System

Abstract

A system is provided.SOLUTION: A system, comprising: means for collecting data from sensors; means for pre-processing the collected data; means for training a machine learning model using the pre-processed data; means for predicting energy output based on new sensor data; and means for monitoring a system based on the predicted energy output and notifying maintenance if needed.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Improving the efficiency and reliability of renewable energy systems is a key challenge in achieving sustainable energy solutions. Conventional technologies lack the ability to adequately predict energy output and monitor systems in real time, making efficient operation and predictive maintenance difficult. The present invention aims to provide a new method for optimizing the performance and improving the reliability of renewable energy systems. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for collecting data from sensors, a means for preprocessing the collected data, a means for training a machine learning model using the preprocessed data, a means for predicting energy output based on new sensor data, and a means for monitoring the system based on the predicted energy output and notifying maintenance as needed. Specifically, the system includes a means for removing missing values ​​from the collected data and extracting multiple features. Furthermore, by using a random forest classifier as the machine learning model, the accuracy of the energy output prediction is improved, resulting in efficient system operation.

[0006] A "sensor" is a device that collects data from the surrounding physical environment.

[0007] "Means of collecting data" are processes and devices that use sensors to obtain the necessary information from the surroundings.

[0008] "Preprocessing" is the process of converting the collected raw data into a form suitable for analysis and modeling.

[0009] "Means for preprocessing data" refers to a program or device that removes missing values ​​and extracts necessary features.

[0010] A "machine learning model" is an algorithm that learns from data and makes predictions and classifications based on specific patterns and trends.

[0011] A "means for training a model" is a process and apparatus that uses preprocessed data to train a machine learning model.

[0012] "Sensor data" refers to information about the surrounding physical environment collected by sensors.

[0013] A "means for predicting energy output" is a process and apparatus that uses a trained machine learning model to estimate future energy production.

[0014] "System monitoring means" are processes and devices that track the operation of an energy system in real time and notify you when a problem occurs.

[0015] "Means for notifying maintenance" refers to the process and devices that notify relevant personnel of required maintenance when a system abnormality is detected.

[0016] A "missing value" is a value that is missing or not entered in a dataset.

[0017] A "feature" is each variable or characteristic of the input data that a machine learning model uses for learning and prediction.

[0018] A "random forest classifier" is a machine learning algorithm that uses a large number of decision trees to perform classification and regression, and then synthesizes the results to achieve high prediction accuracy. [Brief explanation of the drawings]

[0019] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0020] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0021] First, the terms used in the following description will be explained.

[0022] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0023] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0024] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0025] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0026] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0030] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0031] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0032] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0033] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0034] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0037] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0038] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0039] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0040] The present invention provides a system for improving the efficiency and reliability of renewable energy systems, which uses a machine learning model to predict energy output based on data collected from sensors and monitors and manages the system status in real time. The system includes the following main means: data collection means, data preprocessing means, model training means, energy output prediction means, and system monitoring means.

[0041] Data collection methods

[0042] The server collects data from sensors. The sensors measure the physical parameters of the wind turbine, such as temperature, wind speed, and humidity, and sends the data to the server. For example, the various parameters of the wind turbine are saved in the format energy_data.csv.

[0043] Data preprocessing measures

[0044] The server preprocesses the collected data by removing missing values, extracting necessary features (e.g., temperature, wind speed, humidity), and setting targets (energy output). This prepares the training data.

[0045] Model training methods

[0046] The server uses the preprocessed data to train a machine learning model. Specifically, it trains a model using a random forest classifier to improve the accuracy of energy output predictions. This model learns from past data and can predict energy output for new data.

[0047] Energy output prediction means

[0048] The server predicts energy output based on new sensor data. For example, the latest sensor data (temperature 30°C, wind speed 15 m / s, humidity 70%) is input into the model to obtain a prediction result. The system's operating status is evaluated based on the predicted energy output.

[0049] System Monitoring Measures

[0050] The server monitors the system in real time. It periodically updates the model based on data collected daily and predicts energy output. If a system abnormality is detected based on the prediction results, it notifies the user that maintenance is required. For example, if the predicted energy output is below a threshold, maintenance is recommended.

[0051] Specific examples

[0052] As a specific example, when newly collected sensor data (temperature 30 degrees, wind speed 15 m / s, humidity 70%) from a wind turbine is received by the server, preprocessed, and input into the model. The server then predicts energy output and evaluates the health of the system based on the prediction results. For example, if the predicted energy output is very low, the server notifies the user that maintenance is required. On the other hand, if the prediction shows normal energy output, the system is deemed to continue operating efficiently, and no special action is required from the user.

[0053] As described above, the present invention provides specific means for enabling efficient operation and improved reliability of renewable energy systems.

[0054] The processing flow will be explained below.

[0055] Step 1:

[0056] The server collects data from the sensors, specifically, real-time data such as temperature, wind speed, and humidity of the wind turbines, and stores it in the format energy_data.csv.

[0057] Step 2:

[0058] The server preprocesses the collected data by removing missing values, extracting necessary features (e.g., temperature, wind speed, humidity), and setting the target (energy output). For example, the pandas library is used to remove missing values ​​in the data frame and extract necessary columns.

[0059] Step 3:

[0060] The server uses the preprocessed data to train a machine learning model. Specifically, it uses a random forest classifier to create a model for predicting energy output from historical data. The model learns from the training dataset to improve its prediction accuracy.

[0061] Step 4:

[0062] The server predicts energy output based on new sensor data. Specifically, the latest sensor data (e.g., temperature 30°C, wind speed 15m / s, humidity 70%) is input into the model to obtain the predicted results. The model predicts energy output based on the input features and outputs the results.

[0063] Step 5:

[0064] The server monitors the system in real time, periodically updating the model based on the latest collected data and predicting energy output. For example, data collected every 10 minutes is preprocessed and input into the model to obtain prediction results.

[0065] Step 6:

[0066] The server evaluates the health of the system based on the prediction results. Specifically, if the predicted energy output is below a certain threshold, an abnormality is detected and the user is notified that maintenance is required. For example, if the predicted energy output is 50% or less of normal, an alarm is issued.

[0067] Step 7:

[0068] Users receive maintenance notifications, check the status of their systems, and perform necessary maintenance tasks.

[0069] This concludes the specific processing flow of the EnergyEfficient platform. We have explained in detail the operations performed by the server at each step.

[0070] Example 1

[0071] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0072] To improve the efficiency and reliability of renewable energy systems, it is necessary to accurately predict energy output using data collected from sensors and to monitor and manage the system status in real time. However, conventional systems are not able to adequately deal with missing data or improve the accuracy of models, and they also face challenges in quickly responding to system abnormalities.

[0073] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0074] In this invention, the server includes means for collecting data from sensors, means for preprocessing the collected data, means for training a machine learning model using the preprocessed data, means for predicting energy output based on new sensor data, means for monitoring the system based on the predicted energy output and notifying maintenance as necessary, and means for notifying a user that maintenance is required when the system detects an abnormality, thereby improving the accuracy of energy output predictions and enabling system abnormalities to be detected and addressed quickly.

[0075] 1. A "sensor" is a device that measures a physical parameter and transmits that data to a server.

[0076] 2. "Data collection means" refers to the means by which the server receives and stores data collected from the sensors.

[0077] 3. "Data preprocessing means" refers to the means for removing missing values ​​from collected data, extracting necessary features, and setting target variables.

[0078] 4. A "machine learning model" is an algorithm that learns patterns and rules from large amounts of data and makes predictions and classifications for new data.

[0079] 5. "Model Training Means" means a means for training a machine learning model using preprocessed data.

[0080] 6. "Energy output forecasting means" means a means for forecasting energy output based on new sensor data.

[0081] 7. "System monitoring means" means a means for monitoring a system based on predicted energy output and notifying maintenance as needed.

[0082] 8. "Maintenance notification means" means a means of notifying users that maintenance is required when an abnormality is detected in the system.

[0083] 9. A "missing value" is a value that is missing in a dataset.

[0084] 10. "Feature" is a term that refers to the characteristics of data that a machine learning model uses for training.

[0085] 11. A "random forest classifier" is a machine learning algorithm that uses multiple decision trees to perform classification and regression.

[0086] The present invention is a system for improving the efficiency and reliability of renewable energy systems, and aims to predict energy output and monitor and manage the system status in real time using a machine learning model based on data collected from sensors. The system mainly includes the following means: data collection means, data preprocessing means, model training means, energy output prediction means, and system monitoring means.

[0087] In the phase where the server collects data from sensors, sensors installed on the wind turbines measure physical parameters (temperature, wind speed, humidity, etc.) and send the data to the server. The data is saved in the energy_data.csv format.

[0088] Next, the server moves to the preprocessing phase of the collected data, where it removes missing values, extracts necessary features such as temperature, wind speed, and humidity, and sets the target energy output, preparing the data for model training.

[0089] In the training phase, the server uses the preprocessed data to train the machine learning model, using a random forest classifier to learn patterns from past data and improve prediction accuracy for new data.

[0090] In the phase of predicting energy output based on new sensor data, the server inputs the latest sensor data into the model and obtains the predicted energy output. For example, input data of 30 degrees Celsius temperature, 15 m / s wind speed, and 70% humidity, and obtain the predicted energy output.

[0091] Finally, in the real-time monitoring phase, the server periodically updates the model based on data collected daily and predicts energy output. If an abnormality is detected in the system based on the prediction results, the server notifies the user that maintenance is required.

[0092] As a concrete example, when newly collected sensor data (temperature 30 degrees, wind speed 15 m / s, humidity 70%) from a wind turbine is received by the server, preprocessed, and input into the model. The server then predicts energy output and evaluates the health of the system based on the prediction results. For example, if the predicted energy output is very low, the server notifies the user that maintenance is required. On the other hand, if the prediction shows normal energy output, the system is deemed to continue operating efficiently, and no special action is required from the user.

[0093] An example prompt might have the following format:

[0094] "Please predict the energy output of a wind turbine using sensor data. Input the following data: temperature 30°C, wind speed 15m / s, humidity 70%. What is the predicted energy output? Also, based on this, please assess the health of the system and advise any necessary action."

[0095] As described above, the present invention provides specific means for realizing efficient operation and improved reliability of renewable energy systems.

[0096] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0097] Step 1:

[0098] Data collection

[0099] Input: Physical parameters (temperature, wind speed, humidity) from sensors installed on the wind turbines.

[0100] Output: Raw data saved in energy_data.csv.

[0101] Specific actions

[0102] The server collects physical parameters (e.g., temperature 30°C, wind speed 15 m / s, humidity 70%) from sensors installed on each wind turbine and saves the data in a file called energy_data.csv.

[0103] Step 2:

[0104] Data Preprocessing

[0105] Input: Raw data stored in energy_data.csv.

[0106] Output: A preprocessed dataset (data with missing values ​​removed and required features extracted).

[0107] Specific actions

[0108] The server reads the data from energy_data.csv, removes rows with missing values, extracts the required features (temperature, wind speed, humidity), and sets the energy output as the target variable, thus preparing the dataset for model training.

[0109] Step 3:

[0110] Model training

[0111] Input: The preprocessed dataset.

[0112] Output: A trained random forest classifier model.

[0113] Specific actions

[0114] The server uses the preprocessed dataset to train a random forest classifier, which learns patterns and relationships from past data and can accurately predict energy output for new data.

[0115] Step 4:

[0116] Energy Output Forecast

[0117] Input: New sensor data (temperature, wind speed, humidity).

[0118] Output: The predicted energy output value.

[0119] Specific actions

[0120] The server inputs new sensor data (e.g., temperature 30°C, wind speed 15 m / s, humidity 70%) into a trained random forest model to predict energy output, which is then used to assess the current health of the system.

[0121] Step 5:

[0122] System Monitoring

[0123] Input: The predicted energy output value.

[0124] Output: Monitoring results (normal / abnormal notification and corresponding measures).

[0125] Specific actions

[0126] The server monitors the system status in real time and makes decisions based on the model's predictions. If the predicted energy output falls below a threshold, the server detects a system abnormality and notifies the user that maintenance is required. On the other hand, if the energy output is within the normal range, the system is deemed to be operating normally.

[0127] The above is the specific processing flow of this system.

[0128] (Application example 1)

[0129] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0130] Improving the efficiency and reliability of energy output in renewable energy systems is an urgent issue, and the associated need for real-time monitoring of the system health is also important.In addition, energy management is important in industrial facilities, and methods for efficiently managing energy consumption and curbing excessive consumption are required.

[0131] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0132] In this invention, the server includes means for collecting data from sensors, means for preprocessing the collected data, means for training a machine learning model using the preprocessed data, means for predicting energy output based on new sensor data, means for monitoring the system based on the predicted energy output and notifying maintenance as needed, and means for monitoring energy consumption of the industrial facility in real time and proposing optimal energy usage, thereby enabling improved efficiency and reliability of renewable energy systems and optimized energy management of industrial facilities.

[0133] A "sensor" is a device that measures a physical parameter and outputs it as digital data.

[0134] "Data collection means" refers to a means that has the function of aggregating and storing data obtained from sensors.

[0135] The "data preprocessing means" is a means for removing missing values ​​from collected data and extracting features.

[0136] A "machine learning model" is an algorithm that is trained using collected data to make predictions or classifications based on new data.

[0137] A "random forest classifier" is a machine learning model that creates multiple decision trees and combines them to make predictions.

[0138] "New sensor data" is the latest data collected from a sensor at any current or future time.

[0139] The "energy output prediction means" is a means for predicting energy output using new sensor data as input.

[0140] "System monitoring means" refers to means for monitoring the state of the system based on predicted energy output and notifying maintenance as necessary.

[0141] "Maintenance" refers to the maintenance and repair work carried out to maintain the health of the system.

[0142] An "industrial facility" is a place where manufacturing or production activities are carried out and is a facility that consumes a lot of energy.

[0143] "Energy consumption" is the amount of energy used within an industrial facility.

[0144] "Real-time monitoring" means observing the system status immediately and responding quickly if an abnormality occurs.

[0145] "Optimal energy usage" is a way to efficiently manage energy consumption and reduce waste.

[0146] MODE FOR CARRYING OUT THE INVENTION

[0147] The present invention provides a system for improving the efficiency and reliability of energy management systems in industrial facilities. The system predicts energy output using a machine learning model based on data collected from sensors and monitors and manages the system status in real time. The system includes the following main means: data collection means, data preprocessing means, model training means, energy output prediction means, and system monitoring means. The system also includes means for monitoring energy consumption in industrial facilities in real time and proposing optimal energy usage.

[0148] Data collection methods

[0149] The server collects data from sensors, which measure physical parameters such as temperature, wind speed, and humidity on equipment and robots in industrial facilities and send them to the server. For example, sensor data is often stored in CSV format.

[0150] Data preprocessing measures

[0151] The server preprocesses the collected data by removing missing values, extracting necessary features (e.g., temperature, wind speed, humidity), and setting targets (energy output), thus preparing the training data.

[0152] Model training methods

[0153] The server uses the preprocessed data to train a machine learning model, specifically a random forest classifier, to improve the accuracy of energy output predictions. This model learns from past data and can predict energy output for new data.

[0154] Energy output prediction means

[0155] The server predicts energy output based on new sensor data. For example, the latest sensor data (temperature 30 degrees, wind speed 15 m / s, humidity 70%) is input into the model to obtain a prediction result. The system's operating status is evaluated based on the predicted energy output.

[0156] System Monitoring Measures

[0157] The server monitors the system in real time, periodically updating the model based on data collected daily and predicting energy output. If the prediction detects a system abnormality, it notifies the user that maintenance is required. For example, if the predicted energy output is below a threshold, maintenance is recommended.

[0158] Energy consumption management measures

[0159] It has the means to monitor energy consumption in industrial facilities in real time and propose optimal energy usage, thereby reducing energy waste and achieving efficient energy management.

[0160] Specific examples

[0161] As a concrete example, in an energy management system at an industrial facility, when new sensor data is collected showing a temperature of 30 degrees, a wind speed of 15 m / s, and humidity of 70%, the server receives this data, preprocesses it, and inputs it into the model. The server then predicts energy output and evaluates the health of the system based on the prediction results. For example, if the predicted energy output is very low, the server notifies the user that maintenance is required. On the other hand, if the prediction shows normal energy output, the system is deemed to be continuing to operate efficiently, and no special action is required from the user.

[0162] Prompt Sentence Examples

[0163] "Predict the energy output when the temperature is 30 degrees, the wind speed is 15 m / s, and the humidity is 70%."

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

[0165] Step 1:

[0166] The server collects data from sensors. Specifically, physical parameters such as temperature, wind speed, and humidity are acquired in real time from each piece of equipment and robot in the industrial facility and sent to the server in digital form. The input is sensor data, and the output is raw digital data.

[0167] Step 2:

[0168] The server preprocesses the collected raw data. Specifically, it removes missing values ​​from the data and extracts necessary features (temperature, wind speed, humidity). After data preprocessing, it sets a target (energy output) and builds a training dataset. The input is raw data, and the output is preprocessed data.

[0169] Step 3:

[0170] The server uses the preprocessed data to train a machine learning model. Specifically, it uses a random forest classifier to improve the model's predictive accuracy. The model learns from past data and becomes able to accurately predict energy output for new data. The input is the preprocessed data, and the output is the trained model.

[0171] Step 4:

[0172] The server collects new sensor data and predicts energy output based on this new data. Specifically, the latest sensor data (e.g., temperature 30°C, wind speed 15m / s, humidity 70%) is input into the trained model to obtain a prediction result. The input is the new sensor data, and the output is the predicted energy output.

[0173] Step 5:

[0174] The server monitors the system based on the predicted energy output. Specifically, if the predicted result is below a threshold, it notifies the user that maintenance is required. If it is above the threshold, the energy output is normal and no special action is required. The input is the predicted result, and the output is the notification action.

