system

Abstract

We provide the system. [Solution] A data collection means for collecting and storing equipment data, A predictive analysis means that performs equipment failure prediction based on the said data, A scheduling means that generates an optimal maintenance schedule based on predictive analysis results, A monitoring means for monitoring the real-time status of the equipment, An inventory management system that optimizes parts inventory based on demand forecasts, A system for managing engineers' skill information and assigning the most suitable engineers to tasks, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the manufacturing industry, equipment failures and inefficiencies in maintenance planning are causing productivity to decline and maintenance costs to increase. Also, waste of engineers' resources and the inability to properly manage parts inventory are cited as problems. There is a need to realize a system that improves such a situation and optimizes maintenance costs while improving the operating rate of equipment.

Means for Solving the Problems

[0005] This invention provides a system that collects data from equipment and predicts failures using machine learning algorithms. This automatically generates an optimal maintenance schedule based on the predicted failure outcomes. Furthermore, it has a real-time equipment monitoring function that immediately detects abnormalities. It also enables optimization of parts inventory based on demand forecasts and optimal allocation based on technician skill information. This simultaneously reduces equipment downtime and maintenance costs.

[0006] "Data acquisition means" refers to functions and devices for acquiring data from equipment in real time, and for storing and managing that data.

[0007] "Predictive analytics means" refers to functions and algorithms that analyze past and present data to predict the likelihood of future equipment failures.

[0008] "Scheduling means" refers to a function that determines the optimal timing for maintenance work and plans it based on failure predictions.

[0009] "Monitoring means" refers to functions or devices that monitor the status of equipment in real time and detect abnormalities.

[0010] "Inventory management tools" refer to functions for optimizing inventory of parts and materials based on predicted demand.

[0011] "Engineer management tools" refer to functions and systems for managing engineers' skills and experience data and for assigning them to optimal tasks. [Brief explanation of the drawing]

[0012] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3]It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which multiple emotions are mapped. [Figure 10] It shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Embodiments for Carrying Out the Invention

[0013] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0014] First, the language used in the following description will be explained.

[0015] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0016] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0018] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor and 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), or Bluetooth (registered trademark), and the like.

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] As shown in Figure 1, the 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.

[0023] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0024] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0025] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0026] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0027] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0030] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0031] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0032] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0033] The maintenance optimization system according to the present invention is a comprehensive platform for achieving efficient management and maintenance of manufacturing equipment. This system begins by collecting data through sensors attached to various pieces of equipment and transmitting it to a server. The server stores this data in real time and predicts equipment failures by comparing it with past operating patterns.

[0034] Specifically, the server uses machine learning algorithms to analyze data and detect signs of failure. Based on these results, the server generates an optimal maintenance schedule and notifies the user. This makes it easier for the user to perform maintenance at the appropriate time.

[0035] Furthermore, the server monitors the equipment in real time and immediately sends an alert if an anomaly is detected. This allows users to address problems before they become apparent.

[0036] Furthermore, the server also handles inventory management, forecasting parts demand and optimizing inventory to prevent shortages of necessary parts. This ensures that users always have access to the parts they need, when they need them. The server also manages technicians' skills and availability, assigning them the most suitable tasks.

[0037] For example, if motor vibration data exceeds the normal range, the server will determine this is a sign of failure, automatically assign a suitable technician, and secure replacement parts from inventory. This allows the user to resolve the problem quickly and efficiently.

[0038] The following describes the processing flow.

[0039] Step 1:

[0040] The terminal collects data in real time from sensors attached to the equipment. This data includes information such as vibration, temperature, pressure, and power consumption, and is periodically transmitted to a server.

[0041] Step 2:

[0042] The server receives the collected data and stores it in the database. Data preprocessing is performed to detect outliers and impute missing data.

[0043] Step 3:

[0044] The server analyzes data using machine learning algorithms. It compares the current data to past data patterns to predict the likelihood of failure. This analysis is then used to assess future failure risks.

[0045] Step 4:

[0046] The server automatically generates a maintenance schedule based on failure predictions. This ensures that preventative maintenance plans proceed smoothly. The generated schedule is notified to the user's terminal.

[0047] Step 5:

[0048] The user reviews the proposed maintenance schedule. They can adjust or approve the schedule as needed. This enables efficient maintenance.

[0049] Step 6:

[0050] The terminal continues to monitor the equipment status in real time and immediately sends any new abnormalities detected to the server.

[0051] Step 7:

[0052] The server receives an anomaly notification and, if necessary, issues an alert to the user to take emergency response procedures.

[0053] Step 8:

[0054] The server manages inventory based on predicted component demand. It plans component orders in a timely manner to prevent inventory shortages.

[0055] Step 9:

[0056] The server manages technicians' skill data and availability, assigning the most suitable technician to maintenance tasks. Appropriate staffing levels improve work efficiency and output.

[0057] (Example 1)

[0058] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0059] Conventional equipment management systems face challenges in efficient equipment operation due to unexpected equipment failures and inappropriate maintenance timing. Furthermore, inadequate allocation of technicians and optimization of parts inventory can negatively impact equipment utilization rates.

[0060] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0061] In this invention, the server includes data acquisition means for collecting and storing operational information of the equipment, prediction means for predicting equipment abnormalities based on the operational information, and scheduling means for generating an optimal maintenance schedule using a generated AI model. This makes it possible to improve the operating rate of the equipment and enable efficient operation by predicting equipment failures in advance and performing appropriate maintenance.

[0062] "Equipment" is a general term for devices and equipment used in the manufacturing or production process.

[0063] "Operational information" refers to data such as temperature, vibration, and pressure collected when the equipment is in operation.

[0064] A "data acquisition method" is a system that collects and stores operational information from sensors installed on equipment.

[0065] A "predictive means" is a technology that predicts equipment malfunctions in advance based on collected operational information.

[0066] A "generative AI model" refers to artificial intelligence technology that analyzes large amounts of data and proposes optimal results and actions.

[0067] A "scheduling method" is a process for creating optimal work and maintenance schedules based on the results of a prediction method.

[0068] A "monitoring system" is a system that constantly checks the status of equipment and prompts immediate action when an abnormality occurs.

[0069] "Inventory of consumables" is a term that indicates the stockpiling status of replacement parts and materials necessary for the operation of equipment.

[0070] An "inventory control system" is a mechanism for properly managing the inventory of consumables and adjusting supply according to demand.

[0071] "Worker allocation methods" refer to the process of managing engineers' skills and availability, and assigning the most suitable engineers to the appropriate tasks.

[0072] The maintenance optimization system of the present invention streamlines equipment management and enables planned and timely maintenance. The main components of this system consist of data acquisition, forecasting, scheduling, monitoring, inventory control, and worker allocation.

[0073] The server first collects operational information using sensors attached to various pieces of equipment. These sensors send data such as temperature, vibration, and pressure to the server in real time, and this data is stored in a database. Specific hardware includes temperature sensors and vibration sensors. The server then analyzes this data and uses software libraries such as Python's scikit-learn and TENSORFLOW® to run machine learning models and predict equipment anomalies. This allows for the provision of information to enable appropriate maintenance before equipment failures occur.

[0074] Furthermore, the server utilizes a generative AI model to create an optimal maintenance schedule. This allows users to perform planned maintenance at the appropriate time, improving equipment uptime. This schedule is notified to the user via their terminal.

[0075] The server, which also functions as a monitoring system, constantly checks the status of the equipment and sends alerts to terminals if any abnormalities are detected. This function allows users to address abnormalities in real time.

[0076] In inventory management, the server predicts demand based on past consumable usage data and implements appropriate controls to prevent shortages. This process ensures that users always have the necessary parts available when needed, allowing for smooth equipment maintenance.

[0077] Furthermore, regarding the management of technicians, the server considers skill information and availability to efficiently assign the most suitable technician to the relevant maintenance task. This information is also transmitted to the user's terminal to support maintenance planning and execution.

[0078] For example, if the server analyzes motor vibration data and detects an anomaly exceeding the normal range, it can then assign the appropriate technician and prepare consumables based on the results. This allows the user to minimize equipment downtime and operate efficiently.

[0079] An example of a prompt message might be, "Analyze the motor's vibration data, assess the risk of failure, and generate an optimal maintenance schedule." In this way, the system of the present invention contributes to the optimization of equipment operation in manufacturing sites.

[0080] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0081] Step 1:

[0082] The server receives operational information from the sensor in real time. The inputs here are physical quantities such as temperature, vibration, and pressure. Specifically, the sensor sends data to the server at regular intervals, and the server stores this data in a database.

[0083] Step 2:

[0084] The server inputs collected operational information into a machine learning model to predict anomalies. This input includes operational information acquired from sensors. Data processing involves time-series analysis to detect anomaly patterns. Specifically, it uses Python libraries to perform data analysis and calculate the probability of anomalies.

[0085] Step 3:

[0086] The server uses a generative AI model to create an optimal maintenance schedule. The input for this step is the result of anomaly prediction. The output is a schedule that includes specific maintenance timings and required work procedures. In practice, the server generates the schedule based on the analysis results and notifies the terminal.

[0087] Step 4:

[0088] The server continuously monitors the equipment status and immediately sends an alert to the user's terminal if an anomaly is detected. Inputs are real-time sensor data, and outputs are alert notifications. Specifically, when a threshold is exceeded, the server sends an alert email or notification.

[0089] Step 5:

[0090] The server optimizes inventory based on demand forecasts for consumables. The inputs for this step are historical usage data and current anomaly forecasts. The output is an optimal parts inventory list. Specifically, it uses a demand forecasting algorithm to calculate the number of parts needed in the future and plans inventory replenishment.

[0091] Step 6:

[0092] The server assigns the most suitable worker based on the technician's skills and availability. The inputs for this step are the technician's competence information and maintenance schedule. The output is a list of assigned technicians. Specifically, a skill matching algorithm is used to select the most suitable technician and determine their placement.

[0093] (Application Example 1)

[0094] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0095] Modern manufacturing equipment demands efficient maintenance and rapid troubleshooting. However, existing systems struggle to detect signs of failure early, quickly dispatch appropriate technicians, and reliably prepare necessary parts, resulting in reduced equipment uptime. This invention aims to solve these problems and achieve efficient operation and maintenance of equipment.

[0096] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0097] In this invention, the server includes information acquisition means, predictive processing means, planning means, monitoring means, stock management means, engineer coordination means, anomaly notification means, and information provision means. This enables early detection of signs of equipment failure, allowing for timely maintenance and rapid fault response. This improves equipment utilization and increases cost efficiency.

[0098] "Information acquisition means" refers to a function for collecting and storing data from various sensors installed in the equipment.

[0099] The "predictive processing means" is a function that analyzes collected data and uses machine learning algorithms to predict equipment failures.

[0100] The "planning mechanism" is a function that creates an optimal maintenance schedule based on predicted analysis results.

[0101] A "monitoring system" is a function that monitors the real-time status of equipment and immediately detects any abnormalities.

[0102] "Stockpiling management measures" refer to functions that optimize the inventory of necessary parts based on demand forecasts and prevent stockouts.

[0103] "Engineer coordination means" refers to a function that manages engineers' skill information and schedules, and assigns the most suitable engineer to a task.

[0104] The "anomaly notification mechanism" is a function that analyzes the vibration data of the equipment and sends a notification to the user if an anomaly is detected.

[0105] "Information provision means" refers to a function that provides users with information on signs of malfunction and maintenance information through a mobile device application.

[0106] The system implementing this invention is an integrated platform combining various means to promote the efficient operation and maintenance of equipment. This system consists of sensors, servers, and mobile terminal applications.

[0107] First, data is collected from sensors installed on the equipment using information acquisition methods. This data is then transmitted to a server using communication technologies such as Bluetooth or Wi-Fi. The server is implemented using the Python language, and its backend is built using the Flask framework. This ensures that the data is reliably received and stored.

[0108] Next, the server uses a predictive processing mechanism to analyze the data with machine learning models such as TensorFlow and predict equipment failures. This process allows for the early detection of signs of failure, enabling a rapid response.

[0109] Then, using planning tools, an optimal maintenance schedule is created for predicted failures. In addition, using engineer coordination tools, the skill information of engineers is utilized to select the most suitable engineers and assign them tasks.

[0110] Furthermore, an anomaly notification system analyzes the equipment's vibration data and sends a real-time notification to the user's mobile device if an anomaly is detected. In this process, a mobile application using React Native provides the user interface and functions as an information delivery tool.

[0111] For example, if a manufacturing robot exhibits higher-than-normal vibrations, the server will immediately detect the anomaly and notify the user of the need for maintenance. This notification will include a summary of the problem and a recommended maintenance schedule.

[0112] In this way, it becomes possible to maximize the operating efficiency of the equipment while performing necessary maintenance work quickly and efficiently. Further efficiency can be achieved by utilizing a generative AI model, for example, by using prompts such as, "Analyze the vibration data of the power generation equipment, detect anomalies, and propose a maintenance schedule."

