System

Abstract

A system is provided.SOLUTION: A system including means for collecting a past work procedure manual and a past trouble report from a database, means for analyzing the collected data and specifying a pattern and a cause of a trouble, means for causing a generation model to learn analysis data, means for receiving a work procedure manual being created as an input, means for analyzing the input procedure manual and predicting a trouble occurrence risk, means for correcting the procedure manual to a procedure with a low trouble occurrence risk on the basis of a prediction result, and means for presenting the corrected procedure manual, a preliminary measure, and a recovery procedure to a user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] When building or maintaining a system, it is difficult to evaluate the current operational risks by taking into account all past trouble cases and know-how. As a result, there is a risk of similar troubles occurring repeatedly, making it difficult to carry out the work safely and efficiently. To solve this problem, a system is needed that can learn trouble patterns and causes from huge amounts of past data, and automate the creation of procedure manuals with low risk of trouble occurring and the proposal of rapid recovery procedures. [Means for solving the problem]

[0005] The present invention is a system that collects past work procedures and trouble reports from a database, analyzes the collected data, and identifies trouble patterns and causes. It also includes a means for training a generative model on the analysis data, receiving work procedures currently being created as input, and predicting the risk of trouble. Based on the prediction results, the system modifies procedures to reduce the risk of trouble, and presents the modified procedures, preventative measures, and recovery procedures to the user, allowing engineers to work safely and efficiently. Furthermore, by providing a means for generating preventative measures and rapid recovery procedures for procedures predicted to have a high risk of trouble, the impact of trouble when it occurs can be minimized.

[0006] A "work procedure manual" is a document that describes the specific steps and procedures to be followed when building or maintaining a system.

[0007] A "trouble report" is a document that records details, causes, and countermeasures for system failures and problems that have occurred in the past.

[0008] A "database" is an information system for efficiently storing, managing, and searching large amounts of data.

[0009] A "generative model" refers to a machine learning algorithm or AI technique used to analyze data and make predictions.

[0010] "Risk of trouble occurring" is an assessment of the degree of possibility that a system failure or problem will occur in a specific work procedure.

[0011] "Proactive measures" refer to preventive and mitigation measures that should be taken in advance to deal with anticipated problems.

[0012] A "recovery procedure" is a document that describes specific steps and techniques for quickly returning a system to its original, stable state in the event of a problem.

[0013] "Users" refers to the engineers and administrators who use this system.

[0014] "Analysis" is the process of examining collected data in detail to identify patterns and causes.

[0015] "Presenting" refers to showing the user revised procedures, forecast information, countermeasures, etc. [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] The present invention is a system for safely and efficiently implementing system construction and maintenance work by utilizing past trouble reports and work procedure manuals. This system is realized by the following program processing.

[0038] First, the server connects to the database and collects past trouble reports and work procedures. This allows the system to collect past trouble cases and know-how, and obtain data for analyzing trouble patterns and causes.

[0039] The server then analyzes the collected data. This analysis involves identifying patterns in the collected data and identifying the causes of problems and solutions. Based on these analysis results, a generative model is trained on the data. This generative model uses a machine learning algorithm to predict future problems based on past data.

[0040] The user inputs the work procedure manual currently being created from the terminal into the server. The server analyzes the input procedure manual and predicts the risk of trouble occurring. Based on the predicted risk, the server automatically modifies the procedure to reduce the risk of trouble occurring. The modified procedure manual is sent to the terminal and presented to the user.

[0041] Furthermore, the server generates preventative measures to address the predicted risk of trouble occurring. These preventative measures are provided as specific measures to prevent trouble before it occurs. Rapid recovery procedures are also generated in the event of trouble occurring. This allows users to respond quickly when trouble occurs and return the system to its original stable state.

[0042] For example, suppose a user inputs a configuration procedure when configuring a new network. The server predicts risks based on past examples of network failures caused by incorrect firewall configurations, and adds a procedure for immediate testing after changing the configuration. In this way, a correction procedure is generated that reduces the risk of problems occurring.

[0043] Finally, the server sends the revised procedure manual and the generated preventive measures and recovery procedures to the terminal and presents them to the user. The user can then confirm the presented procedure manual and measures and carry out the work safely and efficiently.

[0044] As described above, the present invention provides a specific embodiment for utilizing past trouble data to safely and efficiently implement system construction and maintenance work.

[0045] The processing flow will be explained below.

[0046] Step 1:

[0047] The server connects to the database and collects past trouble reports and work procedures. Specifically, it extracts the latest data from the database using an SQL query and temporarily stores it in memory.

[0048] Step 2:

[0049] The server preprocesses the collected data, which includes extracting the necessary information (cause of the problem, countermeasures, and procedure) and converting it into text format. The preprocessed data is then passed to the analysis module.

[0050] Step 3:

[0051] The server uses an analysis module to identify patterns and causes of problems from the pre-processed data, which involves clustering the data using natural language processing techniques to extract commonalities and patterns of problems.

[0052] Step 4:

[0053] The server trains the generative model on the analysis data, using a machine learning algorithm to learn past trouble patterns and countermeasures, thereby improving prediction accuracy.

[0054] Step 5:

[0055] The user uploads the work procedure manual currently being created from the terminal to the server. The procedure manual is usually sent in text file format.

[0056] Step 6:

[0057] The server analyzes the received procedure manual and compares it with past trouble data, thereby predicting the risk of trouble occurring for the input procedure manual.

[0058] Step 7:

[0059] Based on the predicted risk of trouble occurring, the server makes low-risk modifications to the procedure manual, such as adding or modifying procedures or inserting cautionary notes.

[0060] Step 8:

[0061] The server generates a revised procedure manual and adds preventative measures and recovery procedures. Preventative measures include steps to prevent problems from occurring, and recovery procedures include instructions on how to respond if a problem does occur.

[0062] Step 9:

[0063] The server then sends the corrected procedure manual and the generated preventive measures and recovery procedures to the terminal. The procedure manual is often sent in PDF or text file format.

[0064] Step 10:

[0065] The user checks the procedure manual and countermeasures displayed on the terminal, performs the work based on them, corrects the procedure manual as necessary, and performs a final check.

[0066] The above are the specific processing steps of the program in the system of the present invention, which allows engineers to safely and securely perform system construction and maintenance work.

[0067] Example 1

[0068] 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."

[0069] In modern system construction and maintenance work, past trouble cases and work procedures are not fully utilized, resulting in the recurrence of similar problems. Furthermore, insufficient preventive measures and prompt response measures when a problem occurs can compromise the stability of the system. This leads to reduced work efficiency and ultimately to increased operational costs.

[0070] 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.

[0071] In this invention, the server includes means for collecting past work procedures and trouble reports from a database, means for analyzing the collected data and identifying trouble patterns and causes, and means for training a generative model using the analyzed data. This makes it possible to effectively use past trouble data to automatically predict trouble and take measures against it.

[0072] "Past work procedures" are documents that record procedures previously used for system construction and maintenance work.

[0073] A "trouble report" is a report that details problems or failures that occur during system operation.

[0074] A "database" is a system for efficiently storing, managing, and searching data.

[0075] "Means of collection" refers to the methods and techniques used to retrieve historical data and documents from a database.

[0076] "Analytical means" refers to the methods and techniques used to analyze collected data and identify patterns and causes.

[0077] A "generative model" is a machine learning model that generates new data and information based on collected and analyzed data.

[0078] A "work procedure manual in preparation" is a document that records the procedures for system construction and maintenance work currently in progress.

[0079] "Means for receiving input" refers to the method or technique by which the user inputs the work procedure manual being created into the system.

[0080] "Predictive methods" refer to techniques for assessing the likelihood of problems occurring in current work procedures based on past data.

[0081] "Means of correction" refers to methods and techniques for automatically changing the contents of work procedures to reduce the risk of problems occurring.

[0082] "Presentation means" refers to the method or technique for displaying revised procedures and countermeasures to the user.

[0083] A "database management system" is a software system for storing, managing, and manipulating data.

[0084] A "programming language" is a language for writing instructions for data analysis and processing.

[0085] "Natural language generation technology" refers to technology that enables computers to understand and generate natural human language.

[0086] "Means for automatically generating countermeasures" refers to technology that enables a system to automatically generate appropriate countermeasures for problems.

[0087] The present invention provides a system for safely and efficiently implementing system construction and maintenance work using past trouble reports and work procedure manuals. This system utilizes multiple hardware and software components to collect, analyze, predict, and correct data. Specific embodiments for implementing this system are described below.

[0088] First, the server uses a database management system (DBMS) such as MySQL (registered trademark) or PostgreSQL to collect past work procedures and trouble reports. Specifically, it connects to the database using a MySQL driver and executes SQL queries to obtain the necessary data. The obtained data is then stored in internal memory.

[0089] The server then analyzes the collected data using Python's Pandas library. Data cleansing is performed to extract characteristics of past trouble cases. Furthermore, machine learning algorithms using SciKit-Learn (such as K-Means clustering and Naive Bayes) are used to identify the cause of the trouble and countermeasures. The results of this analysis are input into a generative AI model, forming the basis for new trouble predictions.

[0090] Next, the user enters the work instructions from their device using a dedicated web form via a browser. This web form has the function of sending the entered instructions to the server in JSON format. The server parses the received data and tokenizes and analyzes the content using text analysis tools (NLTK or SpaCy). Furthermore, a generative AI model is used to evaluate the risk of problems occurring for each step.

[0091] The server automatically modifies the operating procedures based on the predicted risks. This process uses natural language generation technology (e.g., the GPT-3 (registered trademark) API). The modified operating procedures include additional checkpoints and test procedures. The modified operating procedures are again sent to the terminal in JSON format and presented to the user. At this point, the user can review the improved operating procedures to ensure the safe and efficient operation of the system.

[0092] Furthermore, based on the risk information obtained from the predictive model, the server automatically generates preventative measures for procedures with a high risk of trouble and rapid recovery procedures in the event of a problem. This is done using automation tools such as Jenkins and Ansible. The generated measures and recovery procedures are then sent back to the terminal and presented to the user, enabling a rapid response when a problem occurs.

[0093] As a concrete example, suppose a user is configuring a new network and enters the following configuration instructions:

[0094] The new network configuration procedure is shown below. Predict the risks and generate a correction procedure that includes the necessary countermeasures.

[0095] The server predicts risks based on past examples of network failures caused by incorrect firewall configurations, and adds a procedure for immediate testing after configuration changes are made. As a result, a correction procedure manual that reduces the risk of problems occurring is generated and provided to the user.

[0096] As described above, the present invention provides a specific embodiment for effectively utilizing past trouble data and for safely and efficiently implementing system construction and maintenance work.

[0097] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0098] Step 1:

[0099] The server connects to the database and collects past work procedures and trouble reports. Specifically, it connects to the database using a MySQL driver and executes SQL queries to retrieve data.

[0100] Input: MySQL database connection information and query

[0101] Data processing: Extract data from the database using SQL queries and store it in the internal memory

[0102] Output: Collected past work procedures and trouble reports

[0103] Step 2:

[0104] The server analyzes the collected data, converts it into DataFrame format using Python's Pandas library, and performs data cleansing. It then uses machine learning algorithms (such as K-Means clustering and Naive Bayes) to identify the cause of the problem and how to resolve it.

[0105] Input: Collected past work procedures and trouble reports

[0106] Data processing: Data tokenization, cleaning, and feature extraction

[0107] Data calculation: Identifying causes of problems and solutions using machine learning algorithms

[0108] Output: Analysis results regarding causes of problems and countermeasures

[0109] Step 3:

[0110] The user inputs the current work procedure from the terminal using a web form via the browser, and the input is sent to the server in JSON format.

[0111] Input: Work procedure text

[0112] Data processing: Converting to JSON format and sending to the server

[0113] Output: Result of sending work procedure data to the server

[0114] Step 4:

[0115] The server analyzes the input instructions and predicts the risk of trouble. It uses a text analysis tool (such as NLTK or SpaCy) to tokenize the contents of the prompt and calculate a risk score for each step.

[0116] Input: Work instructions sent by the user (JSON format)

[0117] Data processing: Text tokenization and analysis

[0118] Data Computing: Predicting the Risk of Problems Using Generative AI Models

[0119] Output: Risk score for trouble occurrence for each step

[0120] Step 5:

[0121] The server automatically modifies the procedure manual based on the predicted risks. It uses natural language generation technology (e.g., GPT-3 API) to create improvement suggestions and reflect them in the procedure manual.

[0122] Input: Predicted results of risk of trouble occurring

[0123] Data processing: Correcting instructions using natural language generation algorithms

[0124] Output: Revised work instructions

[0125] Step 6:

[0126] The server sends the revised procedure manual in JSON format to the terminal and presents it to the user.

[0127] Input: Modified work procedure

[0128] Data processing: Converting to JSON format and sending to the device

[0129] Output: The revised work procedure presented to the user

[0130] Step 7:

[0131] Based on the risk information obtained from the predictive model, the server generates preventative measures and rapid recovery procedures for procedures with a high risk of causing problems, using automation tools such as Jenkins and Ansible.

[0132] Input: Procedure information with high risk of trouble

[0133] Data Transformation: Generating and automating countermeasures and recovery procedures

[0134] Output: Generated proactive and rapid recovery procedures

[0135] Through these steps, this system effectively utilizes past data and enables safe and efficient system construction and maintenance work.

[0136] (Application example 1)

[0137] 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."

[0138] When performing maintenance work on automation systems in factories or creating new setup procedures, it is necessary to utilize past trouble data to reduce the risk of problems occurring and improve work efficiency. However, it is difficult for workers to refer to past data in real time and obtain appropriate procedures and countermeasures. This makes problems more likely to occur and makes it difficult to respond quickly. Furthermore, there is a lack of means to provide specific real-time procedure improvements and proactive measures for dealing with factory automation equipment.

[0139] 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.

[0140] In this invention, the server includes a means for collecting past work procedures and trouble reports from a database, a means for analyzing the collected data and identifying trouble patterns and causes, and a means for training a generative model using the analyzed data. This makes it possible to suggest improvements to procedures and preventative measures in real time while work is in progress. It also makes it possible to provide workers with preventative measures for procedures predicted to have a high risk of trouble, as well as quick recovery procedures in the event of a trouble, in real time using their smart devices. This reduces the risk of trouble and enables quick and accurate responses when performing maintenance work on factory automation systems or setting up new procedures.

[0141] "Past work procedures" are documents that describe the procedures for work that was previously performed.

[0142] A "trouble report" is a document that details past problems and how they were dealt with.

[0143] A "database" is a system for efficiently storing, managing, and retrieving structured data.

[0144] "Collection means" refers to the methods or processes that effectively retrieve the required information from the database.

[0145] "Analytical means" refers to the methods and processes used to analyze collected data in detail and reveal its meaning and patterns.

[0146] "Trouble patterns" refer to common characteristics and trends found in past cases of problems occurring.

[0147] A "cause determination method" is a method or process for finding the root cause of a problem that has occurred.

[0148] A "generative model training method" is a method or process for inputting analytical data into a machine learning algorithm to train the model.

[0149] "Work procedure manual in preparation" means the latest document that describes the procedures for work currently in progress.

[0150] "Problem occurrence risk" refers to the degree to which a particular procedure or action is likely to cause a problem.

[0151] "Risk prediction means" refers to a method or process for estimating the likelihood of a problem occurring based on collected and analyzed data.

[0152] A "procedural modification" is a method or process for changing work procedures to avoid a predicted problem.

[0153] A "modified procedure" is a documented work procedure that has been improved to reduce risk.

[0154] "Proactive measures" refer to specific preventative measures that can be taken before a problem occurs.

[0155] "Recovery procedures" are documents that describe the steps to quickly return to normal operation when a problem occurs.

[0156] "Factory automation equipment" refers to devices and systems that operate automatically in production sites to improve work efficiency.

[0157] "Means for proposing improvements and proactive measures in real time" refers to methods and processes for reviewing procedures and providing safety measures immediately during work.

[0158] A "smart device" is a portable electronic device that can display information, connect to the Internet, and run applications.

[0159] "Workers" refers to people who do the actual work in a factory.

[0160] The present invention aims to improve the safety and efficiency of work procedures in a factory automation system. The system configuration required to implement the present invention is as follows.

[0161] First, the server collects past work procedures and trouble reports from a database. The collected data is disorganized and needs to be analyzed. The server analyzes the collected data to identify patterns and causes of trouble. This analysis step uses data mining tools and machine learning algorithms.

[0162] Based on the analysis results, the server trains the generative AI model on the data. This makes it possible to predict future problems from past data. To train the generative AI model, a machine learning library using Python (such as scikit-learn or TENSORFLOW (registered trademark)) is used.

[0163] The user inputs the work procedure manual they are currently creating into the server from a device (smartphone, tablet, smart glasses, etc.). The server analyzes the input procedure manual and predicts the risk of trouble occurring. To do this, it uses a generative AI model to evaluate the procedure in real time and calculate the predicted risk.

[0164] Based on the prediction results, the server automatically modifies procedures to reduce the risk of problems occurring. The modified procedures are then sent to the terminal along with the details of the modifications. The user can then check the modified procedures, preventative measures, and recovery procedures via the terminal.

[0165] Furthermore, the server generates specific preventative measures for procedures that are predicted to have a high risk of causing trouble, and also generates rapid recovery procedures in the event of a problem, allowing users to take appropriate action immediately.

[0166] For example, if a user inputs a procedure for network configuration, the server will automatically correct the procedure to the optimum one by referring to past examples of problems that have occurred with firewall configuration. It will also make corrections to reduce risks by adding appropriate initialization procedures, etc.

[0167] Examples of specific examples and prompts

[0168] As a specific example, the smart glasses used are a general smart device (e.g., Google® Glass® Enterprise Edition 2), and the tablet is a general high-performance tablet (e.g., iPad® Pro).

[0169] Example prompt sentence:

[0170] Based on past reports of firewall configuration problems, please predict the risks of this new configuration manual and make corrections to proceed safely.

[0171] Configuration parameters:

[0172] setting_1 = 192.168.1.1

[0173] setting_2 = allow_all_ports

[0174] setting_3 = enable_logging

[0175] Output instructions:

[0176] Adding an initialization procedure

[0177] Detailed Port Configuration Verification Steps

[0178] Configuring Log Monitoring

[0179] In this way, the present invention realizes the provision of safe and efficient procedure manuals and proactive measures in real time for maintenance work and new setup procedures for factory automation systems.

[0180] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0181] Step 1:

[0182] The server collects past work instructions and trouble reports from a database. The input to this process is the work instructions and trouble reports retrieved from the database, and the output is an aggregated set of these data. Specifically, the server establishes a database connection and uses SQL queries to retrieve the required data.

[0183] Step 2:

[0184] The server analyzes the collected data and identifies patterns and causes of problems. The input to this process is the data collected in step 1, and the output is a list of identified patterns and causes of problems. Specifically, the server analyzes the data using a data mining tool (for example, Python's pandas or numpy) to extract common patterns and causes.

[0185] Step 3:

[0186] The server trains the generative AI model on the analysis data. The input to this process is the data identified in step 2, and the output is a trained generative AI model. Specifically, the server trains the generative AI model using a machine learning library (e.g., scikit-learn or TensorFlow).

[0187] Step 4:

[0188] The user inputs the work procedure manual currently being created from the terminal to the server. The input in this process is the procedure manual entered by the user into the terminal, and the output is the procedure manual received by the server. In concrete terms, the user inputs the procedure manual on the terminal and sends it to the server via the network.

[0189] Step 5:

[0190] The server analyzes the input procedure manual and predicts the risk of trouble occurring. The input for this process is the procedure manual received in step 4 and the AI ​​model trained in step 3, and the output is the evaluation result of the predicted risk of trouble occurring. Specifically, the AI ​​model is used to evaluate the risk of each step in the procedure manual and calculate the risk level in numerical and graphical form.

[0191] Step 6:

[0192] Based on the prediction results, the server modifies the procedure to reduce the risk of trouble. The input to this process is the risk assessment result obtained in step 5, and the output is a modified procedure manual. Specifically, it identifies high-risk steps and restructures the procedure while incorporating safety measures.

[0193] Step 7:

[0194] The server sends the revised procedure manual and the preventive measures and recovery procedures to the terminal and presents them to the user. The input in this process is the procedure manual revised in step 6, and the output is the revised procedure manual and the preventive measures and recovery procedures displayed on the terminal. Specifically, the server formalizes the revised procedure manual, sends it to the terminal over the network, and displays it so that the user can check it.

[0195] Step 8:

[0196] The user checks the revised procedure manual, preventive measures, and recovery procedures through the terminal and carries out the work in accordance with their contents. The input in this process is the information presented on the terminal in step 7, and the output is the user completing the work safely and efficiently. In concrete terms, the user performs the work on site based on the information presented on the terminal.

