system

Abstract

Provide a system. [Solution] a means for inputting a question from a user; means for transmitting the input question to an artificial intelligence system; means for receiving a response from the artificial intelligence system; means for generating follow-up questions based on the received answers; means for continually sending said follow-up questions to said artificial intelligence system; means for determining a final answer from the artificial intelligence system; A means of summarizing and visualizing the process and results; and means for presenting the summarized and visualized information to a user.

Description

[Technical Field]

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

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

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

[0004] In modern society, identifying the root cause of complex problems is extremely difficult. Finding the problem itself is particularly difficult, and existing AI systems are unable to clarify its root cause, resulting in the time and effort it takes for people to find effective solutions. Furthermore, generative AI generates numerous outputs, but is unable to understand the causal relationships between those outputs and clarify which outputs are linked to the root cause. Therefore, an efficient approach to solving complex problems is needed. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides the following means. The system includes a means for inputting a question from a user, a means for sending the input question to an artificial intelligence system, a means for receiving an answer from the artificial intelligence system, a means for generating a follow-up question based on the received answer, a means for continuously sending the follow-up question to the artificial intelligence system, and a means for identifying a final answer from the artificial intelligence system. The system also includes a means for summarizing and visualizing the process and results, and a means for presenting the summarized and visualized information to a user. This allows a user to efficiently identify the underlying causes of complex problems and quickly find effective solutions.

[0006] A "user" is an entity that enters a question into the system and receives the results.

[0007] A "question" is a question that a user inputs to the system, and indicates the problem that the user wants to solve.

[0008] An "artificial intelligence system" is a program or network that generates answers to input questions and responds to follow-up questions about those answers.

[0009] An "answer" is the information or explanation that an artificial intelligence system outputs in response to a question.

[0010] A "follow-up question" is a question that delves deeper into the initial answer and is asked by the user to find the root cause.

[0011] "Identification" is the act of identifying and articulating the underlying cause information in the response from an AI system.

[0012] "Summarizing" is the process of summarizing multiple answers or pieces of information and putting them together concisely.

[0013] "Visualization" is a method of visually displaying information or data, such as by representing it as graphs or diagrams to make it easier to understand.

[0014] A "flowchart" is a visual representation of the steps in a process or system, showing the order and cause and effect of each step.

[0015] A "cause and effect diagram" is a visual representation of cause and effect relationships that can be used to understand the root causes of complex problems. [Brief explanation of the drawings]

[0016] [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

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] 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).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] System Overview

[0038] The system of the present invention uses an artificial intelligence system to generate answers to questions entered by users, and then identifies the root cause by continually asking "Why?", summarizing and visualizing the results for presentation. This system is composed of a server, a terminal, and a user.

[0039] System Components

[0040] 1. On the user's device:

[0041] Accepts question input.

[0042] Send a question to the server.

[0043] Receives the results from the server and displays them to the user.

[0044] 2. Server:

[0045] A question is received from the user's terminal.

[0046] Send your questions to an artificial intelligence system and receive answers.

[0047] A follow-up question ("Why?") is generated based on the answer and repeatedly sent to the artificial intelligence system.

[0048] Finally, the system generates summarized and visualized information and transmits the results to the user's terminal.

[0049] 3. Artificial Intelligence Systems:

[0050] Generate answers to questions.

[0051] Generate answers even for additional questions sent repeatedly.

[0052] Program processing flow

[0053] 1. User inputs a question

[0054] A user types a question into a terminal, for example, "What is the cause of low sales?"

[0055] 2. Receiving and sending questions

[0056] The terminal sends a user's question to the server, which then sends the question to the artificial intelligence system and receives an initial answer.

[0057] 3. Analyzing initial answers and generating follow-up questions

[0058] The server analyzes the initial answer received from the AI ​​system, generates a follow-up question, "Why?", and sends it back to the AI ​​system.

[0059] 4. Iteration

[0060] The server repeats this process as necessary, asking additional questions and answers, such as "Low sales are due to low customer satisfaction," "Why are customer satisfaction low?", "Because of poor product quality," and "Why is product quality poor?"

[0061] 5. Identifying the root cause

[0062] At some point, the server decides it has reached the root cause, which in this case is "poor supply chain management."

[0063] 6. Summarization and visualization

[0064] The server summarizes all the answers and visualizes them as flowcharts or causal diagrams, for example, generating a flowchart that shows: "Low sales → Low customer satisfaction → Low product quality → Inferior raw materials → Poor supply chain management."

[0065] 7. Displaying the results

[0066] The server generates a visualization and sends it to the user's device, where the user can view it and understand that the root cause of the low sales is "poor supply chain management."

[0067] Specific examples

[0068] For example, if a user types "What is the cause of low sales?" into a terminal, the server sends this question to the artificial intelligence system and receives the initial answer "Because of low customer satisfaction." The server then generates a follow-up question, "Why is customer satisfaction low?" and repeats this process until it finally arrives at the root cause: "Because of poor supply chain management." The results are visualized as a flowchart and displayed to the user.

[0069] The system allows users to quickly and efficiently identify the root cause of a problem, rather than just its surface area.

[0070] The processing flow will be explained below.

[0071] Step 1:

[0072] User enters a question:

[0073] Using the terminal interface, users enter questions about their problems, such as "What is the cause of low sales?"

[0074] Step 2:

[0075] The device sends a question to the server:

[0076] The terminal sends the user's input question to the server, where it is formatted to ensure that the content of the question is accurately conveyed to the server.

[0077] Step 3:

[0078] The server receives the question and sends it to the AI ​​system:

[0079] The server sends the question received from the terminal to the artificial intelligence system, where it checks that the question format can be analyzed by the AI ​​system.

[0080] Step 4:

[0081] An artificial intelligence system generates an initial answer:

[0082] The AI ​​system generates an initial answer based on the submitted question, such as "because customer satisfaction is low," and sends it back to the server.

[0083] Step 5:

[0084] The server receives the initial answer and generates a follow-up question:

[0085] The server analyzes the initial answer received from the AI ​​system, generates a follow-up question, "Why?", formats it, and sends it back to the AI ​​system.

[0086] Step 6:

[0087] Server and AI system iteration:

[0088] The server receives additional answers from the AI ​​system and continues to ask "Why?" about those answers, repeating this process until it arrives at the root cause, for example, "Why is customer satisfaction low?" → "Because the product quality is low" → "Why is the product quality low?" → "Because the raw materials are inferior."

[0089] Step 7:

[0090] Server identifies root cause:

[0091] Finally, the server identifies the root cause from the answers provided by the AI ​​system, which in this case concludes that it is due to "poor supply chain management."

[0092] Step 8:

[0093] Server summarization and visualization:

[0094] The server summarizes all the answers and questions exchanged and visualizes the causal relationships in a visually understandable format (e.g., a flowchart or causal diagram).

[0095] Step 9:

[0096] The server sends the visualized results to the terminal:

[0097] The server then sends the visualized results to the user's device, allowing the user to visually check the overall picture of the answers.

[0098] Step 10:

[0099] The terminal displays the results to the user:

[0100] The terminal displays the visualized results sent from the server to the user, who then checks the results on the terminal and understands that the root cause of low sales is "poor supply chain management."

[0101] These are the steps in which a user inputs a question, the server and the artificial intelligence system work together to identify the root cause of the problem, and then visualize the results and present them to the user.

[0102] Example 1

[0103] 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."

[0104] Conventional information processing systems often focus only on superficial problems, making it difficult to quickly and accurately identify the root cause. Furthermore, there is a lack of means to provide information in a format that allows users to easily understand the root cause of a problem, which can sometimes make the path to problem resolution unclear. In response to this, there is a need for a method to identify the root cause and visually present it to the user.

[0105] 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.

[0106] In this invention, the server includes means for inputting a question from a user, means for transmitting the input question to the data processing device, means for receiving an answer from the data processing device, means for generating a follow-up question based on the received answer, means for continuously sending follow-up questions to the data processing device, means for identifying a final answer from the data processing device, means for summarizing and visualizing the process and result, means for presenting the summarized and visualized information to the user, means for analyzing each answer and generating a follow-up question such as "Why?", and means for visualizing multiple answers and their causal relationships as a flowchart or causal diagram. This allows the user to quickly and accurately identify not only superficial answers but also root causes and to intuitively understand the information visually.

[0107] The "means for inputting a question" is a device or software that provides an interface for a user to input a question in text format.

[0108] The "means for transmitting to the data processing device" is a device or software having a communication function for transmitting the input question to the data processing device via a network.

[0109] The "means for receiving a response" is a device or software having a communication function for receiving a response sent from the data processing device.

[0110] A "means for generating follow-up questions" is an algorithm or software for automatically generating further questions based on the initial answers.

[0111] The "means for continuing to send to the data processing device" refers to a device or software having a communication function for repeatedly sending the generated additional questions to the data processing device.

[0112] The "means for identifying a final answer" is an algorithm or software for identifying a root cause from among multiple answers received from the data processing device.

[0113] The "summarization and visualization tool" is software that concisely summarizes multiple answers and their causal relationships and visually displays them in a format that is easy for users to understand.

[0114] A "means for presenting information to a user" is a device or software for displaying visualized information to a user.

[0115] The "means for generating follow-up "Why?" questions" is an algorithm or software for generating follow-up "Why?" questions for each answer.

[0116] A "causal visualization tool" is software for visualizing multiple answers and their relationships as a flowchart or causal diagram.

[0117] The specific implementation procedure for the mode for implementing the invention is described below. This system uses an artificial intelligence system to generate answers to questions entered by users, and then identifies the root cause by continually asking "Why?", and summarizes and visualizes the results for presentation. This system is composed of a server, a terminal, and a user.

[0118] System Components

[0119] 1. User's device

[0120] A question is input through a user interface.

[0121] Send the question to the server.

[0122] The results received from the server are displayed to the user.

[0123] 2. Server

[0124] A question is received from the user's terminal.

[0125] Send your questions to an artificial intelligence system and receive answers.

[0126] Based on the answers, a follow-up question, "Why?", is generated and repeatedly sent to the artificial intelligence system.

[0127] Finally, the summarized and visualized information is generated and sent to the user's terminal.

[0128] 3. Artificial Intelligence Systems

[0129] A data processing device for generating answers to questions.

[0130] It also generates answers to the follow-up question "Why?" that is repeatedly asked.

[0131] Hardware and Software

[0132] The main components of the system include:

[0133] User's device: A device that performs input and output, such as a regular PC, smartphone, or tablet.

[0134] Server: A high-performance data processing device that calls artificial intelligence models, summarizes data, visualizes data, etc.

[0135] Artificial Intelligence Systems: Utilizing generative AI models such as OpenAI®'s GPT-3® and GPT-4®.

[0136] Program processing overview

[0137] The program for this system includes the following processes:

[0138] 1. A user types a question into a terminal, for example, "What is the cause of low sales?"

[0139] 2. The device sends this question to the server, which sends it to the artificial intelligence system and receives an initial answer.

[0140] 3. The server analyzes the initial answer received from the AI ​​system, generates a follow-up question, "Why?", and sends it back to the AI ​​system.

[0141] 4. The server repeats this process, asking additional questions and answers, for example, "Low sales are due to low customer satisfaction," "Why is customer satisfaction low?", "Because the product quality is low," "Why is the product quality low?"

[0142] 5. At some point, the server determines that it has reached the root cause, which in this example is "poor supply chain management."

[0143] 6. The server summarizes all the answers and visualizes them as flowcharts or causal diagrams. For example, it generates a flowchart that shows: "Low sales → Low customer satisfaction → Low product quality → Inferior raw materials → Poor supply chain management."

[0144] 7. The server sends the visualized results to the user's device, where the user can view them and understand that the root cause of low sales is "poor supply chain management."

[0145] Specific examples

[0146] For example, if a user types "What is the cause of low sales?" into a terminal, the server sends this question to the artificial intelligence system and receives the initial answer "Because of low customer satisfaction." The server then generates a follow-up question, "Why is customer satisfaction low?" and repeats this process until it finally arrives at the root cause: "Because of poor supply chain management." The results are visualized as a flowchart and displayed to the user.

[0147] Prompt Sentence Examples

[0148] "What is the cause of low sales?"

[0149] "Why is customer satisfaction low?"

[0150] "Why is the product quality poor?"

[0151] The above is a specific embodiment for carrying out the invention, which allows the user to quickly and accurately identify the root cause of a problem, not just the surface problem.

[0152] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0153] Program processing flow

[0154] Step 1:

[0155] The user inputs a question into the terminal.

[0156] Input: User input (e.g., "What is the cause of low sales?")

[0157] Output: Text data entered into the terminal

[0158] Specific operation: The user enters a question in the text box on the terminal and presses the send button.

[0159] Step 2:

[0160] The terminal sends a question from the user to the server.

[0161] Input: Text data entered by the user

[0162] Output: HTTP request to the server

[0163] Specific operation: The device sends the entered question as an HTTP request.

[0164] Step 3:

[0165] The server receives the question and sends it to the artificial intelligence system.

[0166] Input: HTTP request (question) from the terminal

[0167] Output: Prompt to the artificial intelligence system

[0168] Specific operation: The server receives an HTTP request and sends it as a prompt to the artificial intelligence system.

[0169] Step 4:

[0170] The artificial intelligence power generates answers to the questions received.

[0171] Input: prompt (question)

[0172] Output: The generated answer

[0173] Specific operation: The AI ​​system uses natural language processing to generate an answer based on the question it receives.

[0174] Step 5:

[0175] The server analyzes the answers received from the artificial intelligence system.

[0176] Input: Answer from an artificial intelligence system

[0177] Output: Analysis results (additional questions)

[0178] Specific behavior: The server analyzes the answer text and generates a follow-up question of the form "Why?"

[0179] Step 6:

[0180] The server generates additional questions and resubmits them to the artificial intelligence system.

[0181] Input: Analysis results (additional questions)

[0182] Output: A new prompt to the artificial intelligence system

[0183] Specific operation: The server resends the additional question as a prompt to the artificial intelligence system.

[0184] Step 7:

[0185] The server repeats this process as necessary.

[0186] Input: Repeated answers from an artificial intelligence system

[0187] Output: Final answer

[0188] Specific operation: The server analyzes the answer and repeats the process of generating and sending a new question.

[0189] Step 8:

[0190] The server determines the final answer.

[0191] Input: Repeated answers

[0192] Output: Root cause (final answer)

[0193] Specific operation: The server identifies the most fundamental cause from the set of answers and determines this as the final answer.

[0194] Step 9:

[0195] The server summarizes and visualizes the process and results.

[0196] Input: All answers and their causal relationships

[0197] Output: Visualized data (flowcharts and causal diagrams)

[0198] Specific behavior: The server uses Python libraries (such as matplotlib and Graphviz) to visualize the relationships between answers.

[0199] Step 10:

[0200] The server sends the visualized results to the user's terminal.

[0201] Input: Visualization data

[0202] Output: Send data to the user's device

[0203] Specific operation: The server sends the generated visualization data to the user's device as an HTTP response.

[0204] Step 11:

[0205] The terminal displays the received results to the user.

[0206] Input: Visualization data from the server

[0207] Output: The result displayed in the user interface

[0208] Specific operation: The device displays the visualization data it receives on the screen so that the user can check it.

[0209] These are the specific processing steps of the system, which allow users to quickly identify and intuitively understand the root cause of any problem, from the surface level.

[0210] (Application example 1)

[0211] 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."

[0212] Conventional production facilities lacked the means to identify production efficiency or quality issues from operational data and quickly and efficiently identify their root causes. As a result, problem resolution took time, leading to a risk of reduced productivity. Furthermore, previous systems required users to manually track problems, often resulting in delayed analysis. This invention solves these issues and aims to improve operational efficiency in factories.

[0213] 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.

[0214] In this invention, the server includes means for inputting a question from a user, means for transmitting the input question to an artificial intelligence system, means for receiving an answer from the artificial intelligence system, means for generating a follow-up question based on the received answer, means for continuously transmitting the follow-up question to the artificial intelligence system, means for identifying a final answer from the artificial intelligence system, means for summarizing and visualizing processes and results, means for presenting the summarized and visualized information to a user, means for collecting operation data of a production facility, means for generating a question regarding a problem with production efficiency or quality based on the operation data, means for identifying a root cause for the question, and means for visualizing the identified root cause and related information, thereby enabling quick and efficient identification and analysis of the root cause of a problem in a production facility.

[0215] "User" refers to an individual or organization who uses the system to enter questions and receive final answers and visualized information.

[0216] "Means for inputting a question" refers to an interface that allows a user to input a question to the system, such as a keyboard or a touch screen.

[0217] "Means for sending questions to an AI system" refers to communications means for transmitting input questions to an AI system, such as the Internet or a local network.

[0218] "Artificial intelligence system" refers to software or hardware that automatically generates answers to questions, such as the generative AI model GPT-3.

[0219] "Means for receiving a response" refers to an interface or system for obtaining and processing a response from an artificial intelligence system.

[0220] "Means for generating follow-up questions" refers to algorithms or logic for automatically generating further follow-up questions based on the initial answers.

[0221] "Means for continuing to send follow-up questions to the artificial intelligence system" refers to communication means for repeatedly sending the generated follow-up questions to the artificial intelligence system.

[0222] "Means for identifying a final answer" refers to the logic or algorithm used to determine a final answer related to the root cause through a process of asking and answering a series of questions.

[0223] "Summarization and visualization tools" refers to software and tools that organize the responses and present them in a visually understandable format.

[0224] The "means for presenting the summarized and visualized information to the user" refers to an interface for displaying the visualized information so that the user can confirm it.

[0225] "Production equipment" is a general term for the machinery and equipment used in factories and production lines.

[0226] "Means for collecting operational data" refers to sensors and data acquisition systems for obtaining operational information and performance data from production equipment.

[0227] The "means for generating questions related to production efficiency and quality issues" refers to an algorithm for identifying issues related to production efficiency and quality based on collected operational data and automatically generating questions related to those issues.

[0228] "Means for identifying root causes" refers to analytical logic or algorithms for identifying the root causes of problems from the answers to the generated questions.

[0229] "Means for visualizing related information" refers to software or tools that provide an easy-to-understand visual display of identified root causes and related information.

[0230] The basic embodiment of this invention relates to a system for identifying the root cause of problems in factory production equipment. This system starts with user input, uses an artificial intelligence system to perform an in-depth analysis of the problem, and visualizes the results. Specifically, this system is implemented as follows.

[0231] System configuration

[0232] User's device

[0233] Question entry interface: An interface through which a user can enter a question, including a keyboard or touchscreen.

[0234] Sending and receiving module: A module for sending the entered question to the server and displaying the results received from the server.

[0235] server

[0236] Communication module: A module for communicating with user terminals to send and receive questions and answers.

[0237] AI processing module: A module that sends questions received from users to an artificial intelligence system and receives answers.

[0238] Follow-up question generation module: A module that generates follow-up questions ("Why?") based on the initial answers.

[0239] Repeated question module: A module that sends the generated additional questions to the artificial intelligence system again.

[0240] Visualization module: A module that visualizes the final answer and its related information as a flowchart or causal diagram.

[0241] Production Equipment

[0242] Data collection module: Sensors and data acquisition systems that collect operational data from production equipment in real time.

[0243] Data Analysis Module: A module that generates questions about production efficiency and quality issues based on collected data.

[0244] Software and hardware used

[0245] Generative AI models: Use generative AI models such as OpenAI's GPT-3.

[0246] Programming language: Program implemented using Python.

[0247] Visualization tools: Graph generation using Matplotlib and NetworkX.

[0248] Communication infrastructure: Internet connection and local network.

[0249] Process Description

[0250] 1. User question input: The user uses the terminal to input a question about the production equipment. A specific example is the question, "Why is the production efficiency low in line A?"

[0251] 2. Sending a question and receiving an answer: The user's device sends the entered question to the server, which then sends the question to the generative AI model, receives the initial answer from the generative AI model, and analyzes the answer.

[0252] 3. Generate and send follow-up questions: The server automatically generates a follow-up question, "Why?", based on the initial answer it received and sends this question to the generative AI model again. For example, for the answer "The machine breaks down frequently," it generates a follow-up question, "Why does the machine break down frequently?"

[0253] 4. Iterative process: This question and answer process continues until the root cause is reached.

[0254] 5. Visualization and display: Finally, the server visualizes the results of the series of questions and answers as a flowchart or causal diagram and sends it to the user's device.

[0255] Examples of concrete examples and prompts

[0256] Specific examples

[0257] If a problem of low production efficiency occurs on production line A in a factory, this system can be used to identify the root cause using the following procedure.

[0258] Q: Why is the production efficiency low in line A?

[0259] A: Because the machine breaks down frequently.

[0260] Q: Why does the machine break down frequently?

[0261] A: Because the regular maintenance is insufficient.

[0262] Q: Why is the regular maintenance insufficient?

[0263] A: Because the maintenance schedule is not properly managed.

[0264] Prompt Sentence Examples

[0265] First prompt:

[0266] "Why is the production efficiency low in line A?"

[0267] Additional prompts:

[0268] "Why does the machine breakdown frequently?"

[0269] "Why is the regular maintenance insufficient?"

[0270] "Why is the maintenance schedule not properly managed?"

[0271] In this way, it becomes possible to specifically and quickly identify the root cause of problems in production equipment.

[0272] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0273] Step 1:

[0274] User question input

[0275] The user uses the terminal to input questions about production equipment. The input questions are in the form of "Why is the production efficiency low in line A?" The terminal is equipped with an interface that allows questions to be input using a keyboard or touch screen. The input here is in text format, and that text is used in the next step.

[0276] Step 2:

[0277] Submit a Question

[0278] The user's device sends the entered question to the server. Specifically, when the user has finished entering the question on the device, they press the send button, which sends the question to the server via the network. The device uses a communication protocol such as an HTTP request to send the entered question to the server. At this stage, text data is sent from the device to the server.

[0279] Step 3:

[0280] Sending questions to an AI system

[0281] The server sends the received question to a generative AI model (e.g., GPT-3). Specifically, the server generates an API request to send the question to the AI ​​model. This request includes the question text and data for the AI ​​to answer. The server prepares to receive the answer from the AI ​​model.

[0282] Step 4:

[0283] Receiving an initial response

[0284] The server receives the answer from the generative AI model. The AI ​​model generates a text answer to the question it received, and this answer is returned to the server. For example, the answer may be "Because the machine breaks down frequently." The next step is based on this answer.