[0113] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0114] Step 1:

[0115] Sensors installed on the equipment collect real-time data such as vibration and temperature. This input data is transmitted to a server via Bluetooth. The server stores the received data in a database and filters the data as needed.

[0116] Step 2:

[0117] The server uses TensorFlow to analyze historical data stored in the database and newly collected data. This machine learning model recognizes data patterns and predicts the likelihood of failure as output. Based on these predictions, the user is notified of signs of failure.

[0118] Step 3:

[0119] The server generates a maintenance schedule using a planning mechanism based on the prediction results. Here, the prediction results and technician schedule information are used as input, and the optimal maintenance data is provided as output. The schedule is automatically updated by the technician coordination mechanism.

[0120] Step 4:

[0121] The server uses an anomaly notification mechanism to inform the user of the generated schedule and predicted anomalies. An alert is displayed on the user's mobile device through a React Native application, clearly indicating the type of anomaly and recommended actions.

[0122] Step 5:

[0123] Users can use a mobile app to check maintenance details and communicate necessary work instructions to technicians. This allows for early problem resolution and efficient equipment operation.

[0124] In this way, a smooth flow of information can be achieved between servers and terminals, optimizing equipment operation and maintenance, and further efficiency can be achieved.

[0125] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0126] This invention aims to further improve efficiency and optimization by incorporating an emotion engine into an equipment maintenance optimization system, taking into account the user's emotional state. First, a terminal collects data from sensors attached to the equipment and transmits it to a server. The server analyzes the data and uses a machine learning algorithm to predict failures. Based on these results, the server generates an optimal maintenance schedule and notifies the user.

[0127] Furthermore, the emotion engine analyzes the user's voice and facial expressions. This allows it to acquire emotional data to perform maintenance tasks at the optimal time based on the user's work efficiency and concentration level. The server takes this emotional data into account and dynamically adjusts the schedule to provide the user with the best possible work environment.

[0128] For example, if a technician is burdened with many high-load tasks, the emotion engine can detect the technician's fatigue and stress. Based on this information, the work schedule can be readjusted to reduce the user's burden. Furthermore, if the user is feeling anxious about a particular maintenance task, the emotion engine can assist in providing learning modules and support functions to address that anxiety.

[0129] Therefore, this system enables efficient equipment maintenance while allowing for flexible responses based on user sentiment, resulting in improved overall operational efficiency and reduced maintenance costs.

[0130] The following describes the processing flow.

[0131] Step 1:

[0132] The terminal continuously collects environmental data from sensors attached to the equipment and periodically transmits it to the server.

[0133] Step 2:

[0134] The server stores the received environmental data in a database and performs data preprocessing. This includes noise reduction and filtering outliers.

[0135] Step 3:

[0136] The server uses machine learning algorithms to analyze data to estimate the likelihood of failure. This analysis is then used to update the failure risk assessment.

[0137] Step 4:

[0138] The server generates an optimal maintenance schedule based on failure predictions and notifies the user's terminal of the schedule. The user can review this and make adjustments as needed.

[0139] Step 5:

[0140] The device's built-in emotion engine analyzes the user's voice and facial expressions, extracting emotional information in real time. Based on this information, the system evaluates the user's concentration level and stress level.

[0141] Step 6:

[0142] The server retrieves information from the emotion engine and readjusts the maintenance schedule to take the user's psychological state into account. If necessary, it distributes the workload and optimizes the allocation of technicians.

[0143] Step 7:

[0144] The server uses its inventory management function to predict the demand for necessary parts and creates an ordering plan to optimize parts supply.

[0145] Step 8:

[0146] Users receive work instructions via their devices and carry out equipment maintenance and repairs according to plan. It's also possible to leverage emotional data to provide appropriate support and educational resources.

[0147] This series of processes allows the system to support the efficient operation of equipment and provide flexible maintenance plans that take into account the user's emotions and psychological factors.

[0148] (Example 2)

[0149] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0150] Conventional equipment maintenance systems primarily focused on predicting equipment failures and optimizing maintenance schedules. However, they failed to consider factors such as workers' emotional states and fluctuations in work efficiency, potentially leading to increased worker burden and decreased equipment utilization. Furthermore, despite the possibility of advanced analysis using machine learning algorithms, it was difficult to utilize the results to adjust the work environment in real time.

[0151] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0152] In this invention, the server includes information gathering means, predictive analysis means, plan generation means, monitoring means, resource management means, worker management means, and emotion analysis means. This enables real-time analysis of workers' emotional states and the generation of an optimal maintenance plan linked to equipment failure prediction results, as well as adjustment of the work environment.

[0153] "Information gathering means" refers to a device or method that has the function of collecting data from various sensors installed in the facility and transmitting it to a server.

[0154] A "predictive analysis means" is a device or method that uses a machine learning algorithm to predict equipment failures based on collected information.

[0155] "Plan generation means" refers to a device or method that generates an optimal maintenance work plan based on the results of failure prediction.

[0156] "Monitoring means" refers to a device or method that has the function of continuously monitoring the instantaneous state of equipment and detecting abnormalities.

[0157] "Resource management means" refers to a device or method that optimizes the inventory of parts and materials based on demand forecasts and supplies the appropriate resources when needed.

[0158] "Worker management means" refers to a device or method for managing information about workers' skills and experience and for assigning the most suitable personnel to the appropriate tasks.

[0159] "Emotional analysis means" refers to a device or method that analyzes a worker's emotional state from their voice and facial expressions and uses the results to adjust the work environment.

[0160] This invention is a system for optimizing equipment maintenance, and by organically linking multiple functions, it realizes the generation of maintenance schedules that take into account equipment failure prediction and the emotional state of workers.

[0161] First, the terminal collects data in real time from sensors attached to the equipment (e.g., temperature sensors, vibration sensors, pressure sensors) and sends that data to the server. These sensors use standard IoT protocols as their communication protocol.

[0162] The server stores received data in a database and performs data formatting and analysis using Python, R, and other tools. Machine learning algorithms such as TensorFlow and scikit-learn are used to predict equipment failures. Based on the failure prediction results, maintenance plans are formulated using linear programming and heuristic methods.

[0163] Furthermore, a terminal or dedicated device collects the worker's voice and facial expressions, which are then analyzed by an emotion analysis engine. This analysis utilizes services such as Microsoft® Azure® Face API. The obtained emotion data is integrated on a server and fed back into the maintenance plan.

[0164] For example, if an engineer is overworked and stressed, the emotion engine can detect this and readjust the maintenance schedule to reduce the engineer's burden. Furthermore, if it detects anxiety about a specific task, it can support the engineer by providing a learning module.

[0165] Examples of prompts for the generating AI model include instructions such as, "Consider the following user emotional state and generate the optimal maintenance schedule," or "Based on the failure prediction results, suggest a corresponding work schedule."

[0166] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0167] Step 1:

[0168] The terminal collects data from the equipment's sensors. The inputs are sensor data such as temperature, vibration, and pressure. The terminal collects this data in real time and performs an initial check for any abnormal values. Data that does not show any abnormalities is sent to the server in batch processing.

[0169] Step 2:

[0170] The server stores the received sensor data in a database. The input is sensor data sent from the terminal. The server formats this data and stores it in a database (e.g., PostgreSQL). The data is converted to an appropriate format for subsequent analysis.

[0171] Step 3:

[0172] The server analyzes stored data to predict failures. The input is sensor data stored in a database. The server uses Python and TensorFlow to analyze the data with machine learning algorithms. This process predicts the risk of equipment failure, and the result is output as numerical data.

[0173] Step 4:

[0174] The server generates a maintenance plan based on the failure prediction results. The input is the failure prediction result data. The server uses linear programming to formulate the optimal maintenance schedule. The created plan is output as schedule data and notified to the user.

[0175] Step 5:

[0176] A terminal or dedicated device collects and analyzes the user's emotional data. The input is audio or video data. The terminal uses a microphone and camera to collect this data and sends it to an emotional analysis engine. The emotional analysis engine analyzes the collected data and outputs the user's emotional state.

[0177] Step 6:

[0178] The server adjusts the maintenance schedule based on emotional data. The input is emotional state data from the emotional analysis engine. The server combines the current schedule with the emotional data to make necessary schedule adjustments to optimize the work environment. The adjusted schedule is then re-notified to the user's terminal.

[0179] (Application Example 2)

[0180] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0181] In equipment maintenance, it has been difficult to enable efficient and optimal responses to anticipated failures while also flexibly adjusting work processes to take into account the emotional state of the workers. Therefore, improvements are needed to increase equipment utilization and reduce maintenance costs.

[0182] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0183] In this invention, the server includes information acquisition means, predictive analysis means, scheduling means, monitoring means, inventory management means, personnel management means, and sentiment analysis means. This allows for real-time monitoring of equipment status, the creation of optimal maintenance plans based on failure predictions, and adjustments to suit the emotional state of workers.

[0184] "Information acquisition means" refers to devices or technologies that have the function of collecting various types of data from equipment and appropriately storing or transferring them.

[0185] "Predictive analytics" refers to technologies that use collected data and machine learning algorithms to predict the probability and timing of equipment failures.

[0186] "Scheduling methods" refer to technologies for creating schedules to carry out maintenance work in the most efficient and effective manner, based on predictive analysis results.

[0187] "Monitoring methods" refer to technologies for checking the real-time status of equipment and issuing notifications or alarms as needed.

[0188] "Inventory management methods" are technologies that optimize the inventory of necessary parts and materials based on demand forecasts, and replenish or place orders at the appropriate time.

[0189] "Personnel management methods" refer to technologies for managing information about engineers' skills and experience, and for flexibly assigning the right personnel to the necessary tasks.

[0190] "Emotional analysis methods" are technologies that analyze emotional data such as workers' voices and facial expressions to provide approaches for improving work efficiency and safety.

[0191] The system that realizes this application example utilizes information acquisition means, predictive analysis means, scheduling means, monitoring means, inventory management means, personnel management means, and sentiment analysis means to streamline the maintenance of factory equipment.

[0192] The server stores equipment data collected from smart sensors using information acquisition methods. This allows for monitoring of equipment operation status and acquisition of necessary data in real time.

[0193] The server uses machine learning algorithms such as TensorFlow to predict equipment failures based on the acquired data. The predictive analysis means analyzes the equipment's operating data and identifies areas where failures are likely. In addition, smart glasses collect the worker's voice and facial expressions, and the emotion analysis means identifies the user's emotional state.

[0194] Based on the generated failure prediction and sentiment data, the server generates an optimal maintenance schedule and notifies the appropriate personnel through scheduling mechanisms. Furthermore, inventory management mechanisms efficiently manage necessary parts and supply them at the required time.

[0195] For example, if a robot in a factory exhibits abnormal behavior, predictive analysis identifies the malfunction as a problem, and a work schedule with reduced stress levels is generated, taking into account the feelings of the workers. The system automatically notifies the staff and initiates an optimized maintenance process.

[0196] An example of an input prompt for a generated AI model is: "Please report on a system that takes into account the user's emotional state to help optimize factory robot maintenance."

[0197] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0198] Step 1:

[0199] The terminal collects real-time data from smart sensors attached to the equipment. This data includes equipment parameters such as vibration, temperature, and current. By sending this data to a server, the basic information necessary for analysis is obtained.

[0200] Step 2:

[0201] The server receives the transmitted equipment data and performs data preprocessing. It cleans and normalizes the data to prepare it for analysis. Using the input equipment parameters, it removes outliers and outputs a standardized dataset.

[0202] Step 3:

[0203] The server uses the organized data to perform failure prediction through predictive analytics. Based on machine learning algorithms (e.g., TensorFlow), it identifies patterns indicating abnormal equipment behavior and evaluates the likelihood of future failures. It analyzes the patterns obtained from the input data and outputs failure prediction results.

[0204] Step 4:

[0205] The server generates an optimal maintenance schedule using scheduling methods based on predictive analytics results and user sentiment data. It creates a realistic work plan considering the workload of the workers. It outputs an efficient schedule proposal from the input failure predictions and sentiment data.

[0206] Step 5:

[0207] The device collects the worker's voice and facial expressions through smart glasses and evaluates their emotional state in real time using emotion analysis. This allows it to recognize the user's stress level, concentration level, etc., and reflect this in their schedule. Emotional results are output from the input audio and video data.

[0208] Step 6:

[0209] The server uses inventory management tools to forecast the demand for maintenance parts and implements an optimized inventory plan. This enables the supply of parts at the necessary time. Based on the input demand forecast data, it outputs the inventory allocation.

[0210] Step 7:

[0211] Users can input prompts into the generated AI model to obtain reports on system operating status and maintenance adjustments. This allows for a deeper understanding of the work process. The system outputs reports generated based on the prompts.

