to adapt its behavior according to the user's emotions and circumstances.

[1597] The present invention combines an emotion engine that recognizes a user's emotions with a system for automatically generating a current state analysis document and a goal state document, and particularly provides an example of application to a virtual store.

[1598] System Configuration

[1599] The system consists of several main components:

[1600] 1. User Device

[1601] Users use devices such as smart glasses or head-mounted displays, equipped with emotion-recognition cameras and sensors.

[1602] This allows the system to sense the user's facial expressions and tone of voice in real time and transmit them as emotional data to the server.

[1603] 2. Server

[1604] The server receives the uploaded current state analysis document and target state document and analyzes them using natural language processing techniques.

[1605] The AI ​​model learns based on important keywords and phrases extracted through analysis.

[1606] By incorporating the analysis results of the user's emotions by the emotion engine, the generated goal state document is adjusted according to the user's emotions.

[1607] 3. Emotion Engine

[1608] Analyzes emotions from the user's facial expressions, tone of voice, and input text.

[1609] The analysis results are sent to the server and reflected in the document generation process and product suggestions in the virtual store.

[1610] 4. Virtual Store

[1611] The virtual store system provides appropriate product suggestions and support messages based on emotion recognition results when users browse and purchase products in a virtual space.

[1612] If the user's stress or discomfort is detected, the system will display suggestions for relaxing products and support messages.

[1613] Program processing overview

[1614] 1. Emotion recognition

[1615] The emotion engine detects and analyzes facial expressions and tone of voice through cameras and sensors installed on the user's device, using software such as OpenCV, TensorFlow, and Keras.

[1616] 2. Document Analysis and Generation

[1617] Using conventional natural language processing techniques, the current state analysis document and the target state document are analyzed and trained into an AI model. Here, key data processing techniques such as keyword extraction and phrase analysis are performed.

[1618] 3. Emotion-Based Adjustment

[1619] The server adjusts the goal state document based on the emotion analysis data provided by the emotion engine. Specifically, if the user is feeling stressed, the server displays a support message and adjusts the goal state document accordingly.

[1620] Specific examples

[1621] If a user feels "stressed" while browsing a specific product in a virtual store, the system will suggest relaxing products or play music. For example, if the emotion analysis results indicate "stress," the system will suggest "play relaxing music" or display a "discount coupon for your next purchase."

[1622] Prompt Sentence Examples

[1623] If a user is experiencing frustration while viewing the details of a particular product:

[1624] Product category: relaxation-related items

[1625] Recommended products include aroma diffusers, relaxing music CDs, and stress balls.

[1626] Message to display: 10% off coupon for your next purchase

[1627] Music to play: Classical music

[1628] The present invention enables flexible responses that are in line with the user's emotional state, contributing to improved system accuracy and user satisfaction. In particular, it is expected to significantly improve the customer experience in virtual stores.

[1629] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1630] Step 1:

[1631] Provide a means for users to upload current state analysis documents and target state documents.

[1632] Input: The user provides the current state analysis document and the target state document to the system through a file upload interface.

[1633] Output: The uploaded document is sent to the server.

[1634] Specific operation: The user operates the interface in the virtual store, selects a document, and presses the upload button. The server receives the document and stores it in the database.

[1635] Step 2:

[1636] The server receives and parses the uploaded document.

[1637] Inputs: Uploaded current state analysis document and target state document.

[1638] Output: Structured data that analyzes the document, especially extracting important keywords and phrases.

[1639] What it does: The server uses natural language processing techniques (e.g., NLTK or spaCy) to analyze the text in the document and extract keywords and related phrases.

[1640] Step 3:

[1641] The server trains the AI ​​model based on the analysis results.

[1642] Input: Document analysis results, keywords and phrases.

[1643] Output: A trained AI model.

[1644] How it works: The server feeds the extracted keywords and phrases to the AI ​​model and trains it using a machine learning algorithm (e.g., TensorFlow or PyTorch). The model learns the correspondence between the current state analysis document and the goal state document.

[1645] Step 4:

[1646] The user inputs a new current situation analysis document.

[1647] Input: The new current situation analysis document entered by the user.

[1648] Output: A new current situation analysis document sent to the server.

[1649] Specific operation: The user uses the text box in the virtual store to input a new current situation analysis document, and the input is sent to the server in real time.

[1650] Step 5:

[1651] The emotion engine recognizes emotions from user input and uploaded documents.

[1652] Input: User text input and uploaded documents.

[1653] Output: The user's emotional state (e.g., stress, joy, frustration).

[1654] Specific operation: An emotion engine (using, for example, OpenCV or Keras) analyzes the user's input text and facial expressions captured by the camera to identify emotions.

[1655] Step 6:

[1656] The server automatically generates a target state document based on the new current state analysis document.

[1657] Input: New current situation analysis document, sentiment engine analysis results, trained AI model.

[1658] Output: A goal state document.

[1659] Specific operation: The server inputs a new current situation analysis document into the AI ​​model, and then automatically generates an optimal target state document, taking into account the analysis results of the emotion engine.

[1660] Step 7:

[1661] The user reviews and modifies the generated goal state document.

[1662] Input: Generated goal state document, user review and revision.

[1663] Output: The revised goal state document.

[1664] Specific operation: The user reviews the generated goal state document and enters corrections as needed. This feedback is sent to the server, and the AI ​​model is updated.

[1665] Step 8:

[1666] The server saves the final target state document and passes it on to the next development stage.

