System

Abstract

A system is provided.SOLUTION: A system that achieves efficient power generation of a solar panel based on means for acquiring solar radiation amount data, means for acquiring weather data and a power generation history, means for predicting an optimum angle and direction of the solar panel using a generation model, means for transmitting the predicted angle and direction to a single-axis tracking system, means for predicting a deterioration state of the solar panel, and means for detecting an abnormality or a failure sign and notifying maintenance.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] ---

[0005] In conventional solar power generation systems, the angle and direction of solar panels are either fixed or require manual adjustment, making it difficult to achieve optimal power generation efficiency. Furthermore, there are limited means to detect signs of solar panel deterioration or failure in advance, resulting in problems such as unexpected downtime and increased maintenance costs. Furthermore, there are insufficient means for users to monitor the status of solar panels in real time, making efficient management difficult. There is a need for a system that solves these issues and streamlines maintenance management while maximizing power generation efficiency. [Means for solving the problem]

[0006] The present invention provides a system that includes means for acquiring solar radiation data, means for acquiring weather data and power generation history, means for predicting the optimal solar panel angle and direction using a generative model, means for transmitting the predicted angle and direction to a single-axis tracking system, means for predicting the deterioration state of the solar panels, and means for detecting abnormalities and signs of failure and notifying maintenance. The system also includes means for collecting sensor data to monitor the status of the solar panels, automatically adjusting the maintenance schedule based on the data, and notifying the user of the maintenance schedule. The system also includes means for the user to check the status of the solar panels in real time using a dedicated application and to query the server with any questions or requests. This system maximizes power generation efficiency and enables early detection of signs of deterioration and failure, thereby achieving efficient maintenance management.

[0007] ---

[0008] "Solar radiation data" is data that indicates the amount of solar radiation energy that reaches the earth's surface from the sun.

[0009] "Weather data" is data that indicates information about weather conditions, and includes temperature, humidity, wind speed, precipitation, and the like.

[0010] "Power generation history" is data that shows a past record of power generated by the solar panels.

[0011] A "generative model" is a type of machine learning model used to derive optimal solutions based on large amounts of data.

[0012] "Solar panel angle" refers to the angle that the surface of the solar panel forms with the ground.

[0013] "Solar panel orientation" refers to the direction in which the solar panel is facing.

[0014] A "single-axis tracking system" is a system that automatically adjusts the angle and direction of a solar panel along a single axis.

[0015] "Sensor data" refers to data obtained from various sensors, including the voltage, current, and temperature of the solar panel.

[0016] "Deteriorated state" refers to a state in which the performance of a solar panel has declined due to the length of use or environmental factors.

[0017] "Abnormalities and signs of failure" refer to signs of deviation from normal operation or signs of failure in solar panels or their related systems.

[0018] A "maintenance schedule" is a timetable for carrying out planned maintenance and inspection work on solar panels and the entire system.

[0019] "User" refers to the person who operates the system to obtain information and give instructions. [Brief explanation of the drawings]

[0020] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7]FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0021] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0023] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0024] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0025] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0026] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0027] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0028] [First embodiment]

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

[0030] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0031] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0032] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0033] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0034] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0035] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0037] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0038] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0039] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0040] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0041] ---

[0042] The present invention aims to efficiently utilize renewable energy, and specifically relates to a system that maximizes the power generation efficiency of solar panels. This system is composed of a server, a terminal, and a user element.

[0043] The server has the following main functions. First, it periodically acquires solar radiation data, weather data, and power generation history data, and inputs this data into a generative model to predict the optimal angle and direction of the solar panels. Next, it sends the prediction results of the generative model to a single-axis tracking system, which automatically adjusts the angle and direction of the solar panels. Furthermore, it predicts the deterioration state of the solar panels based on data acquired from sensors, detects signs of abnormalities or failures, and notifies the user. This makes it possible to automatically adjust an appropriate maintenance schedule and notify the user.

[0044] The terminal mainly provides the user interface. Users can monitor the status of the solar panels in real time through a dedicated application. For example, they can check information such as the current amount of power generated, the angle and direction of the solar panels, and the state of deterioration. Users can also send inquiries or requests to the server via the terminal and receive the results.

[0045] To use the system effectively, users periodically check the information provided, perform maintenance as needed, and respond to notifications from the server. For example, if a notification arrives from the server stating that "maintenance is required," the user responds promptly and performs appropriate maintenance to maintain stable system operation.

[0046] As a specific example, the server collects solar radiation data, weather data, and power generation history data every morning at 6:00 a.m., and based on this, the generative model predicts optimal settings such as "angle: 30 degrees, direction: south-southeast." This prediction result is sent to the single-axis tracking system, and the solar panels are automatically adjusted. At the same time, sensor data is also collected, and if signs of deterioration or abnormalities are detected, a notification is sent to the user's device stating, "Signs of deterioration have been detected. Maintenance is recommended." The user receives this notification, checks detailed information through the application, and adjusts the maintenance schedule.

[0047] Key features of this system include data-based prediction and automatic adjustment, early detection of deterioration and abnormalities, and efficient maintenance management through user interaction, which maximizes the power generation efficiency of the solar panels and ensures stable operation of the system.

[0048] The processing flow will be explained below.

[0049] ---

[0050] Step 1:

[0051] The server collects solar radiation data, weather data, and power generation history data at a fixed time every day. The server accesses each data source via API, collects the data, and stores it in a local database.

[0052] Step 2:

[0053] The server inputs the accumulated data into the generative model, which then combines solar radiation data, weather data, and power generation history and passes it to the generative model to predict the optimal angle and direction of the solar panels.

[0054] Step 3:

[0055] The server sends the prediction results of the generative model to the single-axis tracking system, which automatically adjusts the solar panel by sending prediction results such as "angle: 30 degrees, direction: south-southeast" to the tracking system.

[0056] Step 4:

[0057] The tracking system adjusts the angle and orientation of the solar panels based on the received predictions. The tracking system controls the motors to change the physical position of the solar panels.

[0058] Step 5:

[0059] The server collects solar panel data from sensors, including voltage, current, and temperature, in real time, and monitors for signs of abnormalities or deterioration.

[0060] Step 6:

[0061] The server predicts the deterioration state based on the collected sensor data, and inputs the sensor data into a deterioration prediction model to detect signs of deterioration and abnormalities.

[0062] Step 7:

[0063] If the server detects an abnormality or a sign of a failure, it will notify the user. When an abnormality is detected, the server will send a notification message to the user's device and provide detailed information.

[0064] Step 8:

[0065] The user receives a notification and opens a dedicated application to check detailed information. The user sees a notification such as "Signs of deterioration have been detected. Maintenance is recommended." and considers the necessary action.

[0066] Step 9:

[0067] The server automatically adjusts the maintenance schedule based on abnormalities or deterioration, and sets the next maintenance date based on the results of the predictive model and notifies the user.

[0068] Step 10:

[0069] The user checks the new maintenance schedule and accepts or adjusts it. The user checks the schedule through the terminal and performs maintenance work as necessary.

[0070] Step 11:

[0071] Users can monitor the status of their solar panels in real time through a dedicated application. Users open the app and check the current power generation, angle, direction, and deterioration status.

[0072] Step 12:

[0073] Users can send questions or requests to the server via their device, or submit questions using the inquiry form within the app.

[0074] Step 13:

[0075] The server receives queries from users and provides answers based on the analysis results. The server analyzes the query and returns an appropriate answer to the user.

[0076] Example 1

[0077] 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."

[0078] In conventional solar panel systems, optimal angle adjustment and direction prediction to achieve efficient power generation are often performed manually, which tends to reduce power generation efficiency. It is also difficult to detect deterioration or abnormalities early, which can delay appropriate maintenance. Furthermore, users are sometimes unable to monitor the status of the panels in real time, which creates the challenge of being unable to respond immediately when problems occur.

[0079] 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.

[0080] In this invention, the server includes means for acquiring solar radiation data, means for acquiring weather data and power generation history, means for predicting the optimal solar panel angle and direction using a generative model, means for transmitting the predicted angle and direction to a tracking system, means for predicting the deterioration state of the solar panel, means for detecting abnormalities and signs of failure and notifying maintenance, means for collecting sensor data and physically adjusting the solar panel, means for inputting a data set into a generative AI model to predict the optimal angle and direction, and means for transmitting a notification to the user when an abnormality is detected. This maximizes the power generation efficiency of the solar panel and enables stable operation of the system.

[0081] "Solar radiation data" is data that indicates the amount of solar energy that reaches the Earth's surface from the sun.

[0082] "Weather data" refers to data that indicates weather conditions such as weather conditions (e.g., sunny, cloudy, rainy, etc.), temperature, humidity, and wind speed.

[0083] "Power generation history" is data that records the amount of power generated by the solar cell panel in the past and its fluctuations.

[0084] A "generative model" is an artificial intelligence algorithm that makes predictions and inferences based on input data.

[0085] A "tracking system" is a device that adjusts the angle and direction of solar panels for the purpose of efficient power generation.

[0086] The "deterioration state" refers to the degree of performance degradation or damage that occurs during the course of use of the solar panel.

[0087] "Abnormalities and signs of failure" are signs that the solar panels or related equipment are outside the normal operating range or are signs that indicate the possibility of a failure.

[0088] "Maintenance" means preventative or corrective work performed to maintain the proper functioning of solar panels and related systems.

[0089] "Sensor data" refers to information obtained from sensors, including physical conditions such as temperature, vibration, current, and voltage of solar panels.

[0090] A "generative AI model" is an artificial intelligence model that automatically generates optimal solutions based on large amounts of data.

[0091] A "dataset" is a collection of data compiled for a specific purpose.

[0092] A "user" is a person or organization that uses the system to manage and monitor solar panels.

[0093] The present invention aims to efficiently utilize renewable energy, and specifically relates to a system that maximizes the power generation efficiency of solar panels. This system is composed of a server, a terminal, and a user element.

[0094] First, the server periodically obtains solar radiation data and weather data using a weather API. Next, it obtains historical power generation data from a database. These data are then converted into a single dataset and input into a generative AI model. For example, the generative AI model uses GPT-4, a type of generative AI. This model makes predictions based on prompt statements such as the following:

[0095] "Predict tomorrow's optimal solar panel angle and direction based on yesterday's weather data, solar radiation data, and historical power generation data from the past week."

[0096] The acquired predicted data is sent to the tracking system, which uses an Arduino-based single-axis tracking system and physically adjusts the solar panel based on the predicted angle and direction. The server also collects sensor data from a TI sensor module and checks the solar panel for deterioration or abnormalities. If an abnormality is detected, a notification is sent to the user's device.

[0097] The terminal provides a user interface. Through a dedicated application, users can monitor the status of the solar panels in real time, checking information such as the current power generation amount, panel angle, direction, and deterioration status. Users can also send inquiries or requests to the server via the terminal and receive the results.

[0098] To use the system effectively, users periodically check the information provided, perform maintenance as needed, and respond to notifications from the server. For example, if a notification arrives from the server stating that "maintenance is required," the user responds promptly and performs the appropriate maintenance to maintain stable operation of the system.

[0099] As a specific example, every day at 6:00 AM, the server retrieves solar radiation data and weather data from a weather API and retrieves the past week's power generation history data from a database. This data is formatted and input into a generative AI model. The generative AI model makes predictions such as "angle: 30 degrees, direction: south-southeast," and this information is sent to a tracking system. The tracking system uses this information to physically adjust the solar panel. At the same time, the server collects data from a TI sensor module and checks for deterioration or abnormalities. If an abnormality is detected, a notification is sent to the user's device stating, "Signs of deterioration are present. Maintenance is recommended." The user can then check this notification and schedule appropriate maintenance.

[0100] This system maximizes the power generation efficiency of the solar panels and ensures stable operation of the system.

[0101] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0102] Step 1:

[0103] The server uses a weather API to obtain solar radiation data. In this case, the server sends an API request and receives the obtained data in JSON format. The input is the request information to the API, and the output is the obtained solar radiation data. This data is formatted appropriately for use in subsequent processing.

[0104] Step 2:

[0105] The server retrieves weather data from the same weather API. The server sends an API request and receives data such as weather conditions, temperature, and humidity in JSON format. The input is the request information to the API, and the output is the retrieved weather data. This weather data is also formatted and converted into a format that can be used for subsequent processing.

[0106] Step 3:

[0107] The server retrieves historical power generation data from the database. It executes a database query to retrieve power generation data for the past week. The input is a query to the database, and the output is the retrieved power generation data. This data is formatted as time-series data on power generation.

[0108] Step 4:

[0109] The server converts the acquired solar radiation data, weather data, and power generation history data into a single dataset. This converts the data into a format that is easy for the generative AI model to use. The input is each piece of data acquired in steps 1 to 3, and the output is the converted dataset.

[0110] Step 5:

[0111] The server inputs the formatted dataset into the generative AI model as a prompt. An example prompt is, "Please predict tomorrow's optimal angle and direction of the solar panels based on yesterday's weather data, solar radiation data, and power generation history data from the past week." The input is the formatted dataset and prompt, and the output is the prediction result from the generative AI model.

[0112] Step 6:

[0113] The server receives the optimal solar panel angle and direction data returned by the generative AI model. The input is the predicted result from the generative AI model, and the output is the optimal angle and direction data. This data is used to instruct the tracking system.

[0114] Step 7:

[0115] The server sends the prediction results to the tracking system, which then physically adjusts the angle and orientation of the solar panels based on the received data. The input is the predicted angle and orientation data, and the output is the adjusted physical state of the panels.

[0116] Step 8:

[0117] The server collects sensor data from TI sensor modules. The data from the sensors includes information such as temperature, vibration, current, and voltage. The input is real-time data from the sensors, and the output is the collected sensor data.

[0118] Step 9:

[0119] The server inputs the collected sensor data into an AI model to predict the state of deterioration or abnormalities. The input is sensor data, and the output is the predicted results of the state of deterioration or abnormalities. The results are notified to the user when an abnormality is detected.

[0120] Step 10:

[0121] If an abnormality is detected, the server sends a notification to the user's device. The notification content states, "Signs of deterioration are present. Maintenance is recommended." The input is the predicted abnormality result, and the output is the notification to the user.

[0122] Step 11:

[0123] Users use a dedicated application on their device to monitor the status of their solar panels in real time. The application displays the current amount of power generated, the angle and direction of the panels, and their state of deterioration. The input is various data sent from the server, and the output is real-time information that the user can check.

[0124] Step 12:

[0125] Users receive notifications from the server and schedule appropriate maintenance. The input is a maintenance notification from the server, and the output is the execution of the maintenance schedule. This ensures stable operation of the system.

[0126] (Application example 1)

[0127] 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."

[0128] Efficient energy use is a key issue in modern factories. In particular, to promote the use of renewable energy, it is necessary to maximize the power generation efficiency of solar panels and continuously monitor and adjust their status. However, current systems make it difficult to perform real-time optimization and automatic maintenance prediction based on data. This leads to issues such as reduced energy efficiency and increased factory operating costs.

[0129] 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.

[0130] In this invention, the server includes means for acquiring solar radiation data, means for acquiring weather data and power generation history, and means for predicting the optimal solar panel angle and direction using a generative model. This enables automatic optimization to maximize energy efficiency. The server also includes means for transmitting the predicted angle and direction to a single-axis tracking system, means for predicting the deterioration state of the solar panels, means for detecting abnormalities and signs of failure and notifying maintenance, means for collecting sensor data within the factory, means for analyzing the data in real time to maximize energy efficiency and automatically optimizing equipment settings, and means for predicting a maintenance schedule based on signs of deterioration and abnormalities and notifying the user. This enables efficient energy use.

[0131] "Solar radiation data" is information that measures the radiant energy from the sun to the earth.

[0132] "Weather Data" is information about the weather and meteorological conditions in a particular area.

[0133] "Power generation history" is a record of the electrical energy generated in the past by solar panels or other power generation devices.

[0134] A "generative model" is an algorithm or component of artificial intelligence that predicts optimal outcomes based on acquired data.

[0135] The "optimal solar panel angle and orientation" refers to the best angle and orientation for solar panels to generate electricity as efficiently as possible.

[0136] A "single-axis tracking system" is an automatic control system for adjusting the angle and direction of solar panels.

[0137] "Solar panel deterioration" refers to the degree to which a solar panel is no longer able to perform at its full potential due to use or environmental factors.

[0138] "Abnormalities and signs of failure" are phenomena or signs that a system or device is beyond the range of normal operation or that there is an increased possibility of it failing in the future.

[0139] A "maintenance schedule" is a plan for efficiently maintaining and inspecting facilities and equipment.

[0140] "Sensor data" is information collected from various sensor devices.

[0141] "Energy efficiency" refers to the actual amount of power generated and the efficiency of energy utilization relative to the amount of energy used.

[0142] "Analyzing data in real time" means evaluating and analyzing data as soon as it is generated.

[0143] A "purpose-built application" is a software program designed for a specific purpose.

[0144] A "user" is an entity that operates and manages a system or device.

[0145] The present invention aims to efficiently utilize renewable energy, and specifically relates to a system that maximizes the power generation efficiency of solar panels. This system is composed of a server, a terminal, and a user element.

[0146] The server periodically acquires solar radiation data, weather data, and power generation history data, and inputs this data into a generative model to predict the optimal angle and direction of the solar panels. The server also sends the prediction results of this generative model to the single-axis tracking system, which automatically adjusts the angle and direction of the solar panels. Furthermore, the server predicts the deterioration state of the solar panels based on data acquired from sensors, detects signs of abnormalities or failures, and notifies the user. This makes it possible to automatically adjust appropriate maintenance schedules and notify the user.

[0147] The terminal mainly provides the user interface. Users can monitor the status of the solar panels in real time through a dedicated application. For example, they can check information such as the current amount of power generated, the angle and direction of the solar panels, and the state of deterioration. Users can also send inquiries or requests to the server via the terminal and receive the results.

[0148] To use the system effectively, users are required to regularly check the information provided, perform maintenance as necessary, and respond to notifications from the server. For example, if a notification arrives from the server stating that "maintenance is required," the user must respond promptly and perform the appropriate maintenance to maintain stable system operation.

[0149] The system has the following specific components:

[0150] 1. Data collection function:

[0151] The server automatically collects solar radiation data, weather data, power generation history data, and various sensor data within the factory, which is important information required for subsequent processing.

[0152] 2. Leveraging generative models:

[0153] Based on the collected data, a generative model predicts the optimal angle and direction of the solar panels. This model is implemented using Python and Flask.

[0154] 3. Real-time analysis:

[0155] The collected data is analyzed in real time and any necessary adjustments are automatically made to maximize energy efficiency.

[0156] 4. Maintenance forecasting and notifications:

[0157] The server predicts deterioration and abnormalities, generates a maintenance schedule as needed, and notifies the user through a dedicated application.

[0158] As a specific example, the server collects solar radiation data, weather data, and power generation history data every morning at 6:00 a.m., and based on this, the generative model predicts optimal settings such as "angle: 30 degrees, direction: south-southeast." This prediction result is sent to the single-axis tracking system, and the solar panels are automatically adjusted. At the same time, sensor data is also collected, and if signs of deterioration or abnormalities are detected, a notification is sent to the user's device stating, "Signs of deterioration have been detected. Maintenance is recommended." The user receives this notification, checks detailed information through the application, and adjusts the maintenance schedule.

[0159] Example prompt sentence:

[0160] Please use "solar radiation data, weather data, and power generation history data to optimize factory energy management" to predict "the optimal angle and direction of solar panels." For example, if the solar radiation is 1000W / m^2, the weather is sunny, and the power generation history data shows an efficiency of 90%, please output the optimal setting value.

[0161] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0162] Step 1:

[0163] The server collects solar radiation data, weather data, power generation history data, and sensor data. These data are periodically obtained from sensor devices installed on the server. Solar radiation, temperature, wind speed, and past power generation data are taken as input and stored in a database. The output is a set of the latest state of each data.

[0164] Step 2:

[0165] Based on the data collected by the server, the data is input into a generative AI model to predict the optimal solar panel angle and direction. This process uses a Python-based machine learning model. The dataset collected in step 1 is input into the model, and the process of predicting the optimal angle and direction begins. The output is a set of generated optimal angles and directions.

[0166] Step 3:

[0167] The server sends the generated set of optimal angles and orientations to the single-axis tracking system, which automatically adjusts the angle and orientation of the solar panel. As input, it uses the optimal angle and orientation predicted in step 2. The output is the adjusted state of the solar panel based on the new set values.