[0197] 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.

[0198] This invention is a system for safely and efficiently implementing system construction and maintenance work by utilizing past trouble reports and work procedure manuals, and further optimizing the user's work environment by combining it with an emotion engine that recognizes the user's emotions. This system is realized by the following specific program processing.

[0199] First, the server connects to the database and collects past trouble reports and work procedures. This allows the system to collect past trouble cases and know-how, and obtain data for analyzing trouble patterns and causes.

[0200] The server then preprocesses the collected data. Specifically, it extracts the necessary information (cause of the problem, countermeasures, and procedure) into text format and passes it to the analysis module. The analysis module then uses natural language processing technology to cluster the data and identify commonalities and patterns in the problems.

[0201] The server then trains the generative model with these analysis results. The generative model uses machine learning algorithms to learn past trouble patterns and countermeasures, and uses this information to predict future troubles.

[0202] When a user uploads a work procedure manual they are currently creating from their device to the server, the server analyzes the manual and compares it with past trouble data to predict the risk of trouble occurring. Based on the predicted risks, the server automatically modifies the manual to reduce the risk. The modified manual, along with preventive measures and recovery procedures, is sent to the device and presented to the user.

[0203] Furthermore, the present invention incorporates an emotion engine, which allows the server to recognize the user's emotions. The emotion engine analyzes the user's voice, facial expression, or biometric data to assess the user's emotional state. For example, the server can detect stress or anxiety from the user's facial recognition data or voice tone.

[0204] When the emotion engine recognizes the user's emotions, the server adjusts the way instructions are presented to them based on the user's emotional state. For example, if the user is feeling stressed, instructions may be presented step-by-step or in a visually easy-to-understand format. The emotion engine also provides advice to reduce the user's stress and anxiety. Specifically, practical advice such as "take a deep breath" and "take a short break" are presented.

[0205] Furthermore, the system automatically generates preventative measures for procedures predicted to have a high risk of causing problems, as well as quick recovery procedures in the event of a problem. This allows users to make preparations in advance to minimize the impact of a problem, and to immediately use procedures for rapid response in the event of a problem.

[0206] For example, suppose a user inputs configuration instructions when configuring a new network. The server predicts risks based on past examples of network failures caused by incorrect firewall configurations and adds a procedure for immediate testing after the configuration change. In this way, a correction procedure is generated that reduces the risk of problems occurring. Furthermore, if the emotion engine detects the user's anxiety, it will provide detailed explanations and additional visual guides.

[0207] Finally, the server sends the revised procedure manual and the generated preventive measures and recovery procedures to the terminal and presents them to the user. The user can check the presented procedure manual and measures and work in the optimal environment according to their emotional state.

[0208] The above is the specific processing content of the program in the system of the present invention. This system allows engineers to build and maintain systems in a safe, secure, and stress-free environment.

[0209] The processing flow will be explained below.

[0210] Step 1:

[0211] The server connects to the database and gathers past trouble reports and work instructions using SQL queries. For example, it runs the following query:

[0212] sql

[0213] SELECT FROM trouble_reports WHERE date >= '2021-01-01';

[0214] SELECT FROM procedures WHERE date >= '2021-01-01';

[0215] The collected data is temporarily stored in memory.

[0216] Step 2:

[0217] The server preprocesses the collected data. Specifically, it extracts the cause of the problem, countermeasures, and procedures, converts them into text format, such as JSON format data, and passes them to the analysis module.

[0218] Step 3:

[0219] The server then uses an analysis module to analyze the preprocessed data. This analysis uses natural language processing technology to cluster the data and extract commonalities and patterns among the problems. For example, it divides the data into patterns that are easy to classify based on past cases of problems.

[0220] Step 4:

[0221] The server trains the generative model with the analysis results. Using a machine learning algorithm, past trouble patterns and countermeasures are input into the model, improving prediction accuracy.

[0222] Step 5:

[0223] The user uploads the work procedure manual they are currently creating from their terminal to the server. The procedure manual is usually sent in text file format.

[0224] Step 6:

[0225] The server analyzes the uploaded procedure manual and compares it with past trouble data, calculates the degree of agreement with the past data, and predicts the risk of trouble occurring.

[0226] Step 7:

[0227] Based on the predicted risk of trouble occurring, the server automatically modifies the procedure manual to reduce the risk, for example by adding operation steps, changing the order of steps, or inserting cautionary notes.

[0228] Step 8:

[0229] The server generates a revised procedure manual and adds preventive measures and recovery procedures. The preventive measures include specific measures to prevent problems from occurring, and the recovery procedures include how to respond after a problem occurs.

[0230] Step 9:

[0231] The server then sends the corrected procedure manual and the generated preventive measures and recovery procedures to the terminal, often in PDF or text format.

[0232] Step 10:

[0233] The user checks the procedure manual and countermeasures displayed on the device, revises the procedure manual as necessary, and performs a final check. At this time, the emotion engine analyzes the user's emotions and presents appropriate advice.

[0234] Step 11:

[0235] The server uses an emotion engine to analyze the user's voice and facial expressions to determine the user's emotional state. For example, if the user's voice gets louder, it may sense stress.

[0236] Step 12:

[0237] The server adjusts how instructions are presented based on the user's emotional state: if the user is feeling anxious, it presents the instructions step-by-step and adds visual guides.

[0238] Step 13:

[0239] The server provides appropriate advice until the user's emotions stabilize, such as practical instructions like "take a deep breath" or "take a break."

[0240] The above are the specific processing steps of the program in the system of the present invention. This system allows engineers to build and maintain systems in a safe, secure, and stress-free environment.

[0241] Example 2

[0242] 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."

[0243] There is a need to effectively utilize past trouble reports and work procedures to minimize the risk of trouble occurring during system construction and maintenance work. However, this data exists in large quantities, and analyzing and utilizing it is an extremely complex and time-consuming task. Furthermore, there is insufficient support for optimizing the work environment according to the user's emotional state. A method is needed to solve these problems and perform system construction and maintenance work safely and efficiently.

[0244] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0245] In this invention, the server includes means for collecting past work procedures and trouble reports from a database, means for preprocessing the collected data and identifying trouble patterns and causes, means for training the preprocessed data into a generative model, means for receiving work procedures being created as input, means for analyzing the input procedures and predicting the risk of trouble, means for modifying the procedures to have a lower risk of trouble based on the prediction results, means for presenting the modified procedures, preventative measures, and recovery procedures to the user, means for recognizing the user's emotions and adjusting the presentation method of the procedures depending on the user's emotional state, and means for presenting advice to alleviate the emotions. This makes it possible to perform system construction and maintenance work in an optimal work environment that suits the user's emotional state while reducing the risk of trouble.

[0246] A "database" is a system for managing structured collections of data, allowing for efficient data storage, retrieval, and management.

[0247] A "procedure" is a document that details instructions for performing a specific task or operation.

[0248] A "trouble report" is a document that records the details of problems or troubles that have occurred in a system or process and the countermeasures taken.

[0249] "Preprocessing" is the process of shaping raw data into an analyzable format, and includes removing unnecessary data and extracting necessary data.

[0250] A "generative model" is a mathematical model that uses machine learning algorithms to analyze data and make new predictions or generate new ideas.

[0251] A "work procedure manual" is a document that details the steps required to perform a specific job and is used by employees and technicians to ensure the job is performed correctly.

[0252] "Risk of trouble occurring" indicates the degree of possibility that trouble will occur when a specific operation or procedure is performed.

[0253] "User" refers to a person who uses this system to create work procedures and execute the modified procedures.

[0254] An "emotion engine" is a system that analyzes a user's voice, facial expression, biometric data, etc. to evaluate their emotional state.

[0255] "Advice" is instruction or guidance that suggests what action to take or how to improve a particular situation.

[0256] This invention is a system for safely and efficiently implementing system construction and maintenance work by utilizing past trouble reports and work procedure manuals. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it optimizes the user's work environment. This system is realized by the following specific program processing.

[0257] First, the server connects to the database and collects past trouble reports and work procedures. This collection is done using an SQL database, for example by executing a query such as "SELECT FROM TroubleReports." The data is temporarily stored in memory. The hardware used is a high-performance database server, and the software used is Apache (registered trademark) Kafka, Hadoop, and the Python Pandas library.

[0258] Next, the server preprocesses the collected data. First, unnecessary data is removed, and necessary information (cause of the problem, countermeasures, and procedure details) is extracted in text format. This preprocessing is performed using natural language processing tools such as NLTK and SpaCy. For example, information about past firewall configuration errors is extracted and recorded in text format. The data obtained in this way is passed to the analysis module.

[0259] The server trains a generative model based on the clustering results obtained by the analysis module. Machine learning algorithms such as TensorFlow and PyTorch are used for the generative model. For example, the server uses data on the causes of past network outages to train the model to identify patterns in which outages occur.

[0260] When a user uploads a work procedure manual they are currently creating from their device to the server, the server analyzes the manual and compares it with past trouble data. This analysis is performed using Celery and Flask, which perform reentrant asynchronous task processing.

[0261] Based on the analysis results, the server predicts the risk of trouble occurring. If a high risk is predicted, the procedure manual is automatically revised. For example, if there is a problem with the configuration procedure, additional confirmation and testing procedures are inserted. Specifically, a procedure to "perform immediate testing after changing the firewall configuration" is added.

[0262] Furthermore, the server uses an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's voice, facial expressions, and biometric data. This analysis uses OpenCV, DeepFaceLab, and NLTK. For example, the server can analyze the user's facial expressions via a webcam to detect stress or anxiety.

[0263] This allows the server to adjust how instructions are presented. If the user is feeling stressed, the instructions may be presented step-by-step or in a more visually understandable format. The emotion engine also offers advice to reduce the user's stress, such as "take a deep breath" or "take a short break."

[0264] Finally, the server sends the revised procedure manual and the generated preventive measures and recovery procedures to the terminal and presents them to the user. The user can then check the presented procedure manual and measures and work in the optimal environment.

[0265] An example of a specific prompt to use when configuring a new network is:

[0266] "Please predict the risks that may arise after changing the firewall settings in the new network configuration and provide steps to mitigate those risks."

[0267] The above is a specific embodiment of the present invention. This system allows engineers to build and maintain systems in a safe, secure, and stress-free environment.

[0268] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0269] Step 1:

[0270] The server connects to the database and collects past trouble reports and work procedures. Specifically, it retrieves the data using an SQL query (e.g., "SELECT FROM TroubleReports").

[0271] Input: SQL database connection information

[0272] Output: Raw data for trouble reports and work procedures

[0273] Data processing: The raw data is temporarily stored in memory.

[0274] Step 2:

[0275] The server preprocesses the collected data, removing unnecessary data and extracting the cause of the problem, countermeasures, and procedures. It then converts the data into text format using NLTK or SpaCy.

[0276] Input: Raw data from collected trouble reports and work procedures

[0277] Output: Preprocessed text data

[0278] Data processing: Extract the necessary information using natural language processing techniques.

[0279] Step 3:

[0280] The server passes the preprocessed data to the analysis module, which performs clustering and uses machine learning algorithms to identify commonalities and patterns of problems.

[0281] Input: Preprocessed text data

[0282] Output: Clustered analysis results

[0283] Data Calculation: Group the data using a clustering algorithm.

[0284] Step 4:

[0285] The server trains a generative model using the analysis results. A generative model is created using TensorFlow or PyTorch, and the model is trained using the analysis results.

[0286] Input: Clustered analysis results

[0287] Output: Generative model parameters

[0288] Data calculation: Optimize the parameters of the machine learning model based on the analysis results.

[0289] Step 5:

[0290] The user uploads the work procedure manual they are currently creating from their device to the server, which receives the manual and analyzes its contents.

[0291] Input: User-created work instructions

[0292] Output: Analysis data

[0293] Data calculation: Analyzes the text of the uploaded procedure manual and extracts its contents.

[0294] Step 6:

[0295] The server predicts the risk of trouble based on the analysis data, compares it with past data, and automatically modifies the procedure manual if the risk is high.

[0296] Input: Analysis data and generative model

[0297] Output: Revised instructions

[0298] Data calculations: Risk prediction algorithms are used to assess the risk of procedures and make modifications to reduce the risk.

[0299] Step 7:

[0300] The server uses an emotion engine to recognize the user's emotions. It analyzes data acquired through the webcam and microphone and evaluates the user's emotional state.

[0301] Input: User's voice, facial expression, biometric data

[0302] Output: Emotion evaluation result

[0303] Data processing: Analyze audio and video data to quantify emotional states.

[0304] Step 8:

[0305] The server adjusts the way it presents instructions based on the emotion evaluation results. If the user is feeling stressed, it will adapt by presenting instructions step by step. It also provides advice on how to reduce stress.

[0306] Input: Emotion evaluation results and revised instructions

[0307] Output: User-adapted procedure presentation and advice

[0308] Action: Adjust presentation and provide advice based on emotional assessment.

[0309] Step 9:

[0310] The server then sends the final revised procedure manual and the generated preventive measures and recovery procedures to the terminal and presents them to the user, who can then check the presented procedure manual and measures and work in the optimal environment.

[0311] Input: Modified procedure and generated countermeasures

[0312] Output: Procedures and countermeasures displayed on the terminal

[0313] Operation: Corrective procedures and countermeasures are sent to the device and displayed to the user.

[0314] (Application example 2)

[0315] 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."

[0316] When maintaining and troubleshooting factory robots, it is necessary to effectively utilize past work procedures and trouble reports to perform the work efficiently and safely. It is also important to reduce the stress and anxiety of maintenance personnel and optimize the work environment.

[0317] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0318] In this invention, the server includes means for collecting past work procedures and trouble reports from a database, means for analyzing the collected data and identifying trouble patterns and causes, means for training a generative model based on the analyzed data, means for receiving work procedures being created as input, means for analyzing the input procedures and predicting the risk of trouble, means for evaluating the emotional state using an emotion engine that recognizes the user's emotions, means for adjusting the presentation method of the procedure based on the emotional state, means for modifying the procedure to one with a lower risk of trouble based on the prediction result, and means for presenting the modified procedure, preventative measures, and recovery procedures to the user. This makes it possible to efficiently and safely perform maintenance and troubleshooting of factory robots, reduce stress and anxiety for maintenance personnel, and provide an optimal work environment.

[0319] A "past work procedure manual" is a document that describes specific work content and procedures that have been performed in the past.

[0320] A "trouble report" is a document that describes problems and troubles that have occurred in the past and how they were dealt with.

[0321] A "database" is a system for systematically storing and managing information such as past work procedures and trouble reports.

[0322] "Analysis" is the process of using natural language processing and machine learning techniques to identify characteristics and patterns in collected data.

[0323] A "generative model" is a model that uses machine learning algorithms to learn specific data patterns and make predictions or generate data for the future.

[0324] The "emotion engine" is a system that analyzes a user's voice, facial expressions, biometric data, etc. to evaluate their emotional state.

[0325] "Risk of trouble occurring" indicates the degree of possibility that trouble will occur due to a specific work procedure.

[0326] "Adjusting the way the instructions are presented" means providing instructions in a visually easy-to-understand format and with step-by-step explanations depending on the user's current emotional state.

[0327] "Proactive measures" are preventative measures and preparations that should be taken before a problem occurs.

[0328] "Recovery procedures" are procedures for quickly and appropriately resolving problems after a problem occurs.

[0329] A system for implementing this invention collects past work procedures and trouble reports from a database, analyzes the data, identifies trouble patterns and causes, and trains a generative model. It also receives work procedures currently being created, predicts the risk of trouble, and modifies the procedures based on that risk. It also evaluates the user's emotional state using an emotion engine that recognizes their emotions and adjusts the way the procedures are presented, thereby providing an efficient and safe work environment.

[0330] The system uses the following hardware and software:

[0331] Server: Connects to the database and collects and analyzes data. Specifically, PostgreSQL is used for database connection, and TensorFlow and NLTK are used for natural language processing and machine learning techniques. Machine learning algorithms including Gradient Boosting and Random Forests are applied to the generative model.

[0332] Terminal: Inputs and displays the work procedure manual. Maintenance personnel can check the procedure manual and any revised procedure manual through this terminal.

[0333] User: Refers to the maintenance personnel who perform tasks using this system.

[0334] Emotion Engine: Uses voice and facial recognition technology (such as EmotionRecognition software) to analyze the user's emotional state.

[0335] The specific data processing and calculation procedures are as follows.

[0336] 1. Data Collection:

[0337] The server collects past work procedures and trouble reports from the database by using specific SQL queries to extract the data.

[0338] 2. Data Preprocessing:

[0339] The server performs text analysis on the collected data to extract the required information by using natural language processing tools such as NLTK to tokenize the documents and extract meaningful tokens.

[0340] 3. Data Analysis and Clustering:

[0341] Machine learning algorithms and clustering techniques are used to analyze trouble data and identify patterns and causes of trouble.

[0342] 4. Generative model training:

[0343] A generative model is constructed based on past trouble data, and a machine learning algorithm is applied to predict trouble patterns.

[0344] 5. Emotion recognition and procedural adjustment:

[0345] To analyze the stress and anxiety users feel during maintenance work, the emotion engine uses voice and facial recognition data to assess their emotions. It uses EmotionRecognition software to analyze the user's emotional state in real time and adjusts the way the instructions are presented to them.

[0346] 6. Risk prediction and procedure revision:

[0347] The server analyzes the current work procedures and predicts the risk of problems occurring. Based on the predicted risks, the server automatically modifies the procedures to reduce the risks, and presents the modified procedures, preventative measures, and recovery procedures to the user via the terminal.

[0348] This system enables efficient and safe maintenance and troubleshooting of factory robots, reducing stress and anxiety for maintenance personnel and providing an optimal working environment.

[0349] Specific examples

[0350] For example, when a factory robot undergoes routine maintenance, the system operates as follows:

[0351] User: "Enter a new maintenance procedure."

[0352] Server: "Based on past trouble data, we have revised the following steps to reduce risk. Please take note of this."

[0353] Emotion Engine: "It looks like you're feeling a bit stressed. Take some slow, deep breaths and take a short break before proceeding."

[0354] In this way, the user can carry out maintenance work efficiently and with peace of mind.

[0355] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0356] Processing steps of the system that realizes the application example

[0357] Step 1:

[0358] The server connects to the database and collects past work procedures and trouble reports. Specifically, the server executes SQL queries to retrieve past trouble data and work procedures. The input data are the records in the database, and the output data is a list of work procedures and trouble reports.

[0359] Step 2:

[0360] The server preprocesses the collected data. Specifically, it uses natural language processing technology to extract the necessary information (cause of the problem, countermeasures, and procedure details). This converts the data into a format suitable for analysis. The input data is the raw data collected in step 1, and the output data is tokenized text data.

[0361] Step 3:

[0362] The server analyzes the preprocessed data and identifies patterns and causes of problems. The server uses clustering techniques (e.g., KMeans) to group the data and discover common patterns. The input data is tokenized text data, and the output data is the problem patterns within each cluster.

[0363] Step 4:

[0364] The server trains a generative model based on the analyzed data. Specifically, it uses a machine learning algorithm (e.g., Gradient Boosting or Random Forests) to train the model based on past trouble patterns. The input data is the analyzed trouble patterns, and the output data is the trained generative model.

[0365] Step 5:

[0366] The user uploads the work procedure manual they are creating from their terminal to the server. Specifically, the user inputs the new work procedure manual into their terminal and sends it to the server. The input data is the new work procedure manual, and the output is the data sent to the server.

[0367] Step 6:

[0368] The server analyzes input procedures and predicts the risk of problems. It uses a generative model to evaluate new procedures and identify potential risks. The input data is the new work procedure, and the output is the predicted risk level.

[0369] Step 7:

[0370] Based on the prediction results, the server modifies the procedure manual to one with a lower risk of trouble. Specifically, it applies an algorithm to reconstruct the procedure manual to reduce the predicted risk. The input data is the predicted risk level and the original procedure manual, and the output data is the modified procedure manual.

[0371] Step 8:

[0372] The emotion engine recognizes the user's emotional state. Specifically, it analyzes the user's voice and facial expression data to evaluate stress and anxiety. The input data is the voice and facial expression data obtained from the user, and the output data is the evaluation result of the user's emotional state.

[0373] Step 9:

[0374] The server adjusts the presentation of the instruction manual based on the user's emotional state. If the user is feeling stressed, the server presents the instruction manual in a more visually understandable format. The input data are the evaluation result of the user's emotional state and the modified instruction manual, and the output data is the presentation format of the modified instruction manual.

[0375] Step 10:

[0376] The server sends the revised procedure manual and preventive measures and recovery procedures to the terminal and presents them to the user. This allows the user to refer to the optimized procedure manual and proceed with the work. The input data is the revised and adjusted procedure manual, and the output data is the procedure manual displayed on the terminal.