[0212] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0213] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0214] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0215] [Second Embodiment]

[0216] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0217] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0218] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0219] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0220] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0221] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0222] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0223] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0224] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0225] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0226] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0227] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0228] The maintenance optimization system according to the present invention is a comprehensive platform for achieving efficient management and maintenance of manufacturing equipment. This system begins by collecting data through sensors attached to various pieces of equipment and transmitting it to a server. The server stores this data in real time and predicts equipment failures by comparing it with past operating patterns.

[0229] Specifically, the server uses machine learning algorithms to analyze data and detect signs of failure. Based on these results, the server generates an optimal maintenance schedule and notifies the user. This makes it easier for the user to perform maintenance at the appropriate time.

[0230] Furthermore, the server monitors the equipment in real time and immediately sends an alert if an anomaly is detected. This allows users to address problems before they become apparent.

[0231] Furthermore, the server also handles inventory management, forecasting parts demand and optimizing inventory to prevent shortages of necessary parts. This ensures that users always have access to the parts they need, when they need them. The server also manages technicians' skills and availability, assigning them the most suitable tasks.

[0232] For example, if motor vibration data exceeds the normal range, the server will determine this is a sign of failure, automatically assign a suitable technician, and secure replacement parts from inventory. This allows the user to resolve the problem quickly and efficiently.

[0233] The following describes the processing flow.

[0234] Step 1:

[0235] The terminal collects data in real time from sensors attached to the equipment. This data includes information such as vibration, temperature, pressure, and power consumption, and is periodically transmitted to a server.

[0236] Step 2:

[0237] The server receives the collected data and stores it in the database. Data preprocessing is performed to detect outliers and impute missing data.

[0238] Step 3:

[0239] The server analyzes data using machine learning algorithms. It compares the current data to past data patterns to predict the likelihood of failure. This analysis is then used to assess future failure risks.

[0240] Step 4:

[0241] The server automatically generates a maintenance schedule based on failure predictions. This ensures that preventative maintenance plans proceed smoothly. The generated schedule is notified to the user's terminal.

[0242] Step 5:

[0243] The user reviews the proposed maintenance schedule. They can adjust or approve the schedule as needed. This enables efficient maintenance.

[0244] Step 6:

[0245] The terminal continues to monitor the equipment status in real time and immediately sends any new abnormalities detected to the server.

[0246] Step 7:

[0247] The server receives an anomaly notification and, if necessary, issues an alert to the user to take emergency response procedures.

[0248] Step 8:

[0249] The server manages inventory based on predicted component demand. It plans component orders in a timely manner to prevent inventory shortages.

[0250] Step 9:

[0251] The server manages technicians' skill data and availability, assigning the most suitable technician to maintenance tasks. Appropriate staffing levels improve work efficiency and output.

[0252] (Example 1)

[0253] Next, we will describe Example 1. 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."

[0254] Conventional equipment management systems face challenges in efficient equipment operation due to unexpected equipment failures and inappropriate maintenance timing. Furthermore, inadequate allocation of technicians and optimization of parts inventory can negatively impact equipment utilization rates.

[0255] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0256] In this invention, the server includes data acquisition means for collecting and storing operational information of the equipment, prediction means for predicting equipment abnormalities based on the operational information, and scheduling means for generating an optimal maintenance schedule using a generated AI model. This makes it possible to improve the operating rate of the equipment and enable efficient operation by predicting equipment failures in advance and performing appropriate maintenance.

[0257] "Equipment" is a general term for devices and equipment used in the manufacturing or production process.

[0258] "Operational information" refers to data such as temperature, vibration, and pressure collected when the equipment is in operation.

[0259] A "data acquisition method" is a system that collects and stores operational information from sensors installed on equipment.

[0260] A "predictive means" is a technology that predicts equipment malfunctions in advance based on collected operational information.

[0261] A "generative AI model" refers to artificial intelligence technology that analyzes large amounts of data and proposes optimal results and actions.

[0262] A "scheduling method" is a process for creating optimal work and maintenance schedules based on the results of a prediction method.

[0263] A "monitoring system" is a system that constantly checks the status of equipment and prompts immediate action when an abnormality occurs.

[0264] "Inventory of consumables" is a term that indicates the stockpiling status of replacement parts and materials necessary for the operation of equipment.

[0265] An "inventory control system" is a mechanism for properly managing the inventory of consumables and adjusting supply according to demand.

[0266] "Worker allocation methods" refer to the process of managing engineers' skills and availability, and assigning the most suitable engineers to the appropriate tasks.

[0267] The maintenance optimization system of the present invention streamlines equipment management and enables planned and timely maintenance. The main components of this system consist of data acquisition, forecasting, scheduling, monitoring, inventory control, and worker allocation.

[0268] The server first collects operational information using sensors attached to various pieces of equipment. These sensors send data such as temperature, vibration, and pressure to the server in real time, and this data is stored in a database. Specific hardware includes temperature sensors and vibration sensors. The server then analyzes this data and uses machine learning models, such as Python's scikit-learn or TensorFlow, to predict equipment anomalies. This allows for the provision of information to enable appropriate maintenance before equipment failures occur.

[0269] Furthermore, the server utilizes a generative AI model to create an optimal maintenance schedule. This allows users to perform planned maintenance at the appropriate time, improving equipment uptime. This schedule is notified to the user via their terminal.

[0270] The server, which also functions as a monitoring system, constantly checks the status of the equipment and sends alerts to terminals if any abnormalities are detected. This function allows users to address abnormalities in real time.

[0271] In inventory management, the server predicts demand based on past consumable usage data and implements appropriate controls to prevent shortages. This process ensures that users always have the necessary parts available when needed, allowing for smooth equipment maintenance.

[0272] Furthermore, regarding the management of technicians, the server considers skill information and availability to efficiently assign the most suitable technician to the relevant maintenance task. This information is also transmitted to the user's terminal to support maintenance planning and execution.

[0273] For example, if the server analyzes motor vibration data and detects an anomaly exceeding the normal range, it can then assign the appropriate technician and prepare consumables based on the results. This allows the user to minimize equipment downtime and operate efficiently.

[0274] An example of a prompt message might be, "Analyze the motor's vibration data, assess the risk of failure, and generate an optimal maintenance schedule." In this way, the system of the present invention contributes to the optimization of equipment operation in manufacturing sites.

[0275] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0276] Step 1:

[0277] The server receives operation information from the sensors in real time. The inputs here are physical quantities such as temperature, vibration, and pressure. As a specific operation, the sensors send data to the server at regular intervals, and the server accumulates this in the database.

[0278] Step 2:

[0279] The server inputs the collected operation information into a machine learning model to predict anomalies. The inputs include the operation information obtained by the sensors. As data processing, time series analysis is performed to detect abnormal patterns. As a specific operation, data analysis is carried out using Python libraries to calculate the possibility of anomalies.

[0280] Step 3:

[0281] The server uses a generative AI model to create an optimal maintenance schedule. The input for this step is the result of the anomaly prediction. The output is a schedule that includes the specific maintenance timing and necessary work procedures. As a specific operation, the server generates a schedule based on the analysis results and notifies the terminal.

[0282] Step 4:

[0283] The server continues to monitor the status of the equipment and immediately sends an alert to the user's terminal when an anomaly is detected. The input is various sensor data obtained in real time, and the output is an alert notification. As a specific operation, when the threshold is exceeded, the server sends an alert email or notification.

[0284] Step 5:

[0285] The server optimizes the inventory based on the demand prediction of consumables. The input for this step is the past usage data and the current anomaly prediction. The output is an optimal parts inventory list. As a specific operation, a demand prediction algorithm is used to calculate the number of parts required in the future and plan inventory replenishment.

[0286] Step 6:

[0287] The server assigns the optimal operator based on the skills of the technicians and their available schedules. The input for this step is the ability information of the technicians and the maintenance schedule. The output is a list of the assigned technicians. As a specific operation, an optimal technician is selected and the assignment is determined using a skill matching algorithm.

[0288] (Application Example 1)

[0289] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0290] In modern manufacturing equipment, efficient maintenance and rapid fault response are required. However, in existing systems, it is difficult to detect signs of failure early, quickly dispatch appropriate technicians, and ensure the preparation of necessary parts, resulting in a problem of reduced equipment operation rate. The purpose of the present invention is to solve these problems and achieve efficient operation and maintenance of equipment.

[0291] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following respective means.

[0292] In this invention, the server includes an information acquisition means, a prediction processing means, a plan formulation means, a monitoring means, a stockpiling management means, a technician adjustment means, an abnormality notification means, and an information providing means. Thereby, signs of failure in the equipment can be detected early, maintenance at an appropriate timing and rapid fault response become possible. Thereby, the operation rate of the equipment can be improved and the cost efficiency can be enhanced.

[0293] The "information acquisition means" is a function for collecting data from various sensors installed in the equipment and storing it.

[0294] The "predictive processing means" is a function that analyzes collected data and uses machine learning algorithms to predict equipment failures.

[0295] The "planning mechanism" is a function that creates an optimal maintenance schedule based on predicted analysis results.

[0296] A "monitoring system" is a function that monitors the real-time status of equipment and immediately detects any abnormalities.

[0297] "Stockpiling management measures" refer to functions that optimize the inventory of necessary parts based on demand forecasts and prevent stockouts.

[0298] "Engineer coordination means" refers to a function that manages engineers' skill information and schedules, and assigns the most suitable engineer to a task.

[0299] The "anomaly notification mechanism" is a function that analyzes the vibration data of the equipment and sends a notification to the user if an anomaly is detected.

[0300] "Information provision means" refers to a function that provides users with information on signs of malfunction and maintenance information through a mobile device application.

[0301] The system implementing this invention is an integrated platform combining various means to promote the efficient operation and maintenance of equipment. This system consists of sensors, servers, and mobile terminal applications.

[0302] First, data is collected from sensors installed on the equipment using information acquisition methods. This data is then transmitted to a server using communication technologies such as Bluetooth or Wi-Fi. The server is implemented using the Python language, and its backend is built using the Flask framework. This ensures that the data is reliably received and stored.

[0303] Next, the server uses prediction processing means to analyze data with a machine learning model such as TensorFlow and predict equipment failures. Through this process, signs of failure can be recognized in advance, enabling prompt response.

[0304] Then, the planning means creates an optimal maintenance schedule for the predicted failure. At the same time, the technician adjustment means utilizes the skill information of technicians to select the optimal technician and assign tasks.

[0305] Furthermore, the abnormality notification means analyzes the vibration data of the equipment and sends a notification to the user's mobile terminal in real time when an abnormal value is detected. At this time, a mobile terminal application using React Native provides a user interface and functions as an information providing means.

[0306] For example, when a certain manufacturing robot shows higher vibration than normal, the server immediately detects the abnormality and notifies the user of the need for maintenance. This notification includes an overview of the problem and the recommended maintenance time.

[0307] In this way, it is possible to maximize the operating efficiency of the equipment while performing necessary maintenance work quickly and efficiently. By using a prompt sentence such as "Please analyze the vibration data of the power generation equipment, detect abnormalities, and propose a maintenance schedule", the generative AI model can be utilized to further improve efficiency.

[0308] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0309] Step 1:

[0310] Sensors installed on the equipment collect real-time data such as vibration and temperature. This input data is transmitted to the server via Bluetooth. The server stores the received data in a database and filters the data as needed.

[0311] Step 2:

[0312] The server uses TensorFlow to analyze historical data stored in the database and newly collected data. This machine learning model recognizes data patterns and predicts the likelihood of failure as output. Based on these predictions, the user is notified of signs of failure.

[0313] Step 3:

[0314] The server generates a maintenance schedule using a planning mechanism based on the prediction results. Here, the prediction results and technician schedule information are used as input, and the optimal maintenance data is provided as output. The schedule is automatically updated by the technician coordination mechanism.

[0315] Step 4:

[0316] The server uses an anomaly notification mechanism to inform the user of the generated schedule and predicted anomalies. An alert is displayed on the user's mobile device through a React Native application, clearly indicating the type of anomaly and recommended actions.

[0317] Step 5:

[0318] Users can use a mobile app to check maintenance details and communicate necessary work instructions to technicians. This allows for early problem resolution and efficient equipment operation.

[0319] In this way, a smooth flow of information can be achieved between servers and terminals, optimizing equipment operation and maintenance, and further efficiency can be achieved.

[0320] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0321] This invention aims to further improve efficiency and optimization by incorporating an emotion engine into an equipment maintenance optimization system, taking into account the user's emotional state. First, a terminal collects data from sensors attached to the equipment and transmits it to a server. The server analyzes the data and uses a machine learning algorithm to predict failures. Based on these results, the server generates an optimal maintenance schedule and notifies the user.

