System

Abstract

A system is provided.SOLUTION: A system for performing inspection and maintenance of a photovoltaic power generation facility, comprising: means for collecting image data from the photovoltaic power generation facility; means for collecting weather information; means for integrating and time-stamping the image data and the weather information; means for inputting the collected data into a generative artificial intelligence model and analyzing an anomaly; means for identifying the anomaly and generating a detailed report based thereon; and means for generating repair and aftercare advice based on the report.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] Conventional maintenance methods for solar power generation facilities mainly rely on visual inspections, which lack efficiency and precision. Furthermore, while drone-based inspection methods are suitable for large-scale solar panels, they are difficult to apply to homes or small-scale power generation facilities. This leads to delays in identifying and repairing abnormalities, resulting in reduced operational efficiency. Furthermore, with the newly mandated installation of solar power generation facilities in newly built homes, inspection needs are predicted to increase, raising concerns about increased effort and costs. [Means for solving the problem]

[0005] The present invention provides a system for improving the efficiency of inspection and maintenance work of photovoltaic power generation facilities.

[0006] means for collecting image data from the solar power generation facility;

[0007] a means for collecting meteorological information;

[0008] means for integrating and time-stamping image data and meteorological information;

[0009] A means for inputting the collected data into a generative artificial intelligence model and analyzing abnormalities;

[0010] A means for identifying anomalies and generating detailed reports based on the anomalies;

[0011] means for generating repair and aftercare advice based on the report;

[0012] This system automates the maintenance of homes and small-scale solar power generation facilities, quickly and accurately identifies abnormalities, and provides appropriate repairs and aftercare.

[0013] A "photovoltaic power generation system" is a device that absorbs sunlight and converts it into electrical energy, and is installed in homes and small buildings.

[0014] "Image data" refers to visual information of solar panels obtained using photographic equipment such as cameras and drones.

[0015] "Weather information" refers to data about weather conditions, such as temperature, humidity, precipitation, and wind speed.

[0016] A "timestamp" is information that indicates the date and time that specific data was collected.

[0017] A "generative artificial intelligence model" is an algorithm that uses technologies such as deep learning to analyze data and identify abnormalities.

[0018] "Abnormal areas" refer to abnormal parts such as cracks, dirt, and heat-generating areas on the surface or inside of solar panels.

[0019] A "report" is a document created based on the analysis results, and includes details of abnormalities and weather information.

[0020] "Repair and aftercare advice" is a proposal to provide the user with a repair method for an abnormality and an aftercare procedure. [Brief explanation of the drawings]

[0021] [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

[0022] 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.

[0023] First, the terms used in the following description will be explained.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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."

[0029] [First embodiment]

[0030] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0031] 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.

[0032] 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).

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0038] 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.

[0039] 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.

[0040] 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.

[0041] 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."

[0042] This invention is a system that automates and streamlines the maintenance of home and small-scale solar power generation facilities. The system collects image data and weather information from the solar power generation facility, analyzes this data using generative AI to identify abnormalities, and provides detailed reports and aftercare advice.

[0043] Data collection

[0044] The server periodically collects image data from drones and fixed cameras installed in homes and small-scale solar power generation facilities. It also collects meteorological data using sensors and APIs to obtain meteorological information. The collected image data and meteorological data are time-stamped and integrated into a single data package.

[0045] Data analysis with generative AI

[0046] The server inputs the collected data package into a generative AI model, which analyzes the image data. The generative AI model uses deep learning to identify abnormalities (e.g., cracks, dirt, and heat generation areas) on the surface and inside of the solar panel. The analysis results include the location, type, and severity of the abnormalities.

[0047] Reporting and Advice

[0048] The server generates a detailed report based on the analysis results. This report includes timestamps, weather information, and details of abnormalities. This report is provided to the user, who can view it from their PC, smartphone, or other device.

[0049] Additionally, the server uses generative AI to generate specific repair and aftercare advice, such as how to fix an abnormality or a list of tools to use.

[0050] Specific examples

[0051] A specific example of an actual maintenance operation using the system of the present invention will be described below.

[0052] 1. The server will start the drone and camera system at 10:00 AM every day to collect images of the solar panels and simultaneously acquire weather data.