[0377] 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.

[0378] 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.

[0379] 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.

[0380] [Second embodiment]

[0381] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0382] 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.

[0383] 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).

[0384] 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.

[0385] 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.

[0386] 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).

[0387] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0388] 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.

[0389] 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.

[0390] 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.

[0391] In the smart glasses 214, 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.

[0392] 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."

[0393] The present invention is a system for safely and efficiently implementing system construction and maintenance work by utilizing past trouble reports and work procedure manuals. This system is realized by the following program processing.

[0394] First, the server connects to the database and collects past trouble reports and work procedures. This allows the system to collect past trouble cases and know-how, and obtain data for analyzing trouble patterns and causes.

[0395] The server then analyzes the collected data. This analysis involves identifying patterns in the collected data and identifying the causes of problems and solutions. Based on these analysis results, a generative model is trained on the data. This generative model uses a machine learning algorithm to predict future problems based on past data.

[0396] The user inputs the work procedure manual currently being created from the terminal into the server. The server analyzes the input procedure manual and predicts the risk of trouble occurring. Based on the predicted risk, the server automatically modifies the procedure to reduce the risk of trouble occurring. The modified procedure manual is sent to the terminal and presented to the user.

[0397] Furthermore, the server generates preventative measures to address the predicted risk of trouble occurring. These preventative measures are provided as specific measures to prevent trouble before it occurs. Rapid recovery procedures are also generated in the event of trouble occurring. This allows users to respond quickly when trouble occurs and return the system to its original stable state.

[0398] For example, suppose a user inputs a configuration procedure when configuring a new network. The server predicts risks based on past examples of network failures caused by incorrect firewall configurations, and adds a procedure for immediate testing after changing the configuration. In this way, a correction procedure is generated that reduces the risk of problems occurring.

[0399] Finally, the server sends the revised procedure manual and the generated preventive measures and recovery procedures to the terminal and presents them to the user. The user can then confirm the presented procedure manual and measures and carry out the work safely and efficiently.

[0400] As described above, the present invention provides a specific embodiment for utilizing past trouble data to safely and efficiently implement system construction and maintenance work.

[0401] The processing flow will be explained below.

[0402] Step 1:

[0403] The server connects to the database and collects past trouble reports and work procedures. Specifically, it extracts the latest data from the database using an SQL query and temporarily stores it in memory.

[0404] Step 2:

[0405] The server preprocesses the collected data, which includes extracting the necessary information (cause of the problem, countermeasures, and procedure) and converting it into text format. The preprocessed data is then passed to the analysis module.

[0406] Step 3:

[0407] The server uses an analysis module to identify patterns and causes of problems from the pre-processed data, which involves clustering the data using natural language processing techniques to extract commonalities and patterns of problems.

[0408] Step 4:

[0409] The server trains the generative model on the analysis data, using a machine learning algorithm to learn past trouble patterns and countermeasures, thereby improving prediction accuracy.

[0410] Step 5:

[0411] The user uploads the work procedure manual currently being created from the terminal to the server. The procedure manual is usually sent in text file format.

[0412] Step 6:

[0413] The server analyzes the received procedure manual and compares it with past trouble data, thereby predicting the risk of trouble occurring for the input procedure manual.

[0414] Step 7:

[0415] Based on the predicted risk of trouble occurring, the server makes low-risk modifications to the procedure manual, such as adding or modifying procedures or inserting cautionary notes.

[0416] Step 8:

[0417] The server generates a revised procedure manual and adds preventative measures and recovery procedures. Preventative measures include steps to prevent problems from occurring, and recovery procedures include instructions on how to respond if a problem does occur.

[0418] Step 9:

[0419] The server then sends the corrected procedure manual and the generated preventive measures and recovery procedures to the terminal. The procedure manual is often sent in PDF or text file format.

[0420] Step 10:

[0421] The user checks the procedure manual and countermeasures displayed on the terminal, performs the work based on them, corrects the procedure manual as necessary, and performs a final check.

[0422] The above are the specific processing steps of the program in the system of the present invention, which allows engineers to safely and securely perform system construction and maintenance work.

[0423] Example 1

[0424] 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."

[0425] In modern system construction and maintenance work, past trouble cases and work procedures are not fully utilized, resulting in the recurrence of similar problems. Furthermore, insufficient preventive measures and prompt response measures when a problem occurs can compromise the stability of the system. This leads to reduced work efficiency and ultimately to increased operational costs.

[0426] 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.

[0427] In this invention, the server includes means for collecting past work procedures and trouble reports from a database, means for analyzing the collected data and identifying trouble patterns and causes, and means for training a generative model using the analyzed data. This makes it possible to effectively use past trouble data to automatically predict trouble and take measures against it.

[0428] "Past work procedures" are documents that record procedures previously used for system construction and maintenance work.

[0429] A "trouble report" is a report that details problems or failures that occur during system operation.

[0430] A "database" is a system for efficiently storing, managing, and searching data.

[0431] "Means of collection" refers to the methods and techniques used to retrieve historical data and documents from a database.

[0432] "Analytical means" refers to the methods and techniques used to analyze collected data and identify patterns and causes.

[0433] A "generative model" is a machine learning model that generates new data and information based on collected and analyzed data.

[0434] A "work procedure manual in preparation" is a document that records the procedures for system construction and maintenance work currently in progress.

[0435] "Means for receiving input" refers to the method or technique by which the user inputs the work procedure manual being created into the system.

[0436] "Predictive methods" refer to techniques for assessing the likelihood of problems occurring in current work procedures based on past data.

[0437] "Means of correction" refers to methods and techniques for automatically changing the contents of work procedures to reduce the risk of problems occurring.

[0438] "Presentation means" refers to the method or technique for displaying revised procedures and countermeasures to the user.

[0439] A "database management system" is a software system for storing, managing, and manipulating data.

[0440] A "programming language" is a language for writing instructions for data analysis and processing.

[0441] "Natural language generation technology" refers to technology that enables computers to understand and generate natural human language.

[0442] "Means for automatically generating countermeasures" refers to technology that enables a system to automatically generate appropriate countermeasures for problems.

[0443] The present invention provides a system for safely and efficiently implementing system construction and maintenance work using past trouble reports and work procedure manuals. This system utilizes multiple hardware and software components to collect, analyze, predict, and correct data. Specific embodiments for implementing this system are described below.

[0444] First, the server uses a database management system (DBMS) such as MySQL or PostgreSQL to collect past work procedures and trouble reports. Specifically, it connects to the database using a MySQL driver and executes SQL queries to retrieve the necessary data. The retrieved data is then stored in internal memory.

[0445] The server then analyzes the collected data using Python's Pandas library. Data cleansing is performed to extract characteristics of past trouble cases. Furthermore, machine learning algorithms using SciKit-Learn (such as K-Means clustering and Naive Bayes) are used to identify the cause of the trouble and countermeasures. The results of this analysis are input into a generative AI model, forming the basis for new trouble predictions.

[0446] Next, the user enters the work instructions from their device using a dedicated web form via a browser. This web form has the function of sending the entered instructions to the server in JSON format. The server parses the received data and tokenizes and analyzes the content using text analysis tools (NLTK or SpaCy). Furthermore, a generative AI model is used to evaluate the risk of problems occurring for each step.

[0447] The server automatically modifies the operating instructions based on the predicted risks. This process uses natural language generation technology (e.g., GPT-3 API). The modified operating instructions include additional checkpoints and test procedures. The modified operating instructions are then sent back to the terminal in JSON format and presented to the user. At this point, the user can review the improved operating instructions to ensure the safe and efficient operation of the system.

[0448] Furthermore, based on the risk information obtained from the predictive model, the server automatically generates preventative measures for procedures with a high risk of trouble and rapid recovery procedures in the event of a problem. This is done using automation tools such as Jenkins and Ansible. The generated measures and recovery procedures are then sent back to the terminal and presented to the user, enabling a rapid response when a problem occurs.

[0449] As a concrete example, suppose a user is configuring a new network and enters the following configuration instructions:

[0450] The new network configuration procedure is shown below. Predict the risks and generate a correction procedure that includes the necessary countermeasures.

[0451] The server predicts risks based on past examples of network failures caused by incorrect firewall configurations, and adds a procedure for immediate testing after configuration changes are made. As a result, a correction procedure manual that reduces the risk of problems occurring is generated and provided to the user.

[0452] As described above, the present invention provides a specific embodiment for effectively utilizing past trouble data and for safely and efficiently implementing system construction and maintenance work.

[0453] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0454] Step 1:

[0455] The server connects to the database and collects past work procedures and trouble reports. Specifically, it connects to the database using a MySQL driver and executes SQL queries to retrieve data.

[0456] Input: MySQL database connection information and query

[0457] Data processing: Extract data from the database using SQL queries and store it in the internal memory

[0458] Output: Collected past work procedures and trouble reports

[0459] Step 2:

[0460] The server analyzes the collected data, converts it into DataFrame format using Python's Pandas library, and performs data cleansing. It then uses machine learning algorithms (such as K-Means clustering and Naive Bayes) to identify the cause of the problem and how to resolve it.

[0461] Input: Collected past work procedures and trouble reports

[0462] Data processing: Data tokenization, cleaning, and feature extraction

[0463] Data calculation: Identifying causes of problems and solutions using machine learning algorithms

[0464] Output: Analysis results regarding causes of problems and countermeasures

[0465] Step 3:

[0466] The user inputs the current work procedure from the terminal using a web form via the browser, and the input is sent to the server in JSON format.

[0467] Input: Work procedure text

[0468] Data processing: Converting to JSON format and sending to the server

[0469] Output: Result of sending work procedure data to the server

[0470] Step 4:

[0471] The server analyzes the input instructions and predicts the risk of trouble. It uses a text analysis tool (such as NLTK or SpaCy) to tokenize the contents of the prompt and calculate a risk score for each step.

[0472] Input: Work instructions sent by the user (JSON format)

[0473] Data processing: Text tokenization and analysis

[0474] Data Computing: Predicting the Risk of Problems Using Generative AI Models

[0475] Output: Risk score for trouble occurrence for each step

[0476] Step 5:

[0477] The server automatically modifies the procedure manual based on the predicted risks. It uses natural language generation technology (e.g., GPT-3 API) to create improvement suggestions and reflect them in the procedure manual.

[0478] Input: Predicted results of risk of trouble occurring

[0479] Data processing: Correcting instructions using natural language generation algorithms

[0480] Output: Revised work instructions

[0481] Step 6:

[0482] The server sends the revised procedure manual in JSON format to the terminal and presents it to the user.

[0483] Input: Modified work procedure

[0484] Data processing: Converting to JSON format and sending to the device

[0485] Output: The revised work procedure presented to the user

[0486] Step 7:

[0487] Based on the risk information obtained from the predictive model, the server generates preventative measures and rapid recovery procedures for procedures with a high risk of causing problems, using automation tools such as Jenkins and Ansible.

[0488] Input: Procedure information with high risk of trouble

[0489] Data Transformation: Generating and automating countermeasures and recovery procedures

[0490] Output: Generated proactive and rapid recovery procedures

[0491] Through these steps, this system effectively utilizes past data and enables safe and efficient system construction and maintenance work.

[0492] (Application example 1)

[0493] 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."

[0494] When performing maintenance work on automation systems in factories or creating new setup procedures, it is necessary to utilize past trouble data to reduce the risk of problems occurring and improve work efficiency. However, it is difficult for workers to refer to past data in real time and obtain appropriate procedures and countermeasures. This makes problems more likely to occur and makes it difficult to respond quickly. Furthermore, there is a lack of means to provide specific real-time procedure improvements and proactive measures for dealing with factory automation equipment.

[0495] 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.

[0496] In this invention, the server includes a means for collecting past work procedures and trouble reports from a database, a means for analyzing the collected data and identifying trouble patterns and causes, and a means for training a generative model using the analyzed data. This makes it possible to suggest improvements to procedures and preventative measures in real time while work is in progress. It also makes it possible to provide workers with preventative measures for procedures predicted to have a high risk of trouble, as well as quick recovery procedures in the event of a trouble, in real time using their smart devices. This reduces the risk of trouble and enables quick and accurate responses when performing maintenance work on factory automation systems or setting up new procedures.

[0497] "Past work procedures" are documents that describe the procedures for work that was previously performed.

[0498] A "trouble report" is a document that details past problems and how they were dealt with.

[0499] A "database" is a system for efficiently storing, managing, and retrieving structured data.

[0500] "Collection means" refers to the methods or processes that effectively retrieve the required information from the database.

[0501] "Analytical means" refers to the methods and processes used to analyze collected data in detail and reveal its meaning and patterns.

[0502] "Trouble patterns" refer to common characteristics and trends found in past cases of problems occurring.

[0503] A "cause determination method" is a method or process for finding the root cause of a problem that has occurred.

[0504] A "generative model training method" is a method or process for inputting analytical data into a machine learning algorithm to train the model.

[0505] "Work procedure manual in preparation" means the latest document that describes the procedures for work currently in progress.

[0506] "Problem occurrence risk" refers to the degree to which a particular procedure or action is likely to cause a problem.

[0507] "Risk prediction means" refers to a method or process for estimating the likelihood of a problem occurring based on collected and analyzed data.

[0508] A "procedural modification" is a method or process for changing work procedures to avoid a predicted problem.

[0509] A "modified procedure" is a documented work procedure that has been improved to reduce risk.

[0510] "Proactive measures" refer to specific preventative measures that can be taken before a problem occurs.

[0511] "Recovery procedures" are documents that describe the steps to quickly return to normal operation when a problem occurs.

[0512] "Factory automation equipment" refers to devices and systems that operate automatically in production sites to improve work efficiency.

[0513] "Means for proposing improvements and proactive measures in real time" refers to methods and processes for reviewing procedures and providing safety measures immediately during work.

[0514] A "smart device" is a portable electronic device that can display information, connect to the Internet, and run applications.

[0515] "Workers" refers to people who do the actual work in a factory.

[0516] The present invention aims to improve the safety and efficiency of work procedures in a factory automation system. The system configuration required to implement the present invention is as follows.

[0517] First, the server collects past work procedures and trouble reports from a database. The collected data is disorganized and needs to be analyzed. The server analyzes the collected data to identify patterns and causes of trouble. This analysis step uses data mining tools and machine learning algorithms.

[0518] Based on the analysis results, the server trains the generative AI model on the data. This makes it possible to predict future problems from past data. To train the generative AI model, a machine learning library using Python (such as scikit-learn or TensorFlow) is used.

[0519] The user inputs the work procedure manual they are currently creating into the server from a device (smartphone, tablet, smart glasses, etc.). The server analyzes the input procedure manual and predicts the risk of trouble occurring. To do this, it uses a generative AI model to evaluate the procedure in real time and calculate the predicted risk.

[0520] Based on the prediction results, the server automatically modifies procedures to reduce the risk of problems occurring. The modified procedures are then sent to the terminal along with the details of the modifications. The user can then check the modified procedures, preventative measures, and recovery procedures via the terminal.

[0521] Furthermore, the server generates specific preventative measures for procedures that are predicted to have a high risk of causing trouble, and also generates rapid recovery procedures in the event of a problem, allowing users to take appropriate action immediately.

[0522] For example, if a user inputs a procedure for network configuration, the server will automatically correct the procedure to the optimum one by referring to past examples of problems that have occurred with firewall configuration. It will also make corrections to reduce risks by adding appropriate initialization procedures, etc.

[0523] Examples of specific examples and prompts

[0524] For example, the smart glasses used are general smart devices (e.g., Google Glass Enterprise Edition 2), and the tablet is a general high-performance tablet (e.g., iPad Pro).

[0525] Example prompt sentence:

[0526] Based on past reports of firewall configuration problems, please predict the risks of this new configuration manual and make corrections to proceed safely.

[0527] Configuration parameters:

[0528] setting_1 = 192.168.1.1

[0529] setting_2 = allow_all_ports

[0530] setting_3 = enable_logging

[0531] Output instructions:

[0532] Adding an initialization procedure

[0533] Detailed Port Configuration Verification Steps

[0534] Configuring Log Monitoring

[0535] In this way, the present invention realizes the provision of safe and efficient procedure manuals and proactive measures in real time for maintenance work and new setup procedures for factory automation systems.

[0536] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0537] Step 1:

[0538] The server collects past work instructions and trouble reports from a database. The input to this process is the work instructions and trouble reports retrieved from the database, and the output is an aggregated set of these data. Specifically, the server establishes a database connection and uses SQL queries to retrieve the required data.

[0539] Step 2:

[0540] The server analyzes the collected data and identifies patterns and causes of problems. The input to this process is the data collected in step 1, and the output is a list of identified patterns and causes of problems. Specifically, the server analyzes the data using a data mining tool (for example, Python's pandas or numpy) to extract common patterns and causes.

[0541] Step 3:

[0542] The server trains the generative AI model on the analysis data. The input to this process is the data identified in step 2, and the output is a trained generative AI model. Specifically, the server trains the generative AI model using a machine learning library (e.g., scikit-learn or TensorFlow).

[0543] Step 4:

[0544] The user inputs the work procedure manual currently being created from the terminal to the server. The input in this process is the procedure manual entered by the user into the terminal, and the output is the procedure manual received by the server. In concrete terms, the user inputs the procedure manual on the terminal and sends it to the server via the network.

[0545] Step 5:

[0546] The server analyzes the input procedure manual and predicts the risk of trouble occurring. The input for this process is the procedure manual received in step 4 and the AI ​​model trained in step 3, and the output is the evaluation result of the predicted risk of trouble occurring. Specifically, the AI ​​model is used to evaluate the risk of each step in the procedure manual and calculate the risk level in numerical and graphical form.

[0547] Step 6:

[0548] Based on the prediction results, the server modifies the procedure to reduce the risk of trouble. The input to this process is the risk assessment result obtained in step 5, and the output is a modified procedure manual. Specifically, it identifies high-risk steps and restructures the procedure while incorporating safety measures.

[0549] Step 7:

[0550] The server sends the revised procedure manual and the preventive measures and recovery procedures to the terminal and presents them to the user. The input in this process is the procedure manual revised in step 6, and the output is the revised procedure manual and the preventive measures and recovery procedures displayed on the terminal. Specifically, the server formalizes the revised procedure manual, sends it to the terminal over the network, and displays it so that the user can check it.

[0551] Step 8:

[0552] The user checks the revised procedure manual, preventive measures, and recovery procedures through the terminal and carries out the work in accordance with their contents. The input in this process is the information presented on the terminal in step 7, and the output is the user completing the work safely and efficiently. In concrete terms, the user performs the work on site based on the information presented on the terminal.

[0553] 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.

[0554] This invention is a system for safely and efficiently implementing system construction and maintenance work by utilizing past trouble reports and work procedure manuals, and further optimizing the user's work environment by combining it with an emotion engine that recognizes the user's emotions. This system is realized by the following specific program processing.

[0555] First, the server connects to the database and collects past trouble reports and work procedures. This allows the system to collect past trouble cases and know-how, and obtain data for analyzing trouble patterns and causes.

[0556] The server then preprocesses the collected data. Specifically, it extracts the necessary information (cause of the problem, countermeasures, and procedure) into text format and passes it to the analysis module. The analysis module then uses natural language processing technology to cluster the data and identify commonalities and patterns in the problems.

[0557] The server then trains the generative model with these analysis results. The generative model uses machine learning algorithms to learn past trouble patterns and countermeasures, and uses this information to predict future troubles.

[0558] When a user uploads a work procedure manual they are currently creating from their device to the server, the server analyzes the manual and compares it with past trouble data to predict the risk of trouble occurring. Based on the predicted risks, the server automatically modifies the manual to reduce the risk. The modified manual, along with preventive measures and recovery procedures, is sent to the device and presented to the user.

[0559] Furthermore, the present invention incorporates an emotion engine, which allows the server to recognize the user's emotions. The emotion engine analyzes the user's voice, facial expression, or biometric data to assess the user's emotional state. For example, the server can detect stress or anxiety from the user's facial recognition data or voice tone.

[0560] When the emotion engine recognizes the user's emotions, the server adjusts the way instructions are presented to them based on the user's emotional state. For example, if the user is feeling stressed, instructions may be presented step-by-step or in a visually easy-to-understand format. The emotion engine also provides advice to reduce the user's stress and anxiety. Specifically, practical advice such as "take a deep breath" and "take a short break" are presented.

[0561] Furthermore, the system automatically generates preventative measures for procedures predicted to have a high risk of causing problems, as well as quick recovery procedures in the event of a problem. This allows users to make preparations in advance to minimize the impact of a problem, and to immediately use procedures for rapid response in the event of a problem.