[0322] Furthermore, the emotion engine analyzes the user's voice and facial expressions. This allows it to acquire emotional data to perform maintenance tasks at the optimal time based on the user's work efficiency and concentration level. The server takes this emotional data into account and dynamically adjusts the schedule to provide the user with the best possible work environment.

[0323] For example, if a technician is burdened with many high-load tasks, the emotion engine can detect the technician's fatigue and stress. Based on this information, the work schedule can be readjusted to reduce the user's burden. Furthermore, if the user is feeling anxious about a particular maintenance task, the emotion engine can assist in providing learning modules and support functions to address that anxiety.

[0324] Therefore, this system enables efficient equipment maintenance while allowing for flexible responses based on user sentiment, resulting in improved overall operational efficiency and reduced maintenance costs.

[0325] The following describes the processing flow.

[0326] Step 1:

[0327] The terminal continuously collects environmental data from sensors attached to the equipment and periodically transmits it to the server.

[0328] Step 2:

[0329] The server stores the received environmental data in a database and performs data preprocessing. This includes noise reduction and filtering outliers.

[0330] Step 3:

[0331] The server uses machine learning algorithms to analyze data to estimate the likelihood of failure. This analysis is then used to update the failure risk assessment.

[0332] Step 4:

[0333] The server generates an optimal maintenance schedule based on failure predictions and notifies the user's terminal of the schedule. The user can review this and make adjustments as needed.

[0334] Step 5:

[0335] The device's built-in emotion engine analyzes the user's voice and facial expressions, extracting emotional information in real time. Based on this information, the system evaluates the user's concentration level and stress level.

[0336] Step 6:

[0337] The server retrieves information from the emotion engine and readjusts the maintenance schedule to take the user's psychological state into account. If necessary, it distributes the workload and optimizes the allocation of technicians.

[0338] Step 7:

[0339] The server uses its inventory management function to predict the demand for necessary parts and creates an ordering plan to optimize parts supply.

[0340] Step 8:

[0341] Users receive work instructions via their devices and carry out equipment maintenance and repairs according to plan. It's also possible to leverage emotional data to provide appropriate support and educational resources.

[0342] This series of processes allows the system to support the efficient operation of equipment and provide flexible maintenance plans that take into account the user's emotions and psychological factors.

[0343] (Example 2)

[0344] Next, we will describe Example 2. 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".

[0345] Conventional equipment maintenance systems primarily focused on predicting equipment failures and optimizing maintenance schedules. However, they failed to consider factors such as workers' emotional states and fluctuations in work efficiency, potentially leading to increased worker burden and decreased equipment utilization. Furthermore, despite the possibility of advanced analysis using machine learning algorithms, it was difficult to utilize the results to adjust the work environment in real time.

[0346] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0347] In this invention, the server includes information gathering means, predictive analysis means, plan generation means, monitoring means, resource management means, worker management means, and emotion analysis means. This enables real-time analysis of workers' emotional states and the generation of an optimal maintenance plan linked to equipment failure prediction results, as well as adjustment of the work environment.

[0348] "Information gathering means" refers to a device or method that has the function of collecting data from various sensors installed in the facility and transmitting it to a server.

[0349] A "predictive analysis means" is a device or method that uses a machine learning algorithm to predict equipment failures based on collected information.

[0350] "Plan generation means" refers to a device or method that generates an optimal maintenance work plan based on the results of failure prediction.

[0351] "Monitoring means" refers to a device or method that has the function of continuously monitoring the instantaneous state of equipment and detecting abnormalities.

[0352] "Resource management means" refers to a device or method that optimizes the inventory of parts and materials based on demand forecasts and supplies the appropriate resources when needed.

[0353] "Worker management means" refers to a device or method for managing information about workers' skills and experience and for assigning the most suitable personnel to the appropriate tasks.

[0354] "Emotional analysis means" refers to a device or method that analyzes a worker's emotional state from their voice and facial expressions and uses the results to adjust the work environment.

[0355] This invention is a system for optimizing equipment maintenance, and by organically linking multiple functions, it realizes the generation of maintenance schedules that take into account equipment failure prediction and the emotional state of workers.

[0356] First, the terminal collects data in real time from sensors attached to the equipment (e.g., temperature sensors, vibration sensors, pressure sensors) and sends that data to the server. These sensors use standard IoT protocols as their communication protocol.

[0357] The server stores received data in a database and performs data formatting and analysis using Python, R, and other tools. Machine learning algorithms such as TensorFlow and scikit-learn are used to predict equipment failures. Based on the failure prediction results, maintenance plans are formulated using linear programming and heuristic methods.

[0358] Furthermore, a terminal or dedicated device collects the worker's voice and facial expressions, which are then analyzed by an emotion analysis engine. This analysis utilizes services such as Microsoft Azure Face API. The obtained emotion data is integrated on a server and fed back into the maintenance plan.

[0359] For example, if an engineer is overworked and stressed, the emotion engine can detect this and readjust the maintenance schedule to reduce the engineer's burden. Furthermore, if it detects anxiety about a specific task, it can support the engineer by providing a learning module.

[0360] Examples of prompts for the generating AI model include instructions such as, "Consider the following user emotional state and generate the optimal maintenance schedule," or "Based on the failure prediction results, suggest a corresponding work schedule."

[0361] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0362] Step 1:

[0363] The terminal collects data from the equipment's sensors. The inputs are sensor data such as temperature, vibration, and pressure. The terminal collects this data in real time and performs an initial check for any abnormal values. Data that does not show any abnormalities is sent to the server in batch processing.

[0364] Step 2:

[0365] The server stores the received sensor data in a database. The input is sensor data sent from the terminal. The server formats this data and stores it in a database (e.g., PostgreSQL). The data is converted to an appropriate format for subsequent analysis.

[0366] Step 3:

[0367] The server analyzes stored data to predict failures. The input is sensor data stored in a database. The server uses Python and TensorFlow to analyze the data with machine learning algorithms. This process predicts the risk of equipment failure, and the result is output as numerical data.

[0368] Step 4:

[0369] The server generates a maintenance plan based on the failure prediction results. The input is the failure prediction result data. The server uses linear programming to formulate the optimal maintenance schedule. The created plan is output as schedule data and notified to the user.

[0370] Step 5:

[0371] A terminal or dedicated device collects and analyzes the user's emotional data. The input is audio or video data. The terminal uses a microphone and camera to collect this data and sends it to an emotional analysis engine. The emotional analysis engine analyzes the collected data and outputs the user's emotional state.

[0372] Step 6:

[0373] The server adjusts the maintenance schedule based on emotional data. The input is emotional state data from the emotional analysis engine. The server combines the current schedule with the emotional data to make necessary schedule adjustments to optimize the work environment. The adjusted schedule is then re-notified to the user's terminal.

[0374] (Application Example 2)

[0375] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0376] In equipment maintenance, it has been difficult to enable efficient and optimal responses to anticipated failures while also flexibly adjusting work processes to take into account the emotional state of the workers. Therefore, improvements are needed to increase equipment utilization and reduce maintenance costs.

[0377] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0378] In this invention, the server includes information acquisition means, predictive analysis means, scheduling means, monitoring means, inventory management means, personnel management means, and sentiment analysis means. This allows for real-time monitoring of equipment status, the creation of optimal maintenance plans based on failure predictions, and adjustments to suit the emotional state of workers.

[0379] "Information acquisition means" refers to devices or technologies that have the function of collecting various types of data from equipment and appropriately storing or transferring them.

[0380] "Predictive analytics" refers to technologies that use collected data and machine learning algorithms to predict the probability and timing of equipment failures.

[0381] "Scheduling methods" refer to technologies for creating schedules to carry out maintenance work in the most efficient and effective manner, based on predictive analysis results.

[0382] "Monitoring methods" refer to technologies for checking the real-time status of equipment and issuing notifications or alarms as needed.

[0383] "Inventory management methods" are technologies that optimize the inventory of necessary parts and materials based on demand forecasts, and replenish or place orders at the appropriate time.

[0384] "Personnel management methods" refer to technologies for managing information about engineers' skills and experience, and for flexibly assigning the right personnel to the necessary tasks.

[0385] "Emotional analysis methods" are technologies that analyze emotional data such as workers' voices and facial expressions to provide approaches for improving work efficiency and safety.

[0386] The system that realizes this application example utilizes information acquisition means, predictive analysis means, scheduling means, monitoring means, inventory management means, personnel management means, and sentiment analysis means to streamline the maintenance of factory equipment.

[0387] The server stores equipment data collected from smart sensors using information acquisition methods. This allows for monitoring of equipment operation status and acquisition of necessary data in real time.

[0388] The server uses machine learning algorithms such as TensorFlow to predict equipment failures based on the acquired data. The predictive analysis means analyzes the equipment's operating data and identifies areas where failures are likely. In addition, smart glasses collect the worker's voice and facial expressions, and the emotion analysis means identifies the user's emotional state.

[0389] Based on the generated failure prediction and sentiment data, the server generates an optimal maintenance schedule and notifies the appropriate personnel through scheduling mechanisms. Furthermore, inventory management mechanisms efficiently manage necessary parts and supply them at the required time.

[0390] For example, if a robot in a factory exhibits abnormal behavior, predictive analysis identifies the malfunction as a problem, and a work schedule with reduced stress levels is generated, taking into account the feelings of the workers. The system automatically notifies the staff and initiates an optimized maintenance process.

[0391] An example of an input prompt for a generated AI model is: "Please report on a system that takes into account the user's emotional state to help optimize factory robot maintenance."

[0392] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0393] Step 1:

[0394] The terminal collects real-time data from smart sensors attached to the equipment. This data includes equipment parameters such as vibration, temperature, and current. By sending this data to a server, the basic information necessary for analysis is obtained.

[0395] Step 2:

[0396] The server receives the transmitted equipment data and performs data preprocessing. It cleans and normalizes the data to prepare it for analysis. Using the input equipment parameters, it removes outliers and outputs a standardized dataset.

[0397] Step 3:

[0398] The server uses the organized data to perform failure prediction through predictive analytics. Based on machine learning algorithms (e.g., TensorFlow), it identifies patterns indicating abnormal equipment behavior and evaluates the likelihood of future failures. It analyzes the patterns obtained from the input data and outputs failure prediction results.

[0399] Step 4:

[0400] The server generates an optimal maintenance schedule using scheduling methods based on predictive analytics results and user sentiment data. It creates a realistic work plan considering the workload of the workers. It outputs an efficient schedule proposal from the input failure predictions and sentiment data.

[0401] Step 5:

[0402] The device collects the worker's voice and facial expressions through smart glasses and evaluates their emotional state in real time using emotion analysis. This allows it to recognize the user's stress level, concentration level, etc., and reflect this in their schedule. Emotional results are output from the input audio and video data.

[0403] Step 6:

[0404] The server uses inventory management tools to forecast the demand for maintenance parts and implements an optimized inventory plan. This enables the supply of parts at the necessary time. Based on the input demand forecast data, it outputs the inventory allocation.

[0405] Step 7:

[0406] Users can input prompts into the generated AI model to obtain reports on system operating status and maintenance adjustments. This allows for a deeper understanding of the work process. The system outputs reports generated based on the prompts.

[0407] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0408] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0409] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0410] [Third Embodiment]

[0411] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0412] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0413] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0414] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0415] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0416] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0417] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0418] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0419] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0420] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0421] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0422] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0423] The maintenance optimization system according to the present invention is a comprehensive platform for achieving efficient management and maintenance of manufacturing equipment. This system begins by collecting data through sensors attached to various pieces of equipment and transmitting it to a server. The server stores this data in real time and predicts equipment failures by comparing it with past operating patterns.

[0424] Specifically, the server uses machine learning algorithms to analyze data and detect signs of failure. Based on these results, the server generates an optimal maintenance schedule and notifies the user. This makes it easier for the user to perform maintenance at the appropriate time.

[0425] Furthermore, the server monitors the equipment in real time and immediately sends an alert if an anomaly is detected. This allows users to address problems before they become apparent.

[0426] Furthermore, the server also handles inventory management, forecasting parts demand and optimizing inventory to prevent shortages of necessary parts. This ensures that users always have access to the parts they need, when they need them. The server also manages technicians' skills and availability, assigning them the most suitable tasks.

[0427] For example, if motor vibration data exceeds the normal range, the server will determine this is a sign of failure, automatically assign a suitable technician, and secure replacement parts from inventory. This allows the user to resolve the problem quickly and efficiently.

[0428] The following describes the processing flow.

[0429] Step 1:

[0430] The terminal collects data in real time from sensors attached to the equipment. This data includes information such as vibration, temperature, pressure, and power consumption, and is periodically transmitted to a server.

[0431] Step 2:

[0432] The server receives the collected data and stores it in the database. Data preprocessing is performed to detect outliers and impute missing data.

[0433] Step 3:

[0434] The server analyzes data using machine learning algorithms. It compares the current data to past data patterns to predict the likelihood of failure. This analysis is then used to assess future failure risks.