[0168] Step 4:

[0169] The server analyzes the sensor data to detect the deterioration status and signs of abnormalities in the solar panels and related equipment. This analysis uses AI and a specific pattern matching method to find signs of deterioration and abnormalities. The input is the latest sensor data set obtained in step 1, and the output is information on signs of deterioration and abnormalities.

[0170] Step 5:

[0171] The server automatically generates a maintenance schedule based on the information on deterioration and signs of abnormalities and notifies the user. The user can receive these notifications through a dedicated application. The input is the deterioration information and signs of abnormalities detected in step 4, and the output is a notification message to the user and a recommended maintenance schedule.

[0172] Step 6:

[0173] Using a dedicated application, users can check the status of solar panels and the latest maintenance information in real time. Through the application, users can make inquiries to the server with questions or requests and receive the results. The input is the solar panel status information and maintenance schedule provided by the server, and the output is the information that the user can check on the application screen.

[0174] 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.

[0175] ---

[0176] The present invention is a system that maximizes the power generation efficiency of solar panels and supports users in managing their maintenance. It also incorporates an emotion engine that recognizes the user's emotions and optimizes the system's response.

[0177] The server provides the following main functions: First, it periodically collects solar radiation data, weather data, and power generation history data, and inputs this data into a generative model. The generative model then predicts the optimal angle and direction of the solar panels and sends the results to the single-axis tracking system. The tracking system then automatically adjusts the angle and direction of the solar panels based on the received data.

[0178] The server also collects data from the solar panels via sensors and predicts their deterioration. If signs of deterioration or abnormalities are detected, the server notifies the user. The notification includes maintenance recommendations, allowing the user to take effective action.

[0179] The terminal provides the user interface. Users can monitor the status of the solar panels in real time and receive notification messages through a dedicated application. Users can also contact the server via the terminal with any questions or requests.

[0180] The system also incorporates an emotion engine that recognizes the user's real-time emotional state. The emotion engine analyzes emotions from the user's voice, facial expressions, and text input and transmits them to the server. The server adjusts notification messages based on the received emotion data to provide responses appropriate to the user's emotional state.

[0181] As a specific example, the server collects solar radiation data, weather data, and power generation history data every morning at 6:00 a.m., and based on this, the generative model predicts optimal settings such as "angle: 30 degrees, direction: south-southeast." This prediction result is sent to the single-axis tracking system, and the solar panels are automatically adjusted. At the same time, sensor data is also collected, and if signs of deterioration or abnormalities are detected, a notification is sent to the user's device stating, "Signs of deterioration are present. Maintenance is recommended." The user receives this notification, checks detailed information through the application, and adjusts the maintenance schedule. In addition, emotions are analyzed from the user's facial expressions and voice, and if stress levels are high, appropriate measures are taken, such as softening the tone of the notification.

[0182] This system configuration maximizes the power generation efficiency of solar panels and enables efficient maintenance management by detecting deterioration and abnormalities early. It also improves the user experience by providing responses that take into account the user's emotional state.

[0183] The processing flow will be explained below.

[0184] ---

[0185] Step 1:

[0186] The server acquires solar radiation data, weather data, and power generation history data at a fixed time every day. The server uses an API to download data from the solar radiation database, acquires the latest weather data from the weather information service, and collects past power generation history from an internal database.

[0187] Step 2:

[0188] The server inputs collected solar radiation data, weather data, and historical power generation data into a generative model, which then predicts the optimal solar panel angle and direction. The generative model combines past and current data and uses machine learning to calculate the optimal value.

[0189] Step 3:

[0190] The server sends the prediction results from the generative model to the single-axis tracking system. For example, actual settings such as "angle: 30 degrees, direction: south-southeast" are sent to the tracking system. The tracking system then automatically adjusts the angle and direction of the panel based on this data.

[0191] Step 4:

[0192] The tracking system physically changes the angle and orientation of the solar panels. The system controls motors and actuators to adjust the position of the panels.

[0193] Step 5:

[0194] The server collects solar panel data from sensors in real time, constantly monitoring voltage, current, temperature, vibration, and other data to detect signs of deterioration or abnormalities.

[0195] Step 6:

[0196] The server inputs the collected sensor data into a degradation prediction model to predict the deterioration state of the panels. If any abnormalities or signs of failure are detected, the information is processed in real time.

[0197] Step 7:

[0198] When the server detects an abnormality or a sign of a malfunction, it sends a notification to the user's device. The notification includes a message such as "Signs of deterioration have been detected. Maintenance is recommended."

[0199] Step 8:

[0200] Users receive a notification, open a dedicated application to view more information, and then act based on the recommended maintenance plan.

[0201] Step 9:

[0202] The server utilizes an emotion engine that recognizes the user's emotions and obtains emotion data from the user's voice and facial expressions, for example, by collecting data through a camera or microphone while the user is using the application.

[0203] Step 10:

[0204] The emotion engine analyzes the collected emotion data and evaluates the user's stress level and satisfaction. If the user is feeling anxious or stressed, the emotion engine sends that information to the server.

[0205] Step 11:

[0206] The server adjusts the content and tone of notification messages based on data from the emotion engine. For example, if a user is feeling stressed, the server will send a message with softer language and encouraging words.

[0207] Step 12:

[0208] Users can send questions or requests to the server through the application's inquiry form via their terminal. Users can send questions using real-time chat or the inquiry form.

[0209] Step 13:

[0210] The server receives the user's inquiry, analyzes it, and provides an appropriate answer. Depending on the inquiry, the server provides a specific solution or additional information and replies to the user.

[0211] In this way, the system combines data collection, prediction, physical adjustment, real-time monitoring, and user emotional responses to maximize the power generation efficiency of solar panels and improve the user experience.

[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] Current solar panel management systems not only lack automatic adjustments to maximize power generation efficiency, but are often slow to predict deterioration and provide maintenance notifications. They also lack the ability to provide appropriate responses that take user emotions into account, making it difficult to optimize the user experience. This can lead to reduced power generation efficiency and delayed maintenance, resulting in reduced overall system efficiency.

[0215] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for acquiring solar radiation data, means for acquiring weather data and power generation history, means for predicting the optimal solar panel angle and direction using a generative model, means for transmitting the predicted angle and direction to the single-axis tracking system, means for predicting the deterioration state of the solar panel, means for detecting abnormalities or signs of failure and notifying maintenance, emotion recognition means, and means for adjusting the notification message based on the user's emotional state. This enables efficient power generation by the solar panel and appropriate maintenance through early detection of deterioration or abnormalities, thereby improving the user experience.

[0216] "Solar radiation data" is information collected by sensors or measuring devices to measure the intensity of sunlight.

[0217] "Weather data" is information about weather conditions, and is data based on weather conditions such as temperature, humidity, wind speed, and precipitation.

[0218] "Power generation history" is recorded data regarding the amount of power generated in the past by the solar panel.

[0219] A "generative model" is a machine learning model used to predict the optimal solar panel angle and orientation based on captured data.

[0220] A "single-axis tracking system" is a device or system that automatically adjusts the angle and orientation of a solar panel along a single axis.

[0221] The "means for predicting the deterioration state" refers to a device or method for detecting the deterioration and performance degradation of a solar panel and predicting its state.

[0222] "Detection of abnormalities and signs of failure" is the process of detecting signs of abnormalities or failures that may occur in solar panels and notifying the user.

[0223] A "means for notifying maintenance" is a method or device for notifying a user that maintenance of a solar panel is required.

[0224] An "emotion recognition means" is a device or method for analyzing and recognizing emotions from a user's voice, facial expressions, and text input.

[0225] A "means for tailoring notification messages" is a device or method that changes the content or tone of the system's notification messages based on the user's emotional state.

[0226] The present invention is a system that maximizes the power generation efficiency of solar panels and supports users in managing their maintenance. The system also incorporates an emotion engine that recognizes the user's emotions and optimizes the system's response.

[0227] The server provides the following main functions. First, it periodically acquires solar radiation data, weather data, and power generation history data. Weather data is acquired using the OpenWeatherMap API, and solar radiation data is acquired from sensors via a local connection. Power generation history data is collected from the solar panel inverter. This data is managed centrally within the server.

[0228] The server then inputs the collected data into a generative AI model, which is built using the TensorFlow library. The model predicts the optimal angle and direction of the solar panels based on the input weather data, solar radiation data, and power generation history data. This predicted data is sent to a single-axis tracking system. The tracking system automatically adjusts the angle and direction of the solar panels based on the received data. This adjustment is made using the RS-485 communication protocol.

[0229] The server also collects solar panel status data from sensors to detect signs of deterioration or abnormalities. This process uses machine learning models (e.g., Scikit-learn) and collects sensor data via the LoRa communication protocol. Based on the detected signs of deterioration or abnormalities, the server notifies the user of maintenance recommendations. These notifications are sent to the device and displayed through the user interface.

[0230] The role of the terminal is to provide a user interface. Users can use a dedicated application (developed with React Native) to monitor the status of the solar panels in real time. Furthermore, users can send queries or requests to the server through the application. The application runs on both iOS and Android.

[0231] The emotion engine recognizes the user's real-time emotional state. Specifically, the Emotient API is used to analyze emotions from the user's voice, facial expressions, and text input. The device collects data using the camera and microphone, and the emotion engine performs the analysis. The analysis results are sent to the server, which adjusts the notification message based on the received emotion data. For example, if the user is feeling stressed, the tone of the notification message will be softened. A message such as "Please let us know if you need more specific instructions" will be sent.

[0232] As a specific example, a server collects solar radiation data, weather data, and power generation history data every day at 6:00 a.m. This data is input into a generative AI model, which then predicts optimal settings, such as "angle: 30 degrees, direction: south-southeast." The prediction results are sent to a single-axis tracking system, which automatically adjusts the solar panels. At the same time, sensor data is also collected, and if signs of deterioration or abnormalities are detected, a notification is sent to the user's device stating, "Signs of deterioration have been detected. Maintenance is recommended."

[0233] In addition, emotions are analyzed from the user's facial expressions and voice, and if stress levels are high, the tone of notifications is softened. An example of a specific prompt is, "Please set a method to analyze the user's voice data and facial expression data, recognize their emotional state, and adjust notification messages accordingly."

[0234] This system configuration maximizes the power generation efficiency of the solar panels and enables appropriate maintenance by detecting deterioration or abnormalities early and notifying the user.Furthermore, by using an emotion engine, it is possible to provide responses based on the user's emotional state, improving the user experience.

[0235] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0236] Step 1:

[0237] The server collects solar radiation data, weather data, and power generation history data every day at 6:00 a.m.

[0238] Input: The server sends API requests and collects data from sensors and inverters.

[0239] Operation: Weather data is obtained using the OpenWeatherMap API, solar radiation data is received from the sensor via LoRa communication, and power generation history data is read from the inverter.

[0240] Output: Store the acquired data in a database and format it for further processing.

[0241] Step 2:

[0242] The server inputs the collected data into a generative AI model.

[0243] Input: Solar radiation data, weather data, and historical power generation data collected in step 1.

[0244] How it works: We use the TensorFlow library to run a generative model to predict the optimal solar panel angle and orientation.

[0245] Output: Angle and direction data predicted by the generative AI model.

[0246] Step 3:

[0247] The server sends the prediction results to the single-axis tracking system.

[0248] Input: Prediction data (angle and direction) obtained in step 2.

[0249] Operation: Sends predicted data to a tracking system via RS-485 communication protocol.

[0250] Output: Forecast data received by the tracking system.

[0251] Step 4:

[0252] The tracking system automatically adjusts the angle and direction of the solar panels.

[0253] Input: The forecast data received in step 3.

[0254] Operation: Sends commands to the motor driver, driving the motor to automatically adjust the angle and direction of the solar panel to the set values.

[0255] Output: Regulated solar panel status.

[0256] Step 5:

[0257] The server collects status data from the sensors and predicts the deterioration state of the solar panels.

[0258] Input: Status data such as vibration data and temperature data of the solar panel.

[0259] Operation: Data is received from sensors via LoRa communication, and signs of deterioration or abnormalities are analyzed using Scikit-learn.

[0260] Output: Analyzed data on signs of deterioration and abnormalities.

[0261] Step 6:

[0262] The server sends maintenance notifications to users based on predicted deterioration and abnormality data.

[0263] Input: Data on signs of deterioration and abnormalities analyzed in Step 5.

[0264] Operation: If degradation or abnormality is detected, a notification message is generated and sent to the terminal.

[0265] Output: Maintenance notification displayed on the user's device.

[0266] Step 7:

[0267] The device will display a notification to the user prompting them to take the necessary action.

[0268] Input: Maintenance notification sent in step 6.

[0269] Behavior: Displays a notification message in the user interface of the dedicated application, and also raises an alert so that the user can see it.

[0270] Output: The notification message displayed to the user.

[0271] Step 8:

[0272] The emotion engine analyzes the user's emotions from their facial expressions and voice and sends the results to the server.

[0273] Input: User's facial expression data, voice data.

[0274] How it works: Collects data using the device's camera and microphone and sends it to the Emotient API for sentiment analysis.

[0275] Output: User sentiment data obtained as a result of the analysis.

[0276] Step 9:

[0277] The server adjusts the notification message based on the received emotion data and sends it back to the user.

[0278] Input: User emotion data obtained in step 8.

[0279] Behavior: Adjust the tone and content of notification messages based on your emotional state. For example, soften the tone if you are feeling stressed.

[0280] Output: A notification message appropriate to the user's emotional state.

[0281] Step 10:

[0282] Users can check notifications and messages and take necessary actions.

[0283] Input: The notification message adjusted in step 9.

[0284] Action: The user reviews the notification and adjusts the maintenance schedule through the application as needed.

[0285] Output: User actions such as updating a maintenance schedule or submitting a ticket.

[0286] (Application example 2)

[0287] 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."

[0288] Conventional solar panel systems are often inefficient because optimization and maintenance management to improve power generation efficiency are performed manually. Furthermore, there are insufficient means to detect deterioration or abnormalities that users face early, which can lead to delayed appropriate responses. Furthermore, responses that take into account the user's emotional state are not provided, resulting in a poor user experience regarding notifications and maintenance.

[0289] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring solar radiation data, means for acquiring weather data and power generation history, means for predicting the optimal solar panel angle and direction using a generative model, means for transmitting the predicted angle and direction to the single-axis tracking system, means for predicting the deterioration state of the solar panel, means for detecting abnormalities and signs of failure and notifying maintenance, means for controlling the robot arm using power generation history data and automatically adjusting the solar panel angle, means for collecting sensor data and monitoring the solar panel status, means for automatically adjusting the maintenance schedule based on the collected data, means for notifying the user of the maintenance schedule, means for analyzing the user's emotions using an emotion engine, and means for adjusting notification messages according to the user's emotions. This maximizes the power generation efficiency of the solar panel, enables early detection of deterioration and abnormalities, and realizes efficient maintenance management. Furthermore, providing responses according to the user's emotional state improves the user experience.

[0290] "Solar radiation data" is data that indicates the amount of solar radiation that reaches the earth's surface from the sun.

[0291] "Weather data" refers to data that indicates weather conditions such as temperature, humidity, precipitation, and wind speed.

[0292] "Power generation history data" is recorded data relating to the amount of power generated by the solar panel in the past.

[0293] A "generative model" is a machine learning model that predicts the optimal angle and direction of solar panels based on input data.

[0294] A "single-axis tracking system" is a device that rotates a solar panel along a single axis.

[0295] The "deterioration state of the solar panel" refers to the state that indicates the degree of physical and functional deterioration of the solar panel.

[0296] "Abnormalities and signs of failure" are signs that indicate an abnormal state that deviates from normal operation or a sign that indicates a precursor to failure.

[0297] A "maintenance schedule" is a schedule for performing regular maintenance on solar panels.

[0298] A "robot arm" is a mechanical device that can move with multiple joints like a human arm.

[0299] "Sensor data" refers to data relating to physical quantities obtained from various sensors.

[0300] An "emotion engine" is software or algorithm for analyzing a user's emotional state.

[0301] "User's emotions" are data that indicate the user's psychological state and mood.

[0302] A "notification message" is a message sent by the system to the user to provide information.

[0303] "User experience" refers to the overall experience and satisfaction a user has when using a system or service.

[0304] The present invention is a system that maximizes the power generation efficiency of solar panels and performs efficient maintenance management by predicting deterioration and abnormalities. Furthermore, it incorporates an emotion engine that recognizes the user's emotions and provides optimal responses. The following describes an embodiment of the present invention in detail.

[0305] The server is equipped with a means of acquiring solar radiation data, which is periodically obtained from an external source via an API. Weather data and power generation history data are also collected via the API. This data is input into the generative model, which uses a machine learning algorithm to predict the optimal angle and orientation of the solar panels based on the obtained data. The prediction results are sent to the single-axis tracking system, which automatically adjusts the angle and orientation of the solar panels.

[0306] Furthermore, the server is equipped with a means to predict the deterioration status of the solar panels. This is done by analyzing data from sensors and detecting signs of deterioration or abnormalities. If an abnormality or sign of deterioration is detected, the server sends a notification to the user's device. This notification also includes specific maintenance recommendations, helping the user to take effective action.

[0307] The system also includes a means for utilizing historical power generation data to control a robotic arm, which adjusts the angle of the solar panels to maximize power generation efficiency. The system also provides a function for automatically adjusting maintenance schedules based on sensor data, thereby streamlining maintenance management.

[0308] The server analyzes the user's emotions using an emotion engine. This emotion engine recognizes emotions in real time from the user's voice, facial expressions, and text input, and has a means to adjust the response message based on the analyzed data. If the user is feeling stressed, the tone of the notification message can be softened, for example, to improve the user experience.

[0309] For example, the server uses solar radiation data and weather data to predict that the solar panels should be angled 30 degrees and pointed south-southeast, and sends this prediction to the single-axis tracking system. The solar panels are then automatically adjusted to achieve optimal power generation efficiency. At the same time, if signs of deterioration are detected based on the sensor data, a notification is sent to the user's device stating, "Signs of deterioration have been detected. Maintenance is recommended." The user can check the details and adjust the schedule through a smartphone app. The system also recognizes emotions from the user's facial expressions and voice, and sends softer messages if stress levels are high.

[0310] For example, you can use a prompt such as, "Based on weather data and historical power generation data from the solar panels, predict the optimal angle for the solar panels and control the robot arm. Current weather data is temperature: 25 degrees, solar radiation: 800, and historical power generation data is output: 150."

[0311] In this way, the present invention is a system that enables maximization of power generation efficiency of solar panels, early detection of deterioration and abnormalities, efficient maintenance management, and improved user experience.

[0312] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0313] Step 1:

[0314] The server receives solar radiation data through API. This data is obtained from the solar radiation sensor and sent as input to the server. The server receives this data and passes it to the next processing step.

[0315] Step 2:

[0316] The server uses an API to collect weather data and historical power generation data, including temperature, humidity, wind speed, and past power generation. The server receives this data and stores it in an internal database, which then prepares input data for the generative model along with solar radiation data.

[0317] Step 3:

[0318] The server inputs solar radiation data, weather data, and historical power generation data into the generative model, which uses machine learning algorithms to predict the optimal solar panel angle and direction based on these inputs. The output is the specific angle and direction.

[0319] Step 4:

[0320] The server sends the angle and direction obtained from the generative model to the single-axis tracking system, which instructs the solar panel to be positioned at a 30-degree angle and facing south-southeast. The tracking system then automatically adjusts the solar panel based on the data received.

[0321] Step 5:

[0322] The server collects data from sensors to predict the deterioration state of the solar panels. This data includes the current, voltage, and temperature of the solar panels. The server analyzes this data to detect signs of deterioration or abnormalities. If an abnormality is found, the information is sent to the next step.

[0323] Step 6:

[0324] If the server detects an abnormality or signs of deterioration, it sends a notification to the user's device, for example, a message saying, "Signs of deterioration are present. Maintenance is recommended." The notification includes recommendations for maintenance and suggestions for next steps.

[0325] Step 7:

[0326] The server controls the robot arm based on the power generation history data. It analyzes this data and sends instructions to the robot arm to adjust the angle of the solar panel as needed. The robot arm follows these instructions and actually adjusts the angle.

[0327] Step 8:

[0328] The server automatically adjusts the maintenance schedule based on sensor data, including the status of the solar panels, usage time, environmental conditions, etc. The server analyzes this data, determines the next maintenance date, and notifies the user.

[0329] Step 9:

[0330] The server analyzes the user's emotions using an emotion engine, which analyzes the user's voice, facial expressions, and text input to determine the user's emotional state. For example, if the server determines that the user is tired, it adjusts the notification content to a softer tone.