[0285] Step 5:

[0286] Generate follow-up questions

[0287] The server generates a follow-up question called "Why?" based on the initial answer. Specifically, based on the answer received, the server creates a question by asking the AI ​​model again, "Why does that state occur?" For example, the question "Why does the machine break down frequently?" is automatically generated.

[0288] Step 6:

[0289] Submitting Repeated Questions

[0290] The server then sends the generated questions to the AI ​​model again. This process is similar to step 3, sending the generated questions to the AI ​​model through the API and receiving the answers. This iterative questioning process can continue as needed.

[0291] Step 7:

[0292] Identifying the root cause

[0293] The server repeats this series of questions and answers until it determines that it has reached the root cause of the problem. For example, if the final answer is "Because the maintenance schedule is not properly managed," this answer is identified as the root cause.

[0294] Step 8:

[0295] Summarize and visualize

[0296] The server summarizes the data from a series of questions and answers and visualizes them as flowcharts or causal diagrams. Specifically, it uses NetworkX and Matplotlib to generate graphs of the relationship between questions and answers. This visualized information is used by users to help them understand the overall picture of the problem.

[0297] Step 9:

[0298] Displaying the results

[0299] The server sends the visualized flowchart or causal diagram to the user's device, which then displays the visualized information for the user to review, allowing the user to understand the root cause of the problem at a glance.

[0300] 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.

[0301] System Overview

[0302] The system of the present invention uses an artificial intelligence system to generate answers to questions entered by users, identifies the root cause by continually asking "Why?", analyzes the user's emotions using an emotion engine, and summarizes and visualizes the results for presentation. This system is composed of a server, a terminal, a user, and an emotion engine.

[0303] System Components

[0304] 1. On the user's device:

[0305] Accepts question input.

[0306] Send a question to the server.

[0307] Receives the results from the server and displays them to the user.

[0308] 2. Server:

[0309] A question is received from the user's terminal.

[0310] Send your questions to an artificial intelligence system and receive answers.

[0311] A follow-up question ("Why?") is generated based on the answer and repeatedly sent to the artificial intelligence system.

[0312] Send data to an emotion engine to analyze the user's emotions and receive the analysis results.

[0313] Finally, the system generates summarized and visualized information and transmits the results to the user's terminal.

[0314] 3. Artificial Intelligence Systems:

[0315] Generate answers to questions.

[0316] Generate answers even for additional questions sent repeatedly.

[0317] 4. Emotion Engine:

[0318] Emotional data is extracted by analyzing user input and responses.

[0319] Complementing the context of questions and answers with sentiment data.

[0320] Emotion data is sent to the server and supports the server's processing.

[0321] Program processing flow

[0322] 1. User inputs a question

[0323] A user types a question into a terminal, for example, "What is the cause of low sales?"

[0324] 2. Receiving and sending questions

[0325] The terminal sends a user's question to the server, which then sends the question to the artificial intelligence system and receives an initial answer.

[0326] 3. Analyzing initial answers and generating follow-up questions

[0327] The server analyzes the initial response received from the AI ​​system, combines the user's emotional data analyzed by the emotion engine with the response, generates a follow-up question called "Why?", formats it, and sends it back to the AI ​​system.

[0328] 4. Iteration

[0329] The server receives additional answers from the AI ​​system and continues to ask "Why?" in response to those answers, taking into account the data from the emotion engine. This process is repeated as necessary, for example, "Why is customer satisfaction low?" → "Because the product quality is low" → "Why is the product quality low?" → "Because the raw materials are inferior," until the root cause is identified.

[0330] 5. Identifying the root cause

[0331] At some point, the server decides it has reached the root cause, which in this case is "poor supply chain management."

[0332] 6. Summarization and visualization

[0333] The server summarizes all the answers and questions exchanged and visualizes the causal relationships in a visually understandable format (such as a flowchart or causal diagram). It then adjusts the visualization based on the analysis results of the emotion engine. For example, it generates a flowchart that shows "Low sales → Low customer satisfaction → Low product quality → Poor raw materials → Insufficient supply chain management."

[0334] 7. Displaying the results

[0335] The server generates a visualization and sends it to the user's device, where the user can view it and understand that the root cause of the low sales is "poor supply chain management."

[0336] Specific examples

[0337] For example, if a user types "What is the cause of low sales?" into a terminal, the server sends this question to the artificial intelligence system, which receives the initial answer "Because customer satisfaction is low." The emotion engine then analyzes the emotional data from the user's input and reactions, and the server generates a follow-up question: "Why is customer satisfaction low?" This process is repeated until the root cause is finally identified as "Because of insufficient supply chain management." The results are visualized as a flowchart, adjusted based on the emotion engine's analysis, and displayed to the user.

[0338] This system allows users to efficiently identify the root cause of a problem, rather than simply looking at the surface, through sentiment analysis, enabling them to quickly find an effective solution.

[0339] The processing flow will be explained below.

[0340] Step 1:

[0341] User enters a question:

[0342] Using the terminal interface, the user enters a question about the problem they want to solve, such as "What is the cause of low sales?"

[0343] Step 2:

[0344] The device sends a question to the server:

[0345] The terminal sends the question entered by the user to the server, which formats the question so that it can be accurately transmitted to the server.

[0346] Step 3:

[0347] The server receives the question and sends it to the AI ​​system:

[0348] The server sends the question received from the terminal to the AI ​​system, where it checks that the question is in a format that can be analyzed.

[0349] Step 4:

[0350] An artificial intelligence system generates an initial answer:

[0351] The AI ​​system generates an initial answer based on the submitted question, for example, "Because customer satisfaction is low," and sends it back to the server.

[0352] Step 5:

[0353] The server receives the initial response and sends it to the emotion engine:

[0354] The server sends the initial response received from the AI ​​system to the emotion engine, which extracts emotion data from the user's input and reactions and returns the data to the server.

[0355] Step 6:

[0356] The server generates follow-up questions based on data from the emotion engine:

[0357] The server generates a follow-up question based on the initial answer and the analysis results of the emotion engine, such as "Why is customer satisfaction so low?", and sends it to the AI ​​system.

[0358] Step 7:

[0359] The server receives the additional response and sends it back to the emotion engine:

[0360] The server sends the additional answer received from the AI ​​system to the emotion engine, which analyzes the user's emotion data again. The result is used to generate the next additional question.

[0361] Step 8:

[0362] The server receives and analyzes the final response to determine the root cause:

[0363] The server continues the iterative process, eventually arriving at a root cause such as "poor supply chain management." At this stage, the server identifies the final answer.

[0364] Step 9:

[0365] The server summarizes the answer and visualizes it:

[0366] The server summarizes all responses and generates a flowchart or causal diagram showing the causal relationships. The visualization format is adjusted based on the analysis results of the emotion engine.

[0367] Step 10:

[0368] The server sends the visualized results to the terminal:

[0369] The server transmits the visualized results to the user's terminal.

[0370] Step 11:

[0371] The terminal displays the results to the user:

[0372] The terminal displays the visualized results sent from the server to the user, who then checks the results on the terminal and understands that the root cause of low sales is "poor supply chain management."

[0373] The above are the specific processing steps in a system that combines an emotion engine, from receiving a question from a user, to identifying the root cause, visualizing it, and displaying it to the user.

[0374] Example 2

[0375] 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."

[0376] Conventional question-answering systems only provide simple answers to user questions and are unable to identify the underlying causes behind the answers. Furthermore, they lack the means to analyze and visualize dependencies in detail while taking the user's emotions into account, making it difficult for users to understand the overall picture of the problem they are facing. The objective of this invention is to provide a system that identifies the root causes of user questions and summarizes and visualizes the results while analyzing the user's emotions.

[0377] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for inputting a question from a user, means for transmitting the input question to an artificial intelligence system, means for receiving an answer from the artificial intelligence system, means for generating a follow-up question based on the received answer and analyzing the user's emotions using an emotion analysis means, means for continuously sending the follow-up question to the artificial intelligence system, means for identifying a final answer from the artificial intelligence system, means for summarizing the process and result and visualizing it based on the emotion analysis result, and means for presenting the summarized and visualized information to the user. This makes it possible to identify the root cause of a user's question and efficiently provide analysis results that take the user's emotions into consideration.

[0378] A "user" is a person or organization that enters a question into the system and receives answers or analysis results.

[0379] A "terminal" is a device that a user uses to enter a question and receive and display results from the server.

[0380] The "server" is a central computer that sends questions received from the user's terminal to the artificial intelligence system and manages the answers and analysis results.

[0381] An "artificial intelligence system" is a knowledge processing system that generates answers to user questions and responds to follow-up questions.

[0382] "Emotion analysis means" refers to technology that analyzes user input and responses to extract emotional data and complements the context of questions and answers based on that data.

[0383] A "follow-up question" is a further question that is generated based on the user's initial answer to the first question.

[0384] "Summarizing" refers to summarizing and organizing the entire question and answer process.

[0385] "Visualization" refers to converting summarized information into a visual format such as a flowchart or cause-and-effect diagram and displaying it.

[0386] The "final answer" is the root cause or solution identified at the end of the cyclical process.

[0387] A "prompt" is an input sentence that is used to enter a question into a generative AI model and obtain an answer.

[0388] System Overview

[0389] The system based on this invention generates answers to questions entered by users using a generative AI model (e.g., GPT-3), identifies the root cause by repeatedly asking "Why?", analyzes the user's emotions using emotion analysis means, and summarizes and visualizes the results for presentation. This system is composed of a server, a terminal, a user, and emotion analysis means.

[0390] Hardware and software used

[0391] Server: The central computer that processes user queries and communicates with the AI ​​system and sentiment analysis engine.

[0392] Terminal: A device operated by a user, such as a PC, smartphone, or tablet.

[0393] Generative AI models: Natural language processing models such as GPT-3.

[0394] Sentiment analysis means: An analysis engine for analyzing user input data and reactions and extracting emotional data.

[0395] Specific examples of processing

[0396] 1. User inputs a question

[0397] The user types a question into the terminal, such as: "What is the cause of low sales?"

[0398] 2. Receiving and sending questions

[0399] The device sends the user's question to the server, which then sends the question as a prompt to the generative AI model.

[0400] 3. Analyzing initial answers and generating follow-up questions

[0401] The server analyzes the initial answer received from the generative AI model. For example, if the initial answer is "Because customer satisfaction is low," the server uses sentiment analysis means to analyze the user's sentiment and then generates a follow-up question such as "Why is customer satisfaction low?"

[0402] 4. Iteration

[0403] The server receives additional answers from the generative AI model and repeats the same procedure to ask "Why?" For example, if the server receives the additional answer "The product quality is low," it then generates the question "Why is the product quality low?"

[0404] 5. Identifying the root cause

[0405] The server repeats the circular process, ultimately identifying the root cause as "insufficient supply chain management."

[0406] 6. Summarization and visualization

[0407] The server summarizes all the answers and questions and visualizes them in the form of a flowchart or causal diagram, for example, "Low sales → Low customer satisfaction → Low product quality → Inferior raw materials → Poor supply chain management."

[0408] 7. Displaying the results

[0409] The server then sends the generated visualization results to the user's device, where the user can view them and understand the root cause of the problem.

[0410] Examples of prompt statements

[0411] Initial prompt: "What is the cause of low sales?"

[0412] Follow-up prompt: "Considering the user's frustration, why is customer satisfaction low?"

[0413] This invention allows users to go beyond just superficial answers to problems and identify the root cause with sentiment analysis, allowing them to quickly find effective solutions.

[0414] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0415] Step 1:

[0416] The user enters a question

[0417] Input: The user types a text question into the input field on the device.

[0418] Action: User types question: "What is the cause of low sales?"

[0419] Output: The terminal generates text data of questions from the user.

[0420] Step 2:

[0421] The device sends a question to the server

[0422] Input: The terminal has the question text data entered by the user.

[0423] Processing: The terminal sends this query data to the server.

[0424] Output: The server receives the question text data.

[0425] Step 3:

[0426] The server sends the question to the AI ​​system.

[0427] Input: The server has the question text data received from the terminal.

[0428] Processing: The server sends a question as a prompt to the generative AI model (e.g., GPT-3).

[0429] Output: The generative AI model returns an initial answer to the question it receives.

[0430] Step 4:

[0431] The server receives and analyzes the initial response.

[0432] Input: Contains the initial answer the server received from the generative AI model.

[0433] Processing: The server analyzes the initial response and evaluates the content of the response, for example, "Because customer satisfaction is low."

[0434] Output: A server with the analysis results.

[0435] Step 5:

[0436] The server analyzes the user's emotions using emotion analysis means.

[0437] Input: The server has the user's initial input and response data.

[0438] Processing: The server sends the data to a sentiment analysis means, which analyzes the user's emotional state (e.g., "I feel frustrated").

[0439] Output: Server with sentiment analysis results.

[0440] Step 6:

[0441] The server generates a follow-up question

[0442] Input: The server has the parsed initial answer and sentiment analysis results.

[0443] Processing: The server generates a follow-up question: "Why is customer satisfaction low?"

[0444] Output: Server with additional questions.

[0445] Step 7:

[0446] The server sends additional questions to the generative AI model

[0447] Input: The server has a follow-up question.

[0448] Processing: The server sends a follow-up question to the generative AI model.

[0449] Output: The generative AI model returns an additional answer.

[0450] Step 8:

[0451] The server repeats "Why?" as needed.

[0452] Input: The server has additional answers from the generative AI model.

[0453] Processing: The server analyzes the additional responses, performs sentiment analysis again, and generates a new "Why?" question. This process is repeated until the root cause is identified.

[0454] For example, if an additional response such as "The product quality is low" is received, a new question such as "Why is the product quality low?" is generated.

[0455] Output: The server reaches the final root cause.

[0456] Step 9:

[0457] The server identifies the final answer

[0458] Input: The server has all the questions and answers.

[0459] Processing: The server identifies the root cause from the answers, for example, selecting the final answer "due to insufficient supply chain management."

[0460] Output: The server with the final answer identified.

[0461] Step 10:

[0462] The server summarizes and visualizes the process and results.

[0463] Input: The server has a set of questions and answers, as well as sentiment analysis results.

[0464] Processing: The server summarizes all interactions and visualizes them in the form of flowcharts or cause-and-effect diagrams. For example, it generates a flowchart like this: "Low sales → Low customer satisfaction → Low product quality → Poor raw materials → Poor supply chain management."

[0465] Output: A server with visualized data.

[0466] Step 11:

[0467] The server sends the visualized results to the user's device.

[0468] Input: The server has the data to be visualized.

[0469] Processing: The server sends the visualized results to the user's terminal.

[0470] Output: The visualized result received by the user's device.

[0471] Step 12:

[0472] The user checks the results

[0473] Input: The user's terminal has the visualized results.

[0474] Action: The user reviews the results on their device and understands the root cause of the problem.

[0475] Output: The user gains an understanding of the problem.

[0476] The above processing steps allow the user to navigate through the system to the root cause and visually understand the process and results.

[0477] (Application example 2)

[0478] 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."

[0479] Conventional security incident analysis systems require a great deal of time and effort to identify the root cause of a problem. In addition, they develop countermeasures without taking into account the emotional state of the person in charge of responding to the incident, which reduces the quality of the response and increases the risk of further incidents.

[0480] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting a user's question, means for sending the input question to the artificial intelligence system, means for receiving an answer from the artificial intelligence system, means for generating a follow-up question based on the received answer, means for continuously sending follow-up questions to the artificial intelligence system, means for identifying a final answer from the artificial intelligence system, means for summarizing and visualizing the process and result, means for presenting the summarized and visualized information to the user, emotion analysis means for analyzing the user's emotions, means for complementing the question based on the emotion data analyzed by the emotion analysis means, and means for presenting appropriate countermeasures according to the user's emotional state. This makes it possible to quickly and efficiently identify the root cause of a security incident and propose appropriate countermeasures that take into account the emotional state of the person in charge.

[0481] The "means for inputting questions from the user" is an interface that allows the user to input questions about security incidents into the system.

[0482] The "means for transmitting an input question to the artificial intelligence system" is a communication means for transmitting a question input by a user to the artificial intelligence system.

[0483] The "means for receiving a response from an artificial intelligence system" refers to a means for receiving a response generated by the artificial intelligence system.

[0484] The "means for generating a follow-up question based on the received answer" refers to a means for generating a new question based on the answer received from the artificial intelligence system.

[0485] The "means for continuing to send follow-up questions to the artificial intelligence system" refers to a means for repeatedly sending the generated follow-up questions to the artificial intelligence system.

[0486] "Means for identifying a final answer from an artificial intelligence system" refers to a means for identifying a final root cause through multiple exchanges of questions and answers.

[0487] "Means for summarizing and visualizing processes and results" are means for summarizing the question and answer process and visually displaying the results.

[0488] The "means for presenting summarized and visualized information to a user" refers to a means for displaying summarized and visualized information to a user.

[0489] The "emotion analysis means for analyzing the user's emotions" is a means for extracting and analyzing emotion data from the user's inputs and reactions.

[0490] The "means for completing a question based on emotion data analyzed by the emotion analysis means" is a means for generating or completing a question based on data obtained by emotion analysis.

[0491] The "means for presenting appropriate countermeasures according to the emotional state of the user" is a means for presenting appropriate countermeasures to the user based on the results of emotion analysis.

[0492] The system for implementing the present invention supports the process of a user inputting questions about a security incident and identifying its root cause. The system mainly includes the following components:

[0493] 1. User's device

[0494] It accepts questions from users, sends them to the server, and receives and displays the results from the server. A typical smartphone or head-mounted display (HMD) can be used.

[0495] 2. Server

[0496] The system receives questions from the user's device, sends them to the AI ​​system, and receives answers. It then generates additional questions based on the received answers and sends them back to the AI ​​system. It identifies the final answer, summarizes and visualizes the process and results, and uses emotion analysis to analyze the user's emotions. It complements the questions based on the results and presents appropriate countermeasures to the user.

[0497] 3. Artificial Intelligence Systems

[0498] The system generates answers to user questions and continues to generate answers to follow-up questions. This artificial intelligence system uses a generative AI model that utilizes natural language processing technology.

[0499] 4. Emotion analysis method

[0500] Emotional data is extracted from the user's input and responses and analyzed. Based on this data, the system can complete questions and suggest appropriate countermeasures.

[0501] When a user enters a question about the cause of a security incident, the question is sent to the server via the terminal. The server receives the question and sends it to the AI ​​system. The AI ​​system then receives an initial answer and generates a follow-up question based on that answer. These follow-up questions are in the "Why?" format and are repeatedly generated and sent to the AI ​​system until the root cause is identified.

[0502] The emotion analysis means collects and analyzes emotional data obtained from user input and responses. Based on the analysis results, the server complements the question and presents appropriate responses according to the user's emotional state.

[0503] For example, if a user asks, "Why did the server go down?", the initial answer generated is "Because the server was overloaded." In response to this answer, the server generates a follow-up question, "Why was the server overloaded?" and repeatedly sends this to the AI ​​system. Eventually, the root cause is identified as "inappropriate resource management." During this time, the emotion analysis means assesses the user's stress level and suggests appropriate breaks or assistance as needed.

[0504] In this way, the present invention is a system that can improve the efficiency of analyzing the causes of security incidents and also propose countermeasures that take into account the user's emotional state.

[0505] Example prompt sentence:

[0506] Why did the server go down?

[0507] Why was the server overloaded?

[0508] "Users are stressed"

[0509] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0510] Step 1:

[0511] The user enters a question about the security incident.

[0512] Input: A user-asked question (e.g., "Why is the server down?")

[0513] Output: A query request from the user's device to the server

[0514] Specific operation: The user inputs a question into the interface using a smartphone or HMD.

[0515] Step 2:

[0516] The server sends the question received from the user terminal to the artificial intelligence system.

[0517] Input: Question sent from user device

[0518] Output: A question request to the AI ​​system

[0519] Specific operation: The server converts the question into JSON format and sends it to the artificial intelligence system via an HTTP request.

[0520] Step 3:

[0521] An artificial intelligence system generates initial answers to questions.

[0522] Input: The question sent by the server

[0523] Output: Initial response (e.g. "Because the server load was high")

[0524] Specific operation: The artificial intelligence system uses a generative AI model to generate answers to questions using natural language processing techniques.

[0525] Step 4:

[0526] The server receives the response from the artificial intelligence system.

[0527] Input: Initial response sent by the artificial intelligence system

[0528] Output: Response received at server

[0529] Specific operation: The server receives the HTTP response, parses the JSON formatted answer and stores it in the database.

[0530] Step 5:

[0531] The server generates additional questions based on the answers it receives and sends them back to the artificial intelligence system.

[0532] Input: Initial response (e.g., "Because the server load was high")

[0533] Output: Follow-up questions (e.g., "Why was the server overloaded?") and their submission

[0534] Specific operation: The server generates additional questions and creates another HTTP request and sends it to the artificial intelligence system.

[0535] Step 6:

[0536] An artificial intelligence system generates answers to follow-up questions.

[0537] Input: Follow-up question (e.g., "Why was the server so busy?")

[0538] Output: Additional answer (e.g., "Because of poor resource management")

[0539] Specific operation: The artificial intelligence system again uses the generative AI model to generate answers to follow-up questions.

[0540] Step 7:

[0541] The server receives additional answers from the artificial intelligence system.

[0542] Input: Additional answers sent by the AI ​​system

[0543] Output: Additional answers received at the server

[0544] Specific operation: The server receives the HTTP response and stores the answer in a database.

[0545] Step 8:

[0546] This is repeated until the server repeatedly generates additional questions as needed and sends them to the artificial intelligence system.

[0547] Input: Multiple answers and questions

[0548] Output: Final root cause (e.g., "Poor resource management")

[0549] Specific behavior: The server iterates, exchanging additional questions and answers until a certain condition is met.

[0550] Step 9:

[0551] The server summarizes and visualizes the process and results.

[0552] Input: History of all questions and answers

[0553] Output: Summarized and visualized information (e.g., flowchart)

[0554] Specific operation: The server analyzes the information stored in the database and visualizes it as a flowchart or causal diagram.

[0555] Step 10:

[0556] The server transmits the summarized and visualized information to the user terminal and presents it to the user.

[0557] Input: Summarized and visualized information

[0558] Output: Display information on the user's terminal

[0559] Specific operation: The server sends the visualized information to the user's terminal as an HTTP response and displays it to the user.