[0053] Example: Obtain high-resolution image data from the camera system installed in "panel123" and obtain the current day's weather information from the weather API.

[0054] 2. The collected data is time-stamped, consolidated, and stored as a data package.

[0055] Example: Image data is combined with a timestamp of "2023-10-01 10:00:00" and collected weather data.

[0056] 3. The server inputs the collected data into the generative AI model, which analyzes the image data. The generative AI model identifies abnormalities in the image and returns that information as the analysis result.

[0057] Example: A generative AI model detects a crack at specific coordinates in an image and provides detailed information about it.

[0058] 4. The server generates a report based on the analysis results, including the coordinates of the anomaly, the details of the detection, and weather conditions.

[0059] Example: A report will be generated containing weather data for "2023-10-01 10:00:00" and detailed information on detected cracks.

[0060] 5. The server uses generative AI to provide repair procedures and aftercare advice.

[0061] For example, for detected cracks, an advice is generated recommending the use of epoxy resin and a UV lamp.

[0062] 6. The user checks the report and repair advice on their PC or smartphone and carries out the necessary repair work.

[0063] Example: The user uses the advice provided to repair the crack using epoxy resin.

[0064] As described above, the system of the present invention makes it possible to improve the efficiency of maintenance work for homes and small-scale solar power generation facilities, and to respond quickly and accurately. In addition, the use of generative AI improves the accuracy of identifying abnormalities and the reliability of repair advice.

[0065] The processing flow will be explained below.

[0066] Step 1:

[0067] The server sets up a regular data collection schedule, for example, to launch a data collection task at 10:00 AM every day.

[0068] Step 2:

[0069] The terminal, a drone or fixed camera, is activated to collect image data of the solar panels, taking high-resolution images and saving them.

[0070] Step 3:

[0071] The server retrieves data from weather sensors or APIs to collect weather information, such as temperature, humidity, and weather (sunny, cloudy, rainy, etc.).

[0072] Step 4:

[0073] The server combines the collected image data with weather information and adds a timestamp to indicate when the data was obtained.

[0074] Step 5:

[0075] The server inputs the collected data package into the generative AI model, which then begins analyzing the image data.

[0076] Step 6:

[0077] The server uses the generated AI model to analyze the image data and detect abnormalities, such as cracks, dirt, or heat generation on the surface of a solar panel.

[0078] Step 7:

[0079] The server generates a detailed report based on the detected anomalies, including timestamps, weather information, the location and type of anomaly, and its severity.

[0080] Step 8:

[0081] The server uses the generative AI model to generate repair and aftercare advice. For example, if a crack is found, it will suggest specific steps to repair it and the tools to use.

[0082] Step 9:

[0083] The server generates a report and sends advice to the user, who can then check the report from their PC or smartphone and take any necessary action.

[0084] Step 10:

[0085] The user checks the report provided by the server and performs any necessary repairs or maintenance work, for example, repairing a crack using the suggested method.

[0086] Example 1

[0087] 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."

[0088] Existing inspection and maintenance methods for solar power generation facilities require manual inspection work, which is inefficient and limits the accuracy of identifying and repairing abnormalities. Furthermore, weather and time constraints can make periodic inspections difficult and costly. This results in problems such as a long time before abnormalities are discovered, a decrease in power generation efficiency, and an increased risk of equipment failure.

[0089] 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.

[0090] In this invention, the server includes means for collecting image data from the solar power generation facility using drones and fixed cameras, means for collecting weather information using a weather API or sensors, means for integrating the image data and weather information and attaching a timestamp, means for inputting the collected data package into a generative AI model and analyzing abnormalities, means for generating a detailed report based on the location, type, and severity of the detected abnormalities, and means for generating repair and aftercare advice based on the report using the generative AI model, thereby automating and streamlining the inspection and maintenance process, enabling rapid and accurate identification of abnormalities and appropriate repairs.

[0091] A "drone" is an unmanned aerial vehicle that can be remotely controlled or flown autonomously to collect images and data of a designated area.

[0092] A "fixed camera" is a device that is installed at a specific location and periodically or continuously records still images of a designated object or area.

[0093] A "weather API" is an application programming interface for obtaining weather information via the Internet.

[0094] A "sensor" is a device that detects and measures environmental data such as temperature, humidity, and wind speed, and outputs it as an electrical signal.