[0331] Step 10:

[0332] The server adjusts the notification message based on the user's emotions based on the emotional data obtained by the emotion engine. For example, if the user is feeling stressed, the server sends a soft message such as, "Maintenance is required. However, please rest assured that we will continue to support you."

[0333] In this way, the server can execute a series of processing steps to maximize the power generation efficiency of the solar panels, detect deterioration or abnormalities early, manage maintenance efficiently, and improve the user experience.

[0334] 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.

[0335] 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.

[0336] 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.

[0337] [Second embodiment]

[0338] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0339] 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.

[0340] 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).

[0341] 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.

[0342] 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.

[0343] 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).

[0344] 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.

[0345] 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.

[0346] 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.

[0347] 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.

[0348] 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.

[0349] 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."

[0350] ---

[0351] The present invention aims to efficiently utilize renewable energy, and specifically relates to a system that maximizes the power generation efficiency of solar panels. This system is composed of a server, a terminal, and a user element.

[0352] The server has the following main functions. First, it periodically acquires solar radiation data, weather data, and power generation history data, and inputs this data into a generative model to predict the optimal angle and direction of the solar panels. Next, it sends the prediction results of the generative model to a single-axis tracking system, which automatically adjusts the angle and direction of the solar panels. Furthermore, it predicts the deterioration state of the solar panels based on data acquired from sensors, detects signs of abnormalities or failures, and notifies the user. This makes it possible to automatically adjust an appropriate maintenance schedule and notify the user.

[0353] The terminal mainly provides the user interface. Users can monitor the status of the solar panels in real time through a dedicated application. For example, they can check information such as the current amount of power generated, the angle and direction of the solar panels, and the state of deterioration. Users can also send inquiries or requests to the server via the terminal and receive the results.

[0354] To use the system effectively, users periodically check the information provided, perform maintenance as needed, and respond to notifications from the server. For example, if a notification arrives from the server stating that "maintenance is required," the user responds promptly and performs appropriate maintenance to maintain stable system operation.

[0355] As a specific example, the server collects solar radiation data, weather data, and power generation history data every morning at 6:00 a.m., and based on this, the generative model predicts optimal settings such as "angle: 30 degrees, direction: south-southeast." This prediction result is sent to the single-axis tracking system, and the solar panels are automatically adjusted. At the same time, sensor data is also collected, and if signs of deterioration or abnormalities are detected, a notification is sent to the user's device stating, "Signs of deterioration have been detected. Maintenance is recommended." The user receives this notification, checks detailed information through the application, and adjusts the maintenance schedule.

[0356] Key features of this system include data-based prediction and automatic adjustment, early detection of deterioration and abnormalities, and efficient maintenance management through user interaction, which maximizes the power generation efficiency of the solar panels and ensures stable operation of the system.

[0357] The processing flow will be explained below.

[0358] ---

[0359] Step 1:

[0360] The server collects solar radiation data, weather data, and power generation history data at a fixed time every day. The server accesses each data source via API, collects the data, and stores it in a local database.

[0361] Step 2:

[0362] The server inputs the accumulated data into the generative model, which then combines solar radiation data, weather data, and power generation history and passes it to the generative model to predict the optimal angle and direction of the solar panels.

[0363] Step 3:

[0364] The server sends the prediction results of the generative model to the single-axis tracking system, which automatically adjusts the solar panel by sending prediction results such as "angle: 30 degrees, direction: south-southeast" to the tracking system.

[0365] Step 4:

[0366] The tracking system adjusts the angle and orientation of the solar panels based on the received predictions. The tracking system controls the motors to change the physical position of the solar panels.

[0367] Step 5:

[0368] The server collects solar panel data from sensors, including voltage, current, and temperature, in real time, and monitors for signs of abnormalities or deterioration.

[0369] Step 6:

[0370] The server predicts the deterioration state based on the collected sensor data, and inputs the sensor data into a deterioration prediction model to detect signs of deterioration and abnormalities.

[0371] Step 7:

[0372] If the server detects an abnormality or a sign of a failure, it will notify the user. When an abnormality is detected, the server will send a notification message to the user's device and provide detailed information.

[0373] Step 8:

[0374] The user receives a notification and opens a dedicated application to check detailed information. The user sees a notification such as "Signs of deterioration have been detected. Maintenance is recommended." and considers the necessary action.

[0375] Step 9:

[0376] The server automatically adjusts the maintenance schedule based on abnormalities or deterioration, and sets the next maintenance date based on the results of the predictive model and notifies the user.

[0377] Step 10:

[0378] The user checks the new maintenance schedule and accepts or adjusts it. The user checks the schedule through the terminal and performs maintenance work as necessary.

[0379] Step 11:

[0380] Users can monitor the status of their solar panels in real time through a dedicated application. Users open the app and check the current power generation, angle, direction, and deterioration status.

[0381] Step 12:

[0382] Users can send questions or requests to the server via their device, or submit questions using the inquiry form within the app.

[0383] Step 13:

[0384] The server receives queries from users and provides answers based on the analysis results. The server analyzes the query and returns an appropriate answer to the user.

[0385] Example 1

[0386] 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."

[0387] In conventional solar panel systems, optimal angle adjustment and direction prediction to achieve efficient power generation are often performed manually, which tends to reduce power generation efficiency. It is also difficult to detect deterioration or abnormalities early, which can delay appropriate maintenance. Furthermore, users are sometimes unable to monitor the status of the panels in real time, which creates the challenge of being unable to respond immediately when problems occur.

[0388] 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.

[0389] In this invention, the server includes means for acquiring solar radiation data, means for acquiring weather data and power generation history, means for predicting the optimal solar panel angle and direction using a generative model, means for transmitting the predicted angle and direction to a tracking system, means for predicting the deterioration state of the solar panel, means for detecting abnormalities and signs of failure and notifying maintenance, means for collecting sensor data and physically adjusting the solar panel, means for inputting a data set into a generative AI model to predict the optimal angle and direction, and means for transmitting a notification to the user when an abnormality is detected. This maximizes the power generation efficiency of the solar panel and enables stable operation of the system.

[0390] "Solar radiation data" is data that indicates the amount of solar energy that reaches the Earth's surface from the sun.

[0391] "Weather data" refers to data that indicates weather conditions such as weather conditions (e.g., sunny, cloudy, rainy, etc.), temperature, humidity, and wind speed.

[0392] "Power generation history" is data that records the amount of power generated by the solar cell panel in the past and its fluctuations.

[0393] A "generative model" is an artificial intelligence algorithm that makes predictions and inferences based on input data.

[0394] A "tracking system" is a device that adjusts the angle and direction of solar panels for the purpose of efficient power generation.

[0395] The "deterioration state" refers to the degree of performance degradation or damage that occurs during the course of use of the solar panel.

[0396] "Abnormalities and signs of failure" are signs that the solar panels or related equipment are outside the normal operating range or are signs that indicate the possibility of a failure.

[0397] "Maintenance" means preventative or corrective work performed to maintain the proper functioning of solar panels and related systems.

[0398] "Sensor data" refers to information obtained from sensors, including physical conditions such as temperature, vibration, current, and voltage of solar panels.

[0399] A "generative AI model" is an artificial intelligence model that automatically generates optimal solutions based on large amounts of data.

[0400] A "dataset" is a collection of data compiled for a specific purpose.

[0401] A "user" is a person or organization that uses the system to manage and monitor solar panels.

[0402] The present invention aims to efficiently utilize renewable energy, and specifically relates to a system that maximizes the power generation efficiency of solar panels. This system is composed of a server, a terminal, and a user element.

[0403] First, the server periodically obtains solar radiation data and weather data using a weather API. Next, it obtains historical power generation data from a database. These data are then converted into a single dataset and input into a generative AI model. For example, the generative AI model uses GPT-4, a type of generative AI. This model makes predictions based on prompt statements such as the following:

[0404] "Predict tomorrow's optimal solar panel angle and direction based on yesterday's weather data, solar radiation data, and historical power generation data from the past week."

[0405] The acquired predicted data is sent to the tracking system, which uses an Arduino-based single-axis tracking system and physically adjusts the solar panel based on the predicted angle and direction. The server also collects sensor data from a TI sensor module and checks the solar panel for deterioration or abnormalities. If an abnormality is detected, a notification is sent to the user's device.

[0406] The terminal provides a user interface. Through a dedicated application, users can monitor the status of the solar panels in real time, checking information such as the current power generation amount, panel angle, direction, and deterioration status. Users can also send inquiries or requests to the server via the terminal and receive the results.

[0407] To use the system effectively, users periodically check the information provided, perform maintenance as needed, and respond to notifications from the server. For example, if a notification arrives from the server stating that "maintenance is required," the user responds promptly and performs the appropriate maintenance to maintain stable operation of the system.

[0408] As a specific example, every day at 6:00 AM, the server retrieves solar radiation data and weather data from a weather API and retrieves the past week's power generation history data from a database. This data is formatted and input into a generative AI model. The generative AI model makes predictions such as "angle: 30 degrees, direction: south-southeast," and this information is sent to a tracking system. The tracking system uses this information to physically adjust the solar panel. At the same time, the server collects data from a TI sensor module and checks for deterioration or abnormalities. If an abnormality is detected, a notification is sent to the user's device stating, "Signs of deterioration are present. Maintenance is recommended." The user can then check this notification and schedule appropriate maintenance.

[0409] This system maximizes the power generation efficiency of the solar panels and ensures stable operation of the system.

[0410] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0411] Step 1:

[0412] The server uses a weather API to obtain solar radiation data. In this case, the server sends an API request and receives the obtained data in JSON format. The input is the request information to the API, and the output is the obtained solar radiation data. This data is formatted appropriately for use in subsequent processing.

[0413] Step 2:

[0414] The server retrieves weather data from the same weather API. The server sends an API request and receives data such as weather conditions, temperature, and humidity in JSON format. The input is the request information to the API, and the output is the retrieved weather data. This weather data is also formatted and converted into a format that can be used for subsequent processing.

[0415] Step 3:

[0416] The server retrieves historical power generation data from the database. It executes a database query to retrieve power generation data for the past week. The input is a query to the database, and the output is the retrieved power generation data. This data is formatted as time-series data on power generation.

[0417] Step 4:

[0418] The server converts the acquired solar radiation data, weather data, and power generation history data into a single dataset. This converts the data into a format that is easy for the generative AI model to use. The input is each piece of data acquired in steps 1 to 3, and the output is the converted dataset.

[0419] Step 5:

[0420] The server inputs the formatted dataset into the generative AI model as a prompt. An example prompt is, "Please predict tomorrow's optimal angle and direction of the solar panels based on yesterday's weather data, solar radiation data, and power generation history data from the past week." The input is the formatted dataset and prompt, and the output is the prediction result from the generative AI model.

[0421] Step 6:

[0422] The server receives the optimal solar panel angle and direction data returned by the generative AI model. The input is the predicted result from the generative AI model, and the output is the optimal angle and direction data. This data is used to instruct the tracking system.

[0423] Step 7:

[0424] The server sends the prediction results to the tracking system, which then physically adjusts the angle and orientation of the solar panels based on the received data. The input is the predicted angle and orientation data, and the output is the adjusted physical state of the panels.

[0425] Step 8:

[0426] The server collects sensor data from TI sensor modules. The data from the sensors includes information such as temperature, vibration, current, and voltage. The input is real-time data from the sensors, and the output is the collected sensor data.

[0427] Step 9:

[0428] The server inputs the collected sensor data into an AI model to predict the state of deterioration or abnormalities. The input is sensor data, and the output is the predicted results of the state of deterioration or abnormalities. The results are notified to the user when an abnormality is detected.

[0429] Step 10:

[0430] If an abnormality is detected, the server sends a notification to the user's device. The notification content states, "Signs of deterioration are present. Maintenance is recommended." The input is the predicted abnormality result, and the output is the notification to the user.

[0431] Step 11:

[0432] Users use a dedicated application on their device to monitor the status of their solar panels in real time. The application displays the current amount of power generated, the angle and direction of the panels, and their state of deterioration. The input is various data sent from the server, and the output is real-time information that the user can check.

[0433] Step 12:

[0434] Users receive notifications from the server and schedule appropriate maintenance. The input is a maintenance notification from the server, and the output is the execution of the maintenance schedule. This ensures stable operation of the system.

[0435] (Application example 1)

[0436] 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."

[0437] Efficient energy use is a key issue in modern factories. In particular, to promote the use of renewable energy, it is necessary to maximize the power generation efficiency of solar panels and continuously monitor and adjust their status. However, current systems make it difficult to perform real-time optimization and automatic maintenance prediction based on data. This leads to issues such as reduced energy efficiency and increased factory operating costs.

[0438] 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.

[0439] In this invention, the server includes means for acquiring solar radiation data, means for acquiring weather data and power generation history, and means for predicting the optimal solar panel angle and direction using a generative model. This enables automatic optimization to maximize energy efficiency. The server also includes means for transmitting the predicted angle and direction to a single-axis tracking system, means for predicting the deterioration state of the solar panels, means for detecting abnormalities and signs of failure and notifying maintenance, means for collecting sensor data within the factory, means for analyzing the data in real time to maximize energy efficiency and automatically optimizing equipment settings, and means for predicting a maintenance schedule based on signs of deterioration and abnormalities and notifying the user. This enables efficient energy use.

[0440] "Solar radiation data" is information that measures the radiant energy from the sun to the earth.

[0441] "Weather Data" is information about the weather and meteorological conditions in a particular area.

[0442] "Power generation history" is a record of the electrical energy generated in the past by solar panels or other power generation devices.

[0443] A "generative model" is an algorithm or component of artificial intelligence that predicts optimal outcomes based on acquired data.

[0444] The "optimal solar panel angle and orientation" refers to the best angle and orientation for solar panels to generate electricity as efficiently as possible.

[0445] A "single-axis tracking system" is an automatic control system for adjusting the angle and direction of solar panels.

[0446] "Solar panel deterioration" refers to the degree to which a solar panel is no longer able to perform at its full potential due to use or environmental factors.

[0447] "Abnormalities and signs of failure" are phenomena or signs that a system or device is beyond the range of normal operation or that there is an increased possibility of it failing in the future.

[0448] A "maintenance schedule" is a plan for efficiently maintaining and inspecting facilities and equipment.

[0449] "Sensor data" is information collected from various sensor devices.

[0450] "Energy efficiency" refers to the actual amount of power generated and the efficiency of energy utilization relative to the amount of energy used.

[0451] "Analyzing data in real time" means evaluating and analyzing data as soon as it is generated.

[0452] A "purpose-built application" is a software program designed for a specific purpose.

[0453] A "user" is an entity that operates and manages a system or device.

[0454] The present invention aims to efficiently utilize renewable energy, and specifically relates to a system that maximizes the power generation efficiency of solar panels. This system is composed of a server, a terminal, and a user element.

[0455] The server periodically acquires solar radiation data, weather data, and power generation history data, and inputs this data into a generative model to predict the optimal angle and direction of the solar panels. The server also sends the prediction results of this generative model to the single-axis tracking system, which automatically adjusts the angle and direction of the solar panels. Furthermore, the server predicts the deterioration state of the solar panels based on data acquired from sensors, detects signs of abnormalities or failures, and notifies the user. This makes it possible to automatically adjust appropriate maintenance schedules and notify the user.

[0456] The terminal mainly provides the user interface. Users can monitor the status of the solar panels in real time through a dedicated application. For example, they can check information such as the current amount of power generated, the angle and direction of the solar panels, and the state of deterioration. Users can also send inquiries or requests to the server via the terminal and receive the results.

[0457] To use the system effectively, users are required to regularly check the information provided, perform maintenance as necessary, and respond to notifications from the server. For example, if a notification arrives from the server stating that "maintenance is required," the user must respond promptly and perform the appropriate maintenance to maintain stable system operation.

[0458] The system has the following specific components:

[0459] 1. Data collection function:

[0460] The server automatically collects solar radiation data, weather data, power generation history data, and various sensor data within the factory, which is important information required for subsequent processing.

[0461] 2. Leveraging generative models:

[0462] Based on the collected data, a generative model predicts the optimal angle and direction of the solar panels. This model is implemented using Python and Flask.

[0463] 3. Real-time analysis:

[0464] The collected data is analyzed in real time and any necessary adjustments are automatically made to maximize energy efficiency.

[0465] 4. Maintenance forecasting and notifications:

[0466] The server predicts deterioration and abnormalities, generates a maintenance schedule as needed, and notifies the user through a dedicated application.

[0467] As a specific example, the server collects solar radiation data, weather data, and power generation history data every morning at 6:00 a.m., and based on this, the generative model predicts optimal settings such as "angle: 30 degrees, direction: south-southeast." This prediction result is sent to the single-axis tracking system, and the solar panels are automatically adjusted. At the same time, sensor data is also collected, and if signs of deterioration or abnormalities are detected, a notification is sent to the user's device stating, "Signs of deterioration have been detected. Maintenance is recommended." The user receives this notification, checks detailed information through the application, and adjusts the maintenance schedule.

[0468] Example prompt sentence:

[0469] Please use "solar radiation data, weather data, and power generation history data to optimize factory energy management" to predict "the optimal angle and direction of solar panels." For example, if the solar radiation is 1000W / m^2, the weather is sunny, and the power generation history data shows an efficiency of 90%, please output the optimal setting value.

[0470] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0471] Step 1:

[0472] The server collects solar radiation data, weather data, power generation history data, and sensor data. These data are periodically obtained from sensor devices installed on the server. Solar radiation, temperature, wind speed, and past power generation data are taken as input and stored in a database. The output is a set of the latest state of each data.

[0473] Step 2:

[0474] Based on the data collected by the server, the data is input into a generative AI model to predict the optimal solar panel angle and direction. This process uses a Python-based machine learning model. The dataset collected in step 1 is input into the model, and the process of predicting the optimal angle and direction begins. The output is a set of generated optimal angles and directions.

[0475] Step 3:

[0476] The server sends the generated set of optimal angles and orientations to the single-axis tracking system, which automatically adjusts the angle and orientation of the solar panel. As input, it uses the optimal angle and orientation predicted in step 2. The output is the adjusted state of the solar panel based on the new set values.

[0477] Step 4:

[0478] The server analyzes the sensor data to detect the deterioration status and signs of abnormalities in the solar panels and related equipment. This analysis uses AI and a specific pattern matching method to find signs of deterioration and abnormalities. The input is the latest sensor data set obtained in step 1, and the output is information on signs of deterioration and abnormalities.

[0479] Step 5:

[0480] The server automatically generates a maintenance schedule based on the information on deterioration and signs of abnormalities and notifies the user. The user can receive these notifications through a dedicated application. The input is the deterioration information and signs of abnormalities detected in step 4, and the output is a notification message to the user and a recommended maintenance schedule.

[0481] Step 6:

[0482] Using a dedicated application, users can check the status of solar panels and the latest maintenance information in real time. Through the application, users can make inquiries to the server with questions or requests and receive the results. The input is the solar panel status information and maintenance schedule provided by the server, and the output is the information that the user can check on the application screen.

[0483] 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.

[0484] ---

[0485] The present invention is a system that maximizes the power generation efficiency of solar panels and supports users in managing their maintenance. It also incorporates an emotion engine that recognizes the user's emotions and optimizes the system's response.

[0486] The server provides the following main functions: First, it periodically collects solar radiation data, weather data, and power generation history data, and inputs this data into a generative model. The generative model then predicts the optimal angle and direction of the solar panels and sends the results to the single-axis tracking system. The tracking system then automatically adjusts the angle and direction of the solar panels based on the received data.

[0487] The server also collects data from the solar panels via sensors and predicts their deterioration. If signs of deterioration or abnormalities are detected, the server notifies the user. The notification includes maintenance recommendations, allowing the user to take effective action.

[0488] The terminal provides the user interface. Users can monitor the status of the solar panels in real time and receive notification messages through a dedicated application. Users can also contact the server via the terminal with any questions or requests.

[0489] The system also incorporates an emotion engine that recognizes the user's real-time emotional state. The emotion engine analyzes emotions from the user's voice, facial expressions, and text input and transmits them to the server. The server adjusts notification messages based on the received emotion data to provide responses appropriate to the user's emotional state.

[0490] As a specific example, the server collects solar radiation data, weather data, and power generation history data every morning at 6:00 a.m., and based on this, the generative model predicts optimal settings such as "angle: 30 degrees, direction: south-southeast." This prediction result is sent to the single-axis tracking system, and the solar panels are automatically adjusted. At the same time, sensor data is also collected, and if signs of deterioration or abnormalities are detected, a notification is sent to the user's device stating, "Signs of deterioration are present. Maintenance is recommended." The user receives this notification, checks detailed information through the application, and adjusts the maintenance schedule. In addition, emotions are analyzed from the user's facial expressions and voice, and if stress levels are high, appropriate measures are taken, such as softening the tone of the notification.