[0560] Step 11:

[0561] The server analyzes the user's emotions and completes the questions and answers.

[0562] Input: User input and responses

[0563] Output: Question completion and response suggestions based on emotion data

[0564] Specific operation: The server analyzes the user's emotional data using emotion analysis means and reflects the data in questions and answers as necessary. It also generates and presents appropriate countermeasures according to the user's emotional state.

[0565] 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.

[0566] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0567] 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.

[0568] [Second embodiment]

[0569] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0570] 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.

[0571] 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).

[0572] 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.

[0573] 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.

[0574] 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).

[0575] 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. 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.

[0576] 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.

[0577] 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.

[0578] 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.

[0579] 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.

[0580] 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."

[0581] System Overview

[0582] The system of the present invention uses an artificial intelligence system to generate answers to questions entered by users, and then identifies the root cause by continually asking "Why?", summarizing and visualizing the results for presentation. This system is composed of a server, a terminal, and a user.

[0583] System Components

[0584] 1. On the user's device:

[0585] Accepts question input.

[0586] Send a question to the server.

[0587] Receives the results from the server and displays them to the user.

[0588] 2. Server:

[0589] A question is received from the user's terminal.

[0590] Send your questions to an artificial intelligence system and receive answers.

[0591] A follow-up question ("Why?") is generated based on the answer and repeatedly sent to the artificial intelligence system.

[0592] Finally, the system generates summarized and visualized information and transmits the results to the user's terminal.

[0593] 3. Artificial Intelligence Systems:

[0594] Generate answers to questions.

[0595] Generate answers even for additional questions sent repeatedly.

[0596] Program processing flow

[0597] 1. User inputs a question

[0598] A user types a question into a terminal, for example, "What is the cause of low sales?"

[0599] 2. Receiving and sending questions

[0600] The terminal sends a user's question to the server, which then sends the question to the artificial intelligence system and receives an initial answer.

[0601] 3. Analyzing initial answers and generating follow-up questions

[0602] The server analyzes the initial answer received from the AI ​​system, generates a follow-up question, "Why?", and sends it back to the AI ​​system.

[0603] 4. Iteration

[0604] The server repeats this process as necessary, asking additional questions and answers, such as "Low sales are due to low customer satisfaction," "Why are customer satisfaction low?", "Because of poor product quality," and "Why is product quality poor?"

[0605] 5. Identifying the root cause

[0606] At some point, the server decides it has reached the root cause, which in this case is "poor supply chain management."

[0607] 6. Summarization and visualization

[0608] The server summarizes all the answers and visualizes them as flowcharts or causal diagrams, for example, generating a flowchart that shows: "Low sales → Low customer satisfaction → Low product quality → Inferior raw materials → Poor supply chain management."

[0609] 7. Displaying the results

[0610] The server generates a visualization and sends it to the user's device, where the user can view it and understand that the root cause of the low sales is "poor supply chain management."

[0611] Specific examples

[0612] For example, if a user types "What is the cause of low sales?" into a terminal, the server sends this question to the artificial intelligence system and receives the initial answer "Because of low customer satisfaction." The server then generates a follow-up question, "Why is customer satisfaction low?" and repeats this process until it finally arrives at the root cause: "Because of poor supply chain management." The results are visualized as a flowchart and displayed to the user.

[0613] The system allows users to quickly and efficiently identify the root cause of a problem, rather than just its surface area.

[0614] The processing flow will be explained below.

[0615] Step 1:

[0616] User enters a question:

[0617] Using the terminal interface, users enter questions about their problems, such as "What is the cause of low sales?"

[0618] Step 2:

[0619] The device sends a question to the server:

[0620] The terminal sends the user's input question to the server, where it is formatted to ensure that the content of the question is accurately conveyed to the server.

[0621] Step 3:

[0622] The server receives the question and sends it to the AI ​​system:

[0623] The server sends the question received from the terminal to the artificial intelligence system, where it checks that the question format can be analyzed by the AI ​​system.

[0624] Step 4:

[0625] An artificial intelligence system generates an initial answer:

[0626] The AI ​​system generates an initial answer based on the submitted question, such as "because customer satisfaction is low," and sends it back to the server.

[0627] Step 5:

[0628] The server receives the initial answer and generates a follow-up question:

[0629] The server analyzes the initial answer received from the AI ​​system, generates a follow-up question, "Why?", formats it, and sends it back to the AI ​​system.

[0630] Step 6:

[0631] Server and AI system iteration:

[0632] The server receives additional answers from the AI ​​system and continues to ask "Why?" about those answers, repeating this process until it arrives at the root cause, for example, "Why is customer satisfaction low?" → "Because the product quality is low" → "Why is the product quality low?" → "Because the raw materials are inferior."

[0633] Step 7:

[0634] Server identifies root cause:

[0635] Finally, the server identifies the root cause from the answers provided by the AI ​​system, which in this case concludes that it is due to "poor supply chain management."

[0636] Step 8:

[0637] Server summarization and visualization:

[0638] The server summarizes all the answers and questions exchanged and visualizes the causal relationships in a visually understandable format (e.g., a flowchart or causal diagram).

[0639] Step 9:

[0640] The server sends the visualized results to the terminal:

[0641] The server then sends the visualized results to the user's device, allowing the user to visually check the overall picture of the answers.

[0642] Step 10:

[0643] The terminal displays the results to the user:

[0644] The terminal displays the visualized results sent from the server to the user, who then checks the results on the terminal and understands that the root cause of low sales is "poor supply chain management."

[0645] These are the steps in which a user inputs a question, the server and the artificial intelligence system work together to identify the root cause of the problem, and then visualize the results and present them to the user.

[0646] Example 1

[0647] 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."

[0648] Conventional information processing systems often focus only on superficial problems, making it difficult to quickly and accurately identify the root cause. Furthermore, there is a lack of means to provide information in a format that allows users to easily understand the root cause of a problem, which can sometimes make the path to problem resolution unclear. In response to this, there is a need for a method to identify the root cause and visually present it to the user.

[0649] 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.

[0650] In this invention, the server includes means for inputting a question from a user, means for transmitting the input question to the data processing device, means for receiving an answer from the data processing device, means for generating a follow-up question based on the received answer, means for continuously sending follow-up questions to the data processing device, means for identifying a final answer from the data processing device, means for summarizing and visualizing the process and result, means for presenting the summarized and visualized information to the user, means for analyzing each answer and generating a follow-up question such as "Why?", and means for visualizing multiple answers and their causal relationships as a flowchart or causal diagram. This allows the user to quickly and accurately identify not only superficial answers but also root causes and to intuitively understand the information visually.

[0651] The "means for inputting a question" is a device or software that provides an interface for a user to input a question in text format.

[0652] The "means for transmitting to the data processing device" is a device or software having a communication function for transmitting the input question to the data processing device via a network.

[0653] The "means for receiving a response" is a device or software having a communication function for receiving a response sent from the data processing device.

[0654] A "means for generating follow-up questions" is an algorithm or software for automatically generating further questions based on the initial answers.

[0655] The "means for continuing to send to the data processing device" refers to a device or software having a communication function for repeatedly sending the generated additional questions to the data processing device.

[0656] The "means for identifying a final answer" is an algorithm or software for identifying a root cause from among multiple answers received from the data processing device.

[0657] The "summarization and visualization tool" is software that concisely summarizes multiple answers and their causal relationships and visually displays them in a format that is easy for users to understand.

[0658] A "means for presenting information to a user" is a device or software for displaying visualized information to a user.

[0659] The "means for generating follow-up "Why?" questions" is an algorithm or software for generating follow-up "Why?" questions for each answer.

[0660] A "causal visualization tool" is software for visualizing multiple answers and their relationships as a flowchart or causal diagram.

[0661] The specific implementation procedure for the mode for implementing the invention is described below. This system uses an artificial intelligence system to generate answers to questions entered by users, and then identifies the root cause by continually asking "Why?", and summarizes and visualizes the results for presentation. This system is composed of a server, a terminal, and a user.

[0662] System Components

[0663] 1. User's device

[0664] A question is input through a user interface.

[0665] Send the question to the server.

[0666] The results received from the server are displayed to the user.

[0667] 2. Server

[0668] A question is received from the user's terminal.

[0669] Send your questions to an artificial intelligence system and receive answers.

[0670] Based on the answers, a follow-up question, "Why?", is generated and repeatedly sent to the artificial intelligence system.

[0671] Finally, the summarized and visualized information is generated and sent to the user's terminal.

[0672] 3. Artificial Intelligence Systems

[0673] A data processing device for generating answers to questions.

[0674] It also generates answers to the follow-up question "Why?" that is repeatedly asked.

[0675] Hardware and Software

[0676] The main components of the system include:

[0677] User's device: A device that performs input and output, such as a regular PC, smartphone, or tablet.

[0678] Server: A high-performance data processing device that calls artificial intelligence models, summarizes data, visualizes data, etc.

[0679] Artificial intelligence systems: Use generative AI models such as OpenAI's GPT-3 and GPT-4.

[0680] Program processing overview

[0681] The program for this system includes the following processes:

[0682] 1. A user types a question into a terminal, for example, "What is the cause of low sales?"

[0683] 2. The device sends this question to the server, which sends it to the artificial intelligence system and receives an initial answer.

[0684] 3. The server analyzes the initial answer received from the AI ​​system, generates a follow-up question, "Why?", and sends it back to the AI ​​system.

[0685] 4. The server repeats this process, asking additional questions and answers, for example, "Low sales are due to low customer satisfaction," "Why is customer satisfaction low?", "Because the product quality is low," "Why is the product quality low?"

[0686] 5. At some point, the server determines that it has reached the root cause, which in this example is "poor supply chain management."

[0687] 6. The server summarizes all the answers and visualizes them as flowcharts or causal diagrams. For example, it generates a flowchart that shows: "Low sales → Low customer satisfaction → Low product quality → Inferior raw materials → Poor supply chain management."

[0688] 7. The server sends the visualized results to the user's device, where the user can view them and understand that the root cause of low sales is "poor supply chain management."

[0689] Specific examples

[0690] For example, if a user types "What is the cause of low sales?" into a terminal, the server sends this question to the artificial intelligence system and receives the initial answer "Because of low customer satisfaction." The server then generates a follow-up question, "Why is customer satisfaction low?" and repeats this process until it finally arrives at the root cause: "Because of poor supply chain management." The results are visualized as a flowchart and displayed to the user.

[0691] Prompt Sentence Examples

[0692] "What is the cause of low sales?"

[0693] "Why is customer satisfaction low?"

[0694] "Why is the product quality poor?"

[0695] The above is a specific embodiment for carrying out the invention, which allows the user to quickly and accurately identify the root cause of a problem, not just the surface problem.

[0696] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0697] Program processing flow

[0698] Step 1:

[0699] The user inputs a question into the terminal.

[0700] Input: User input (e.g., "What is the cause of low sales?")

[0701] Output: Text data entered into the terminal

[0702] Specific operation: The user enters a question in the text box on the terminal and presses the send button.

[0703] Step 2:

[0704] The terminal sends a question from the user to the server.

[0705] Input: Text data entered by the user

[0706] Output: HTTP request to the server

[0707] Specific operation: The device sends the entered question as an HTTP request.

[0708] Step 3:

[0709] The server receives the question and sends it to the artificial intelligence system.

[0710] Input: HTTP request (question) from the terminal

[0711] Output: Prompt to the artificial intelligence system

[0712] Specific operation: The server receives an HTTP request and sends it as a prompt to the artificial intelligence system.

[0713] Step 4:

[0714] The artificial intelligence power generates answers to the questions received.

[0715] Input: prompt (question)

[0716] Output: The generated answer

[0717] Specific operation: The AI ​​system uses natural language processing to generate an answer based on the question it receives.

[0718] Step 5:

[0719] The server analyzes the answers received from the artificial intelligence system.

[0720] Input: Answer from an artificial intelligence system

[0721] Output: Analysis results (additional questions)

[0722] Specific behavior: The server analyzes the answer text and generates a follow-up question of the form "Why?"

[0723] Step 6:

[0724] The server generates additional questions and resubmits them to the artificial intelligence system.

[0725] Input: Analysis results (additional questions)

[0726] Output: A new prompt to the artificial intelligence system

[0727] Specific operation: The server resends the additional question as a prompt to the artificial intelligence system.

[0728] Step 7:

[0729] The server repeats this process as necessary.

[0730] Input: Repeated answers from an artificial intelligence system

[0731] Output: Final answer

[0732] Specific operation: The server analyzes the answer and repeats the process of generating and sending a new question.

[0733] Step 8:

[0734] The server determines the final answer.

[0735] Input: Repeated answers

[0736] Output: Root cause (final answer)

[0737] Specific operation: The server identifies the most fundamental cause from the set of answers and determines this as the final answer.

[0738] Step 9:

[0739] The server summarizes and visualizes the process and results.

[0740] Input: All answers and their causal relationships

[0741] Output: Visualized data (flowcharts and causal diagrams)

[0742] Specific behavior: The server uses Python libraries (such as matplotlib and Graphviz) to visualize the relationships between answers.

[0743] Step 10:

[0744] The server sends the visualized results to the user's terminal.

[0745] Input: Visualization data

[0746] Output: Send data to the user's device

[0747] Specific operation: The server sends the generated visualization data to the user's device as an HTTP response.

[0748] Step 11:

[0749] The terminal displays the received results to the user.

[0750] Input: Visualization data from the server

[0751] Output: The result displayed in the user interface

[0752] Specific operation: The device displays the visualization data it receives on the screen so that the user can check it.

[0753] These are the specific processing steps of the system, which allow users to quickly identify and intuitively understand the root cause of any problem, from the surface level.

[0754] (Application example 1)

[0755] 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."

[0756] Conventional production facilities lacked the means to identify production efficiency or quality issues from operational data and quickly and efficiently identify their root causes. As a result, problem resolution took time, leading to a risk of reduced productivity. Furthermore, previous systems required users to manually track problems, often resulting in delayed analysis. This invention solves these issues and aims to improve operational efficiency in factories.

[0757] 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.

[0758] In this invention, the server includes means for inputting a question from a user, means for transmitting the input question to an artificial intelligence system, means for receiving an answer from the artificial intelligence system, means for generating a follow-up question based on the received answer, means for continuously transmitting the follow-up question to the artificial intelligence system, means for identifying a final answer from the artificial intelligence system, means for summarizing and visualizing processes and results, means for presenting the summarized and visualized information to a user, means for collecting operation data of a production facility, means for generating a question regarding a problem with production efficiency or quality based on the operation data, means for identifying a root cause for the question, and means for visualizing the identified root cause and related information, thereby enabling quick and efficient identification and analysis of the root cause of a problem in a production facility.

[0759] "User" refers to an individual or organization who uses the system to enter questions and receive final answers and visualized information.

[0760] "Means for inputting a question" refers to an interface that allows a user to input a question to the system, such as a keyboard or a touch screen.

[0761] "Means for sending questions to an AI system" refers to communications means for transmitting input questions to an AI system, such as the Internet or a local network.

[0762] "Artificial intelligence system" refers to software or hardware that automatically generates answers to questions, such as the generative AI model GPT-3.

[0763] "Means for receiving a response" refers to an interface or system for obtaining and processing a response from an artificial intelligence system.

[0764] "Means for generating follow-up questions" refers to algorithms or logic for automatically generating further follow-up questions based on the initial answers.

[0765] "Means for continuing to send follow-up questions to the artificial intelligence system" refers to communication means for repeatedly sending the generated follow-up questions to the artificial intelligence system.

[0766] "Means for identifying a final answer" refers to the logic or algorithm used to determine a final answer related to the root cause through a process of asking and answering a series of questions.

[0767] "Summarization and visualization tools" refers to software and tools that organize the responses and present them in a visually understandable format.

[0768] The "means for presenting the summarized and visualized information to the user" refers to an interface for displaying the visualized information so that the user can confirm it.

[0769] "Production equipment" is a general term for the machinery and equipment used in factories and production lines.

[0770] "Means for collecting operational data" refers to sensors and data acquisition systems for obtaining operational information and performance data from production equipment.

[0771] The "means for generating questions related to production efficiency and quality issues" refers to an algorithm for identifying issues related to production efficiency and quality based on collected operational data and automatically generating questions related to those issues.

[0772] "Means for identifying root causes" refers to analytical logic or algorithms for identifying the root causes of problems from the answers to the generated questions.

[0773] "Means for visualizing related information" refers to software or tools that provide an easy-to-understand visual display of identified root causes and related information.

[0774] The basic embodiment of this invention relates to a system for identifying the root cause of problems in factory production equipment. This system starts with user input, uses an artificial intelligence system to perform an in-depth analysis of the problem, and visualizes the results. Specifically, this system is implemented as follows.

[0775] System configuration

[0776] User's device

[0777] Question entry interface: An interface through which a user can enter a question, including a keyboard or touchscreen.

[0778] Sending and receiving module: A module for sending the entered question to the server and displaying the results received from the server.

[0779] server

[0780] Communication module: A module for communicating with user terminals to send and receive questions and answers.

[0781] AI processing module: A module that sends questions received from users to an artificial intelligence system and receives answers.

[0782] Follow-up question generation module: A module that generates follow-up questions ("Why?") based on the initial answers.

[0783] Repeated question module: A module that sends the generated additional questions to the artificial intelligence system again.

[0784] Visualization module: A module that visualizes the final answer and its related information as a flowchart or causal diagram.

[0785] Production Equipment

[0786] Data collection module: Sensors and data acquisition systems that collect operational data from production equipment in real time.

[0787] Data Analysis Module: A module that generates questions about production efficiency and quality issues based on collected data.

[0788] Software and hardware used

[0789] Generative AI models: Use generative AI models such as OpenAI's GPT-3.

[0790] Programming language: Program implemented using Python.

[0791] Visualization tools: Graph generation using Matplotlib and NetworkX.

[0792] Communication infrastructure: Internet connection and local network.

[0793] Process Description

[0794] 1. User question input: The user uses the terminal to input a question about the production equipment. A specific example is the question, "Why is the production efficiency low in line A?"

[0795] 2. Sending a question and receiving an answer: The user's device sends the entered question to the server, which then sends the question to the generative AI model, receives the initial answer from the generative AI model, and analyzes the answer.

[0796] 3. Generate and send follow-up questions: The server automatically generates a follow-up question, "Why?", based on the initial answer it received and sends this question to the generative AI model again. For example, for the answer "The machine breaks down frequently," it generates a follow-up question, "Why does the machine break down frequently?"

[0797] 4. Iterative process: This question and answer process continues until the root cause is reached.

[0798] 5. Visualization and display: Finally, the server visualizes the results of the series of questions and answers as a flowchart or causal diagram and sends it to the user's device.

[0799] Examples of concrete examples and prompts

[0800] Specific examples

[0801] If a problem of low production efficiency occurs on production line A in a factory, this system can be used to identify the root cause using the following procedure.

[0802] Q: Why is the production efficiency low in line A?

[0803] A: Because the machine breaks down frequently.

[0804] Q: Why does the machine break down frequently?

[0805] A: Because the regular maintenance is insufficient.

[0806] Q: Why is the regular maintenance insufficient?

[0807] A: Because the maintenance schedule is not properly managed.

[0808] Prompt Sentence Examples

[0809] First prompt:

[0810] "Why is the production efficiency low in line A?"

[0811] Additional prompts:

[0812] "Why does the machine breakdown frequently?"

[0813] "Why is the regular maintenance insufficient?"

[0814] "Why is the maintenance schedule not properly managed?"

[0815] In this way, it becomes possible to specifically and quickly identify the root cause of problems in production equipment.

[0816] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0817] Step 1:

[0818] User question input

[0819] The user uses the terminal to input questions about production equipment. The input questions are in the form of "Why is the production efficiency low in line A?" The terminal is equipped with an interface that allows questions to be input using a keyboard or touch screen. The input here is in text format, and that text is used in the next step.

[0820] Step 2:

[0821] Submit a Question

[0822] The user's device sends the entered question to the server. Specifically, when the user has finished entering the question on the device, they press the send button, which sends the question to the server via the network. The device uses a communication protocol such as an HTTP request to send the entered question to the server. At this stage, text data is sent from the device to the server.

[0823] Step 3:

[0824] Sending questions to an AI system

[0825] The server sends the received question to a generative AI model (e.g., GPT-3). Specifically, the server generates an API request to send the question to the AI ​​model. This request includes the question text and data for the AI ​​to answer. The server prepares to receive the answer from the AI ​​model.

[0826] Step 4:

[0827] Receiving an initial response

[0828] The server receives the answer from the generative AI model. The AI ​​model generates a text answer to the question it received, and this answer is returned to the server. For example, the answer may be "Because the machine breaks down frequently." The next step is based on this answer.

[0829] Step 5:

[0830] Generate follow-up questions

[0831] The server generates a follow-up question called "Why?" based on the initial answer. Specifically, based on the answer received, the server creates a question by asking the AI ​​model again, "Why does that state occur?" For example, the question "Why does the machine break down frequently?" is automatically generated.

[0832] Step 6:

[0833] Submitting Repeated Questions

[0834] The server then sends the generated questions to the AI ​​model again. This process is similar to step 3, sending the generated questions to the AI ​​model through the API and receiving the answers. This iterative questioning process can continue as needed.

[0835] Step 7:

[0836] Identifying the root cause

[0837] The server repeats this series of questions and answers until it determines that it has reached the root cause of the problem. For example, if the final answer is "Because the maintenance schedule is not properly managed," this answer is identified as the root cause.

[0838] Step 8:

[0839] Summarize and visualize

[0840] The server summarizes the data from a series of questions and answers and visualizes them as flowcharts or causal diagrams. Specifically, it uses NetworkX and Matplotlib to generate graphs of the relationship between questions and answers. This visualized information is used by users to help them understand the overall picture of the problem.

[0841] Step 9:

[0842] Displaying the results

[0843] The server sends the visualized flowchart or causal diagram to the user's device, which then displays the visualized information for the user to review, allowing the user to understand the root cause of the problem at a glance.

[0844] 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.

[0845] System Overview

[0846] The system of the present invention uses an artificial intelligence system to generate answers to questions entered by users, identifies the root cause by continually asking "Why?", analyzes the user's emotions using an emotion engine, and summarizes and visualizes the results for presentation. This system is composed of a server, a terminal, a user, and an emotion engine.

[0847] System Components

[0848] 1. On the user's device:

[0849] Accepts question input.

[0850] Send a question to the server.