[0095] A "timestamp" is data that is used to assign the exact date and time when image data and weather information were recorded or collected.

[0096] A "data package" is a single information unit that integrates image data and meteorological information together with a timestamp.

[0097] A "generative AI model" is an artificial intelligence program that uses deep learning to analyze input data and automatically perform specific tasks (e.g., anomaly detection, report generation, advice provision).

[0098] "Abnormal part" refers to a defective or problematic part of a solar power generation facility that affects its normal operation or performance.

[0099] A "detailed report" is a document generated by the server that includes a timestamp, meteorological information, and analysis results such as the location, type, and severity of anomalies.

[0100] "Repair and aftercare advice" is information that includes specific suggestions on appropriate repair methods, tools to be used, or preventive measures for detected abnormalities.

[0101] This invention is a system for automating and streamlining the inspection and maintenance of solar power generation facilities. The system collects image data of solar panels using drones or fixed cameras, and obtains weather information using weather APIs or sensors. These data are time-stamped, integrated, and processed as a data package. The collected data package is input into a generative AI model, which analyzes abnormalities. A detailed report is generated based on the analysis results, and the generative AI model is used to provide repair and aftercare advice.

[0102] The server collects image data using drones and fixed cameras installed at the solar power generation facilities. The drones take pictures by remote control or autonomous flight, and the fixed cameras capture still images from specific positions, resulting in high-resolution image data.

[0103] To obtain weather information, weather APIs or environmental sensors are used. Weather APIs are application programming interfaces that provide the latest weather information via the Internet, while environmental sensors are devices that collect weather data directly from the local area.

[0104] The system's server timestamps the collected image data and weather information and combines them into a single data package. The data package is stored in a database and input into a generative AI model for analysis. The generative AI model uses deep learning to preprocess the image data (color correction and noise removal), then detects anomalies. The generative AI model analyzes the location, type, and severity of anomalies and returns the analysis results.

[0105] Based on the analysis results, the server generates a detailed report that includes timestamps, weather information, the location and type of abnormality, and its severity. Furthermore, the server uses a generative AI model to generate repair and aftercare advice based on the report, providing users with information on specific repair procedures and tools to use.

[0106] As a specific example, the server activates a drone at a specified time every morning (for example, 10:00 AM) to collect images of solar panels. A fixed camera also operates at the same time to take still images. At this time, the server sends a request to a weather API to obtain the day's weather information. The collected image data and weather information are integrated with a timestamp and stored in a database. The generative AI model receives this data package as input and detects and analyzes abnormalities. The analysis results are generated as a detailed report including the location, type, and severity of the abnormality. The server generates repair and after-care advice based on this report and provides it to the user. Users can view these reports and advice via their PC or smartphone and carry out appropriate repair work.

[0107] An example of a prompt is:

[0108] "High-resolution image data is acquired from the camera system installed on panel 123, and the weather information for the day is obtained from the weather API."

[0109] "The image data is combined with the timestamp 2023-10-01 10:00:00 and the collected meteorological data."

[0110] "The generative AI model detects cracks at specific coordinates in the image and provides detailed information about them."

[0111] Examples include:

[0112] As a result, using this system will improve the efficiency of maintenance work for solar power generation facilities and enable quick and accurate responses. In particular, the use of a generative AI model is a distinctive feature of this invention, as it improves the accuracy of identifying abnormalities and the reliability of repair advice.

[0113] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0114] Step 1:

[0115] The server starts up the drone and camera system at a specified time every morning (e.g., 10:00 AM) and collects image data of the solar panels. The input is image data from the drone and fixed camera, and the output is high-resolution still image data. Specifically, the server calls the drone's API and sends a flight plan.

[0116] Step 2:

[0117] The server uses the weather API or environmental sensors to obtain the weather information for the day. The input is a request from the weather API and data from the environmental sensors, and the output is weather information such as temperature, humidity, and wind speed. Specifically, the server uses the OpenWeatherMap API to obtain weather information for "Tokyo."

[0118] Step 3:

[0119] The server assigns a timestamp to the collected image data and weather information and integrates them into a single data package. The input is image data and weather information, and the output is a time-stamped data package. Specifically, the image data and weather data with a timestamp of "2023-10-01 10:00:00" are integrated into a single JSON file.