[0491] This system configuration maximizes the power generation efficiency of solar panels and enables efficient maintenance management by detecting deterioration and abnormalities early. It also improves the user experience by providing responses that take into account the user's emotional state.

[0492] The processing flow will be explained below.

[0493] ---

[0494] Step 1:

[0495] The server acquires solar radiation data, weather data, and power generation history data at a fixed time every day. The server uses an API to download data from the solar radiation database, acquires the latest weather data from the weather information service, and collects past power generation history from an internal database.

[0496] Step 2:

[0497] The server inputs collected solar radiation data, weather data, and historical power generation data into a generative model, which then predicts the optimal solar panel angle and direction. The generative model combines past and current data and uses machine learning to calculate the optimal value.

[0498] Step 3:

[0499] The server sends the prediction results from the generative model to the single-axis tracking system. For example, actual settings such as "angle: 30 degrees, direction: south-southeast" are sent to the tracking system. The tracking system then automatically adjusts the angle and direction of the panel based on this data.

[0500] Step 4:

[0501] The tracking system physically changes the angle and orientation of the solar panels. The system controls motors and actuators to adjust the position of the panels.

[0502] Step 5:

[0503] The server collects solar panel data from sensors in real time, constantly monitoring voltage, current, temperature, vibration, and other data to detect signs of deterioration or abnormalities.

[0504] Step 6:

[0505] The server inputs the collected sensor data into a degradation prediction model to predict the deterioration state of the panels. If any abnormalities or signs of failure are detected, the information is processed in real time.

[0506] Step 7:

[0507] When the server detects an abnormality or a sign of a malfunction, it sends a notification to the user's device. The notification includes a message such as "Signs of deterioration have been detected. Maintenance is recommended."

[0508] Step 8:

[0509] Users receive a notification, open a dedicated application to view more information, and then act based on the recommended maintenance plan.

[0510] Step 9:

[0511] The server utilizes an emotion engine that recognizes the user's emotions and obtains emotion data from the user's voice and facial expressions, for example, by collecting data through a camera or microphone while the user is using the application.

[0512] Step 10:

[0513] The emotion engine analyzes the collected emotion data and evaluates the user's stress level and satisfaction. If the user is feeling anxious or stressed, the emotion engine sends that information to the server.

[0514] Step 11:

[0515] The server adjusts the content and tone of notification messages based on data from the emotion engine. For example, if a user is feeling stressed, the server will send a message with softer language and encouraging words.

[0516] Step 12:

[0517] Users can send questions or requests to the server through the application's inquiry form via their terminal. Users can send questions using real-time chat or the inquiry form.

[0518] Step 13:

[0519] The server receives the user's inquiry, analyzes it, and provides an appropriate answer. Depending on the inquiry, the server provides a specific solution or additional information and replies to the user.

[0520] In this way, the system combines data collection, prediction, physical adjustment, real-time monitoring, and user emotional responses to maximize the power generation efficiency of solar panels and improve the user experience.

[0521] Example 2

[0522] 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."

[0523] Current solar panel management systems not only lack automatic adjustments to maximize power generation efficiency, but are often slow to predict deterioration and provide maintenance notifications. They also lack the ability to provide appropriate responses that take user emotions into account, making it difficult to optimize the user experience. This can lead to reduced power generation efficiency and delayed maintenance, resulting in reduced overall system efficiency.

[0524] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for acquiring solar radiation data, means for acquiring weather data and power generation history, means for predicting the optimal solar panel angle and direction using a generative model, means for transmitting the predicted angle and direction to the single-axis tracking system, means for predicting the deterioration state of the solar panel, means for detecting abnormalities or signs of failure and notifying maintenance, emotion recognition means, and means for adjusting the notification message based on the user's emotional state. This enables efficient power generation by the solar panel and appropriate maintenance through early detection of deterioration or abnormalities, thereby improving the user experience.

[0525] "Solar radiation data" is information collected by sensors or measuring devices to measure the intensity of sunlight.

[0526] "Weather data" is information about weather conditions, and is data based on weather conditions such as temperature, humidity, wind speed, and precipitation.

[0527] "Power generation history" is recorded data regarding the amount of power generated in the past by the solar panel.

[0528] A "generative model" is a machine learning model used to predict the optimal solar panel angle and orientation based on captured data.

[0529] A "single-axis tracking system" is a device or system that automatically adjusts the angle and orientation of a solar panel along a single axis.

[0530] The "means for predicting the deterioration state" refers to a device or method for detecting the deterioration and performance degradation of a solar panel and predicting its state.

[0531] "Detection of abnormalities and signs of failure" is the process of detecting signs of abnormalities or failures that may occur in solar panels and notifying the user.

[0532] A "means for notifying maintenance" is a method or device for notifying a user that maintenance of a solar panel is required.

[0533] An "emotion recognition means" is a device or method for analyzing and recognizing emotions from a user's voice, facial expressions, and text input.

[0534] A "means for tailoring notification messages" is a device or method that changes the content or tone of the system's notification messages based on the user's emotional state.

[0535] The present invention is a system that maximizes the power generation efficiency of solar panels and supports users in managing their maintenance. The system also incorporates an emotion engine that recognizes the user's emotions and optimizes the system's response.

[0536] The server provides the following main functions. First, it periodically acquires solar radiation data, weather data, and power generation history data. Weather data is acquired using the OpenWeatherMap API, and solar radiation data is acquired from sensors via a local connection. Power generation history data is collected from the solar panel inverter. This data is managed centrally within the server.

[0537] The server then inputs the collected data into a generative AI model, which is built using the TensorFlow library. The model predicts the optimal angle and direction of the solar panels based on the input weather data, solar radiation data, and power generation history data. This predicted data is sent to a single-axis tracking system. The tracking system automatically adjusts the angle and direction of the solar panels based on the received data. This adjustment is made using the RS-485 communication protocol.

[0538] The server also collects solar panel status data from sensors to detect signs of deterioration or abnormalities. This process uses machine learning models (e.g., Scikit-learn) and collects sensor data via the LoRa communication protocol. Based on the detected signs of deterioration or abnormalities, the server notifies the user of maintenance recommendations. These notifications are sent to the device and displayed through the user interface.

[0539] The role of the terminal is to provide a user interface. Users can use a dedicated application (developed with React Native) to monitor the status of the solar panels in real time. Furthermore, users can send queries or requests to the server through the application. The application runs on both iOS and Android.

[0540] The emotion engine recognizes the user's real-time emotional state. Specifically, the Emotient API is used to analyze emotions from the user's voice, facial expressions, and text input. The device collects data using the camera and microphone, and the emotion engine performs the analysis. The analysis results are sent to the server, which adjusts the notification message based on the received emotion data. For example, if the user is feeling stressed, the tone of the notification message will be softened. A message such as "Please let us know if you need more specific instructions" will be sent.

[0541] As a specific example, a server collects solar radiation data, weather data, and power generation history data every day at 6:00 a.m. This data is input into a generative AI model, which then predicts optimal settings, such as "angle: 30 degrees, direction: south-southeast." The prediction results are sent to a single-axis tracking system, which automatically adjusts the solar panels. At the same time, sensor data is also collected, and if signs of deterioration or abnormalities are detected, a notification is sent to the user's device stating, "Signs of deterioration have been detected. Maintenance is recommended."

[0542] In addition, emotions are analyzed from the user's facial expressions and voice, and if stress levels are high, the tone of notifications is softened. An example of a specific prompt is, "Please set a method to analyze the user's voice data and facial expression data, recognize their emotional state, and adjust notification messages accordingly."

[0543] This system configuration maximizes the power generation efficiency of the solar panels and enables appropriate maintenance by detecting deterioration or abnormalities early and notifying the user.Furthermore, by using an emotion engine, it is possible to provide responses based on the user's emotional state, improving the user experience.

[0544] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0545] Step 1:

[0546] The server collects solar radiation data, weather data, and power generation history data every day at 6:00 a.m.

[0547] Input: The server sends API requests and collects data from sensors and inverters.

[0548] Operation: Weather data is obtained using the OpenWeatherMap API, solar radiation data is received from the sensor via LoRa communication, and power generation history data is read from the inverter.

[0549] Output: Store the acquired data in a database and format it for further processing.

[0550] Step 2:

[0551] The server inputs the collected data into a generative AI model.

[0552] Input: Solar radiation data, weather data, and historical power generation data collected in step 1.

[0553] How it works: We use the TensorFlow library to run a generative model to predict the optimal solar panel angle and orientation.

[0554] Output: Angle and direction data predicted by the generative AI model.

[0555] Step 3:

[0556] The server sends the prediction results to the single-axis tracking system.

[0557] Input: Prediction data (angle and direction) obtained in step 2.

[0558] Operation: Sends predicted data to a tracking system via RS-485 communication protocol.

[0559] Output: Forecast data received by the tracking system.

[0560] Step 4:

[0561] The tracking system automatically adjusts the angle and direction of the solar panels.

[0562] Input: The forecast data received in step 3.

[0563] Operation: Sends commands to the motor driver, driving the motor to automatically adjust the angle and direction of the solar panel to the set values.

[0564] Output: Regulated solar panel status.

[0565] Step 5:

[0566] The server collects status data from the sensors and predicts the deterioration state of the solar panels.

[0567] Input: Status data such as vibration data and temperature data of the solar panel.

[0568] Operation: Data is received from sensors via LoRa communication, and signs of deterioration or abnormalities are analyzed using Scikit-learn.

[0569] Output: Analyzed data on signs of deterioration and abnormalities.

[0570] Step 6:

[0571] The server sends maintenance notifications to users based on predicted deterioration and abnormality data.

[0572] Input: Data on signs of deterioration and abnormalities analyzed in Step 5.

[0573] Operation: If degradation or abnormality is detected, a notification message is generated and sent to the terminal.

[0574] Output: Maintenance notification displayed on the user's device.

[0575] Step 7:

[0576] The device will display a notification to the user prompting them to take the necessary action.

[0577] Input: Maintenance notification sent in step 6.

[0578] Behavior: Displays a notification message in the user interface of the dedicated application, and also raises an alert so that the user can see it.

[0579] Output: The notification message displayed to the user.

[0580] Step 8:

[0581] The emotion engine analyzes the user's emotions from their facial expressions and voice and sends the results to the server.

[0582] Input: User's facial expression data, voice data.

[0583] How it works: Collects data using the device's camera and microphone and sends it to the Emotient API for sentiment analysis.

[0584] Output: User sentiment data obtained as a result of the analysis.

[0585] Step 9:

[0586] The server adjusts the notification message based on the received emotion data and sends it back to the user.

[0587] Input: User emotion data obtained in step 8.

[0588] Behavior: Adjust the tone and content of notification messages based on your emotional state. For example, soften the tone if you are feeling stressed.

[0589] Output: A notification message appropriate to the user's emotional state.

[0590] Step 10:

[0591] Users can check notifications and messages and take necessary actions.

[0592] Input: The notification message adjusted in step 9.

[0593] Action: The user reviews the notification and adjusts the maintenance schedule through the application as needed.

[0594] Output: User actions such as updating a maintenance schedule or submitting a ticket.

[0595] (Application example 2)

[0596] 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."

[0597] Conventional solar panel systems are often inefficient because optimization and maintenance management to improve power generation efficiency are performed manually. Furthermore, there are insufficient means to detect deterioration or abnormalities that users face early, which can lead to delayed appropriate responses. Furthermore, responses that take into account the user's emotional state are not provided, resulting in a poor user experience regarding notifications and maintenance.

[0598] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring solar radiation data, means for acquiring weather data and power generation history, means for predicting the optimal solar panel angle and direction using a generative model, means for transmitting the predicted angle and direction to the single-axis tracking system, means for predicting the deterioration state of the solar panel, means for detecting abnormalities and signs of failure and notifying maintenance, means for controlling the robot arm using power generation history data and automatically adjusting the solar panel angle, means for collecting sensor data and monitoring the solar panel status, means for automatically adjusting the maintenance schedule based on the collected data, means for notifying the user of the maintenance schedule, means for analyzing the user's emotions using an emotion engine, and means for adjusting notification messages according to the user's emotions. This maximizes the power generation efficiency of the solar panel, enables early detection of deterioration and abnormalities, and realizes efficient maintenance management. Furthermore, providing responses according to the user's emotional state improves the user experience.

[0599] "Solar radiation data" is data that indicates the amount of solar radiation that reaches the earth's surface from the sun.

[0600] "Weather data" refers to data that indicates weather conditions such as temperature, humidity, precipitation, and wind speed.

[0601] "Power generation history data" is recorded data relating to the amount of power generated by the solar panel in the past.

[0602] A "generative model" is a machine learning model that predicts the optimal angle and direction of solar panels based on input data.

[0603] A "single-axis tracking system" is a device that rotates a solar panel along a single axis.

[0604] The "deterioration state of the solar panel" refers to the state that indicates the degree of physical and functional deterioration of the solar panel.

[0605] "Abnormalities and signs of failure" are signs that indicate an abnormal state that deviates from normal operation or a sign that indicates a precursor to failure.

[0606] A "maintenance schedule" is a schedule for performing regular maintenance on solar panels.

[0607] A "robot arm" is a mechanical device that can move with multiple joints like a human arm.

[0608] "Sensor data" refers to data relating to physical quantities obtained from various sensors.

[0609] An "emotion engine" is software or algorithm for analyzing a user's emotional state.

[0610] "User's emotions" are data that indicate the user's psychological state and mood.

[0611] A "notification message" is a message sent by the system to the user to provide information.

[0612] "User experience" refers to the overall experience and satisfaction a user has when using a system or service.

[0613] The present invention is a system that maximizes the power generation efficiency of solar panels and performs efficient maintenance management by predicting deterioration and abnormalities. Furthermore, it incorporates an emotion engine that recognizes the user's emotions and provides optimal responses. The following describes an embodiment of the present invention in detail.

[0614] The server is equipped with a means of acquiring solar radiation data, which is periodically obtained from an external source via an API. Weather data and power generation history data are also collected via the API. This data is input into the generative model, which uses a machine learning algorithm to predict the optimal angle and orientation of the solar panels based on the obtained data. The prediction results are sent to the single-axis tracking system, which automatically adjusts the angle and orientation of the solar panels.

[0615] Furthermore, the server is equipped with a means to predict the deterioration status of the solar panels. This is done by analyzing data from sensors and detecting signs of deterioration or abnormalities. If an abnormality or sign of deterioration is detected, the server sends a notification to the user's device. This notification also includes specific maintenance recommendations, helping the user to take effective action.

[0616] The system also includes a means for utilizing historical power generation data to control a robotic arm, which adjusts the angle of the solar panels to maximize power generation efficiency. The system also provides a function for automatically adjusting maintenance schedules based on sensor data, thereby streamlining maintenance management.

[0617] The server analyzes the user's emotions using an emotion engine. This emotion engine recognizes emotions in real time from the user's voice, facial expressions, and text input, and has a means to adjust the response message based on the analyzed data. If the user is feeling stressed, the tone of the notification message can be softened, for example, to improve the user experience.

[0618] For example, the server uses solar radiation data and weather data to predict that the solar panels should be angled 30 degrees and pointed south-southeast, and sends this prediction to the single-axis tracking system. The solar panels are then automatically adjusted to achieve optimal power generation efficiency. At the same time, if signs of deterioration are detected based on the sensor data, a notification is sent to the user's device stating, "Signs of deterioration have been detected. Maintenance is recommended." The user can check the details and adjust the schedule through a smartphone app. The system also recognizes emotions from the user's facial expressions and voice, and sends softer messages if stress levels are high.

[0619] For example, you can use a prompt such as, "Based on weather data and historical power generation data from the solar panels, predict the optimal angle for the solar panels and control the robot arm. Current weather data is temperature: 25 degrees, solar radiation: 800, and historical power generation data is output: 150."

[0620] In this way, the present invention is a system that enables maximization of power generation efficiency of solar panels, early detection of deterioration and abnormalities, efficient maintenance management, and improved user experience.

[0621] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0622] Step 1:

[0623] The server receives solar radiation data through API. This data is obtained from the solar radiation sensor and sent as input to the server. The server receives this data and passes it to the next processing step.

[0624] Step 2:

[0625] The server uses an API to collect weather data and historical power generation data, including temperature, humidity, wind speed, and past power generation. The server receives this data and stores it in an internal database, which then prepares input data for the generative model along with solar radiation data.

[0626] Step 3:

[0627] The server inputs solar radiation data, weather data, and historical power generation data into the generative model, which uses machine learning algorithms to predict the optimal solar panel angle and direction based on these inputs. The output is the specific angle and direction.

[0628] Step 4:

[0629] The server sends the angle and direction obtained from the generative model to the single-axis tracking system, which instructs the solar panel to be positioned at a 30-degree angle and facing south-southeast. The tracking system then automatically adjusts the solar panel based on the data received.

[0630] Step 5:

[0631] The server collects data from sensors to predict the deterioration state of the solar panels. This data includes the current, voltage, and temperature of the solar panels. The server analyzes this data to detect signs of deterioration or abnormalities. If an abnormality is found, the information is sent to the next step.

[0632] Step 6:

[0633] If the server detects an abnormality or signs of deterioration, it sends a notification to the user's device, for example, a message saying, "Signs of deterioration are present. Maintenance is recommended." The notification includes recommendations for maintenance and suggestions for next steps.

[0634] Step 7:

[0635] The server controls the robot arm based on the power generation history data. It analyzes this data and sends instructions to the robot arm to adjust the angle of the solar panel as needed. The robot arm follows these instructions and actually adjusts the angle.

[0636] Step 8:

[0637] The server automatically adjusts the maintenance schedule based on sensor data, including the status of the solar panels, usage time, environmental conditions, etc. The server analyzes this data, determines the next maintenance date, and notifies the user.

[0638] Step 9:

[0639] The server analyzes the user's emotions using an emotion engine, which analyzes the user's voice, facial expressions, and text input to determine the user's emotional state. For example, if the server determines that the user is tired, it adjusts the notification content to a softer tone.

[0640] Step 10:

[0641] The server adjusts the notification message based on the user's emotions based on the emotional data obtained by the emotion engine. For example, if the user is feeling stressed, the server sends a soft message such as, "Maintenance is required. However, please rest assured that we will continue to support you."

[0642] In this way, the server can execute a series of processing steps to maximize the power generation efficiency of the solar panels, detect deterioration or abnormalities early, manage maintenance efficiently, and improve the user experience.

[0643] 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.

[0644] 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.

[0645] 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.

[0646] [Third embodiment]

[0647] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0648] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0649] 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).

[0650] 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.

[0651] 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.

[0652] 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).

[0653] 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.

[0654] 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.

[0655] 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.

[0656] 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.

[0657] 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.

[0658] 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."

[0659] ---

[0660] The present invention aims to efficiently utilize renewable energy, and specifically relates to a system that maximizes the power generation efficiency of solar panels. This system is composed of a server, a terminal, and a user element.

[0661] The server has the following main functions. First, it periodically acquires solar radiation data, weather data, and power generation history data, and inputs this data into a generative model to predict the optimal angle and direction of the solar panels. Next, it sends the prediction results of the generative model to a single-axis tracking system, which automatically adjusts the angle and direction of the solar panels. Furthermore, it predicts the deterioration state of the solar panels based on data acquired from sensors, detects signs of abnormalities or failures, and notifies the user. This makes it possible to automatically adjust an appropriate maintenance schedule and notify the user.

[0662] The terminal mainly provides the user interface. Users can monitor the status of the solar panels in real time through a dedicated application. For example, they can check information such as the current amount of power generated, the angle and direction of the solar panels, and the state of deterioration. Users can also send inquiries or requests to the server via the terminal and receive the results.

[0663] To use the system effectively, users periodically check the information provided, perform maintenance as needed, and respond to notifications from the server. For example, if a notification arrives from the server stating that "maintenance is required," the user responds promptly and performs appropriate maintenance to maintain stable system operation.

[0664] As a specific example, the server collects solar radiation data, weather data, and power generation history data every morning at 6:00 a.m., and based on this, the generative model predicts optimal settings such as "angle: 30 degrees, direction: south-southeast." This prediction result is sent to the single-axis tracking system, and the solar panels are automatically adjusted. At the same time, sensor data is also collected, and if signs of deterioration or abnormalities are detected, a notification is sent to the user's device stating, "Signs of deterioration have been detected. Maintenance is recommended." The user receives this notification, checks detailed information through the application, and adjusts the maintenance schedule.