[0851] Receives the results from the server and displays them to the user.

[0852] 2. Server:

[0853] A question is received from the user's terminal.

[0854] Send your questions to an artificial intelligence system and receive answers.

[0855] A follow-up question ("Why?") is generated based on the answer and repeatedly sent to the artificial intelligence system.

[0856] Send data to an emotion engine to analyze the user's emotions and receive the analysis results.

[0857] Finally, the system generates summarized and visualized information and transmits the results to the user's terminal.

[0858] 3. Artificial Intelligence Systems:

[0859] Generate answers to questions.

[0860] Generate answers even for additional questions sent repeatedly.

[0861] 4. Emotion Engine:

[0862] Emotional data is extracted by analyzing user input and responses.

[0863] Complementing the context of questions and answers with sentiment data.

[0864] Emotion data is sent to the server and supports the server's processing.

[0865] Program processing flow

[0866] 1. User inputs a question

[0867] A user types a question into a terminal, for example, "What is the cause of low sales?"

[0868] 2. Receiving and sending questions

[0869] The terminal sends a user's question to the server, which then sends the question to the artificial intelligence system and receives an initial answer.

[0870] 3. Analyzing initial answers and generating follow-up questions

[0871] The server analyzes the initial response received from the AI ​​system, combines the user's emotional data analyzed by the emotion engine with the response, generates a follow-up question called "Why?", formats it, and sends it back to the AI ​​system.

[0872] 4. Iteration

[0873] The server receives additional answers from the AI ​​system and continues to ask "Why?" in response to those answers, taking into account the data from the emotion engine. This process is repeated as necessary, for example, "Why is customer satisfaction low?" → "Because the product quality is low" → "Why is the product quality low?" → "Because the raw materials are inferior," until the root cause is identified.

[0874] 5. Identifying the root cause

[0875] At some point, the server decides it has reached the root cause, which in this case is "poor supply chain management."

[0876] 6. Summarization and visualization

[0877] The server summarizes all the answers and questions exchanged and visualizes the causal relationships in a visually understandable format (such as a flowchart or causal diagram). It then adjusts the visualization based on the analysis results of the emotion engine. For example, it generates a flowchart that shows "Low sales → Low customer satisfaction → Low product quality → Poor raw materials → Insufficient supply chain management."

[0878] 7. Displaying the results

[0879] The server generates a visualization and sends it to the user's device, where the user can view it and understand that the root cause of the low sales is "poor supply chain management."

[0880] Specific examples

[0881] For example, if a user types "What is the cause of low sales?" into a terminal, the server sends this question to the artificial intelligence system, which receives the initial answer "Because customer satisfaction is low." The emotion engine then analyzes the emotional data from the user's input and reactions, and the server generates a follow-up question: "Why is customer satisfaction low?" This process is repeated until the root cause is finally identified as "Because of insufficient supply chain management." The results are visualized as a flowchart, adjusted based on the emotion engine's analysis, and displayed to the user.

[0882] This system allows users to efficiently identify the root cause of a problem, rather than simply looking at the surface, through sentiment analysis, enabling them to quickly find an effective solution.

[0883] The processing flow will be explained below.

[0884] Step 1:

[0885] User enters a question:

[0886] Using the terminal interface, the user enters a question about the problem they want to solve, such as "What is the cause of low sales?"

[0887] Step 2:

[0888] The device sends a question to the server:

[0889] The terminal sends the question entered by the user to the server, which formats the question so that it can be accurately transmitted to the server.

[0890] Step 3:

[0891] The server receives the question and sends it to the AI ​​system:

[0892] The server sends the question received from the terminal to the AI ​​system, where it checks that the question is in a format that can be analyzed.

[0893] Step 4:

[0894] An artificial intelligence system generates an initial answer:

[0895] The AI ​​system generates an initial answer based on the submitted question, for example, "Because customer satisfaction is low," and sends it back to the server.

[0896] Step 5:

[0897] The server receives the initial response and sends it to the emotion engine:

[0898] The server sends the initial response received from the AI ​​system to the emotion engine, which extracts emotion data from the user's input and reactions and returns the data to the server.

[0899] Step 6:

[0900] The server generates follow-up questions based on data from the emotion engine:

[0901] The server generates a follow-up question based on the initial answer and the analysis results of the emotion engine, such as "Why is customer satisfaction so low?", and sends it to the AI ​​system.

[0902] Step 7:

[0903] The server receives the additional response and sends it back to the emotion engine:

[0904] The server sends the additional answer received from the AI ​​system to the emotion engine, which analyzes the user's emotion data again. The result is used to generate the next additional question.

[0905] Step 8:

[0906] The server receives and analyzes the final response to determine the root cause:

[0907] The server continues the iterative process, eventually arriving at a root cause such as "poor supply chain management." At this stage, the server identifies the final answer.

[0908] Step 9:

[0909] The server summarizes the answer and visualizes it:

[0910] The server summarizes all responses and generates a flowchart or causal diagram showing the causal relationships. The visualization format is adjusted based on the analysis results of the emotion engine.

[0911] Step 10:

[0912] The server sends the visualized results to the terminal:

[0913] The server transmits the visualized results to the user's terminal.

[0914] Step 11:

[0915] The terminal displays the results to the user:

[0916] The terminal displays the visualized results sent from the server to the user, who then checks the results on the terminal and understands that the root cause of low sales is "poor supply chain management."

[0917] The above are the specific processing steps in a system that combines an emotion engine, from receiving a question from a user, to identifying the root cause, visualizing it, and displaying it to the user.

[0918] Example 2

[0919] 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."

[0920] Conventional question-answering systems only provide simple answers to user questions and are unable to identify the underlying causes behind the answers. Furthermore, they lack the means to analyze and visualize dependencies in detail while taking the user's emotions into account, making it difficult for users to understand the overall picture of the problem they are facing. The objective of this invention is to provide a system that identifies the root causes of user questions and summarizes and visualizes the results while analyzing the user's emotions.

[0921] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for inputting a question from a user, means for transmitting the input question to an artificial intelligence system, means for receiving an answer from the artificial intelligence system, means for generating a follow-up question based on the received answer and analyzing the user's emotions using an emotion analysis means, means for continuously sending the follow-up question to the artificial intelligence system, means for identifying a final answer from the artificial intelligence system, means for summarizing the process and result and visualizing it based on the emotion analysis result, and means for presenting the summarized and visualized information to the user. This makes it possible to identify the root cause of a user's question and efficiently provide analysis results that take the user's emotions into consideration.

[0922] A "user" is a person or organization that enters a question into the system and receives answers or analysis results.

[0923] A "terminal" is a device that a user uses to enter a question and receive and display results from the server.

[0924] The "server" is a central computer that sends questions received from the user's terminal to the artificial intelligence system and manages the answers and analysis results.

[0925] An "artificial intelligence system" is a knowledge processing system that generates answers to user questions and responds to follow-up questions.

[0926] "Emotion analysis means" refers to technology that analyzes user input and responses to extract emotional data and complements the context of questions and answers based on that data.

[0927] A "follow-up question" is a further question that is generated based on the user's initial answer to the first question.

[0928] "Summarizing" refers to summarizing and organizing the entire question and answer process.

[0929] "Visualization" refers to converting summarized information into a visual format such as a flowchart or cause-and-effect diagram and displaying it.

[0930] The "final answer" is the root cause or solution identified at the end of the cyclical process.

[0931] A "prompt" is an input sentence that is used to enter a question into a generative AI model and obtain an answer.

[0932] System Overview

[0933] The system based on this invention generates answers to questions entered by users using a generative AI model (e.g., GPT-3), identifies the root cause by repeatedly asking "Why?", analyzes the user's emotions using emotion analysis means, and summarizes and visualizes the results for presentation. This system is composed of a server, a terminal, a user, and emotion analysis means.

[0934] Hardware and software used

[0935] Server: The central computer that processes user queries and communicates with the AI ​​system and sentiment analysis engine.

[0936] Terminal: A device operated by a user, such as a PC, smartphone, or tablet.

[0937] Generative AI models: Natural language processing models such as GPT-3.

[0938] Sentiment analysis means: An analysis engine for analyzing user input data and reactions and extracting emotional data.

[0939] Specific examples of processing

[0940] 1. User inputs a question

[0941] The user types a question into the terminal, such as: "What is the cause of low sales?"

[0942] 2. Receiving and sending questions

[0943] The device sends the user's question to the server, which then sends the question as a prompt to the generative AI model.

[0944] 3. Analyzing initial answers and generating follow-up questions

[0945] The server analyzes the initial answer received from the generative AI model. For example, if the initial answer is "Because customer satisfaction is low," the server uses sentiment analysis means to analyze the user's sentiment and then generates a follow-up question such as "Why is customer satisfaction low?"

[0946] 4. Iteration

[0947] The server receives additional answers from the generative AI model and repeats the same procedure to ask "Why?" For example, if the server receives the additional answer "The product quality is low," it then generates the question "Why is the product quality low?"

[0948] 5. Identifying the root cause

[0949] The server repeats the circular process, ultimately identifying the root cause as "insufficient supply chain management."

[0950] 6. Summarization and visualization

[0951] The server summarizes all the answers and questions and visualizes them in the form of a flowchart or causal diagram, for example, "Low sales → Low customer satisfaction → Low product quality → Inferior raw materials → Poor supply chain management."

[0952] 7. Displaying the results

[0953] The server then sends the generated visualization results to the user's device, where the user can view them and understand the root cause of the problem.

[0954] Examples of prompt statements

[0955] Initial prompt: "What is the cause of low sales?"

[0956] Follow-up prompt: "Considering the user's frustration, why is customer satisfaction low?"

[0957] This invention allows users to go beyond just superficial answers to problems and identify the root cause with sentiment analysis, allowing them to quickly find effective solutions.

[0958] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0959] Step 1:

[0960] The user enters a question

[0961] Input: The user types a text question into the input field on the device.

[0962] Action: User types question: "What is the cause of low sales?"

[0963] Output: The terminal generates text data of questions from the user.

[0964] Step 2:

[0965] The device sends a question to the server

[0966] Input: The terminal has the question text data entered by the user.

[0967] Processing: The terminal sends this query data to the server.

[0968] Output: The server receives the question text data.

[0969] Step 3:

[0970] The server sends the question to the AI ​​system.

[0971] Input: The server has the question text data received from the terminal.

[0972] Processing: The server sends a question as a prompt to the generative AI model (e.g., GPT-3).

[0973] Output: The generative AI model returns an initial answer to the question it receives.

[0974] Step 4:

[0975] The server receives and analyzes the initial response.

[0976] Input: Contains the initial answer the server received from the generative AI model.

[0977] Processing: The server analyzes the initial response and evaluates the content of the response, for example, "Because customer satisfaction is low."

[0978] Output: A server with the analysis results.

[0979] Step 5:

[0980] The server analyzes the user's emotions using emotion analysis means.

[0981] Input: The server has the user's initial input and response data.

[0982] Processing: The server sends the data to a sentiment analysis means, which analyzes the user's emotional state (e.g., "I feel frustrated").

[0983] Output: Server with sentiment analysis results.

[0984] Step 6:

[0985] The server generates a follow-up question

[0986] Input: The server has the parsed initial answer and sentiment analysis results.

[0987] Processing: The server generates a follow-up question: "Why is customer satisfaction low?"

[0988] Output: Server with additional questions.

[0989] Step 7:

[0990] The server sends additional questions to the generative AI model

[0991] Input: The server has a follow-up question.

[0992] Processing: The server sends a follow-up question to the generative AI model.

[0993] Output: The generative AI model returns an additional answer.

[0994] Step 8:

[0995] The server repeats "Why?" as needed.

[0996] Input: The server has additional answers from the generative AI model.

[0997] Processing: The server analyzes the additional responses, performs sentiment analysis again, and generates a new "Why?" question. This process is repeated until the root cause is identified.

[0998] For example, if an additional response such as "The product quality is low" is received, a new question such as "Why is the product quality low?" is generated.

[0999] Output: The server reaches the final root cause.

[1000] Step 9:

[1001] The server identifies the final answer

[1002] Input: The server has all the questions and answers.

[1003] Processing: The server identifies the root cause from the answers, for example, selecting the final answer "due to insufficient supply chain management."

[1004] Output: The server with the final answer identified.

[1005] Step 10:

[1006] The server summarizes and visualizes the process and results.

[1007] Input: The server has a set of questions and answers, as well as sentiment analysis results.

[1008] Processing: The server summarizes all interactions and visualizes them in the form of flowcharts or cause-and-effect diagrams. For example, it generates a flowchart like this: "Low sales → Low customer satisfaction → Low product quality → Poor raw materials → Poor supply chain management."

[1009] Output: A server with visualized data.

[1010] Step 11:

[1011] The server sends the visualized results to the user's device.

[1012] Input: The server has the data to be visualized.

[1013] Processing: The server sends the visualized results to the user's terminal.

[1014] Output: The visualized result received by the user's device.

[1015] Step 12:

[1016] The user checks the results

[1017] Input: The user's terminal has the visualized results.

[1018] Action: The user reviews the results on their device and understands the root cause of the problem.

[1019] Output: The user gains an understanding of the problem.

[1020] The above processing steps allow the user to navigate through the system to the root cause and visually understand the process and results.

[1021] (Application example 2)

[1022] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1023] Conventional security incident analysis systems require a great deal of time and effort to identify the root cause of a problem. In addition, they develop countermeasures without taking into account the emotional state of the person in charge of responding to the incident, which reduces the quality of the response and increases the risk of further incidents.

[1024] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting a user's question, means for sending the input question to the artificial intelligence system, means for receiving an answer from the artificial intelligence system, means for generating a follow-up question based on the received answer, means for continuously sending follow-up questions to the artificial intelligence system, means for identifying a final answer from the artificial intelligence system, means for summarizing and visualizing the process and result, means for presenting the summarized and visualized information to the user, emotion analysis means for analyzing the user's emotions, means for complementing the question based on the emotion data analyzed by the emotion analysis means, and means for presenting appropriate countermeasures according to the user's emotional state. This makes it possible to quickly and efficiently identify the root cause of a security incident and propose appropriate countermeasures that take into account the emotional state of the person in charge.

[1025] The "means for inputting questions from the user" is an interface that allows the user to input questions about security incidents into the system.

[1026] The "means for transmitting an input question to the artificial intelligence system" is a communication means for transmitting a question input by a user to the artificial intelligence system.

[1027] The "means for receiving a response from an artificial intelligence system" refers to a means for receiving a response generated by the artificial intelligence system.

[1028] The "means for generating a follow-up question based on the received answer" refers to a means for generating a new question based on the answer received from the artificial intelligence system.

[1029] The "means for continuing to send follow-up questions to the artificial intelligence system" refers to a means for repeatedly sending the generated follow-up questions to the artificial intelligence system.

[1030] "Means for identifying a final answer from an artificial intelligence system" refers to a means for identifying a final root cause through multiple exchanges of questions and answers.

[1031] "Means for summarizing and visualizing processes and results" are means for summarizing the question and answer process and visually displaying the results.

[1032] The "means for presenting summarized and visualized information to a user" refers to a means for displaying summarized and visualized information to a user.

[1033] The "emotion analysis means for analyzing the user's emotions" is a means for extracting and analyzing emotion data from the user's inputs and reactions.

[1034] The "means for completing a question based on emotion data analyzed by the emotion analysis means" is a means for generating or completing a question based on data obtained by emotion analysis.

[1035] The "means for presenting appropriate countermeasures according to the emotional state of the user" is a means for presenting appropriate countermeasures to the user based on the results of emotion analysis.

[1036] The system for implementing the present invention supports the process of a user inputting questions about a security incident and identifying its root cause. The system mainly includes the following components:

[1037] 1. User's device

[1038] It accepts questions from users, sends them to the server, and receives and displays the results from the server. A typical smartphone or head-mounted display (HMD) can be used.

[1039] 2. Server

[1040] The system receives questions from the user's device, sends them to the AI ​​system, and receives answers. It then generates additional questions based on the received answers and sends them back to the AI ​​system. It identifies the final answer, summarizes and visualizes the process and results, and uses emotion analysis to analyze the user's emotions. It complements the questions based on the results and presents appropriate countermeasures to the user.

[1041] 3. Artificial Intelligence Systems

[1042] The system generates answers to user questions and continues to generate answers to follow-up questions. This artificial intelligence system uses a generative AI model that utilizes natural language processing technology.

[1043] 4. Emotion analysis method

[1044] Emotional data is extracted from the user's input and responses and analyzed. Based on this data, the system can complete questions and suggest appropriate countermeasures.

[1045] When a user enters a question about the cause of a security incident, the question is sent to the server via the terminal. The server receives the question and sends it to the AI ​​system. The AI ​​system then receives an initial answer and generates a follow-up question based on that answer. These follow-up questions are in the "Why?" format and are repeatedly generated and sent to the AI ​​system until the root cause is identified.

[1046] The emotion analysis means collects and analyzes emotional data obtained from user input and responses. Based on the analysis results, the server complements the question and presents appropriate responses according to the user's emotional state.

[1047] For example, if a user asks, "Why did the server go down?", the initial answer generated is "Because the server was overloaded." In response to this answer, the server generates a follow-up question, "Why was the server overloaded?" and repeatedly sends this to the AI ​​system. Eventually, the root cause is identified as "inappropriate resource management." During this time, the emotion analysis means assesses the user's stress level and suggests appropriate breaks or assistance as needed.

[1048] In this way, the present invention is a system that can improve the efficiency of analyzing the causes of security incidents and also propose countermeasures that take into account the user's emotional state.

[1049] Example prompt sentence:

[1050] Why did the server go down?

[1051] Why was the server overloaded?

[1052] "Users are stressed"

[1053] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1054] Step 1:

[1055] The user enters a question about the security incident.

[1056] Input: A user-asked question (e.g., "Why is the server down?")

[1057] Output: A query request from the user's device to the server

[1058] Specific operation: The user inputs a question into the interface using a smartphone or HMD.

[1059] Step 2:

[1060] The server sends the question received from the user terminal to the artificial intelligence system.

[1061] Input: Question sent from user device

[1062] Output: A question request to the AI ​​system

[1063] Specific operation: The server converts the question into JSON format and sends it to the artificial intelligence system via an HTTP request.

[1064] Step 3:

[1065] An artificial intelligence system generates initial answers to questions.

[1066] Input: The question sent by the server

[1067] Output: Initial response (e.g. "Because the server load was high")

[1068] Specific operation: The artificial intelligence system uses a generative AI model to generate answers to questions using natural language processing techniques.

[1069] Step 4:

[1070] The server receives the response from the artificial intelligence system.

[1071] Input: Initial response sent by the artificial intelligence system

[1072] Output: Response received at server

[1073] Specific operation: The server receives the HTTP response, parses the JSON formatted answer and stores it in the database.

[1074] Step 5:

[1075] The server generates additional questions based on the answers it receives and sends them back to the artificial intelligence system.

[1076] Input: Initial response (e.g., "Because the server load was high")

[1077] Output: Follow-up questions (e.g., "Why was the server overloaded?") and their submission

[1078] Specific operation: The server generates additional questions and creates another HTTP request and sends it to the artificial intelligence system.

[1079] Step 6:

[1080] An artificial intelligence system generates answers to follow-up questions.

[1081] Input: Follow-up question (e.g., "Why was the server so busy?")

[1082] Output: Additional answer (e.g., "Because of poor resource management")

[1083] Specific operation: The artificial intelligence system again uses the generative AI model to generate answers to follow-up questions.

[1084] Step 7:

[1085] The server receives additional answers from the artificial intelligence system.

[1086] Input: Additional answers sent by the AI ​​system

[1087] Output: Additional answers received at the server

[1088] Specific operation: The server receives the HTTP response and stores the answer in a database.

[1089] Step 8:

[1090] This is repeated until the server repeatedly generates additional questions as needed and sends them to the artificial intelligence system.

[1091] Input: Multiple answers and questions

[1092] Output: Final root cause (e.g., "Poor resource management")

[1093] Specific behavior: The server iterates, exchanging additional questions and answers until a certain condition is met.

[1094] Step 9:

[1095] The server summarizes and visualizes the process and results.

[1096] Input: History of all questions and answers

[1097] Output: Summarized and visualized information (e.g., flowchart)

[1098] Specific operation: The server analyzes the information stored in the database and visualizes it as a flowchart or causal diagram.

[1099] Step 10:

[1100] The server transmits the summarized and visualized information to the user terminal and presents it to the user.

[1101] Input: Summarized and visualized information

[1102] Output: Display information on the user's terminal

[1103] Specific operation: The server sends the visualized information to the user's terminal as an HTTP response and displays it to the user.

[1104] Step 11:

[1105] The server analyzes the user's emotions and completes the questions and answers.

[1106] Input: User input and responses

[1107] Output: Question completion and response suggestions based on emotion data

[1108] Specific operation: The server analyzes the user's emotional data using emotion analysis means and reflects the data in questions and answers as necessary. It also generates and presents appropriate countermeasures according to the user's emotional state.

[1109] 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.

[1110] 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.

[1111] 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.

[1112] [Third embodiment]

[1113] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1114] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1115] 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).

[1116] 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.

[1117] 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.

[1118] 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).

[1119] 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. 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.

[1120] 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.

[1121] 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.

[1122] 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.

[1123] 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.

[1124] 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."

[1125] System Overview

[1126] The system of the present invention uses an artificial intelligence system to generate answers to questions entered by users, and then identifies the root cause by continually asking "Why?", summarizing and visualizing the results for presentation. This system is composed of a server, a terminal, and a user.

[1127] System Components

[1128] 1. On the user's device:

[1129] Accepts question input.

[1130] Send a question to the server.

[1131] Receives the results from the server and displays them to the user.

[1132] 2. Server:

[1133] A question is received from the user's terminal.

[1134] Send your questions to an artificial intelligence system and receive answers.

[1135] A follow-up question ("Why?") is generated based on the answer and repeatedly sent to the artificial intelligence system.

[1136] Finally, the system generates summarized and visualized information and transmits the results to the user's terminal.

[1137] 3. Artificial Intelligence Systems:

[1138] Generate answers to questions.

[1139] Generate answers even for additional questions sent repeatedly.

[1140] Program processing flow

[1141] 1. User inputs a question

[1142] A user types a question into a terminal, for example, "What is the cause of low sales?"

[1143] 2. Receiving and sending questions

[1144] The terminal sends a user's question to the server, which then sends the question to the artificial intelligence system and receives an initial answer.