[0562] For example, suppose a user inputs configuration instructions when configuring a new network. The server predicts risks based on past examples of network failures caused by incorrect firewall configurations and adds a procedure for immediate testing after the configuration change. In this way, a correction procedure is generated that reduces the risk of problems occurring. Furthermore, if the emotion engine detects the user's anxiety, it will provide detailed explanations and additional visual guides.

[0563] Finally, the server sends the revised procedure manual and the generated preventive measures and recovery procedures to the terminal and presents them to the user. The user can check the presented procedure manual and measures and work in the optimal environment according to their emotional state.

[0564] The above is the specific processing content of the program in the system of the present invention. This system allows engineers to build and maintain systems in a safe, secure, and stress-free environment.

[0565] The processing flow will be explained below.

[0566] Step 1:

[0567] The server connects to the database and gathers past trouble reports and work instructions using SQL queries. For example, it runs the following query:

[0568] sql

[0569] SELECT FROM trouble_reports WHERE date >= '2021-01-01';

[0570] SELECT FROM procedures WHERE date >= '2021-01-01';

[0571] The collected data is temporarily stored in memory.

[0572] Step 2:

[0573] The server preprocesses the collected data. Specifically, it extracts the cause of the problem, countermeasures, and procedures, converts them into text format, such as JSON format data, and passes them to the analysis module.

[0574] Step 3:

[0575] The server then uses an analysis module to analyze the preprocessed data. This analysis uses natural language processing technology to cluster the data and extract commonalities and patterns among the problems. For example, it divides the data into patterns that are easy to classify based on past cases of problems.

[0576] Step 4:

[0577] The server trains the generative model with the analysis results. Using a machine learning algorithm, past trouble patterns and countermeasures are input into the model, improving prediction accuracy.

[0578] Step 5:

[0579] The user uploads the work procedure manual they are currently creating from their terminal to the server. The procedure manual is usually sent in text file format.

[0580] Step 6:

[0581] The server analyzes the uploaded procedure manual and compares it with past trouble data, calculates the degree of agreement with the past data, and predicts the risk of trouble occurring.

[0582] Step 7:

[0583] Based on the predicted risk of trouble occurring, the server automatically modifies the procedure manual to reduce the risk, for example by adding operation steps, changing the order of steps, or inserting cautionary notes.

[0584] Step 8:

[0585] The server generates a revised procedure manual and adds preventive measures and recovery procedures. The preventive measures include specific measures to prevent problems from occurring, and the recovery procedures include how to respond after a problem occurs.

[0586] Step 9:

[0587] The server then sends the corrected procedure manual and the generated preventive measures and recovery procedures to the terminal, often in PDF or text format.

[0588] Step 10:

[0589] The user checks the procedure manual and countermeasures displayed on the device, revises the procedure manual as necessary, and performs a final check. At this time, the emotion engine analyzes the user's emotions and presents appropriate advice.

[0590] Step 11:

[0591] The server uses an emotion engine to analyze the user's voice and facial expressions to determine the user's emotional state. For example, if the user's voice gets louder, it may sense stress.

[0592] Step 12:

[0593] The server adjusts how instructions are presented based on the user's emotional state: if the user is feeling anxious, it presents the instructions step-by-step and adds visual guides.

[0594] Step 13:

[0595] The server provides appropriate advice until the user's emotions stabilize, such as practical instructions like "take a deep breath" or "take a break."

[0596] The above are the specific processing steps of the program in the system of the present invention. This system allows engineers to build and maintain systems in a safe, secure, and stress-free environment.

[0597] Example 2

[0598] 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."

[0599] There is a need to effectively utilize past trouble reports and work procedures to minimize the risk of trouble occurring during system construction and maintenance work. However, this data exists in large quantities, and analyzing and utilizing it is an extremely complex and time-consuming task. Furthermore, there is insufficient support for optimizing the work environment according to the user's emotional state. A method is needed to solve these problems and perform system construction and maintenance work safely and efficiently.

[0600] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0601] In this invention, the server includes means for collecting past work procedures and trouble reports from a database, means for preprocessing the collected data and identifying trouble patterns and causes, means for training the preprocessed data into a generative model, means for receiving work procedures being created as input, means for analyzing the input procedures and predicting the risk of trouble, means for modifying the procedures to have a lower risk of trouble based on the prediction results, means for presenting the modified procedures, preventative measures, and recovery procedures to the user, means for recognizing the user's emotions and adjusting the presentation method of the procedures depending on the user's emotional state, and means for presenting advice to alleviate the emotions. This makes it possible to perform system construction and maintenance work in an optimal work environment that suits the user's emotional state while reducing the risk of trouble.

[0602] A "database" is a system for managing structured collections of data, allowing for efficient data storage, retrieval, and management.

[0603] A "procedure" is a document that details instructions for performing a specific task or operation.

[0604] A "trouble report" is a document that records the details of problems or troubles that have occurred in a system or process and the countermeasures taken.

[0605] "Preprocessing" is the process of shaping raw data into an analyzable format, and includes removing unnecessary data and extracting necessary data.

[0606] A "generative model" is a mathematical model that uses machine learning algorithms to analyze data and make new predictions or generate new ideas.

[0607] A "work procedure manual" is a document that details the steps required to perform a specific job and is used by employees and technicians to ensure the job is performed correctly.

[0608] "Risk of trouble occurring" indicates the degree of possibility that trouble will occur when a specific operation or procedure is performed.

[0609] "User" refers to a person who uses this system to create work procedures and execute the modified procedures.

[0610] An "emotion engine" is a system that analyzes a user's voice, facial expression, biometric data, etc. to evaluate their emotional state.

[0611] "Advice" is instruction or guidance that suggests what action to take or how to improve a particular situation.

[0612] This invention is a system for safely and efficiently implementing system construction and maintenance work by utilizing past trouble reports and work procedure manuals. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it optimizes the user's work environment. This system is realized by the following specific program processing.

[0613] First, the server connects to the database and collects past trouble reports and work procedures. This collection is done using an SQL database, for example by executing a query such as "SELECT FROM TroubleReports." The data is temporarily stored in memory. The hardware used is a high-performance database server, and the software used is Apache Kafka, Hadoop, and the Python Pandas library.

[0614] Next, the server preprocesses the collected data. First, unnecessary data is removed, and necessary information (cause of the problem, countermeasures, and procedure details) is extracted in text format. This preprocessing is performed using natural language processing tools such as NLTK and SpaCy. For example, information about past firewall configuration errors is extracted and recorded in text format. The data obtained in this way is passed to the analysis module.

[0615] The server trains a generative model based on the clustering results obtained by the analysis module. Machine learning algorithms such as TensorFlow and PyTorch are used for the generative model. For example, the server uses data on the causes of past network outages to train the model to identify patterns in which outages occur.

[0616] When a user uploads a work procedure manual they are currently creating from their device to the server, the server analyzes the manual and compares it with past trouble data. This analysis is performed using Celery and Flask, which perform reentrant asynchronous task processing.

[0617] Based on the analysis results, the server predicts the risk of trouble occurring. If a high risk is predicted, the procedure manual is automatically revised. For example, if there is a problem with the configuration procedure, additional confirmation and testing procedures are inserted. Specifically, a procedure to "perform immediate testing after changing the firewall configuration" is added.

[0618] Furthermore, the server uses an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's voice, facial expressions, and biometric data. This analysis uses OpenCV, DeepFaceLab, and NLTK. For example, the server can analyze the user's facial expressions via a webcam to detect stress or anxiety.

[0619] This allows the server to adjust how instructions are presented. If the user is feeling stressed, the instructions may be presented step-by-step or in a more visually understandable format. The emotion engine also offers advice to reduce the user's stress, such as "take a deep breath" or "take a short break."

[0620] Finally, the server sends the revised procedure manual and the generated preventive measures and recovery procedures to the terminal and presents them to the user. The user can then check the presented procedure manual and measures and work in the optimal environment.

[0621] An example of a specific prompt to use when configuring a new network is:

[0622] "Please predict the risks that may arise after changing the firewall settings in the new network configuration and provide steps to mitigate those risks."

[0623] The above is a specific embodiment of the present invention. This system allows engineers to build and maintain systems in a safe, secure, and stress-free environment.

[0624] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0625] Step 1:

[0626] The server connects to the database and collects past trouble reports and work procedures. Specifically, it retrieves the data using an SQL query (e.g., "SELECT FROM TroubleReports").

[0627] Input: SQL database connection information

[0628] Output: Raw data for trouble reports and work procedures

[0629] Data processing: The raw data is temporarily stored in memory.

[0630] Step 2:

[0631] The server preprocesses the collected data, removing unnecessary data and extracting the cause of the problem, countermeasures, and procedures. It then converts the data into text format using NLTK or SpaCy.

[0632] Input: Raw data from collected trouble reports and work procedures

[0633] Output: Preprocessed text data

[0634] Data processing: Extract the necessary information using natural language processing techniques.

[0635] Step 3:

[0636] The server passes the preprocessed data to the analysis module, which performs clustering and uses machine learning algorithms to identify commonalities and patterns of problems.

[0637] Input: Preprocessed text data

[0638] Output: Clustered analysis results

[0639] Data Calculation: Group the data using a clustering algorithm.

[0640] Step 4:

[0641] The server trains a generative model using the analysis results. A generative model is created using TensorFlow or PyTorch, and the model is trained using the analysis results.

[0642] Input: Clustered analysis results

[0643] Output: Generative model parameters

[0644] Data calculation: Optimize the parameters of the machine learning model based on the analysis results.

[0645] Step 5:

[0646] The user uploads the work procedure manual they are currently creating from their device to the server, which receives the manual and analyzes its contents.

[0647] Input: User-created work instructions

[0648] Output: Analysis data

[0649] Data calculation: Analyzes the text of the uploaded procedure manual and extracts its contents.

[0650] Step 6:

[0651] The server predicts the risk of trouble based on the analysis data, compares it with past data, and automatically modifies the procedure manual if the risk is high.

[0652] Input: Analysis data and generative model

[0653] Output: Revised instructions

[0654] Data calculations: Risk prediction algorithms are used to assess the risk of procedures and make modifications to reduce the risk.

[0655] Step 7:

[0656] The server uses an emotion engine to recognize the user's emotions. It analyzes data acquired through the webcam and microphone and evaluates the user's emotional state.

[0657] Input: User's voice, facial expression, biometric data

[0658] Output: Emotion evaluation result

[0659] Data processing: Analyze audio and video data to quantify emotional states.

[0660] Step 8:

[0661] The server adjusts the way it presents instructions based on the emotion evaluation results. If the user is feeling stressed, it will adapt by presenting instructions step by step. It also provides advice on how to reduce stress.

[0662] Input: Emotion evaluation results and revised instructions

[0663] Output: User-adapted procedure presentation and advice

[0664] Action: Adjust presentation and provide advice based on emotional assessment.

[0665] Step 9:

[0666] The server then sends the final revised procedure manual and the generated preventive measures and recovery procedures to the terminal and presents them to the user, who can then check the presented procedure manual and measures and work in the optimal environment.

[0667] Input: Modified procedure and generated countermeasures

[0668] Output: Procedures and countermeasures displayed on the terminal

[0669] Operation: Corrective procedures and countermeasures are sent to the device and displayed to the user.

[0670] (Application example 2)

[0671] 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."

[0672] When maintaining and troubleshooting factory robots, it is necessary to effectively utilize past work procedures and trouble reports to perform the work efficiently and safely. It is also important to reduce the stress and anxiety of maintenance personnel and optimize the work environment.

[0673] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0674] In this invention, the server includes means for collecting past work procedures and trouble reports from a database, means for analyzing the collected data and identifying trouble patterns and causes, means for training a generative model based on the analyzed data, means for receiving work procedures being created as input, means for analyzing the input procedures and predicting the risk of trouble, means for evaluating the emotional state using an emotion engine that recognizes the user's emotions, means for adjusting the presentation method of the procedure based on the emotional state, means for modifying the procedure to one with a lower risk of trouble based on the prediction result, and means for presenting the modified procedure, preventative measures, and recovery procedures to the user. This makes it possible to efficiently and safely perform maintenance and troubleshooting of factory robots, reduce stress and anxiety for maintenance personnel, and provide an optimal work environment.

[0675] A "past work procedure manual" is a document that describes specific work content and procedures that have been performed in the past.

[0676] A "trouble report" is a document that describes problems and troubles that have occurred in the past and how they were dealt with.

[0677] A "database" is a system for systematically storing and managing information such as past work procedures and trouble reports.

[0678] "Analysis" is the process of using natural language processing and machine learning techniques to identify characteristics and patterns in collected data.

[0679] A "generative model" is a model that uses machine learning algorithms to learn specific data patterns and make predictions or generate data for the future.

[0680] The "emotion engine" is a system that analyzes a user's voice, facial expressions, biometric data, etc. to evaluate their emotional state.

[0681] "Risk of trouble occurring" indicates the degree of possibility that trouble will occur due to a specific work procedure.

[0682] "Adjusting the way the instructions are presented" means providing instructions in a visually easy-to-understand format and with step-by-step explanations depending on the user's current emotional state.

[0683] "Proactive measures" are preventative measures and preparations that should be taken before a problem occurs.

[0684] "Recovery procedures" are procedures for quickly and appropriately resolving problems after a problem occurs.

[0685] A system for implementing this invention collects past work procedures and trouble reports from a database, analyzes the data, identifies trouble patterns and causes, and trains a generative model. It also receives work procedures currently being created, predicts the risk of trouble, and modifies the procedures based on that risk. It also evaluates the user's emotional state using an emotion engine that recognizes their emotions and adjusts the way the procedures are presented, thereby providing an efficient and safe work environment.

[0686] The system uses the following hardware and software:

[0687] Server: Connects to the database and collects and analyzes data. Specifically, PostgreSQL is used for database connection, and TensorFlow and NLTK are used for natural language processing and machine learning techniques. Machine learning algorithms including Gradient Boosting and Random Forests are applied to the generative model.

[0688] Terminal: Inputs and displays the work procedure manual. Maintenance personnel can check the procedure manual and any revised procedure manual through this terminal.

[0689] User: Refers to the maintenance personnel who perform tasks using this system.

[0690] Emotion Engine: Uses voice and facial recognition technology (such as EmotionRecognition software) to analyze the user's emotional state.

[0691] The specific data processing and calculation procedures are as follows.

[0692] 1. Data Collection:

[0693] The server collects past work procedures and trouble reports from the database by using specific SQL queries to extract the data.

[0694] 2. Data Preprocessing:

[0695] The server performs text analysis on the collected data to extract the required information by using natural language processing tools such as NLTK to tokenize the documents and extract meaningful tokens.

[0696] 3. Data Analysis and Clustering:

[0697] Machine learning algorithms and clustering techniques are used to analyze trouble data and identify patterns and causes of trouble.

[0698] 4. Generative model training:

[0699] A generative model is constructed based on past trouble data, and a machine learning algorithm is applied to predict trouble patterns.

[0700] 5. Emotion recognition and procedural adjustment:

[0701] To analyze the stress and anxiety users feel during maintenance work, the emotion engine uses voice and facial recognition data to assess their emotions. It uses EmotionRecognition software to analyze the user's emotional state in real time and adjusts the way the instructions are presented to them.

[0702] 6. Risk prediction and procedure revision:

[0703] The server analyzes the current work procedures and predicts the risk of problems occurring. Based on the predicted risks, the server automatically modifies the procedures to reduce the risks, and presents the modified procedures, preventative measures, and recovery procedures to the user via the terminal.

[0704] This system enables efficient and safe maintenance and troubleshooting of factory robots, reducing stress and anxiety for maintenance personnel and providing an optimal working environment.

[0705] Specific examples

[0706] For example, when a factory robot undergoes routine maintenance, the system operates as follows:

[0707] User: "Enter a new maintenance procedure."

[0708] Server: "Based on past trouble data, we have revised the following steps to reduce risk. Please take note of this."

[0709] Emotion Engine: "It looks like you're feeling a bit stressed. Take some slow, deep breaths and take a short break before proceeding."

[0710] In this way, the user can carry out maintenance work efficiently and with peace of mind.

[0711] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0712] Processing steps of the system that realizes the application example

[0713] Step 1:

[0714] The server connects to the database and collects past work procedures and trouble reports. Specifically, the server executes SQL queries to retrieve past trouble data and work procedures. The input data are the records in the database, and the output data is a list of work procedures and trouble reports.

[0715] Step 2:

[0716] The server preprocesses the collected data. Specifically, it uses natural language processing technology to extract the necessary information (cause of the problem, countermeasures, and procedure details). This converts the data into a format suitable for analysis. The input data is the raw data collected in step 1, and the output data is tokenized text data.

[0717] Step 3:

[0718] The server analyzes the preprocessed data and identifies patterns and causes of problems. The server uses clustering techniques (e.g., KMeans) to group the data and discover common patterns. The input data is tokenized text data, and the output data is the problem patterns within each cluster.

[0719] Step 4:

[0720] The server trains a generative model based on the analyzed data. Specifically, it uses a machine learning algorithm (e.g., Gradient Boosting or Random Forests) to train the model based on past trouble patterns. The input data is the analyzed trouble patterns, and the output data is the trained generative model.

[0721] Step 5:

[0722] The user uploads the work procedure manual they are creating from their terminal to the server. Specifically, the user inputs the new work procedure manual into their terminal and sends it to the server. The input data is the new work procedure manual, and the output is the data sent to the server.

[0723] Step 6:

[0724] The server analyzes input procedures and predicts the risk of problems. It uses a generative model to evaluate new procedures and identify potential risks. The input data is the new work procedure, and the output is the predicted risk level.

[0725] Step 7:

[0726] Based on the prediction results, the server modifies the procedure manual to one with a lower risk of trouble. Specifically, it applies an algorithm to reconstruct the procedure manual to reduce the predicted risk. The input data is the predicted risk level and the original procedure manual, and the output data is the modified procedure manual.

[0727] Step 8:

[0728] The emotion engine recognizes the user's emotional state. Specifically, it analyzes the user's voice and facial expression data to evaluate stress and anxiety. The input data is the voice and facial expression data obtained from the user, and the output data is the evaluation result of the user's emotional state.

[0729] Step 9:

[0730] The server adjusts the presentation of the instruction manual based on the user's emotional state. If the user is feeling stressed, the server presents the instruction manual in a more visually understandable format. The input data are the evaluation result of the user's emotional state and the modified instruction manual, and the output data is the presentation format of the modified instruction manual.

[0731] Step 10:

[0732] The server sends the revised procedure manual and preventive measures and recovery procedures to the terminal and presents them to the user. This allows the user to refer to the optimized procedure manual and proceed with the work. The input data is the revised and adjusted procedure manual, and the output data is the procedure manual displayed on the terminal.

[0733] 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.

[0734] 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.

[0735] 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.

[0736] [Third embodiment]

[0737] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0738] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0739] 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).

[0740] 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.

[0741] 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.

[0742] 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).

[0743] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0744] 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.

[0745] 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.

[0746] 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.

[0747] 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.

[0748] 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."

[0749] The present invention is a system for safely and efficiently implementing system construction and maintenance work by utilizing past trouble reports and work procedure manuals. This system is realized by the following program processing.

[0750] First, the server connects to the database and collects past trouble reports and work procedures. This allows the system to collect past trouble cases and know-how, and obtain data for analyzing trouble patterns and causes.

[0751] The server then analyzes the collected data. This analysis involves identifying patterns in the collected data and identifying the causes of problems and solutions. Based on these analysis results, a generative model is trained on the data. This generative model uses a machine learning algorithm to predict future problems based on past data.

[0752] The user inputs the work procedure manual currently being created from the terminal into the server. The server analyzes the input procedure manual and predicts the risk of trouble occurring. Based on the predicted risk, the server automatically modifies the procedure to reduce the risk of trouble occurring. The modified procedure manual is sent to the terminal and presented to the user.

[0753] Furthermore, the server generates preventative measures to address the predicted risk of trouble occurring. These preventative measures are provided as specific measures to prevent trouble before it occurs. Rapid recovery procedures are also generated in the event of trouble occurring. This allows users to respond quickly when trouble occurs and return the system to its original stable state.

[0754] For example, suppose a user inputs a configuration procedure when configuring a new network. The server predicts risks based on past examples of network failures caused by incorrect firewall configurations, and adds a procedure for immediate testing after changing the configuration. In this way, a correction procedure is generated that reduces the risk of problems occurring.

[0755] Finally, the server sends the revised procedure manual and the generated preventive measures and recovery procedures to the terminal and presents them to the user. The user can then confirm the presented procedure manual and measures and carry out the work safely and efficiently.

[0756] As described above, the present invention provides a specific embodiment for utilizing past trouble data to safely and efficiently implement system construction and maintenance work.

[0757] The processing flow will be explained below.