[0175] Step 6:

[0176] The server monitors the energy consumption of industrial facilities in real time and proposes optimal energy usage. Specifically, it combines sensor data and model output to generate recommendations to reduce energy waste and optimize efficiency, and notifies the user. The input is real-time sensor data and model predictions, and the output is energy usage recommendations.

[0177] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0178] The present invention provides a system for improving the efficiency and reliability of renewable energy systems, which uses machine learning models to predict energy output based on data collected from sensors and monitors and manages the system status in real time. The system further has a function to adapt the notification method to the user by combining an emotion engine that recognizes the user's emotions.

[0179] Data collection methods

[0180] The server collects data from sensors. The sensors measure the physical parameters of the wind turbine, such as temperature, wind speed, and humidity, and sends the data to the server. For example, the various parameters of the wind turbine are saved in the format energy_data.csv.

[0181] Data preprocessing measures

[0182] The server preprocesses the collected data by removing missing values, extracting necessary features (e.g., temperature, wind speed, humidity), and setting targets (energy output). This prepares the training data.

[0183] Model training methods

[0184] The server uses the preprocessed data to train a machine learning model, using a random forest classifier, which learns from past data and is able to predict energy output for new data.

[0185] Energy output prediction means

[0186] The server predicts energy output based on new sensor data. For example, new sensor data (temperature 30 degrees, wind speed 15 m / s, humidity 70%) is input into the model and a prediction result is obtained. The model predicts energy output based on the input features and outputs the result.

[0187] System Monitoring Measures

[0188] The server monitors the system in real time. It periodically updates the model based on data collected daily and predicts energy output. If it detects a system abnormality based on the predicted energy output, it notifies the user that maintenance is required. For example, if the predicted energy output is 50% or less of normal, it issues a maintenance notification.

[0189] emotion recognition means

[0190] The server recognizes the user's emotions. The emotion engine analyzes the user's emotions from their voice and facial expressions, and adjusts the notification method from the system based on that information. For example, if the server determines that the user is feeling stressed, it will change the content and method of notifications and use more friendly language.

[0191] Specific examples

[0192] As a specific example, when newly collected sensor data (temperature 30 degrees, wind speed 15 m / s, humidity 70%) from a wind turbine is received by the server, preprocessed, and input into the model. The server then predicts energy output and evaluates the health of the system based on the prediction results. For example, if the predicted energy output is very low, the server notifies the user that maintenance is required. Furthermore, if the emotion engine analyzes that the user is in a state of high stress, the wording of the notification is changed to, "Thank you for your hard work. Your energy output is decreasing, so maintenance is required."

[0193] As described above, the present invention enables efficient operation and improved reliability of renewable energy systems, and also provides a flexible notification method that takes into consideration the user's feelings.

[0194] The processing flow will be explained below.

[0195] Step 1:

[0196] The server collects data from sensors. Specifically, sensors on the wind turbines acquire data such as temperature, wind speed, and humidity, and sends it to the server in real time. The server saves this data in the energy_data.csv format.

[0197] Step 2:

[0198] The server preprocesses the collected data. First, it reads the data from energy_data.csv and removes missing values. Then it extracts the necessary features (temperature, wind speed, humidity) from the data and sets the energy output as the target. This prepares the training dataset.

[0199] Step 3:

[0200] The server uses the preprocessed data to train a machine learning model. Specifically, it trains a random forest classifier using the preprocessed features and targets. The model learns from past data and is able to predict energy output for new data.

[0201] Step 4:

[0202] The server predicts energy output based on new sensor data. For example, the latest sensor data collected in real time (temperature 30 degrees, wind speed 15 m / s, humidity 70%) is input into the model to obtain a prediction result. The predicted energy output result is recorded on the server.

[0203] Step 5:

[0204] The server monitors the system in real time. It continuously updates the model based on new sensor data collected periodically. It uses the collected data to make predictions and detect anomalies in energy output. For example, an anomaly is detected if the predicted energy output is below a certain threshold.

[0205] Step 6:

[0206] The server uses an emotion engine to analyze the user's emotions. The emotion engine inputs the user's voice and facial expression data to determine the user's emotional state. For example, voice analysis can be used to determine whether the user is under stress.

[0207] Step 7:

[0208] The server adjusts the notification method based on the user's emotional state. For example, if the emotion engine determines that the user is feeling stressed, the notification method will be adjusted to use more friendly language and formatting. Specifically, the notification may say something like, "Thank you for your hard work. Your energy output is low, so maintenance is required."

[0209] Step 8:

[0210] The user receives notifications from the server, and based on the notifications, checks the system status and performs necessary maintenance work, for example, investigating the cause of the notified low energy output and adjusting or repairing the turbine.

[0211] The above is the specific processing flow of the EnergyEfficient platform using an emotion recognition engine. At each step, the server takes flexible measures that prioritize well-being, enabling efficient and stress-free operation for users.

[0212] Example 2

[0213] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0214] Renewable energy systems are expected to improve in efficiency and reliability. However, conventional systems have difficulty accurately analyzing data collected from sensors, resulting in insufficient energy output forecast accuracy and real-time system monitoring. Furthermore, communication with end users lacks the flexibility to respond to user emotions, limiting the effectiveness of maintenance and notifications. A new system is needed to solve these issues.

[0215] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0216] In this invention, the server includes means for collecting data from sensors, means for preprocessing the collected data, means for training a machine learning model using the preprocessed data, means for predicting energy output based on new sensor data, means for monitoring the system based on the predicted energy output and notifying maintenance as needed, means for recognizing a user's emotion, and means for adapting a notification method based on the recognized emotion information. This enables efficient operation and improved reliability of the renewable energy system. Furthermore, the notification method that takes user emotion into consideration can increase the user's sense of security and promote appropriate maintenance.

[0217] A "sensor" is a device that detects a physical parameter and transmits it as data to the outside.

[0218] "Data preprocessing" is the process of preparing collected data in a format suitable for training a machine learning model, such as by removing missing values ​​and extracting necessary features.

[0219] A "machine learning model" refers to an algorithm or mathematical model built to use data to predict future outputs or patterns.

[0220] A "random forest classifier" is a machine learning algorithm that uses multiple decision tree models to perform classification and regression.

[0221] "Energy output" refers to the amount of electricity or other energy produced from a renewable energy system.

[0222] "System monitoring" is the process of observing the system status in real time and notifying the user if an abnormality is detected.

[0223] "Maintenance notification" is a function that notifies the user that repair or inspection is required when an abnormality or problem occurs in the system.

[0224] "Emotion recognition" is a technology that analyzes a user's emotional state from their voice, facial expressions, etc., and uses the results to adjust their behavior and responses.

[0225] "Notification adaptation" refers to the process of optimizing the content and format of notifications based on the user's emotional state.

[0226] "Data collection" refers to the process of gathering observational data from sensors and other devices.

[0227] The present invention provides a system for improving the efficiency and reliability of renewable energy systems, which uses machine learning models to predict energy output based on data collected from sensors and monitors and manages the system status in real time. The system further has a function to adapt the notification method to the user by combining an emotion engine that recognizes the user's emotions.

[0228] Data collection methods

[0229] The server collects data from sensors. These sensors measure the physical parameters of the wind turbine, such as temperature, wind speed, and humidity, and then sends the data to the server. For example, the various parameters of the wind turbine are saved in the format energy_data.csv. Specifically, the data is obtained from the sensors in real time and stored on the server.

[0230] Data preprocessing measures

[0231] The server preprocesses the collected data by removing missing values, extracting necessary features (e.g., temperature, wind speed, humidity), and setting targets (energy output). This prepares the training data. The preprocessed data is stored in a database and used for the next model training.

[0232] Model training methods

[0233] The server uses the preprocessed data to train a machine learning model, using a random forest classifier, that learns from past data and can predict energy output based on new data. This trained model is stored locally and used for updates.

[0234] Energy output prediction means

[0235] The server predicts energy output based on new sensor data. For example, new sensor data such as a temperature of 30 degrees, a wind speed of 15 m / s, and humidity of 70% is input into the model, and a prediction result is obtained. The model output is stored in the server and used for subsequent system monitoring measures.

[0236] System Monitoring Measures

[0237] The server monitors the system in real time. Based on data collected daily, it periodically updates the model and predicts energy output. If it detects a system abnormality based on the predicted energy output, it notifies the user that maintenance is required. For example, if the predicted energy output is 50% or less of normal, it issues a maintenance notification.

[0238] emotion recognition means

[0239] The server recognizes the user's emotions. The emotion engine analyzes the user's emotions from their voice and facial expressions and adjusts the notification method based on that information. For example, if the server determines that the user is feeling stressed, it will change the content and method of the notification and use more friendly language.

[0240] Specific examples

[0241] When new sensor data (temperature 30 degrees, wind speed 15 m / s, humidity 70%) is collected from a wind turbine, the server receives it, preprocesses the data, and inputs it into the trained model. It then predicts the energy output and evaluates the health of the system based on the results. If the predicted energy output is very low, the server notifies the user that maintenance is required. Also, if the emotion engine analyzes that the user is in a high stress state, it changes the wording of the notification to "Thank you for your hard work, your energy output is decreasing, so maintenance is required."

[0242] Prompt Sentence Examples

[0243] "Use new sensor data to predict energy output and send maintenance notifications to users in case of low predictions."

[0244] "Can you give me an example of how you can change notification content based on user sentiment?"

[0245] "Please explain how you monitor your systems in real time."

[0246] As described above, the present invention enables efficient operation and improved reliability of renewable energy systems, and also provides a flexible notification method that takes into consideration the user's feelings.

[0247] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0248] Step 1: Data collection

[0249] The server collects data from sensors. The sensors measure physical parameters such as temperature, wind speed, and humidity of the wind turbines and send the data to the server. The input is the temperature, wind speed, and humidity data from the sensors, and the output is the energy_data.csv file containing these data. Specifically, the sensors send data in real time, and the server stores the data in an appropriate format.

[0250] Step 2: Data Preprocessing

[0251] The server preprocesses the collected data by removing missing values, extracting necessary features (temperature, wind speed, humidity), and setting the target (energy output). The input is the energy_data.csv file, and the output is the preprocessed dataset. This dataset has been cleaned of missing values ​​and incomplete data, and is formatted in a way that is suitable for machine learning models.

[0252] Step 3: Model training

[0253] The server uses the preprocessed data to train a machine learning model. Here, we use a random forest classifier. The input is the preprocessed dataset and the output is a trained machine learning model. The server uses this dataset to train the model so that it can predict energy output. The model is stored in the server and used in the next step.

[0254] Step 4: Energy output forecast

[0255] The server inputs new sensor data into the model and predicts the energy output. The input is the new sensor data (e.g., temperature 30 degrees, wind speed 15 m / s, humidity 70%), and the output is the predicted energy output. The server inputs new data into the model, obtains the prediction results, and stores them.

[0256] Step 5: System monitoring

[0257] The server monitors the system status in real time. The input is the sensor data collected daily and the predicted energy output, and the output is the system health assessment and maintenance notifications as needed. The server detects abnormal values ​​based on the collected data and predicted data, and if an abnormality is found, it sends a maintenance notification to the user. For example, if energy output is 50% or less of normal, a notification is sent to the user.

[0258] Step 6: Emotion Recognition

[0259] The server uses an emotion engine to recognize the user's emotions. The input is the user's voice and facial expression data, and the output is the user's emotional status. The emotion engine analyzes the user's emotions from their voice and facial expressions, and adjusts the notification method based on the results. For example, if the server determines that the user is feeling stressed, it will change the wording and content of the notification to be more friendly.

[0260] (Application example 2)

[0261] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0262] Conventional renewable energy systems were able to predict energy output and monitor the system with a certain degree of accuracy, but they had limitations in detecting software and hardware anomalies in real time and optimizing notification methods based on user emotions. Furthermore, factories operate many robots and devices, and monitoring their operating status in real time requires a large amount of information, making it difficult to provide efficient maintenance notifications. This can hinder the efficiency of energy management and reduce worker stress.

[0263] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data from sensors, means for preprocessing the collected data, means for training a machine learning model using the preprocessed data, means for predicting energy output based on new sensor data, means for monitoring the system based on the predicted energy output and notifying maintenance as necessary, means for recognizing user emotions and optimizing the notification method, and means for detecting abnormalities by monitoring the operation of equipment and robots in the factory in real time. This makes it possible to improve the efficiency of energy management in the factory, detect abnormalities early, and notify appropriate maintenance in accordance with the user's emotional state.

[0264] A "sensor" is a device that measures information from the physical environment and converts it into a digital or analog signal.

[0265] "Data collection" is the process of acquiring information generated by devices such as sensors and providing it to a system.

[0266] "Data preprocessing" refers to the process of converting collected raw data into an analyzable format, including missing value imputation and feature extraction.

[0267] A "machine learning model" is an algorithmic model that allows a system to make optimal decisions using collected data.

[0268] "Energy output forecasting" is a method of estimating future energy production based on data collected from sensors.

[0269] "System monitoring" is the process of checking the operating status of energy generation systems and related equipment in real time and detecting abnormalities.

[0270] "Maintenance notification" is the process of notifying relevant parties of necessary maintenance work when the system detects an abnormality.

[0271] "User emotion recognition" is a technology that uses devices such as cameras and microphones to analyze emotions from a user's facial expressions and voice.

[0272] "Notification method optimization" is the process of changing the content and method of notifications from the system depending on the user's emotional state.

[0273] "Real-time monitoring" is a method of constantly acquiring data and instantly analyzing and evaluating the current situation.

[0274] "Monitoring of equipment and robots in factories" is the process of checking the operating status of equipment and robots used in factories in real time.

[0275] "Abnormality detection" is a technology that identifies conditions that deviate from the normal operating range and notifies users that countermeasures are necessary.

[0276] The system for implementing this invention enables real-time monitoring of robots and equipment operating in a factory, optimization of energy management, and optimization of notification methods taking into account the emotional state of the user. Specific examples are shown below.

[0277] System Overview

[0278] The server collects data from various sensors installed in the factory, including devices that measure temperature, vibration, and power consumption, as well as from robots and machines, to monitor their operating status in real time.

[0279] The server preprocesses the collected data, completing missing values ​​and extracting features. This preprocessing prepares the data in an analyzable format. The server then uses a machine learning model, a random forest classifier, to predict energy output and system anomalies.

[0280] Furthermore, the server recognizes the user's emotions and optimizes the notification method. Specifically, it analyzes the user's facial expressions and voice through the smart glasses' camera and microphone to determine whether the user is feeling stressed. Based on this information, it adjusts the content and method of notifications, and notifies the user of maintenance using more user-friendly language and methods.

[0281] Hardware and software used

[0282] Hardware:

[0283] Smart glasses (e.g. Google Glass)

[0284] Various sensors (temperature sensors, vibration sensors, power measurement devices)

[0285] Server (performs data analysis and model training)

[0286] software:

[0287] Python (data analysis, machine learning)

[0288] TensorFlow (training machine learning models)

[0289] Scikit-learn (machine learning algorithms)

[0290] OpenCV (emotion recognition)

[0291] Specific examples

[0292] For example, imagine a robot in a factory is equipped with a temperature sensor, a vibration sensor, and a power measurement device. The data collected from these sensors (temperature, vibration, and power consumption) is analyzed in real time by a server. For example, if new sensor data such as "Temperature: 22 degrees, Vibration: 1.5G, Power consumption: 3000W" is collected, the machine learning model analyzes this data and predicts energy output. If a decrease or abnormality in energy output is detected as a result, the server immediately issues a maintenance notification.

[0293] On the other hand, when an engineer wearing smart glasses is on-site, the server analyzes the engineer's facial expressions and voice through the camera and microphone installed in the glasses to determine their stress level. For example, if it determines that the engineer is feeling stressed, it will notify them in a gentle manner, saying, "Thank you for your hard work. Equipment maintenance is required."

[0294] Prompt Sentence Examples

[0295] You want to use data about renewable energy to train a machine learning model to predict energy output and detect system anomalies. Example sensor data includes temperature, vibration, and power consumption. Additionally, you want the system to recognize user emotions and adapt notifications based on them. Build your model based on the following steps:

[0296] As described above, the present invention improves the efficiency of energy management within a factory, realizes early detection of abnormalities, and provides appropriate maintenance notifications according to the emotional state of the user.

[0297] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0298] Step 1:

[0299] Data collection

[0300] The server collects data from various sensors (temperature sensors, vibration sensors, power measurement devices, etc.) installed in the factory. Physical parameters (temperature, vibration, power consumption, etc.) sent from the sensors are sent to the server in real time, and this data is stored in a database. The input is sensor data, and the output is a set of formatted data.

[0301] Step 2:

[0302] Data Preprocessing

[0303] The server preprocesses the collected sensor data by imputing missing values, removing outliers, and extracting required features (temperature, vibration, power consumption). This process converts the raw data into an analyzable format. The input is the collected sensor data, and the output is a preprocessed dataset.

[0304] Step 3:

[0305] Training a machine learning model

[0306] The server uses the preprocessed data to train a machine learning model (random forest classifier). This model is used to predict energy output and anomalies from past data. The training data is input to the model, and a model that can make predictions with a certain level of accuracy is generated as output. Specifically, the dataset is divided into training data and test data, and these are input to the model to train it.

[0307] Step 4:

[0308] Energy output forecast

[0309] The server predicts energy output based on new sensor data. Newly collected temperature, vibration, and power consumption data is input into the model, which gives the predicted energy output as output. The model instantly calculates energy output based on the input data.

[0310] Step 5:

[0311] System Monitoring and Anomaly Detection

[0312] The server monitors the system in real time based on the predicted energy output and detects abnormalities. Specifically, it inputs data collected daily into the model and compares the predicted output with the actual output to detect abnormalities. If an abnormality is detected, it notifies the user that maintenance is required. The inputs are new sensor data and the output of the predictive model, and the output is the presence or absence of an abnormality and a notification of that presence.