[0435] Step 4:

[0436] The server automatically generates a maintenance schedule based on failure predictions. This ensures that preventative maintenance plans proceed smoothly. The generated schedule is notified to the user's terminal.

[0437] Step 5:

[0438] The user reviews the proposed maintenance schedule. They can adjust or approve the schedule as needed. This enables efficient maintenance.

[0439] Step 6:

[0440] The terminal continues to monitor the equipment status in real time and immediately sends any new abnormalities detected to the server.

[0441] Step 7:

[0442] The server receives an anomaly notification and, if necessary, issues an alert to the user to take emergency response procedures.

[0443] Step 8:

[0444] The server manages inventory based on predicted component demand. It plans component orders in a timely manner to prevent inventory shortages.

[0445] Step 9:

[0446] The server manages technicians' skill data and availability, assigning the most suitable technician to maintenance tasks. Appropriate staffing levels improve work efficiency and output.

[0447] (Example 1)

[0448] Next, we will describe Example 1. 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."

[0449] Conventional equipment management systems face challenges in efficient equipment operation due to unexpected equipment failures and inappropriate maintenance timing. Furthermore, inadequate allocation of technicians and optimization of parts inventory can negatively impact equipment utilization rates.

[0450] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0451] In this invention, the server includes data acquisition means for collecting and storing operational information of the equipment, prediction means for predicting equipment abnormalities based on the operational information, and scheduling means for generating an optimal maintenance schedule using a generated AI model. This makes it possible to improve the operating rate of the equipment and enable efficient operation by predicting equipment failures in advance and performing appropriate maintenance.

[0452] "Equipment" is a general term for devices and equipment used in the manufacturing or production process.

[0453] "Operational information" refers to data such as temperature, vibration, and pressure collected when the equipment is in operation.

[0454] A "data acquisition method" is a system that collects and stores operational information from sensors installed on equipment.

[0455] A "predictive means" is a technology that predicts equipment malfunctions in advance based on collected operational information.

[0456] A "generative AI model" refers to artificial intelligence technology that analyzes large amounts of data and proposes optimal results and actions.

[0457] A "scheduling method" is a process for creating optimal work and maintenance schedules based on the results of a prediction method.

[0458] A "monitoring system" is a system that constantly checks the status of equipment and prompts immediate action when an abnormality occurs.

[0459] "Inventory of consumables" is a term that indicates the stockpiling status of replacement parts and materials necessary for the operation of equipment.

[0460] An "inventory control system" is a mechanism for properly managing the inventory of consumables and adjusting supply according to demand.

[0461] "Worker allocation methods" refer to the process of managing engineers' skills and availability, and assigning the most suitable engineers to the appropriate tasks.

[0462] The maintenance optimization system of the present invention streamlines equipment management and enables planned and timely maintenance. The main components of this system consist of data acquisition, forecasting, scheduling, monitoring, inventory control, and worker allocation.

[0463] The server first collects operational information using sensors attached to various pieces of equipment. These sensors send data such as temperature, vibration, and pressure to the server in real time, and this data is stored in a database. Specific hardware includes temperature sensors and vibration sensors. The server then analyzes this data and uses machine learning models, such as Python's scikit-learn or TensorFlow, to predict equipment anomalies. This allows for the provision of information to enable appropriate maintenance before equipment failures occur.

[0464] Furthermore, the server utilizes a generative AI model to create an optimal maintenance schedule. This allows users to perform planned maintenance at the appropriate time, improving equipment uptime. This schedule is notified to the user via their terminal.

[0465] The server, which also functions as a monitoring system, constantly checks the status of the equipment and sends alerts to terminals if any abnormalities are detected. This function allows users to address abnormalities in real time.

[0466] In inventory management, the server predicts demand based on past consumable usage data and implements appropriate controls to prevent shortages. This process ensures that users always have the necessary parts available when needed, allowing for smooth equipment maintenance.

[0467] Furthermore, regarding the management of technicians, the server considers skill information and availability to efficiently assign the most suitable technician to the relevant maintenance task. This information is also transmitted to the user's terminal to support maintenance planning and execution.

[0468] For example, if the server analyzes motor vibration data and detects an anomaly exceeding the normal range, it can then assign the appropriate technician and prepare consumables based on the results. This allows the user to minimize equipment downtime and operate efficiently.

[0469] An example of a prompt message might be, "Analyze the motor's vibration data, assess the risk of failure, and generate an optimal maintenance schedule." In this way, the system of the present invention contributes to the optimization of equipment operation in manufacturing sites.

[0470] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0471] Step 1:

[0472] The server receives operational information from the sensor in real time. The inputs here are physical quantities such as temperature, vibration, and pressure. Specifically, the sensor sends data to the server at regular intervals, and the server stores this data in a database.

[0473] Step 2:

[0474] The server inputs collected operational information into a machine learning model to predict anomalies. This input includes operational information acquired from sensors. Data processing involves time-series analysis to detect anomaly patterns. Specifically, it uses Python libraries to perform data analysis and calculate the probability of anomalies.

[0475] Step 3:

[0476] The server uses a generative AI model to create an optimal maintenance schedule. The input for this step is the result of anomaly prediction. The output is a schedule that includes specific maintenance timings and required work procedures. In practice, the server generates the schedule based on the analysis results and notifies the terminal.

[0477] Step 4:

[0478] The server continuously monitors the equipment status and immediately sends an alert to the user's terminal if an anomaly is detected. Inputs are real-time sensor data, and outputs are alert notifications. Specifically, when a threshold is exceeded, the server sends an alert email or notification.

[0479] Step 5:

[0480] The server optimizes inventory based on demand forecasts for consumables. The inputs for this step are historical usage data and current anomaly forecasts. The output is an optimal parts inventory list. Specifically, it uses a demand forecasting algorithm to calculate the number of parts needed in the future and plans inventory replenishment.

[0481] Step 6:

[0482] The server assigns the most suitable worker based on the technician's skills and availability. The inputs for this step are the technician's competence information and maintenance schedule. The output is a list of assigned technicians. Specifically, a skill matching algorithm is used to select the most suitable technician and determine their placement.

[0483] (Application Example 1)

[0484] Next, we will explain Application Example 1. In the following explanation, 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."

[0485] Modern manufacturing equipment demands efficient maintenance and rapid troubleshooting. However, existing systems struggle to detect signs of failure early, quickly dispatch appropriate technicians, and reliably prepare necessary parts, resulting in reduced equipment uptime. This invention aims to solve these problems and achieve efficient operation and maintenance of equipment.

[0486] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0487] In this invention, the server includes information acquisition means, predictive processing means, planning means, monitoring means, stock management means, engineer coordination means, anomaly notification means, and information provision means. This enables early detection of signs of equipment failure, allowing for timely maintenance and rapid fault response. This improves equipment utilization and increases cost efficiency.

[0488] "Information acquisition means" refers to a function for collecting and storing data from various sensors installed in the equipment.

[0489] The "predictive processing means" is a function that analyzes collected data and uses machine learning algorithms to predict equipment failures.

[0490] The "planning mechanism" is a function that creates an optimal maintenance schedule based on predicted analysis results.

[0491] A "monitoring system" is a function that monitors the real-time status of equipment and immediately detects any abnormalities.

[0492] "Stockpiling management measures" refer to functions that optimize the inventory of necessary parts based on demand forecasts and prevent stockouts.

[0493] "Engineer coordination means" refers to a function that manages engineers' skill information and schedules, and assigns the most suitable engineer to a task.

[0494] The "anomaly notification mechanism" is a function that analyzes the vibration data of the equipment and sends a notification to the user if an anomaly is detected.

[0495] "Information provision means" refers to a function that provides users with information on signs of malfunction and maintenance information through a mobile device application.

[0496] The system implementing this invention is an integrated platform combining various means to promote the efficient operation and maintenance of equipment. This system consists of sensors, servers, and mobile terminal applications.

[0497] First, data is collected from sensors installed on the equipment using information acquisition methods. This data is then transmitted to a server using communication technologies such as Bluetooth or Wi-Fi. The server is implemented using the Python language, and its backend is built using the Flask framework. This ensures that the data is reliably received and stored.

[0498] Next, the server uses a predictive processing mechanism to analyze the data with machine learning models such as TensorFlow and predict equipment failures. This process allows for the early detection of signs of failure, enabling a rapid response.

[0499] Then, using planning tools, an optimal maintenance schedule is created for predicted failures. In addition, using engineer coordination tools, the skill information of engineers is utilized to select the most suitable engineers and assign them tasks.

[0500] Furthermore, an anomaly notification system analyzes the equipment's vibration data and sends a real-time notification to the user's mobile device if an anomaly is detected. In this process, a mobile application using React Native provides the user interface and functions as an information delivery tool.

[0501] For example, if a manufacturing robot exhibits higher-than-normal vibrations, the server will immediately detect the anomaly and notify the user of the need for maintenance. This notification will include a summary of the problem and a recommended maintenance schedule.

[0502] In this way, it becomes possible to maximize the operating efficiency of the equipment while performing necessary maintenance work quickly and efficiently. Further efficiency can be achieved by utilizing a generative AI model, for example, by using prompts such as, "Analyze the vibration data of the power generation equipment, detect anomalies, and propose a maintenance schedule."

[0503] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0504] Step 1:

[0505] Sensors installed on the equipment collect real-time data such as vibration and temperature. This input data is transmitted to a server via Bluetooth. The server stores the received data in a database and filters the data as needed.

[0506] Step 2:

[0507] The server uses TensorFlow to analyze historical data stored in the database and newly collected data. This machine learning model recognizes data patterns and predicts the likelihood of failure as output. Based on these predictions, the user is notified of signs of failure.

[0508] Step 3:

[0509] The server generates a maintenance schedule using a planning mechanism based on the prediction results. Here, the prediction results and technician schedule information are used as input, and the optimal maintenance data is provided as output. The schedule is automatically updated by the technician coordination mechanism.

[0510] Step 4:

[0511] The server uses an anomaly notification mechanism to inform the user of the generated schedule and predicted anomalies. An alert is displayed on the user's mobile device through a React Native application, clearly indicating the type of anomaly and recommended actions.

[0512] Step 5:

[0513] Users can use a mobile app to check maintenance details and communicate necessary work instructions to technicians. This allows for early problem resolution and efficient equipment operation.

[0514] In this way, a smooth flow of information can be achieved between servers and terminals, optimizing equipment operation and maintenance, and further efficiency can be achieved.

[0515] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0516] This invention aims to further improve efficiency and optimization by incorporating an emotion engine into an equipment maintenance optimization system, taking into account the user's emotional state. First, a terminal collects data from sensors attached to the equipment and transmits it to a server. The server analyzes the data and uses a machine learning algorithm to predict failures. Based on these results, the server generates an optimal maintenance schedule and notifies the user.

[0517] Furthermore, the emotion engine analyzes the user's voice and facial expressions. This allows it to acquire emotional data to perform maintenance tasks at the optimal time based on the user's work efficiency and concentration level. The server takes this emotional data into account and dynamically adjusts the schedule to provide the user with the best possible work environment.

[0518] For example, if a technician is burdened with many high-load tasks, the emotion engine can detect the technician's fatigue and stress. Based on this information, the work schedule can be readjusted to reduce the user's burden. Furthermore, if the user is feeling anxious about a particular maintenance task, the emotion engine can assist in providing learning modules and support functions to address that anxiety.

[0519] Therefore, this system enables efficient equipment maintenance while allowing for flexible responses based on user sentiment, resulting in improved overall operational efficiency and reduced maintenance costs.

[0520] The following describes the processing flow.

[0521] Step 1:

[0522] The terminal continuously collects environmental data from sensors attached to the equipment and periodically transmits it to the server.

[0523] Step 2:

[0524] The server stores the received environmental data in a database and performs data preprocessing. This includes noise reduction and filtering outliers.

[0525] Step 3:

[0526] The server uses machine learning algorithms to analyze data to estimate the likelihood of failure. This analysis is then used to update the failure risk assessment.

[0527] Step 4:

[0528] The server generates an optimal maintenance schedule based on failure predictions and notifies the user's terminal of the schedule. The user can review this and make adjustments as needed.

[0529] Step 5:

[0530] The device's built-in emotion engine analyzes the user's voice and facial expressions, extracting emotional information in real time. Based on this information, the system evaluates the user's concentration level and stress level.

[0531] Step 6:

[0532] The server retrieves information from the emotion engine and readjusts the maintenance schedule to take the user's psychological state into account. If necessary, it distributes the workload and optimizes the allocation of technicians.

[0533] Step 7:

[0534] The server uses its inventory management function to predict the demand for necessary parts and creates an ordering plan to optimize parts supply.

[0535] Step 8:

[0536] Users receive work instructions via their devices and carry out equipment maintenance and repairs according to plan. It's also possible to leverage emotional data to provide appropriate support and educational resources.