[0120] Step 4:

[0121] The server inputs the data package into the generative AI model and analyzes the anomaly. The input is a time-stamped data package, and the output is an analysis result of the location, type, and severity of the anomaly. Specifically, the server converts the image data into input tensors for the generative AI model and performs analysis using deep learning.

[0122] Step 5:

[0123] The generative AI model performs color correction and noise reduction as preprocessing of image data. The input is image data, and the output is cleaned-up image data. Specifically, the generative AI model applies a Gaussian filter to reduce noise in the image.

[0124] Step 6:

[0125] The generative AI model analyzes the preprocessed image data and detects anomalies (e.g., cracks, stains, and hot spots). The input is the cleaned-up image data, and the output is detailed information about the anomalies. Specifically, the generative AI model detects a crack at a specific coordinate in the image (e.g., (150, 200)) and reports it as "Crack, Severity 3 / 5."

[0126] Step 7:

[0127] The server generates a detailed report based on the analysis results. The input is the analysis results from the generative AI model, and the output is a detailed report including the location, type, and severity of the anomaly. Specifically, the server generates a PDF report including a timestamp, weather information, and information about the detected anomaly.

[0128] Step 8:

[0129] The server uses a generative AI model to generate repair and aftercare advice based on the report. The input is a detailed report, and the output is advice including specific repair procedures and a list of tools to use. Specifically, the generative AI model generates advice in text form, such as "For the detected cracks, we recommend using epoxy resin and a UV lamp."

[0130] Step 9:

[0131] The server sends the generated report and advice to the user's device. The input is a detailed report and advice, and the output is data sent to the user's PC or smartphone. Specifically, the server sends a PDF report and advice in text format to the user's email address.

[0132] Step 10:

[0133] The user checks the report and repair advice via a PC or smartphone and carries out the necessary repair work. The input is the report and advice sent from the server, and the output is the actual repair work. In concrete terms, the user repairs the cracked area using epoxy resin based on the advice provided.

[0134] As described above, by implementing this system, maintenance work for solar power generation facilities can be automated, enabling prompt and accurate responses.

[0135] (Application example 1)

[0136] 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."

[0137] Inspection and maintenance of solar power generation facilities often requires manual checking, which is time-consuming and costly. It is also difficult for users without specialized knowledge to perform maintenance properly. Furthermore, delays in identifying abnormalities can lead to reduced power generation efficiency and serious breakdowns. There is a need for a system that can address these issues quickly and accurately by automating and streamlining the process.

[0138] 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.

[0139] In this invention, the server includes means for collecting image data from the solar power generation facility, means for collecting weather information, means for integrating the image data and weather information and assigning a timestamp, means for inputting the collected data into a generative artificial intelligence model and analyzing abnormalities, means for identifying abnormalities and generating a detailed report based on the identified abnormalities, means for generating repair and aftercare advice based on the report, means for transmitting the report and advice to a user's information terminal, and a mobile machine that autonomously patrols the solar power generation facility within the industrial facility and collects data. This makes it possible to automate and streamline inspection and maintenance of the solar power generation facility.

[0140] A "photovoltaic power generation facility" is a system that includes devices and associated equipment for converting solar light energy into electrical energy.

[0141] "Means for collecting image data" refers to equipment and technology for photographing the condition of solar power generation facilities and saving them as digital images.

[0142] "Means of collecting weather information" refers to sensors and APIs for obtaining environmental data such as temperature, humidity, wind speed, and solar radiation.

[0143] "Means for adding a timestamp" refers to the technology and method for adding date and time information to data.

[0144] A "generative artificial intelligence model" refers to an algorithm or set of computational models that are trained to perform a specific task using machine learning or deep learning.

[0145] "Means for analyzing abnormalities" refers to technology that uses collected image data and weather information to detect and evaluate abnormalities and deterioration in solar power generation equipment.

[0146] "Means for generating a report" refers to the technology and method for creating a document based on the analysis results that details any anomalies and other important information.

[0147] "Means for generating repair and aftercare advice" refers to techniques and methods for generating advice and recommendations regarding necessary repair procedures and maintenance methods based on the results of the analysis.