[0313] Step 6:

[0314] User Emotion Recognition

[0315] The device (smart glasses) recognizes the user's emotions. It uses a camera and microphone to analyze the user's facial expressions and voice to determine whether the user is feeling stressed. The input is camera video and audio data, and the output is emotion recognition results. The emotion engine analyzes the user's emotions and sends the analysis results to the server.

[0316] Step 7:

[0317] Optimized notification method

[0318] The server optimizes the notification method based on the user's emotion recognition results. Specifically, it flexibly changes the content and wording of the notification, and if the user is feeling stressed, it notifies them in more friendly language. The input is the emotion recognition results and the maintenance notification content, and the optimized notification message is generated as the output.

[0319] In this way, it is possible to improve the efficiency of energy management within factories, detect abnormalities early, and provide flexible notifications according to the user's emotions.

[0320] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0321] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0322] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0323] [Second embodiment]

[0324] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0325] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0326] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0327] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0328] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0329] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0330] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0331] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0332] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0333] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0334] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0335] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0336] The present invention provides a system for improving the efficiency and reliability of renewable energy systems, which uses a machine learning model to predict energy output based on data collected from sensors and monitors and manages the system status in real time. The system includes the following main means: data collection means, data preprocessing means, model training means, energy output prediction means, and system monitoring means.

[0337] Data collection methods

[0338] The server collects data from sensors. The sensors measure the physical parameters of the wind turbine, such as temperature, wind speed, and humidity, and sends the data to the server. For example, the various parameters of the wind turbine are saved in the format energy_data.csv.

[0339] Data preprocessing measures

[0340] The server preprocesses the collected data by removing missing values, extracting necessary features (e.g., temperature, wind speed, humidity), and setting targets (energy output). This prepares the training data.

[0341] Model training methods

[0342] The server uses the preprocessed data to train a machine learning model. Specifically, it trains a model using a random forest classifier to improve the accuracy of energy output predictions. This model learns from past data and can predict energy output for new data.

[0343] Energy output prediction means

[0344] The server predicts energy output based on new sensor data. For example, the latest sensor data (temperature 30°C, wind speed 15 m / s, humidity 70%) is input into the model to obtain a prediction result. The system's operating status is evaluated based on the predicted energy output.

[0345] System Monitoring Measures

[0346] The server monitors the system in real time. It periodically updates the model based on data collected daily and predicts energy output. If a system abnormality is detected based on the prediction results, it notifies the user that maintenance is required. For example, if the predicted energy output is below a threshold, maintenance is recommended.

[0347] Specific examples

[0348] As a specific example, when newly collected sensor data (temperature 30 degrees, wind speed 15 m / s, humidity 70%) from a wind turbine is received by the server, preprocessed, and input into the model. The server then predicts energy output and evaluates the health of the system based on the prediction results. For example, if the predicted energy output is very low, the server notifies the user that maintenance is required. On the other hand, if the prediction shows normal energy output, the system is deemed to continue operating efficiently, and no special action is required from the user.

[0349] As described above, the present invention provides specific means for enabling efficient operation and improved reliability of renewable energy systems.

[0350] The processing flow will be explained below.

[0351] Step 1:

[0352] The server collects data from the sensors, specifically, real-time data such as temperature, wind speed, and humidity of the wind turbines, and stores it in the format energy_data.csv.

[0353] Step 2:

[0354] The server preprocesses the collected data by removing missing values, extracting necessary features (e.g., temperature, wind speed, humidity), and setting the target (energy output). For example, the pandas library is used to remove missing values ​​in the data frame and extract necessary columns.

[0355] Step 3:

[0356] The server uses the preprocessed data to train a machine learning model. Specifically, it uses a random forest classifier to create a model for predicting energy output from historical data. The model learns from the training dataset to improve its prediction accuracy.

[0357] Step 4:

[0358] The server predicts energy output based on new sensor data. Specifically, the latest sensor data (e.g., temperature 30°C, wind speed 15m / s, humidity 70%) is input into the model to obtain the predicted results. The model predicts energy output based on the input features and outputs the results.

[0359] Step 5:

[0360] The server monitors the system in real time, periodically updating the model based on the latest collected data and predicting energy output. For example, data collected every 10 minutes is preprocessed and input into the model to obtain prediction results.

[0361] Step 6:

[0362] The server evaluates the health of the system based on the prediction results. Specifically, if the predicted energy output is below a certain threshold, an abnormality is detected and the user is notified that maintenance is required. For example, if the predicted energy output is 50% or less of normal, an alarm is issued.

[0363] Step 7:

[0364] Users receive maintenance notifications, check the status of their systems, and perform necessary maintenance tasks.

[0365] This concludes the specific processing flow of the EnergyEfficient platform. We have explained in detail the operations performed by the server at each step.

[0366] Example 1

[0367] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0368] To improve the efficiency and reliability of renewable energy systems, it is necessary to accurately predict energy output using data collected from sensors and to monitor and manage the system status in real time. However, conventional systems are not able to adequately deal with missing data or improve the accuracy of models, and they also face challenges in quickly responding to system abnormalities.

[0369] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0370] In this invention, the server includes means for collecting data from sensors, means for preprocessing the collected data, means for training a machine learning model using the preprocessed data, means for predicting energy output based on new sensor data, means for monitoring the system based on the predicted energy output and notifying maintenance as necessary, and means for notifying a user that maintenance is required when the system detects an abnormality, thereby improving the accuracy of energy output predictions and enabling system abnormalities to be detected and addressed quickly.

[0371] 1. A "sensor" is a device that measures a physical parameter and transmits that data to a server.

[0372] 2. "Data collection means" refers to the means by which the server receives and stores data collected from the sensors.

[0373] 3. "Data preprocessing means" refers to the means for removing missing values ​​from collected data, extracting necessary features, and setting target variables.

[0374] 4. A "machine learning model" is an algorithm that learns patterns and rules from large amounts of data and makes predictions and classifications for new data.

[0375] 5. "Model Training Means" means a means for training a machine learning model using preprocessed data.

[0376] 6. "Energy output forecasting means" means a means for forecasting energy output based on new sensor data.

[0377] 7. "System monitoring means" means a means for monitoring a system based on predicted energy output and notifying maintenance as needed.

[0378] 8. "Maintenance notification means" means a means of notifying users that maintenance is required when an abnormality is detected in the system.

[0379] 9. A "missing value" is a value that is missing in a dataset.

[0380] 10. "Feature" is a term that refers to the characteristics of data that a machine learning model uses for training.

[0381] 11. A "random forest classifier" is a machine learning algorithm that uses multiple decision trees to perform classification and regression.

[0382] The present invention is a system for improving the efficiency and reliability of renewable energy systems, and aims to predict energy output and monitor and manage the system status in real time using a machine learning model based on data collected from sensors. The system mainly includes the following means: data collection means, data preprocessing means, model training means, energy output prediction means, and system monitoring means.

[0383] In the phase where the server collects data from sensors, sensors installed on the wind turbines measure physical parameters (temperature, wind speed, humidity, etc.) and send the data to the server. The data is saved in the energy_data.csv format.

[0384] Next, the server moves to the preprocessing phase of the collected data, where it removes missing values, extracts necessary features such as temperature, wind speed, and humidity, and sets the target energy output, preparing the data for model training.

[0385] In the training phase, the server uses the preprocessed data to train the machine learning model, using a random forest classifier to learn patterns from past data and improve prediction accuracy for new data.

[0386] In the phase of predicting energy output based on new sensor data, the server inputs the latest sensor data into the model and obtains the predicted energy output. For example, input data of 30 degrees Celsius temperature, 15 m / s wind speed, and 70% humidity, and obtain the predicted energy output.

[0387] Finally, in the real-time monitoring phase, the server periodically updates the model based on data collected daily and predicts energy output. If an abnormality is detected in the system based on the prediction results, the server notifies the user that maintenance is required.

[0388] As a concrete example, when newly collected sensor data (temperature 30 degrees, wind speed 15 m / s, humidity 70%) from a wind turbine is received by the server, preprocessed, and input into the model. The server then predicts energy output and evaluates the health of the system based on the prediction results. For example, if the predicted energy output is very low, the server notifies the user that maintenance is required. On the other hand, if the prediction shows normal energy output, the system is deemed to continue operating efficiently, and no special action is required from the user.

[0389] An example prompt might have the following format:

[0390] "Please predict the energy output of a wind turbine using sensor data. Input the following data: temperature 30°C, wind speed 15m / s, humidity 70%. What is the predicted energy output? Also, based on this, please assess the health of the system and advise any necessary action."

[0391] As described above, the present invention provides specific means for realizing efficient operation and improved reliability of renewable energy systems.

[0392] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0393] Step 1:

[0394] Data collection

[0395] Input: Physical parameters (temperature, wind speed, humidity) from sensors installed on the wind turbines.

[0396] Output: Raw data saved in energy_data.csv.

[0397] Specific actions

[0398] The server collects physical parameters (e.g., temperature 30°C, wind speed 15 m / s, humidity 70%) from sensors installed on each wind turbine and saves the data in a file called energy_data.csv.

[0399] Step 2:

[0400] Data Preprocessing

[0401] Input: Raw data stored in energy_data.csv.

[0402] Output: A preprocessed dataset (data with missing values ​​removed and required features extracted).

[0403] Specific actions

[0404] The server reads the data from energy_data.csv, removes rows with missing values, extracts the required features (temperature, wind speed, humidity), and sets the energy output as the target variable, thus preparing the dataset for model training.

[0405] Step 3:

[0406] Model training

[0407] Input: The preprocessed dataset.

[0408] Output: A trained random forest classifier model.

[0409] Specific actions

[0410] The server uses the preprocessed dataset to train a random forest classifier, which learns patterns and relationships from past data and can accurately predict energy output for new data.

[0411] Step 4:

[0412] Energy Output Forecast

[0413] Input: New sensor data (temperature, wind speed, humidity).

[0414] Output: The predicted energy output value.

[0415] Specific actions

[0416] The server inputs new sensor data (e.g., temperature 30°C, wind speed 15 m / s, humidity 70%) into a trained random forest model to predict energy output, which is then used to assess the current health of the system.

[0417] Step 5:

[0418] System Monitoring

[0419] Input: The predicted energy output value.

[0420] Output: Monitoring results (normal / abnormal notification and corresponding measures).

[0421] Specific actions

[0422] The server monitors the system status in real time and makes decisions based on the model's predictions. If the predicted energy output falls below a threshold, the server detects a system abnormality and notifies the user that maintenance is required. On the other hand, if the energy output is within the normal range, the system is deemed to be operating normally.

[0423] The above is the specific processing flow of this system.

[0424] (Application example 1)

[0425] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0426] Improving the efficiency and reliability of energy output in renewable energy systems is an urgent issue, and the associated need for real-time monitoring of the system health is also important.In addition, energy management is important in industrial facilities, and methods for efficiently managing energy consumption and curbing excessive consumption are required.

[0427] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0428] In this invention, the server includes means for collecting data from sensors, means for preprocessing the collected data, means for training a machine learning model using the preprocessed data, means for predicting energy output based on new sensor data, means for monitoring the system based on the predicted energy output and notifying maintenance as needed, and means for monitoring energy consumption of the industrial facility in real time and proposing optimal energy usage, thereby enabling improved efficiency and reliability of renewable energy systems and optimized energy management of industrial facilities.

[0429] A "sensor" is a device that measures a physical parameter and outputs it as digital data.

[0430] "Data collection means" refers to a means that has the function of aggregating and storing data obtained from sensors.

[0431] The "data preprocessing means" is a means for removing missing values ​​from collected data and extracting features.

[0432] A "machine learning model" is an algorithm that is trained using collected data to make predictions or classifications based on new data.

[0433] A "random forest classifier" is a machine learning model that creates multiple decision trees and combines them to make predictions.

[0434] "New sensor data" is the latest data collected from a sensor at any current or future time.

[0435] The "energy output prediction means" is a means for predicting energy output using new sensor data as input.

[0436] "System monitoring means" refers to means for monitoring the state of the system based on predicted energy output and notifying maintenance as necessary.

[0437] "Maintenance" refers to the maintenance and repair work carried out to maintain the health of the system.

[0438] An "industrial facility" is a place where manufacturing or production activities are carried out and is a facility that consumes a lot of energy.

[0439] "Energy consumption" is the amount of energy used within an industrial facility.

[0440] "Real-time monitoring" means observing the system status immediately and responding quickly if an abnormality occurs.

[0441] "Optimal energy usage" is a way to efficiently manage energy consumption and reduce waste.

[0442] MODE FOR CARRYING OUT THE INVENTION

[0443] The present invention provides a system for improving the efficiency and reliability of energy management systems in industrial facilities. The system predicts energy output using a machine learning model based on data collected from sensors and monitors and manages the system status in real time. The system includes the following main means: data collection means, data preprocessing means, model training means, energy output prediction means, and system monitoring means. The system also includes means for monitoring energy consumption in industrial facilities in real time and proposing optimal energy usage.

[0444] Data collection methods

[0445] The server collects data from sensors, which measure physical parameters such as temperature, wind speed, and humidity on equipment and robots in industrial facilities and send them to the server. For example, sensor data is often stored in CSV format.

[0446] Data preprocessing measures

[0447] The server preprocesses the collected data by removing missing values, extracting necessary features (e.g., temperature, wind speed, humidity), and setting targets (energy output), thus preparing the training data.

[0448] Model training methods

[0449] The server uses the preprocessed data to train a machine learning model, specifically a random forest classifier, to improve the accuracy of energy output predictions. This model learns from past data and can predict energy output for new data.

[0450] Energy output prediction means

[0451] The server predicts energy output based on new sensor data. For example, the latest sensor data (temperature 30 degrees, wind speed 15 m / s, humidity 70%) is input into the model to obtain a prediction result. The system's operating status is evaluated based on the predicted energy output.

[0452] System Monitoring Measures

[0453] The server monitors the system in real time, periodically updating the model based on data collected daily and predicting energy output. If the prediction detects a system abnormality, it notifies the user that maintenance is required. For example, if the predicted energy output is below a threshold, maintenance is recommended.

[0454] Energy consumption management measures

[0455] It has the means to monitor energy consumption in industrial facilities in real time and propose optimal energy usage, thereby reducing energy waste and achieving efficient energy management.

[0456] Specific examples

[0457] As a concrete example, in an energy management system at an industrial facility, when new sensor data is collected showing a temperature of 30 degrees, a wind speed of 15 m / s, and humidity of 70%, the server receives this data, preprocesses it, and inputs it into the model. The server then predicts energy output and evaluates the health of the system based on the prediction results. For example, if the predicted energy output is very low, the server notifies the user that maintenance is required. On the other hand, if the prediction shows normal energy output, the system is deemed to be continuing to operate efficiently, and no special action is required from the user.

[0458] Prompt Sentence Examples

[0459] "Predict the energy output when the temperature is 30 degrees, the wind speed is 15 m / s, and the humidity is 70%."

[0460] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0461] Step 1:

[0462] The server collects data from sensors. Specifically, physical parameters such as temperature, wind speed, and humidity are acquired in real time from each piece of equipment and robot in the industrial facility and sent to the server in digital form. The input is sensor data, and the output is raw digital data.

[0463] Step 2:

[0464] The server preprocesses the collected raw data. Specifically, it removes missing values ​​from the data and extracts necessary features (temperature, wind speed, humidity). After data preprocessing, it sets a target (energy output) and builds a training dataset. The input is raw data, and the output is preprocessed data.

[0465] Step 3:

[0466] The server uses the preprocessed data to train a machine learning model. Specifically, it uses a random forest classifier to improve the model's predictive accuracy. The model learns from past data and becomes able to accurately predict energy output for new data. The input is the preprocessed data, and the output is the trained model.

[0467] Step 4:

[0468] The server collects new sensor data and predicts energy output based on this new data. Specifically, the latest sensor data (e.g., temperature 30°C, wind speed 15m / s, humidity 70%) is input into the trained model to obtain a prediction result. The input is the new sensor data, and the output is the predicted energy output.

[0469] Step 5:

[0470] The server monitors the system based on the predicted energy output. Specifically, if the predicted result is below a threshold, it notifies the user that maintenance is required. If it is above the threshold, the energy output is normal and no special action is required. The input is the predicted result, and the output is the notification action.

[0471] Step 6:

[0472] The server monitors the energy consumption of industrial facilities in real time and proposes optimal energy usage. Specifically, it combines sensor data and model output to generate recommendations to reduce energy waste and optimize efficiency, and notifies the user. The input is real-time sensor data and model predictions, and the output is energy usage recommendations.

[0473] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0474] The present invention provides a system for improving the efficiency and reliability of renewable energy systems, which uses machine learning models to predict energy output based on data collected from sensors and monitors and manages the system status in real time. The system further has a function to adapt the notification method to the user by combining an emotion engine that recognizes the user's emotions.

[0475] Data collection methods

[0476] The server collects data from sensors. The sensors measure the physical parameters of the wind turbine, such as temperature, wind speed, and humidity, and sends the data to the server. For example, the various parameters of the wind turbine are saved in the format energy_data.csv.

[0477] Data preprocessing measures

[0478] The server preprocesses the collected data by removing missing values, extracting necessary features (e.g., temperature, wind speed, humidity), and setting targets (energy output). This prepares the training data.

[0479] Model training methods

[0480] The server uses the preprocessed data to train a machine learning model, using a random forest classifier, which learns from past data and is able to predict energy output for new data.

[0481] Energy output prediction means

[0482] The server predicts energy output based on new sensor data. For example, new sensor data (temperature 30 degrees, wind speed 15 m / s, humidity 70%) is input into the model and a prediction result is obtained. The model predicts energy output based on the input features and outputs the result.

[0483] System Monitoring Measures

[0484] The server monitors the system in real time. It periodically updates the model based on data collected daily and predicts energy output. If it detects a system abnormality based on the predicted energy output, it notifies the user that maintenance is required. For example, if the predicted energy output is 50% or less of normal, it issues a maintenance notification.