[0758] Step 1:

[0759] The server connects to the database and collects past trouble reports and work procedures. Specifically, it extracts the latest data from the database using an SQL query and temporarily stores it in memory.

[0760] Step 2:

[0761] The server preprocesses the collected data, which includes extracting the necessary information (cause of the problem, countermeasures, and procedure) and converting it into text format. The preprocessed data is then passed to the analysis module.

[0762] Step 3:

[0763] The server uses an analysis module to identify patterns and causes of problems from the pre-processed data, which involves clustering the data using natural language processing techniques to extract commonalities and patterns of problems.

[0764] Step 4:

[0765] The server trains the generative model on the analysis data, using a machine learning algorithm to learn past trouble patterns and countermeasures, thereby improving prediction accuracy.

[0766] Step 5:

[0767] The user uploads the work procedure manual currently being created from the terminal to the server. The procedure manual is usually sent in text file format.

[0768] Step 6:

[0769] The server analyzes the received procedure manual and compares it with past trouble data, thereby predicting the risk of trouble occurring for the input procedure manual.

[0770] Step 7:

[0771] Based on the predicted risk of trouble occurring, the server makes low-risk modifications to the procedure manual, such as adding or modifying procedures or inserting cautionary notes.

[0772] Step 8:

[0773] The server generates a revised procedure manual and adds preventative measures and recovery procedures. Preventative measures include steps to prevent problems from occurring, and recovery procedures include instructions on how to respond if a problem does occur.

[0774] Step 9:

[0775] The server then sends the corrected procedure manual and the generated preventive measures and recovery procedures to the terminal. The procedure manual is often sent in PDF or text file format.

[0776] Step 10:

[0777] The user checks the procedure manual and countermeasures displayed on the terminal, performs the work based on them, corrects the procedure manual as necessary, and performs a final check.

[0778] The above are the specific processing steps of the program in the system of the present invention, which allows engineers to safely and securely perform system construction and maintenance work.

[0779] Example 1

[0780] 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."

[0781] In modern system construction and maintenance work, past trouble cases and work procedures are not fully utilized, resulting in the recurrence of similar problems. Furthermore, insufficient preventive measures and prompt response measures when a problem occurs can compromise the stability of the system. This leads to reduced work efficiency and ultimately to increased operational costs.

[0782] 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.

[0783] In this invention, the server includes means for collecting past work procedures and trouble reports from a database, means for analyzing the collected data and identifying trouble patterns and causes, and means for training a generative model using the analyzed data. This makes it possible to effectively use past trouble data to automatically predict trouble and take measures against it.

[0784] "Past work procedures" are documents that record procedures previously used for system construction and maintenance work.

[0785] A "trouble report" is a report that details problems or failures that occur during system operation.

[0786] A "database" is a system for efficiently storing, managing, and searching data.

[0787] "Means of collection" refers to the methods and techniques used to retrieve historical data and documents from a database.

[0788] "Analytical means" refers to the methods and techniques used to analyze collected data and identify patterns and causes.

[0789] A "generative model" is a machine learning model that generates new data and information based on collected and analyzed data.

[0790] A "work procedure manual in preparation" is a document that records the procedures for system construction and maintenance work currently in progress.

[0791] "Means for receiving input" refers to the method or technique by which the user inputs the work procedure manual being created into the system.

[0792] "Predictive methods" refer to techniques for assessing the likelihood of problems occurring in current work procedures based on past data.

[0793] "Means of correction" refers to methods and techniques for automatically changing the contents of work procedures to reduce the risk of problems occurring.

[0794] "Presentation means" refers to the method or technique for displaying revised procedures and countermeasures to the user.

[0795] A "database management system" is a software system for storing, managing, and manipulating data.

[0796] A "programming language" is a language for writing instructions for data analysis and processing.

[0797] "Natural language generation technology" refers to technology that enables computers to understand and generate natural human language.

[0798] "Means for automatically generating countermeasures" refers to technology that enables a system to automatically generate appropriate countermeasures for problems.

[0799] The present invention provides a system for safely and efficiently implementing system construction and maintenance work using past trouble reports and work procedure manuals. This system utilizes multiple hardware and software components to collect, analyze, predict, and correct data. Specific embodiments for implementing this system are described below.

[0800] First, the server uses a database management system (DBMS) such as MySQL or PostgreSQL to collect past work procedures and trouble reports. Specifically, it connects to the database using a MySQL driver and executes SQL queries to retrieve the necessary data. The retrieved data is then stored in internal memory.

[0801] The server then analyzes the collected data using Python's Pandas library. Data cleansing is performed to extract characteristics of past trouble cases. Furthermore, machine learning algorithms using SciKit-Learn (such as K-Means clustering and Naive Bayes) are used to identify the cause of the trouble and countermeasures. The results of this analysis are input into a generative AI model, forming the basis for new trouble predictions.

[0802] Next, the user enters the work instructions from their device using a dedicated web form via a browser. This web form has the function of sending the entered instructions to the server in JSON format. The server parses the received data and tokenizes and analyzes the content using text analysis tools (NLTK or SpaCy). Furthermore, a generative AI model is used to evaluate the risk of problems occurring for each step.

[0803] The server automatically modifies the operating instructions based on the predicted risks. This process uses natural language generation technology (e.g., GPT-3 API). The modified operating instructions include additional checkpoints and test procedures. The modified operating instructions are then sent back to the terminal in JSON format and presented to the user. At this point, the user can review the improved operating instructions to ensure the safe and efficient operation of the system.

[0804] Furthermore, based on the risk information obtained from the predictive model, the server automatically generates preventative measures for procedures with a high risk of trouble and rapid recovery procedures in the event of a problem. This is done using automation tools such as Jenkins and Ansible. The generated measures and recovery procedures are then sent back to the terminal and presented to the user, enabling a rapid response when a problem occurs.

[0805] As a concrete example, suppose a user is configuring a new network and enters the following configuration instructions:

[0806] The new network configuration procedure is shown below. Predict the risks and generate a correction procedure that includes the necessary countermeasures.

[0807] The server predicts risks based on past examples of network failures caused by incorrect firewall configurations, and adds a procedure for immediate testing after configuration changes are made. As a result, a correction procedure manual that reduces the risk of problems occurring is generated and provided to the user.

[0808] As described above, the present invention provides a specific embodiment for effectively utilizing past trouble data and for safely and efficiently implementing system construction and maintenance work.

[0809] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0810] Step 1:

[0811] The server connects to the database and collects past work procedures and trouble reports. Specifically, it connects to the database using a MySQL driver and executes SQL queries to retrieve data.

[0812] Input: MySQL database connection information and query

[0813] Data processing: Extract data from the database using SQL queries and store it in the internal memory

[0814] Output: Collected past work procedures and trouble reports

[0815] Step 2:

[0816] The server analyzes the collected data, converts it into DataFrame format using Python's Pandas library, and performs data cleansing. It then uses machine learning algorithms (such as K-Means clustering and Naive Bayes) to identify the cause of the problem and how to resolve it.

[0817] Input: Collected past work procedures and trouble reports

[0818] Data processing: Data tokenization, cleaning, and feature extraction

[0819] Data calculation: Identifying causes of problems and solutions using machine learning algorithms

[0820] Output: Analysis results regarding causes of problems and countermeasures

[0821] Step 3:

[0822] The user inputs the current work procedure from the terminal using a web form via the browser, and the input is sent to the server in JSON format.

[0823] Input: Work procedure text

[0824] Data processing: Converting to JSON format and sending to the server

[0825] Output: Result of sending work procedure data to the server

[0826] Step 4:

[0827] The server analyzes the input instructions and predicts the risk of trouble. It uses a text analysis tool (such as NLTK or SpaCy) to tokenize the contents of the prompt and calculate a risk score for each step.

[0828] Input: Work instructions sent by the user (JSON format)

[0829] Data processing: Text tokenization and analysis

[0830] Data Computing: Predicting the Risk of Problems Using Generative AI Models

[0831] Output: Risk score for trouble occurrence for each step

[0832] Step 5:

[0833] The server automatically modifies the procedure manual based on the predicted risks. It uses natural language generation technology (e.g., GPT-3 API) to create improvement suggestions and reflect them in the procedure manual.

[0834] Input: Predicted results of risk of trouble occurring

[0835] Data processing: Correcting instructions using natural language generation algorithms

[0836] Output: Revised work instructions

[0837] Step 6:

[0838] The server sends the revised procedure manual in JSON format to the terminal and presents it to the user.

[0839] Input: Modified work procedure

[0840] Data processing: Converting to JSON format and sending to the device

[0841] Output: The revised work procedure presented to the user

[0842] Step 7:

[0843] Based on the risk information obtained from the predictive model, the server generates preventative measures and rapid recovery procedures for procedures with a high risk of causing problems, using automation tools such as Jenkins and Ansible.

[0844] Input: Procedure information with high risk of trouble

[0845] Data Transformation: Generating and automating countermeasures and recovery procedures

[0846] Output: Generated proactive and rapid recovery procedures

[0847] Through these steps, this system effectively utilizes past data and enables safe and efficient system construction and maintenance work.

[0848] (Application example 1)

[0849] 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."

[0850] When performing maintenance work on automation systems in factories or creating new setup procedures, it is necessary to utilize past trouble data to reduce the risk of problems occurring and improve work efficiency. However, it is difficult for workers to refer to past data in real time and obtain appropriate procedures and countermeasures. This makes problems more likely to occur and makes it difficult to respond quickly. Furthermore, there is a lack of means to provide specific real-time procedure improvements and proactive measures for dealing with factory automation equipment.

[0851] 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.

[0852] In this invention, the server includes a means for collecting past work procedures and trouble reports from a database, a means for analyzing the collected data and identifying trouble patterns and causes, and a means for training a generative model using the analyzed data. This makes it possible to suggest improvements to procedures and preventative measures in real time while work is in progress. It also makes it possible to provide workers with preventative measures for procedures predicted to have a high risk of trouble, as well as quick recovery procedures in the event of a trouble, in real time using their smart devices. This reduces the risk of trouble and enables quick and accurate responses when performing maintenance work on factory automation systems or setting up new procedures.

[0853] "Past work procedures" are documents that describe the procedures for work that was previously performed.

[0854] A "trouble report" is a document that details past problems and how they were dealt with.

[0855] A "database" is a system for efficiently storing, managing, and retrieving structured data.

[0856] "Collection means" refers to the methods or processes that effectively retrieve the required information from the database.

[0857] "Analytical means" refers to the methods and processes used to analyze collected data in detail and reveal its meaning and patterns.

[0858] "Trouble patterns" refer to common characteristics and trends found in past cases of problems occurring.

[0859] A "cause determination method" is a method or process for finding the root cause of a problem that has occurred.

[0860] A "generative model training method" is a method or process for inputting analytical data into a machine learning algorithm to train the model.

[0861] "Work procedure manual in preparation" means the latest document that describes the procedures for work currently in progress.

[0862] "Problem occurrence risk" refers to the degree to which a particular procedure or action is likely to cause a problem.

[0863] "Risk prediction means" refers to a method or process for estimating the likelihood of a problem occurring based on collected and analyzed data.

[0864] A "procedural modification" is a method or process for changing work procedures to avoid a predicted problem.

[0865] A "modified procedure" is a documented work procedure that has been improved to reduce risk.

[0866] "Proactive measures" refer to specific preventative measures that can be taken before a problem occurs.

[0867] "Recovery procedures" are documents that describe the steps to quickly return to normal operation when a problem occurs.

[0868] "Factory automation equipment" refers to devices and systems that operate automatically in production sites to improve work efficiency.

[0869] "Means for proposing improvements and proactive measures in real time" refers to methods and processes for reviewing procedures and providing safety measures immediately during work.

[0870] A "smart device" is a portable electronic device that can display information, connect to the Internet, and run applications.

[0871] "Workers" refers to people who do the actual work in a factory.

[0872] The present invention aims to improve the safety and efficiency of work procedures in a factory automation system. The system configuration required to implement the present invention is as follows.

[0873] First, the server collects past work procedures and trouble reports from a database. The collected data is disorganized and needs to be analyzed. The server analyzes the collected data to identify patterns and causes of trouble. This analysis step uses data mining tools and machine learning algorithms.

[0874] Based on the analysis results, the server trains the generative AI model on the data. This makes it possible to predict future problems from past data. To train the generative AI model, a machine learning library using Python (such as scikit-learn or TensorFlow) is used.

[0875] The user inputs the work procedure manual they are currently creating into the server from a device (smartphone, tablet, smart glasses, etc.). The server analyzes the input procedure manual and predicts the risk of trouble occurring. To do this, it uses a generative AI model to evaluate the procedure in real time and calculate the predicted risk.

[0876] Based on the prediction results, the server automatically modifies procedures to reduce the risk of problems occurring. The modified procedures are then sent to the terminal along with the details of the modifications. The user can then check the modified procedures, preventative measures, and recovery procedures via the terminal.

[0877] Furthermore, the server generates specific preventative measures for procedures that are predicted to have a high risk of causing trouble, and also generates rapid recovery procedures in the event of a problem, allowing users to take appropriate action immediately.

[0878] For example, if a user inputs a procedure for network configuration, the server will automatically correct the procedure to the optimum one by referring to past examples of problems that have occurred with firewall configuration. It will also make corrections to reduce risks by adding appropriate initialization procedures, etc.

[0879] Examples of specific examples and prompts

[0880] For example, the smart glasses used are general smart devices (e.g., Google Glass Enterprise Edition 2), and the tablet is a general high-performance tablet (e.g., iPad Pro).

[0881] Example prompt sentence:

[0882] Based on past reports of firewall configuration problems, please predict the risks of this new configuration manual and make corrections to proceed safely.

[0883] Configuration parameters:

[0884] setting_1 = 192.168.1.1

[0885] setting_2 = allow_all_ports

[0886] setting_3 = enable_logging

[0887] Output instructions:

[0888] Adding an initialization procedure

[0889] Detailed Port Configuration Verification Steps

[0890] Configuring Log Monitoring

[0891] In this way, the present invention realizes the provision of safe and efficient procedure manuals and proactive measures in real time for maintenance work and new setup procedures for factory automation systems.

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

[0893] Step 1:

[0894] The server collects past work instructions and trouble reports from a database. The input to this process is the work instructions and trouble reports retrieved from the database, and the output is an aggregated set of these data. Specifically, the server establishes a database connection and uses SQL queries to retrieve the required data.

[0895] Step 2:

[0896] The server analyzes the collected data and identifies patterns and causes of problems. The input to this process is the data collected in step 1, and the output is a list of identified patterns and causes of problems. Specifically, the server analyzes the data using a data mining tool (for example, Python's pandas or numpy) to extract common patterns and causes.

[0897] Step 3:

[0898] The server trains the generative AI model on the analysis data. The input to this process is the data identified in step 2, and the output is a trained generative AI model. Specifically, the server trains the generative AI model using a machine learning library (e.g., scikit-learn or TensorFlow).

[0899] Step 4:

[0900] The user inputs the work procedure manual currently being created from the terminal to the server. The input in this process is the procedure manual entered by the user into the terminal, and the output is the procedure manual received by the server. In concrete terms, the user inputs the procedure manual on the terminal and sends it to the server via the network.

[0901] Step 5:

[0902] The server analyzes the input procedure manual and predicts the risk of trouble occurring. The input for this process is the procedure manual received in step 4 and the AI ​​model trained in step 3, and the output is the evaluation result of the predicted risk of trouble occurring. Specifically, the AI ​​model is used to evaluate the risk of each step in the procedure manual and calculate the risk level in numerical and graphical form.

[0903] Step 6:

[0904] Based on the prediction results, the server modifies the procedure to reduce the risk of trouble. The input to this process is the risk assessment result obtained in step 5, and the output is a modified procedure manual. Specifically, it identifies high-risk steps and restructures the procedure while incorporating safety measures.

[0905] Step 7:

[0906] The server sends the revised procedure manual and the preventive measures and recovery procedures to the terminal and presents them to the user. The input in this process is the procedure manual revised in step 6, and the output is the revised procedure manual and the preventive measures and recovery procedures displayed on the terminal. Specifically, the server formalizes the revised procedure manual, sends it to the terminal over the network, and displays it so that the user can check it.

[0907] Step 8:

[0908] The user checks the revised procedure manual, preventive measures, and recovery procedures through the terminal and carries out the work in accordance with their contents. The input in this process is the information presented on the terminal in step 7, and the output is the user completing the work safely and efficiently. In concrete terms, the user performs the work on site based on the information presented on the terminal.

[0909] 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.

[0910] This invention is a system for safely and efficiently implementing system construction and maintenance work by utilizing past trouble reports and work procedure manuals, and further optimizing the user's work environment by combining it with an emotion engine that recognizes the user's emotions. This system is realized by the following specific program processing.

[0911] First, the server connects to the database and collects past trouble reports and work procedures. This allows the system to collect past trouble cases and know-how, and obtain data for analyzing trouble patterns and causes.

[0912] The server then preprocesses the collected data. Specifically, it extracts the necessary information (cause of the problem, countermeasures, and procedure) into text format and passes it to the analysis module. The analysis module then uses natural language processing technology to cluster the data and identify commonalities and patterns in the problems.

[0913] The server then trains the generative model with these analysis results. The generative model uses machine learning algorithms to learn past trouble patterns and countermeasures, and uses this information to predict future troubles.

[0914] When a user uploads a work procedure manual they are currently creating from their device to the server, the server analyzes the manual and compares it with past trouble data to predict the risk of trouble occurring. Based on the predicted risks, the server automatically modifies the manual to reduce the risk. The modified manual, along with preventive measures and recovery procedures, is sent to the device and presented to the user.

[0915] Furthermore, the present invention incorporates an emotion engine, which allows the server to recognize the user's emotions. The emotion engine analyzes the user's voice, facial expression, or biometric data to assess the user's emotional state. For example, the server can detect stress or anxiety from the user's facial recognition data or voice tone.

[0916] When the emotion engine recognizes the user's emotions, the server adjusts the way instructions are presented to them based on the user's emotional state. For example, if the user is feeling stressed, instructions may be presented step-by-step or in a visually easy-to-understand format. The emotion engine also provides advice to reduce the user's stress and anxiety. Specifically, practical advice such as "take a deep breath" and "take a short break" are presented.

[0917] Furthermore, the system automatically generates preventative measures for procedures predicted to have a high risk of causing problems, as well as quick recovery procedures in the event of a problem. This allows users to make preparations in advance to minimize the impact of a problem, and to immediately use procedures for rapid response in the event of a problem.

[0918] For example, suppose a user inputs configuration instructions when configuring a new network. The server predicts risks based on past examples of network failures caused by incorrect firewall configurations and adds a procedure for immediate testing after the configuration change. In this way, a correction procedure is generated that reduces the risk of problems occurring. Furthermore, if the emotion engine detects the user's anxiety, it will provide detailed explanations and additional visual guides.

[0919] Finally, the server sends the revised procedure manual and the generated preventive measures and recovery procedures to the terminal and presents them to the user. The user can check the presented procedure manual and measures and work in the optimal environment according to their emotional state.

[0920] The above is the specific processing content of the program in the system of the present invention. This system allows engineers to build and maintain systems in a safe, secure, and stress-free environment.

[0921] The processing flow will be explained below.

[0922] Step 1:

[0923] The server connects to the database and gathers past trouble reports and work instructions using SQL queries. For example, it runs the following query:

[0924] sql

[0925] SELECT FROM trouble_reports WHERE date >= '2021-01-01';

[0926] SELECT FROM procedures WHERE date >= '2021-01-01';

[0927] The collected data is temporarily stored in memory.

[0928] Step 2:

[0929] The server preprocesses the collected data. Specifically, it extracts the cause of the problem, countermeasures, and procedures, converts them into text format, such as JSON format data, and passes them to the analysis module.

[0930] Step 3:

[0931] The server then uses an analysis module to analyze the preprocessed data. This analysis uses natural language processing technology to cluster the data and extract commonalities and patterns among the problems. For example, it divides the data into patterns that are easy to classify based on past cases of problems.

[0932] Step 4:

[0933] The server trains the generative model with the analysis results. Using a machine learning algorithm, past trouble patterns and countermeasures are input into the model, improving prediction accuracy.

[0934] Step 5:

[0935] The user uploads the work procedure manual they are currently creating from their terminal to the server. The procedure manual is usually sent in text file format.

[0936] Step 6:

[0937] The server analyzes the uploaded procedure manual and compares it with past trouble data, calculates the degree of agreement with the past data, and predicts the risk of trouble occurring.

[0938] Step 7:

[0939] Based on the predicted risk of trouble occurring, the server automatically modifies the procedure manual to reduce the risk, for example by adding operation steps, changing the order of steps, or inserting cautionary notes.

[0940] Step 8:

[0941] The server generates a revised procedure manual and adds preventive measures and recovery procedures. The preventive measures include specific measures to prevent problems from occurring, and the recovery procedures include how to respond after a problem occurs.