[0665] Key features of this system include data-based prediction and automatic adjustment, early detection of deterioration and abnormalities, and efficient maintenance management through user interaction, which maximizes the power generation efficiency of the solar panels and ensures stable operation of the system.

[0666] The processing flow will be explained below.

[0667] ---

[0668] Step 1:

[0669] The server collects solar radiation data, weather data, and power generation history data at a fixed time every day. The server accesses each data source via API, collects the data, and stores it in a local database.

[0670] Step 2:

[0671] The server inputs the accumulated data into the generative model, which then combines solar radiation data, weather data, and power generation history and passes it to the generative model to predict the optimal angle and direction of the solar panels.

[0672] Step 3:

[0673] The server sends the prediction results of the generative model to the single-axis tracking system, which automatically adjusts the solar panel by sending prediction results such as "angle: 30 degrees, direction: south-southeast" to the tracking system.

[0674] Step 4:

[0675] The tracking system adjusts the angle and orientation of the solar panels based on the received predictions. The tracking system controls the motors to change the physical position of the solar panels.

[0676] Step 5:

[0677] The server collects solar panel data from sensors, including voltage, current, and temperature, in real time, and monitors for signs of abnormalities or deterioration.

[0678] Step 6:

[0679] The server predicts the deterioration state based on the collected sensor data, and inputs the sensor data into a deterioration prediction model to detect signs of deterioration and abnormalities.

[0680] Step 7:

[0681] If the server detects an abnormality or a sign of a failure, it will notify the user. When an abnormality is detected, the server will send a notification message to the user's device and provide detailed information.

[0682] Step 8:

[0683] The user receives a notification and opens a dedicated application to check detailed information. The user sees a notification such as "Signs of deterioration have been detected. Maintenance is recommended." and considers the necessary action.

[0684] Step 9:

[0685] The server automatically adjusts the maintenance schedule based on abnormalities or deterioration, and sets the next maintenance date based on the results of the predictive model and notifies the user.

[0686] Step 10:

[0687] The user checks the new maintenance schedule and accepts or adjusts it. The user checks the schedule through the terminal and performs maintenance work as necessary.

[0688] Step 11:

[0689] Users can monitor the status of their solar panels in real time through a dedicated application. Users open the app and check the current power generation, angle, direction, and deterioration status.

[0690] Step 12:

[0691] Users can send questions or requests to the server via their device, or submit questions using the inquiry form within the app.

[0692] Step 13:

[0693] The server receives queries from users and provides answers based on the analysis results. The server analyzes the query and returns an appropriate answer to the user.

[0694] Example 1

[0695] 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."

[0696] In conventional solar panel systems, optimal angle adjustment and direction prediction to achieve efficient power generation are often performed manually, which tends to reduce power generation efficiency. It is also difficult to detect deterioration or abnormalities early, which can delay appropriate maintenance. Furthermore, users are sometimes unable to monitor the status of the panels in real time, which creates the challenge of being unable to respond immediately when problems occur.

[0697] 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.

[0698] In this invention, the server includes means for acquiring solar radiation data, means for acquiring weather data and power generation history, means for predicting the optimal solar panel angle and direction using a generative model, means for transmitting the predicted angle and direction to a tracking system, means for predicting the deterioration state of the solar panel, means for detecting abnormalities and signs of failure and notifying maintenance, means for collecting sensor data and physically adjusting the solar panel, means for inputting a data set into a generative AI model to predict the optimal angle and direction, and means for transmitting a notification to the user when an abnormality is detected. This maximizes the power generation efficiency of the solar panel and enables stable operation of the system.

[0699] "Solar radiation data" is data that indicates the amount of solar energy that reaches the Earth's surface from the sun.

[0700] "Weather data" refers to data that indicates weather conditions such as weather conditions (e.g., sunny, cloudy, rainy, etc.), temperature, humidity, and wind speed.

[0701] "Power generation history" is data that records the amount of power generated by the solar cell panel in the past and its fluctuations.

[0702] A "generative model" is an artificial intelligence algorithm that makes predictions and inferences based on input data.

[0703] A "tracking system" is a device that adjusts the angle and direction of solar panels for the purpose of efficient power generation.

[0704] The "deterioration state" refers to the degree of performance degradation or damage that occurs during the course of use of the solar panel.

[0705] "Abnormalities and signs of failure" are signs that the solar panels or related equipment are outside the normal operating range or are signs that indicate the possibility of a failure.

[0706] "Maintenance" means preventative or corrective work performed to maintain the proper functioning of solar panels and related systems.

[0707] "Sensor data" refers to information obtained from sensors, including physical conditions such as temperature, vibration, current, and voltage of solar panels.

[0708] A "generative AI model" is an artificial intelligence model that automatically generates optimal solutions based on large amounts of data.

[0709] A "dataset" is a collection of data compiled for a specific purpose.

[0710] A "user" is a person or organization that uses the system to manage and monitor solar panels.

[0711] The present invention aims to efficiently utilize renewable energy, and specifically relates to a system that maximizes the power generation efficiency of solar panels. This system is composed of a server, a terminal, and a user element.

[0712] First, the server periodically obtains solar radiation data and weather data using a weather API. Next, it obtains historical power generation data from a database. These data are then converted into a single dataset and input into a generative AI model. For example, the generative AI model uses GPT-4, a type of generative AI. This model makes predictions based on prompt statements such as the following:

[0713] "Predict tomorrow's optimal solar panel angle and direction based on yesterday's weather data, solar radiation data, and historical power generation data from the past week."

[0714] The acquired predicted data is sent to the tracking system, which uses an Arduino-based single-axis tracking system and physically adjusts the solar panel based on the predicted angle and direction. The server also collects sensor data from a TI sensor module and checks the solar panel for deterioration or abnormalities. If an abnormality is detected, a notification is sent to the user's device.

[0715] The terminal provides a user interface. Through a dedicated application, users can monitor the status of the solar panels in real time, checking information such as the current power generation amount, panel angle, direction, and deterioration status. Users can also send inquiries or requests to the server via the terminal and receive the results.

[0716] To use the system effectively, users periodically check the information provided, perform maintenance as needed, and respond to notifications from the server. For example, if a notification arrives from the server stating that "maintenance is required," the user responds promptly and performs the appropriate maintenance to maintain stable operation of the system.

[0717] As a specific example, every day at 6:00 AM, the server retrieves solar radiation data and weather data from a weather API and retrieves the past week's power generation history data from a database. This data is formatted and input into a generative AI model. The generative AI model makes predictions such as "angle: 30 degrees, direction: south-southeast," and this information is sent to a tracking system. The tracking system uses this information to physically adjust the solar panel. At the same time, the server collects data from a TI sensor module and checks for deterioration or abnormalities. If an abnormality is detected, a notification is sent to the user's device stating, "Signs of deterioration are present. Maintenance is recommended." The user can then check this notification and schedule appropriate maintenance.

[0718] This system maximizes the power generation efficiency of the solar panels and ensures stable operation of the system.

[0719] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0720] Step 1:

[0721] The server uses a weather API to obtain solar radiation data. In this case, the server sends an API request and receives the obtained data in JSON format. The input is the request information to the API, and the output is the obtained solar radiation data. This data is formatted appropriately for use in subsequent processing.

[0722] Step 2:

[0723] The server retrieves weather data from the same weather API. The server sends an API request and receives data such as weather conditions, temperature, and humidity in JSON format. The input is the request information to the API, and the output is the retrieved weather data. This weather data is also formatted and converted into a format that can be used for subsequent processing.

[0724] Step 3:

[0725] The server retrieves historical power generation data from the database. It executes a database query to retrieve power generation data for the past week. The input is a query to the database, and the output is the retrieved power generation data. This data is formatted as time-series data on power generation.

[0726] Step 4:

[0727] The server converts the acquired solar radiation data, weather data, and power generation history data into a single dataset. This converts the data into a format that is easy for the generative AI model to use. The input is each piece of data acquired in steps 1 to 3, and the output is the converted dataset.

[0728] Step 5:

[0729] The server inputs the formatted dataset into the generative AI model as a prompt. An example prompt is, "Please predict tomorrow's optimal angle and direction of the solar panels based on yesterday's weather data, solar radiation data, and power generation history data from the past week." The input is the formatted dataset and prompt, and the output is the prediction result from the generative AI model.

[0730] Step 6:

[0731] The server receives the optimal solar panel angle and direction data returned by the generative AI model. The input is the predicted result from the generative AI model, and the output is the optimal angle and direction data. This data is used to instruct the tracking system.

[0732] Step 7:

[0733] The server sends the prediction results to the tracking system, which then physically adjusts the angle and orientation of the solar panels based on the received data. The input is the predicted angle and orientation data, and the output is the adjusted physical state of the panels.

[0734] Step 8:

[0735] The server collects sensor data from TI sensor modules. The data from the sensors includes information such as temperature, vibration, current, and voltage. The input is real-time data from the sensors, and the output is the collected sensor data.

[0736] Step 9:

[0737] The server inputs the collected sensor data into an AI model to predict the state of deterioration or abnormalities. The input is sensor data, and the output is the predicted results of the state of deterioration or abnormalities. The results are notified to the user when an abnormality is detected.

[0738] Step 10:

[0739] If an abnormality is detected, the server sends a notification to the user's device. The notification content states, "Signs of deterioration are present. Maintenance is recommended." The input is the predicted abnormality result, and the output is the notification to the user.

[0740] Step 11:

[0741] Users use a dedicated application on their device to monitor the status of their solar panels in real time. The application displays the current amount of power generated, the angle and direction of the panels, and their state of deterioration. The input is various data sent from the server, and the output is real-time information that the user can check.

[0742] Step 12:

[0743] Users receive notifications from the server and schedule appropriate maintenance. The input is a maintenance notification from the server, and the output is the execution of the maintenance schedule. This ensures stable operation of the system.

[0744] (Application example 1)

[0745] 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."

[0746] Efficient energy use is a key issue in modern factories. In particular, to promote the use of renewable energy, it is necessary to maximize the power generation efficiency of solar panels and continuously monitor and adjust their status. However, current systems make it difficult to perform real-time optimization and automatic maintenance prediction based on data. This leads to issues such as reduced energy efficiency and increased factory operating costs.

[0747] 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.

[0748] In this invention, the server includes means for acquiring solar radiation data, means for acquiring weather data and power generation history, and means for predicting the optimal solar panel angle and direction using a generative model. This enables automatic optimization to maximize energy efficiency. The server also includes means for transmitting the predicted angle and direction to a single-axis tracking system, means for predicting the deterioration state of the solar panels, means for detecting abnormalities and signs of failure and notifying maintenance, means for collecting sensor data within the factory, means for analyzing the data in real time to maximize energy efficiency and automatically optimizing equipment settings, and means for predicting a maintenance schedule based on signs of deterioration and abnormalities and notifying the user. This enables efficient energy use.

[0749] "Solar radiation data" is information that measures the radiant energy from the sun to the earth.

[0750] "Weather Data" is information about the weather and meteorological conditions in a particular area.

[0751] "Power generation history" is a record of the electrical energy generated in the past by solar panels or other power generation devices.

[0752] A "generative model" is an algorithm or component of artificial intelligence that predicts optimal outcomes based on acquired data.

[0753] The "optimal solar panel angle and orientation" refers to the best angle and orientation for solar panels to generate electricity as efficiently as possible.

[0754] A "single-axis tracking system" is an automatic control system for adjusting the angle and direction of solar panels.

[0755] "Solar panel deterioration" refers to the degree to which a solar panel is no longer able to perform at its full potential due to use or environmental factors.

[0756] "Abnormalities and signs of failure" are phenomena or signs that a system or device is beyond the range of normal operation or that there is an increased possibility of it failing in the future.

[0757] A "maintenance schedule" is a plan for efficiently maintaining and inspecting facilities and equipment.

[0758] "Sensor data" is information collected from various sensor devices.

[0759] "Energy efficiency" refers to the actual amount of power generated and the efficiency of energy utilization relative to the amount of energy used.

[0760] "Analyzing data in real time" means evaluating and analyzing data as soon as it is generated.

[0761] A "purpose-built application" is a software program designed for a specific purpose.

[0762] A "user" is an entity that operates and manages a system or device.

[0763] The present invention aims to efficiently utilize renewable energy, and specifically relates to a system that maximizes the power generation efficiency of solar panels. This system is composed of a server, a terminal, and a user element.

[0764] The server periodically acquires solar radiation data, weather data, and power generation history data, and inputs this data into a generative model to predict the optimal angle and direction of the solar panels. The server also sends the prediction results of this generative model to the single-axis tracking system, which automatically adjusts the angle and direction of the solar panels. Furthermore, the server predicts the deterioration state of the solar panels based on data acquired from sensors, detects signs of abnormalities or failures, and notifies the user. This makes it possible to automatically adjust appropriate maintenance schedules and notify the user.

[0765] The terminal mainly provides the user interface. Users can monitor the status of the solar panels in real time through a dedicated application. For example, they can check information such as the current amount of power generated, the angle and direction of the solar panels, and the state of deterioration. Users can also send inquiries or requests to the server via the terminal and receive the results.

[0766] To use the system effectively, users are required to regularly check the information provided, perform maintenance as necessary, and respond to notifications from the server. For example, if a notification arrives from the server stating that "maintenance is required," the user must respond promptly and perform the appropriate maintenance to maintain stable system operation.

[0767] The system has the following specific components:

[0768] 1. Data collection function:

[0769] The server automatically collects solar radiation data, weather data, power generation history data, and various sensor data within the factory, which is important information required for subsequent processing.

[0770] 2. Leveraging generative models:

[0771] Based on the collected data, a generative model predicts the optimal angle and direction of the solar panels. This model is implemented using Python and Flask.

[0772] 3. Real-time analysis:

[0773] The collected data is analyzed in real time and any necessary adjustments are automatically made to maximize energy efficiency.

[0774] 4. Maintenance forecasting and notifications:

[0775] The server predicts deterioration and abnormalities, generates a maintenance schedule as needed, and notifies the user through a dedicated application.

[0776] As a specific example, the server collects solar radiation data, weather data, and power generation history data every morning at 6:00 a.m., and based on this, the generative model predicts optimal settings such as "angle: 30 degrees, direction: south-southeast." This prediction result is sent to the single-axis tracking system, and the solar panels are automatically adjusted. At the same time, sensor data is also collected, and if signs of deterioration or abnormalities are detected, a notification is sent to the user's device stating, "Signs of deterioration have been detected. Maintenance is recommended." The user receives this notification, checks detailed information through the application, and adjusts the maintenance schedule.

[0777] Example prompt sentence:

[0778] Please use "solar radiation data, weather data, and power generation history data to optimize factory energy management" to predict "the optimal angle and direction of solar panels." For example, if the solar radiation is 1000W / m^2, the weather is sunny, and the power generation history data shows an efficiency of 90%, please output the optimal setting value.

[0779] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0780] Step 1:

[0781] The server collects solar radiation data, weather data, power generation history data, and sensor data. These data are periodically obtained from sensor devices installed on the server. Solar radiation, temperature, wind speed, and past power generation data are taken as input and stored in a database. The output is a set of the latest state of each data.

[0782] Step 2:

[0783] Based on the data collected by the server, the data is input into a generative AI model to predict the optimal solar panel angle and direction. This process uses a Python-based machine learning model. The dataset collected in step 1 is input into the model, and the process of predicting the optimal angle and direction begins. The output is a set of generated optimal angles and directions.

[0784] Step 3:

[0785] The server sends the generated set of optimal angles and orientations to the single-axis tracking system, which automatically adjusts the angle and orientation of the solar panel. As input, it uses the optimal angle and orientation predicted in step 2. The output is the adjusted state of the solar panel based on the new set values.

[0786] Step 4:

[0787] The server analyzes the sensor data to detect the deterioration status and signs of abnormalities in the solar panels and related equipment. This analysis uses AI and a specific pattern matching method to find signs of deterioration and abnormalities. The input is the latest sensor data set obtained in step 1, and the output is information on signs of deterioration and abnormalities.

[0788] Step 5:

[0789] The server automatically generates a maintenance schedule based on the information on deterioration and signs of abnormalities and notifies the user. The user can receive these notifications through a dedicated application. The input is the deterioration information and signs of abnormalities detected in step 4, and the output is a notification message to the user and a recommended maintenance schedule.

[0790] Step 6:

[0791] Using a dedicated application, users can check the status of solar panels and the latest maintenance information in real time. Through the application, users can make inquiries to the server with questions or requests and receive the results. The input is the solar panel status information and maintenance schedule provided by the server, and the output is the information that the user can check on the application screen.

[0792] 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.

[0793] ---

[0794] The present invention is a system that maximizes the power generation efficiency of solar panels and supports users in managing their maintenance. It also incorporates an emotion engine that recognizes the user's emotions and optimizes the system's response.

[0795] The server provides the following main functions: First, it periodically collects solar radiation data, weather data, and power generation history data, and inputs this data into a generative model. The generative model then predicts the optimal angle and direction of the solar panels and sends the results to the single-axis tracking system. The tracking system then automatically adjusts the angle and direction of the solar panels based on the received data.

[0796] The server also collects data from the solar panels via sensors and predicts their deterioration. If signs of deterioration or abnormalities are detected, the server notifies the user. The notification includes maintenance recommendations, allowing the user to take effective action.

[0797] The terminal provides the user interface. Users can monitor the status of the solar panels in real time and receive notification messages through a dedicated application. Users can also contact the server via the terminal with any questions or requests.

[0798] The system also incorporates an emotion engine that recognizes the user's real-time emotional state. The emotion engine analyzes emotions from the user's voice, facial expressions, and text input and transmits them to the server. The server adjusts notification messages based on the received emotion data to provide responses appropriate to the user's emotional state.

[0799] As a specific example, the server collects solar radiation data, weather data, and power generation history data every morning at 6:00 a.m., and based on this, the generative model predicts optimal settings such as "angle: 30 degrees, direction: south-southeast." This prediction result is sent to the single-axis tracking system, and the solar panels are automatically adjusted. At the same time, sensor data is also collected, and if signs of deterioration or abnormalities are detected, a notification is sent to the user's device stating, "Signs of deterioration are present. Maintenance is recommended." The user receives this notification, checks detailed information through the application, and adjusts the maintenance schedule. In addition, emotions are analyzed from the user's facial expressions and voice, and if stress levels are high, appropriate measures are taken, such as softening the tone of the notification.

[0800] This system configuration maximizes the power generation efficiency of solar panels and enables efficient maintenance management by detecting deterioration and abnormalities early. It also improves the user experience by providing responses that take into account the user's emotional state.

[0801] The processing flow will be explained below.

[0802] ---

[0803] Step 1:

[0804] The server acquires solar radiation data, weather data, and power generation history data at a fixed time every day. The server uses an API to download data from the solar radiation database, acquires the latest weather data from the weather information service, and collects past power generation history from an internal database.

[0805] Step 2:

[0806] The server inputs collected solar radiation data, weather data, and historical power generation data into a generative model, which then predicts the optimal solar panel angle and direction. The generative model combines past and current data and uses machine learning to calculate the optimal value.

[0807] Step 3:

[0808] The server sends the prediction results from the generative model to the single-axis tracking system. For example, actual settings such as "angle: 30 degrees, direction: south-southeast" are sent to the tracking system. The tracking system then automatically adjusts the angle and direction of the panel based on this data.

[0809] Step 4:

[0810] The tracking system physically changes the angle and orientation of the solar panels. The system controls motors and actuators to adjust the position of the panels.

[0811] Step 5:

[0812] The server collects solar panel data from sensors in real time, constantly monitoring voltage, current, temperature, vibration, and other data to detect signs of deterioration or abnormalities.

[0813] Step 6:

[0814] The server inputs the collected sensor data into a degradation prediction model to predict the deterioration state of the panels. If any abnormalities or signs of failure are detected, the information is processed in real time.

[0815] Step 7:

[0816] When the server detects an abnormality or a sign of a malfunction, it sends a notification to the user's device. The notification includes a message such as "Signs of deterioration have been detected. Maintenance is recommended."

[0817] Step 8:

[0818] Users receive a notification, open a dedicated application to view more information, and then act based on the recommended maintenance plan.

[0819] Step 9:

[0820] The server utilizes an emotion engine that recognizes the user's emotions and obtains emotion data from the user's voice and facial expressions, for example, by collecting data through a camera or microphone while the user is using the application.

[0821] Step 10:

[0822] The emotion engine analyzes the collected emotion data and evaluates the user's stress level and satisfaction. If the user is feeling anxious or stressed, the emotion engine sends that information to the server.