[1145] 3. Analyzing initial answers and generating follow-up questions

[1146] The server analyzes the initial answer received from the AI ​​system, generates a follow-up question, "Why?", and sends it back to the AI ​​system.

[1147] 4. Iteration

[1148] The server repeats this process as necessary, asking additional questions and answers, such as "Low sales are due to low customer satisfaction," "Why are customer satisfaction low?", "Because of poor product quality," and "Why is product quality poor?"

[1149] 5. Identifying the root cause

[1150] At some point, the server decides it has reached the root cause, which in this case is "poor supply chain management."

[1151] 6. Summarization and visualization

[1152] The server summarizes all the answers and visualizes them as flowcharts or causal diagrams, for example, generating a flowchart that shows: "Low sales → Low customer satisfaction → Low product quality → Inferior raw materials → Poor supply chain management."

[1153] 7. Displaying the results

[1154] The server generates a visualization and sends it to the user's device, where the user can view it and understand that the root cause of the low sales is "poor supply chain management."

[1155] Specific examples

[1156] For example, if a user types "What is the cause of low sales?" into a terminal, the server sends this question to the artificial intelligence system and receives the initial answer "Because of low customer satisfaction." The server then generates a follow-up question, "Why is customer satisfaction low?" and repeats this process until it finally arrives at the root cause: "Because of poor supply chain management." The results are visualized as a flowchart and displayed to the user.

[1157] The system allows users to quickly and efficiently identify the root cause of a problem, rather than just its surface area.

[1158] The processing flow will be explained below.

[1159] Step 1:

[1160] User enters a question:

[1161] Using the terminal interface, users enter questions about their problems, such as "What is the cause of low sales?"

[1162] Step 2:

[1163] The device sends a question to the server:

[1164] The terminal sends the user's input question to the server, where it is formatted to ensure that the content of the question is accurately conveyed to the server.

[1165] Step 3:

[1166] The server receives the question and sends it to the AI ​​system:

[1167] The server sends the question received from the terminal to the artificial intelligence system, where it checks that the question format can be analyzed by the AI ​​system.

[1168] Step 4:

[1169] An artificial intelligence system generates an initial answer:

[1170] The AI ​​system generates an initial answer based on the submitted question, such as "because customer satisfaction is low," and sends it back to the server.

[1171] Step 5:

[1172] The server receives the initial answer and generates a follow-up question:

[1173] The server analyzes the initial answer received from the AI ​​system, generates a follow-up question, "Why?", formats it, and sends it back to the AI ​​system.

[1174] Step 6:

[1175] Server and AI system iteration:

[1176] The server receives additional answers from the AI ​​system and continues to ask "Why?" about those answers, repeating this process until it arrives at the root cause, for example, "Why is customer satisfaction low?" → "Because the product quality is low" → "Why is the product quality low?" → "Because the raw materials are inferior."

[1177] Step 7:

[1178] Server identifies root cause:

[1179] Finally, the server identifies the root cause from the answers provided by the AI ​​system, which in this case concludes that it is due to "poor supply chain management."

[1180] Step 8:

[1181] Server summarization and visualization:

[1182] The server summarizes all the answers and questions exchanged and visualizes the causal relationships in a visually understandable format (e.g., a flowchart or causal diagram).

[1183] Step 9:

[1184] The server sends the visualized results to the terminal:

[1185] The server then sends the visualized results to the user's device, allowing the user to visually check the overall picture of the answers.

[1186] Step 10:

[1187] The terminal displays the results to the user:

[1188] The terminal displays the visualized results sent from the server to the user, who then checks the results on the terminal and understands that the root cause of low sales is "poor supply chain management."

[1189] These are the steps in which a user inputs a question, the server and the artificial intelligence system work together to identify the root cause of the problem, and then visualize the results and present them to the user.

[1190] Example 1

[1191] 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."

[1192] Conventional information processing systems often focus only on superficial problems, making it difficult to quickly and accurately identify the root cause. Furthermore, there is a lack of means to provide information in a format that allows users to easily understand the root cause of a problem, which can sometimes make the path to problem resolution unclear. In response to this, there is a need for a method to identify the root cause and visually present it to the user.

[1193] 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.

[1194] In this invention, the server includes means for inputting a question from a user, means for transmitting the input question to the data processing device, means for receiving an answer from the data processing device, means for generating a follow-up question based on the received answer, means for continuously sending follow-up questions to the data processing device, means for identifying a final answer from the data processing device, means for summarizing and visualizing the process and result, means for presenting the summarized and visualized information to the user, means for analyzing each answer and generating a follow-up question such as "Why?", and means for visualizing multiple answers and their causal relationships as a flowchart or causal diagram. This allows the user to quickly and accurately identify not only superficial answers but also root causes and to intuitively understand the information visually.

[1195] The "means for inputting a question" is a device or software that provides an interface for a user to input a question in text format.

[1196] The "means for transmitting to the data processing device" is a device or software having a communication function for transmitting the input question to the data processing device via a network.

[1197] The "means for receiving a response" is a device or software having a communication function for receiving a response sent from the data processing device.

[1198] A "means for generating follow-up questions" is an algorithm or software for automatically generating further questions based on the initial answers.

[1199] The "means for continuing to send to the data processing device" refers to a device or software having a communication function for repeatedly sending the generated additional questions to the data processing device.

[1200] The "means for identifying a final answer" is an algorithm or software for identifying a root cause from among multiple answers received from the data processing device.

[1201] The "summarization and visualization tool" is software that concisely summarizes multiple answers and their causal relationships and visually displays them in a format that is easy for users to understand.

[1202] A "means for presenting information to a user" is a device or software for displaying visualized information to a user.

[1203] The "means for generating follow-up "Why?" questions" is an algorithm or software for generating follow-up "Why?" questions for each answer.

[1204] A "causal visualization tool" is software for visualizing multiple answers and their relationships as a flowchart or causal diagram.

[1205] The specific implementation procedure for the mode for implementing the invention is described below. This system uses an artificial intelligence system to generate answers to questions entered by users, and then identifies the root cause by continually asking "Why?", and summarizes and visualizes the results for presentation. This system is composed of a server, a terminal, and a user.

[1206] System Components

[1207] 1. User's device

[1208] A question is input through a user interface.

[1209] Send the question to the server.

[1210] The results received from the server are displayed to the user.

[1211] 2. Server

[1212] A question is received from the user's terminal.

[1213] Send your questions to an artificial intelligence system and receive answers.

[1214] Based on the answers, a follow-up question, "Why?", is generated and repeatedly sent to the artificial intelligence system.

[1215] Finally, the summarized and visualized information is generated and sent to the user's terminal.

[1216] 3. Artificial Intelligence Systems

[1217] A data processing device for generating answers to questions.

[1218] It also generates answers to the follow-up question "Why?" that is repeatedly asked.

[1219] Hardware and Software

[1220] The main components of the system include:

[1221] User's device: A device that performs input and output, such as a regular PC, smartphone, or tablet.

[1222] Server: A high-performance data processing device that calls artificial intelligence models, summarizes data, visualizes data, etc.

[1223] Artificial intelligence systems: Use generative AI models such as OpenAI's GPT-3 and GPT-4.

[1224] Program processing overview

[1225] The program for this system includes the following processes:

[1226] 1. A user types a question into a terminal, for example, "What is the cause of low sales?"

[1227] 2. The device sends this question to the server, which sends it to the artificial intelligence system and receives an initial answer.

[1228] 3. The server analyzes the initial answer received from the AI ​​system, generates a follow-up question, "Why?", and sends it back to the AI ​​system.

[1229] 4. The server repeats this process, asking additional questions and answers, for example, "Low sales are due to low customer satisfaction," "Why is customer satisfaction low?", "Because the product quality is low," "Why is the product quality low?"

[1230] 5. At some point, the server determines that it has reached the root cause, which in this example is "poor supply chain management."

[1231] 6. The server summarizes all the answers and visualizes them as flowcharts or causal diagrams. For example, it generates a flowchart that shows: "Low sales → Low customer satisfaction → Low product quality → Inferior raw materials → Poor supply chain management."

[1232] 7. The server sends the visualized results to the user's device, where the user can view them and understand that the root cause of low sales is "poor supply chain management."

[1233] Specific examples

[1234] For example, if a user types "What is the cause of low sales?" into a terminal, the server sends this question to the artificial intelligence system and receives the initial answer "Because of low customer satisfaction." The server then generates a follow-up question, "Why is customer satisfaction low?" and repeats this process until it finally arrives at the root cause: "Because of poor supply chain management." The results are visualized as a flowchart and displayed to the user.

[1235] Prompt Sentence Examples

[1236] "What is the cause of low sales?"

[1237] "Why is customer satisfaction low?"

[1238] "Why is the product quality poor?"

[1239] The above is a specific embodiment for carrying out the invention, which allows the user to quickly and accurately identify the root cause of a problem, not just the surface problem.

[1240] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1241] Program processing flow

[1242] Step 1:

[1243] The user inputs a question into the terminal.

[1244] Input: User input (e.g., "What is the cause of low sales?")

[1245] Output: Text data entered into the terminal

[1246] Specific operation: The user enters a question in the text box on the terminal and presses the send button.

[1247] Step 2:

[1248] The terminal sends a question from the user to the server.

[1249] Input: Text data entered by the user

[1250] Output: HTTP request to the server

[1251] Specific operation: The device sends the entered question as an HTTP request.

[1252] Step 3:

[1253] The server receives the question and sends it to the artificial intelligence system.

[1254] Input: HTTP request (question) from the terminal

[1255] Output: Prompt to the artificial intelligence system

[1256] Specific operation: The server receives an HTTP request and sends it as a prompt to the artificial intelligence system.

[1257] Step 4:

[1258] The artificial intelligence power generates answers to the questions received.

[1259] Input: prompt (question)

[1260] Output: The generated answer

[1261] Specific operation: The AI ​​system uses natural language processing to generate an answer based on the question it receives.

[1262] Step 5:

[1263] The server analyzes the answers received from the artificial intelligence system.

[1264] Input: Answer from an artificial intelligence system

[1265] Output: Analysis results (additional questions)

[1266] Specific behavior: The server analyzes the answer text and generates a follow-up question of the form "Why?"

[1267] Step 6:

[1268] The server generates additional questions and resubmits them to the artificial intelligence system.

[1269] Input: Analysis results (additional questions)

[1270] Output: A new prompt to the artificial intelligence system

[1271] Specific operation: The server resends the additional question as a prompt to the artificial intelligence system.

[1272] Step 7:

[1273] The server repeats this process as necessary.

[1274] Input: Repeated answers from an artificial intelligence system

[1275] Output: Final answer

[1276] Specific operation: The server analyzes the answer and repeats the process of generating and sending a new question.

[1277] Step 8:

[1278] The server determines the final answer.

[1279] Input: Repeated answers

[1280] Output: Root cause (final answer)

[1281] Specific operation: The server identifies the most fundamental cause from the set of answers and determines this as the final answer.

[1282] Step 9:

[1283] The server summarizes and visualizes the process and results.

[1284] Input: All answers and their causal relationships

[1285] Output: Visualized data (flowcharts and causal diagrams)

[1286] Specific behavior: The server uses Python libraries (such as matplotlib and Graphviz) to visualize the relationships between answers.

[1287] Step 10:

[1288] The server sends the visualized results to the user's terminal.

[1289] Input: Visualization data

[1290] Output: Send data to the user's device

[1291] Specific operation: The server sends the generated visualization data to the user's device as an HTTP response.

[1292] Step 11:

[1293] The terminal displays the received results to the user.

[1294] Input: Visualization data from the server

[1295] Output: The result displayed in the user interface

[1296] Specific operation: The device displays the visualization data it receives on the screen so that the user can check it.

[1297] These are the specific processing steps of the system, which allow users to quickly identify and intuitively understand the root cause of any problem, from the surface level.

[1298] (Application example 1)

[1299] 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."

[1300] Conventional production facilities lacked the means to identify production efficiency or quality issues from operational data and quickly and efficiently identify their root causes. As a result, problem resolution took time, leading to a risk of reduced productivity. Furthermore, previous systems required users to manually track problems, often resulting in delayed analysis. This invention solves these issues and aims to improve operational efficiency in factories.

[1301] 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.

[1302] In this invention, the server includes means for inputting a question from a user, means for transmitting the input question to an artificial intelligence system, means for receiving an answer from the artificial intelligence system, means for generating a follow-up question based on the received answer, means for continuously transmitting the follow-up question to the artificial intelligence system, means for identifying a final answer from the artificial intelligence system, means for summarizing and visualizing processes and results, means for presenting the summarized and visualized information to a user, means for collecting operation data of a production facility, means for generating a question regarding a problem with production efficiency or quality based on the operation data, means for identifying a root cause for the question, and means for visualizing the identified root cause and related information, thereby enabling quick and efficient identification and analysis of the root cause of a problem in a production facility.

[1303] "User" refers to an individual or organization who uses the system to enter questions and receive final answers and visualized information.

[1304] "Means for inputting a question" refers to an interface that allows a user to input a question to the system, such as a keyboard or a touch screen.

[1305] "Means for sending questions to an AI system" refers to communications means for transmitting input questions to an AI system, such as the Internet or a local network.

[1306] "Artificial intelligence system" refers to software or hardware that automatically generates answers to questions, such as the generative AI model GPT-3.

[1307] "Means for receiving a response" refers to an interface or system for obtaining and processing a response from an artificial intelligence system.

[1308] "Means for generating follow-up questions" refers to algorithms or logic for automatically generating further follow-up questions based on the initial answers.

[1309] "Means for continuing to send follow-up questions to the artificial intelligence system" refers to communication means for repeatedly sending the generated follow-up questions to the artificial intelligence system.

[1310] "Means for identifying a final answer" refers to the logic or algorithm used to determine a final answer related to the root cause through a process of asking and answering a series of questions.

[1311] "Summarization and visualization tools" refers to software and tools that organize the responses and present them in a visually understandable format.

[1312] The "means for presenting the summarized and visualized information to the user" refers to an interface for displaying the visualized information so that the user can confirm it.

[1313] "Production equipment" is a general term for the machinery and equipment used in factories and production lines.

[1314] "Means for collecting operational data" refers to sensors and data acquisition systems for obtaining operational information and performance data from production equipment.

[1315] The "means for generating questions related to production efficiency and quality issues" refers to an algorithm for identifying issues related to production efficiency and quality based on collected operational data and automatically generating questions related to those issues.

[1316] "Means for identifying root causes" refers to analytical logic or algorithms for identifying the root causes of problems from the answers to the generated questions.

[1317] "Means for visualizing related information" refers to software or tools that provide an easy-to-understand visual display of identified root causes and related information.

[1318] The basic embodiment of this invention relates to a system for identifying the root cause of problems in factory production equipment. This system starts with user input, uses an artificial intelligence system to perform an in-depth analysis of the problem, and visualizes the results. Specifically, this system is implemented as follows.

[1319] System configuration

[1320] User's device

[1321] Question entry interface: An interface through which a user can enter a question, including a keyboard or touchscreen.

[1322] Sending and receiving module: A module for sending the entered question to the server and displaying the results received from the server.

[1323] server

[1324] Communication module: A module for communicating with user terminals to send and receive questions and answers.

[1325] AI processing module: A module that sends questions received from users to an artificial intelligence system and receives answers.

[1326] Follow-up question generation module: A module that generates follow-up questions ("Why?") based on the initial answers.

[1327] Repeated question module: A module that sends the generated additional questions to the artificial intelligence system again.

[1328] Visualization module: A module that visualizes the final answer and its related information as a flowchart or causal diagram.

[1329] Production Equipment

[1330] Data collection module: Sensors and data acquisition systems that collect operational data from production equipment in real time.

[1331] Data Analysis Module: A module that generates questions about production efficiency and quality issues based on collected data.

[1332] Software and hardware used

[1333] Generative AI models: Use generative AI models such as OpenAI's GPT-3.

[1334] Programming language: Program implemented using Python.

[1335] Visualization tools: Graph generation using Matplotlib and NetworkX.

[1336] Communication infrastructure: Internet connection and local network.

[1337] Process Description

[1338] 1. User question input: The user uses the terminal to input a question about the production equipment. A specific example is the question, "Why is the production efficiency low in line A?"

[1339] 2. Sending a question and receiving an answer: The user's device sends the entered question to the server, which then sends the question to the generative AI model, receives the initial answer from the generative AI model, and analyzes the answer.

[1340] 3. Generate and send follow-up questions: The server automatically generates a follow-up question, "Why?", based on the initial answer it received and sends this question to the generative AI model again. For example, for the answer "The machine breaks down frequently," it generates a follow-up question, "Why does the machine break down frequently?"

[1341] 4. Iterative process: This question and answer process continues until the root cause is reached.

[1342] 5. Visualization and display: Finally, the server visualizes the results of the series of questions and answers as a flowchart or causal diagram and sends it to the user's device.

[1343] Examples of concrete examples and prompts

[1344] Specific examples

[1345] If a problem of low production efficiency occurs on production line A in a factory, this system can be used to identify the root cause using the following procedure.

[1346] Q: Why is the production efficiency low in line A?

[1347] A: Because the machine breaks down frequently.

[1348] Q: Why does the machine break down frequently?

[1349] A: Because the regular maintenance is insufficient.

[1350] Q: Why is the regular maintenance insufficient?

[1351] A: Because the maintenance schedule is not properly managed.

[1352] Prompt Sentence Examples

[1353] First prompt:

[1354] "Why is the production efficiency low in line A?"

[1355] Additional prompts:

[1356] "Why does the machine breakdown frequently?"

[1357] "Why is the regular maintenance insufficient?"

[1358] "Why is the maintenance schedule not properly managed?"

[1359] In this way, it becomes possible to specifically and quickly identify the root cause of problems in production equipment.

[1360] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1361] Step 1:

[1362] User question input

[1363] The user uses the terminal to input questions about production equipment. The input questions are in the form of "Why is the production efficiency low in line A?" The terminal is equipped with an interface that allows questions to be input using a keyboard or touch screen. The input here is in text format, and that text is used in the next step.

[1364] Step 2:

[1365] Submit a Question

[1366] The user's device sends the entered question to the server. Specifically, when the user has finished entering the question on the device, they press the send button, which sends the question to the server via the network. The device uses a communication protocol such as an HTTP request to send the entered question to the server. At this stage, text data is sent from the device to the server.

[1367] Step 3:

[1368] Sending questions to an AI system

[1369] The server sends the received question to a generative AI model (e.g., GPT-3). Specifically, the server generates an API request to send the question to the AI ​​model. This request includes the question text and data for the AI ​​to answer. The server prepares to receive the answer from the AI ​​model.

[1370] Step 4:

[1371] Receiving an initial response

[1372] The server receives the answer from the generative AI model. The AI ​​model generates a text answer to the question it received, and this answer is returned to the server. For example, the answer may be "Because the machine breaks down frequently." The next step is based on this answer.

[1373] Step 5:

[1374] Generate follow-up questions

[1375] The server generates a follow-up question called "Why?" based on the initial answer. Specifically, based on the answer received, the server creates a question by asking the AI ​​model again, "Why does that state occur?" For example, the question "Why does the machine break down frequently?" is automatically generated.

[1376] Step 6:

[1377] Submitting Repeated Questions

[1378] The server then sends the generated questions to the AI ​​model again. This process is similar to step 3, sending the generated questions to the AI ​​model through the API and receiving the answers. This iterative questioning process can continue as needed.

[1379] Step 7:

[1380] Identifying the root cause

[1381] The server repeats this series of questions and answers until it determines that it has reached the root cause of the problem. For example, if the final answer is "Because the maintenance schedule is not properly managed," this answer is identified as the root cause.

[1382] Step 8:

[1383] Summarize and visualize

[1384] The server summarizes the data from a series of questions and answers and visualizes them as flowcharts or causal diagrams. Specifically, it uses NetworkX and Matplotlib to generate graphs of the relationship between questions and answers. This visualized information is used by users to help them understand the overall picture of the problem.

[1385] Step 9:

[1386] Displaying the results

[1387] The server sends the visualized flowchart or causal diagram to the user's device, which then displays the visualized information for the user to review, allowing the user to understand the root cause of the problem at a glance.

[1388] 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.

[1389] System Overview

[1390] The system of the present invention uses an artificial intelligence system to generate answers to questions entered by users, identifies the root cause by continually asking "Why?", analyzes the user's emotions using an emotion engine, and summarizes and visualizes the results for presentation. This system is composed of a server, a terminal, a user, and an emotion engine.

[1391] System Components

[1392] 1. On the user's device:

[1393] Accepts question input.

[1394] Send a question to the server.

[1395] Receives the results from the server and displays them to the user.

[1396] 2. Server:

[1397] A question is received from the user's terminal.

[1398] Send your questions to an artificial intelligence system and receive answers.

[1399] A follow-up question ("Why?") is generated based on the answer and repeatedly sent to the artificial intelligence system.

[1400] Send data to an emotion engine to analyze the user's emotions and receive the analysis results.

[1401] Finally, the system generates summarized and visualized information and transmits the results to the user's terminal.

[1402] 3. Artificial Intelligence Systems:

[1403] Generate answers to questions.

[1404] Generate answers even for additional questions sent repeatedly.

[1405] 4. Emotion Engine:

[1406] Emotional data is extracted by analyzing user input and responses.

[1407] Complementing the context of questions and answers with sentiment data.

[1408] Emotion data is sent to the server and supports the server's processing.

[1409] Program processing flow

[1410] 1. User inputs a question

[1411] A user types a question into a terminal, for example, "What is the cause of low sales?"

[1412] 2. Receiving and sending questions

[1413] The terminal sends a user's question to the server, which then sends the question to the artificial intelligence system and receives an initial answer.

[1414] 3. Analyzing initial answers and generating follow-up questions

[1415] The server analyzes the initial response received from the AI ​​system, combines the user's emotional data analyzed by the emotion engine with the response, generates a follow-up question called "Why?", formats it, and sends it back to the AI ​​system.

[1416] 4. Iteration

[1417] The server receives additional answers from the AI ​​system and continues to ask "Why?" in response to those answers, taking into account the data from the emotion engine. This process is repeated as necessary, for example, "Why is customer satisfaction low?" → "Because the product quality is low" → "Why is the product quality low?" → "Because the raw materials are inferior," until the root cause is identified.

[1418] 5. Identifying the root cause

[1419] At some point, the server decides it has reached the root cause, which in this case is "poor supply chain management."