[0148] "Means for sending to the user's information terminal" refers to communication technology for transferring the generated report or advice to a device such as a smartphone or computer used by the user.

[0149] "Mobile machines that autonomously patrol solar power generation facilities and collect data" refers to automated devices such as self-driving robots and drones that automatically patrol solar power generation facilities within factories and collect image data and weather information.

[0150] The present invention relates to a system for automating and streamlining the inspection and maintenance of solar power generation facilities. The system is intended for use in industrial facilities and autonomously patrols the facilities, identifies abnormalities, and generates reports and advice.

[0151] First, the server runs on the following hardware and software: Drones and fixed cameras are used to collect image data, and API-enabled weather sensors are used to collect weather information. A generative AI model such as YOLOv5 is used for data analysis. This model uses deep learning to identify anomalies in the images.

[0152] The server periodically collects image data from drones and fixed cameras, and simultaneously retrieves weather data from weather sensors and APIs. These data are time-stamped and integrated. This integrated data package is then fed into a generative AI model to identify anomalies.

[0153] The analysis results include the location, type, and severity of the anomaly. The server generates a detailed report based on the analysis results, including a timestamp, weather information, and details of the anomaly. This report is sent to the user's information terminal and can be viewed from a PC or smartphone. The server also uses generative AI to provide repair and aftercare advice, such as how to repair the anomaly and a list of tools that should be used.

[0154] In a specific example, the server launches a drone inside the factory at 10:00 AM every day to collect images of the solar panels. At the same time, it obtains the day's weather information from an external weather API. The collected data is integrated with a timestamp such as "2023-10-01 10:00:00" and input into a generative AI model (e.g., YOLOv5). This model detects cracks at specific coordinates in the image and provides detailed information about them.

[0155] The generated report includes weather data for 2023-10-01 10:00:00 and detailed information about the detected cracks. The server also uses the generative AI to provide repair procedures and aftercare advice, such as recommending the use of epoxy resin and a UV lamp for the detected cracks.

[0156] Example prompt sentence:

[0157] "Image data: capture1.jpg, Weather data: Sunny, 24.5°C, Humidity 60%, Analysis result: Crack detected (coordinates: x=123, y=456), Repair advice: Use epoxy resin."

[0158] This system will improve the efficiency of maintenance work for solar power generation equipment in factories, enabling quick and accurate responses. By utilizing generative AI, the system is characterized by improved accuracy in identifying abnormalities and reliability of repair advice.

[0159] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0160] Step 1:

[0161] The server activates drones and fixed cameras installed at the solar power generation facility and collects image data. Control commands for the facility's cameras and drones are given as input. Specifically, the server sends flight commands to the drones to take photos of the solar panels. The output is high-resolution image data.

[0162] Step 2:

[0163] The server retrieves weather data using an external weather API. As input, it is given the API endpoint URL and any necessary authentication information. Using these, the server sends a request to the API server to retrieve current weather information (e.g., temperature, humidity, solar radiation, etc.). The output is weather data in JSON format.

[0164] Step 3:

[0165] The server integrates the image data and meteorological data and assigns a timestamp to each piece of data. The input is the image data and meteorological data obtained in steps 1 and 2. Specifically, the server combines these pieces of data into a single data package and adds the current date and time information. The output is a data package with a timestamp.

[0166] Step 4:

[0167] The server inputs the integrated data package into a generative AI model (e.g., YOLOv5) to analyze anomalies. The input is a time-stamped data package, and data processing involves image analysis to detect anomalies (e.g., cracks or stains) in the image. The generative AI model identifies the coordinates and type of anomalies and outputs the results. The output is the analysis result of the anomalies.

[0168] Step 5:

[0169] The server generates a detailed report based on the analysis results. The inputs are the analysis results obtained in step 4 and time-stamped weather data. Specifically, the server compiles the analysis results into a text report, listing the location, type, and severity of any anomalies. The output is a detailed report.

[0170] Step 6:

[0171] The server uses generative AI to generate repair and aftercare advice based on the analysis results. The input is the detailed report generated in step 5. Specifically, the server generates advice that lists appropriate repair methods and tools to be used based on the anomaly information in the report. The output is repair and aftercare advice.