[0823] Step 11:

[0824] The server adjusts the content and tone of notification messages based on data from the emotion engine. For example, if a user is feeling stressed, the server will send a message with softer language and encouraging words.

[0825] Step 12:

[0826] Users can send questions or requests to the server through the application's inquiry form via their terminal. Users can send questions using real-time chat or the inquiry form.

[0827] Step 13:

[0828] The server receives the user's inquiry, analyzes it, and provides an appropriate answer. Depending on the inquiry, the server provides a specific solution or additional information and replies to the user.

[0829] In this way, the system combines data collection, prediction, physical adjustment, real-time monitoring, and user emotional responses to maximize the power generation efficiency of solar panels and improve the user experience.

[0830] Example 2

[0831] 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."

[0832] Current solar panel management systems not only lack automatic adjustments to maximize power generation efficiency, but are often slow to predict deterioration and provide maintenance notifications. They also lack the ability to provide appropriate responses that take user emotions into account, making it difficult to optimize the user experience. This can lead to reduced power generation efficiency and delayed maintenance, resulting in reduced overall system efficiency.

[0833] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for acquiring solar radiation data, means for acquiring weather data and power generation history, means for predicting the optimal solar panel angle and direction using a generative model, means for transmitting the predicted angle and direction to the single-axis tracking system, means for predicting the deterioration state of the solar panel, means for detecting abnormalities or signs of failure and notifying maintenance, emotion recognition means, and means for adjusting the notification message based on the user's emotional state. This enables efficient power generation by the solar panel and appropriate maintenance through early detection of deterioration or abnormalities, thereby improving the user experience.

[0834] "Solar radiation data" is information collected by sensors or measuring devices to measure the intensity of sunlight.

[0835] "Weather data" is information about weather conditions, and is data based on weather conditions such as temperature, humidity, wind speed, and precipitation.

[0836] "Power generation history" is recorded data regarding the amount of power generated in the past by the solar panel.

[0837] A "generative model" is a machine learning model used to predict the optimal solar panel angle and orientation based on captured data.

[0838] A "single-axis tracking system" is a device or system that automatically adjusts the angle and orientation of a solar panel along a single axis.

[0839] The "means for predicting the deterioration state" refers to a device or method for detecting the deterioration and performance degradation of a solar panel and predicting its state.

[0840] "Detection of abnormalities and signs of failure" is the process of detecting signs of abnormalities or failures that may occur in solar panels and notifying the user.

[0841] A "means for notifying maintenance" is a method or device for notifying a user that maintenance of a solar panel is required.

[0842] An "emotion recognition means" is a device or method for analyzing and recognizing emotions from a user's voice, facial expressions, and text input.

[0843] A "means for tailoring notification messages" is a device or method that changes the content or tone of the system's notification messages based on the user's emotional state.

[0844] The present invention is a system that maximizes the power generation efficiency of solar panels and supports users in managing their maintenance. The system also incorporates an emotion engine that recognizes the user's emotions and optimizes the system's response.

[0845] The server provides the following main functions. First, it periodically acquires solar radiation data, weather data, and power generation history data. Weather data is acquired using the OpenWeatherMap API, and solar radiation data is acquired from sensors via a local connection. Power generation history data is collected from the solar panel inverter. This data is managed centrally within the server.

[0846] The server then inputs the collected data into a generative AI model, which is built using the TensorFlow library. The model predicts the optimal angle and direction of the solar panels based on the input weather data, solar radiation data, and power generation history data. This predicted data is sent to a single-axis tracking system. The tracking system automatically adjusts the angle and direction of the solar panels based on the received data. This adjustment is made using the RS-485 communication protocol.

[0847] The server also collects solar panel status data from sensors to detect signs of deterioration or abnormalities. This process uses machine learning models (e.g., Scikit-learn) and collects sensor data via the LoRa communication protocol. Based on the detected signs of deterioration or abnormalities, the server notifies the user of maintenance recommendations. These notifications are sent to the device and displayed through the user interface.

[0848] The role of the terminal is to provide a user interface. Users can use a dedicated application (developed with React Native) to monitor the status of the solar panels in real time. Furthermore, users can send queries or requests to the server through the application. The application runs on both iOS and Android.

[0849] The emotion engine recognizes the user's real-time emotional state. Specifically, the Emotient API is used to analyze emotions from the user's voice, facial expressions, and text input. The device collects data using the camera and microphone, and the emotion engine performs the analysis. The analysis results are sent to the server, which adjusts the notification message based on the received emotion data. For example, if the user is feeling stressed, the tone of the notification message will be softened. A message such as "Please let us know if you need more specific instructions" will be sent.

[0850] As a specific example, a server collects solar radiation data, weather data, and power generation history data every day at 6:00 a.m. This data is input into a generative AI model, which then predicts optimal settings, such as "angle: 30 degrees, direction: south-southeast." The prediction results are sent to a single-axis tracking system, which automatically adjusts the solar panels. At the same time, sensor data is also collected, and if signs of deterioration or abnormalities are detected, a notification is sent to the user's device stating, "Signs of deterioration have been detected. Maintenance is recommended."

[0851] In addition, emotions are analyzed from the user's facial expressions and voice, and if stress levels are high, the tone of notifications is softened. An example of a specific prompt is, "Please set a method to analyze the user's voice data and facial expression data, recognize their emotional state, and adjust notification messages accordingly."

[0852] This system configuration maximizes the power generation efficiency of the solar panels and enables appropriate maintenance by detecting deterioration or abnormalities early and notifying the user.Furthermore, by using an emotion engine, it is possible to provide responses based on the user's emotional state, improving the user experience.

[0853] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0854] Step 1:

[0855] The server collects solar radiation data, weather data, and power generation history data every day at 6:00 a.m.

[0856] Input: The server sends API requests and collects data from sensors and inverters.

[0857] Operation: Weather data is obtained using the OpenWeatherMap API, solar radiation data is received from the sensor via LoRa communication, and power generation history data is read from the inverter.

[0858] Output: Store the acquired data in a database and format it for further processing.

[0859] Step 2:

[0860] The server inputs the collected data into a generative AI model.

[0861] Input: Solar radiation data, weather data, and historical power generation data collected in step 1.

[0862] How it works: We use the TensorFlow library to run a generative model to predict the optimal solar panel angle and orientation.

[0863] Output: Angle and direction data predicted by the generative AI model.

[0864] Step 3:

[0865] The server sends the prediction results to the single-axis tracking system.

[0866] Input: Prediction data (angle and direction) obtained in step 2.

[0867] Operation: Sends predicted data to a tracking system via RS-485 communication protocol.

[0868] Output: Forecast data received by the tracking system.

[0869] Step 4:

[0870] The tracking system automatically adjusts the angle and direction of the solar panels.

[0871] Input: The forecast data received in step 3.

[0872] Operation: Sends commands to the motor driver, driving the motor to automatically adjust the angle and direction of the solar panel to the set values.

[0873] Output: Regulated solar panel status.

[0874] Step 5:

[0875] The server collects status data from the sensors and predicts the deterioration state of the solar panels.

[0876] Input: Status data such as vibration data and temperature data of the solar panel.

[0877] Operation: Data is received from sensors via LoRa communication, and signs of deterioration or abnormalities are analyzed using Scikit-learn.

[0878] Output: Analyzed data on signs of deterioration and abnormalities.

[0879] Step 6:

[0880] The server sends maintenance notifications to users based on predicted deterioration and abnormality data.

[0881] Input: Data on signs of deterioration and abnormalities analyzed in Step 5.

[0882] Operation: If degradation or abnormality is detected, a notification message is generated and sent to the terminal.

[0883] Output: Maintenance notification displayed on the user's device.

[0884] Step 7:

[0885] The device will display a notification to the user prompting them to take the necessary action.

[0886] Input: Maintenance notification sent in step 6.

[0887] Behavior: Displays a notification message in the user interface of the dedicated application, and also raises an alert so that the user can see it.

[0888] Output: The notification message displayed to the user.

[0889] Step 8:

[0890] The emotion engine analyzes the user's emotions from their facial expressions and voice and sends the results to the server.

[0891] Input: User's facial expression data, voice data.

[0892] How it works: Collects data using the device's camera and microphone and sends it to the Emotient API for sentiment analysis.

[0893] Output: User sentiment data obtained as a result of the analysis.

[0894] Step 9:

[0895] The server adjusts the notification message based on the received emotion data and sends it back to the user.

[0896] Input: User emotion data obtained in step 8.

[0897] Behavior: Adjust the tone and content of notification messages based on your emotional state. For example, soften the tone if you are feeling stressed.

[0898] Output: A notification message appropriate to the user's emotional state.

[0899] Step 10:

[0900] Users can check notifications and messages and take necessary actions.

[0901] Input: The notification message adjusted in step 9.

[0902] Action: The user reviews the notification and adjusts the maintenance schedule through the application as needed.

[0903] Output: User actions such as updating a maintenance schedule or submitting a ticket.

[0904] (Application example 2)

[0905] 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."

[0906] Conventional solar panel systems are often inefficient because optimization and maintenance management to improve power generation efficiency are performed manually. Furthermore, there are insufficient means to detect deterioration or abnormalities that users face early, which can lead to delayed appropriate responses. Furthermore, responses that take into account the user's emotional state are not provided, resulting in a poor user experience regarding notifications and maintenance.

[0907] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring solar radiation data, means for acquiring weather data and power generation history, means for predicting the optimal solar panel angle and direction using a generative model, means for transmitting the predicted angle and direction to the single-axis tracking system, means for predicting the deterioration state of the solar panel, means for detecting abnormalities and signs of failure and notifying maintenance, means for controlling the robot arm using power generation history data and automatically adjusting the solar panel angle, means for collecting sensor data and monitoring the solar panel status, means for automatically adjusting the maintenance schedule based on the collected data, means for notifying the user of the maintenance schedule, means for analyzing the user's emotions using an emotion engine, and means for adjusting notification messages according to the user's emotions. This maximizes the power generation efficiency of the solar panel, enables early detection of deterioration and abnormalities, and realizes efficient maintenance management. Furthermore, providing responses according to the user's emotional state improves the user experience.

[0908] "Solar radiation data" is data that indicates the amount of solar radiation that reaches the earth's surface from the sun.

[0909] "Weather data" refers to data that indicates weather conditions such as temperature, humidity, precipitation, and wind speed.

[0910] "Power generation history data" is recorded data relating to the amount of power generated by the solar panel in the past.

[0911] A "generative model" is a machine learning model that predicts the optimal angle and direction of solar panels based on input data.

[0912] A "single-axis tracking system" is a device that rotates a solar panel along a single axis.

[0913] The "deterioration state of the solar panel" refers to the state that indicates the degree of physical and functional deterioration of the solar panel.

[0914] "Abnormalities and signs of failure" are signs that indicate an abnormal state that deviates from normal operation or a sign that indicates a precursor to failure.

[0915] A "maintenance schedule" is a schedule for performing regular maintenance on solar panels.

[0916] A "robot arm" is a mechanical device that can move with multiple joints like a human arm.

[0917] "Sensor data" refers to data relating to physical quantities obtained from various sensors.

[0918] An "emotion engine" is software or algorithm for analyzing a user's emotional state.

[0919] "User's emotions" are data that indicate the user's psychological state and mood.

[0920] A "notification message" is a message sent by the system to the user to provide information.

[0921] "User experience" refers to the overall experience and satisfaction a user has when using a system or service.

[0922] The present invention is a system that maximizes the power generation efficiency of solar panels and performs efficient maintenance management by predicting deterioration and abnormalities. Furthermore, it incorporates an emotion engine that recognizes the user's emotions and provides optimal responses. The following describes an embodiment of the present invention in detail.

[0923] The server is equipped with a means of acquiring solar radiation data, which is periodically obtained from an external source via an API. Weather data and power generation history data are also collected via the API. This data is input into the generative model, which uses a machine learning algorithm to predict the optimal angle and orientation of the solar panels based on the obtained data. The prediction results are sent to the single-axis tracking system, which automatically adjusts the angle and orientation of the solar panels.

[0924] Furthermore, the server is equipped with a means to predict the deterioration status of the solar panels. This is done by analyzing data from sensors and detecting signs of deterioration or abnormalities. If an abnormality or sign of deterioration is detected, the server sends a notification to the user's device. This notification also includes specific maintenance recommendations, helping the user to take effective action.

[0925] The system also includes a means for utilizing historical power generation data to control a robotic arm, which adjusts the angle of the solar panels to maximize power generation efficiency. The system also provides a function for automatically adjusting maintenance schedules based on sensor data, thereby streamlining maintenance management.

[0926] The server analyzes the user's emotions using an emotion engine. This emotion engine recognizes emotions in real time from the user's voice, facial expressions, and text input, and has a means to adjust the response message based on the analyzed data. If the user is feeling stressed, the tone of the notification message can be softened, for example, to improve the user experience.

[0927] For example, the server uses solar radiation data and weather data to predict that the solar panels should be angled 30 degrees and pointed south-southeast, and sends this prediction to the single-axis tracking system. The solar panels are then automatically adjusted to achieve optimal power generation efficiency. At the same time, if signs of deterioration are detected based on the sensor data, a notification is sent to the user's device stating, "Signs of deterioration have been detected. Maintenance is recommended." The user can check the details and adjust the schedule through a smartphone app. The system also recognizes emotions from the user's facial expressions and voice, and sends softer messages if stress levels are high.

[0928] For example, you can use a prompt such as, "Based on weather data and historical power generation data from the solar panels, predict the optimal angle for the solar panels and control the robot arm. Current weather data is temperature: 25 degrees, solar radiation: 800, and historical power generation data is output: 150."

[0929] In this way, the present invention is a system that enables maximization of power generation efficiency of solar panels, early detection of deterioration and abnormalities, efficient maintenance management, and improved user experience.

[0930] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0931] Step 1:

[0932] The server receives solar radiation data through API. This data is obtained from the solar radiation sensor and sent as input to the server. The server receives this data and passes it to the next processing step.

[0933] Step 2:

[0934] The server uses an API to collect weather data and historical power generation data, including temperature, humidity, wind speed, and past power generation. The server receives this data and stores it in an internal database, which then prepares input data for the generative model along with solar radiation data.

[0935] Step 3:

[0936] The server inputs solar radiation data, weather data, and historical power generation data into the generative model, which uses machine learning algorithms to predict the optimal solar panel angle and direction based on these inputs. The output is the specific angle and direction.

[0937] Step 4:

[0938] The server sends the angle and direction obtained from the generative model to the single-axis tracking system, which instructs the solar panel to be positioned at a 30-degree angle and facing south-southeast. The tracking system then automatically adjusts the solar panel based on the data received.

[0939] Step 5:

[0940] The server collects data from sensors to predict the deterioration state of the solar panels. This data includes the current, voltage, and temperature of the solar panels. The server analyzes this data to detect signs of deterioration or abnormalities. If an abnormality is found, the information is sent to the next step.

[0941] Step 6:

[0942] If the server detects an abnormality or signs of deterioration, it sends a notification to the user's device, for example, a message saying, "Signs of deterioration are present. Maintenance is recommended." The notification includes recommendations for maintenance and suggestions for next steps.

[0943] Step 7:

[0944] The server controls the robot arm based on the power generation history data. It analyzes this data and sends instructions to the robot arm to adjust the angle of the solar panel as needed. The robot arm follows these instructions and actually adjusts the angle.

[0945] Step 8:

[0946] The server automatically adjusts the maintenance schedule based on sensor data, including the status of the solar panels, usage time, environmental conditions, etc. The server analyzes this data, determines the next maintenance date, and notifies the user.

[0947] Step 9:

[0948] The server analyzes the user's emotions using an emotion engine, which analyzes the user's voice, facial expressions, and text input to determine the user's emotional state. For example, if the server determines that the user is tired, it adjusts the notification content to a softer tone.

[0949] Step 10:

[0950] The server adjusts the notification message based on the user's emotions based on the emotional data obtained by the emotion engine. For example, if the user is feeling stressed, the server sends a soft message such as, "Maintenance is required. However, please rest assured that we will continue to support you."

[0951] In this way, the server can execute a series of processing steps to maximize the power generation efficiency of the solar panels, detect deterioration or abnormalities early, manage maintenance efficiently, and improve the user experience.

[0952] 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.

[0953] 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.

[0954] 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.

[0955] [Fourth embodiment]

[0956] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0957] 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.

[0958] 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).

[0959] 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.

[0960] 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.

[0961] 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).

[0962] 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.

[0963] 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.

[0964] 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.

[0965] 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.

[0966] 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.

[0967] 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.

[0968] 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."

[0969] ---

[0970] The present invention aims to efficiently utilize renewable energy, and specifically relates to a system that maximizes the power generation efficiency of solar panels. This system is composed of a server, a terminal, and a user element.

[0971] The server has the following main functions. First, it periodically acquires solar radiation data, weather data, and power generation history data, and inputs this data into a generative model to predict the optimal angle and direction of the solar panels. Next, it sends the prediction results of the generative model to a single-axis tracking system, which automatically adjusts the angle and direction of the solar panels. Furthermore, it predicts the deterioration state of the solar panels based on data acquired from sensors, detects signs of abnormalities or failures, and notifies the user. This makes it possible to automatically adjust an appropriate maintenance schedule and notify the user.

[0972] The terminal mainly provides the user interface. Users can monitor the status of the solar panels in real time through a dedicated application. For example, they can check information such as the current amount of power generated, the angle and direction of the solar panels, and the state of deterioration. Users can also send inquiries or requests to the server via the terminal and receive the results.

[0973] To use the system effectively, users periodically check the information provided, perform maintenance as needed, and respond to notifications from the server. For example, if a notification arrives from the server stating that "maintenance is required," the user responds promptly and performs appropriate maintenance to maintain stable system operation.

[0974] As a specific example, the server collects solar radiation data, weather data, and power generation history data every morning at 6:00 a.m., and based on this, the generative model predicts optimal settings such as "angle: 30 degrees, direction: south-southeast." This prediction result is sent to the single-axis tracking system, and the solar panels are automatically adjusted. At the same time, sensor data is also collected, and if signs of deterioration or abnormalities are detected, a notification is sent to the user's device stating, "Signs of deterioration have been detected. Maintenance is recommended." The user receives this notification, checks detailed information through the application, and adjusts the maintenance schedule.

[0975] Key features of this system include data-based prediction and automatic adjustment, early detection of deterioration and abnormalities, and efficient maintenance management through user interaction, which maximizes the power generation efficiency of the solar panels and ensures stable operation of the system.

[0976] The processing flow will be explained below.

[0977] ---

[0978] Step 1:

[0979] The server collects solar radiation data, weather data, and power generation history data at a fixed time every day. The server accesses each data source via API, collects the data, and stores it in a local database.

[0980] Step 2:

[0981] The server inputs the accumulated data into the generative model, which then combines solar radiation data, weather data, and power generation history and passes it to the generative model to predict the optimal angle and direction of the solar panels.

[0982] Step 3:

[0983] The server sends the prediction results of the generative model to the single-axis tracking system, which automatically adjusts the solar panel by sending prediction results such as "angle: 30 degrees, direction: south-southeast" to the tracking system.

[0984] Step 4:

[0985] The tracking system adjusts the angle and orientation of the solar panels based on the received predictions. The tracking system controls the motors to change the physical position of the solar panels.

[0986] Step 5:

[0987] The server collects solar panel data from sensors, including voltage, current, and temperature, in real time, and monitors for signs of abnormalities or deterioration.

[0988] Step 6:

[0989] The server predicts the deterioration state based on the collected sensor data, and inputs the sensor data into a deterioration prediction model to detect signs of deterioration and abnormalities.

[0990] Step 7:

[0991] If the server detects an abnormality or a sign of a failure, it will notify the user. When an abnormality is detected, the server will send a notification message to the user's device and provide detailed information.

[0992] Step 8:

[0993] The user receives a notification and opens a dedicated application to check detailed information. The user sees a notification such as "Signs of deterioration have been detected. Maintenance is recommended." and considers the necessary action.

[0994] Step 9:

[0995] The server automatically adjusts the maintenance schedule based on abnormalities or deterioration, and sets the next maintenance date based on the results of the predictive model and notifies the user.

[0996] Step 10:

[0997] The user checks the new maintenance schedule and accepts or adjusts it. The user checks the schedule through the terminal and performs maintenance work as necessary.

[0998] Step 11:

[0999] Users can monitor the status of their solar panels in real time through a dedicated application. Users open the app and check the current power generation, angle, direction, and deterioration status.

[1000] Step 12:

[1001] Users can send questions or requests to the server via their device, or submit questions using the inquiry form within the app.