[0942] Step 9:

[0943] The server then sends the corrected procedure manual and the generated preventive measures and recovery procedures to the terminal, often in PDF or text format.

[0944] Step 10:

[0945] The user checks the procedure manual and countermeasures displayed on the device, revises the procedure manual as necessary, and performs a final check. At this time, the emotion engine analyzes the user's emotions and presents appropriate advice.

[0946] Step 11:

[0947] The server uses an emotion engine to analyze the user's voice and facial expressions to determine the user's emotional state. For example, if the user's voice gets louder, it may sense stress.

[0948] Step 12:

[0949] The server adjusts how instructions are presented based on the user's emotional state: if the user is feeling anxious, it presents the instructions step-by-step and adds visual guides.

[0950] Step 13:

[0951] The server provides appropriate advice until the user's emotions stabilize, such as practical instructions like "take a deep breath" or "take a break."

[0952] The above are the specific processing steps of the program in the system of the present invention. This system allows engineers to build and maintain systems in a safe, secure, and stress-free environment.

[0953] Example 2

[0954] 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."

[0955] There is a need to effectively utilize past trouble reports and work procedures to minimize the risk of trouble occurring during system construction and maintenance work. However, this data exists in large quantities, and analyzing and utilizing it is an extremely complex and time-consuming task. Furthermore, there is insufficient support for optimizing the work environment according to the user's emotional state. A method is needed to solve these problems and perform system construction and maintenance work safely and efficiently.

[0956] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0957] In this invention, the server includes means for collecting past work procedures and trouble reports from a database, means for preprocessing the collected data and identifying trouble patterns and causes, means for training the preprocessed data into a generative model, means for receiving work procedures being created as input, means for analyzing the input procedures and predicting the risk of trouble, means for modifying the procedures to have a lower risk of trouble based on the prediction results, means for presenting the modified procedures, preventative measures, and recovery procedures to the user, means for recognizing the user's emotions and adjusting the presentation method of the procedures depending on the user's emotional state, and means for presenting advice to alleviate the emotions. This makes it possible to perform system construction and maintenance work in an optimal work environment that suits the user's emotional state while reducing the risk of trouble.

[0958] A "database" is a system for managing structured collections of data, allowing for efficient data storage, retrieval, and management.

[0959] A "procedure" is a document that details instructions for performing a specific task or operation.

[0960] A "trouble report" is a document that records the details of problems or troubles that have occurred in a system or process and the countermeasures taken.

[0961] "Preprocessing" is the process of shaping raw data into an analyzable format, and includes removing unnecessary data and extracting necessary data.

[0962] A "generative model" is a mathematical model that uses machine learning algorithms to analyze data and make new predictions or generate new ideas.

[0963] A "work procedure manual" is a document that details the steps required to perform a specific job and is used by employees and technicians to ensure the job is performed correctly.

[0964] "Risk of trouble occurring" indicates the degree of possibility that trouble will occur when a specific operation or procedure is performed.

[0965] "User" refers to a person who uses this system to create work procedures and execute the modified procedures.

[0966] An "emotion engine" is a system that analyzes a user's voice, facial expression, biometric data, etc. to evaluate their emotional state.

[0967] "Advice" is instruction or guidance that suggests what action to take or how to improve a particular situation.

[0968] This invention is a system for safely and efficiently implementing system construction and maintenance work by utilizing past trouble reports and work procedure manuals. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it optimizes the user's work environment. This system is realized by the following specific program processing.

[0969] First, the server connects to the database and collects past trouble reports and work procedures. This collection is done using an SQL database, for example by executing a query such as "SELECT FROM TroubleReports." The data is temporarily stored in memory. The hardware used is a high-performance database server, and the software used is Apache Kafka, Hadoop, and the Python Pandas library.

[0970] Next, the server preprocesses the collected data. First, unnecessary data is removed, and necessary information (cause of the problem, countermeasures, and procedure details) is extracted in text format. This preprocessing is performed using natural language processing tools such as NLTK and SpaCy. For example, information about past firewall configuration errors is extracted and recorded in text format. The data obtained in this way is passed to the analysis module.

[0971] The server trains a generative model based on the clustering results obtained by the analysis module. Machine learning algorithms such as TensorFlow and PyTorch are used for the generative model. For example, the server uses data on the causes of past network outages to train the model to identify patterns in which outages occur.

[0972] When a user uploads a work procedure manual they are currently creating from their device to the server, the server analyzes the manual and compares it with past trouble data. This analysis is performed using Celery and Flask, which perform reentrant asynchronous task processing.

[0973] Based on the analysis results, the server predicts the risk of trouble occurring. If a high risk is predicted, the procedure manual is automatically revised. For example, if there is a problem with the configuration procedure, additional confirmation and testing procedures are inserted. Specifically, a procedure to "perform immediate testing after changing the firewall configuration" is added.

[0974] Furthermore, the server uses an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's voice, facial expressions, and biometric data. This analysis uses OpenCV, DeepFaceLab, and NLTK. For example, the server can analyze the user's facial expressions via a webcam to detect stress or anxiety.

[0975] This allows the server to adjust how instructions are presented. If the user is feeling stressed, the instructions may be presented step-by-step or in a more visually understandable format. The emotion engine also offers advice to reduce the user's stress, such as "take a deep breath" or "take a short break."

[0976] Finally, the server sends the revised procedure manual and the generated preventive measures and recovery procedures to the terminal and presents them to the user. The user can then check the presented procedure manual and measures and work in the optimal environment.

[0977] An example of a specific prompt to use when configuring a new network is:

[0978] "Please predict the risks that may arise after changing the firewall settings in the new network configuration and provide steps to mitigate those risks."

[0979] The above is a specific embodiment of the present invention. This system allows engineers to build and maintain systems in a safe, secure, and stress-free environment.

[0980] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0981] Step 1:

[0982] The server connects to the database and collects past trouble reports and work procedures. Specifically, it retrieves the data using an SQL query (e.g., "SELECT FROM TroubleReports").

[0983] Input: SQL database connection information

[0984] Output: Raw data for trouble reports and work procedures

[0985] Data processing: The raw data is temporarily stored in memory.

[0986] Step 2:

[0987] The server preprocesses the collected data, removing unnecessary data and extracting the cause of the problem, countermeasures, and procedures. It then converts the data into text format using NLTK or SpaCy.

[0988] Input: Raw data from collected trouble reports and work procedures

[0989] Output: Preprocessed text data

[0990] Data processing: Extract the necessary information using natural language processing techniques.

[0991] Step 3:

[0992] The server passes the preprocessed data to the analysis module, which performs clustering and uses machine learning algorithms to identify commonalities and patterns of problems.

[0993] Input: Preprocessed text data

[0994] Output: Clustered analysis results

[0995] Data Calculation: Group the data using a clustering algorithm.

[0996] Step 4:

[0997] The server trains a generative model using the analysis results. A generative model is created using TensorFlow or PyTorch, and the model is trained using the analysis results.

[0998] Input: Clustered analysis results

[0999] Output: Generative model parameters

[1000] Data calculation: Optimize the parameters of the machine learning model based on the analysis results.

[1001] Step 5:

[1002] The user uploads the work procedure manual they are currently creating from their device to the server, which receives the manual and analyzes its contents.

[1003] Input: User-created work instructions

[1004] Output: Analysis data

[1005] Data calculation: Analyzes the text of the uploaded procedure manual and extracts its contents.

[1006] Step 6:

[1007] The server predicts the risk of trouble based on the analysis data, compares it with past data, and automatically modifies the procedure manual if the risk is high.

[1008] Input: Analysis data and generative model

[1009] Output: Revised instructions

[1010] Data calculations: Risk prediction algorithms are used to assess the risk of procedures and make modifications to reduce the risk.

[1011] Step 7:

[1012] The server uses an emotion engine to recognize the user's emotions. It analyzes data acquired through the webcam and microphone and evaluates the user's emotional state.

[1013] Input: User's voice, facial expression, biometric data

[1014] Output: Emotion evaluation result

[1015] Data processing: Analyze audio and video data to quantify emotional states.

[1016] Step 8:

[1017] The server adjusts the way it presents instructions based on the emotion evaluation results. If the user is feeling stressed, it will adapt by presenting instructions step by step. It also provides advice on how to reduce stress.

[1018] Input: Emotion evaluation results and revised instructions

[1019] Output: User-adapted procedure presentation and advice

[1020] Action: Adjust presentation and provide advice based on emotional assessment.

[1021] Step 9:

[1022] The server then sends the final revised procedure manual and the generated preventive measures and recovery procedures to the terminal and presents them to the user, who can then check the presented procedure manual and measures and work in the optimal environment.

[1023] Input: Modified procedure and generated countermeasures

[1024] Output: Procedures and countermeasures displayed on the terminal

[1025] Operation: Corrective procedures and countermeasures are sent to the device and displayed to the user.

[1026] (Application example 2)

[1027] 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."

[1028] When maintaining and troubleshooting factory robots, it is necessary to effectively utilize past work procedures and trouble reports to perform the work efficiently and safely. It is also important to reduce the stress and anxiety of maintenance personnel and optimize the work environment.

[1029] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1030] In this invention, the server includes means for collecting past work procedures and trouble reports from a database, means for analyzing the collected data and identifying trouble patterns and causes, means for training a generative model based on the analyzed data, means for receiving work procedures being created as input, means for analyzing the input procedures and predicting the risk of trouble, means for evaluating the emotional state using an emotion engine that recognizes the user's emotions, means for adjusting the presentation method of the procedure based on the emotional state, means for modifying the procedure to one with a lower risk of trouble based on the prediction result, and means for presenting the modified procedure, preventative measures, and recovery procedures to the user. This makes it possible to efficiently and safely perform maintenance and troubleshooting of factory robots, reduce stress and anxiety for maintenance personnel, and provide an optimal work environment.

[1031] A "past work procedure manual" is a document that describes specific work content and procedures that have been performed in the past.

[1032] A "trouble report" is a document that describes problems and troubles that have occurred in the past and how they were dealt with.

[1033] A "database" is a system for systematically storing and managing information such as past work procedures and trouble reports.

[1034] "Analysis" is the process of using natural language processing and machine learning techniques to identify characteristics and patterns in collected data.

[1035] A "generative model" is a model that uses machine learning algorithms to learn specific data patterns and make predictions or generate data for the future.

[1036] The "emotion engine" is a system that analyzes a user's voice, facial expressions, biometric data, etc. to evaluate their emotional state.

[1037] "Risk of trouble occurring" indicates the degree of possibility that trouble will occur due to a specific work procedure.

[1038] "Adjusting the way the instructions are presented" means providing instructions in a visually easy-to-understand format and with step-by-step explanations depending on the user's current emotional state.

[1039] "Proactive measures" are preventative measures and preparations that should be taken before a problem occurs.

[1040] "Recovery procedures" are procedures for quickly and appropriately resolving problems after a problem occurs.

[1041] A system for implementing this invention collects past work procedures and trouble reports from a database, analyzes the data, identifies trouble patterns and causes, and trains a generative model. It also receives work procedures currently being created, predicts the risk of trouble, and modifies the procedures based on that risk. It also evaluates the user's emotional state using an emotion engine that recognizes their emotions and adjusts the way the procedures are presented, thereby providing an efficient and safe work environment.

[1042] The system uses the following hardware and software:

[1043] Server: Connects to the database and collects and analyzes data. Specifically, PostgreSQL is used for database connection, and TensorFlow and NLTK are used for natural language processing and machine learning techniques. Machine learning algorithms including Gradient Boosting and Random Forests are applied to the generative model.

[1044] Terminal: Inputs and displays the work procedure manual. Maintenance personnel can check the procedure manual and any revised procedure manual through this terminal.

[1045] User: Refers to the maintenance personnel who perform tasks using this system.

[1046] Emotion Engine: Uses voice and facial recognition technology (such as EmotionRecognition software) to analyze the user's emotional state.

[1047] The specific data processing and calculation procedures are as follows.

[1048] 1. Data Collection:

[1049] The server collects past work procedures and trouble reports from the database by using specific SQL queries to extract the data.

[1050] 2. Data Preprocessing:

[1051] The server performs text analysis on the collected data to extract the required information by using natural language processing tools such as NLTK to tokenize the documents and extract meaningful tokens.

[1052] 3. Data Analysis and Clustering:

[1053] Machine learning algorithms and clustering techniques are used to analyze trouble data and identify patterns and causes of trouble.

[1054] 4. Generative model training:

[1055] A generative model is constructed based on past trouble data, and a machine learning algorithm is applied to predict trouble patterns.

[1056] 5. Emotion recognition and procedural adjustment:

[1057] To analyze the stress and anxiety users feel during maintenance work, the emotion engine uses voice and facial recognition data to assess their emotions. It uses EmotionRecognition software to analyze the user's emotional state in real time and adjusts the way the instructions are presented to them.

[1058] 6. Risk prediction and procedure revision:

[1059] The server analyzes the current work procedures and predicts the risk of problems occurring. Based on the predicted risks, the server automatically modifies the procedures to reduce the risks, and presents the modified procedures, preventative measures, and recovery procedures to the user via the terminal.

[1060] This system enables efficient and safe maintenance and troubleshooting of factory robots, reducing stress and anxiety for maintenance personnel and providing an optimal working environment.

[1061] Specific examples

[1062] For example, when a factory robot undergoes routine maintenance, the system operates as follows:

[1063] User: "Enter a new maintenance procedure."

[1064] Server: "Based on past trouble data, we have revised the following steps to reduce risk. Please take note of this."

[1065] Emotion Engine: "It looks like you're feeling a bit stressed. Take some slow, deep breaths and take a short break before proceeding."

[1066] In this way, the user can carry out maintenance work efficiently and with peace of mind.

[1067] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1068] Processing steps of the system that realizes the application example

[1069] Step 1:

[1070] The server connects to the database and collects past work procedures and trouble reports. Specifically, the server executes SQL queries to retrieve past trouble data and work procedures. The input data are the records in the database, and the output data is a list of work procedures and trouble reports.

[1071] Step 2:

[1072] The server preprocesses the collected data. Specifically, it uses natural language processing technology to extract the necessary information (cause of the problem, countermeasures, and procedure details). This converts the data into a format suitable for analysis. The input data is the raw data collected in step 1, and the output data is tokenized text data.

[1073] Step 3:

[1074] The server analyzes the preprocessed data and identifies patterns and causes of problems. The server uses clustering techniques (e.g., KMeans) to group the data and discover common patterns. The input data is tokenized text data, and the output data is the problem patterns within each cluster.

[1075] Step 4:

[1076] The server trains a generative model based on the analyzed data. Specifically, it uses a machine learning algorithm (e.g., Gradient Boosting or Random Forests) to train the model based on past trouble patterns. The input data is the analyzed trouble patterns, and the output data is the trained generative model.

[1077] Step 5:

[1078] The user uploads the work procedure manual they are creating from their terminal to the server. Specifically, the user inputs the new work procedure manual into their terminal and sends it to the server. The input data is the new work procedure manual, and the output is the data sent to the server.

[1079] Step 6:

[1080] The server analyzes input procedures and predicts the risk of problems. It uses a generative model to evaluate new procedures and identify potential risks. The input data is the new work procedure, and the output is the predicted risk level.

[1081] Step 7:

[1082] Based on the prediction results, the server modifies the procedure manual to one with a lower risk of trouble. Specifically, it applies an algorithm to reconstruct the procedure manual to reduce the predicted risk. The input data is the predicted risk level and the original procedure manual, and the output data is the modified procedure manual.

[1083] Step 8:

[1084] The emotion engine recognizes the user's emotional state. Specifically, it analyzes the user's voice and facial expression data to evaluate stress and anxiety. The input data is the voice and facial expression data obtained from the user, and the output data is the evaluation result of the user's emotional state.

[1085] Step 9:

[1086] The server adjusts the presentation of the instruction manual based on the user's emotional state. If the user is feeling stressed, the server presents the instruction manual in a more visually understandable format. The input data are the evaluation result of the user's emotional state and the modified instruction manual, and the output data is the presentation format of the modified instruction manual.

[1087] Step 10:

[1088] The server sends the revised procedure manual and preventive measures and recovery procedures to the terminal and presents them to the user. This allows the user to refer to the optimized procedure manual and proceed with the work. The input data is the revised and adjusted procedure manual, and the output data is the procedure manual displayed on the terminal.

[1089] 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.

[1090] 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.

[1091] 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.

[1092] [Fourth embodiment]

[1093] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1094] 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.

[1095] 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).

[1096] 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.

[1097] 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.

[1098] 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).

[1099] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1100] 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.

[1101] 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.

[1102] 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.

[1103] 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.

[1104] 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.

[1105] 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."

[1106] The present invention is a system for safely and efficiently implementing system construction and maintenance work by utilizing past trouble reports and work procedure manuals. This system is realized by the following program processing.

[1107] First, the server connects to the database and collects past trouble reports and work procedures. This allows the system to collect past trouble cases and know-how, and obtain data for analyzing trouble patterns and causes.

[1108] The server then analyzes the collected data. This analysis involves identifying patterns in the collected data and identifying the causes of problems and solutions. Based on these analysis results, a generative model is trained on the data. This generative model uses a machine learning algorithm to predict future problems based on past data.

[1109] The user inputs the work procedure manual currently being created from the terminal into the server. The server analyzes the input procedure manual and predicts the risk of trouble occurring. Based on the predicted risk, the server automatically modifies the procedure to reduce the risk of trouble occurring. The modified procedure manual is sent to the terminal and presented to the user.

[1110] Furthermore, the server generates preventative measures to address the predicted risk of trouble occurring. These preventative measures are provided as specific measures to prevent trouble before it occurs. Rapid recovery procedures are also generated in the event of trouble occurring. This allows users to respond quickly when trouble occurs and return the system to its original stable state.

[1111] For example, suppose a user inputs a configuration procedure when configuring a new network. The server predicts risks based on past examples of network failures caused by incorrect firewall configurations, and adds a procedure for immediate testing after changing the configuration. In this way, a correction procedure is generated that reduces the risk of problems occurring.

[1112] Finally, the server sends the revised procedure manual and the generated preventive measures and recovery procedures to the terminal and presents them to the user. The user can then confirm the presented procedure manual and measures and carry out the work safely and efficiently.

[1113] As described above, the present invention provides a specific embodiment for utilizing past trouble data to safely and efficiently implement system construction and maintenance work.

[1114] The processing flow will be explained below.

[1115] Step 1:

[1116] The server connects to the database and collects past trouble reports and work procedures. Specifically, it extracts the latest data from the database using an SQL query and temporarily stores it in memory.

[1117] Step 2:

[1118] The server preprocesses the collected data, which includes extracting the necessary information (cause of the problem, countermeasures, and procedure) and converting it into text format. The preprocessed data is then passed to the analysis module.

[1119] Step 3:

[1120] The server uses an analysis module to identify patterns and causes of problems from the pre-processed data, which involves clustering the data using natural language processing techniques to extract commonalities and patterns of problems.

[1121] Step 4:

[1122] The server trains the generative model on the analysis data, using a machine learning algorithm to learn past trouble patterns and countermeasures, thereby improving prediction accuracy.

[1123] Step 5:

[1124] The user uploads the work procedure manual currently being created from the terminal to the server. The procedure manual is usually sent in text file format.

[1125] Step 6:

[1126] The server analyzes the received procedure manual and compares it with past trouble data, thereby predicting the risk of trouble occurring for the input procedure manual.

[1127] Step 7:

[1128] Based on the predicted risk of trouble occurring, the server makes low-risk modifications to the procedure manual, such as adding or modifying procedures or inserting cautionary notes.

[1129] Step 8:

[1130] The server generates a revised procedure manual and adds preventative measures and recovery procedures. Preventative measures include steps to prevent problems from occurring, and recovery procedures include instructions on how to respond if a problem does occur.

[1131] Step 9:

[1132] The server then sends the corrected procedure manual and the generated preventive measures and recovery procedures to the terminal. The procedure manual is often sent in PDF or text file format.

[1133] Step 10:

[1134] The user checks the procedure manual and countermeasures displayed on the terminal, performs the work based on them, corrects the procedure manual as necessary, and performs a final check.

[1135] The above are the specific processing steps of the program in the system of the present invention, which allows engineers to safely and securely perform system construction and maintenance work.

[1136] Example 1

[1137] 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."

[1138] In modern system construction and maintenance work, past trouble cases and work procedures are not fully utilized, resulting in the recurrence of similar problems. Furthermore, insufficient preventive measures and prompt response measures when a problem occurs can compromise the stability of the system. This leads to reduced work efficiency and ultimately to increased operational costs.

[1139] 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.