[0485] emotion recognition means

[0486] The server recognizes the user's emotions. The emotion engine analyzes the user's emotions from their voice and facial expressions, and adjusts the notification method from the system based on that information. For example, if the server determines that the user is feeling stressed, it will change the content and method of notifications and use more friendly language.

[0487] Specific examples

[0488] As a specific example, when newly collected sensor data (temperature 30 degrees, wind speed 15 m / s, humidity 70%) from a wind turbine is received by the server, preprocessed, and input into the model. The server then predicts energy output and evaluates the health of the system based on the prediction results. For example, if the predicted energy output is very low, the server notifies the user that maintenance is required. Furthermore, if the emotion engine analyzes that the user is in a state of high stress, the wording of the notification is changed to, "Thank you for your hard work. Your energy output is decreasing, so maintenance is required."

[0489] As described above, the present invention enables efficient operation and improved reliability of renewable energy systems, and also provides a flexible notification method that takes into consideration the user's feelings.

[0490] The processing flow will be explained below.

[0491] Step 1:

[0492] The server collects data from sensors. Specifically, sensors on the wind turbines acquire data such as temperature, wind speed, and humidity, and sends it to the server in real time. The server saves this data in the energy_data.csv format.

[0493] Step 2:

[0494] The server preprocesses the collected data. First, it reads the data from energy_data.csv and removes missing values. Then it extracts the necessary features (temperature, wind speed, humidity) from the data and sets the energy output as the target. This prepares the training dataset.

[0495] Step 3:

[0496] The server uses the preprocessed data to train a machine learning model. Specifically, it trains a random forest classifier using the preprocessed features and targets. The model learns from past data and is able to predict energy output for new data.

[0497] Step 4:

[0498] The server predicts energy output based on new sensor data. For example, the latest sensor data collected in real time (temperature 30 degrees, wind speed 15 m / s, humidity 70%) is input into the model to obtain a prediction result. The predicted energy output result is recorded on the server.

[0499] Step 5:

[0500] The server monitors the system in real time. It continuously updates the model based on new sensor data collected periodically. It uses the collected data to make predictions and detect anomalies in energy output. For example, an anomaly is detected if the predicted energy output is below a certain threshold.

[0501] Step 6:

[0502] The server uses an emotion engine to analyze the user's emotions. The emotion engine inputs the user's voice and facial expression data to determine the user's emotional state. For example, voice analysis can be used to determine whether the user is under stress.

[0503] Step 7:

[0504] The server adjusts the notification method based on the user's emotional state. For example, if the emotion engine determines that the user is feeling stressed, the notification method will be adjusted to use more friendly language and formatting. Specifically, the notification may say something like, "Thank you for your hard work. Your energy output is low, so maintenance is required."

[0505] Step 8:

[0506] The user receives notifications from the server, and based on the notifications, checks the system status and performs necessary maintenance work, for example, investigating the cause of the notified low energy output and adjusting or repairing the turbine.

[0507] The above is the specific processing flow of the EnergyEfficient platform using an emotion recognition engine. At each step, the server takes flexible measures that prioritize well-being, enabling efficient and stress-free operation for users.

[0508] Example 2

[0509] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0510] Renewable energy systems are expected to improve in efficiency and reliability. However, conventional systems have difficulty accurately analyzing data collected from sensors, resulting in insufficient energy output forecast accuracy and real-time system monitoring. Furthermore, communication with end users lacks the flexibility to respond to user emotions, limiting the effectiveness of maintenance and notifications. A new system is needed to solve these issues.

[0511] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0512] In this invention, the server includes means for collecting data from sensors, means for preprocessing the collected data, means for training a machine learning model using the preprocessed data, means for predicting energy output based on new sensor data, means for monitoring the system based on the predicted energy output and notifying maintenance as needed, means for recognizing a user's emotion, and means for adapting a notification method based on the recognized emotion information. This enables efficient operation and improved reliability of the renewable energy system. Furthermore, the notification method that takes user emotion into consideration can increase the user's sense of security and promote appropriate maintenance.

[0513] A "sensor" is a device that detects a physical parameter and transmits it as data to the outside.

[0514] "Data preprocessing" is the process of preparing collected data in a format suitable for training a machine learning model, such as by removing missing values ​​and extracting necessary features.

[0515] A "machine learning model" refers to an algorithm or mathematical model built to use data to predict future outputs or patterns.

[0516] A "random forest classifier" is a machine learning algorithm that uses multiple decision tree models to perform classification and regression.

[0517] "Energy output" refers to the amount of electricity or other energy produced from a renewable energy system.

[0518] "System monitoring" is the process of observing the system status in real time and notifying the user if an abnormality is detected.

[0519] "Maintenance notification" is a function that notifies the user that repair or inspection is required when an abnormality or problem occurs in the system.

[0520] "Emotion recognition" is a technology that analyzes a user's emotional state from their voice, facial expressions, etc., and uses the results to adjust their behavior and responses.

[0521] "Notification adaptation" refers to the process of optimizing the content and format of notifications based on the user's emotional state.

[0522] "Data collection" refers to the process of gathering observational data from sensors and other devices.

[0523] The present invention provides a system for improving the efficiency and reliability of renewable energy systems, which uses machine learning models to predict energy output based on data collected from sensors and monitors and manages the system status in real time. The system further has a function to adapt the notification method to the user by combining an emotion engine that recognizes the user's emotions.

[0524] Data collection methods

[0525] The server collects data from sensors. These sensors measure the physical parameters of the wind turbine, such as temperature, wind speed, and humidity, and then sends the data to the server. For example, the various parameters of the wind turbine are saved in the format energy_data.csv. Specifically, the data is obtained from the sensors in real time and stored on the server.

[0526] Data preprocessing measures

[0527] The server preprocesses the collected data by removing missing values, extracting necessary features (e.g., temperature, wind speed, humidity), and setting targets (energy output). This prepares the training data. The preprocessed data is stored in a database and used for the next model training.

[0528] Model training methods

[0529] The server uses the preprocessed data to train a machine learning model, using a random forest classifier, that learns from past data and can predict energy output based on new data. This trained model is stored locally and used for updates.

[0530] Energy output prediction means

[0531] The server predicts energy output based on new sensor data. For example, new sensor data such as a temperature of 30 degrees, a wind speed of 15 m / s, and humidity of 70% is input into the model, and a prediction result is obtained. The model output is stored in the server and used for subsequent system monitoring measures.

[0532] System Monitoring Measures

[0533] The server monitors the system in real time. Based on data collected daily, it periodically updates the model and predicts energy output. If it detects a system abnormality based on the predicted energy output, it notifies the user that maintenance is required. For example, if the predicted energy output is 50% or less of normal, it issues a maintenance notification.

[0534] emotion recognition means

[0535] The server recognizes the user's emotions. The emotion engine analyzes the user's emotions from their voice and facial expressions and adjusts the notification method based on that information. For example, if the server determines that the user is feeling stressed, it will change the content and method of the notification and use more friendly language.

[0536] Specific examples

[0537] When new sensor data (temperature 30 degrees, wind speed 15 m / s, humidity 70%) is collected from a wind turbine, the server receives it, preprocesses the data, and inputs it into the trained model. It then predicts the energy output and evaluates the health of the system based on the results. If the predicted energy output is very low, the server notifies the user that maintenance is required. Also, if the emotion engine analyzes that the user is in a high stress state, it changes the wording of the notification to "Thank you for your hard work, your energy output is decreasing, so maintenance is required."

[0538] Prompt Sentence Examples

[0539] "Use new sensor data to predict energy output and send maintenance notifications to users in case of low predictions."

[0540] "Can you give me an example of how you can change notification content based on user sentiment?"

[0541] "Please explain how you monitor your systems in real time."

[0542] As described above, the present invention enables efficient operation and improved reliability of renewable energy systems, and also provides a flexible notification method that takes into consideration the user's feelings.

[0543] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0544] Step 1: Data collection

[0545] The server collects data from sensors. The sensors measure physical parameters such as temperature, wind speed, and humidity of the wind turbines and send the data to the server. The input is the temperature, wind speed, and humidity data from the sensors, and the output is the energy_data.csv file containing these data. Specifically, the sensors send data in real time, and the server stores the data in an appropriate format.

[0546] Step 2: Data Preprocessing

[0547] The server preprocesses the collected data by removing missing values, extracting necessary features (temperature, wind speed, humidity), and setting the target (energy output). The input is the energy_data.csv file, and the output is the preprocessed dataset. This dataset has been cleaned of missing values ​​and incomplete data, and is formatted in a way that is suitable for machine learning models.

[0548] Step 3: Model training

[0549] The server uses the preprocessed data to train a machine learning model. Here, we use a random forest classifier. The input is the preprocessed dataset and the output is a trained machine learning model. The server uses this dataset to train the model so that it can predict energy output. The model is stored in the server and used in the next step.

[0550] Step 4: Energy output forecast

[0551] The server inputs new sensor data into the model and predicts the energy output. The input is the new sensor data (e.g., temperature 30 degrees, wind speed 15 m / s, humidity 70%), and the output is the predicted energy output. The server inputs new data into the model, obtains the prediction results, and stores them.

[0552] Step 5: System monitoring

[0553] The server monitors the system status in real time. The input is the sensor data collected daily and the predicted energy output, and the output is the system health assessment and maintenance notifications as needed. The server detects abnormal values ​​based on the collected data and predicted data, and if an abnormality is found, it sends a maintenance notification to the user. For example, if energy output is 50% or less of normal, a notification is sent to the user.

[0554] Step 6: Emotion Recognition

[0555] The server uses an emotion engine to recognize the user's emotions. The input is the user's voice and facial expression data, and the output is the user's emotional status. The emotion engine analyzes the user's emotions from their voice and facial expressions, and adjusts the notification method based on the results. For example, if the server determines that the user is feeling stressed, it will change the wording and content of the notification to be more friendly.

[0556] (Application example 2)

[0557] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0558] Conventional renewable energy systems were able to predict energy output and monitor the system with a certain degree of accuracy, but they had limitations in detecting software and hardware anomalies in real time and optimizing notification methods based on user emotions. Furthermore, factories operate many robots and devices, and monitoring their operating status in real time requires a large amount of information, making it difficult to provide efficient maintenance notifications. This can hinder the efficiency of energy management and reduce worker stress.

[0559] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data from sensors, means for preprocessing the collected data, means for training a machine learning model using the preprocessed data, means for predicting energy output based on new sensor data, means for monitoring the system based on the predicted energy output and notifying maintenance as necessary, means for recognizing user emotions and optimizing the notification method, and means for detecting abnormalities by monitoring the operation of equipment and robots in the factory in real time. This makes it possible to improve the efficiency of energy management in the factory, detect abnormalities early, and notify appropriate maintenance in accordance with the user's emotional state.

[0560] A "sensor" is a device that measures information from the physical environment and converts it into a digital or analog signal.

[0561] "Data collection" is the process of acquiring information generated by devices such as sensors and providing it to a system.

[0562] "Data preprocessing" refers to the process of converting collected raw data into an analyzable format, including missing value imputation and feature extraction.

[0563] A "machine learning model" is an algorithmic model that allows a system to make optimal decisions using collected data.

[0564] "Energy output forecasting" is a method of estimating future energy production based on data collected from sensors.

[0565] "System monitoring" is the process of checking the operating status of energy generation systems and related equipment in real time and detecting abnormalities.

[0566] "Maintenance notification" is the process of notifying relevant parties of necessary maintenance work when the system detects an abnormality.

[0567] "User emotion recognition" is a technology that uses devices such as cameras and microphones to analyze emotions from a user's facial expressions and voice.

[0568] "Notification method optimization" is the process of changing the content and method of notifications from the system depending on the user's emotional state.

[0569] "Real-time monitoring" is a method of constantly acquiring data and instantly analyzing and evaluating the current situation.

[0570] "Monitoring of equipment and robots in factories" is the process of checking the operating status of equipment and robots used in factories in real time.

[0571] "Abnormality detection" is a technology that identifies conditions that deviate from the normal operating range and notifies users that countermeasures are necessary.

[0572] The system for implementing this invention enables real-time monitoring of robots and equipment operating in a factory, optimization of energy management, and optimization of notification methods taking into account the emotional state of the user. Specific examples are shown below.

[0573] System Overview

[0574] The server collects data from various sensors installed in the factory, including devices that measure temperature, vibration, and power consumption, as well as from robots and machines, to monitor their operating status in real time.

[0575] The server preprocesses the collected data, completing missing values ​​and extracting features. This preprocessing prepares the data in an analyzable format. The server then uses a machine learning model, a random forest classifier, to predict energy output and system anomalies.

[0576] Furthermore, the server recognizes the user's emotions and optimizes the notification method. Specifically, it analyzes the user's facial expressions and voice through the smart glasses' camera and microphone to determine whether the user is feeling stressed. Based on this information, it adjusts the content and method of notifications, and notifies the user of maintenance using more user-friendly language and methods.

[0577] Hardware and software used

[0578] Hardware:

[0579] Smart glasses (e.g. Google Glass)

[0580] Various sensors (temperature sensors, vibration sensors, power measurement devices)

[0581] Server (performs data analysis and model training)

[0582] software:

[0583] Python (data analysis, machine learning)

[0584] TensorFlow (training machine learning models)

[0585] Scikit-learn (machine learning algorithms)

[0586] OpenCV (emotion recognition)

[0587] Specific examples

[0588] For example, imagine a robot in a factory is equipped with a temperature sensor, a vibration sensor, and a power measurement device. The data collected from these sensors (temperature, vibration, and power consumption) is analyzed in real time by a server. For example, if new sensor data such as "Temperature: 22 degrees, Vibration: 1.5G, Power consumption: 3000W" is collected, the machine learning model analyzes this data and predicts energy output. If a decrease or abnormality in energy output is detected as a result, the server immediately issues a maintenance notification.

[0589] On the other hand, when an engineer wearing smart glasses is on-site, the server analyzes the engineer's facial expressions and voice through the camera and microphone installed in the glasses to determine their stress level. For example, if it determines that the engineer is feeling stressed, it will notify them in a gentle manner, saying, "Thank you for your hard work. Equipment maintenance is required."

[0590] Prompt Sentence Examples

[0591] You want to use data about renewable energy to train a machine learning model to predict energy output and detect system anomalies. Example sensor data includes temperature, vibration, and power consumption. Additionally, you want the system to recognize user emotions and adapt notifications based on them. Build your model based on the following steps:

[0592] As described above, the present invention improves the efficiency of energy management within a factory, realizes early detection of abnormalities, and provides appropriate maintenance notifications according to the emotional state of the user.

[0593] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0594] Step 1:

[0595] Data collection

[0596] The server collects data from various sensors (temperature sensors, vibration sensors, power measurement devices, etc.) installed in the factory. Physical parameters (temperature, vibration, power consumption, etc.) sent from the sensors are sent to the server in real time, and this data is stored in a database. The input is sensor data, and the output is a set of formatted data.

[0597] Step 2:

[0598] Data Preprocessing

[0599] The server preprocesses the collected sensor data by imputing missing values, removing outliers, and extracting required features (temperature, vibration, power consumption). This process converts the raw data into an analyzable format. The input is the collected sensor data, and the output is a preprocessed dataset.

[0600] Step 3:

[0601] Training a machine learning model

[0602] The server uses the preprocessed data to train a machine learning model (random forest classifier). This model is used to predict energy output and anomalies from past data. The training data is input to the model, and a model that can make predictions with a certain level of accuracy is generated as output. Specifically, the dataset is divided into training data and test data, and these are input to the model to train it.

[0603] Step 4:

[0604] Energy output forecast

[0605] The server predicts energy output based on new sensor data. Newly collected temperature, vibration, and power consumption data is input into the model, which gives the predicted energy output as output. The model instantly calculates energy output based on the input data.

[0606] Step 5:

[0607] System Monitoring and Anomaly Detection

[0608] The server monitors the system in real time based on the predicted energy output and detects abnormalities. Specifically, it inputs data collected daily into the model and compares the predicted output with the actual output to detect abnormalities. If an abnormality is detected, it notifies the user that maintenance is required. The inputs are new sensor data and the output of the predictive model, and the output is the presence or absence of an abnormality and a notification of that presence.

[0609] Step 6:

[0610] User Emotion Recognition

[0611] The device (smart glasses) recognizes the user's emotions. It uses a camera and microphone to analyze the user's facial expressions and voice to determine whether the user is feeling stressed. The input is camera video and audio data, and the output is emotion recognition results. The emotion engine analyzes the user's emotions and sends the analysis results to the server.

[0612] Step 7:

[0613] Optimized notification method

[0614] The server optimizes the notification method based on the user's emotion recognition results. Specifically, it flexibly changes the content and wording of the notification, and if the user is feeling stressed, it notifies them in more friendly language. The input is the emotion recognition results and the maintenance notification content, and the optimized notification message is generated as the output.

[0615] In this way, it is possible to improve the efficiency of energy management within factories, detect abnormalities early, and provide flexible notifications according to the user's emotions.

[0616] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0617] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0618] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0619] [Third embodiment]

[0620] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0621] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0622] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0623] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0624] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0625] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0626] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0627] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0628] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0629] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0630] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0631] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0632] The present invention provides a system for improving the efficiency and reliability of renewable energy systems, which uses a machine learning model to predict energy output based on data collected from sensors and monitors and manages the system status in real time. The system includes the following main means: data collection means, data preprocessing means, model training means, energy output prediction means, and system monitoring means.

[0633] Data collection methods

[0634] The server collects data from sensors. The sensors measure the physical parameters of the wind turbine, such as temperature, wind speed, and humidity, and sends the data to the server. For example, the various parameters of the wind turbine are saved in the format energy_data.csv.

[0635] Data preprocessing measures

[0636] The server preprocesses the collected data by removing missing values, extracting necessary features (e.g., temperature, wind speed, humidity), and setting targets (energy output). This prepares the training data.