[1002] Step 13:

[1003] The server receives queries from users and provides answers based on the analysis results. The server analyzes the query and returns an appropriate answer to the user.

[1004] Example 1

[1005] 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."

[1006] In conventional solar panel systems, optimal angle adjustment and direction prediction to achieve efficient power generation are often performed manually, which tends to reduce power generation efficiency. It is also difficult to detect deterioration or abnormalities early, which can delay appropriate maintenance. Furthermore, users are sometimes unable to monitor the status of the panels in real time, which creates the challenge of being unable to respond immediately when problems occur.

[1007] 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.

[1008] In this invention, the server includes means for acquiring solar radiation data, means for acquiring weather data and power generation history, means for predicting the optimal solar panel angle and direction using a generative model, means for transmitting the predicted angle and direction to a tracking system, means for predicting the deterioration state of the solar panel, means for detecting abnormalities and signs of failure and notifying maintenance, means for collecting sensor data and physically adjusting the solar panel, means for inputting a data set into a generative AI model to predict the optimal angle and direction, and means for transmitting a notification to the user when an abnormality is detected. This maximizes the power generation efficiency of the solar panel and enables stable operation of the system.

[1009] "Solar radiation data" is data that indicates the amount of solar energy that reaches the Earth's surface from the sun.

[1010] "Weather data" refers to data that indicates weather conditions such as weather conditions (e.g., sunny, cloudy, rainy, etc.), temperature, humidity, and wind speed.

[1011] "Power generation history" is data that records the amount of power generated by the solar cell panel in the past and its fluctuations.

[1012] A "generative model" is an artificial intelligence algorithm that makes predictions and inferences based on input data.

[1013] A "tracking system" is a device that adjusts the angle and direction of solar panels for the purpose of efficient power generation.

[1014] The "deterioration state" refers to the degree of performance degradation or damage that occurs during the course of use of the solar panel.

[1015] "Abnormalities and signs of failure" are signs that the solar panels or related equipment are outside the normal operating range or are signs that indicate the possibility of a failure.

[1016] "Maintenance" means preventative or corrective work performed to maintain the proper functioning of solar panels and related systems.

[1017] "Sensor data" refers to information obtained from sensors, including physical conditions such as temperature, vibration, current, and voltage of solar panels.

[1018] A "generative AI model" is an artificial intelligence model that automatically generates optimal solutions based on large amounts of data.

[1019] A "dataset" is a collection of data compiled for a specific purpose.

[1020] A "user" is a person or organization that uses the system to manage and monitor solar panels.

[1021] The present invention aims to efficiently utilize renewable energy, and specifically relates to a system that maximizes the power generation efficiency of solar panels. This system is composed of a server, a terminal, and a user element.

[1022] First, the server periodically obtains solar radiation data and weather data using a weather API. Next, it obtains historical power generation data from a database. These data are then converted into a single dataset and input into a generative AI model. For example, the generative AI model uses GPT-4, a type of generative AI. This model makes predictions based on prompt statements such as the following:

[1023] "Predict tomorrow's optimal solar panel angle and direction based on yesterday's weather data, solar radiation data, and historical power generation data from the past week."

[1024] The acquired predicted data is sent to the tracking system, which uses an Arduino-based single-axis tracking system and physically adjusts the solar panel based on the predicted angle and direction. The server also collects sensor data from a TI sensor module and checks the solar panel for deterioration or abnormalities. If an abnormality is detected, a notification is sent to the user's device.

[1025] The terminal provides a user interface. Through a dedicated application, users can monitor the status of the solar panels in real time, checking information such as the current power generation amount, panel angle, direction, and deterioration status. Users can also send inquiries or requests to the server via the terminal and receive the results.

[1026] To use the system effectively, users periodically check the information provided, perform maintenance as needed, and respond to notifications from the server. For example, if a notification arrives from the server stating that "maintenance is required," the user responds promptly and performs the appropriate maintenance to maintain stable operation of the system.

[1027] As a specific example, every day at 6:00 AM, the server retrieves solar radiation data and weather data from a weather API and retrieves the past week's power generation history data from a database. This data is formatted and input into a generative AI model. The generative AI model makes predictions such as "angle: 30 degrees, direction: south-southeast," and this information is sent to a tracking system. The tracking system uses this information to physically adjust the solar panel. At the same time, the server collects data from a TI sensor module and checks for deterioration or abnormalities. If an abnormality is detected, a notification is sent to the user's device stating, "Signs of deterioration are present. Maintenance is recommended." The user can then check this notification and schedule appropriate maintenance.

[1028] This system maximizes the power generation efficiency of the solar panels and ensures stable operation of the system.

[1029] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1030] Step 1:

[1031] The server uses a weather API to obtain solar radiation data. In this case, the server sends an API request and receives the obtained data in JSON format. The input is the request information to the API, and the output is the obtained solar radiation data. This data is formatted appropriately for use in subsequent processing.

[1032] Step 2:

[1033] The server retrieves weather data from the same weather API. The server sends an API request and receives data such as weather conditions, temperature, and humidity in JSON format. The input is the request information to the API, and the output is the retrieved weather data. This weather data is also formatted and converted into a format that can be used for subsequent processing.

[1034] Step 3:

[1035] The server retrieves historical power generation data from the database. It executes a database query to retrieve power generation data for the past week. The input is a query to the database, and the output is the retrieved power generation data. This data is formatted as time-series data on power generation.

[1036] Step 4:

[1037] The server converts the acquired solar radiation data, weather data, and power generation history data into a single dataset. This converts the data into a format that is easy for the generative AI model to use. The input is each piece of data acquired in steps 1 to 3, and the output is the converted dataset.

[1038] Step 5:

[1039] The server inputs the formatted dataset into the generative AI model as a prompt. An example prompt is, "Please predict tomorrow's optimal angle and direction of the solar panels based on yesterday's weather data, solar radiation data, and power generation history data from the past week." The input is the formatted dataset and prompt, and the output is the prediction result from the generative AI model.

[1040] Step 6:

[1041] The server receives the optimal solar panel angle and direction data returned by the generative AI model. The input is the predicted result from the generative AI model, and the output is the optimal angle and direction data. This data is used to instruct the tracking system.

[1042] Step 7:

[1043] The server sends the prediction results to the tracking system, which then physically adjusts the angle and orientation of the solar panels based on the received data. The input is the predicted angle and orientation data, and the output is the adjusted physical state of the panels.

[1044] Step 8:

[1045] The server collects sensor data from TI sensor modules. The data from the sensors includes information such as temperature, vibration, current, and voltage. The input is real-time data from the sensors, and the output is the collected sensor data.

[1046] Step 9:

[1047] The server inputs the collected sensor data into an AI model to predict the state of deterioration or abnormalities. The input is sensor data, and the output is the predicted results of the state of deterioration or abnormalities. The results are notified to the user when an abnormality is detected.

[1048] Step 10:

[1049] If an abnormality is detected, the server sends a notification to the user's device. The notification content states, "Signs of deterioration are present. Maintenance is recommended." The input is the predicted abnormality result, and the output is the notification to the user.

[1050] Step 11:

[1051] Users use a dedicated application on their device to monitor the status of their solar panels in real time. The application displays the current amount of power generated, the angle and direction of the panels, and their state of deterioration. The input is various data sent from the server, and the output is real-time information that the user can check.

[1052] Step 12:

[1053] Users receive notifications from the server and schedule appropriate maintenance. The input is a maintenance notification from the server, and the output is the execution of the maintenance schedule. This ensures stable operation of the system.

[1054] (Application example 1)

[1055] 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."

[1056] Efficient energy use is a key issue in modern factories. In particular, to promote the use of renewable energy, it is necessary to maximize the power generation efficiency of solar panels and continuously monitor and adjust their status. However, current systems make it difficult to perform real-time optimization and automatic maintenance prediction based on data. This leads to issues such as reduced energy efficiency and increased factory operating costs.

[1057] 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.

[1058] In this invention, the server includes means for acquiring solar radiation data, means for acquiring weather data and power generation history, and means for predicting the optimal solar panel angle and direction using a generative model. This enables automatic optimization to maximize energy efficiency. The server also includes means for transmitting the predicted angle and direction to a single-axis tracking system, means for predicting the deterioration state of the solar panels, means for detecting abnormalities and signs of failure and notifying maintenance, means for collecting sensor data within the factory, means for analyzing the data in real time to maximize energy efficiency and automatically optimizing equipment settings, and means for predicting a maintenance schedule based on signs of deterioration and abnormalities and notifying the user. This enables efficient energy use.

[1059] "Solar radiation data" is information that measures the radiant energy from the sun to the earth.

[1060] "Weather Data" is information about the weather and meteorological conditions in a particular area.

[1061] "Power generation history" is a record of the electrical energy generated in the past by solar panels or other power generation devices.

[1062] A "generative model" is an algorithm or component of artificial intelligence that predicts optimal outcomes based on acquired data.

[1063] The "optimal solar panel angle and orientation" refers to the best angle and orientation for solar panels to generate electricity as efficiently as possible.

[1064] A "single-axis tracking system" is an automatic control system for adjusting the angle and direction of solar panels.

[1065] "Solar panel deterioration" refers to the degree to which a solar panel is no longer able to perform at its full potential due to use or environmental factors.

[1066] "Abnormalities and signs of failure" are phenomena or signs that a system or device is beyond the range of normal operation or that there is an increased possibility of it failing in the future.

[1067] A "maintenance schedule" is a plan for efficiently maintaining and inspecting facilities and equipment.

[1068] "Sensor data" is information collected from various sensor devices.

[1069] "Energy efficiency" refers to the actual amount of power generated and the efficiency of energy utilization relative to the amount of energy used.

[1070] "Analyzing data in real time" means evaluating and analyzing data as soon as it is generated.

[1071] A "purpose-built application" is a software program designed for a specific purpose.

[1072] A "user" is an entity that operates and manages a system or device.

[1073] The present invention aims to efficiently utilize renewable energy, and specifically relates to a system that maximizes the power generation efficiency of solar panels. This system is composed of a server, a terminal, and a user element.

[1074] The server periodically acquires solar radiation data, weather data, and power generation history data, and inputs this data into a generative model to predict the optimal angle and direction of the solar panels. The server also sends the prediction results of this generative model to the single-axis tracking system, which automatically adjusts the angle and direction of the solar panels. Furthermore, the server predicts the deterioration state of the solar panels based on data acquired from sensors, detects signs of abnormalities or failures, and notifies the user. This makes it possible to automatically adjust appropriate maintenance schedules and notify the user.

[1075] The terminal mainly provides the user interface. Users can monitor the status of the solar panels in real time through a dedicated application. For example, they can check information such as the current amount of power generated, the angle and direction of the solar panels, and the state of deterioration. Users can also send inquiries or requests to the server via the terminal and receive the results.

[1076] To use the system effectively, users are required to regularly check the information provided, perform maintenance as necessary, and respond to notifications from the server. For example, if a notification arrives from the server stating that "maintenance is required," the user must respond promptly and perform the appropriate maintenance to maintain stable system operation.

[1077] The system has the following specific components:

[1078] 1. Data collection function:

[1079] The server automatically collects solar radiation data, weather data, power generation history data, and various sensor data within the factory, which is important information required for subsequent processing.

[1080] 2. Leveraging generative models:

[1081] Based on the collected data, a generative model predicts the optimal angle and direction of the solar panels. This model is implemented using Python and Flask.

[1082] 3. Real-time analysis:

[1083] The collected data is analyzed in real time and any necessary adjustments are automatically made to maximize energy efficiency.

[1084] 4. Maintenance forecasting and notifications:

[1085] The server predicts deterioration and abnormalities, generates a maintenance schedule as needed, and notifies the user through a dedicated application.

[1086] As a specific example, the server collects solar radiation data, weather data, and power generation history data every morning at 6:00 a.m., and based on this, the generative model predicts optimal settings such as "angle: 30 degrees, direction: south-southeast." This prediction result is sent to the single-axis tracking system, and the solar panels are automatically adjusted. At the same time, sensor data is also collected, and if signs of deterioration or abnormalities are detected, a notification is sent to the user's device stating, "Signs of deterioration have been detected. Maintenance is recommended." The user receives this notification, checks detailed information through the application, and adjusts the maintenance schedule.

[1087] Example prompt sentence:

[1088] Please use "solar radiation data, weather data, and power generation history data to optimize factory energy management" to predict "the optimal angle and direction of solar panels." For example, if the solar radiation is 1000W / m^2, the weather is sunny, and the power generation history data shows an efficiency of 90%, please output the optimal setting value.

[1089] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1090] Step 1:

[1091] The server collects solar radiation data, weather data, power generation history data, and sensor data. These data are periodically obtained from sensor devices installed on the server. Solar radiation, temperature, wind speed, and past power generation data are taken as input and stored in a database. The output is a set of the latest state of each data.

[1092] Step 2:

[1093] Based on the data collected by the server, the data is input into a generative AI model to predict the optimal solar panel angle and direction. This process uses a Python-based machine learning model. The dataset collected in step 1 is input into the model, and the process of predicting the optimal angle and direction begins. The output is a set of generated optimal angles and directions.

[1094] Step 3:

[1095] The server sends the generated set of optimal angles and orientations to the single-axis tracking system, which automatically adjusts the angle and orientation of the solar panel. As input, it uses the optimal angle and orientation predicted in step 2. The output is the adjusted state of the solar panel based on the new set values.

[1096] Step 4:

[1097] The server analyzes the sensor data to detect the deterioration status and signs of abnormalities in the solar panels and related equipment. This analysis uses AI and a specific pattern matching method to find signs of deterioration and abnormalities. The input is the latest sensor data set obtained in step 1, and the output is information on signs of deterioration and abnormalities.

[1098] Step 5:

[1099] The server automatically generates a maintenance schedule based on the information on deterioration and signs of abnormalities and notifies the user. The user can receive these notifications through a dedicated application. The input is the deterioration information and signs of abnormalities detected in step 4, and the output is a notification message to the user and a recommended maintenance schedule.

[1100] Step 6:

[1101] Using a dedicated application, users can check the status of solar panels and the latest maintenance information in real time. Through the application, users can make inquiries to the server with questions or requests and receive the results. The input is the solar panel status information and maintenance schedule provided by the server, and the output is the information that the user can check on the application screen.

[1102] 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.

[1103] ---

[1104] The present invention is a system that maximizes the power generation efficiency of solar panels and supports users in managing their maintenance. It also incorporates an emotion engine that recognizes the user's emotions and optimizes the system's response.

[1105] The server provides the following main functions: First, it periodically collects solar radiation data, weather data, and power generation history data, and inputs this data into a generative model. The generative model then predicts the optimal angle and direction of the solar panels and sends the results to the single-axis tracking system. The tracking system then automatically adjusts the angle and direction of the solar panels based on the received data.

[1106] The server also collects data from the solar panels via sensors and predicts their deterioration. If signs of deterioration or abnormalities are detected, the server notifies the user. The notification includes maintenance recommendations, allowing the user to take effective action.

[1107] The terminal provides the user interface. Users can monitor the status of the solar panels in real time and receive notification messages through a dedicated application. Users can also contact the server via the terminal with any questions or requests.

[1108] The system also incorporates an emotion engine that recognizes the user's real-time emotional state. The emotion engine analyzes emotions from the user's voice, facial expressions, and text input and transmits them to the server. The server adjusts notification messages based on the received emotion data to provide responses appropriate to the user's emotional state.

[1109] As a specific example, the server collects solar radiation data, weather data, and power generation history data every morning at 6:00 a.m., and based on this, the generative model predicts optimal settings such as "angle: 30 degrees, direction: south-southeast." This prediction result is sent to the single-axis tracking system, and the solar panels are automatically adjusted. At the same time, sensor data is also collected, and if signs of deterioration or abnormalities are detected, a notification is sent to the user's device stating, "Signs of deterioration are present. Maintenance is recommended." The user receives this notification, checks detailed information through the application, and adjusts the maintenance schedule. In addition, emotions are analyzed from the user's facial expressions and voice, and if stress levels are high, appropriate measures are taken, such as softening the tone of the notification.

[1110] This system configuration maximizes the power generation efficiency of solar panels and enables efficient maintenance management by detecting deterioration and abnormalities early. It also improves the user experience by providing responses that take into account the user's emotional state.

[1111] The processing flow will be explained below.

[1112] ---

[1113] Step 1:

[1114] The server acquires solar radiation data, weather data, and power generation history data at a fixed time every day. The server uses an API to download data from the solar radiation database, acquires the latest weather data from the weather information service, and collects past power generation history from an internal database.

[1115] Step 2:

[1116] The server inputs collected solar radiation data, weather data, and historical power generation data into a generative model, which then predicts the optimal solar panel angle and direction. The generative model combines past and current data and uses machine learning to calculate the optimal value.

[1117] Step 3:

[1118] The server sends the prediction results from the generative model to the single-axis tracking system. For example, actual settings such as "angle: 30 degrees, direction: south-southeast" are sent to the tracking system. The tracking system then automatically adjusts the angle and direction of the panel based on this data.

[1119] Step 4:

[1120] The tracking system physically changes the angle and orientation of the solar panels. The system controls motors and actuators to adjust the position of the panels.

[1121] Step 5:

[1122] The server collects solar panel data from sensors in real time, constantly monitoring voltage, current, temperature, vibration, and other data to detect signs of deterioration or abnormalities.

[1123] Step 6:

[1124] The server inputs the collected sensor data into a degradation prediction model to predict the deterioration state of the panels. If any abnormalities or signs of failure are detected, the information is processed in real time.

[1125] Step 7:

[1126] When the server detects an abnormality or a sign of a malfunction, it sends a notification to the user's device. The notification includes a message such as "Signs of deterioration have been detected. Maintenance is recommended."

[1127] Step 8:

[1128] Users receive a notification, open a dedicated application to view more information, and then act based on the recommended maintenance plan.

[1129] Step 9:

[1130] The server utilizes an emotion engine that recognizes the user's emotions and obtains emotion data from the user's voice and facial expressions, for example, by collecting data through a camera or microphone while the user is using the application.

[1131] Step 10:

[1132] The emotion engine analyzes the collected emotion data and evaluates the user's stress level and satisfaction. If the user is feeling anxious or stressed, the emotion engine sends that information to the server.

[1133] Step 11:

[1134] The server adjusts the content and tone of notification messages based on data from the emotion engine. For example, if a user is feeling stressed, the server will send a message with softer language and encouraging words.

[1135] Step 12:

[1136] Users can send questions or requests to the server through the application's inquiry form via their terminal. Users can send questions using real-time chat or the inquiry form.

[1137] Step 13:

[1138] The server receives the user's inquiry, analyzes it, and provides an appropriate answer. Depending on the inquiry, the server provides a specific solution or additional information and replies to the user.

[1139] In this way, the system combines data collection, prediction, physical adjustment, real-time monitoring, and user emotional responses to maximize the power generation efficiency of solar panels and improve the user experience.

[1140] Example 2

[1141] 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."

[1142] Current solar panel management systems not only lack automatic adjustments to maximize power generation efficiency, but are often slow to predict deterioration and provide maintenance notifications. They also lack the ability to provide appropriate responses that take user emotions into account, making it difficult to optimize the user experience. This can lead to reduced power generation efficiency and delayed maintenance, resulting in reduced overall system efficiency.

[1143] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for acquiring solar radiation data, means for acquiring weather data and power generation history, means for predicting the optimal solar panel angle and direction using a generative model, means for transmitting the predicted angle and direction to the single-axis tracking system, means for predicting the deterioration state of the solar panel, means for detecting abnormalities or signs of failure and notifying maintenance, emotion recognition means, and means for adjusting the notification message based on the user's emotional state. This enables efficient power generation by the solar panel and appropriate maintenance through early detection of deterioration or abnormalities, thereby improving the user experience.

[1144] "Solar radiation data" is information collected by sensors or measuring devices to measure the intensity of sunlight.

[1145] "Weather data" is information about weather conditions, and is data based on weather conditions such as temperature, humidity, wind speed, and precipitation.

[1146] "Power generation history" is recorded data regarding the amount of power generated in the past by the solar panel.

[1147] A "generative model" is a machine learning model used to predict the optimal solar panel angle and orientation based on captured data.

[1148] A "single-axis tracking system" is a device or system that automatically adjusts the angle and orientation of a solar panel along a single axis.

[1149] The "means for predicting the deterioration state" refers to a device or method for detecting the deterioration and performance degradation of a solar panel and predicting its state.

[1150] "Detection of abnormalities and signs of failure" is the process of detecting signs of abnormalities or failures that may occur in solar panels and notifying the user.