[1420] 6. Summarization and visualization

[1421] The server summarizes all the answers and questions exchanged and visualizes the causal relationships in a visually understandable format (such as a flowchart or causal diagram). It then adjusts the visualization based on the analysis results of the emotion engine. For example, it generates a flowchart that shows "Low sales → Low customer satisfaction → Low product quality → Poor raw materials → Insufficient supply chain management."

[1422] 7. Displaying the results

[1423] The server generates a visualization and sends it to the user's device, where the user can view it and understand that the root cause of the low sales is "poor supply chain management."

[1424] Specific examples

[1425] For example, if a user types "What is the cause of low sales?" into a terminal, the server sends this question to the artificial intelligence system, which receives the initial answer "Because customer satisfaction is low." The emotion engine then analyzes the emotional data from the user's input and reactions, and the server generates a follow-up question: "Why is customer satisfaction low?" This process is repeated until the root cause is finally identified as "Because of insufficient supply chain management." The results are visualized as a flowchart, adjusted based on the emotion engine's analysis, and displayed to the user.

[1426] This system allows users to efficiently identify the root cause of a problem, rather than simply looking at the surface, through sentiment analysis, enabling them to quickly find an effective solution.

[1427] The processing flow will be explained below.

[1428] Step 1:

[1429] User enters a question:

[1430] Using the terminal interface, the user enters a question about the problem they want to solve, such as "What is the cause of low sales?"

[1431] Step 2:

[1432] The device sends a question to the server:

[1433] The terminal sends the question entered by the user to the server, which formats the question so that it can be accurately transmitted to the server.

[1434] Step 3:

[1435] The server receives the question and sends it to the AI ​​system:

[1436] The server sends the question received from the terminal to the AI ​​system, where it checks that the question is in a format that can be analyzed.

[1437] Step 4:

[1438] An artificial intelligence system generates an initial answer:

[1439] The AI ​​system generates an initial answer based on the submitted question, for example, "Because customer satisfaction is low," and sends it back to the server.

[1440] Step 5:

[1441] The server receives the initial response and sends it to the emotion engine:

[1442] The server sends the initial response received from the AI ​​system to the emotion engine, which extracts emotion data from the user's input and reactions and returns the data to the server.

[1443] Step 6:

[1444] The server generates follow-up questions based on data from the emotion engine:

[1445] The server generates a follow-up question based on the initial answer and the analysis results of the emotion engine, such as "Why is customer satisfaction so low?", and sends it to the AI ​​system.

[1446] Step 7:

[1447] The server receives the additional response and sends it back to the emotion engine:

[1448] The server sends the additional answer received from the AI ​​system to the emotion engine, which analyzes the user's emotion data again. The result is used to generate the next additional question.

[1449] Step 8:

[1450] The server receives and analyzes the final response to determine the root cause:

[1451] The server continues the iterative process, eventually arriving at a root cause such as "poor supply chain management." At this stage, the server identifies the final answer.

[1452] Step 9:

[1453] The server summarizes the answer and visualizes it:

[1454] The server summarizes all responses and generates a flowchart or causal diagram showing the causal relationships. The visualization format is adjusted based on the analysis results of the emotion engine.

[1455] Step 10:

[1456] The server sends the visualized results to the terminal:

[1457] The server transmits the visualized results to the user's terminal.

[1458] Step 11:

[1459] The terminal displays the results to the user:

[1460] The terminal displays the visualized results sent from the server to the user, who then checks the results on the terminal and understands that the root cause of low sales is "poor supply chain management."

[1461] The above are the specific processing steps in a system that combines an emotion engine, from receiving a question from a user, to identifying the root cause, visualizing it, and displaying it to the user.

[1462] Example 2

[1463] 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."

[1464] Conventional question-answering systems only provide simple answers to user questions and are unable to identify the underlying causes behind the answers. Furthermore, they lack the means to analyze and visualize dependencies in detail while taking the user's emotions into account, making it difficult for users to understand the overall picture of the problem they are facing. The objective of this invention is to provide a system that identifies the root causes of user questions and summarizes and visualizes the results while analyzing the user's emotions.

[1465] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for inputting a question from a user, means for transmitting the input question to an artificial intelligence system, means for receiving an answer from the artificial intelligence system, means for generating a follow-up question based on the received answer and analyzing the user's emotions using an emotion analysis means, means for continuously sending the follow-up question to the artificial intelligence system, means for identifying a final answer from the artificial intelligence system, means for summarizing the process and result and visualizing it based on the emotion analysis result, and means for presenting the summarized and visualized information to the user. This makes it possible to identify the root cause of a user's question and efficiently provide analysis results that take the user's emotions into consideration.

[1466] A "user" is a person or organization that enters a question into the system and receives answers or analysis results.

[1467] A "terminal" is a device that a user uses to enter a question and receive and display results from the server.

[1468] The "server" is a central computer that sends questions received from the user's terminal to the artificial intelligence system and manages the answers and analysis results.

[1469] An "artificial intelligence system" is a knowledge processing system that generates answers to user questions and responds to follow-up questions.

[1470] "Emotion analysis means" refers to technology that analyzes user input and responses to extract emotional data and complements the context of questions and answers based on that data.

[1471] A "follow-up question" is a further question that is generated based on the user's initial answer to the first question.

[1472] "Summarizing" refers to summarizing and organizing the entire question and answer process.

[1473] "Visualization" refers to converting summarized information into a visual format such as a flowchart or cause-and-effect diagram and displaying it.

[1474] The "final answer" is the root cause or solution identified at the end of the cyclical process.

[1475] A "prompt" is an input sentence that is used to enter a question into a generative AI model and obtain an answer.

[1476] System Overview

[1477] The system based on this invention generates answers to questions entered by users using a generative AI model (e.g., GPT-3), identifies the root cause by repeatedly asking "Why?", analyzes the user's emotions using emotion analysis means, and summarizes and visualizes the results for presentation. This system is composed of a server, a terminal, a user, and emotion analysis means.

[1478] Hardware and software used

[1479] Server: The central computer that processes user queries and communicates with the AI ​​system and sentiment analysis engine.

[1480] Terminal: A device operated by a user, such as a PC, smartphone, or tablet.

[1481] Generative AI models: Natural language processing models such as GPT-3.

[1482] Sentiment analysis means: An analysis engine for analyzing user input data and reactions and extracting emotional data.

[1483] Specific examples of processing

[1484] 1. User inputs a question

[1485] The user types a question into the terminal, such as: "What is the cause of low sales?"

[1486] 2. Receiving and sending questions

[1487] The device sends the user's question to the server, which then sends the question as a prompt to the generative AI model.

[1488] 3. Analyzing initial answers and generating follow-up questions

[1489] The server analyzes the initial answer received from the generative AI model. For example, if the initial answer is "Because customer satisfaction is low," the server uses sentiment analysis means to analyze the user's sentiment and then generates a follow-up question such as "Why is customer satisfaction low?"

[1490] 4. Iteration

[1491] The server receives additional answers from the generative AI model and repeats the same procedure to ask "Why?" For example, if the server receives the additional answer "The product quality is low," it then generates the question "Why is the product quality low?"

[1492] 5. Identifying the root cause

[1493] The server repeats the circular process, ultimately identifying the root cause as "insufficient supply chain management."

[1494] 6. Summarization and visualization

[1495] The server summarizes all the answers and questions and visualizes them in the form of a flowchart or causal diagram, for example, "Low sales → Low customer satisfaction → Low product quality → Inferior raw materials → Poor supply chain management."

[1496] 7. Displaying the results

[1497] The server then sends the generated visualization results to the user's device, where the user can view them and understand the root cause of the problem.

[1498] Examples of prompt statements

[1499] Initial prompt: "What is the cause of low sales?"

[1500] Follow-up prompt: "Considering the user's frustration, why is customer satisfaction low?"

[1501] This invention allows users to go beyond just superficial answers to problems and identify the root cause with sentiment analysis, allowing them to quickly find effective solutions.

[1502] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1503] Step 1:

[1504] The user enters a question

[1505] Input: The user types a text question into the input field on the device.

[1506] Action: User types question: "What is the cause of low sales?"

[1507] Output: The terminal generates text data of questions from the user.

[1508] Step 2:

[1509] The device sends a question to the server

[1510] Input: The terminal has the question text data entered by the user.

[1511] Processing: The terminal sends this query data to the server.

[1512] Output: The server receives the question text data.

[1513] Step 3:

[1514] The server sends the question to the AI ​​system.

[1515] Input: The server has the question text data received from the terminal.

[1516] Processing: The server sends a question as a prompt to the generative AI model (e.g., GPT-3).

[1517] Output: The generative AI model returns an initial answer to the question it receives.

[1518] Step 4:

[1519] The server receives and analyzes the initial response.

[1520] Input: Contains the initial answer the server received from the generative AI model.

[1521] Processing: The server analyzes the initial response and evaluates the content of the response, for example, "Because customer satisfaction is low."

[1522] Output: A server with the analysis results.

[1523] Step 5:

[1524] The server analyzes the user's emotions using emotion analysis means.

[1525] Input: The server has the user's initial input and response data.

[1526] Processing: The server sends the data to a sentiment analysis means, which analyzes the user's emotional state (e.g., "I feel frustrated").

[1527] Output: Server with sentiment analysis results.

[1528] Step 6:

[1529] The server generates a follow-up question

[1530] Input: The server has the parsed initial answer and sentiment analysis results.

[1531] Processing: The server generates a follow-up question: "Why is customer satisfaction low?"

[1532] Output: Server with additional questions.

[1533] Step 7:

[1534] The server sends additional questions to the generative AI model

[1535] Input: The server has a follow-up question.

[1536] Processing: The server sends a follow-up question to the generative AI model.

[1537] Output: The generative AI model returns an additional answer.

[1538] Step 8:

[1539] The server repeats "Why?" as needed.

[1540] Input: The server has additional answers from the generative AI model.

[1541] Processing: The server analyzes the additional responses, performs sentiment analysis again, and generates a new "Why?" question. This process is repeated until the root cause is identified.

[1542] For example, if an additional response such as "The product quality is low" is received, a new question such as "Why is the product quality low?" is generated.

[1543] Output: The server reaches the final root cause.

[1544] Step 9:

[1545] The server identifies the final answer

[1546] Input: The server has all the questions and answers.

[1547] Processing: The server identifies the root cause from the answers, for example, selecting the final answer "due to insufficient supply chain management."

[1548] Output: The server with the final answer identified.

[1549] Step 10:

[1550] The server summarizes and visualizes the process and results.

[1551] Input: The server has a set of questions and answers, as well as sentiment analysis results.

[1552] Processing: The server summarizes all interactions and visualizes them in the form of flowcharts or cause-and-effect diagrams. For example, it generates a flowchart like this: "Low sales → Low customer satisfaction → Low product quality → Poor raw materials → Poor supply chain management."

[1553] Output: A server with visualized data.

[1554] Step 11:

[1555] The server sends the visualized results to the user's device.

[1556] Input: The server has the data to be visualized.

[1557] Processing: The server sends the visualized results to the user's terminal.

[1558] Output: The visualized result received by the user's device.

[1559] Step 12:

[1560] The user checks the results

[1561] Input: The user's terminal has the visualized results.

[1562] Action: The user reviews the results on their device and understands the root cause of the problem.

[1563] Output: The user gains an understanding of the problem.

[1564] The above processing steps allow the user to navigate through the system to the root cause and visually understand the process and results.

[1565] (Application example 2)

[1566] 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."

[1567] Conventional security incident analysis systems require a great deal of time and effort to identify the root cause of a problem. In addition, they develop countermeasures without taking into account the emotional state of the person in charge of responding to the incident, which reduces the quality of the response and increases the risk of further incidents.

[1568] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting a user's question, means for sending the input question to the artificial intelligence system, means for receiving an answer from the artificial intelligence system, means for generating a follow-up question based on the received answer, means for continuously sending follow-up questions to the artificial intelligence system, means for identifying a final answer from the artificial intelligence system, means for summarizing and visualizing the process and result, means for presenting the summarized and visualized information to the user, emotion analysis means for analyzing the user's emotions, means for complementing the question based on the emotion data analyzed by the emotion analysis means, and means for presenting appropriate countermeasures according to the user's emotional state. This makes it possible to quickly and efficiently identify the root cause of a security incident and propose appropriate countermeasures that take into account the emotional state of the person in charge.

[1569] The "means for inputting questions from the user" is an interface that allows the user to input questions about security incidents into the system.

[1570] The "means for transmitting an input question to the artificial intelligence system" is a communication means for transmitting a question input by a user to the artificial intelligence system.

[1571] The "means for receiving a response from an artificial intelligence system" refers to a means for receiving a response generated by the artificial intelligence system.

[1572] The "means for generating a follow-up question based on the received answer" refers to a means for generating a new question based on the answer received from the artificial intelligence system.

[1573] The "means for continuing to send follow-up questions to the artificial intelligence system" refers to a means for repeatedly sending the generated follow-up questions to the artificial intelligence system.

[1574] "Means for identifying a final answer from an artificial intelligence system" refers to a means for identifying a final root cause through multiple exchanges of questions and answers.

[1575] "Means for summarizing and visualizing processes and results" are means for summarizing the question and answer process and visually displaying the results.

[1576] The "means for presenting summarized and visualized information to a user" refers to a means for displaying summarized and visualized information to a user.

[1577] The "emotion analysis means for analyzing the user's emotions" is a means for extracting and analyzing emotion data from the user's inputs and reactions.

[1578] The "means for completing a question based on emotion data analyzed by the emotion analysis means" is a means for generating or completing a question based on data obtained by emotion analysis.

[1579] The "means for presenting appropriate countermeasures according to the emotional state of the user" is a means for presenting appropriate countermeasures to the user based on the results of emotion analysis.

[1580] The system for implementing the present invention supports the process of a user inputting questions about a security incident and identifying its root cause. The system mainly includes the following components:

[1581] 1. User's device

[1582] It accepts questions from users, sends them to the server, and receives and displays the results from the server. A typical smartphone or head-mounted display (HMD) can be used.

[1583] 2. Server

[1584] The system receives questions from the user's device, sends them to the AI ​​system, and receives answers. It then generates additional questions based on the received answers and sends them back to the AI ​​system. It identifies the final answer, summarizes and visualizes the process and results, and uses emotion analysis to analyze the user's emotions. It complements the questions based on the results and presents appropriate countermeasures to the user.

[1585] 3. Artificial Intelligence Systems

[1586] The system generates answers to user questions and continues to generate answers to follow-up questions. This artificial intelligence system uses a generative AI model that utilizes natural language processing technology.

[1587] 4. Emotion analysis method

[1588] Emotional data is extracted from the user's input and responses and analyzed. Based on this data, the system can complete questions and suggest appropriate countermeasures.

[1589] When a user enters a question about the cause of a security incident, the question is sent to the server via the terminal. The server receives the question and sends it to the AI ​​system. The AI ​​system then receives an initial answer and generates a follow-up question based on that answer. These follow-up questions are in the "Why?" format and are repeatedly generated and sent to the AI ​​system until the root cause is identified.

[1590] The emotion analysis means collects and analyzes emotional data obtained from user input and responses. Based on the analysis results, the server complements the question and presents appropriate responses according to the user's emotional state.

[1591] For example, if a user asks, "Why did the server go down?", the initial answer generated is "Because the server was overloaded." In response to this answer, the server generates a follow-up question, "Why was the server overloaded?" and repeatedly sends this to the AI ​​system. Eventually, the root cause is identified as "inappropriate resource management." During this time, the emotion analysis means assesses the user's stress level and suggests appropriate breaks or assistance as needed.

[1592] In this way, the present invention is a system that can improve the efficiency of analyzing the causes of security incidents and also propose countermeasures that take into account the user's emotional state.

[1593] Example prompt sentence:

[1594] Why did the server go down?

[1595] Why was the server overloaded?

[1596] "Users are stressed"

[1597] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1598] Step 1:

[1599] The user enters a question about the security incident.

[1600] Input: A user-asked question (e.g., "Why is the server down?")

[1601] Output: A query request from the user's device to the server

[1602] Specific operation: The user inputs a question into the interface using a smartphone or HMD.

[1603] Step 2:

[1604] The server sends the question received from the user terminal to the artificial intelligence system.

[1605] Input: Question sent from user device

[1606] Output: A question request to the AI ​​system

[1607] Specific operation: The server converts the question into JSON format and sends it to the artificial intelligence system via an HTTP request.

[1608] Step 3:

[1609] An artificial intelligence system generates initial answers to questions.

[1610] Input: The question sent by the server

[1611] Output: Initial response (e.g. "Because the server load was high")

[1612] Specific operation: The artificial intelligence system uses a generative AI model to generate answers to questions using natural language processing techniques.

[1613] Step 4:

[1614] The server receives the response from the artificial intelligence system.

[1615] Input: Initial response sent by the artificial intelligence system

[1616] Output: Response received at server

[1617] Specific operation: The server receives the HTTP response, parses the JSON formatted answer and stores it in the database.

[1618] Step 5:

[1619] The server generates additional questions based on the answers it receives and sends them back to the artificial intelligence system.

[1620] Input: Initial response (e.g., "Because the server load was high")

[1621] Output: Follow-up questions (e.g., "Why was the server overloaded?") and their submission

[1622] Specific operation: The server generates additional questions and creates another HTTP request and sends it to the artificial intelligence system.

[1623] Step 6:

[1624] An artificial intelligence system generates answers to follow-up questions.

[1625] Input: Follow-up question (e.g., "Why was the server so busy?")

[1626] Output: Additional answer (e.g., "Because of poor resource management")

[1627] Specific operation: The artificial intelligence system again uses the generative AI model to generate answers to follow-up questions.

[1628] Step 7:

[1629] The server receives additional answers from the artificial intelligence system.

[1630] Input: Additional answers sent by the AI ​​system

[1631] Output: Additional answers received at the server

[1632] Specific operation: The server receives the HTTP response and stores the answer in a database.

[1633] Step 8:

[1634] This is repeated until the server repeatedly generates additional questions as needed and sends them to the artificial intelligence system.

[1635] Input: Multiple answers and questions

[1636] Output: Final root cause (e.g., "Poor resource management")

[1637] Specific behavior: The server iterates, exchanging additional questions and answers until a certain condition is met.

[1638] Step 9:

[1639] The server summarizes and visualizes the process and results.

[1640] Input: History of all questions and answers

[1641] Output: Summarized and visualized information (e.g., flowchart)

[1642] Specific operation: The server analyzes the information stored in the database and visualizes it as a flowchart or causal diagram.

[1643] Step 10:

[1644] The server transmits the summarized and visualized information to the user terminal and presents it to the user.

[1645] Input: Summarized and visualized information

[1646] Output: Display information on the user's terminal

[1647] Specific operation: The server sends the visualized information to the user's terminal as an HTTP response and displays it to the user.

[1648] Step 11:

[1649] The server analyzes the user's emotions and completes the questions and answers.

[1650] Input: User input and responses

[1651] Output: Question completion and response suggestions based on emotion data

[1652] Specific operation: The server analyzes the user's emotional data using emotion analysis means and reflects the data in questions and answers as necessary. It also generates and presents appropriate countermeasures according to the user's emotional state.

[1653] 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.

[1654] 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.

[1655] 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.

[1656] [Fourth embodiment]

[1657] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1658] 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.

[1659] 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).

[1660] 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.

[1661] 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.

[1662] 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).

[1663] 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. 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.

[1664] 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.

[1665] 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.

[1666] 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.

[1667] 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.

[1668] 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.

[1669] 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."

[1670] System Overview

[1671] The system of the present invention uses an artificial intelligence system to generate answers to questions entered by users, and then identifies the root cause by continually asking "Why?", summarizing and visualizing the results for presentation. This system is composed of a server, a terminal, and a user.

[1672] System Components

[1673] 1. On the user's device:

[1674] Accepts question input.

[1675] Send a question to the server.

[1676] Receives the results from the server and displays them to the user.

[1677] 2. Server:

[1678] A question is received from the user's terminal.

[1679] Send your questions to an artificial intelligence system and receive answers.

[1680] A follow-up question ("Why?") is generated based on the answer and repeatedly sent to the artificial intelligence system.

[1681] Finally, the system generates summarized and visualized information and transmits the results to the user's terminal.

[1682] 3. Artificial Intelligence Systems:

[1683] Generate answers to questions.

[1684] Generate answers even for additional questions sent repeatedly.

[1685] Program processing flow

[1686] 1. User inputs a question

[1687] A user types a question into a terminal, for example, "What is the cause of low sales?"

[1688] 2. Receiving and sending questions

[1689] The terminal sends a user's question to the server, which then sends the question to the artificial intelligence system and receives an initial answer.

[1690] 3. Analyzing initial answers and generating follow-up questions

[1691] The server analyzes the initial answer received from the AI ​​system, generates a follow-up question, "Why?", and sends it back to the AI ​​system.

[1692] 4. Iteration

[1693] The server repeats this process as necessary, asking additional questions and answers, such as "Low sales are due to low customer satisfaction," "Why are customer satisfaction low?", "Because of poor product quality," and "Why is product quality poor?"

[1694] 5. Identifying the root cause

[1695] At some point, the server decides it has reached the root cause, which in this case is "poor supply chain management."

[1696] 6. Summarization and visualization

[1697] The server summarizes all the answers and visualizes them as flowcharts or causal diagrams, for example, generating a flowchart that shows: "Low sales → Low customer satisfaction → Low product quality → Inferior raw materials → Poor supply chain management."

[1698] 7. Displaying the results

[1699] The server generates a visualization and sends it to the user's device, where the user can view it and understand that the root cause of the low sales is "poor supply chain management."

[1700] Specific examples

[1701] For example, if a user types "What is the cause of low sales?" into a terminal, the server sends this question to the artificial intelligence system and receives the initial answer "Because of low customer satisfaction." The server then generates a follow-up question, "Why is customer satisfaction low?" and repeats this process until it finally arrives at the root cause: "Because of poor supply chain management." The results are visualized as a flowchart and displayed to the user.

[1702] The system allows users to quickly and efficiently identify the root cause of a problem, rather than just its surface area.

[1703] The processing flow will be explained below.

[1704] Step 1:

[1705] User enters a question:

[1706] Using the terminal interface, users enter questions about their problems, such as "What is the cause of low sales?"