[0172] Step 7:

[0173] The server sends the generated report and advice to the user's information device (e.g., a smartphone or PC). The input is the report and advice generated in step 6. Specifically, the server transfers this information to the user's device via email or a dedicated app. The output is the report and advice displayed on the user's device.

[0174] Step 8:

[0175] The user checks the report and advice received from the information terminal and carries out the necessary repair work. The input is the report and advice sent in step 7. In concrete terms, the user repairs the abnormal part using appropriate tools and materials based on the advice provided. The output is the repaired solar power generation equipment.

[0176] 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.

[0177] This invention is a system for streamlining the maintenance of home and small-scale solar power generation facilities. This system collects image data and weather information from the solar power generation facility and identifies abnormalities by analyzing the data using generative AI. In addition, by combining it with an emotion engine, the system recognizes the user's emotions and provides appropriate repair and aftercare advice.

[0178] Data collection

[0179] The server periodically collects image data from drones and fixed cameras installed in homes and small-scale solar power generation facilities. It also collects meteorological data using sensors and APIs to obtain meteorological information. The collected image data and meteorological data are time-stamped and integrated into a single data package.

[0180] Data analysis with generative AI

[0181] The server inputs the collected data package into a generative AI model, which analyzes the image data. The generative AI model uses deep learning to identify abnormalities on the surface and inside of the solar panel. The analysis results include the location, type, and severity of the abnormality.

[0182] Reporting and Advice

[0183] The server generates a detailed report based on the analysis results. This report includes timestamps, weather information, and details of abnormalities. This report is provided to the user, who can view it from their PC, smartphone, or other device.

[0184] Additionally, the server uses generative AI to generate specific repair and aftercare advice, such as how to fix an abnormality or a list of tools to use.

[0185] Recognizing user emotions with an emotion engine

[0186] The server also uses an emotion engine to recognize the user's emotions. This emotion engine identifies the user's current emotional state by analyzing the user's voice data, facial expression data, and operation history. For example, if the user is feeling anxious or stressed, the server can provide enhanced advice and support that takes those emotions into account.

[0187] Specific examples

[0188] A specific example of an actual maintenance operation using the system of the present invention will be described below.

[0189] 1. The server will start the drone and camera system at 10:00 AM every day to collect images of the solar panels and simultaneously acquire weather data.

[0190] Example: Obtain high-resolution image data from the camera system installed in "panel123" and obtain the current day's weather information from the weather API.

[0191] 2. The collected data is time-stamped, consolidated, and stored as a data package.

[0192] Example: Image data is combined with a timestamp of "2023-10-01 10:00:00" and collected weather data.

[0193] 3. The server inputs the collected data into the generative AI model, which analyzes the image data. The generative AI model identifies abnormalities in the image and returns that information as the analysis result.

[0194] Example: A generative AI model detects a crack at specific coordinates in an image and provides detailed information about it.

[0195] 4. The server generates a report based on the analysis results, including the coordinates of the anomaly, the details of the detection, and weather conditions.

[0196] Example: A report will be generated containing weather data for "2023-10-01 10:00:00" and detailed information on detected cracks.

[0197] 5. The server uses generative AI to provide repair procedures and aftercare advice.

[0198] For example, for detected cracks, an advice is generated recommending the use of epoxy resin and a UV lamp.

[0199] 6. The server uses an emotion engine to recognize the user's emotions. For example, it analyzes the voice data when the user connects to the system and determines that the user is feeling anxious.

[0200] Example: Voice analysis detects when a user is speaking in an anxious tone.

[0201] 7. The server takes into account the emotional information obtained by the emotion engine and provides appropriate support enhancements, for example, providing detailed explanations or additional support contacts.

[0202] For example, provide a user who is concerned with the repair process with more detailed instructions or contact information for an expert.

[0203] 8. The user checks the report and repair advice on their PC or smartphone and carries out the necessary repairs. Based on the information obtained from the emotion engine, the user can proceed with the work with peace of mind.

[0204] Example: The user uses the advice provided to repair the crack using epoxy resin.

[0205] As described above, the system of the present invention can improve the efficiency of maintenance of photovoltaic power generation facilities and provide support that takes into consideration the emotions of users.

[0206] The processing flow will be explained below.

[0207] Step 1:

[0208] The server sets up a regular data collection schedule, for example, to launch a data collection task at 10:00 AM every day.