[0537] This series of processes allows the system to support the efficient operation of equipment and provide flexible maintenance plans that take into account the user's emotions and psychological factors.

[0538] (Example 2)

[0539] Next, we will describe Example 2. 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."

[0540] Conventional equipment maintenance systems primarily focused on predicting equipment failures and optimizing maintenance schedules. However, they failed to consider factors such as workers' emotional states and fluctuations in work efficiency, potentially leading to increased worker burden and decreased equipment utilization. Furthermore, despite the possibility of advanced analysis using machine learning algorithms, it was difficult to utilize the results to adjust the work environment in real time.

[0541] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0542] In this invention, the server includes information gathering means, predictive analysis means, plan generation means, monitoring means, resource management means, worker management means, and emotion analysis means. This enables real-time analysis of workers' emotional states and the generation of an optimal maintenance plan linked to equipment failure prediction results, as well as adjustment of the work environment.

[0543] "Information gathering means" refers to a device or method that has the function of collecting data from various sensors installed in the facility and transmitting it to a server.

[0544] A "predictive analysis means" is a device or method that uses a machine learning algorithm to predict equipment failures based on collected information.

[0545] "Plan generation means" refers to a device or method that generates an optimal maintenance work plan based on the results of failure prediction.

[0546] "Monitoring means" refers to a device or method that has the function of continuously monitoring the instantaneous state of equipment and detecting abnormalities.

[0547] "Resource management means" refers to a device or method that optimizes the inventory of parts and materials based on demand forecasts and supplies the appropriate resources when needed.

[0548] "Worker management means" refers to a device or method for managing information about workers' skills and experience and for assigning the most suitable personnel to the appropriate tasks.

[0549] "Emotional analysis means" refers to a device or method that analyzes a worker's emotional state from their voice and facial expressions and uses the results to adjust the work environment.

[0550] This invention is a system for optimizing equipment maintenance, and by organically linking multiple functions, it realizes the generation of maintenance schedules that take into account equipment failure prediction and the emotional state of workers.

[0551] First, the terminal collects data in real time from sensors attached to the equipment (e.g., temperature sensors, vibration sensors, pressure sensors) and sends that data to the server. These sensors use standard IoT protocols as their communication protocol.

[0552] The server stores received data in a database and performs data formatting and analysis using Python, R, and other tools. Machine learning algorithms such as TensorFlow and scikit-learn are used to predict equipment failures. Based on the failure prediction results, maintenance plans are formulated using linear programming and heuristic methods.

[0553] Furthermore, a terminal or dedicated device collects the worker's voice and facial expressions, which are then analyzed by an emotion analysis engine. This analysis utilizes services such as Microsoft Azure Face API. The obtained emotion data is integrated on a server and fed back into the maintenance plan.

[0554] For example, if an engineer is overworked and stressed, the emotion engine can detect this and readjust the maintenance schedule to reduce the engineer's burden. Furthermore, if it detects anxiety about a specific task, it can support the engineer by providing a learning module.

[0555] Examples of prompts for the generating AI model include instructions such as, "Consider the following user emotional state and generate the optimal maintenance schedule," or "Based on the failure prediction results, suggest a corresponding work schedule."

[0556] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0557] Step 1:

[0558] The terminal collects data from the equipment's sensors. The inputs are sensor data such as temperature, vibration, and pressure. The terminal collects this data in real time and performs an initial check for any abnormal values. Data that does not show any abnormalities is sent to the server in batch processing.

[0559] Step 2:

[0560] The server stores the received sensor data in a database. The input is sensor data sent from the terminal. The server formats this data and stores it in a database (e.g., PostgreSQL). The data is converted to an appropriate format for subsequent analysis.

[0561] Step 3:

[0562] The server analyzes stored data to predict failures. The input is sensor data stored in a database. The server uses Python and TensorFlow to analyze the data with machine learning algorithms. This process predicts the risk of equipment failure, and the result is output as numerical data.

[0563] Step 4:

[0564] The server generates a maintenance plan based on the failure prediction results. The input is the failure prediction result data. The server uses linear programming to formulate the optimal maintenance schedule. The created plan is output as schedule data and notified to the user.

[0565] Step 5:

[0566] A terminal or dedicated device collects and analyzes the user's emotional data. The input is audio or video data. The terminal uses a microphone and camera to collect this data and sends it to an emotional analysis engine. The emotional analysis engine analyzes the collected data and outputs the user's emotional state.

[0567] Step 6:

[0568] The server adjusts the maintenance schedule based on emotional data. The input is emotional state data from the emotional analysis engine. The server combines the current schedule with the emotional data to make necessary schedule adjustments to optimize the work environment. The adjusted schedule is then re-notified to the user's terminal.

[0569] (Application Example 2)

[0570] Next, we will explain application example 2. In the following explanation, 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."

[0571] In equipment maintenance, it has been difficult to enable efficient and optimal responses to anticipated failures while also flexibly adjusting work processes to take into account the emotional state of the workers. Therefore, improvements are needed to increase equipment utilization and reduce maintenance costs.

[0572] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0573] In this invention, the server includes information acquisition means, predictive analysis means, scheduling means, monitoring means, inventory management means, personnel management means, and sentiment analysis means. This allows for real-time monitoring of equipment status, the creation of optimal maintenance plans based on failure predictions, and adjustments to suit the emotional state of workers.

[0574] "Information acquisition means" refers to devices or technologies that have the function of collecting various types of data from equipment and appropriately storing or transferring them.

[0575] "Predictive analytics" refers to technologies that use collected data and machine learning algorithms to predict the probability and timing of equipment failures.

[0576] "Scheduling methods" refer to technologies for creating schedules to carry out maintenance work in the most efficient and effective manner, based on predictive analysis results.

[0577] "Monitoring methods" refer to technologies for checking the real-time status of equipment and issuing notifications or alarms as needed.

[0578] "Inventory management methods" are technologies that optimize the inventory of necessary parts and materials based on demand forecasts, and replenish or place orders at the appropriate time.

[0579] "Personnel management methods" refer to technologies for managing information about engineers' skills and experience, and for flexibly assigning the right personnel to the necessary tasks.

[0580] "Emotional analysis methods" are technologies that analyze emotional data such as workers' voices and facial expressions to provide approaches for improving work efficiency and safety.

[0581] The system that realizes this application example utilizes information acquisition means, predictive analysis means, scheduling means, monitoring means, inventory management means, personnel management means, and sentiment analysis means to streamline the maintenance of factory equipment.

[0582] The server stores equipment data collected from smart sensors using information acquisition methods. This allows for monitoring of equipment operation status and acquisition of necessary data in real time.

[0583] The server uses machine learning algorithms such as TensorFlow to predict equipment failures based on the acquired data. The predictive analysis means analyzes the equipment's operating data and identifies areas where failures are likely. In addition, smart glasses collect the worker's voice and facial expressions, and the emotion analysis means identifies the user's emotional state.

[0584] Based on the generated failure prediction and sentiment data, the server generates an optimal maintenance schedule and notifies the appropriate personnel through scheduling mechanisms. Furthermore, inventory management mechanisms efficiently manage necessary parts and supply them at the required time.

[0585] For example, if a robot in a factory exhibits abnormal behavior, predictive analysis identifies the malfunction as a problem, and a work schedule with reduced stress levels is generated, taking into account the feelings of the workers. The system automatically notifies the staff and initiates an optimized maintenance process.

[0586] An example of an input prompt for a generated AI model is: "Please report on a system that takes into account the user's emotional state to help optimize factory robot maintenance."

[0587] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0588] Step 1:

[0589] The terminal collects real-time data from smart sensors attached to the equipment. This data includes equipment parameters such as vibration, temperature, and current. By sending this data to a server, the basic information necessary for analysis is obtained.

[0590] Step 2:

[0591] The server receives the transmitted equipment data and performs data preprocessing. It cleans and normalizes the data to prepare it for analysis. Using the input equipment parameters, it removes outliers and outputs a standardized dataset.

[0592] Step 3:

[0593] The server uses the organized data to perform failure prediction through predictive analytics. Based on machine learning algorithms (e.g., TensorFlow), it identifies patterns indicating abnormal equipment behavior and evaluates the likelihood of future failures. It analyzes the patterns obtained from the input data and outputs failure prediction results.

[0594] Step 4:

[0595] The server generates an optimal maintenance schedule using scheduling methods based on predictive analytics results and user sentiment data. It creates a realistic work plan considering the workload of the workers. It outputs an efficient schedule proposal from the input failure predictions and sentiment data.

[0596] Step 5:

[0597] The device collects the worker's voice and facial expressions through smart glasses and evaluates their emotional state in real time using emotion analysis. This allows it to recognize the user's stress level, concentration level, etc., and reflect this in their schedule. Emotional results are output from the input audio and video data.

[0598] Step 6:

[0599] The server uses inventory management tools to forecast the demand for maintenance parts and implements an optimized inventory plan. This enables the supply of parts at the necessary time. Based on the input demand forecast data, it outputs the inventory allocation.

[0600] Step 7:

[0601] Users can input prompts into the generated AI model to obtain reports on system operating status and maintenance adjustments. This allows for a deeper understanding of the work process. The system outputs reports generated based on the prompts.

[0602] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0603] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0604] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0605] [Fourth Embodiment]

[0606] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0607] As shown in Figure 7, the 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.

[0608] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0609] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0610] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0611] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0612] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0613] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0614] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0615] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0616] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0617] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0618] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0619] The maintenance optimization system according to the present invention is a comprehensive platform for achieving efficient management and maintenance of manufacturing equipment. This system begins by collecting data through sensors attached to various pieces of equipment and transmitting it to a server. The server stores this data in real time and predicts equipment failures by comparing it with past operating patterns.

[0620] Specifically, the server uses machine learning algorithms to analyze data and detect signs of failure. Based on these results, the server generates an optimal maintenance schedule and notifies the user. This makes it easier for the user to perform maintenance at the appropriate time.

[0621] Furthermore, the server monitors the equipment in real time and immediately sends an alert if an anomaly is detected. This allows users to address problems before they become apparent.

[0622] Furthermore, the server also handles inventory management, forecasting parts demand and optimizing inventory to prevent shortages of necessary parts. This ensures that users always have access to the parts they need, when they need them. The server also manages technicians' skills and availability, assigning them the most suitable tasks.

[0623] For example, if motor vibration data exceeds the normal range, the server will determine this is a sign of failure, automatically assign a suitable technician, and secure replacement parts from inventory. This allows the user to resolve the problem quickly and efficiently.

[0624] The following describes the processing flow.

[0625] Step 1:

[0626] The terminal collects data in real time from sensors attached to the equipment. This data includes information such as vibration, temperature, pressure, and power consumption, and is periodically transmitted to a server.

[0627] Step 2:

[0628] The server receives the collected data and stores it in the database. Data preprocessing is performed to detect outliers and impute missing data.

[0629] Step 3:

[0630] The server analyzes data using machine learning algorithms. It compares the current data to past data patterns to predict the likelihood of failure. This analysis is then used to assess future failure risks.

[0631] Step 4:

[0632] The server automatically generates a maintenance schedule based on failure predictions. This ensures that preventative maintenance plans proceed smoothly. The generated schedule is notified to the user's terminal.

[0633] Step 5:

[0634] The user reviews the proposed maintenance schedule. They can adjust or approve the schedule as needed. This enables efficient maintenance.

[0635] Step 6:

[0636] The terminal continues to monitor the equipment status in real time and immediately sends any new abnormalities detected to the server.

[0637] Step 7:

[0638] The server receives an anomaly notification and, if necessary, issues an alert to the user to take emergency response procedures.

[0639] Step 8:

[0640] The server manages inventory based on predicted component demand. It plans component orders in a timely manner to prevent inventory shortages.

[0641] Step 9:

[0642] The server manages technicians' skill data and availability, assigning the most suitable technician to maintenance tasks. Appropriate staffing levels improve work efficiency and output.

[0643] (Example 1)

[0644] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0645] Conventional equipment management systems face challenges in efficient equipment operation due to unexpected equipment failures and inappropriate maintenance timing. Furthermore, inadequate allocation of technicians and optimization of parts inventory can negatively impact equipment utilization rates.

[0646] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0647] In this invention, the server includes data acquisition means for collecting and storing operational information of the equipment, prediction means for predicting equipment abnormalities based on the operational information, and scheduling means for generating an optimal maintenance schedule using a generated AI model. This makes it possible to improve the operating rate of the equipment and enable efficient operation by predicting equipment failures in advance and performing appropriate maintenance.

[0648] "Equipment" is a general term for devices and equipment used in the manufacturing or production process.

[0649] "Operational information" refers to data such as temperature, vibration, and pressure collected when the equipment is in operation.