[1667] Input: The modified goal state document.

[1668] Output: Final goal state document.

[1669] Specific operation: The server saves the final modified target state document, exports it in the format required for the next development phase, and shares it with other systems as needed.

[1670] 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.

[1671] 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.

[1672] 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.

[1673] 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.

[1674] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1675] 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.

[1676] 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).

[1677] 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.

[1678] 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."

[1679] 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.

[1680] 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).

[1681] 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.

[1682] 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.

[1683] 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.

[1684] 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.

[1685] 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.

[1686] 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.

[1687] 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.

[1688] 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.

[1689] 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.

[1690] 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.

[1691] The following is further disclosed regarding the above embodiment.

[1692] (Claim 1)

[1693] means for users to upload current state analysis documents and target state documents;

[1694] means for the server to receive and parse the uploaded document;

[1695] A means for the server to make the generating AI learn based on the analysis results;

[1696] a means for the server to receive a new current state analysis document from a user and automatically generate a new target state document;

[1697] a means for a user to review and modify the generated goal state document;

[1698] A system in which the server stores the final goal state document and includes a means to hand it over to the next development stage.

[1699] (Claim 2)

[1700] The system of claim 1, wherein the server provides analysis results to the generating artificial intelligence and performs training.

[1701] (Claim 3)

[1702] 10. The system of claim 1, further comprising a text box for a user to input a current situation analysis document.

[1703] "Example 1"

[1704] (Claim 1)

[1705] means for users to upload current state analysis documents and target state documents;

[1706] means for the server to receive the uploaded document and parse it using natural language processing techniques;

[1707] A means for the server to train the generating AI based on the analysis results;

[1708] a means for the server to receive a new current state analysis document from a user and generate a new goal state document;

[1709] A means for the generating artificial intelligence to automatically generate a goal state document based on the analysis results;

[1710] a means for a user to review and modify the generated goal state document;

[1711] A system in which the server stores the final goal state document and includes a means to hand it over to the next development stage.

[1712] (Claim 2)

[1713] 10. The system of claim 1, comprising a generative artificial intelligence that provides analytical results and performs training.

[1714] (Claim 3)

[1715] 10. The system of claim 1, further comprising a text box for a user to input a current situation analysis document.

[1716] "Application Example 1"

[1717] (Claim 1)

[1718] A means for a user to input current state analysis information and target state information;

[1719] A means for the server to receive the input information and analyze it using natural language processing technology;

[1720] A means for the server to train a generative machine learning algorithm based on the analysis results;

[1721] a means for the server to receive new current state analysis information from the user and automatically generate new target state information;

[1722] means for a user to review and modify the generated goal state information;

[1723] A system in which the server includes a means for saving the final goal state information and passing it on to the next process.

[1724] (Claim 2)

[1725] The system of claim 1, wherein the server provides the analysis results to the generative machine learning algorithm and performs training.

[1726] (Claim 3)

[1727] 10. The system of claim 1, further comprising an input device for a user to input current situation analysis information.

[1728] "Example 2: Combining Emotion Engines"

[1729] (Claim 1)

[1730] means for users to upload current state analysis documents and target state documents;

[1731] a server receiving the uploaded document and analyzing it using natural language processing techniques;

[1732] A means for the server to train a machine learning model based on the analysis results;

[1733] means for receiving a new current state analysis document from a user and automatically generating a new target state document;

[1734] A means for analyzing the user's emotions using emotion recognition technology and reflecting the emotions in the goal state document;

[1735] a means for a user to review and modify the generated goal state document;

[1736] A system that includes a means for the server to save the final goal state document and pass it on to the next process.

[1737] (Claim 2)

[1738] The system of claim 1, wherein the server provides analysis results to the machine learning model and performs training.

[1739] (Claim 3)

[1740] 10. The system of claim 1, further comprising a text entry field for a user to enter a current situation analysis document.

[1741] "Application example 2 when combining emotion engines"

[1742] New Claims

[1743] (Claim 1)

[1744] means for users to upload current state analysis documents and target state documents;

[1745] means for the server to receive and parse the uploaded document;

[1746] A means for the server to make the generating AI learn based on the analysis results;

[1747] a means for the server to receive a new current state analysis document from a user and automatically generate a new target state document;

[1748] a means for a user to review and modify the generated goal state document;

[1749] The server stores the final goal state document and passes it on to the next development stage.

[1750] a means for recognizing a user's emotions and providing emotion-based suggestions and assistance;

[1751] A system that includes a means for analyzing a user's emotions in a virtual store and providing product suggestions and support messages according to the emotions.

[1752] (Claim 2)

[1753] The system of claim 1, wherein the server provides analysis results to the generating artificial intelligence and performs training.

[1754] (Claim 3)

[1755] 10. The system of claim 1, further comprising a text box for a user to input a current situation analysis document. [Explanation of symbols]

[1756] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for users to upload current state analysis documents and target state documents; means for the server to receive and parse the uploaded document; A means for the server to make the generating AI learn based on the analysis results; a means for the server to receive a new current state analysis document from a user and automatically generate a new target state document; a means for a user to review and modify the generated goal state document; A system in which the server stores the final goal state document and includes a means to hand it over to the next development stage.

2. The system according to claim 1, wherein the server provides the analysis results to the generating artificial intelligence and performs training.

3. The system of claim 1 , further comprising a text box for a user to input a current situation analysis document.

Images