[0209] Step 2:

[0210] The terminal, a drone or fixed camera, is activated to collect image data of the solar panels, taking high-resolution images and saving them.

[0211] Step 3:

[0212] The server retrieves data from weather sensors or APIs to collect weather information, such as temperature, humidity, and weather (sunny, cloudy, rainy, etc.).

[0213] Step 4:

[0214] The server combines the collected image data with weather information and adds a timestamp to indicate when the data was obtained.

[0215] Step 5:

[0216] The server inputs the collected data package into the generative AI model, which then begins analyzing the image data.

[0217] Step 6:

[0218] The server uses the generated AI model to analyze the image data and detect abnormalities, such as cracks, dirt, or heat generation on the surface of a solar panel.

[0219] Step 7:

[0220] The server generates a detailed report based on the detected anomalies, including timestamps, weather information, the location and type of anomaly, and its severity.

[0221] Step 8:

[0222] The server uses the generative AI model to generate repair and aftercare advice. For example, if a crack is found, it will suggest specific steps to repair it and the tools to use.

[0223] Step 9:

[0224] The server uses an emotion engine to recognize the user's emotions, for example, by analyzing the user's voice data, facial expression data, and operation history to determine the user's current emotional state.

[0225] Step 10:

[0226] The server takes emotional information into account and, if the user feels anxious or stressed, enhances the advice and support according to the emotion, for example by providing detailed explanations or additional support contacts.

[0227] Step 11:

[0228] The server generates a report and sends advice to the user, who can then check the report from their PC or smartphone and take any necessary action.

[0229] Step 12:

[0230] The user can check the report provided by the server and carry out the necessary repairs and maintenance work, for example, repairing a crack using the suggested method, and proceed with the work with peace of mind using the additional support suggested by the emotion engine.

[0231] Example 2

[0232] 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."

[0233] In the inspection and maintenance of solar power generation facilities, it is extremely important to quickly and accurately detect abnormalities in the facilities and provide users with appropriate repair and aftercare advice. However, current systems require time and effort to collect and analyze data, and do not take user feelings into consideration, resulting in a lack of appropriate support.

[0234] 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 collecting image data, means for collecting weather information, means for integrating image data and weather information and assigning a timestamp, means for inputting the collected data into a generative AI model and analyzing abnormalities, means for identifying abnormalities and generating a detailed report based on the identified abnormalities, means for generating repair and aftercare advice based on the report, means for recognizing the user's emotional state, and means for providing additional support based on the recognized emotional state. This makes it possible to quickly and accurately detect abnormalities in the solar power generation equipment and provide the user with appropriate repair and aftercare advice. Furthermore, providing support that takes the user's emotions into consideration reduces the user's anxiety and stress, allowing the work to proceed smoothly.

[0235] "Means for collecting image data" refers to a device or system for acquiring image data from a photovoltaic power generation facility.

[0236] "Means for collecting weather information" refers to devices or systems for acquiring weather data in the surrounding environment of the solar power generation facility.

[0237] The "time stamping means" is a system for adding date and time information to collected image data and meteorological data.

[0238] A "generative artificial intelligence model" is a system that includes a deep learning model for analyzing collected data and automatically detecting abnormalities.

[0239] The "means for analyzing abnormal locations" refers to a method and system for identifying abnormal locations in a photovoltaic power generation facility using image data and meteorological data.

[0240] The "means for generating a detailed report" is a system for creating a report containing detailed information based on the identified abnormality.

[0241] The "means for generating repair and aftercare advice" is a system that uses a generative AI model to provide recommendations regarding repair methods and aftercare.

[0242] The "means for recognizing the user's emotional state" is a technology for identifying the user's emotions by analyzing voice data, facial expression data, and operation history.

[0243] The "means for providing additional support" is a system that provides appropriate advice and support information based on the recognized emotional state of the user.

[0244] This invention is a system for improving the efficiency of inspection and maintenance of solar power generation facilities. This system collects image data and weather information, analyzes them using a generative AI model, identifies abnormalities, and provides appropriate repair and aftercare advice to users. It also has a function to recognize users' emotions and enhance support based on those emotions.