[0650] A "data acquisition method" is a system that collects and stores operational information from sensors installed on equipment.

[0651] A "predictive means" is a technology that predicts equipment malfunctions in advance based on collected operational information.

[0652] A "generative AI model" refers to artificial intelligence technology that analyzes large amounts of data and proposes optimal results and actions.

[0653] A "scheduling method" is a process for creating optimal work and maintenance schedules based on the results of a prediction method.

[0654] A "monitoring system" is a system that constantly checks the status of equipment and prompts immediate action when an abnormality occurs.

[0655] "Inventory of consumables" is a term that indicates the stockpiling status of replacement parts and materials necessary for the operation of equipment.

[0656] An "inventory control system" is a mechanism for properly managing the inventory of consumables and adjusting supply according to demand.

[0657] "Worker allocation methods" refer to the process of managing engineers' skills and availability, and assigning the most suitable engineers to the appropriate tasks.

[0658] The maintenance optimization system of the present invention streamlines equipment management and enables planned and timely maintenance. The main components of this system consist of data acquisition, forecasting, scheduling, monitoring, inventory control, and worker allocation.

[0659] The server first collects operational information using sensors attached to various pieces of equipment. These sensors send data such as temperature, vibration, and pressure to the server in real time, and this data is stored in a database. Specific hardware includes temperature sensors and vibration sensors. The server then analyzes this data and uses machine learning models, such as Python's scikit-learn or TensorFlow, to predict equipment anomalies. This allows for the provision of information to enable appropriate maintenance before equipment failures occur.

[0660] Furthermore, the server utilizes a generative AI model to create an optimal maintenance schedule. This allows users to perform planned maintenance at the appropriate time, improving equipment uptime. This schedule is notified to the user via their terminal.

[0661] The server, which also functions as a monitoring system, constantly checks the status of the equipment and sends alerts to terminals if any abnormalities are detected. This function allows users to address abnormalities in real time.

[0662] In inventory management, the server predicts demand based on past consumable usage data and implements appropriate controls to prevent shortages. This process ensures that users always have the necessary parts available when needed, allowing for smooth equipment maintenance.

[0663] Furthermore, regarding the management of technicians, the server considers skill information and availability to efficiently assign the most suitable technician to the relevant maintenance task. This information is also transmitted to the user's terminal to support maintenance planning and execution.

[0664] For example, if the server analyzes motor vibration data and detects an anomaly exceeding the normal range, it can then assign the appropriate technician and prepare consumables based on the results. This allows the user to minimize equipment downtime and operate efficiently.

[0665] An example of a prompt message might be, "Analyze the motor's vibration data, assess the risk of failure, and generate an optimal maintenance schedule." In this way, the system of the present invention contributes to the optimization of equipment operation in manufacturing sites.

[0666] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0667] Step 1:

[0668] The server receives operational information from the sensor in real time. The inputs here are physical quantities such as temperature, vibration, and pressure. Specifically, the sensor sends data to the server at regular intervals, and the server stores this data in a database.

[0669] Step 2:

[0670] The server inputs collected operational information into a machine learning model to predict anomalies. This input includes operational information acquired from sensors. Data processing involves time-series analysis to detect anomaly patterns. Specifically, it uses Python libraries to perform data analysis and calculate the probability of anomalies.

[0671] Step 3:

[0672] The server uses a generative AI model to create an optimal maintenance schedule. The input for this step is the result of anomaly prediction. The output is a schedule that includes specific maintenance timings and required work procedures. In practice, the server generates the schedule based on the analysis results and notifies the terminal.

[0673] Step 4:

[0674] The server continuously monitors the equipment status and immediately sends an alert to the user's terminal if an anomaly is detected. Inputs are real-time sensor data, and outputs are alert notifications. Specifically, when a threshold is exceeded, the server sends an alert email or notification.

[0675] Step 5:

[0676] The server optimizes inventory based on demand forecasts for consumables. The inputs for this step are historical usage data and current anomaly forecasts. The output is an optimal parts inventory list. Specifically, it uses a demand forecasting algorithm to calculate the number of parts needed in the future and plans inventory replenishment.

[0677] Step 6:

[0678] The server assigns the most suitable worker based on the technician's skills and availability. The inputs for this step are the technician's competence information and maintenance schedule. The output is a list of assigned technicians. Specifically, a skill matching algorithm is used to select the most suitable technician and determine their placement.

[0679] (Application Example 1)

[0680] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0681] Modern manufacturing equipment demands efficient maintenance and rapid troubleshooting. However, existing systems struggle to detect signs of failure early, quickly dispatch appropriate technicians, and reliably prepare necessary parts, resulting in reduced equipment uptime. This invention aims to solve these problems and achieve efficient operation and maintenance of equipment.

[0682] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0683] In this invention, the server includes information acquisition means, predictive processing means, planning means, monitoring means, stock management means, engineer coordination means, anomaly notification means, and information provision means. This enables early detection of signs of equipment failure, allowing for timely maintenance and rapid fault response. This improves equipment utilization and increases cost efficiency.

[0684] "Information acquisition means" refers to a function for collecting and storing data from various sensors installed in the equipment.

[0685] The "predictive processing means" is a function that analyzes collected data and uses machine learning algorithms to predict equipment failures.

[0686] The "planning mechanism" is a function that creates an optimal maintenance schedule based on predicted analysis results.

[0687] A "monitoring system" is a function that monitors the real-time status of equipment and immediately detects any abnormalities.

[0688] "Stockpiling management measures" refer to functions that optimize the inventory of necessary parts based on demand forecasts and prevent stockouts.

[0689] "Engineer coordination means" refers to a function that manages engineers' skill information and schedules, and assigns the most suitable engineer to a task.

[0690] The "anomaly notification mechanism" is a function that analyzes the vibration data of the equipment and sends a notification to the user if an anomaly is detected.

[0691] "Information provision means" refers to a function that provides users with information on signs of malfunction and maintenance information through a mobile device application.

[0692] The system implementing this invention is an integrated platform combining various means to promote the efficient operation and maintenance of equipment. This system consists of sensors, servers, and mobile terminal applications.

[0693] First, data is collected from sensors installed on the equipment using information acquisition methods. This data is then transmitted to a server using communication technologies such as Bluetooth or Wi-Fi. The server is implemented using the Python language, and its backend is built using the Flask framework. This ensures that the data is reliably received and stored.

[0694] Next, the server uses a predictive processing mechanism to analyze the data with machine learning models such as TensorFlow and predict equipment failures. This process allows for the early detection of signs of failure, enabling a rapid response.

[0695] Then, using planning tools, an optimal maintenance schedule is created for predicted failures. In addition, using engineer coordination tools, the skill information of engineers is utilized to select the most suitable engineers and assign them tasks.

[0696] Furthermore, an anomaly notification system analyzes the equipment's vibration data and sends a real-time notification to the user's mobile device if an anomaly is detected. In this process, a mobile application using React Native provides the user interface and functions as an information delivery tool.

[0697] For example, if a manufacturing robot exhibits higher-than-normal vibrations, the server will immediately detect the anomaly and notify the user of the need for maintenance. This notification will include a summary of the problem and a recommended maintenance schedule.

[0698] In this way, it becomes possible to maximize the operating efficiency of the equipment while performing necessary maintenance work quickly and efficiently. Further efficiency can be achieved by utilizing a generative AI model, for example, by using prompts such as, "Analyze the vibration data of the power generation equipment, detect anomalies, and propose a maintenance schedule."

[0699] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0700] Step 1:

[0701] Sensors installed on the equipment collect real-time data such as vibration and temperature. This input data is transmitted to a server via Bluetooth. The server stores the received data in a database and filters the data as needed.

[0702] Step 2:

[0703] The server uses TensorFlow to analyze historical data stored in the database and newly collected data. This machine learning model recognizes data patterns and predicts the likelihood of failure as output. Based on these predictions, the user is notified of signs of failure.

[0704] Step 3:

[0705] The server generates a maintenance schedule using a planning mechanism based on the prediction results. Here, the prediction results and technician schedule information are used as input, and the optimal maintenance data is provided as output. The schedule is automatically updated by the technician coordination mechanism.

[0706] Step 4:

[0707] The server uses an anomaly notification mechanism to inform the user of the generated schedule and predicted anomalies. An alert is displayed on the user's mobile device through a React Native application, clearly indicating the type of anomaly and recommended actions.

[0708] Step 5:

[0709] Users can use a mobile app to check maintenance details and communicate necessary work instructions to technicians. This allows for early problem resolution and efficient equipment operation.

[0710] In this way, a smooth flow of information can be achieved between servers and terminals, optimizing equipment operation and maintenance, and further efficiency can be achieved.

[0711] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0712] This invention aims to further improve efficiency and optimization by incorporating an emotion engine into an equipment maintenance optimization system, taking into account the user's emotional state. First, a terminal collects data from sensors attached to the equipment and transmits it to a server. The server analyzes the data and uses a machine learning algorithm to predict failures. Based on these results, the server generates an optimal maintenance schedule and notifies the user.

[0713] Furthermore, the emotion engine analyzes the user's voice and facial expressions. This allows it to acquire emotional data to perform maintenance tasks at the optimal time based on the user's work efficiency and concentration level. The server takes this emotional data into account and dynamically adjusts the schedule to provide the user with the best possible work environment.

[0714] For example, if a technician is burdened with many high-load tasks, the emotion engine can detect the technician's fatigue and stress. Based on this information, the work schedule can be readjusted to reduce the user's burden. Furthermore, if the user is feeling anxious about a particular maintenance task, the emotion engine can assist in providing learning modules and support functions to address that anxiety.

[0715] Therefore, this system enables efficient equipment maintenance while allowing for flexible responses based on user sentiment, resulting in improved overall operational efficiency and reduced maintenance costs.

[0716] The following describes the processing flow.

[0717] Step 1:

[0718] The terminal continuously collects environmental data from sensors attached to the equipment and periodically transmits it to the server.

[0719] Step 2:

[0720] The server stores the received environmental data in a database and performs data preprocessing. This includes noise reduction and filtering outliers.

[0721] Step 3:

[0722] The server uses machine learning algorithms to analyze data to estimate the likelihood of failure. This analysis is then used to update the failure risk assessment.

[0723] Step 4:

[0724] The server generates an optimal maintenance schedule based on failure predictions and notifies the user's terminal of the schedule. The user can review this and make adjustments as needed.

[0725] Step 5:

[0726] The device's built-in emotion engine analyzes the user's voice and facial expressions, extracting emotional information in real time. Based on this information, the system evaluates the user's concentration level and stress level.

[0727] Step 6:

[0728] The server retrieves information from the emotion engine and readjusts the maintenance schedule to take the user's psychological state into account. If necessary, it distributes the workload and optimizes the allocation of technicians.

[0729] Step 7:

[0730] The server uses its inventory management function to predict the demand for necessary parts and creates an ordering plan to optimize parts supply.

[0731] Step 8:

[0732] Users receive work instructions via their devices and carry out equipment maintenance and repairs according to plan. It's also possible to leverage emotional data to provide appropriate support and educational resources.

[0733] This series of processes allows the system to support the efficient operation of equipment and provide flexible maintenance plans that take into account the user's emotions and psychological factors.

[0734] (Example 2)

[0735] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0736] Conventional equipment maintenance systems primarily focused on predicting equipment failures and optimizing maintenance schedules. However, they failed to consider factors such as workers' emotional states and fluctuations in work efficiency, potentially leading to increased worker burden and decreased equipment utilization. Furthermore, despite the possibility of advanced analysis using machine learning algorithms, it was difficult to utilize the results to adjust the work environment in real time.

[0737] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0738] In this invention, the server includes information gathering means, predictive analysis means, plan generation means, monitoring means, resource management means, worker management means, and emotion analysis means. This enables real-time analysis of workers' emotional states and the generation of an optimal maintenance plan linked to equipment failure prediction results, as well as adjustment of the work environment.

[0739] "Information gathering means" refers to a device or method that has the function of collecting data from various sensors installed in the facility and transmitting it to a server.

[0740] A "predictive analysis means" is a device or method that uses a machine learning algorithm to predict equipment failures based on collected information.

[0741] "Plan generation means" refers to a device or method that generates an optimal maintenance work plan based on the results of failure prediction.

[0742] "Monitoring means" refers to a device or method that has the function of continuously monitoring the instantaneous state of equipment and detecting abnormalities.

[0743] "Resource management means" refers to a device or method that optimizes the inventory of parts and materials based on demand forecasts and supplies the appropriate resources when needed.

[0744] "Worker management means" refers to a device or method for managing information about workers' skills and experience and for assigning the most suitable personnel to the appropriate tasks.

[0745] "Emotional analysis means" refers to a device or method that analyzes a worker's emotional state from their voice and facial expressions and uses the results to adjust the work environment.