[0637] Model training methods

[0638] The server uses the preprocessed data to train a machine learning model. Specifically, it trains a model using a random forest classifier to improve the accuracy of energy output predictions. This model learns from past data and can predict energy output for new data.

[0639] Energy output prediction means

[0640] The server predicts energy output based on new sensor data. For example, the latest sensor data (temperature 30°C, wind speed 15 m / s, humidity 70%) is input into the model to obtain a prediction result. The system's operating status is evaluated based on the predicted energy output.

[0641] System Monitoring Measures

[0642] The server monitors the system in real time. It periodically updates the model based on data collected daily and predicts energy output. If a system abnormality is detected based on the prediction results, it notifies the user that maintenance is required. For example, if the predicted energy output is below a threshold, maintenance is recommended.

[0643] Specific examples

[0644] As a specific example, when newly collected sensor data (temperature 30 degrees, wind speed 15 m / s, humidity 70%) from a wind turbine is received by the server, preprocessed, and input into the model. The server then predicts energy output and evaluates the health of the system based on the prediction results. For example, if the predicted energy output is very low, the server notifies the user that maintenance is required. On the other hand, if the prediction shows normal energy output, the system is deemed to continue operating efficiently, and no special action is required from the user.

[0645] As described above, the present invention provides specific means for enabling efficient operation and improved reliability of renewable energy systems.

[0646] The processing flow will be explained below.

[0647] Step 1:

[0648] The server collects data from the sensors, specifically, real-time data such as temperature, wind speed, and humidity of the wind turbines, and stores it in the format energy_data.csv.

[0649] Step 2:

[0650] The server preprocesses the collected data by removing missing values, extracting necessary features (e.g., temperature, wind speed, humidity), and setting the target (energy output). For example, the pandas library is used to remove missing values ​​in the data frame and extract necessary columns.

[0651] Step 3:

[0652] The server uses the preprocessed data to train a machine learning model. Specifically, it uses a random forest classifier to create a model for predicting energy output from historical data. The model learns from the training dataset to improve its prediction accuracy.

[0653] Step 4:

[0654] The server predicts energy output based on new sensor data. Specifically, the latest sensor data (e.g., temperature 30°C, wind speed 15m / s, humidity 70%) is input into the model to obtain the predicted results. The model predicts energy output based on the input features and outputs the results.

[0655] Step 5:

[0656] The server monitors the system in real time, periodically updating the model based on the latest collected data and predicting energy output. For example, data collected every 10 minutes is preprocessed and input into the model to obtain prediction results.

[0657] Step 6:

[0658] The server evaluates the health of the system based on the prediction results. Specifically, if the predicted energy output is below a certain threshold, an abnormality is detected and the user is notified that maintenance is required. For example, if the predicted energy output is 50% or less of normal, an alarm is issued.

[0659] Step 7:

[0660] Users receive maintenance notifications, check the status of their systems, and perform necessary maintenance tasks.

[0661] This concludes the specific processing flow of the EnergyEfficient platform. We have explained in detail the operations performed by the server at each step.

[0662] Example 1

[0663] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0664] To improve the efficiency and reliability of renewable energy systems, it is necessary to accurately predict energy output using data collected from sensors and to monitor and manage the system status in real time. However, conventional systems are not able to adequately deal with missing data or improve the accuracy of models, and they also face challenges in quickly responding to system abnormalities.

[0665] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0666] In this invention, the server includes means for collecting data from sensors, means for preprocessing the collected data, means for training a machine learning model using the preprocessed data, means for predicting energy output based on new sensor data, means for monitoring the system based on the predicted energy output and notifying maintenance as necessary, and means for notifying a user that maintenance is required when the system detects an abnormality, thereby improving the accuracy of energy output predictions and enabling system abnormalities to be detected and addressed quickly.

[0667] 1. A "sensor" is a device that measures a physical parameter and transmits that data to a server.

[0668] 2. "Data collection means" refers to the means by which the server receives and stores data collected from the sensors.

[0669] 3. "Data preprocessing means" refers to the means for removing missing values ​​from collected data, extracting necessary features, and setting target variables.

[0670] 4. A "machine learning model" is an algorithm that learns patterns and rules from large amounts of data and makes predictions and classifications for new data.

[0671] 5. "Model Training Means" means a means for training a machine learning model using preprocessed data.

[0672] 6. "Energy output forecasting means" means a means for forecasting energy output based on new sensor data.

[0673] 7. "System monitoring means" means a means for monitoring a system based on predicted energy output and notifying maintenance as needed.

[0674] 8. "Maintenance notification means" means a means of notifying users that maintenance is required when an abnormality is detected in the system.

[0675] 9. A "missing value" is a value that is missing in a dataset.

[0676] 10. "Feature" is a term that refers to the characteristics of data that a machine learning model uses for training.

[0677] 11. A "random forest classifier" is a machine learning algorithm that uses multiple decision trees to perform classification and regression.

[0678] The present invention is a system for improving the efficiency and reliability of renewable energy systems, and aims to predict energy output and monitor and manage the system status in real time using a machine learning model based on data collected from sensors. The system mainly includes the following means: data collection means, data preprocessing means, model training means, energy output prediction means, and system monitoring means.

[0679] In the phase where the server collects data from sensors, sensors installed on the wind turbines measure physical parameters (temperature, wind speed, humidity, etc.) and send the data to the server. The data is saved in the energy_data.csv format.

[0680] Next, the server moves to the preprocessing phase of the collected data, where it removes missing values, extracts necessary features such as temperature, wind speed, and humidity, and sets the target energy output, preparing the data for model training.

[0681] In the training phase, the server uses the preprocessed data to train the machine learning model, using a random forest classifier to learn patterns from past data and improve prediction accuracy for new data.

[0682] In the phase of predicting energy output based on new sensor data, the server inputs the latest sensor data into the model and obtains the predicted energy output. For example, input data of 30 degrees Celsius temperature, 15 m / s wind speed, and 70% humidity, and obtain the predicted energy output.

[0683] Finally, in the real-time monitoring phase, the server periodically updates the model based on data collected daily and predicts energy output. If an abnormality is detected in the system based on the prediction results, the server notifies the user that maintenance is required.

[0684] As a concrete example, when newly collected sensor data (temperature 30 degrees, wind speed 15 m / s, humidity 70%) from a wind turbine is received by the server, preprocessed, and input into the model. The server then predicts energy output and evaluates the health of the system based on the prediction results. For example, if the predicted energy output is very low, the server notifies the user that maintenance is required. On the other hand, if the prediction shows normal energy output, the system is deemed to continue operating efficiently, and no special action is required from the user.

[0685] An example prompt might have the following format:

[0686] "Please predict the energy output of a wind turbine using sensor data. Input the following data: temperature 30°C, wind speed 15m / s, humidity 70%. What is the predicted energy output? Also, based on this, please assess the health of the system and advise any necessary action."

[0687] As described above, the present invention provides specific means for realizing efficient operation and improved reliability of renewable energy systems.

[0688] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0689] Step 1:

[0690] Data collection

[0691] Input: Physical parameters (temperature, wind speed, humidity) from sensors installed on the wind turbines.

[0692] Output: Raw data saved in energy_data.csv.

[0693] Specific actions

[0694] The server collects physical parameters (e.g., temperature 30°C, wind speed 15 m / s, humidity 70%) from sensors installed on each wind turbine and saves the data in a file called energy_data.csv.

[0695] Step 2:

[0696] Data Preprocessing

[0697] Input: Raw data stored in energy_data.csv.

[0698] Output: A preprocessed dataset (data with missing values ​​removed and required features extracted).

[0699] Specific actions

[0700] The server reads the data from energy_data.csv, removes rows with missing values, extracts the required features (temperature, wind speed, humidity), and sets the energy output as the target variable, thus preparing the dataset for model training.

[0701] Step 3:

[0702] Model training

[0703] Input: The preprocessed dataset.

[0704] Output: A trained random forest classifier model.

[0705] Specific actions

[0706] The server uses the preprocessed dataset to train a random forest classifier, which learns patterns and relationships from past data and can accurately predict energy output for new data.

[0707] Step 4:

[0708] Energy Output Forecast

[0709] Input: New sensor data (temperature, wind speed, humidity).

[0710] Output: The predicted energy output value.

[0711] Specific actions

[0712] The server inputs new sensor data (e.g., temperature 30°C, wind speed 15 m / s, humidity 70%) into a trained random forest model to predict energy output, which is then used to assess the current health of the system.

[0713] Step 5:

[0714] System Monitoring

[0715] Input: The predicted energy output value.

[0716] Output: Monitoring results (normal / abnormal notification and corresponding measures).

[0717] Specific actions

[0718] The server monitors the system status in real time and makes decisions based on the model's predictions. If the predicted energy output falls below a threshold, the server detects a system abnormality and notifies the user that maintenance is required. On the other hand, if the energy output is within the normal range, the system is deemed to be operating normally.

[0719] The above is the specific processing flow of this system.

[0720] (Application example 1)

[0721] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0722] Improving the efficiency and reliability of energy output in renewable energy systems is an urgent issue, and the associated need for real-time monitoring of the system health is also important.In addition, energy management is important in industrial facilities, and methods for efficiently managing energy consumption and curbing excessive consumption are required.

[0723] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0724] In this invention, the server includes means for collecting data from sensors, means for preprocessing the collected data, means for training a machine learning model using the preprocessed data, means for predicting energy output based on new sensor data, means for monitoring the system based on the predicted energy output and notifying maintenance as needed, and means for monitoring energy consumption of the industrial facility in real time and proposing optimal energy usage, thereby enabling improved efficiency and reliability of renewable energy systems and optimized energy management of industrial facilities.

[0725] A "sensor" is a device that measures a physical parameter and outputs it as digital data.

[0726] "Data collection means" refers to a means that has the function of aggregating and storing data obtained from sensors.

[0727] The "data preprocessing means" is a means for removing missing values ​​from collected data and extracting features.

[0728] A "machine learning model" is an algorithm that is trained using collected data to make predictions or classifications based on new data.

[0729] A "random forest classifier" is a machine learning model that creates multiple decision trees and combines them to make predictions.

[0730] "New sensor data" is the latest data collected from a sensor at any current or future time.

[0731] The "energy output prediction means" is a means for predicting energy output using new sensor data as input.

[0732] "System monitoring means" refers to means for monitoring the state of the system based on predicted energy output and notifying maintenance as necessary.

[0733] "Maintenance" refers to the maintenance and repair work carried out to maintain the health of the system.

[0734] An "industrial facility" is a place where manufacturing or production activities are carried out and is a facility that consumes a lot of energy.

[0735] "Energy consumption" is the amount of energy used within an industrial facility.

[0736] "Real-time monitoring" means observing the system status immediately and responding quickly if an abnormality occurs.

[0737] "Optimal energy usage" is a way to efficiently manage energy consumption and reduce waste.

[0738] MODE FOR CARRYING OUT THE INVENTION

[0739] The present invention provides a system for improving the efficiency and reliability of energy management systems in industrial facilities. The system predicts energy output using a machine learning model based on data collected from sensors and monitors and manages the system status in real time. The system includes the following main means: data collection means, data preprocessing means, model training means, energy output prediction means, and system monitoring means. The system also includes means for monitoring energy consumption in industrial facilities in real time and proposing optimal energy usage.

[0740] Data collection methods

[0741] The server collects data from sensors, which measure physical parameters such as temperature, wind speed, and humidity on equipment and robots in industrial facilities and send them to the server. For example, sensor data is often stored in CSV format.

[0742] Data preprocessing measures

[0743] The server preprocesses the collected data by removing missing values, extracting necessary features (e.g., temperature, wind speed, humidity), and setting targets (energy output), thus preparing the training data.

[0744] Model training methods

[0745] The server uses the preprocessed data to train a machine learning model, specifically a random forest classifier, to improve the accuracy of energy output predictions. This model learns from past data and can predict energy output for new data.

[0746] Energy output prediction means

[0747] The server predicts energy output based on new sensor data. For example, the latest sensor data (temperature 30 degrees, wind speed 15 m / s, humidity 70%) is input into the model to obtain a prediction result. The system's operating status is evaluated based on the predicted energy output.

[0748] System Monitoring Measures

[0749] The server monitors the system in real time, periodically updating the model based on data collected daily and predicting energy output. If the prediction detects a system abnormality, it notifies the user that maintenance is required. For example, if the predicted energy output is below a threshold, maintenance is recommended.

[0750] Energy consumption management measures

[0751] It has the means to monitor energy consumption in industrial facilities in real time and propose optimal energy usage, thereby reducing energy waste and achieving efficient energy management.

[0752] Specific examples

[0753] As a concrete example, in an energy management system at an industrial facility, when new sensor data is collected showing a temperature of 30 degrees, a wind speed of 15 m / s, and humidity of 70%, the server receives this data, preprocesses it, and inputs it into the model. The server then predicts energy output and evaluates the health of the system based on the prediction results. For example, if the predicted energy output is very low, the server notifies the user that maintenance is required. On the other hand, if the prediction shows normal energy output, the system is deemed to be continuing to operate efficiently, and no special action is required from the user.

[0754] Prompt Sentence Examples

[0755] "Predict the energy output when the temperature is 30 degrees, the wind speed is 15 m / s, and the humidity is 70%."

[0756] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0757] Step 1:

[0758] The server collects data from sensors. Specifically, physical parameters such as temperature, wind speed, and humidity are acquired in real time from each piece of equipment and robot in the industrial facility and sent to the server in digital form. The input is sensor data, and the output is raw digital data.

[0759] Step 2:

[0760] The server preprocesses the collected raw data. Specifically, it removes missing values ​​from the data and extracts necessary features (temperature, wind speed, humidity). After data preprocessing, it sets a target (energy output) and builds a training dataset. The input is raw data, and the output is preprocessed data.

[0761] Step 3:

[0762] The server uses the preprocessed data to train a machine learning model. Specifically, it uses a random forest classifier to improve the model's predictive accuracy. The model learns from past data and becomes able to accurately predict energy output for new data. The input is the preprocessed data, and the output is the trained model.

[0763] Step 4:

[0764] The server collects new sensor data and predicts energy output based on this new data. Specifically, the latest sensor data (e.g., temperature 30°C, wind speed 15m / s, humidity 70%) is input into the trained model to obtain a prediction result. The input is the new sensor data, and the output is the predicted energy output.

[0765] Step 5:

[0766] The server monitors the system based on the predicted energy output. Specifically, if the predicted result is below a threshold, it notifies the user that maintenance is required. If it is above the threshold, the energy output is normal and no special action is required. The input is the predicted result, and the output is the notification action.

[0767] Step 6:

[0768] The server monitors the energy consumption of industrial facilities in real time and proposes optimal energy usage. Specifically, it combines sensor data and model output to generate recommendations to reduce energy waste and optimize efficiency, and notifies the user. The input is real-time sensor data and model predictions, and the output is energy usage recommendations.

[0769] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0770] The present invention provides a system for improving the efficiency and reliability of renewable energy systems, which uses machine learning models to predict energy output based on data collected from sensors and monitors and manages the system status in real time. The system further has a function to adapt the notification method to the user by combining an emotion engine that recognizes the user's emotions.

[0771] Data collection methods

[0772] The server collects data from sensors. The sensors measure the physical parameters of the wind turbine, such as temperature, wind speed, and humidity, and sends the data to the server. For example, the various parameters of the wind turbine are saved in the format energy_data.csv.

[0773] Data preprocessing measures

[0774] The server preprocesses the collected data by removing missing values, extracting necessary features (e.g., temperature, wind speed, humidity), and setting targets (energy output). This prepares the training data.

[0775] Model training methods

[0776] The server uses the preprocessed data to train a machine learning model, using a random forest classifier, which learns from past data and is able to predict energy output for new data.

[0777] Energy output prediction means

[0778] The server predicts energy output based on new sensor data. For example, new sensor data (temperature 30 degrees, wind speed 15 m / s, humidity 70%) is input into the model and a prediction result is obtained. The model predicts energy output based on the input features and outputs the result.

[0779] System Monitoring Measures

[0780] The server monitors the system in real time. It periodically updates the model based on data collected daily and predicts energy output. If it detects a system abnormality based on the predicted energy output, it notifies the user that maintenance is required. For example, if the predicted energy output is 50% or less of normal, it issues a maintenance notification.

[0781] emotion recognition means

[0782] The server recognizes the user's emotions. The emotion engine analyzes the user's emotions from their voice and facial expressions, and adjusts the notification method from the system based on that information. For example, if the server determines that the user is feeling stressed, it will change the content and method of notifications and use more friendly language.

[0783] Specific examples

[0784] As a specific example, when newly collected sensor data (temperature 30 degrees, wind speed 15 m / s, humidity 70%) from a wind turbine is received by the server, preprocessed, and input into the model. The server then predicts energy output and evaluates the health of the system based on the prediction results. For example, if the predicted energy output is very low, the server notifies the user that maintenance is required. Furthermore, if the emotion engine analyzes that the user is in a state of high stress, the wording of the notification is changed to, "Thank you for your hard work. Your energy output is decreasing, so maintenance is required."

[0785] As described above, the present invention enables efficient operation and improved reliability of renewable energy systems, and also provides a flexible notification method that takes into consideration the user's feelings.

[0786] The processing flow will be explained below.

[0787] Step 1:

[0788] The server collects data from sensors. Specifically, sensors on the wind turbines acquire data such as temperature, wind speed, and humidity, and sends it to the server in real time. The server saves this data in the energy_data.csv format.

[0789] Step 2:

[0790] The server preprocesses the collected data. First, it reads the data from energy_data.csv and removes missing values. Then it extracts the necessary features (temperature, wind speed, humidity) from the data and sets the energy output as the target. This prepares the training dataset.

[0791] Step 3:

[0792] The server uses the preprocessed data to train a machine learning model. Specifically, it trains a random forest classifier using the preprocessed features and targets. The model learns from past data and is able to predict energy output for new data.