[1140] In this invention, the server includes means for collecting past work procedures and trouble reports from a database, means for analyzing the collected data and identifying trouble patterns and causes, and means for training a generative model using the analyzed data. This makes it possible to effectively use past trouble data to automatically predict trouble and take measures against it.

[1141] "Past work procedures" are documents that record procedures previously used for system construction and maintenance work.

[1142] A "trouble report" is a report that details problems or failures that occur during system operation.

[1143] A "database" is a system for efficiently storing, managing, and searching data.

[1144] "Means of collection" refers to the methods and techniques used to retrieve historical data and documents from a database.

[1145] "Analytical means" refers to the methods and techniques used to analyze collected data and identify patterns and causes.

[1146] A "generative model" is a machine learning model that generates new data and information based on collected and analyzed data.

[1147] A "work procedure manual in preparation" is a document that records the procedures for system construction and maintenance work currently in progress.

[1148] "Means for receiving input" refers to the method or technique by which the user inputs the work procedure manual being created into the system.

[1149] "Predictive methods" refer to techniques for assessing the likelihood of problems occurring in current work procedures based on past data.

[1150] "Means of correction" refers to methods and techniques for automatically changing the contents of work procedures to reduce the risk of problems occurring.

[1151] "Presentation means" refers to the method or technique for displaying revised procedures and countermeasures to the user.

[1152] A "database management system" is a software system for storing, managing, and manipulating data.

[1153] A "programming language" is a language for writing instructions for data analysis and processing.

[1154] "Natural language generation technology" refers to technology that enables computers to understand and generate natural human language.

[1155] "Means for automatically generating countermeasures" refers to technology that enables a system to automatically generate appropriate countermeasures for problems.

[1156] The present invention provides a system for safely and efficiently implementing system construction and maintenance work using past trouble reports and work procedure manuals. This system utilizes multiple hardware and software components to collect, analyze, predict, and correct data. Specific embodiments for implementing this system are described below.

[1157] First, the server uses a database management system (DBMS) such as MySQL or PostgreSQL to collect past work procedures and trouble reports. Specifically, it connects to the database using a MySQL driver and executes SQL queries to retrieve the necessary data. The retrieved data is then stored in internal memory.

[1158] The server then analyzes the collected data using Python's Pandas library. Data cleansing is performed to extract characteristics of past trouble cases. Furthermore, machine learning algorithms using SciKit-Learn (such as K-Means clustering and Naive Bayes) are used to identify the cause of the trouble and countermeasures. The results of this analysis are input into a generative AI model, forming the basis for new trouble predictions.

[1159] Next, the user enters the work instructions from their device using a dedicated web form via a browser. This web form has the function of sending the entered instructions to the server in JSON format. The server parses the received data and tokenizes and analyzes the content using text analysis tools (NLTK or SpaCy). Furthermore, a generative AI model is used to evaluate the risk of problems occurring for each step.

[1160] The server automatically modifies the operating instructions based on the predicted risks. This process uses natural language generation technology (e.g., GPT-3 API). The modified operating instructions include additional checkpoints and test procedures. The modified operating instructions are then sent back to the terminal in JSON format and presented to the user. At this point, the user can review the improved operating instructions to ensure the safe and efficient operation of the system.

[1161] Furthermore, based on the risk information obtained from the predictive model, the server automatically generates preventative measures for procedures with a high risk of trouble and rapid recovery procedures in the event of a problem. This is done using automation tools such as Jenkins and Ansible. The generated measures and recovery procedures are then sent back to the terminal and presented to the user, enabling a rapid response when a problem occurs.

[1162] As a concrete example, suppose a user is configuring a new network and enters the following configuration instructions:

[1163] The new network configuration procedure is shown below. Predict the risks and generate a correction procedure that includes the necessary countermeasures.

[1164] The server predicts risks based on past examples of network failures caused by incorrect firewall configurations, and adds a procedure for immediate testing after configuration changes are made. As a result, a correction procedure manual that reduces the risk of problems occurring is generated and provided to the user.

[1165] As described above, the present invention provides a specific embodiment for effectively utilizing past trouble data and for safely and efficiently implementing system construction and maintenance work.

[1166] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1167] Step 1:

[1168] The server connects to the database and collects past work procedures and trouble reports. Specifically, it connects to the database using a MySQL driver and executes SQL queries to retrieve data.

[1169] Input: MySQL database connection information and query

[1170] Data processing: Extract data from the database using SQL queries and store it in the internal memory

[1171] Output: Collected past work procedures and trouble reports

[1172] Step 2:

[1173] The server analyzes the collected data, converts it into DataFrame format using Python's Pandas library, and performs data cleansing. It then uses machine learning algorithms (such as K-Means clustering and Naive Bayes) to identify the cause of the problem and how to resolve it.

[1174] Input: Collected past work procedures and trouble reports

[1175] Data processing: Data tokenization, cleaning, and feature extraction

[1176] Data calculation: Identifying causes of problems and solutions using machine learning algorithms

[1177] Output: Analysis results regarding causes of problems and countermeasures

[1178] Step 3:

[1179] The user inputs the current work procedure from the terminal using a web form via the browser, and the input is sent to the server in JSON format.

[1180] Input: Work procedure text

[1181] Data processing: Converting to JSON format and sending to the server

[1182] Output: Result of sending work procedure data to the server

[1183] Step 4:

[1184] The server analyzes the input instructions and predicts the risk of trouble. It uses a text analysis tool (such as NLTK or SpaCy) to tokenize the contents of the prompt and calculate a risk score for each step.

[1185] Input: Work instructions sent by the user (JSON format)

[1186] Data processing: Text tokenization and analysis

[1187] Data Computing: Predicting the Risk of Problems Using Generative AI Models

[1188] Output: Risk score for trouble occurrence for each step

[1189] Step 5:

[1190] The server automatically modifies the procedure manual based on the predicted risks. It uses natural language generation technology (e.g., GPT-3 API) to create improvement suggestions and reflect them in the procedure manual.

[1191] Input: Predicted results of risk of trouble occurring

[1192] Data processing: Correcting instructions using natural language generation algorithms

[1193] Output: Revised work instructions

[1194] Step 6:

[1195] The server sends the revised procedure manual in JSON format to the terminal and presents it to the user.

[1196] Input: Modified work procedure

[1197] Data processing: Converting to JSON format and sending to the device

[1198] Output: The revised work procedure presented to the user

[1199] Step 7:

[1200] Based on the risk information obtained from the predictive model, the server generates preventative measures and rapid recovery procedures for procedures with a high risk of causing problems, using automation tools such as Jenkins and Ansible.

[1201] Input: Procedure information with high risk of trouble

[1202] Data Transformation: Generating and automating countermeasures and recovery procedures

[1203] Output: Generated proactive and rapid recovery procedures

[1204] Through these steps, this system effectively utilizes past data and enables safe and efficient system construction and maintenance work.

[1205] (Application example 1)

[1206] 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."

[1207] When performing maintenance work on automation systems in factories or creating new setup procedures, it is necessary to utilize past trouble data to reduce the risk of problems occurring and improve work efficiency. However, it is difficult for workers to refer to past data in real time and obtain appropriate procedures and countermeasures. This makes problems more likely to occur and makes it difficult to respond quickly. Furthermore, there is a lack of means to provide specific real-time procedure improvements and proactive measures for dealing with factory automation equipment.

[1208] 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.

[1209] In this invention, the server includes a means for collecting past work procedures and trouble reports from a database, a means for analyzing the collected data and identifying trouble patterns and causes, and a means for training a generative model using the analyzed data. This makes it possible to suggest improvements to procedures and preventative measures in real time while work is in progress. It also makes it possible to provide workers with preventative measures for procedures predicted to have a high risk of trouble, as well as quick recovery procedures in the event of a trouble, in real time using their smart devices. This reduces the risk of trouble and enables quick and accurate responses when performing maintenance work on factory automation systems or setting up new procedures.

[1210] "Past work procedures" are documents that describe the procedures for work that was previously performed.

[1211] A "trouble report" is a document that details past problems and how they were dealt with.

[1212] A "database" is a system for efficiently storing, managing, and retrieving structured data.

[1213] "Collection means" refers to the methods or processes that effectively retrieve the required information from the database.

[1214] "Analytical means" refers to the methods and processes used to analyze collected data in detail and reveal its meaning and patterns.

[1215] "Trouble patterns" refer to common characteristics and trends found in past cases of problems occurring.

[1216] A "cause determination method" is a method or process for finding the root cause of a problem that has occurred.

[1217] A "generative model training method" is a method or process for inputting analytical data into a machine learning algorithm to train the model.

[1218] "Work procedure manual in preparation" means the latest document that describes the procedures for work currently in progress.

[1219] "Problem occurrence risk" refers to the degree to which a particular procedure or action is likely to cause a problem.

[1220] "Risk prediction means" refers to a method or process for estimating the likelihood of a problem occurring based on collected and analyzed data.

[1221] A "procedural modification" is a method or process for changing work procedures to avoid a predicted problem.

[1222] A "modified procedure" is a documented work procedure that has been improved to reduce risk.

[1223] "Proactive measures" refer to specific preventative measures that can be taken before a problem occurs.

[1224] "Recovery procedures" are documents that describe the steps to quickly return to normal operation when a problem occurs.

[1225] "Factory automation equipment" refers to devices and systems that operate automatically in production sites to improve work efficiency.

[1226] "Means for proposing improvements and proactive measures in real time" refers to methods and processes for reviewing procedures and providing safety measures immediately during work.

[1227] A "smart device" is a portable electronic device that can display information, connect to the Internet, and run applications.

[1228] "Workers" refers to people who do the actual work in a factory.

[1229] The present invention aims to improve the safety and efficiency of work procedures in a factory automation system. The system configuration required to implement the present invention is as follows.

[1230] First, the server collects past work procedures and trouble reports from a database. The collected data is disorganized and needs to be analyzed. The server analyzes the collected data to identify patterns and causes of trouble. This analysis step uses data mining tools and machine learning algorithms.

[1231] Based on the analysis results, the server trains the generative AI model on the data. This makes it possible to predict future problems from past data. To train the generative AI model, a machine learning library using Python (such as scikit-learn or TensorFlow) is used.

[1232] The user inputs the work procedure manual they are currently creating into the server from a device (smartphone, tablet, smart glasses, etc.). The server analyzes the input procedure manual and predicts the risk of trouble occurring. To do this, it uses a generative AI model to evaluate the procedure in real time and calculate the predicted risk.

[1233] Based on the prediction results, the server automatically modifies procedures to reduce the risk of problems occurring. The modified procedures are then sent to the terminal along with the details of the modifications. The user can then check the modified procedures, preventative measures, and recovery procedures via the terminal.

[1234] Furthermore, the server generates specific preventative measures for procedures that are predicted to have a high risk of causing trouble, and also generates rapid recovery procedures in the event of a problem, allowing users to take appropriate action immediately.

[1235] For example, if a user inputs a procedure for network configuration, the server will automatically correct the procedure to the optimum one by referring to past examples of problems that have occurred with firewall configuration. It will also make corrections to reduce risks by adding appropriate initialization procedures, etc.

[1236] Examples of specific examples and prompts

[1237] For example, the smart glasses used are general smart devices (e.g., Google Glass Enterprise Edition 2), and the tablet is a general high-performance tablet (e.g., iPad Pro).

[1238] Example prompt sentence:

[1239] Based on past reports of firewall configuration problems, please predict the risks of this new configuration manual and make corrections to proceed safely.

[1240] Configuration parameters:

[1241] setting_1 = 192.168.1.1

[1242] setting_2 = allow_all_ports

[1243] setting_3 = enable_logging

[1244] Output instructions:

[1245] Adding an initialization procedure

[1246] Detailed Port Configuration Verification Steps

[1247] Configuring Log Monitoring

[1248] In this way, the present invention realizes the provision of safe and efficient procedure manuals and proactive measures in real time for maintenance work and new setup procedures for factory automation systems.

[1249] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1250] Step 1:

[1251] The server collects past work instructions and trouble reports from a database. The input to this process is the work instructions and trouble reports retrieved from the database, and the output is an aggregated set of these data. Specifically, the server establishes a database connection and uses SQL queries to retrieve the required data.

[1252] Step 2:

[1253] The server analyzes the collected data and identifies patterns and causes of problems. The input to this process is the data collected in step 1, and the output is a list of identified patterns and causes of problems. Specifically, the server analyzes the data using a data mining tool (for example, Python's pandas or numpy) to extract common patterns and causes.

[1254] Step 3:

[1255] The server trains the generative AI model on the analysis data. The input to this process is the data identified in step 2, and the output is a trained generative AI model. Specifically, the server trains the generative AI model using a machine learning library (e.g., scikit-learn or TensorFlow).

[1256] Step 4:

[1257] The user inputs the work procedure manual currently being created from the terminal to the server. The input in this process is the procedure manual entered by the user into the terminal, and the output is the procedure manual received by the server. In concrete terms, the user inputs the procedure manual on the terminal and sends it to the server via the network.

[1258] Step 5:

[1259] The server analyzes the input procedure manual and predicts the risk of trouble occurring. The input for this process is the procedure manual received in step 4 and the AI ​​model trained in step 3, and the output is the evaluation result of the predicted risk of trouble occurring. Specifically, the AI ​​model is used to evaluate the risk of each step in the procedure manual and calculate the risk level in numerical and graphical form.

[1260] Step 6:

[1261] Based on the prediction results, the server modifies the procedure to reduce the risk of trouble. The input to this process is the risk assessment result obtained in step 5, and the output is a modified procedure manual. Specifically, it identifies high-risk steps and restructures the procedure while incorporating safety measures.

[1262] Step 7:

[1263] The server sends the revised procedure manual and the preventive measures and recovery procedures to the terminal and presents them to the user. The input in this process is the procedure manual revised in step 6, and the output is the revised procedure manual and the preventive measures and recovery procedures displayed on the terminal. Specifically, the server formalizes the revised procedure manual, sends it to the terminal over the network, and displays it so that the user can check it.

[1264] Step 8:

[1265] The user checks the revised procedure manual, preventive measures, and recovery procedures through the terminal and carries out the work in accordance with their contents. The input in this process is the information presented on the terminal in step 7, and the output is the user completing the work safely and efficiently. In concrete terms, the user performs the work on site based on the information presented on the terminal.

[1266] 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.

[1267] This invention is a system for safely and efficiently implementing system construction and maintenance work by utilizing past trouble reports and work procedure manuals, and further optimizing the user's work environment by combining it with an emotion engine that recognizes the user's emotions. This system is realized by the following specific program processing.

[1268] First, the server connects to the database and collects past trouble reports and work procedures. This allows the system to collect past trouble cases and know-how, and obtain data for analyzing trouble patterns and causes.

[1269] The server then preprocesses the collected data. Specifically, it extracts the necessary information (cause of the problem, countermeasures, and procedure) into text format and passes it to the analysis module. The analysis module then uses natural language processing technology to cluster the data and identify commonalities and patterns in the problems.

[1270] The server then trains the generative model with these analysis results. The generative model uses machine learning algorithms to learn past trouble patterns and countermeasures, and uses this information to predict future troubles.

[1271] When a user uploads a work procedure manual they are currently creating from their device to the server, the server analyzes the manual and compares it with past trouble data to predict the risk of trouble occurring. Based on the predicted risks, the server automatically modifies the manual to reduce the risk. The modified manual, along with preventive measures and recovery procedures, is sent to the device and presented to the user.

[1272] Furthermore, the present invention incorporates an emotion engine, which allows the server to recognize the user's emotions. The emotion engine analyzes the user's voice, facial expression, or biometric data to assess the user's emotional state. For example, the server can detect stress or anxiety from the user's facial recognition data or voice tone.

[1273] When the emotion engine recognizes the user's emotions, the server adjusts the way instructions are presented to them based on the user's emotional state. For example, if the user is feeling stressed, instructions may be presented step-by-step or in a visually easy-to-understand format. The emotion engine also provides advice to reduce the user's stress and anxiety. Specifically, practical advice such as "take a deep breath" and "take a short break" are presented.

[1274] Furthermore, the system automatically generates preventative measures for procedures predicted to have a high risk of causing problems, as well as quick recovery procedures in the event of a problem. This allows users to make preparations in advance to minimize the impact of a problem, and to immediately use procedures for rapid response in the event of a problem.

[1275] For example, suppose a user inputs configuration instructions when configuring a new network. The server predicts risks based on past examples of network failures caused by incorrect firewall configurations and adds a procedure for immediate testing after the configuration change. In this way, a correction procedure is generated that reduces the risk of problems occurring. Furthermore, if the emotion engine detects the user's anxiety, it will provide detailed explanations and additional visual guides.

[1276] Finally, the server sends the revised procedure manual and the generated preventive measures and recovery procedures to the terminal and presents them to the user. The user can check the presented procedure manual and measures and work in the optimal environment according to their emotional state.

[1277] The above is the specific processing content of the program in the system of the present invention. This system allows engineers to build and maintain systems in a safe, secure, and stress-free environment.

[1278] The processing flow will be explained below.

[1279] Step 1:

[1280] The server connects to the database and gathers past trouble reports and work instructions using SQL queries. For example, it runs the following query:

[1281] sql

[1282] SELECT FROM trouble_reports WHERE date >= '2021-01-01';

[1283] SELECT FROM procedures WHERE date >= '2021-01-01';

[1284] The collected data is temporarily stored in memory.

[1285] Step 2:

[1286] The server preprocesses the collected data. Specifically, it extracts the cause of the problem, countermeasures, and procedures, converts them into text format, such as JSON format data, and passes them to the analysis module.

[1287] Step 3:

[1288] The server then uses an analysis module to analyze the preprocessed data. This analysis uses natural language processing technology to cluster the data and extract commonalities and patterns among the problems. For example, it divides the data into patterns that are easy to classify based on past cases of problems.

[1289] Step 4:

[1290] The server trains the generative model with the analysis results. Using a machine learning algorithm, past trouble patterns and countermeasures are input into the model, improving prediction accuracy.

[1291] Step 5:

[1292] The user uploads the work procedure manual they are currently creating from their terminal to the server. The procedure manual is usually sent in text file format.

[1293] Step 6:

[1294] The server analyzes the uploaded procedure manual and compares it with past trouble data, calculates the degree of agreement with the past data, and predicts the risk of trouble occurring.

[1295] Step 7:

[1296] Based on the predicted risk of trouble occurring, the server automatically modifies the procedure manual to reduce the risk, for example by adding operation steps, changing the order of steps, or inserting cautionary notes.

[1297] Step 8:

[1298] The server generates a revised procedure manual and adds preventive measures and recovery procedures. The preventive measures include specific measures to prevent problems from occurring, and the recovery procedures include how to respond after a problem occurs.

[1299] Step 9:

[1300] The server then sends the corrected procedure manual and the generated preventive measures and recovery procedures to the terminal, often in PDF or text format.

[1301] Step 10:

[1302] The user checks the procedure manual and countermeasures displayed on the device, revises the procedure manual as necessary, and performs a final check. At this time, the emotion engine analyzes the user's emotions and presents appropriate advice.

[1303] Step 11:

[1304] The server uses an emotion engine to analyze the user's voice and facial expressions to determine the user's emotional state. For example, if the user's voice gets louder, it may sense stress.

[1305] Step 12:

[1306] The server adjusts how instructions are presented based on the user's emotional state: if the user is feeling anxious, it presents the instructions step-by-step and adds visual guides.

[1307] Step 13:

[1308] The server provides appropriate advice until the user's emotions stabilize, such as practical instructions like "take a deep breath" or "take a break."

[1309] The above are the specific processing steps of the program in the system of the present invention. This system allows engineers to build and maintain systems in a safe, secure, and stress-free environment.

[1310] Example 2

[1311] 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."

[1312] There is a need to effectively utilize past trouble reports and work procedures to minimize the risk of trouble occurring during system construction and maintenance work. However, this data exists in large quantities, and analyzing and utilizing it is an extremely complex and time-consuming task. Furthermore, there is insufficient support for optimizing the work environment according to the user's emotional state. A method is needed to solve these problems and perform system construction and maintenance work safely and efficiently.

[1313] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1314] In this invention, the server includes means for collecting past work procedures and trouble reports from a database, means for preprocessing the collected data and identifying trouble patterns and causes, means for training the preprocessed data into a generative model, means for receiving work procedures being created as input, means for analyzing the input procedures and predicting the risk of trouble, means for modifying the procedures to have a lower risk of trouble based on the prediction results, means for presenting the modified procedures, preventative measures, and recovery procedures to the user, means for recognizing the user's emotions and adjusting the presentation method of the procedures depending on the user's emotional state, and means for presenting advice to alleviate the emotions. This makes it possible to perform system construction and maintenance work in an optimal work environment that suits the user's emotional state while reducing the risk of trouble.