[1151] A "means for notifying maintenance" is a method or device for notifying a user that maintenance of a solar panel is required.

[1152] An "emotion recognition means" is a device or method for analyzing and recognizing emotions from a user's voice, facial expressions, and text input.

[1153] A "means for tailoring notification messages" is a device or method that changes the content or tone of the system's notification messages based on the user's emotional state.

[1154] The present invention is a system that maximizes the power generation efficiency of solar panels and supports users in managing their maintenance. The system also incorporates an emotion engine that recognizes the user's emotions and optimizes the system's response.

[1155] The server provides the following main functions. First, it periodically acquires solar radiation data, weather data, and power generation history data. Weather data is acquired using the OpenWeatherMap API, and solar radiation data is acquired from sensors via a local connection. Power generation history data is collected from the solar panel inverter. This data is managed centrally within the server.

[1156] The server then inputs the collected data into a generative AI model, which is built using the TensorFlow library. The model predicts the optimal angle and direction of the solar panels based on the input weather data, solar radiation data, and power generation history data. This predicted data is sent to a single-axis tracking system. The tracking system automatically adjusts the angle and direction of the solar panels based on the received data. This adjustment is made using the RS-485 communication protocol.

[1157] The server also collects solar panel status data from sensors to detect signs of deterioration or abnormalities. This process uses machine learning models (e.g., Scikit-learn) and collects sensor data via the LoRa communication protocol. Based on the detected signs of deterioration or abnormalities, the server notifies the user of maintenance recommendations. These notifications are sent to the device and displayed through the user interface.

[1158] The role of the terminal is to provide a user interface. Users can use a dedicated application (developed with React Native) to monitor the status of the solar panels in real time. Furthermore, users can send queries or requests to the server through the application. The application runs on both iOS and Android.

[1159] The emotion engine recognizes the user's real-time emotional state. Specifically, the Emotient API is used to analyze emotions from the user's voice, facial expressions, and text input. The device collects data using the camera and microphone, and the emotion engine performs the analysis. The analysis results are sent to the server, which adjusts the notification message based on the received emotion data. For example, if the user is feeling stressed, the tone of the notification message will be softened. A message such as "Please let us know if you need more specific instructions" will be sent.

[1160] As a specific example, a server collects solar radiation data, weather data, and power generation history data every day at 6:00 a.m. This data is input into a generative AI model, which then predicts optimal settings, such as "angle: 30 degrees, direction: south-southeast." The prediction results are sent to a single-axis tracking system, which automatically adjusts the solar panels. At the same time, sensor data is also collected, and if signs of deterioration or abnormalities are detected, a notification is sent to the user's device stating, "Signs of deterioration have been detected. Maintenance is recommended."

[1161] In addition, emotions are analyzed from the user's facial expressions and voice, and if stress levels are high, the tone of notifications is softened. An example of a specific prompt is, "Please set a method to analyze the user's voice data and facial expression data, recognize their emotional state, and adjust notification messages accordingly."

[1162] This system configuration maximizes the power generation efficiency of the solar panels and enables appropriate maintenance by detecting deterioration or abnormalities early and notifying the user.Furthermore, by using an emotion engine, it is possible to provide responses based on the user's emotional state, improving the user experience.

[1163] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1164] Step 1:

[1165] The server collects solar radiation data, weather data, and power generation history data every day at 6:00 a.m.

[1166] Input: The server sends API requests and collects data from sensors and inverters.

[1167] Operation: Weather data is obtained using the OpenWeatherMap API, solar radiation data is received from the sensor via LoRa communication, and power generation history data is read from the inverter.

[1168] Output: Store the acquired data in a database and format it for further processing.

[1169] Step 2:

[1170] The server inputs the collected data into a generative AI model.

[1171] Input: Solar radiation data, weather data, and historical power generation data collected in step 1.

[1172] How it works: We use the TensorFlow library to run a generative model to predict the optimal solar panel angle and orientation.

[1173] Output: Angle and direction data predicted by the generative AI model.

[1174] Step 3:

[1175] The server sends the prediction results to the single-axis tracking system.

[1176] Input: Prediction data (angle and direction) obtained in step 2.

[1177] Operation: Sends predicted data to a tracking system via RS-485 communication protocol.

[1178] Output: Forecast data received by the tracking system.

[1179] Step 4:

[1180] The tracking system automatically adjusts the angle and direction of the solar panels.

[1181] Input: The forecast data received in step 3.

[1182] Operation: Sends commands to the motor driver, driving the motor to automatically adjust the angle and direction of the solar panel to the set values.

[1183] Output: Regulated solar panel status.

[1184] Step 5:

[1185] The server collects status data from the sensors and predicts the deterioration state of the solar panels.

[1186] Input: Status data such as vibration data and temperature data of the solar panel.

[1187] Operation: Data is received from sensors via LoRa communication, and signs of deterioration or abnormalities are analyzed using Scikit-learn.

[1188] Output: Analyzed data on signs of deterioration and abnormalities.

[1189] Step 6:

[1190] The server sends maintenance notifications to users based on predicted deterioration and abnormality data.

[1191] Input: Data on signs of deterioration and abnormalities analyzed in Step 5.

[1192] Operation: If degradation or abnormality is detected, a notification message is generated and sent to the terminal.

[1193] Output: Maintenance notification displayed on the user's device.

[1194] Step 7:

[1195] The device will display a notification to the user prompting them to take the necessary action.

[1196] Input: Maintenance notification sent in step 6.

[1197] Behavior: Displays a notification message in the user interface of the dedicated application, and also raises an alert so that the user can see it.

[1198] Output: The notification message displayed to the user.

[1199] Step 8:

[1200] The emotion engine analyzes the user's emotions from their facial expressions and voice and sends the results to the server.

[1201] Input: User's facial expression data, voice data.

[1202] How it works: Collects data using the device's camera and microphone and sends it to the Emotient API for sentiment analysis.

[1203] Output: User sentiment data obtained as a result of the analysis.

[1204] Step 9:

[1205] The server adjusts the notification message based on the received emotion data and sends it back to the user.

[1206] Input: User emotion data obtained in step 8.

[1207] Behavior: Adjust the tone and content of notification messages based on your emotional state. For example, soften the tone if you are feeling stressed.

[1208] Output: A notification message appropriate to the user's emotional state.

[1209] Step 10:

[1210] Users can check notifications and messages and take necessary actions.

[1211] Input: The notification message adjusted in step 9.

[1212] Action: The user reviews the notification and adjusts the maintenance schedule through the application as needed.

[1213] Output: User actions such as updating a maintenance schedule or submitting a ticket.

[1214] (Application example 2)

[1215] 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."

[1216] Conventional solar panel systems are often inefficient because optimization and maintenance management to improve power generation efficiency are performed manually. Furthermore, there are insufficient means to detect deterioration or abnormalities that users face early, which can lead to delayed appropriate responses. Furthermore, responses that take into account the user's emotional state are not provided, resulting in a poor user experience regarding notifications and maintenance.

[1217] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring solar radiation data, means for acquiring weather data and power generation history, means for predicting the optimal solar panel angle and direction using a generative model, means for transmitting the predicted angle and direction to the single-axis tracking system, means for predicting the deterioration state of the solar panel, means for detecting abnormalities and signs of failure and notifying maintenance, means for controlling the robot arm using power generation history data and automatically adjusting the solar panel angle, means for collecting sensor data and monitoring the solar panel status, means for automatically adjusting the maintenance schedule based on the collected data, means for notifying the user of the maintenance schedule, means for analyzing the user's emotions using an emotion engine, and means for adjusting notification messages according to the user's emotions. This maximizes the power generation efficiency of the solar panel, enables early detection of deterioration and abnormalities, and realizes efficient maintenance management. Furthermore, providing responses according to the user's emotional state improves the user experience.

[1218] "Solar radiation data" is data that indicates the amount of solar radiation that reaches the earth's surface from the sun.

[1219] "Weather data" refers to data that indicates weather conditions such as temperature, humidity, precipitation, and wind speed.

[1220] "Power generation history data" is recorded data relating to the amount of power generated by the solar panel in the past.

[1221] A "generative model" is a machine learning model that predicts the optimal angle and direction of solar panels based on input data.

[1222] A "single-axis tracking system" is a device that rotates a solar panel along a single axis.

[1223] The "deterioration state of the solar panel" refers to the state that indicates the degree of physical and functional deterioration of the solar panel.

[1224] "Abnormalities and signs of failure" are signs that indicate an abnormal state that deviates from normal operation or a sign that indicates a precursor to failure.

[1225] A "maintenance schedule" is a schedule for performing regular maintenance on solar panels.

[1226] A "robot arm" is a mechanical device that can move with multiple joints like a human arm.

[1227] "Sensor data" refers to data relating to physical quantities obtained from various sensors.

[1228] An "emotion engine" is software or algorithm for analyzing a user's emotional state.

[1229] "User's emotions" are data that indicate the user's psychological state and mood.

[1230] A "notification message" is a message sent by the system to the user to provide information.

[1231] "User experience" refers to the overall experience and satisfaction a user has when using a system or service.

[1232] The present invention is a system that maximizes the power generation efficiency of solar panels and performs efficient maintenance management by predicting deterioration and abnormalities. Furthermore, it incorporates an emotion engine that recognizes the user's emotions and provides optimal responses. The following describes an embodiment of the present invention in detail.

[1233] The server is equipped with a means of acquiring solar radiation data, which is periodically obtained from an external source via an API. Weather data and power generation history data are also collected via the API. This data is input into the generative model, which uses a machine learning algorithm to predict the optimal angle and orientation of the solar panels based on the obtained data. The prediction results are sent to the single-axis tracking system, which automatically adjusts the angle and orientation of the solar panels.

[1234] Furthermore, the server is equipped with a means to predict the deterioration status of the solar panels. This is done by analyzing data from sensors and detecting signs of deterioration or abnormalities. If an abnormality or sign of deterioration is detected, the server sends a notification to the user's device. This notification also includes specific maintenance recommendations, helping the user to take effective action.

[1235] The system also includes a means for utilizing historical power generation data to control a robotic arm, which adjusts the angle of the solar panels to maximize power generation efficiency. The system also provides a function for automatically adjusting maintenance schedules based on sensor data, thereby streamlining maintenance management.

[1236] The server analyzes the user's emotions using an emotion engine. This emotion engine recognizes emotions in real time from the user's voice, facial expressions, and text input, and has a means to adjust the response message based on the analyzed data. If the user is feeling stressed, the tone of the notification message can be softened, for example, to improve the user experience.

[1237] For example, the server uses solar radiation data and weather data to predict that the solar panels should be angled 30 degrees and pointed south-southeast, and sends this prediction to the single-axis tracking system. The solar panels are then automatically adjusted to achieve optimal power generation efficiency. At the same time, if signs of deterioration are detected based on the sensor data, a notification is sent to the user's device stating, "Signs of deterioration have been detected. Maintenance is recommended." The user can check the details and adjust the schedule through a smartphone app. The system also recognizes emotions from the user's facial expressions and voice, and sends softer messages if stress levels are high.

[1238] For example, you can use a prompt such as, "Based on weather data and historical power generation data from the solar panels, predict the optimal angle for the solar panels and control the robot arm. Current weather data is temperature: 25 degrees, solar radiation: 800, and historical power generation data is output: 150."

[1239] In this way, the present invention is a system that enables maximization of power generation efficiency of solar panels, early detection of deterioration and abnormalities, efficient maintenance management, and improved user experience.

[1240] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1241] Step 1:

[1242] The server receives solar radiation data through API. This data is obtained from the solar radiation sensor and sent as input to the server. The server receives this data and passes it to the next processing step.

[1243] Step 2:

[1244] The server uses an API to collect weather data and historical power generation data, including temperature, humidity, wind speed, and past power generation. The server receives this data and stores it in an internal database, which then prepares input data for the generative model along with solar radiation data.

[1245] Step 3:

[1246] The server inputs solar radiation data, weather data, and historical power generation data into the generative model, which uses machine learning algorithms to predict the optimal solar panel angle and direction based on these inputs. The output is the specific angle and direction.

[1247] Step 4:

[1248] The server sends the angle and direction obtained from the generative model to the single-axis tracking system, which instructs the solar panel to be positioned at a 30-degree angle and facing south-southeast. The tracking system then automatically adjusts the solar panel based on the data received.

[1249] Step 5:

[1250] The server collects data from sensors to predict the deterioration state of the solar panels. This data includes the current, voltage, and temperature of the solar panels. The server analyzes this data to detect signs of deterioration or abnormalities. If an abnormality is found, the information is sent to the next step.

[1251] Step 6:

[1252] If the server detects an abnormality or signs of deterioration, it sends a notification to the user's device, for example, a message saying, "Signs of deterioration are present. Maintenance is recommended." The notification includes recommendations for maintenance and suggestions for next steps.

[1253] Step 7:

[1254] The server controls the robot arm based on the power generation history data. It analyzes this data and sends instructions to the robot arm to adjust the angle of the solar panel as needed. The robot arm follows these instructions and actually adjusts the angle.

[1255] Step 8:

[1256] The server automatically adjusts the maintenance schedule based on sensor data, including the status of the solar panels, usage time, environmental conditions, etc. The server analyzes this data, determines the next maintenance date, and notifies the user.

[1257] Step 9:

[1258] The server analyzes the user's emotions using an emotion engine, which analyzes the user's voice, facial expressions, and text input to determine the user's emotional state. For example, if the server determines that the user is tired, it adjusts the notification content to a softer tone.

[1259] Step 10:

[1260] The server adjusts the notification message based on the user's emotions based on the emotional data obtained by the emotion engine. For example, if the user is feeling stressed, the server sends a soft message such as, "Maintenance is required. However, please rest assured that we will continue to support you."

[1261] In this way, the server can execute a series of processing steps to maximize the power generation efficiency of the solar panels, detect deterioration or abnormalities early, manage maintenance efficiently, and improve the user experience.

[1262] 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.

[1263] 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.

[1264] 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.

[1265] 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.

[1266] 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.

[1267] 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.

[1268] 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).

[1269] 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.

[1270] 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."

[1271] 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.

[1272] 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).

[1273] 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.

[1274] 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.

[1275] 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.

[1276] 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.

[1277] 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.

[1278] 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.

[1279] 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.

[1280] 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.

[1281] 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.

[1282] 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.

[1283] The following is further disclosed regarding the above embodiment.

[1284] ---

[1285] (Claim 1)

[1286] a means for acquiring solar radiation data;

[1287] a means for obtaining weather data and power generation history;

[1288] A means of predicting optimal solar panel angle and orientation using a generative model; and

[1289] means for transmitting the predicted angle and heading to a single axis tracking system;

[1290] A means for predicting the deterioration state of a solar panel;

[1291] A means of detecting abnormalities and signs of failure and notifying maintenance,

[1292] A system that realizes efficient power generation from solar panels based on the above means.

[1293] (Claim 2)

[1294] a means for collecting sensor data to monitor the condition of the solar panels;

[1295] A means for automatically adjusting maintenance schedules based on collected data;

[1296] including means for notifying users of scheduled maintenance;

[1297] 10. The system of claim 1.

[1298] (Claim 3)

[1299] A means for users to check the status of their solar panels in real time using a dedicated application;

[1300] including a means for users to contact the server with questions or requests,

[1301] 10. The system of claim 1.

[1302] "Example 1"

[1303] (Claim 1)

[1304] a means for acquiring solar radiation data;

[1305] a means for obtaining weather data and power generation history;

[1306] A means for predicting optimal solar panel angle and orientation using a generative model; and

[1307] means for transmitting the predicted angle and heading to a tracking system;

[1308] A means for predicting the degradation state of the solar panel;

[1309] A means of detecting abnormalities and signs of failure and notifying maintenance;

[1310] a means for collecting sensor data and physically adjusting the solar panel;

[1311] A means to input a dataset into a generative AI model to predict the optimal angle and direction;

[1312] The system includes a means for sending a notification to a user when an anomaly is detected.

[1313] (Claim 2)

[1314] A means of automatically adjusting maintenance schedules based on sensor data;

[1315] 10. The system of claim 1, further comprising means for notifying a user of a maintenance schedule.

[1316] (Claim 3)

[1317] A means for users to check the status of solar panels in real time using a dedicated application;

[1318] 2. The system of claim 1, further comprising means for a user to inquire of questions or requests to the server.

[1319] "Application Example 1"

[1320] (Claim 1)

[1321] a means for acquiring solar radiation data;

[1322] a means for obtaining weather data and power generation history;

[1323] A means of predicting optimal solar panel angle and orientation using a generative model; and

[1324] means for transmitting the predicted angle and heading to a single axis tracking system;

[1325] A means for predicting the deterioration state of a solar panel;

[1326] A means of detecting abnormalities and signs of failure and notifying maintenance,

[1327] A means of collecting sensor data within the factory;

[1328] A means to analyze data in real time and automatically optimize equipment settings to maximize energy efficiency;

[1329] A method for predicting maintenance schedules based on signs of deterioration or abnormalities and notifying users of them.

[1330] A system that realizes efficient energy utilization based on the above-mentioned means.

[1331] (Claim 2)

[1332] a means for collecting sensor data to monitor the condition of the solar panels;

[1333] A means for automatically adjusting maintenance schedules based on collected data;

[1334] including means for notifying users of scheduled maintenance;

[1335] 10. The system of claim 1.

[1336] (Claim 3)

[1337] A means for users to check the status of their solar panels in real time using a dedicated application;

[1338] including a means for users to contact the server with questions or requests,

[1339] 10. The system of claim 1.

[1340] "Example 2: Combining Emotion Engines"

[1341] (Claim 1)

[1342] a means for acquiring solar radiation data;

[1343] a means for obtaining weather data and power generation history;

[1344] A means of predicting optimal solar panel angle and orientation using a generative model; and

[1345] means for transmitting the predicted angle and heading to a single axis tracking system;

[1346] A means for predicting the deterioration state of a solar panel;

[1347] A means of detecting abnormalities and signs of failure and notifying maintenance,

[1348] An emotion recognition means;

[1349] means for adjusting the notification message based on the emotional state of the user;

[1350] A system that realizes efficient power generation from solar panels based on the above means.

[1351] (Claim 2)

[1352] a means for collecting sensor data to monitor the condition of the solar panels;

[1353] A means for automatically adjusting maintenance schedules based on collected data;

[1354] including means for notifying users of scheduled maintenance;

[1355] 10. The system of claim 1.

[1356] (Claim 3)

[1357] A means for users to check the status of their solar panels in real time using a dedicated application;

[1358] including a means for users to contact the server with questions or requests,

[1359] 10. The system of claim 1.

[1360] "Application example 2 when combining emotion engines"

[1361] (Claim 1)

[1362] a means for acquiring solar radiation data;

[1363] a means for obtaining weather data and power generation history;

[1364] A means of predicting optimal solar panel angle and orientation using a generative model; and

[1365] means for transmitting the predicted angle and heading to a single axis tracking system;

[1366] A means for predicting the deterioration state of a solar panel;

[1367] A means of detecting abnormalities and signs of failure and notifying maintenance,

[1368] A means for controlling the robot arm using power generation history data and automatically adjusting the angle of the solar panel;

[1369] A system that realizes efficient power generation from solar panels based on the above means.

[1370] (Claim 2)

[1371] a means for collecting sensor data to monitor the status of the solar panel;

[1372] A means for automatically adjusting maintenance schedules based on collected data;

[1373] a means for notifying users of the maintenance schedule;

[1374] means for analyzing a user's emotions using an emotion engine;

[1375] means for adjusting the notification message according to the user's emotion;

[1376] 10. The system of claim 1.

[1377] (Claim 3)

[1378] A means for users to check the status of their solar panels in real time using a dedicated application;

[1379] A means for users to contact the server with questions or requests;

[1380] means for analyzing the emotional state of the user and adjusting the response message;

[1381] 10. The system of claim 1. [Explanation of symbols]

[1382] 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 acquiring solar radiation data; a means for obtaining weather data and power generation history; A means of predicting optimal solar panel angle and orientation using a generative model; and means for transmitting the predicted angle and heading to a single axis tracking system; A means for predicting the deterioration state of a solar panel; A means of detecting abnormalities and signs of failure and notifying maintenance, A system that realizes efficient power generation from solar panels based on the above means.

2. a means for collecting sensor data to monitor the condition of the solar panels; A means for automatically adjusting maintenance schedules based on collected data; including means for notifying users of scheduled maintenance; The system of claim 1 .

3. A means for users to check the status of their solar panels in real time using a dedicated application; including a means for users to contact the server with questions or requests, The system of claim 1 .

Images