[0746] This invention is a system for optimizing equipment maintenance, and by organically linking multiple functions, it realizes the generation of maintenance schedules that take into account equipment failure prediction and the emotional state of workers.

[0747] First, the terminal collects data in real time from sensors attached to the equipment (e.g., temperature sensors, vibration sensors, pressure sensors) and sends that data to the server. These sensors use standard IoT protocols as their communication protocol.

[0748] The server stores received data in a database and performs data formatting and analysis using Python, R, and other tools. Machine learning algorithms such as TensorFlow and scikit-learn are used to predict equipment failures. Based on the failure prediction results, maintenance plans are formulated using linear programming and heuristic methods.

[0749] Furthermore, a terminal or dedicated device collects the worker's voice and facial expressions, which are then analyzed by an emotion analysis engine. This analysis utilizes services such as Microsoft Azure Face API. The obtained emotion data is integrated on a server and fed back into the maintenance plan.

[0750] For example, if an engineer is overworked and stressed, the emotion engine can detect this and readjust the maintenance schedule to reduce the engineer's burden. Furthermore, if it detects anxiety about a specific task, it can support the engineer by providing a learning module.

[0751] Examples of prompts for the generating AI model include instructions such as, "Consider the following user emotional state and generate the optimal maintenance schedule," or "Based on the failure prediction results, suggest a corresponding work schedule."

[0752] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0753] Step 1:

[0754] The terminal collects data from the equipment's sensors. The inputs are sensor data such as temperature, vibration, and pressure. The terminal collects this data in real time and performs an initial check for any abnormal values. Data that does not show any abnormalities is sent to the server in batch processing.

[0755] Step 2:

[0756] The server stores the received sensor data in a database. The input is sensor data sent from the terminal. The server formats this data and stores it in a database (e.g., PostgreSQL). The data is converted to an appropriate format for subsequent analysis.

[0757] Step 3:

[0758] The server analyzes stored data to predict failures. The input is sensor data stored in a database. The server uses Python and TensorFlow to analyze the data with machine learning algorithms. This process predicts the risk of equipment failure, and the result is output as numerical data.

[0759] Step 4:

[0760] The server generates a maintenance plan based on the failure prediction results. The input is the failure prediction result data. The server uses linear programming to formulate the optimal maintenance schedule. The created plan is output as schedule data and notified to the user.

[0761] Step 5:

[0762] A terminal or dedicated device collects and analyzes the user's emotional data. The input is audio or video data. The terminal uses a microphone and camera to collect this data and sends it to an emotional analysis engine. The emotional analysis engine analyzes the collected data and outputs the user's emotional state.

[0763] Step 6:

[0764] The server adjusts the maintenance schedule based on emotional data. The input is emotional state data from the emotional analysis engine. The server combines the current schedule with the emotional data to make necessary schedule adjustments to optimize the work environment. The adjusted schedule is then re-notified to the user's terminal.

[0765] (Application Example 2)

[0766] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0767] In equipment maintenance, it has been difficult to enable efficient and optimal responses to anticipated failures while also flexibly adjusting work processes to take into account the emotional state of the workers. Therefore, improvements are needed to increase equipment utilization and reduce maintenance costs.

[0768] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0769] In this invention, the server includes information acquisition means, predictive analysis means, scheduling means, monitoring means, inventory management means, personnel management means, and sentiment analysis means. This allows for real-time monitoring of equipment status, the creation of optimal maintenance plans based on failure predictions, and adjustments to suit the emotional state of workers.

[0770] "Information acquisition means" refers to devices or technologies that have the function of collecting various types of data from equipment and appropriately storing or transferring them.

[0771] "Predictive analytics" refers to technologies that use collected data and machine learning algorithms to predict the probability and timing of equipment failures.

[0772] "Scheduling methods" refer to technologies for creating schedules to carry out maintenance work in the most efficient and effective manner, based on predictive analysis results.

[0773] "Monitoring methods" refer to technologies for checking the real-time status of equipment and issuing notifications or alarms as needed.

[0774] "Inventory management methods" are technologies that optimize the inventory of necessary parts and materials based on demand forecasts, and replenish or place orders at the appropriate time.

[0775] "Personnel management methods" refer to technologies for managing information about engineers' skills and experience, and for flexibly assigning the right personnel to the necessary tasks.

[0776] "Emotional analysis methods" are technologies that analyze emotional data such as workers' voices and facial expressions to provide approaches for improving work efficiency and safety.

[0777] The system that realizes this application example utilizes information acquisition means, predictive analysis means, scheduling means, monitoring means, inventory management means, personnel management means, and sentiment analysis means to streamline the maintenance of factory equipment.

[0778] The server stores equipment data collected from smart sensors using information acquisition methods. This allows for monitoring of equipment operation status and acquisition of necessary data in real time.

[0779] The server uses machine learning algorithms such as TensorFlow to predict equipment failures based on the acquired data. The predictive analysis means analyzes the equipment's operating data and identifies areas where failures are likely. In addition, smart glasses collect the worker's voice and facial expressions, and the emotion analysis means identifies the user's emotional state.

[0780] Based on the generated failure prediction and sentiment data, the server generates an optimal maintenance schedule and notifies the appropriate personnel through scheduling mechanisms. Furthermore, inventory management mechanisms efficiently manage necessary parts and supply them at the required time.

[0781] For example, if a robot in a factory exhibits abnormal behavior, predictive analysis identifies the malfunction as a problem, and a work schedule with reduced stress levels is generated, taking into account the feelings of the workers. The system automatically notifies the staff and initiates an optimized maintenance process.

[0782] An example of an input prompt for a generated AI model is: "Please report on a system that takes into account the user's emotional state to help optimize factory robot maintenance."

[0783] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0784] Step 1:

[0785] The terminal collects real-time data from smart sensors attached to the equipment. This data includes equipment parameters such as vibration, temperature, and current. By sending this data to a server, the basic information necessary for analysis is obtained.

[0786] Step 2:

[0787] The server receives the transmitted equipment data and performs data preprocessing. It cleans and normalizes the data to prepare it for analysis. Using the input equipment parameters, it removes outliers and outputs a standardized dataset.

[0788] Step 3:

[0789] The server uses the organized data to perform failure prediction through predictive analytics. Based on machine learning algorithms (e.g., TensorFlow), it identifies patterns indicating abnormal equipment behavior and evaluates the likelihood of future failures. It analyzes the patterns obtained from the input data and outputs failure prediction results.

[0790] Step 4:

[0791] The server generates an optimal maintenance schedule using scheduling methods based on predictive analytics results and user sentiment data. It creates a realistic work plan considering the workload of the workers. It outputs an efficient schedule proposal from the input failure predictions and sentiment data.

[0792] Step 5:

[0793] The device collects the worker's voice and facial expressions through smart glasses and evaluates their emotional state in real time using emotion analysis. This allows it to recognize the user's stress level, concentration level, etc., and reflect this in their schedule. Emotional results are output from the input audio and video data.

[0794] Step 6:

[0795] The server uses inventory management tools to forecast the demand for maintenance parts and implements an optimized inventory plan. This enables the supply of parts at the necessary time. Based on the input demand forecast data, it outputs the inventory allocation.

[0796] Step 7:

[0797] Users can input prompts into the generated AI model to obtain reports on system operating status and maintenance adjustments. This allows for a deeper understanding of the work process. The system outputs reports generated based on the prompts.

[0798] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0799] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0800] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0801] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0802] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0803] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0804] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0805] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0806] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0807] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0808] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0809] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0810] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0811] 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.

[0812] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0813] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0814] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0815] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0816] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0817] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0818] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0819] The following is further disclosed regarding the embodiments described above.

[0820] (Claim 1)

[0821] A data collection means for collecting and storing equipment data,

[0822] A predictive analysis means that performs equipment failure prediction based on the said data,

[0823] A scheduling means that generates an optimal maintenance schedule based on predictive analysis results,

[0824] A monitoring means for monitoring the real-time status of the equipment,

[0825] An inventory management system that optimizes parts inventory based on demand forecasts,

[0826] A system for managing engineers' skill information and assigning the most suitable engineers to tasks,

[0827] A system that includes this.

[0828] (Claim 2)

[0829] The system according to claim 1, characterized in that the predictive analysis means uses a machine learning algorithm to predict equipment failures.

[0830] (Claim 3)

[0831] The system according to claim 1, characterized in that the scheduling means uses the information of the engineer management means to perform optimal personnel allocation.

[0832] "Example 1"

[0833] (Claim 1)

[0834] A data acquisition means for collecting and storing operational information of equipment,

[0835] A prediction means for predicting equipment abnormalities based on the said operation information,

[0836] A scheduling means that generates an optimal maintenance schedule using a generative AI model based on prediction results,

[0837] A monitoring means that immediately monitors the status of the equipment and sends a warning when an abnormality occurs,

[0838] An inventory control means for optimizing the inventory of consumables based on demand forecasts,

[0839] A means for managing the competence information of engineers and assigning the most suitable engineers to tasks,

[0840] A system that includes this.

[0841] (Claim 2)

[0842] The system according to claim 1, characterized in that the prediction means performs equipment anomaly prediction using machine learning processing.

[0843] (Claim 3)

[0844] The system according to claim 1, characterized in that the scheduling means uses the information of the worker placement means to perform optimal personnel placement.

[0845] "Application Example 1"

[0846] (Claim 1)

[0847] Information acquisition means for acquiring and storing information about equipment,

[0848] A prediction processing means that performs equipment failure prediction based on the said information,

[0849] A planning method for formulating an optimal maintenance plan based on the prediction processing results,

[0850] A monitoring system for monitoring the real-time status of equipment,

[0851] A stock management system that optimizes parts stockpiling based on demand forecasts,

[0852] A means of coordinating engineers to manage engineers' competence information and assign the most suitable engineers to tasks,

[0853] An anomaly notification means that analyzes the vibration data of the equipment and notifies of abnormal values,

[0854] A means of providing information to users through a mobile device application that indicates signs of malfunction,

[0855] A system that includes this.

[0856] (Claim 2)

[0857] The system according to claim 1, characterized in that the prediction processing means performs equipment failure prediction using a machine learning algorithm.

[0858] (Claim 3)

[0859] The system according to claim 1, characterized in that the planning means uses the information of the engineer coordination means to perform appropriate labor force allocation.

[0860] "Example 2 of combining an emotion engine"

[0861] (Claim 1)

[0862] Information gathering means for collecting and storing information about equipment,

[0863] A predictive analysis means that performs equipment failure prediction based on the said information,

[0864] A plan generation means that generates an optimal maintenance plan based on predictive analysis results,

[0865] A monitoring means for monitoring the instantaneous status of the equipment,

[0866] Resource management means for optimizing parts inventory based on demand forecasts,

[0867] A worker management system that manages worker skill information and assigns the most suitable worker to tasks,

[0868] An emotion analysis tool that analyzes the emotional state of workers and adjusts the work environment accordingly,

[0869] A system that includes this.

[0870] (Claim 2)

[0871] The system according to claim 1, characterized in that the predictive analysis means performs equipment failure prediction using a machine learning algorithm.

[0872] (Claim 3)

[0873] The system according to claim 1, characterized in that the plan generation means uses information from the worker management means and the emotion analysis means to perform optimal personnel allocation.

[0874] "Application example 2 when combining with an emotional engine"

[0875] (Claim 1)

[0876] A means of acquiring information to collect and store equipment data,

[0877] A predictive analysis means that performs equipment failure prediction based on the said data,

[0878] A scheduling means that generates an optimal maintenance schedule based on predictive analysis results,

[0879] A monitoring means for monitoring the real-time status of the equipment,

[0880] An inventory management system that optimizes parts inventory based on demand forecasts,

[0881] A personnel management system that manages the skills information of engineers and assigns the most suitable engineers to tasks,

[0882] An emotion analysis tool that analyzes the emotional state of users and aims to improve and optimize work efficiency,

[0883] A system that includes this.

[0884] (Claim 2)

[0885] The system according to claim 1, characterized in that the predictive analysis means uses a machine learning algorithm to predict equipment failures.

[0886] (Claim 3)

[0887] The system according to claim 1, characterized in that the scheduling means uses information from the personnel management means and the emotion analysis means to perform optimal personnel allocation and work adjustments. [Explanation of Symbols]

[0888] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A data collection means for collecting and storing equipment data, A predictive analysis means that performs equipment failure prediction based on the said data, A scheduling means that generates an optimal maintenance schedule based on predictive analysis results, A monitoring means for monitoring the real-time status of the equipment, An inventory management system that optimizes parts inventory based on demand forecasts, A system for managing engineers' skill information and assigning the most suitable engineers to tasks, A system that includes this.

2. The system according to claim 1, characterized in that the predictive analysis means uses a machine learning algorithm to predict equipment failures.

3. The system according to claim 1, characterized in that the scheduling means uses the information of the engineer management means to perform optimal personnel allocation.

Images