[1315] A "database" is a system for managing structured collections of data, allowing for efficient data storage, retrieval, and management.

[1316] A "procedure" is a document that details instructions for performing a specific task or operation.

[1317] A "trouble report" is a document that records the details of problems or troubles that have occurred in a system or process and the countermeasures taken.

[1318] "Preprocessing" is the process of shaping raw data into an analyzable format, and includes removing unnecessary data and extracting necessary data.

[1319] A "generative model" is a mathematical model that uses machine learning algorithms to analyze data and make new predictions or generate new ideas.

[1320] A "work procedure manual" is a document that details the steps required to perform a specific job and is used by employees and technicians to ensure the job is performed correctly.

[1321] "Risk of trouble occurring" indicates the degree of possibility that trouble will occur when a specific operation or procedure is performed.

[1322] "User" refers to a person who uses this system to create work procedures and execute the modified procedures.

[1323] An "emotion engine" is a system that analyzes a user's voice, facial expression, biometric data, etc. to evaluate their emotional state.

[1324] "Advice" is instruction or guidance that suggests what action to take or how to improve a particular situation.

[1325] This invention is a system for safely and efficiently implementing system construction and maintenance work by utilizing past trouble reports and work procedure manuals. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it optimizes the user's work environment. This system is realized by the following specific program processing.

[1326] First, the server connects to the database and collects past trouble reports and work procedures. This collection is done using an SQL database, for example by executing a query such as "SELECT FROM TroubleReports." The data is temporarily stored in memory. The hardware used is a high-performance database server, and the software used is Apache Kafka, Hadoop, and the Python Pandas library.

[1327] Next, the server preprocesses the collected data. First, unnecessary data is removed, and necessary information (cause of the problem, countermeasures, and procedure details) is extracted in text format. This preprocessing is performed using natural language processing tools such as NLTK and SpaCy. For example, information about past firewall configuration errors is extracted and recorded in text format. The data obtained in this way is passed to the analysis module.

[1328] The server trains a generative model based on the clustering results obtained by the analysis module. Machine learning algorithms such as TensorFlow and PyTorch are used for the generative model. For example, the server uses data on the causes of past network outages to train the model to identify patterns in which outages occur.

[1329] When a user uploads a work procedure manual they are currently creating from their device to the server, the server analyzes the manual and compares it with past trouble data. This analysis is performed using Celery and Flask, which perform reentrant asynchronous task processing.

[1330] Based on the analysis results, the server predicts the risk of trouble occurring. If a high risk is predicted, the procedure manual is automatically revised. For example, if there is a problem with the configuration procedure, additional confirmation and testing procedures are inserted. Specifically, a procedure to "perform immediate testing after changing the firewall configuration" is added.

[1331] Furthermore, the server uses an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's voice, facial expressions, and biometric data. This analysis uses OpenCV, DeepFaceLab, and NLTK. For example, the server can analyze the user's facial expressions via a webcam to detect stress or anxiety.

[1332] This allows the server to adjust how instructions are presented. If the user is feeling stressed, the instructions may be presented step-by-step or in a more visually understandable format. The emotion engine also offers advice to reduce the user's stress, such as "take a deep breath" or "take a short break."

[1333] Finally, the server sends the revised procedure manual and the generated preventive measures and recovery procedures to the terminal and presents them to the user. The user can then check the presented procedure manual and measures and work in the optimal environment.

[1334] An example of a specific prompt to use when configuring a new network is:

[1335] "Please predict the risks that may arise after changing the firewall settings in the new network configuration and provide steps to mitigate those risks."

[1336] The above is a specific embodiment of the present invention. This system allows engineers to build and maintain systems in a safe, secure, and stress-free environment.

[1337] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1338] Step 1:

[1339] The server connects to the database and collects past trouble reports and work procedures. Specifically, it retrieves the data using an SQL query (e.g., "SELECT FROM TroubleReports").

[1340] Input: SQL database connection information

[1341] Output: Raw data for trouble reports and work procedures

[1342] Data processing: The raw data is temporarily stored in memory.

[1343] Step 2:

[1344] The server preprocesses the collected data, removing unnecessary data and extracting the cause of the problem, countermeasures, and procedures. It then converts the data into text format using NLTK or SpaCy.

[1345] Input: Raw data from collected trouble reports and work procedures

[1346] Output: Preprocessed text data

[1347] Data processing: Extract the necessary information using natural language processing techniques.

[1348] Step 3:

[1349] The server passes the preprocessed data to the analysis module, which performs clustering and uses machine learning algorithms to identify commonalities and patterns of problems.

[1350] Input: Preprocessed text data

[1351] Output: Clustered analysis results

[1352] Data Calculation: Group the data using a clustering algorithm.

[1353] Step 4:

[1354] The server trains a generative model using the analysis results. A generative model is created using TensorFlow or PyTorch, and the model is trained using the analysis results.

[1355] Input: Clustered analysis results

[1356] Output: Generative model parameters

[1357] Data calculation: Optimize the parameters of the machine learning model based on the analysis results.

[1358] Step 5:

[1359] The user uploads the work procedure manual they are currently creating from their device to the server, which receives the manual and analyzes its contents.

[1360] Input: User-created work instructions

[1361] Output: Analysis data

[1362] Data calculation: Analyzes the text of the uploaded procedure manual and extracts its contents.

[1363] Step 6:

[1364] The server predicts the risk of trouble based on the analysis data, compares it with past data, and automatically modifies the procedure manual if the risk is high.

[1365] Input: Analysis data and generative model

[1366] Output: Revised instructions

[1367] Data calculations: Risk prediction algorithms are used to assess the risk of procedures and make modifications to reduce the risk.

[1368] Step 7:

[1369] The server uses an emotion engine to recognize the user's emotions. It analyzes data acquired through the webcam and microphone and evaluates the user's emotional state.

[1370] Input: User's voice, facial expression, biometric data

[1371] Output: Emotion evaluation result

[1372] Data processing: Analyze audio and video data to quantify emotional states.

[1373] Step 8:

[1374] The server adjusts the way it presents instructions based on the emotion evaluation results. If the user is feeling stressed, it will adapt by presenting instructions step by step. It also provides advice on how to reduce stress.

[1375] Input: Emotion evaluation results and revised instructions

[1376] Output: User-adapted procedure presentation and advice

[1377] Action: Adjust presentation and provide advice based on emotional assessment.

[1378] Step 9:

[1379] The server then sends the final revised procedure manual and the generated preventive measures and recovery procedures to the terminal and presents them to the user, who can then check the presented procedure manual and measures and work in the optimal environment.

[1380] Input: Modified procedure and generated countermeasures

[1381] Output: Procedures and countermeasures displayed on the terminal

[1382] Operation: Corrective procedures and countermeasures are sent to the device and displayed to the user.

[1383] (Application example 2)

[1384] 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."

[1385] When maintaining and troubleshooting factory robots, it is necessary to effectively utilize past work procedures and trouble reports to perform the work efficiently and safely. It is also important to reduce the stress and anxiety of maintenance personnel and optimize the work environment.

[1386] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1387] In this invention, the server includes means for collecting past work procedures and trouble reports from a database, means for analyzing the collected data and identifying trouble patterns and causes, means for training a generative model based on the analyzed data, means for receiving work procedures being created as input, means for analyzing the input procedures and predicting the risk of trouble, means for evaluating the emotional state using an emotion engine that recognizes the user's emotions, means for adjusting the presentation method of the procedure based on the emotional state, means for modifying the procedure to one with a lower risk of trouble based on the prediction result, and means for presenting the modified procedure, preventative measures, and recovery procedures to the user. This makes it possible to efficiently and safely perform maintenance and troubleshooting of factory robots, reduce stress and anxiety for maintenance personnel, and provide an optimal work environment.

[1388] A "past work procedure manual" is a document that describes specific work content and procedures that have been performed in the past.

[1389] A "trouble report" is a document that describes problems and troubles that have occurred in the past and how they were dealt with.

[1390] A "database" is a system for systematically storing and managing information such as past work procedures and trouble reports.

[1391] "Analysis" is the process of using natural language processing and machine learning techniques to identify characteristics and patterns in collected data.

[1392] A "generative model" is a model that uses machine learning algorithms to learn specific data patterns and make predictions or generate data for the future.

[1393] The "emotion engine" is a system that analyzes a user's voice, facial expressions, biometric data, etc. to evaluate their emotional state.

[1394] "Risk of trouble occurring" indicates the degree of possibility that trouble will occur due to a specific work procedure.

[1395] "Adjusting the way the instructions are presented" means providing instructions in a visually easy-to-understand format and with step-by-step explanations depending on the user's current emotional state.

[1396] "Proactive measures" are preventative measures and preparations that should be taken before a problem occurs.

[1397] "Recovery procedures" are procedures for quickly and appropriately resolving problems after a problem occurs.

[1398] A system for implementing this invention collects past work procedures and trouble reports from a database, analyzes the data, identifies trouble patterns and causes, and trains a generative model. It also receives work procedures currently being created, predicts the risk of trouble, and modifies the procedures based on that risk. It also evaluates the user's emotional state using an emotion engine that recognizes their emotions and adjusts the way the procedures are presented, thereby providing an efficient and safe work environment.

[1399] The system uses the following hardware and software:

[1400] Server: Connects to the database and collects and analyzes data. Specifically, PostgreSQL is used for database connection, and TensorFlow and NLTK are used for natural language processing and machine learning techniques. Machine learning algorithms including Gradient Boosting and Random Forests are applied to the generative model.

[1401] Terminal: Inputs and displays the work procedure manual. Maintenance personnel can check the procedure manual and any revised procedure manual through this terminal.

[1402] User: Refers to the maintenance personnel who perform tasks using this system.

[1403] Emotion Engine: Uses voice and facial recognition technology (such as EmotionRecognition software) to analyze the user's emotional state.

[1404] The specific data processing and calculation procedures are as follows.

[1405] 1. Data Collection:

[1406] The server collects past work procedures and trouble reports from the database by using specific SQL queries to extract the data.

[1407] 2. Data Preprocessing:

[1408] The server performs text analysis on the collected data to extract the required information by using natural language processing tools such as NLTK to tokenize the documents and extract meaningful tokens.

[1409] 3. Data Analysis and Clustering:

[1410] Machine learning algorithms and clustering techniques are used to analyze trouble data and identify patterns and causes of trouble.

[1411] 4. Generative model training:

[1412] A generative model is constructed based on past trouble data, and a machine learning algorithm is applied to predict trouble patterns.

[1413] 5. Emotion recognition and procedural adjustment:

[1414] To analyze the stress and anxiety users feel during maintenance work, the emotion engine uses voice and facial recognition data to assess their emotions. It uses EmotionRecognition software to analyze the user's emotional state in real time and adjusts the way the instructions are presented to them.

[1415] 6. Risk prediction and procedure revision:

[1416] The server analyzes the current work procedures and predicts the risk of problems occurring. Based on the predicted risks, the server automatically modifies the procedures to reduce the risks, and presents the modified procedures, preventative measures, and recovery procedures to the user via the terminal.

[1417] This system enables efficient and safe maintenance and troubleshooting of factory robots, reducing stress and anxiety for maintenance personnel and providing an optimal working environment.

[1418] Specific examples

[1419] For example, when a factory robot undergoes routine maintenance, the system operates as follows:

[1420] User: "Enter a new maintenance procedure."

[1421] Server: "Based on past trouble data, we have revised the following steps to reduce risk. Please take note of this."

[1422] Emotion Engine: "It looks like you're feeling a bit stressed. Take some slow, deep breaths and take a short break before proceeding."

[1423] In this way, the user can carry out maintenance work efficiently and with peace of mind.

[1424] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1425] Processing steps of the system that realizes the application example

[1426] Step 1:

[1427] The server connects to the database and collects past work procedures and trouble reports. Specifically, the server executes SQL queries to retrieve past trouble data and work procedures. The input data are the records in the database, and the output data is a list of work procedures and trouble reports.

[1428] Step 2:

[1429] The server preprocesses the collected data. Specifically, it uses natural language processing technology to extract the necessary information (cause of the problem, countermeasures, and procedure details). This converts the data into a format suitable for analysis. The input data is the raw data collected in step 1, and the output data is tokenized text data.

[1430] Step 3:

[1431] The server analyzes the preprocessed data and identifies patterns and causes of problems. The server uses clustering techniques (e.g., KMeans) to group the data and discover common patterns. The input data is tokenized text data, and the output data is the problem patterns within each cluster.

[1432] Step 4:

[1433] The server trains a generative model based on the analyzed data. Specifically, it uses a machine learning algorithm (e.g., Gradient Boosting or Random Forests) to train the model based on past trouble patterns. The input data is the analyzed trouble patterns, and the output data is the trained generative model.

[1434] Step 5:

[1435] The user uploads the work procedure manual they are creating from their terminal to the server. Specifically, the user inputs the new work procedure manual into their terminal and sends it to the server. The input data is the new work procedure manual, and the output is the data sent to the server.

[1436] Step 6:

[1437] The server analyzes input procedures and predicts the risk of problems. It uses a generative model to evaluate new procedures and identify potential risks. The input data is the new work procedure, and the output is the predicted risk level.

[1438] Step 7:

[1439] Based on the prediction results, the server modifies the procedure manual to one with a lower risk of trouble. Specifically, it applies an algorithm to reconstruct the procedure manual to reduce the predicted risk. The input data is the predicted risk level and the original procedure manual, and the output data is the modified procedure manual.

[1440] Step 8:

[1441] The emotion engine recognizes the user's emotional state. Specifically, it analyzes the user's voice and facial expression data to evaluate stress and anxiety. The input data is the voice and facial expression data obtained from the user, and the output data is the evaluation result of the user's emotional state.

[1442] Step 9:

[1443] The server adjusts the presentation of the instruction manual based on the user's emotional state. If the user is feeling stressed, the server presents the instruction manual in a more visually understandable format. The input data are the evaluation result of the user's emotional state and the modified instruction manual, and the output data is the presentation format of the modified instruction manual.

[1444] Step 10:

[1445] The server sends the revised procedure manual and preventive measures and recovery procedures to the terminal and presents them to the user. This allows the user to refer to the optimized procedure manual and proceed with the work. The input data is the revised and adjusted procedure manual, and the output data is the procedure manual displayed on the terminal.

[1446] 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.

[1447] 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.

[1448] 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 robot 414.

[1449] 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.

[1450] 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.

[1451] 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.

[1452] 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).

[1453] 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.

[1454] 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."

[1455] 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.

[1456] 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).

[1457] 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.

[1458] 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.

[1459] 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.

[1460] 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.

[1461] 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.

[1462] 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.

[1463] 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.

[1464] 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.

[1465] 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.

[1466] 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.

[1467] The following is further disclosed regarding the above embodiment.

[1468] (Claim 1)

[1469] A means for collecting past work procedures and trouble reports from a database;

[1470] A method for analyzing collected data and identifying patterns and causes of problems,

[1471] A means for training a generative model on the analysis data;

[1472] means for receiving as input the work procedure manual being created;

[1473] A method for analyzing input procedures and predicting the risk of problems occurring,

[1474] Based on the prediction results, there are ways to modify procedures to reduce the risk of problems occurring.

[1475] a means for presenting the revised procedure and the preventative and recovery procedures to the user;

[1476] A system including:

[1477] (Claim 2)

[1478] A means for generating preventive measures for procedures predicted to have a high risk of trouble;

[1479] A means for generating quick recovery procedures in the event of a problem;

[1480] The system of claim 1 further comprising:

[1481] (Claim 3)

[1482] 2. The system according to claim 1, wherein the data collected and analyzed includes the causes of trouble, countermeasures, and procedure details.

[1483] "Example 1"

[1484] (Claim 1)

[1485] A means for collecting past work procedures and trouble reports from a database;

[1486] A method for analyzing collected data and identifying patterns and causes of problems,

[1487] A means for training a generative model on the analysis data;

[1488] means for receiving as input the work procedure manual being created;

[1489] A method for analyzing input procedures using a text analysis tool to predict the risk of problems occurring;

[1490] Based on the prediction results, a method is provided to automatically correct procedures to reduce the risk of problems occurring.

[1491] a means for presenting the revised procedure and the preventative and recovery procedures to the user;

[1492] means including a database management system for data collection, a programming language for data analysis, and natural language generation techniques;

[1493] A system including:

[1494] (Claim 2)

[1495] A means for generating preventive measures for procedures predicted to have a high risk of trouble;

[1496] A means for generating quick recovery procedures in the event of a problem;

[1497] The system according to claim 1, further comprising means for automatically generating countermeasures based on risk information obtained from the predictive model.

[1498] (Claim 3)

[1499] 2. The system according to claim 1, wherein the data collected and analyzed includes the causes of trouble, countermeasures, and procedure details.

[1500] "Application Example 1"

[1501] (Claim 1)

[1502] A means for collecting past work procedures and trouble reports from a database;

[1503] A method for analyzing collected data and identifying patterns and causes of problems,

[1504] A means for training a generative model on the analysis data;

[1505] means for receiving as input the work procedure manual being created;

[1506] A method for analyzing input procedures and predicting the risk of problems occurring,

[1507] Based on the prediction results, there are ways to modify procedures to reduce the risk of problems occurring.

[1508] a means for presenting the revised procedure and the preventative and recovery procedures to the user;

[1509] A means to suggest improvements to procedures and preventative measures in real time during operation for factory automation equipment,

[1510] A system including:

[1511] (Claim 2)

[1512] A means for generating preventive measures for procedures predicted to have a high risk of trouble;

[1513] A means for generating quick recovery procedures in the event of a problem;

[1514] A means of providing this information to workers in real time using smart devices;

[1515] The system of claim 1 further comprising:

[1516] (Claim 3)

[1517] 2. The system according to claim 1, wherein the data collected and analyzed includes the causes of trouble, countermeasures, and procedure details.

[1518] "Example 2: Combining Emotion Engines"

[1519] (Claim 1)

[1520] A means for collecting past work procedures and trouble reports from a database;

[1521] A means of preprocessing the collected data and identifying patterns and causes of problems,

[1522] a means for training a generative model on the preprocessed data;

[1523] means for receiving as input the work procedure manual being created;

[1524] A method for analyzing input procedures and predicting the risk of problems occurring,

[1525] Based on the prediction results, there are ways to modify procedures to reduce the risk of problems occurring.

[1526] a means for presenting the revised procedure and the preventative and recovery procedures to the user;

[1527] means for recognizing the user's emotions and adjusting the presentation method of the instruction manual according to the user's emotional state;

[1528] A means of providing advice to reduce emotions;

[1529] A system including:

[1530] (Claim 2)

[1531] A means for generating preventive measures for procedures predicted to have a high risk of trouble;

[1532] A means for generating quick recovery procedures in the event of a problem;

[1533] The system of claim 1 further comprising:

[1534] (Claim 3)

[1535] 2. The system according to claim 1, wherein the collected and preprocessed data includes the cause of the trouble, countermeasures, and procedure details.

[1536] "Application example 2 when combining emotion engines"

[1537] (Claim 1)

[1538] A means for collecting past work procedures and trouble reports from a database;

[1539] A method for analyzing collected data and identifying patterns and causes of problems,

[1540] A means for training a generative model on the analysis data;

[1541] means for receiving as input the work procedure manual being created;

[1542] A method for analyzing input procedures and predicting the risk of problems occurring,

[1543] means for assessing an emotional state using an emotion engine that recognizes the user's emotions;

[1544] means for adjusting the presentation of instructions based on the emotional state;

[1545] Based on the prediction results, there are ways to modify procedures to reduce the risk of problems occurring.

[1546] a means for presenting the revised procedure and the preventative and recovery procedures to the user;

[1547] A system including:

[1548] (Claim 2)

[1549] A means for generating preventive measures for procedures predicted to have a high risk of trouble;

[1550] A means for generating quick recovery procedures in the event of a problem;

[1551] The system of claim 1 further comprising:

[1552] (Claim 3)

[1553] 2. The system according to claim 1, wherein the data collected and analyzed includes the causes of trouble, countermeasures, and procedure details. [Explanation of symbols]

[1554] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for collecting past work procedures and trouble reports from a database; A method for analyzing collected data and identifying patterns and causes of problems, A means for training a generative model on the analysis data; means for receiving as input the work procedure manual being created; A method for analyzing input procedures and predicting the risk of problems occurring, Based on the prediction results, there are ways to modify procedures to reduce the risk of problems occurring. a means for presenting the revised procedure and the preventative and recovery procedures to the user; A system including:

2. A means for generating preventive measures for procedures predicted to have a high risk of trouble; A means for generating quick recovery procedures in the event of a problem; The system of claim 1 further comprising:

3. 2. The system according to claim 1, wherein the collected and analyzed data includes the cause of the trouble, countermeasures, and procedure details.

Images