[0793] Step 4:

[0794] The server predicts energy output based on new sensor data. For example, the latest sensor data collected in real time (temperature 30 degrees, wind speed 15 m / s, humidity 70%) is input into the model to obtain a prediction result. The predicted energy output result is recorded on the server.

[0795] Step 5:

[0796] The server monitors the system in real time. It continuously updates the model based on new sensor data collected periodically. It uses the collected data to make predictions and detect anomalies in energy output. For example, an anomaly is detected if the predicted energy output is below a certain threshold.

[0797] Step 6:

[0798] The server uses an emotion engine to analyze the user's emotions. The emotion engine inputs the user's voice and facial expression data to determine the user's emotional state. For example, voice analysis can be used to determine whether the user is under stress.

[0799] Step 7:

[0800] The server adjusts the notification method based on the user's emotional state. For example, if the emotion engine determines that the user is feeling stressed, the notification method will be adjusted to use more friendly language and formatting. Specifically, the notification may say something like, "Thank you for your hard work. Your energy output is low, so maintenance is required."

[0801] Step 8:

[0802] The user receives notifications from the server, and based on the notifications, checks the system status and performs necessary maintenance work, for example, investigating the cause of the notified low energy output and adjusting or repairing the turbine.

[0803] The above is the specific processing flow of the EnergyEfficient platform using an emotion recognition engine. At each step, the server takes flexible measures that prioritize well-being, enabling efficient and stress-free operation for users.

[0804] Example 2

[0805] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0806] Renewable energy systems are expected to improve in efficiency and reliability. However, conventional systems have difficulty accurately analyzing data collected from sensors, resulting in insufficient energy output forecast accuracy and real-time system monitoring. Furthermore, communication with end users lacks the flexibility to respond to user emotions, limiting the effectiveness of maintenance and notifications. A new system is needed to solve these issues.

[0807] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0808] In this invention, the server includes means for collecting data from sensors, means for preprocessing the collected data, means for training a machine learning model using the preprocessed data, means for predicting energy output based on new sensor data, means for monitoring the system based on the predicted energy output and notifying maintenance as needed, means for recognizing a user's emotion, and means for adapting a notification method based on the recognized emotion information. This enables efficient operation and improved reliability of the renewable energy system. Furthermore, the notification method that takes user emotion into consideration can increase the user's sense of security and promote appropriate maintenance.

[0809] A "sensor" is a device that detects a physical parameter and transmits it as data to the outside.

[0810] "Data preprocessing" is the process of preparing collected data in a format suitable for training a machine learning model, such as by removing missing values ​​and extracting necessary features.

[0811] A "machine learning model" refers to an algorithm or mathematical model built to use data to predict future outputs or patterns.

[0812] A "random forest classifier" is a machine learning algorithm that uses multiple decision tree models to perform classification and regression.

[0813] "Energy output" refers to the amount of electricity or other energy produced from a renewable energy system.

[0814] "System monitoring" is the process of observing the system status in real time and notifying the user if an abnormality is detected.

[0815] "Maintenance notification" is a function that notifies the user that repair or inspection is required when an abnormality or problem occurs in the system.

[0816] "Emotion recognition" is a technology that analyzes a user's emotional state from their voice, facial expressions, etc., and uses the results to adjust their behavior and responses.

[0817] "Notification adaptation" refers to the process of optimizing the content and format of notifications based on the user's emotional state.

[0818] "Data collection" refers to the process of gathering observational data from sensors and other devices.

[0819] The present invention provides a system for improving the efficiency and reliability of renewable energy systems, which uses machine learning models to predict energy output based on data collected from sensors and monitors and manages the system status in real time. The system further has a function to adapt the notification method to the user by combining an emotion engine that recognizes the user's emotions.

[0820] Data collection methods

[0821] The server collects data from sensors. These sensors measure the physical parameters of the wind turbine, such as temperature, wind speed, and humidity, and then sends the data to the server. For example, the various parameters of the wind turbine are saved in the format energy_data.csv. Specifically, the data is obtained from the sensors in real time and stored on the server.

[0822] Data preprocessing measures

[0823] The server preprocesses the collected data by removing missing values, extracting necessary features (e.g., temperature, wind speed, humidity), and setting targets (energy output). This prepares the training data. The preprocessed data is stored in a database and used for the next model training.

[0824] Model training methods

[0825] The server uses the preprocessed data to train a machine learning model, using a random forest classifier, that learns from past data and can predict energy output based on new data. This trained model is stored locally and used for updates.

[0826] Energy output prediction means

[0827] The server predicts energy output based on new sensor data. For example, new sensor data such as a temperature of 30 degrees, a wind speed of 15 m / s, and humidity of 70% is input into the model, and a prediction result is obtained. The model output is stored in the server and used for subsequent system monitoring measures.

[0828] System Monitoring Measures

[0829] The server monitors the system in real time. Based on data collected daily, it periodically updates the model and predicts energy output. If it detects a system abnormality based on the predicted energy output, it notifies the user that maintenance is required. For example, if the predicted energy output is 50% or less of normal, it issues a maintenance notification.

[0830] emotion recognition means

[0831] The server recognizes the user's emotions. The emotion engine analyzes the user's emotions from their voice and facial expressions and adjusts the notification method based on that information. For example, if the server determines that the user is feeling stressed, it will change the content and method of the notification and use more friendly language.

[0832] Specific examples

[0833] When new sensor data (temperature 30 degrees, wind speed 15 m / s, humidity 70%) is collected from a wind turbine, the server receives it, preprocesses the data, and inputs it into the trained model. It then predicts the energy output and evaluates the health of the system based on the results. If the predicted energy output is very low, the server notifies the user that maintenance is required. Also, if the emotion engine analyzes that the user is in a high stress state, it changes the wording of the notification to "Thank you for your hard work, your energy output is decreasing, so maintenance is required."

[0834] Prompt Sentence Examples

[0835] "Use new sensor data to predict energy output and send maintenance notifications to users in case of low predictions."

[0836] "Can you give me an example of how you can change notification content based on user sentiment?"

[0837] "Please explain how you monitor your systems in real time."

[0838] As described above, the present invention enables efficient operation and improved reliability of renewable energy systems, and also provides a flexible notification method that takes into consideration the user's feelings.

[0839] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0840] Step 1: Data collection

[0841] The server collects data from sensors. The sensors measure physical parameters such as temperature, wind speed, and humidity of the wind turbines and send the data to the server. The input is the temperature, wind speed, and humidity data from the sensors, and the output is the energy_data.csv file containing these data. Specifically, the sensors send data in real time, and the server stores the data in an appropriate format.

[0842] Step 2: Data Preprocessing

[0843] The server preprocesses the collected data by removing missing values, extracting necessary features (temperature, wind speed, humidity), and setting the target (energy output). The input is the energy_data.csv file, and the output is the preprocessed dataset. This dataset has been cleaned of missing values ​​and incomplete data, and is formatted in a way that is suitable for machine learning models.

[0844] Step 3: Model training

[0845] The server uses the preprocessed data to train a machine learning model. Here, we use a random forest classifier. The input is the preprocessed dataset and the output is a trained machine learning model. The server uses this dataset to train the model so that it can predict energy output. The model is stored in the server and used in the next step.

[0846] Step 4: Energy output forecast

[0847] The server inputs new sensor data into the model and predicts the energy output. The input is the new sensor data (e.g., temperature 30 degrees, wind speed 15 m / s, humidity 70%), and the output is the predicted energy output. The server inputs new data into the model, obtains the prediction results, and stores them.

[0848] Step 5: System monitoring

[0849] The server monitors the system status in real time. The input is the sensor data collected daily and the predicted energy output, and the output is the system health assessment and maintenance notifications as needed. The server detects abnormal values ​​based on the collected data and predicted data, and if an abnormality is found, it sends a maintenance notification to the user. For example, if energy output is 50% or less of normal, a notification is sent to the user.

[0850] Step 6: Emotion Recognition

[0851] The server uses an emotion engine to recognize the user's emotions. The input is the user's voice and facial expression data, and the output is the user's emotional status. The emotion engine analyzes the user's emotions from their voice and facial expressions, and adjusts the notification method based on the results. For example, if the server determines that the user is feeling stressed, it will change the wording and content of the notification to be more friendly.

[0852] (Application example 2)

[0853] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0854] Conventional renewable energy systems were able to predict energy output and monitor the system with a certain degree of accuracy, but they had limitations in detecting software and hardware anomalies in real time and optimizing notification methods based on user emotions. Furthermore, factories operate many robots and devices, and monitoring their operating status in real time requires a large amount of information, making it difficult to provide efficient maintenance notifications. This can hinder the efficiency of energy management and reduce worker stress.

[0855] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data from sensors, means for preprocessing the collected data, means for training a machine learning model using the preprocessed data, means for predicting energy output based on new sensor data, means for monitoring the system based on the predicted energy output and notifying maintenance as necessary, means for recognizing user emotions and optimizing the notification method, and means for detecting abnormalities by monitoring the operation of equipment and robots in the factory in real time. This makes it possible to improve the efficiency of energy management in the factory, detect abnormalities early, and notify appropriate maintenance in accordance with the user's emotional state.

[0856] A "sensor" is a device that measures information from the physical environment and converts it into a digital or analog signal.

[0857] "Data collection" is the process of acquiring information generated by devices such as sensors and providing it to a system.

[0858] "Data preprocessing" refers to the process of converting collected raw data into an analyzable format, including missing value imputation and feature extraction.

[0859] A "machine learning model" is an algorithmic model that allows a system to make optimal decisions using collected data.

[0860] "Energy output forecasting" is a method of estimating future energy production based on data collected from sensors.

[0861] "System monitoring" is the process of checking the operating status of energy generation systems and related equipment in real time and detecting abnormalities.

[0862] "Maintenance notification" is the process of notifying relevant parties of necessary maintenance work when the system detects an abnormality.

[0863] "User emotion recognition" is a technology that uses devices such as cameras and microphones to analyze emotions from a user's facial expressions and voice.

[0864] "Notification method optimization" is the process of changing the content and method of notifications from the system depending on the user's emotional state.

[0865] "Real-time monitoring" is a method of constantly acquiring data and instantly analyzing and evaluating the current situation.

[0866] "Monitoring of equipment and robots in factories" is the process of checking the operating status of equipment and robots used in factories in real time.

[0867] "Abnormality detection" is a technology that identifies conditions that deviate from the normal operating range and notifies users that countermeasures are necessary.

[0868] The system for implementing this invention enables real-time monitoring of robots and equipment operating in a factory, optimization of energy management, and optimization of notification methods taking into account the emotional state of the user. Specific examples are shown below.

[0869] System Overview

[0870] The server collects data from various sensors installed in the factory, including devices that measure temperature, vibration, and power consumption, as well as from robots and machines, to monitor their operating status in real time.

[0871] The server preprocesses the collected data, completing missing values ​​and extracting features. This preprocessing prepares the data in an analyzable format. The server then uses a machine learning model, a random forest classifier, to predict energy output and system anomalies.

[0872] Furthermore, the server recognizes the user's emotions and optimizes the notification method. Specifically, it analyzes the user's facial expressions and voice through the smart glasses' camera and microphone to determine whether the user is feeling stressed. Based on this information, it adjusts the content and method of notifications, and notifies the user of maintenance using more user-friendly language and methods.

[0873] Hardware and software used

[0874] Hardware:

[0875] Smart glasses (e.g. Google Glass)

[0876] Various sensors (temperature sensors, vibration sensors, power measurement devices)

[0877] Server (performs data analysis and model training)

[0878] software:

[0879] Python (data analysis, machine learning)

[0880] TensorFlow (training machine learning models)

[0881] Scikit-learn (machine learning algorithms)

[0882] OpenCV (emotion recognition)

[0883] Specific examples

[0884] For example, imagine a robot in a factory is equipped with a temperature sensor, a vibration sensor, and a power measurement device. The data collected from these sensors (temperature, vibration, and power consumption) is analyzed in real time by a server. For example, if new sensor data such as "Temperature: 22 degrees, Vibration: 1.5G, Power consumption: 3000W" is collected, the machine learning model analyzes this data and predicts energy output. If a decrease or abnormality in energy output is detected as a result, the server immediately issues a maintenance notification.

[0885] On the other hand, when an engineer wearing smart glasses is on-site, the server analyzes the engineer's facial expressions and voice through the camera and microphone installed in the glasses to determine their stress level. For example, if it determines that the engineer is feeling stressed, it will notify them in a gentle manner, saying, "Thank you for your hard work. Equipment maintenance is required."

[0886] Prompt Sentence Examples

[0887] You want to use data about renewable energy to train a machine learning model to predict energy output and detect system anomalies. Example sensor data includes temperature, vibration, and power consumption. Additionally, you want the system to recognize user emotions and adapt notifications based on them. Build your model based on the following steps:

[0888] As described above, the present invention improves the efficiency of energy management within a factory, realizes early detection of abnormalities, and provides appropriate maintenance notifications according to the emotional state of the user.

[0889] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0890] Step 1:

[0891] Data collection

[0892] The server collects data from various sensors (temperature sensors, vibration sensors, power measurement devices, etc.) installed in the factory. Physical parameters (temperature, vibration, power consumption, etc.) sent from the sensors are sent to the server in real time, and this data is stored in a database. The input is sensor data, and the output is a set of formatted data.

[0893] Step 2:

[0894] Data Preprocessing

[0895] The server preprocesses the collected sensor data by imputing missing values, removing outliers, and extracting required features (temperature, vibration, power consumption). This process converts the raw data into an analyzable format. The input is the collected sensor data, and the output is a preprocessed dataset.

[0896] Step 3:

[0897] Training a machine learning model

[0898] The server uses the preprocessed data to train a machine learning model (random forest classifier). This model is used to predict energy output and anomalies from past data. The training data is input to the model, and a model that can make predictions with a certain level of accuracy is generated as output. Specifically, the dataset is divided into training data and test data, and these are input to the model to train it.

[0899] Step 4:

[0900] Energy output forecast

[0901] The server predicts energy output based on new sensor data. Newly collected temperature, vibration, and power consumption data is input into the model, which gives the predicted energy output as output. The model instantly calculates energy output based on the input data.

[0902] Step 5:

[0903] System Monitoring and Anomaly Detection

[0904] The server monitors the system in real time based on the predicted energy output and detects abnormalities. Specifically, it inputs data collected daily into the model and compares the predicted output with the actual output to detect abnormalities. If an abnormality is detected, it notifies the user that maintenance is required. The inputs are new sensor data and the output of the predictive model, and the output is the presence or absence of an abnormality and a notification of that presence.

[0905] Step 6:

[0906] User Emotion Recognition

[0907] The device (smart glasses) recognizes the user's emotions. It uses a camera and microphone to analyze the user's facial expressions and voice to determine whether the user is feeling stressed. The input is camera video and audio data, and the output is emotion recognition results. The emotion engine analyzes the user's emotions and sends the analysis results to the server.

[0908] Step 7:

[0909] Optimized notification method

[0910] The server optimizes the notification method based on the user's emotion recognition results. Specifically, it flexibly changes the content and wording of the notification, and if the user is feeling stressed, it notifies them in more friendly language. The input is the emotion recognition results and the maintenance notification content, and the optimized notification message is generated as the output.

[0911] In this way, it is possible to improve the efficiency of energy management within factories, detect abnormalities early, and provide flexible notifications according to the user's emotions.

[0912] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0913] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0914] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[0915] [Fourth embodiment]

[0916] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0917] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0918] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0919] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0920] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0921] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0922] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0923] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0924] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0925] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0926] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0927] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0928] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0929] The present invention provides a system for improving the efficiency and reliability of renewable energy systems, which uses a machine learning model to predict energy output based on data collected from sensors and monitors and manages the system status in real time. The system includes the following main means: data collection means, data preprocessing means, model training means, energy output prediction means, and system monitoring means.

[0930] Data collection methods

[0931] The server collects data from sensors. The sensors measure the physical parameters of the wind turbine, such as temperature, wind speed, and humidity, and sends the data to the server. For example, the various parameters of the wind turbine are saved in the format energy_data.csv.

[0932] Data preprocessing measures

[0933] The server preprocesses the collected data by removing missing values, extracting necessary features (e.g., temperature, wind speed, humidity), and setting targets (energy output). This prepares the training data.

[0934] Model training methods

[0935] The server uses the preprocessed data to train a machine learning model. Specifically, it trains a model using a random forest classifier to improve the accuracy of energy output predictions. This model learns from past data and can predict energy output for new data.

[0936] Energy output prediction means

[0937] The server predicts energy output based on new sensor data. For example, the latest sensor data (temperature 30°C, wind speed 15 m / s, humidity 70%) is input into the model to obtain a prediction result. The system's operating status is evaluated based on the predicted energy output.

[0938] System Monitoring Measures

[0939] The server monitors the system in real time. It periodically updates the model based on data collected daily and predicts energy output. If a system abnormality is detected based on the prediction results, it notifies the user that maintenance is required. For example, if the predicted energy output is below a threshold, maintenance is recommended.

[0940] Specific examples

[0941] As a specific example, when newly collected sensor data (temperature 30 degrees, wind speed 15 m / s, humidity 70%) from a wind turbine is received by the server, preprocessed, and input into the model. The server then predicts energy output and evaluates the health of the system based on the prediction results. For example, if the predicted energy output is very low, the server notifies the user that maintenance is required. On the other hand, if the prediction shows normal energy output, the system is deemed to continue operating efficiently, and no special action is required from the user.

[0942] As described above, the present invention provides specific means for enabling efficient operation and improved reliability of renewable energy systems.

[0943] The processing flow will be explained below.

[0944] Step 1:

[0945] The server collects data from the sensors, specifically, real-time data such as temperature, wind speed, and humidity of the wind turbines, and stores it in the format energy_data.csv.

[0946] Step 2:

[0947] The server preprocesses the collected data by removing missing values, extracting necessary features (e.g., temperature, wind speed, humidity), and setting the target (energy output). For example, the pandas library is used to remove missing values ​​in the data frame and extract necessary columns.