[1707] Step 2:

[1708] The device sends a question to the server:

[1709] The terminal sends the user's input question to the server, where it is formatted to ensure that the content of the question is accurately conveyed to the server.

[1710] Step 3:

[1711] The server receives the question and sends it to the AI ​​system:

[1712] The server sends the question received from the terminal to the artificial intelligence system, where it checks that the question format can be analyzed by the AI ​​system.

[1713] Step 4:

[1714] An artificial intelligence system generates an initial answer:

[1715] The AI ​​system generates an initial answer based on the submitted question, such as "because customer satisfaction is low," and sends it back to the server.

[1716] Step 5:

[1717] The server receives the initial answer and generates a follow-up question:

[1718] The server analyzes the initial answer received from the AI ​​system, generates a follow-up question, "Why?", formats it, and sends it back to the AI ​​system.

[1719] Step 6:

[1720] Server and AI system iteration:

[1721] The server receives additional answers from the AI ​​system and continues to ask "Why?" about those answers, repeating this process until it arrives at the root cause, for example, "Why is customer satisfaction low?" → "Because the product quality is low" → "Why is the product quality low?" → "Because the raw materials are inferior."

[1722] Step 7:

[1723] Server identifies root cause:

[1724] Finally, the server identifies the root cause from the answers provided by the AI ​​system, which in this case concludes that it is due to "poor supply chain management."

[1725] Step 8:

[1726] Server summarization and visualization:

[1727] The server summarizes all the answers and questions exchanged and visualizes the causal relationships in a visually understandable format (e.g., a flowchart or causal diagram).

[1728] Step 9:

[1729] The server sends the visualized results to the terminal:

[1730] The server then sends the visualized results to the user's device, allowing the user to visually check the overall picture of the answers.

[1731] Step 10:

[1732] The terminal displays the results to the user:

[1733] The terminal displays the visualized results sent from the server to the user, who then checks the results on the terminal and understands that the root cause of low sales is "poor supply chain management."

[1734] These are the steps in which a user inputs a question, the server and the artificial intelligence system work together to identify the root cause of the problem, and then visualize the results and present them to the user.

[1735] Example 1

[1736] 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."

[1737] Conventional information processing systems often focus only on superficial problems, making it difficult to quickly and accurately identify the root cause. Furthermore, there is a lack of means to provide information in a format that allows users to easily understand the root cause of a problem, which can sometimes make the path to problem resolution unclear. In response to this, there is a need for a method to identify the root cause and visually present it to the user.

[1738] 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.

[1739] In this invention, the server includes means for inputting a question from a user, means for transmitting the input question to the data processing device, means for receiving an answer from the data processing device, means for generating a follow-up question based on the received answer, means for continuously sending follow-up questions to the data processing device, means for identifying a final answer from the data processing device, means for summarizing and visualizing the process and result, means for presenting the summarized and visualized information to the user, means for analyzing each answer and generating a follow-up question such as "Why?", and means for visualizing multiple answers and their causal relationships as a flowchart or causal diagram. This allows the user to quickly and accurately identify not only superficial answers but also root causes and to intuitively understand the information visually.

[1740] The "means for inputting a question" is a device or software that provides an interface for a user to input a question in text format.

[1741] The "means for transmitting to the data processing device" is a device or software having a communication function for transmitting the input question to the data processing device via a network.

[1742] The "means for receiving a response" is a device or software having a communication function for receiving a response sent from the data processing device.

[1743] A "means for generating follow-up questions" is an algorithm or software for automatically generating further questions based on the initial answers.

[1744] The "means for continuing to send to the data processing device" refers to a device or software having a communication function for repeatedly sending the generated additional questions to the data processing device.

[1745] The "means for identifying a final answer" is an algorithm or software for identifying a root cause from among multiple answers received from the data processing device.

[1746] The "summarization and visualization tool" is software that concisely summarizes multiple answers and their causal relationships and visually displays them in a format that is easy for users to understand.

[1747] A "means for presenting information to a user" is a device or software for displaying visualized information to a user.

[1748] The "means for generating follow-up "Why?" questions" is an algorithm or software for generating follow-up "Why?" questions for each answer.

[1749] A "causal visualization tool" is software for visualizing multiple answers and their relationships as a flowchart or causal diagram.

[1750] The specific implementation procedure for the mode for implementing the invention is described below. This system uses an artificial intelligence system to generate answers to questions entered by users, and then identifies the root cause by continually asking "Why?", and summarizes and visualizes the results for presentation. This system is composed of a server, a terminal, and a user.

[1751] System Components

[1752] 1. User's device

[1753] A question is input through a user interface.

[1754] Send the question to the server.

[1755] The results received from the server are displayed to the user.

[1756] 2. Server

[1757] A question is received from the user's terminal.

[1758] Send your questions to an artificial intelligence system and receive answers.

[1759] Based on the answers, a follow-up question, "Why?", is generated and repeatedly sent to the artificial intelligence system.

[1760] Finally, the summarized and visualized information is generated and sent to the user's terminal.

[1761] 3. Artificial Intelligence Systems

[1762] A data processing device for generating answers to questions.

[1763] It also generates answers to the follow-up question "Why?" that is repeatedly asked.

[1764] Hardware and Software

[1765] The main components of the system include:

[1766] User's device: A device that performs input and output, such as a regular PC, smartphone, or tablet.

[1767] Server: A high-performance data processing device that calls artificial intelligence models, summarizes data, visualizes data, etc.

[1768] Artificial intelligence systems: Use generative AI models such as OpenAI's GPT-3 and GPT-4.

[1769] Program processing overview

[1770] The program for this system includes the following processes:

[1771] 1. A user types a question into a terminal, for example, "What is the cause of low sales?"

[1772] 2. The device sends this question to the server, which sends it to the artificial intelligence system and receives an initial answer.

[1773] 3. The server analyzes the initial answer received from the AI ​​system, generates a follow-up question, "Why?", and sends it back to the AI ​​system.

[1774] 4. The server repeats this process, asking additional questions and answers, for example, "Low sales are due to low customer satisfaction," "Why is customer satisfaction low?", "Because the product quality is low," "Why is the product quality low?"

[1775] 5. At some point, the server determines that it has reached the root cause, which in this example is "poor supply chain management."

[1776] 6. The server summarizes all the answers and visualizes them as flowcharts or causal diagrams. For example, it generates a flowchart that shows: "Low sales → Low customer satisfaction → Low product quality → Inferior raw materials → Poor supply chain management."

[1777] 7. The server sends the visualized results to the user's device, where the user can view them and understand that the root cause of low sales is "poor supply chain management."

[1778] Specific examples

[1779] For example, if a user types "What is the cause of low sales?" into a terminal, the server sends this question to the artificial intelligence system and receives the initial answer "Because of low customer satisfaction." The server then generates a follow-up question, "Why is customer satisfaction low?" and repeats this process until it finally arrives at the root cause: "Because of poor supply chain management." The results are visualized as a flowchart and displayed to the user.

[1780] Prompt Sentence Examples

[1781] "What is the cause of low sales?"

[1782] "Why is customer satisfaction low?"

[1783] "Why is the product quality poor?"

[1784] The above is a specific embodiment for carrying out the invention, which allows the user to quickly and accurately identify the root cause of a problem, not just the surface problem.

[1785] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1786] Program processing flow

[1787] Step 1:

[1788] The user inputs a question into the terminal.

[1789] Input: User input (e.g., "What is the cause of low sales?")

[1790] Output: Text data entered into the terminal

[1791] Specific operation: The user enters a question in the text box on the terminal and presses the send button.

[1792] Step 2:

[1793] The terminal sends a question from the user to the server.

[1794] Input: Text data entered by the user

[1795] Output: HTTP request to the server

[1796] Specific operation: The device sends the entered question as an HTTP request.

[1797] Step 3:

[1798] The server receives the question and sends it to the artificial intelligence system.

[1799] Input: HTTP request (question) from the terminal

[1800] Output: Prompt to the artificial intelligence system

[1801] Specific operation: The server receives an HTTP request and sends it as a prompt to the artificial intelligence system.

[1802] Step 4:

[1803] The artificial intelligence power generates answers to the questions received.

[1804] Input: prompt (question)

[1805] Output: The generated answer

[1806] Specific operation: The AI ​​system uses natural language processing to generate an answer based on the question it receives.

[1807] Step 5:

[1808] The server analyzes the answers received from the artificial intelligence system.

[1809] Input: Answer from an artificial intelligence system

[1810] Output: Analysis results (additional questions)

[1811] Specific behavior: The server analyzes the answer text and generates a follow-up question of the form "Why?"

[1812] Step 6:

[1813] The server generates additional questions and resubmits them to the artificial intelligence system.

[1814] Input: Analysis results (additional questions)

[1815] Output: A new prompt to the artificial intelligence system

[1816] Specific operation: The server resends the additional question as a prompt to the artificial intelligence system.

[1817] Step 7:

[1818] The server repeats this process as necessary.

[1819] Input: Repeated answers from an artificial intelligence system

[1820] Output: Final answer

[1821] Specific operation: The server analyzes the answer and repeats the process of generating and sending a new question.

[1822] Step 8:

[1823] The server determines the final answer.

[1824] Input: Repeated answers

[1825] Output: Root cause (final answer)

[1826] Specific operation: The server identifies the most fundamental cause from the set of answers and determines this as the final answer.

[1827] Step 9:

[1828] The server summarizes and visualizes the process and results.

[1829] Input: All answers and their causal relationships

[1830] Output: Visualized data (flowcharts and causal diagrams)

[1831] Specific behavior: The server uses Python libraries (such as matplotlib and Graphviz) to visualize the relationships between answers.

[1832] Step 10:

[1833] The server sends the visualized results to the user's terminal.

[1834] Input: Visualization data

[1835] Output: Send data to the user's device

[1836] Specific operation: The server sends the generated visualization data to the user's device as an HTTP response.

[1837] Step 11:

[1838] The terminal displays the received results to the user.

[1839] Input: Visualization data from the server

[1840] Output: The result displayed in the user interface

[1841] Specific operation: The device displays the visualization data it receives on the screen so that the user can check it.

[1842] These are the specific processing steps of the system, which allow users to quickly identify and intuitively understand the root cause of any problem, from the surface level.

[1843] (Application example 1)

[1844] 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."

[1845] Conventional production facilities lacked the means to identify production efficiency or quality issues from operational data and quickly and efficiently identify their root causes. As a result, problem resolution took time, leading to a risk of reduced productivity. Furthermore, previous systems required users to manually track problems, often resulting in delayed analysis. This invention solves these issues and aims to improve operational efficiency in factories.

[1846] 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.

[1847] In this invention, the server includes means for inputting a question from a user, means for transmitting the input question to an artificial intelligence system, means for receiving an answer from the artificial intelligence system, means for generating a follow-up question based on the received answer, means for continuously transmitting the follow-up question to the artificial intelligence system, means for identifying a final answer from the artificial intelligence system, means for summarizing and visualizing processes and results, means for presenting the summarized and visualized information to a user, means for collecting operation data of a production facility, means for generating a question regarding a problem with production efficiency or quality based on the operation data, means for identifying a root cause for the question, and means for visualizing the identified root cause and related information, thereby enabling quick and efficient identification and analysis of the root cause of a problem in a production facility.

[1848] "User" refers to an individual or organization who uses the system to enter questions and receive final answers and visualized information.

[1849] "Means for inputting a question" refers to an interface that allows a user to input a question to the system, such as a keyboard or a touch screen.

[1850] "Means for sending questions to an AI system" refers to communications means for transmitting input questions to an AI system, such as the Internet or a local network.

[1851] "Artificial intelligence system" refers to software or hardware that automatically generates answers to questions, such as the generative AI model GPT-3.

[1852] "Means for receiving a response" refers to an interface or system for obtaining and processing a response from an artificial intelligence system.

[1853] "Means for generating follow-up questions" refers to algorithms or logic for automatically generating further follow-up questions based on the initial answers.

[1854] "Means for continuing to send follow-up questions to the artificial intelligence system" refers to communication means for repeatedly sending the generated follow-up questions to the artificial intelligence system.

[1855] "Means for identifying a final answer" refers to the logic or algorithm used to determine a final answer related to the root cause through a process of asking and answering a series of questions.

[1856] "Summarization and visualization tools" refers to software and tools that organize the responses and present them in a visually understandable format.

[1857] The "means for presenting the summarized and visualized information to the user" refers to an interface for displaying the visualized information so that the user can confirm it.

[1858] "Production equipment" is a general term for the machinery and equipment used in factories and production lines.

[1859] "Means for collecting operational data" refers to sensors and data acquisition systems for obtaining operational information and performance data from production equipment.

[1860] The "means for generating questions related to production efficiency and quality issues" refers to an algorithm for identifying issues related to production efficiency and quality based on collected operational data and automatically generating questions related to those issues.

[1861] "Means for identifying root causes" refers to analytical logic or algorithms for identifying the root causes of problems from the answers to the generated questions.

[1862] "Means for visualizing related information" refers to software or tools that provide an easy-to-understand visual display of identified root causes and related information.

[1863] The basic embodiment of this invention relates to a system for identifying the root cause of problems in factory production equipment. This system starts with user input, uses an artificial intelligence system to perform an in-depth analysis of the problem, and visualizes the results. Specifically, this system is implemented as follows.

[1864] System configuration

[1865] User's device

[1866] Question entry interface: An interface through which a user can enter a question, including a keyboard or touchscreen.

[1867] Sending and receiving module: A module for sending the entered question to the server and displaying the results received from the server.

[1868] server

[1869] Communication module: A module for communicating with user terminals to send and receive questions and answers.

[1870] AI processing module: A module that sends questions received from users to an artificial intelligence system and receives answers.

[1871] Follow-up question generation module: A module that generates follow-up questions ("Why?") based on the initial answers.

[1872] Repeated question module: A module that sends the generated additional questions to the artificial intelligence system again.

[1873] Visualization module: A module that visualizes the final answer and its related information as a flowchart or causal diagram.

[1874] Production Equipment

[1875] Data collection module: Sensors and data acquisition systems that collect operational data from production equipment in real time.

[1876] Data Analysis Module: A module that generates questions about production efficiency and quality issues based on collected data.

[1877] Software and hardware used

[1878] Generative AI models: Use generative AI models such as OpenAI's GPT-3.

[1879] Programming language: Program implemented using Python.

[1880] Visualization tools: Graph generation using Matplotlib and NetworkX.

[1881] Communication infrastructure: Internet connection and local network.

[1882] Process Description

[1883] 1. User question input: The user uses the terminal to input a question about the production equipment. A specific example is the question, "Why is the production efficiency low in line A?"

[1884] 2. Sending a question and receiving an answer: The user's device sends the entered question to the server, which then sends the question to the generative AI model, receives the initial answer from the generative AI model, and analyzes the answer.

[1885] 3. Generate and send follow-up questions: The server automatically generates a follow-up question, "Why?", based on the initial answer it received and sends this question to the generative AI model again. For example, for the answer "The machine breaks down frequently," it generates a follow-up question, "Why does the machine break down frequently?"

[1886] 4. Iterative process: This question and answer process continues until the root cause is reached.

[1887] 5. Visualization and display: Finally, the server visualizes the results of the series of questions and answers as a flowchart or causal diagram and sends it to the user's device.

[1888] Examples of concrete examples and prompts

[1889] Specific examples

[1890] If a problem of low production efficiency occurs on production line A in a factory, this system can be used to identify the root cause using the following procedure.

[1891] Q: Why is the production efficiency low in line A?

[1892] A: Because the machine breaks down frequently.

[1893] Q: Why does the machine break down frequently?

[1894] A: Because the regular maintenance is insufficient.

[1895] Q: Why is the regular maintenance insufficient?

[1896] A: Because the maintenance schedule is not properly managed.

[1897] Prompt Sentence Examples

[1898] First prompt:

[1899] "Why is the production efficiency low in line A?"

[1900] Additional prompts:

[1901] "Why does the machine breakdown frequently?"

[1902] "Why is the regular maintenance insufficient?"

[1903] "Why is the maintenance schedule not properly managed?"

[1904] In this way, it becomes possible to specifically and quickly identify the root cause of problems in production equipment.

[1905] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1906] Step 1:

[1907] User question input

[1908] The user uses the terminal to input questions about production equipment. The input questions are in the form of "Why is the production efficiency low in line A?" The terminal is equipped with an interface that allows questions to be input using a keyboard or touch screen. The input here is in text format, and that text is used in the next step.

[1909] Step 2:

[1910] Submit a Question

[1911] The user's device sends the entered question to the server. Specifically, when the user has finished entering the question on the device, they press the send button, which sends the question to the server via the network. The device uses a communication protocol such as an HTTP request to send the entered question to the server. At this stage, text data is sent from the device to the server.

[1912] Step 3:

[1913] Sending questions to an AI system

[1914] The server sends the received question to a generative AI model (e.g., GPT-3). Specifically, the server generates an API request to send the question to the AI ​​model. This request includes the question text and data for the AI ​​to answer. The server prepares to receive the answer from the AI ​​model.

[1915] Step 4:

[1916] Receiving an initial response

[1917] The server receives the answer from the generative AI model. The AI ​​model generates a text answer to the question it received, and this answer is returned to the server. For example, the answer may be "Because the machine breaks down frequently." The next step is based on this answer.

[1918] Step 5:

[1919] Generate follow-up questions

[1920] The server generates a follow-up question called "Why?" based on the initial answer. Specifically, based on the answer received, the server creates a question by asking the AI ​​model again, "Why does that state occur?" For example, the question "Why does the machine break down frequently?" is automatically generated.

[1921] Step 6:

[1922] Submitting Repeated Questions

[1923] The server then sends the generated questions to the AI ​​model again. This process is similar to step 3, sending the generated questions to the AI ​​model through the API and receiving the answers. This iterative questioning process can continue as needed.

[1924] Step 7:

[1925] Identifying the root cause

[1926] The server repeats this series of questions and answers until it determines that it has reached the root cause of the problem. For example, if the final answer is "Because the maintenance schedule is not properly managed," this answer is identified as the root cause.

[1927] Step 8:

[1928] Summarize and visualize

[1929] The server summarizes the data from a series of questions and answers and visualizes them as flowcharts or causal diagrams. Specifically, it uses NetworkX and Matplotlib to generate graphs of the relationship between questions and answers. This visualized information is used by users to help them understand the overall picture of the problem.

[1930] Step 9:

[1931] Displaying the results

[1932] The server sends the visualized flowchart or causal diagram to the user's device, which then displays the visualized information for the user to review, allowing the user to understand the root cause of the problem at a glance.

[1933] 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.

[1934] System Overview

[1935] The system of the present invention uses an artificial intelligence system to generate answers to questions entered by users, identifies the root cause by continually asking "Why?", analyzes the user's emotions using an emotion engine, and summarizes and visualizes the results for presentation. This system is composed of a server, a terminal, a user, and an emotion engine.

[1936] System Components

[1937] 1. On the user's device:

[1938] Accepts question input.

[1939] Send a question to the server.

[1940] Receives the results from the server and displays them to the user.

[1941] 2. Server:

[1942] A question is received from the user's terminal.

[1943] Send your questions to an artificial intelligence system and receive answers.

[1944] A follow-up question ("Why?") is generated based on the answer and repeatedly sent to the artificial intelligence system.

[1945] Send data to an emotion engine to analyze the user's emotions and receive the analysis results.

[1946] Finally, the system generates summarized and visualized information and transmits the results to the user's terminal.

[1947] 3. Artificial Intelligence Systems:

[1948] Generate answers to questions.

[1949] Generate answers even for additional questions sent repeatedly.

[1950] 4. Emotion Engine:

[1951] Emotional data is extracted by analyzing user input and responses.

[1952] Complementing the context of questions and answers with sentiment data.

[1953] Emotion data is sent to the server and supports the server's processing.

[1954] Program processing flow

[1955] 1. User inputs a question

[1956] A user types a question into a terminal, for example, "What is the cause of low sales?"

[1957] 2. Receiving and sending questions

[1958] The terminal sends a user's question to the server, which then sends the question to the artificial intelligence system and receives an initial answer.

[1959] 3. Analyzing initial answers and generating follow-up questions

[1960] The server analyzes the initial response received from the AI ​​system, combines the user's emotional data analyzed by the emotion engine with the response, generates a follow-up question called "Why?", formats it, and sends it back to the AI ​​system.

[1961] 4. Iteration

[1962] The server receives additional answers from the AI ​​system and continues to ask "Why?" in response to those answers, taking into account the data from the emotion engine. This process is repeated as necessary, for example, "Why is customer satisfaction low?" → "Because the product quality is low" → "Why is the product quality low?" → "Because the raw materials are inferior," until the root cause is identified.

[1963] 5. Identifying the root cause

[1964] At some point, the server decides it has reached the root cause, which in this case is "poor supply chain management."

[1965] 6. Summarization and visualization

[1966] The server summarizes all the answers and questions exchanged and visualizes the causal relationships in a visually understandable format (such as a flowchart or causal diagram). It then adjusts the visualization based on the analysis results of the emotion engine. For example, it generates a flowchart that shows "Low sales → Low customer satisfaction → Low product quality → Poor raw materials → Insufficient supply chain management."

[1967] 7. Displaying the results

[1968] The server generates a visualization and sends it to the user's device, where the user can view it and understand that the root cause of the low sales is "poor supply chain management."

[1969] Specific examples

[1970] For example, if a user types "What is the cause of low sales?" into a terminal, the server sends this question to the artificial intelligence system, which receives the initial answer "Because customer satisfaction is low." The emotion engine then analyzes the emotional data from the user's input and reactions, and the server generates a follow-up question: "Why is customer satisfaction low?" This process is repeated until the root cause is finally identified as "Because of insufficient supply chain management." The results are visualized as a flowchart, adjusted based on the emotion engine's analysis, and displayed to the user.

[1971] This system allows users to efficiently identify the root cause of a problem, rather than simply looking at the surface, through sentiment analysis, enabling them to quickly find an effective solution.

[1972] The processing flow will be explained below.

[1973] Step 1:

[1974] User enters a question:

[1975] Using the terminal interface, the user enters a question about the problem they want to solve, such as "What is the cause of low sales?"

[1976] Step 2:

[1977] The device sends a question to the server:

[1978] The terminal sends the question entered by the user to the server, which formats the question so that it can be accurately transmitted to the server.

[1979] Step 3:

[1980] The server receives the question and sends it to the AI ​​system:

[1981] The server sends the question received from the terminal to the AI ​​system, where it checks that the question is in a format that can be analyzed.

[1982] Step 4:

[1983] An artificial intelligence system generates an initial answer:

[1984] The AI ​​system generates an initial answer based on the submitted question, for example, "Because customer satisfaction is low," and sends it back to the server.

[1985] Step 5:

[1986] The server receives the initial response and sends it to the emotion engine:

[1987] The server sends the initial response received from the AI ​​system to the emotion engine, which extracts emotion data from the user's input and reactions and returns the data to the server.

[1988] Step 6:

[1989] The server generates follow-up questions based on data from the emotion engine:

[1990] The server generates a follow-up question based on the initial answer and the analysis results of the emotion engine, such as "Why is customer satisfaction so low?", and sends it to the AI ​​system.

[1991] Step 7:

[1992] The server receives the additional response and sends it back to the emotion engine:

[1993] The server sends the additional answer received from the AI ​​system to the emotion engine, which analyzes the user's emotion data again. The result is used to generate the next additional question.

[1994] Step 8:

[1995] The server receives and analyzes the final response to determine the root cause:

[1996] The server continues the iterative process, eventually arriving at a root cause such as "poor supply chain management." At this stage, the server identifies the final answer.

[1997] Step 9:

[1998] The server summarizes the answer and visualizes it:

[1999] The server summarizes all responses and generates a flowchart or causal diagram showing the causal relationships. The visualization format is adjusted based on the analysis results of the emotion engine.

[2000] Step 10:

[2001] The server sends the visualized results to the terminal:

[2002] The server transmits the visualized results to the user's terminal.

[2003] Step 11:

[2004] The terminal displays the results to the user:

[2005] The terminal displays the visualized results sent from the server to the user, who then checks the results on the terminal and understands that the root cause of low sales is "poor supply chain management."

[2006] The above are the specific processing steps in a system that combines an emotion engine, from receiving a question from a user, to identifying the root cause, visualizing it, and displaying it to the user.

[2007] Example 2

[2008] 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."

[2009] Conventional question-answering systems only provide simple answers to user questions and are unable to identify the underlying causes behind the answers. Furthermore, they lack the means to analyze and visualize dependencies in detail while taking the user's emotions into account, making it difficult for users to understand the overall picture of the problem they are facing. The objective of this invention is to provide a system that identifies the root causes of user questions and summarizes and visualizes the results while analyzing the user's emotions.

[2010] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for inputting a question from a user, means for transmitting the input question to an artificial intelligence system, means for receiving an answer from the artificial intelligence system, means for generating a follow-up question based on the received answer and analyzing the user's emotions using an emotion analysis means, means for continuously sending the follow-up question to the artificial intelligence system, means for identifying a final answer from the artificial intelligence system, means for summarizing the process and result and visualizing it based on the emotion analysis result, and means for presenting the summarized and visualized information to the user. This makes it possible to identify the root cause of a user's question and efficiently provide analysis results that take the user's emotions into consideration.

[2011] A "user" is a person or organization that enters a question into the system and receives answers or analysis results.

[2012] A "terminal" is a device that a user uses to enter a question and receive and display results from the server.

[2013] The "server" is a central computer that sends questions received from the user's terminal to the artificial intelligence system and manages the answers and analysis results.

[2014] An "artificial intelligence system" is a knowledge processing system that generates answers to user questions and responds to follow-up questions.

[2015] "Emotion analysis means" refers to technology that analyzes user input and responses to extract emotional data and complements the context of questions and answers based on that data.

[2016] A "follow-up question" is a further question that is generated based on the user's initial answer to the first question.

[2017] "Summarizing" refers to summarizing and organizing the entire question and answer process.

[2018] "Visualization" refers to converting summarized information into a visual format such as a flowchart or cause-and-effect diagram and displaying it.

[2019] The "final answer" is the root cause or solution identified at the end of the cyclical process.

[2020] A "prompt" is an input sentence that is used to enter a question into a generative AI model and obtain an answer.

[2021] System Overview

[2022] The system based on this invention generates answers to questions entered by users using a generative AI model (e.g., GPT-3), identifies the root cause by repeatedly asking "Why?", analyzes the user's emotions using emotion analysis means, and summarizes and visualizes the results for presentation. This system is composed of a server, a terminal, a user, and emotion analysis means.

[2023] Hardware and software used

[2024] Server: The central computer that processes user queries and communicates with the AI ​​system and sentiment analysis engine.

[2025] Terminal: A device operated by a user, such as a PC, smartphone, or tablet.

[2026] Generative AI models: Natural language processing models such as GPT-3.

[2027] Sentiment analysis means: An analysis engine for analyzing user input data and reactions and extracting emotional data.

[2028] Specific examples of processing

[2029] 1. User inputs a question

[2030] The user types a question into the terminal, such as: "What is the cause of low sales?"

[2031] 2. Receiving and sending questions

[2032] The device sends the user's question to the server, which then sends the question as a prompt to the generative AI model.

[2033] 3. Analyzing initial answers and generating follow-up questions

[2034] The server analyzes the initial answer received from the generative AI model. For example, if the initial answer is "Because customer satisfaction is low," the server uses sentiment analysis means to analyze the user's sentiment and then generates a follow-up question such as "Why is customer satisfaction low?"

[2035] 4. Iteration

[2036] The server receives additional answers from the generative AI model and repeats the same procedure to ask "Why?" For example, if the server receives the additional answer "The product quality is low," it then generates the question "Why is the product quality low?"

[2037] 5. Identifying the root cause

[2038] The server repeats the circular process, ultimately identifying the root cause as "insufficient supply chain management."

[2039] 6. Summarization and visualization

[2040] The server summarizes all the answers and questions and visualizes them in the form of a flowchart or causal diagram, for example, "Low sales → Low customer satisfaction → Low product quality → Inferior raw materials → Poor supply chain management."

[2041] 7. Displaying the results

[2042] The server then sends the generated visualization results to the user's device, where the user can view them and understand the root cause of the problem.

[2043] Examples of prompt statements

[2044] Initial prompt: "What is the cause of low sales?"

[2045] Follow-up prompt: "Considering the user's frustration, why is customer satisfaction low?"

[2046] This invention allows users to go beyond just superficial answers to problems and identify the root cause with sentiment analysis, allowing them to quickly find effective solutions.

[2047] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2048] Step 1:

[2049] The user enters a question

[2050] Input: The user types a text question into the input field on the device.

[2051] Action: User types question: "What is the cause of low sales?"

[2052] Output: The terminal generates text data of questions from the user.

[2053] Step 2:

[2054] The device sends a question to the server

[2055] Input: The terminal has the question text data entered by the user.

[2056] Processing: The terminal sends this query data to the server.

[2057] Output: The server receives the question text data.

[2058] Step 3:

[2059] The server sends the question to the AI ​​system.

[2060] Input: The server has the question text data received from the terminal.

[2061] Processing: The server sends a question as a prompt to the generative AI model (e.g., GPT-3).

[2062] Output: The generative AI model returns an initial answer to the question it receives.

[2063] Step 4:

[2064] The server receives and analyzes the initial response.

[2065] Input: Contains the initial answer the server received from the generative AI model.

[2066] Processing: The server analyzes the initial response and evaluates the content of the response, for example, "Because customer satisfaction is low."

[2067] Output: A server with the analysis results.

[2068] Step 5:

[2069] The server analyzes the user's emotions using emotion analysis means.

[2070] Input: The server has the user's initial input and response data.

[2071] Processing: The server sends the data to a sentiment analysis means, which analyzes the user's emotional state (e.g., "I feel frustrated").

[2072] Output: Server with sentiment analysis results.

[2073] Step 6:

[2074] The server generates a follow-up question

[2075] Input: The server has the parsed initial answer and sentiment analysis results.

[2076] Processing: The server generates a follow-up question: "Why is customer satisfaction low?"

[2077] Output: Server with additional questions.

[2078] Step 7:

[2079] The server sends additional questions to the generative AI model

[2080] Input: The server has a follow-up question.

[2081] Processing: The server sends a follow-up question to the generative AI model.

[2082] Output: The generative AI model returns an additional answer.

[2083] Step 8:

[2084] The server repeats "Why?" as needed.

[2085] Input: The server has additional answers from the generative AI model.

[2086] Processing: The server analyzes the additional responses, performs sentiment analysis again, and generates a new "Why?" question. This process is repeated until the root cause is identified.

[2087] For example, if an additional response such as "The product quality is low" is received, a new question such as "Why is the product quality low?" is generated.

[2088] Output: The server reaches the final root cause.

[2089] Step 9:

[2090] The server identifies the final answer

[2091] Input: The server has all the questions and answers.

[2092] Processing: The server identifies the root cause from the answers, for example, selecting the final answer "due to insufficient supply chain management."

[2093] Output: The server with the final answer identified.

[2094] Step 10:

[2095] The server summarizes and visualizes the process and results.

[2096] Input: The server has a set of questions and answers, as well as sentiment analysis results.

[2097] Processing: The server summarizes all interactions and visualizes them in the form of flowcharts or cause-and-effect diagrams. For example, it generates a flowchart that shows: "Low sales → Low customer satisfaction → Low product quality → Poor raw materials → Poor supply chain management."

[2098] Output: A server with visualized data.

[2099] Step 11:

[2100] The server sends the visualized results to the user's device.

[2101] Input: The server has the data to be visualized.

[2102] Processing: The server sends the visualized results to the user's terminal.

[2103] Output: The visualized result received by the user's device.

[2104] Step 12:

[2105] The user checks the results

[2106] Input: The user's terminal has the visualized results.

[2107] Action: The user reviews the results on their device and understands the root cause of the problem.

[2108] Output: The user gains an understanding of the problem.

[2109] The above processing steps allow the user to navigate through the system to the root cause and visually understand the process and results.

[2110] (Application example 2)

[2111] 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."

[2112] Conventional security incident analysis systems require a great deal of time and effort to identify the root cause of a problem. In addition, they develop countermeasures without taking into account the emotional state of the person in charge of responding to the incident, which reduces the quality of the response and increases the risk of further incidents.

[2113] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting a user's question, means for sending the input question to the artificial intelligence system, means for receiving an answer from the artificial intelligence system, means for generating a follow-up question based on the received answer, means for continuously sending follow-up questions to the artificial intelligence system, means for identifying a final answer from the artificial intelligence system, means for summarizing and visualizing the process and result, means for presenting the summarized and visualized information to the user, emotion analysis means for analyzing the user's emotions, means for complementing the question based on the emotion data analyzed by the emotion analysis means, and means for presenting appropriate countermeasures according to the user's emotional state. This makes it possible to quickly and efficiently identify the root cause of a security incident and propose appropriate countermeasures that take into account the emotional state of the person in charge.

[2114] The "means for inputting questions from the user" is an interface that allows the user to input questions about security incidents into the system.

[2115] The "means for transmitting an input question to the artificial intelligence system" is a communication means for transmitting a question input by a user to the artificial intelligence system.

[2116] The "means for receiving a response from an artificial intelligence system" refers to a means for receiving a response generated by the artificial intelligence system.

[2117] The "means for generating a follow-up question based on the received answer" refers to a means for generating a new question based on the answer received from the artificial intelligence system.

[2118] The "means for continuing to send follow-up questions to the artificial intelligence system" refers to a means for repeatedly sending the generated follow-up questions to the artificial intelligence system.

[2119] "Means for identifying a final answer from an artificial intelligence system" refers to a means for identifying a final root cause through multiple exchanges of questions and answers.

[2120] "Means for summarizing and visualizing processes and results" are means for summarizing the question and answer process and visually displaying the results.

[2121] The "means for presenting summarized and visualized information to a user" refers to a means for displaying summarized and visualized information to a user.

[2122] The "emotion analysis means for analyzing the user's emotions" is a means for extracting and analyzing emotion data from the user's inputs and reactions.

[2123] The "means for completing a question based on emotion data analyzed by the emotion analysis means" is a means for generating or completing a question based on data obtained by emotion analysis.

[2124] The "means for presenting appropriate countermeasures according to the emotional state of the user" is a means for presenting appropriate countermeasures to the user based on the results of emotion analysis.

[2125] The system for implementing the present invention supports the process of a user inputting questions about a security incident and identifying its root cause. The system mainly includes the following components:

[2126] 1. User's device

[2127] It accepts questions from users, sends them to the server, and receives and displays the results from the server. A typical smartphone or head-mounted display (HMD) can be used.

[2128] 2. Server

[2129] The system receives questions from the user's device, sends them to the AI ​​system, and receives answers. It then generates additional questions based on the received answers and sends them back to the AI ​​system. It identifies the final answer, summarizes and visualizes the process and results, and uses emotion analysis to analyze the user's emotions. It complements the questions based on the results and presents appropriate countermeasures to the user.

[2130] 3. Artificial Intelligence Systems

[2131] The system generates answers to user questions and continues to generate answers to follow-up questions. This artificial intelligence system uses a generative AI model that utilizes natural language processing technology.

[2132] 4. Emotion analysis method

[2133] Emotional data is extracted from the user's input and responses and analyzed. Based on this data, the system can complete questions and suggest appropriate countermeasures.

[2134] When a user enters a question about the cause of a security incident, the question is sent to the server via the terminal. The server receives the question and sends it to the AI ​​system. The AI ​​system then receives an initial answer and generates a follow-up question based on that answer. These follow-up questions are in the "Why?" format and are repeatedly generated and sent to the AI ​​system until the root cause is identified.

[2135] The emotion analysis means collects and analyzes emotional data obtained from user input and responses. Based on the analysis results, the server complements the question and presents appropriate responses according to the user's emotional state.

[2136] For example, if a user asks, "Why did the server go down?", the initial answer generated is "Because the server was overloaded." In response to this answer, the server generates a follow-up question, "Why was the server overloaded?" and repeatedly sends this to the AI ​​system. Eventually, the root cause is identified as "inappropriate resource management." During this time, the emotion analysis means assesses the user's stress level and suggests appropriate breaks or assistance as needed.

[2137] In this way, the present invention is a system that can improve the efficiency of analyzing the causes of security incidents and also propose countermeasures that take into account the user's emotional state.

[2138] Example prompt sentence:

[2139] Why did the server go down?

[2140] Why was the server overloaded?

[2141] "Users are stressed"

[2142] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2143] Step 1:

[2144] The user enters a question about the security incident.

[2145] Input: A user-asked question (e.g., "Why is the server down?")

[2146] Output: A query request from the user's device to the server

[2147] Specific operation: The user inputs a question into the interface using a smartphone or HMD.

[2148] Step 2:

[2149] The server sends the question received from the user terminal to the artificial intelligence system.

[2150] Input: Question sent from user device

[2151] Output: A question request to the AI ​​system

[2152] Specific operation: The server converts the question into JSON format and sends it to the artificial intelligence system via an HTTP request.

[2153] Step 3:

[2154] An artificial intelligence system generates initial answers to questions.

[2155] Input: The question sent by the server

[2156] Output: Initial response (e.g. "Because the server load was high")

[2157] Specific operation: The artificial intelligence system uses a generative AI model to generate answers to questions using natural language processing techniques.

[2158] Step 4:

[2159] The server receives the response from the artificial intelligence system.

[2160] Input: Initial response sent by the artificial intelligence system

[2161] Output: Response received at server

[2162] Specific operation: The server receives the HTTP response, parses the JSON formatted answer and stores it in the database.

[2163] Step 5:

[2164] The server generates additional questions based on the answers it receives and sends them back to the artificial intelligence system.

[2165] Input: Initial response (e.g., "Because the server load was high")

[2166] Output: Follow-up questions (e.g., "Why was the server overloaded?") and their submission

[2167] Specific operation: The server generates additional questions and creates another HTTP request and sends it to the artificial intelligence system.

[2168] Step 6:

[2169] An artificial intelligence system generates answers to follow-up questions.

[2170] Input: Follow-up question (e.g., "Why was the server so busy?")

[2171] Output: Additional answer (e.g., "Because of poor resource management")

[2172] Specific operation: The artificial intelligence system again uses the generative AI model to generate answers to follow-up questions.

[2173] Step 7:

[2174] The server receives additional answers from the artificial intelligence system.

[2175] Input: Additional answers sent by the AI ​​system

[2176] Output: Additional answers received at the server

[2177] Specific operation: The server receives the HTTP response and stores the answer in a database.

[2178] Step 8:

[2179] This is repeated until the server repeatedly generates additional questions as needed and sends them to the artificial intelligence system.

[2180] Input: Multiple answers and questions

[2181] Output: Final root cause (e.g., "Poor resource management")

[2182] Specific behavior: The server iterates, exchanging additional questions and answers until a certain condition is met.

[2183] Step 9:

[2184] The server summarizes and visualizes the process and results.

[2185] Input: History of all questions and answers

[2186] Output: Summarized and visualized information (e.g., flowchart)

[2187] Specific operation: The server analyzes the information stored in the database and visualizes it as a flowchart or causal diagram.

[2188] Step 10:

[2189] The server transmits the summarized and visualized information to the user terminal and presents it to the user.

[2190] Input: Summarized and visualized information

[2191] Output: Display information on the user's terminal

[2192] Specific operation: The server sends the visualized information to the user's terminal as an HTTP response and displays it to the user.

[2193] Step 11:

[2194] The server analyzes the user's emotions and completes the questions and answers.

[2195] Input: User input and responses

[2196] Output: Question completion and response suggestions based on emotion data

[2197] Specific operation: The server analyzes the user's emotional data using emotion analysis means and reflects the data in questions and answers as necessary. It also generates and presents appropriate countermeasures according to the user's emotional state.

[2198] 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.

[2199] 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.

[2200] 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.

[2201] 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.

[2202] 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.

[2203] 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.

[2204] 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).

[2205] 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.

[2206] 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."

[2207] 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.

[2208] 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).

[2209] 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.

[2210] 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.

[2211] 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.

[2212] 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.

[2213] 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.

[2214] 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.

[2215] 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.

[2216] 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.

[2217] 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.

[2218] 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.

[2219] The following is further disclosed regarding the above embodiment.

[2220] (Claim 1)

[2221] a means for inputting a question from a user;

[2222] means for transmitting the input question to an artificial intelligence system;

[2223] means for receiving a response from the artificial intelligence system;

[2224] means for generating follow-up questions based on the received answers;

[2225] means for continually sending said follow-up questions to said artificial intelligence system;

[2226] means for determining a final answer from the artificial intelligence system;

[2227] A means of summarizing and visualizing the process and results;

[2228] and means for presenting the summarized and visualized information to a user.

[2229] (Claim 2)

[2230] 2. The system of claim 1, wherein the follow-up question is "Why?"

[2231] (Claim 3)

[2232] 2. The system of claim 1, wherein the visualization is performed in the form of a flowchart or a causal diagram.

[2233] "Example 1"

[2234] (Claim 1)

[2235] a means for inputting a question from a user;

[2236] means for transmitting the input question to a data processing device;

[2237] means for receiving a response from the data processing device;

[2238] means for generating follow-up questions based on the received answers;

[2239] means for continuing to send said follow-up queries to said data processing device;

[2240] means for determining a final response from said data processing device;

[2241] a means of summarizing and visualizing the process and results;

[2242] means for presenting the summarized and visualized information to a user;

[2243] a means of parsing each response and generating a follow-up question: "Why?"

[2244] A system that includes multiple answers and a means to visualize the causal relationships as a flowchart or causal diagram.

[2245] (Claim 2)

[2246] 2. The system of claim 1, wherein the follow-up question is "Why?"

[2247] (Claim 3)

[2248] The system of claim 1, wherein the visualization is performed in the form of a flowchart or a causal diagram.

[2249] "Application Example 1"

[2250] (Claim 1)

[2251] a means for inputting a question from a user;

[2252] means for transmitting the input question to an artificial intelligence system;

[2253] means for receiving a response from the artificial intelligence system;

[2254] means for generating follow-up questions based on the received answers;

[2255] means for continually sending said follow-up questions to said artificial intelligence system;

[2256] means for determining a final answer from the artificial intelligence system;

[2257] A means of summarizing and visualizing the process and results;

[2258] means for presenting the summarized and visualized information to a user;

[2259] Collect operational data from production equipment,

[2260] means for generating questions related to production efficiency and quality issues based on the operational data;

[2261] means for identifying root causes of said queries;

[2262] a means for visualizing the identified root cause and its related information;

[2263] A system including:

[2264] (Claim 2)

[2265] 2. The system of claim 1, wherein the follow-up question is "Why?"

[2266] (Claim 3)

[2267] 2. The system of claim 1, wherein the visualization is performed in the form of a flowchart or a causal diagram.

[2268] "Example 2: Combining Emotion Engines"

[2269] (Claim 1)

[2270] a means for inputting a question from a user;

[2271] means for transmitting the input question to an artificial intelligence system;

[2272] means for receiving a response from the artificial intelligence system;

[2273] means for generating follow-up questions based on the received answers and analyzing the user's emotions using emotion analysis means;

[2274] means for continually sending said follow-up questions to said artificial intelligence system;

[2275] means for determining a final answer from the artificial intelligence system;

[2276] A method to summarize the process and results and visualize them based on the results of sentiment analysis.

[2277] and means for presenting the summarized and visualized information to a user.

[2278] (Claim 2)

[2279] 2. The system of claim 1, wherein the follow-up question is "Why?"

[2280] (Claim 3)

[2281] 2. The system of claim 1, wherein the visualization is performed in the form of a flowchart or a causal diagram.

[2282] "Application example 2 when combining emotion engines"

[2283] (Claim 1)

[2284] a means for inputting a question from a user;

[2285] means for transmitting the input question to an artificial intelligence system;

[2286] means for receiving a response from the artificial intelligence system;

[2287] means for generating follow-up questions based on the received answers;

[2288] means for continually sending said follow-up questions to said artificial intelligence system;

[2289] means for determining a final answer from the artificial intelligence system;

[2290] A means of summarizing and visualizing the process and result...

Claims

1. a means for inputting a question from a user; means for transmitting the input question to an artificial intelligence system; means for receiving a response from the artificial intelligence system; means for generating follow-up questions based on the received answers; means for continually sending said follow-up questions to said artificial intelligence system; means for determining a final answer from the artificial intelligence system; A means of summarizing and visualizing the process and results; and means for presenting the summarized and visualized information to a user.

2. 2. The system of claim 1, wherein the follow-up question is "Why?"

3. The system of claim 1 , wherein the visualization is performed in the form of a flowchart or a causal diagram.

Images