[0948] Step 3:

[0949] The server uses the preprocessed data to train a machine learning model. Specifically, it uses a random forest classifier to create a model for predicting energy output from historical data. The model learns from the training dataset to improve its prediction accuracy.

[0950] Step 4:

[0951] The server predicts energy output based on new sensor data. Specifically, the latest sensor data (e.g., temperature 30°C, wind speed 15m / s, humidity 70%) is input into the model to obtain the predicted results. The model predicts energy output based on the input features and outputs the results.

[0952] Step 5:

[0953] The server monitors the system in real time, periodically updating the model based on the latest collected data and predicting energy output. For example, data collected every 10 minutes is preprocessed and input into the model to obtain prediction results.

[0954] Step 6:

[0955] The server evaluates the health of the system based on the prediction results. Specifically, if the predicted energy output is below a certain threshold, an abnormality is detected and the user is notified that maintenance is required. For example, if the predicted energy output is 50% or less of normal, an alarm is issued.

[0956] Step 7:

[0957] Users receive maintenance notifications, check the status of their systems, and perform necessary maintenance tasks.

[0958] This concludes the specific processing flow of the EnergyEfficient platform. We have explained in detail the operations performed by the server at each step.

[0959] Example 1

[0960] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0961] To improve the efficiency and reliability of renewable energy systems, it is necessary to accurately predict energy output using data collected from sensors and to monitor and manage the system status in real time. However, conventional systems are not able to adequately deal with missing data or improve the accuracy of models, and they also face challenges in quickly responding to system abnormalities.

[0962] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0963] In this invention, the server includes means for collecting data from sensors, means for preprocessing the collected data, means for training a machine learning model using the preprocessed data, means for predicting energy output based on new sensor data, means for monitoring the system based on the predicted energy output and notifying maintenance as necessary, and means for notifying a user that maintenance is required when the system detects an abnormality, thereby improving the accuracy of energy output predictions and enabling system abnormalities to be detected and addressed quickly.

[0964] 1. A "sensor" is a device that measures a physical parameter and transmits that data to a server.

[0965] 2. "Data collection means" refers to the means by which the server receives and stores data collected from the sensors.

[0966] 3. "Data preprocessing means" refers to the means for removing missing values ​​from collected data, extracting necessary features, and setting target variables.

[0967] 4. A "machine learning model" is an algorithm that learns patterns and rules from large amounts of data and makes predictions and classifications for new data.

[0968] 5. "Model Training Means" means a means for training a machine learning model using preprocessed data.

[0969] 6. "Energy output forecasting means" means a means for forecasting energy output based on new sensor data.

[0970] 7. "System monitoring means" means a means for monitoring a system based on predicted energy output and notifying maintenance as needed.

[0971] 8. "Maintenance notification means" means a means of notifying users that maintenance is required when an abnormality is detected in the system.

[0972] 9. A "missing value" is a value that is missing in a dataset.

[0973] 10. "Feature" is a term that refers to the characteristics of data that a machine learning model uses for training.

[0974] 11. A "random forest classifier" is a machine learning algorithm that uses multiple decision trees to perform classification and regression.

[0975] The present invention is a system for improving the efficiency and reliability of renewable energy systems, and aims to predict energy output and monitor and manage the system status in real time using a machine learning model based on data collected from sensors. The system mainly includes the following means: data collection means, data preprocessing means, model training means, energy output prediction means, and system monitoring means.

[0976] In the phase where the server collects data from sensors, sensors installed on the wind turbines measure physical parameters (temperature, wind speed, humidity, etc.) and send the data to the server. The data is saved in the energy_data.csv format.

[0977] Next, the server moves to the preprocessing phase of the collected data, where it removes missing values, extracts necessary features such as temperature, wind speed, and humidity, and sets the target energy output, preparing the data for model training.

[0978] In the training phase, the server uses the preprocessed data to train the machine learning model, using a random forest classifier to learn patterns from past data and improve prediction accuracy for new data.

[0979] In the phase of predicting energy output based on new sensor data, the server inputs the latest sensor data into the model and obtains the predicted energy output. For example, input data of 30 degrees Celsius temperature, 15 m / s wind speed, and 70% humidity, and obtain the predicted energy output.

[0980] Finally, in the real-time monitoring phase, the server periodically updates the model based on data collected daily and predicts energy output. If an abnormality is detected in the system based on the prediction results, the server notifies the user that maintenance is required.

[0981] As a concrete example, when newly collected sensor data (temperature 30 degrees, wind speed 15 m / s, humidity 70%) from a wind turbine is received by the server, preprocessed, and input into the model. The server then predicts energy output and evaluates the health of the system based on the prediction results. For example, if the predicted energy output is very low, the server notifies the user that maintenance is required. On the other hand, if the prediction shows normal energy output, the system is deemed to continue operating efficiently, and no special action is required from the user.

[0982] An example prompt might have the following format:

[0983] "Please predict the energy output of a wind turbine using sensor data. Input the following data: temperature 30°C, wind speed 15m / s, humidity 70%. What is the predicted energy output? Also, based on this, please assess the health of the system and advise any necessary action."

[0984] As described above, the present invention provides specific means for realizing efficient operation and improved reliability of renewable energy systems.

[0985] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0986] Step 1:

[0987] Data collection

[0988] Input: Physical parameters (temperature, wind speed, humidity) from sensors installed on the wind turbines.

[0989] Output: Raw data saved in energy_data.csv.

[0990] Specific actions

[0991] The server collects physical parameters (e.g., temperature 30°C, wind speed 15 m / s, humidity 70%) from sensors installed on each wind turbine and saves the data in a file called energy_data.csv.

[0992] Step 2:

[0993] Data Preprocessing

[0994] Input: Raw data stored in energy_data.csv.

[0995] Output: A preprocessed dataset (data with missing values ​​removed and required features extracted).

[0996] Specific actions

[0997] The server reads the data from energy_data.csv, removes rows with missing values, extracts the required features (temperature, wind speed, humidity), and sets the energy output as the target variable, thus preparing the dataset for model training.

[0998] Step 3:

[0999] Model training

[1000] Input: The preprocessed dataset.

[1001] Output: A trained random forest classifier model.

[1002] Specific actions

[1003] The server uses the preprocessed dataset to train a random forest classifier, which learns patterns and relationships from past data and can accurately predict energy output for new data.

[1004] Step 4:

[1005] Energy Output Forecast

[1006] Input: New sensor data (temperature, wind speed, humidity).

[1007] Output: The predicted energy output value.

[1008] Specific actions

[1009] The server inputs new sensor data (e.g., temperature 30°C, wind speed 15 m / s, humidity 70%) into a trained random forest model to predict energy output, which is then used to assess the current health of the system.

[1010] Step 5:

[1011] System Monitoring

[1012] Input: The predicted energy output value.

[1013] Output: Monitoring results (normal / abnormal notification and corresponding measures).

[1014] Specific actions

[1015] The server monitors the system status in real time and makes decisions based on the model's predictions. If the predicted energy output falls below a threshold, the server detects a system abnormality and notifies the user that maintenance is required. On the other hand, if the energy output is within the normal range, the system is deemed to be operating normally.

[1016] The above is the specific processing flow of this system.

[1017] (Application example 1)

[1018] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1019] Improving the efficiency and reliability of energy output in renewable energy systems is an urgent issue, and the associated need for real-time monitoring of the system health is also important.In addition, energy management is important in industrial facilities, and methods for efficiently managing energy consumption and curbing excessive consumption are required.

[1020] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1021] In this invention, the server includes means for collecting data from sensors, means for preprocessing the collected data, means for training a machine learning model using the preprocessed data, means for predicting energy output based on new sensor data, means for monitoring the system based on the predicted energy output and notifying maintenance as needed, and means for monitoring energy consumption of the industrial facility in real time and proposing optimal energy usage, thereby enabling improved efficiency and reliability of renewable energy systems and optimized energy management of industrial facilities.

[1022] A "sensor" is a device that measures a physical parameter and outputs it as digital data.

[1023] "Data collection means" refers to a means that has the function of aggregating and storing data obtained from sensors.

[1024] The "data preprocessing means" is a means for removing missing values ​​from collected data and extracting features.

[1025] A "machine learning model" is an algorithm that is trained using collected data to make predictions or classifications based on new data.

[1026] A "random forest classifier" is a machine learning model that creates multiple decision trees and combines them to make predictions.

[1027] "New sensor data" is the latest data collected from a sensor at any current or future time.

[1028] The "energy output prediction means" is a means for predicting energy output using new sensor data as input.

[1029] "System monitoring means" refers to means for monitoring the state of the system based on predicted energy output and notifying maintenance as necessary.

[1030] "Maintenance" refers to the maintenance and repair work carried out to maintain the health of the system.

[1031] An "industrial facility" is a place where manufacturing or production activities are carried out and is a facility that consumes a lot of energy.

[1032] "Energy consumption" is the amount of energy used within an industrial facility.

[1033] "Real-time monitoring" means observing the system status immediately and responding quickly if an abnormality occurs.

[1034] "Optimal energy usage" is a way to efficiently manage energy consumption and reduce waste.

[1035] MODE FOR CARRYING OUT THE INVENTION

[1036] The present invention provides a system for improving the efficiency and reliability of energy management systems in industrial facilities. The system predicts energy output using a machine learning model based on data collected from sensors and monitors and manages the system status in real time. The system includes the following main means: data collection means, data preprocessing means, model training means, energy output prediction means, and system monitoring means. The system also includes means for monitoring energy consumption in industrial facilities in real time and proposing optimal energy usage.

[1037] Data collection methods

[1038] The server collects data from sensors, which measure physical parameters such as temperature, wind speed, and humidity on equipment and robots in industrial facilities and send them to the server. For example, sensor data is often stored in CSV format.

[1039] Data preprocessing measures

[1040] The server preprocesses the collected data by removing missing values, extracting necessary features (e.g., temperature, wind speed, humidity), and setting targets (energy output), thus preparing the training data.

[1041] Model training methods

[1042] The server uses the preprocessed data to train a machine learning model, specifically a random forest classifier, to improve the accuracy of energy output predictions. This model learns from past data and can predict energy output for new data.

[1043] Energy output prediction means

[1044] The server predicts energy output based on new sensor data. For example, the latest sensor data (temperature 30 degrees, wind speed 15 m / s, humidity 70%) is input into the model to obtain a prediction result. The system's operating status is evaluated based on the predicted energy output.

[1045] System Monitoring Measures

[1046] The server monitors the system in real time, periodically updating the model based on data collected daily and predicting energy output. If the prediction detects a system abnormality, it notifies the user that maintenance is required. For example, if the predicted energy output is below a threshold, maintenance is recommended.

[1047] Energy consumption management measures

[1048] It has the means to monitor energy consumption in industrial facilities in real time and propose optimal energy usage, thereby reducing energy waste and achieving efficient energy management.

[1049] Specific examples

[1050] As a concrete example, in an energy management system at an industrial facility, when new sensor data is collected showing a temperature of 30 degrees, a wind speed of 15 m / s, and humidity of 70%, the server receives this data, preprocesses it, and inputs it into the model. The server then predicts energy output and evaluates the health of the system based on the prediction results. For example, if the predicted energy output is very low, the server notifies the user that maintenance is required. On the other hand, if the prediction shows normal energy output, the system is deemed to be continuing to operate efficiently, and no special action is required from the user.

[1051] Prompt Sentence Examples

[1052] "Predict the energy output when the temperature is 30 degrees, the wind speed is 15 m / s, and the humidity is 70%."

[1053] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1054] Step 1:

[1055] The server collects data from sensors. Specifically, physical parameters such as temperature, wind speed, and humidity are acquired in real time from each piece of equipment and robot in the industrial facility and sent to the server in digital form. The input is sensor data, and the output is raw digital data.

[1056] Step 2:

[1057] The server preprocesses the collected raw data. Specifically, it removes missing values ​​from the data and extracts necessary features (temperature, wind speed, humidity). After data preprocessing, it sets a target (energy output) and builds a training dataset. The input is raw data, and the output is preprocessed data.

[1058] Step 3:

[1059] The server uses the preprocessed data to train a machine learning model. Specifically, it uses a random forest classifier to improve the model's predictive accuracy. The model learns from past data and becomes able to accurately predict energy output for new data. The input is the preprocessed data, and the output is the trained model.

[1060] Step 4:

[1061] The server collects new sensor data and predicts energy output based on this new data. Specifically, the latest sensor data (e.g., temperature 30°C, wind speed 15m / s, humidity 70%) is input into the trained model to obtain a prediction result. The input is the new sensor data, and the output is the predicted energy output.

[1062] Step 5:

[1063] The server monitors the system based on the predicted energy output. Specifically, if the predicted result is below a threshold, it notifies the user that maintenance is required. If it is above the threshold, the energy output is normal and no special action is required. The input is the predicted result, and the output is the notification action.

[1064] Step 6:

[1065] The server monitors the energy consumption of industrial facilities in real time and proposes optimal energy usage. Specifically, it combines sensor data and model output to generate recommendations to reduce energy waste and optimize efficiency, and notifies the user. The input is real-time sensor data and model predictions, and the output is energy usage recommendations.

[1066] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1067] The present invention provides a system for improving the efficiency and reliability of renewable energy systems, which uses machine learning models to predict energy output based on data collected from sensors and monitors and manages the system status in real time. The system further has a function to adapt the notification method to the user by combining an emotion engine that recognizes the user's emotions.

[1068] Data collection methods

[1069] The server collects data from sensors. The sensors measure the physical parameters of the wind turbine, such as temperature, wind speed, and humidity, and sends the data to the server. For example, the various parameters of the wind turbine are saved in the format energy_data.csv.

[1070] Data preprocessing measures

[1071] The server preprocesses the collected data by removing missing values, extracting necessary features (e.g., temperature, wind speed, humidity), and setting targets (energy output). This prepares the training data.

[1072] Model training methods

[1073] The server uses the preprocessed data to train a machine learning model, using a random forest classifier, which learns from past data and is able to predict energy output for new data.

[1074] Energy output prediction means

[1075] The server predicts energy output based on new sensor data. For example, new sensor data (temperature 30 degrees, wind speed 15 m / s, humidity 70%) is input into the model and a prediction result is obtained. The model predicts energy output based on the input features and outputs the result.

[1076] System Monitoring Measures

[1077] The server monitors the system in real time. It periodically updates the model based on data collected daily and predicts energy output. If it detects a system abnormality based on the predicted energy output, it notifies the user that maintenance is required. For example, if the predicted energy output is 50% or less of normal, it issues a maintenance notification.

[1078] emotion recognition means

[1079] The server recognizes the user's emotions. The emotion engine analyzes the user's emotions from their voice and facial expressions, and adjusts the notification method from the system based on that information. For example, if the server determines that the user is feeling stressed, it will change the content and method of notifications and use more friendly language.

[1080] Specific examples

[1081] As a specific example, when newly collected sensor data (temperature 30 degrees, wind speed 15 m / s, humidity 70%) from a wind turbine is received by the server, preprocessed, and input into the model. The server then predicts energy output and evaluates the health of the system based on the prediction results. For example, if the predicted energy output is very low, the server notifies the user that maintenance is required. Furthermore, if the emotion engine analyzes that the user is in a state of high stress, the wording of the notification is changed to, "Thank you for your hard work. Your energy output is decreasing, so maintenance is required."

[1082] As described above, the present invention enables efficient operation and improved reliability of renewable energy systems, and also provides a flexible notification method that takes into consideration the user's feelings.

[1083] The processing flow will be explained below.

[1084] Step 1:

[1085] The server collects data from sensors. Specifically, sensors on the wind turbines acquire data such as temperature, wind speed, and humidity, and sends it to the server in real time. The server saves this data in the energy_data.csv format.

[1086] Step 2:

[1087] The server preprocesses the collected data. First, it reads the data from energy_data.csv and removes missing values. Then it extracts the necessary features (temperature, wind speed, humidity) from the data and sets the energy output as the target. This prepares the training dataset.

[1088] Step 3:

[1089] The server uses the preprocessed data to train a machine learning model. Specifically, it trains a random forest classifier using the preprocessed features and targets. The model learns from past data and is able to predict energy output for new data.

[1090] Step 4:

[1091] The server predicts energy output based on new sensor data. For example, the latest sensor data collected in real time (temperature 30 degrees, wind speed 15 m / s, humidity 70%) is input into the model to obtain a prediction result. The predicted energy output result is recorded on the server.

[1092] Step 5:

[1093] The server monitors the system in real time. It continuously updates the model based on new sensor data collected periodically. It uses the collected data to make predictions and detect anomalies in energy output. For example, an anomaly is detected if the predicted energy output is below a certain threshold.

[1094] Step 6:

[1095] The server uses an emotion engine to analyze the user's emotions. The emotion engine inputs the user's voice and facial expression data to determine the user's emotional state. For example, voice analysis can be used to determine whether the user is under stress.

[1096] Step 7:

[1097] The server adjusts the notification method based on the user's emotional state. For example, if the emotion engine determines that the user is feeling stressed, the notification method will be adjusted to use more friendly language and formatting. Specifically, the notification may say something like, "Thank you for your hard work. Your energy output is low, so maintenance is required."

[1098] Step 8:

[1099] The user receives notifications from the server, and based on the notifications, checks the system status and performs necessary maintenance work, for example, investigating the cause of the notified low energy output and adjusting or repairing the turbine.

[1100] The above is the specific processing flow of the EnergyEfficient platform using an emotion recognition engine. At each step, the server takes flexible measures that prioritize well-being, enabling efficient and stress-free operation for users.

[1101] Example 2

[1102] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1103] Renewable energy systems are expected to improve in efficiency and reliability. However, conventional systems have difficulty accurately analyzing data collected from sensors, resulting in insufficient energy output forecast accuracy and real-time system monitoring. Furthermore, communication with end users lacks the flexibility to respond to user emotions, limiting the effectiveness of maintenance and notifications. A new system is needed to solve these issues.

[1104] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1105] In this invention, the server includes means for collecting data from sensors, means for preprocessing the collected data, means for training a machine learning model using the preprocessed data, means for predicting energy output based on new sensor data, means for monitoring the system based on the predicted energy output and notifying maintenance as needed, means for recognizing a user's emotion, and means for adapting a notification method based on the recognized emotion information. This enables efficient operation and improved reliability of the renewable energy system. Furthermore, the notification method that takes user emotion into consideration can increase the user's sense of security and promote appropriate maintenance.

[1106] A "sensor" is a device that detects a physical parameter and transmits it as data to the outside.

[1107] "Data preprocessing" is the process of preparing collected data in a format suitable for training a machine learning model, such as by removing missing values ​​and extracting necessary features.

[1108] A "machine learning model" refers to an algorithm or mathematical model built to use data to predict future outputs or patterns.

[1109] A "random forest classifier" is a machine learning algorithm that uses multiple decision tree models to perform classification and regression.

[1110] "Energy output" refers to the amount of electricity or other energy produced from a renewable energy system.

[1111] "System monitoring" is the process of observing the system status in real time and notifying the user if an abnormality is detected.

[1112] "Maintenance notification" is a function that notifies the user that repair or inspection is required when an abnormality or problem occurs in the system.

[1113] "Emotion recognition" is a technology that analyzes a user's emotional state from their voice, facial expressions, etc., and uses the results to adjust their behavior and responses.

[1114] "Notification adaptation" refers to the process of optimizing the content and format of notifications based on the user's emotional state.

[1115] "Data collection" refers to the process of gathering observational data from sensors and other devices.

[1116] The present invention provides a system for improving the efficiency and reliability of renewable energy systems, which uses machine learning models to predict energy output based on data collected from sensors and monitors and manages the system status in real time. The system further has a function to adapt the notification method to the user by combining an emotion engine that recognizes the user's emotions.

[1117] Data collection methods

[1118] The server collects data from sensors. These sensors measure the physical parameters of the wind turbine, such as temperature, wind speed, and humidity, and then sends the data to the server. For example, the various parameters of the wind turbine are saved in the format energy_data.csv. Specifically, the data is obtained from the sensors in real time and stored on the server.

[1119] Data preprocessing measures

[1120] The server preprocesses the collected data by removing missing values, extracting necessary features (e.g., temperature, wind speed, humidity), and setting targets (energy output). This prepares the training data. The preprocessed data is stored in a database and used for the next model training.

[1121] Model training methods

[1122] The server uses the preprocessed data to train a machine learning model, using a random forest classifier, that learns from past data and can predict energy output based on new data. This trained model is stored locally and used for updates.

[1123] Energy output prediction means

[1124] The server predicts energy output based on new sensor data. For example, new sensor data such as a temperature of 30 degrees, a wind speed of 15 m / s, and humidity of 70% is input into the model, and a prediction result is obtained. The model output is stored in the server and used for subsequent system monitoring measures.

[1125] System Monitoring Measures

[1126] The server monitors the system in real time. Based on data collected daily, it periodically updates the model and predicts energy output. If it detects a system abnormality based on the predicted energy output, it notifies the user that maintenance is required. For example, if the predicted energy output is 50% or less of normal, it issues a maintenance notification.

[1127] emotion recognition means

[1128] The server recognizes the user's emotions. The emotion engine analyzes the user's emotions from their voice and facial expressions and adjusts the notification method based on that information. For example, if the server determines that the user is feeling stressed, it will change the content and method of the notification and use more friendly language.

[1129] Specific examples

[1130] When new sensor data (temperature 30 degrees, wind speed 15 m / s, humidity 70%) is collected from a wind turbine, the server receives it, preprocesses the data, and inputs it into the trained model. It then predicts the energy output and evaluates the health of the system based on the results. If the predicted energy output is very low, the server notifies the user that maintenance is required. Also, if the emotion engine analyzes that the user is in a high stress state, it changes the wording of the notification to "Thank you for your hard work, your energy output is decreasing, so maintenance is required."

[1131] Prompt Sentence Examples

[1132] "Use new sensor data to predict energy output and send maintenance notifications to users in case of low predictions."

[1133] "Can you give me an example of how you can change notification content based on user sentiment?"

[1134] "Please explain how you monitor your systems in real time."

[1135] As described above, the present invention enables efficient operation and improved reliability of renewable energy systems, and also provides a flexible notification method that takes into consideration the user's feelings.

[1136] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1137] Step 1: Data collection

[1138] The server collects data from sensors. The sensors measure physical parameters such as temperature, wind speed, and humidity of the wind turbines and send the data to the server. The input is the temperature, wind speed, and humidity data from the sensors, and the output is the energy_data.csv file containing these data. Specifically, the sensors send data in real time, and the server stores the data in an appropriate format.

[1139] Step 2: Data Preprocessing

[1140] The server preprocesses the collected data by removing missing values, extracting necessary features (temperature, wind speed, humidity), and setting the target (energy output). The input is the energy_data.csv file, and the output is the preprocessed dataset. This dataset has been cleaned of missing values ​​and incomplete data, and is formatted in a way that is suitable for machine learning models.

[1141] Step 3: Model training

[1142] The server uses the preprocessed data to train a machine learning model. Here, we use a random forest classifier. The input is the preprocessed dataset and the output is a trained machine learning model. The server uses this dataset to train the model so that it can predict energy output. The model is stored in the server and used in the next step.

[1143] Step 4: Energy output forecast

[1144] The server inputs new sensor data into the model and predicts the energy output. The input is the new sensor data (e.g., temperature 30 degrees, wind speed 15 m / s, humidity 70%), and the output is the predicted energy output. The server inputs new data into the model, obtains the prediction results, and stores them.

[1145] Step 5: System monitoring

[1146] The server monitors the system status in real time. The input is the sensor data collected daily and the predicted energy output, and the output is the system health assessment and maintenance notifications as needed. The server detects abnormal values ​​based on the collected data and predicted data, and if an abnormality is found, it sends a maintenance notification to the user. For example, if energy output is 50% or less of normal, a notification is sent to the user.

[1147] Step 6: Emotion Recognition

[1148] The server uses an emotion engine to recognize the user's emotions. The input is the user's voice and facial expression data, and the output is the user's emotional status. The emotion engine analyzes the user's emotions from their voice and facial expressions, and adjusts the notification method based on the results. For example, if the server determines that the user is feeling stressed, it will change the wording and content of the notification to be more friendly.

[1149] (Application example 2)

[1150] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1151] Conventional renewable energy systems were able to predict energy output and monitor the system with a certain degree of accuracy, but they had limitations in detecting software and hardware anomalies in real time and optimizing notification methods based on user emotions. Furthermore, factories operate many robots and devices, and monitoring their operating status in real time requires a large amount of information, making it difficult to provide efficient maintenance notifications. This can hinder the efficiency of energy management and reduce worker stress.

[1152] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data from sensors, means for preprocessing the collected data, means for training a machine learning model using the preprocessed data, means for predicting energy output based on new sensor data, means for monitoring the system based on the predicted energy output and notifying maintenance as necessary, means for recognizing user emotions and optimizing the notification method, and means for detecting abnormalities by monitoring the operation of equipment and robots in the factory in real time. This makes it possible to improve the efficiency of energy management in the factory, detect abnormalities early, and notify appropriate maintenance in accordance with the user's emotional state.

[1153] A "sensor" is a device that measures information from the physical environment and converts it into a digital or analog signal.

[1154] "Data collection" is the process of acquiring information generated by devices such as sensors and providing it to a system.

[1155] "Data preprocessing" refers to the process of converting collected raw data into an analyzable format, including missing value imputation and feature extraction.

[1156] A "machine learning model" is an algorithmic model that allows a system to make optimal decisions using collected data.

[1157] "Energy output forecasting" is a method of estimating future energy production based on data collected from sensors.

[1158] "System monitoring" is the process of checking the operating status of energy generation systems and related equipment in real time and detecting abnormalities.

[1159] "Maintenance notification" is the process of notifying relevant parties of necessary maintenance work when the system detects an abnormality.

[1160] "User emotion recognition" is a technology that uses devices such as cameras and microphones to analyze emotions from a user's facial expressions and voice.

[1161] "Notification method optimization" is the process of changing the content and method of notifications from the system depending on the user's emotional state.

[1162] "Real-time monitoring" is a method of constantly acquiring data and instantly analyzing and evaluating the current situation.

[1163] "Monitoring of equipment and robots in factories" is the process of checking the operating status of equipment and robots used in factories in real time.

[1164] "Abnormality detection" is a technology that identifies conditions that deviate from the normal operating range and notifies users that countermeasures are necessary.

[1165] The system for implementing this invention enables real-time monitoring of robots and equipment operating in a factory, optimization of energy management, and optimization of notification methods taking into account the emotional state of the user. Specific examples are shown below.

[1166] System Overview

[1167] The server collects data from various sensors installed in the factory, including devices that measure temperature, vibration, and power consumption, as well as from robots and machines, to monitor their operating status in real time.

[1168] The server preprocesses the collected data, completing missing values ​​and extracting features. This preprocessing prepares the data in an analyzable format. The server then uses a machine learning model, a random forest classifier, to predict energy output and system anomalies.

[1169] Furthermore, the server recognizes the user's emotions and optimizes the notification method. Specifically, it analyzes the user's facial expressions and voice through the smart glasses' camera and microphone to determine whether the user is feeling stressed. Based on this information, it adjusts the content and method of notifications, and notifies the user of maintenance using more user-friendly language and methods.

[1170] Hardware and software used

[1171] Hardware:

[1172] Smart glasses (e.g. Google Glass)

[1173] Various sensors (temperature sensors, vibration sensors, power measurement devices)

[1174] Server (performs data analysis and model training)

[1175] software:

[1176] Python (data analysis, machine learning)

[1177] TensorFlow (training machine learning models)

[1178] Scikit-learn (machine learning algorithms)

[1179] OpenCV (emotion recognition)

[1180] Specific examples

[1181] For example, imagine a robot in a factory is equipped with a temperature sensor, a vibration sensor, and a power measurement device. The data collected from these sensors (temperature, vibration, and power consumption) is analyzed in real time by a server. For example, if new sensor data such as "Temperature: 22 degrees, Vibration: 1.5G, Power consumption: 3000W" is collected, the machine learning model analyzes this data and predicts energy output. If a decrease or abnormality in energy output is detected as a result, the server immediately issues a maintenance notification.

[1182] On the other hand, when an engineer wearing smart glasses is on-site, the server analyzes the engineer's facial expressions and voice through the camera and microphone installed in the glasses to determine their stress level. For example, if it determines that the engineer is feeling stressed, it will notify them in a gentle manner, saying, "Thank you for your hard work. Equipment maintenance is required."

[1183] Prompt Sentence Examples

[1184] You want to use data about renewable energy to train a machine learning model to predict energy output and detect system anomalies. Example sensor data includes temperature, vibration, and power consumption. Additionally, you want the system to recognize user emotions and adapt notifications based on them. Build your model based on the following steps:

[1185] As described above, the present invention improves the efficiency of energy management within a factory, realizes early detection of abnormalities, and provides appropriate maintenance notifications according to the emotional state of the user.

[1186] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1187] Step 1:

[1188] Data collection

[1189] The server collects data from various sensors (temperature sensors, vibration sensors, power measurement devices, etc.) installed in the factory. Physical parameters (temperature, vibration, power consumption, etc.) sent from the sensors are sent to the server in real time, and this data is stored in a database. The input is sensor data, and the output is a set of formatted data.

[1190] Step 2:

[1191] Data Preprocessing

[1192] The server preprocesses the collected sensor data by imputing missing values, removing outliers, and extracting required features (temperature, vibration, power consumption). This process converts the raw data into an analyzable format. The input is the collected sensor data, and the output is a preprocessed dataset.

[1193] Step 3:

[1194] Training a machine learning model

[1195] The server uses the preprocessed data to train a machine learning model (random forest classifier). This model is used to predict energy output and anomalies from past data. The training data is input to the model, and a model that can make predictions with a certain level of accuracy is generated as output. Specifically, the dataset is divided into training data and test data, and these are input to the model to train it.

[1196] Step 4:

[1197] Energy output forecast

[1198] The server predicts energy output based on new sensor data. Newly collected temperature, vibration, and power consumption data is input into the model, which gives the predicted energy output as output. The model instantly calculates energy output based on the input data.

[1199] Step 5:

[1200] System Monitoring and Anomaly Detection

[1201] The server monitors the system in real time based on the predicted energy output and detects abnormalities. Specifically, it inputs data collected daily into the model and compares the predicted output with the actual output to detect abnormalities. If an abnormality is detected, it notifies the user that maintenance is required. The inputs are new sensor data and the output of the predictive model, and the output is the presence or absence of an abnormality and a notification of that presence.

[1202] Step 6:

[1203] User Emotion Recognition

[1204] The device (smart glasses) recognizes the user's emotions. It uses a camera and microphone to analyze the user's facial expressions and voice to determine whether the user is feeling stressed. The input is camera video and audio data, and the output is emotion recognition results. The emotion engine analyzes the user's emotions and sends the analysis results to the server.

[1205] Step 7:

[1206] Optimized notification method

[1207] The server optimizes the notification method based on the user's emotion recognition results. Specifically, it flexibly changes the content and wording of the notification, and if the user is feeling stressed, it notifies them in more friendly language. The input is the emotion recognition results and the maintenance notification content, and the optimized notification message is generated as the output.

[1208] In this way, it is possible to improve the efficiency of energy management within factories, detect abnormalities early, and provide flexible notifications according to the user's emotions.

[1209] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1210] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1211] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1212] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1213] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1214] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1215] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1216] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1217] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1218] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1219] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1220] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1221] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1222] 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.

[1223] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1224] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1225] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1226] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1227] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1228] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1229] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1230] The following is further disclosed regarding the above embodiment.

[1231] (Claim 1)

[1232] a means for collecting data from the sensor;

[1233] means for pre-processing the collected data;

[1234] means for training a machine learning model using the preprocessed data;

[1235] a means for predicting energy output based on new sensor data;

[1236] means for monitoring the system based on said predicted energy output and notifying maintenance as necessary;

[1237] A system including:

[1238] (Claim 2)

[1239] 10. The system of claim 1, further comprising means for removing missing values ​​from the collected data and extracting a plurality of features.

[1240] (Claim 3)

[1241] 2. The system of claim 1, wherein the machine learning model is a random forest classifier.

[1242] "Example 1"

[1243] (Claim 1)

[1244] a means for collecting data from the sensor;

[1245] means for pre-processing the collected data;

[1246] means for training a machine learning model using the preprocessed data;

[1247] a means for predicting energy output based on new sensor data;

[1248] means for monitoring the system based on said predicted energy output and notifying maintenance as necessary;

[1249] means for notifying a user that maintenance is required when the system detects an abnormality;

[1250] A system including:

[1251] (Claim 2)

[1252] 10. The system of claim 1, further comprising means for removing missing values ​​from the collected data and extracting a plurality of features.

[1253] (Claim 3)

[1254] 2. The system of claim 1, wherein the machine learning model is a random forest classifier.

[1255] "Application Example 1"

[1256] (Claim 1)

[1257] a means for collecting data from the sensor;

[1258] means for pre-processing the collected data;

[1259] means for training a machine learning model using the preprocessed data;

[1260] a means for predicting energy output based on new sensor data;

[1261] means for monitoring the system based on said predicted energy output and notifying maintenance as necessary;

[1262] A means of monitoring energy consumption in industrial facilities in real time and suggesting optimal energy usage;

[1263] A system including:

[1264] (Claim 2)

[1265] 10. The system of claim 1, further comprising means for removing missing values ​​from the collected data and extracting a plurality of features.

[1266] (Claim 3)

[1267] 2. The system of claim 1, wherein the machine learning model is a random forest classifier.

[1268] "Example 2: Combining Emotion Engines"

[1269] (Claim 1)

[1270] a means for collecting data from the sensor;

[1271] means for pre-processing the collected data;

[1272] means for training a machine learning model using the preprocessed data;

[1273] a means for predicting energy output based on new sensor data;

[1274] means for monitoring the system based on said predicted energy output and notifying maintenance as necessary;

[1275] means for recognizing a user's emotion;

[1276] means for adapting a notification method based on the recognized emotion information;

[1277] A system including:

[1278] (Claim 2)

[1279] 10. The system of claim 1, further comprising means for removing missing values ​​from the collected data and extracting a plurality of features.

[1280] (Claim 3)

[1281] 2. The system of claim 1, wherein the machine learning model is a random forest classifier.

[1282] "Application example 2 when combining emotion engines"

[1283] (Claim 1)

[1284] a means for collecting data from the sensor;

[1285] means for pre-processing the collected data;

[1286] means for training a machine learning model using the preprocessed data;

[1287] a means for predicting energy output based on new sensor data;

[1288] means for monitoring the system based on said predicted energy output and notifying maintenance as necessary;

[1289] A means for recognizing a user's emotions and optimizing the notification method;

[1290] A means of detecting abnormalities by monitoring the operation of equipment and robots in the factory in real time,

[1291] A system including:

[1292] (Claim 2)

[1293] 10. The system of claim 1, further comprising means for removing missing values ​​from the collected data and extracting a plurality of features.

[1294] (Claim 3)

[1295] 2. The system of claim 1, wherein the machine learning model is a random forest classifier. [Explanation of symbols]

[1296] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for collecting data from the sensor; means for pre-processing the collected data; means for training a machine learning model using the preprocessed data; a means for predicting energy output based on new sensor data; means for monitoring the system based on said predicted energy output and notifying maintenance as necessary; A system including:

2. The system of claim 1 further comprising means for removing missing values ​​from the collected data and extracting a plurality of features.

3. The system of claim 1 , wherein the machine learning model is a random forest classifier.

Images