[0245] Data collection

[0246] The server periodically collects image data of the solar power generation facility using drones and fixed cameras. The drones are equipped with an automatic navigation system, and the fixed cameras use high-resolution cameras. Weather information is also collected using sensors and weather APIs. For example, the API can be used to obtain the current day's weather information, and sensors can be used to collect local weather data in real time.

[0247] Data package integration

[0248] The collected image data and meteorological data are each given a timestamp, which clarifies when each piece of data was collected. The server then integrates this data and stores it in a database as a single data package.

[0249] Data analysis with generative AI

[0250] The server inputs the integrated data package into a generative AI model, which uses a deep learning algorithm to analyze the image data and identify abnormalities in the solar panels. The generative AI model outputs the location, type, and severity of the abnormalities as analysis results.

[0251] Reporting and Advice

[0252] The server generates a detailed report based on the analysis results. This report includes timestamps, weather information, and details of any identified anomalies. The report is output in a format that is easy for users to understand and can be viewed on a PC or smartphone. Furthermore, the generative AI provides advice such as specific repair methods and a list of tools to use.

[0253] Recognizing user emotions with an emotion engine

[0254] The server recognizes the user's emotional state using an emotion engine, which analyzes the user's voice data, facial expression data, and operation history to determine whether the user is feeling anxious or stressed.

[0255] Providing enhanced support

[0256] The server provides detailed instructions and additional support contact information based on the user's emotional state, allowing the user to proceed with the task without anxiety. For example, if the server analyzes the voice data when the user connects to the system and determines that the user is feeling anxious, it provides detailed repair guides and contact information for experts.

[0257] Specific examples

[0258] Here is a concrete example:

[0259] 1. The server starts the drone and camera system at 10:00 AM every day to collect images of the solar panels and retrieves the day's weather information from the weather API.

[0260] Example: High-resolution image data is acquired from a camera system installed on "panel123."

[0261] 2. The collected data is given a timestamp "2023-10-01 10:00:00", consolidated, and saved as a data package.

[0262] Example: Integrating image data with meteorological data.

[0263] 3. The server inputs the data package into a generative AI model and analyzes the image data.

[0264] Example: A generative AI model detects a crack at coordinates (50,100) in an image.

[0265] 4. Generate a report based on the analysis results and provide it to the user.

[0266] Example: The report will show the anomaly location as "(50,100): Crack".

[0267] 5. The server uses generative AI to provide specific repair and aftercare advice.

[0268] For example: We recommend using epoxy resin and a UV lamp.

[0269] 6. The server uses an emotion engine to detect anxiety from the user's voice data.

[0270] Example: Analyzing anxious tone.

[0271] 7. Provide users with additional support information to expedite their work.

[0272] Example: Detailed repair guides.

[0273] As described above, the present invention improves the efficiency of maintenance of photovoltaic power generation facilities and provides support that takes into account the emotions of users.

[0274] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0275] Step 1:

[0276] The server activates the drone and fixed camera to collect image data of the solar power plant. The drone is equipped with an automatic navigation system and flies automatically to specified coordinates. The fixed camera uses a high-resolution camera system to capture images at specific times. The input is the operation time and coordinates of the drone and camera system, and the output is the collected high-resolution image file.

[0277] Example: At 10:00 AM, the drone and camera will start up and collect high-resolution image "image_20231001.png" from "panel123."

[0278] Step 2:

[0279] The server collects weather data via weather sensors and weather APIs. The weather sensors measure local temperature, humidity, wind speed, etc. in real time, and obtains the day's weather information from the API. The input is real-time data from the weather sensors and API requests, and the output is a weather information dataset.

[0280] Example: Collect real-time data from weather sensors and weather information obtained from a weather API.

[0281] Step 3:

[0282] The server assigns a timestamp to the collected image data and meteorological data, and integrates them to create a data package. The timestamp indicates the collection time and is used to maintain data consistency. The input is image data and meteorological data, and the output is the integrated data package.

[0283] Example: Create a data package by adding the timestamp "2023-10-01 10:00:00" to the image data "image_20231001.png" and weather data.

[0284] Step 4:

[0285] The server inputs the data package into a generative AI model that analyzes the image data. The generative AI model uses a deep learning algorithm to identify abnormalities in the solar panels. The input is the data package, and the output is the analysis results, including the location, type, and severity of the abnormality.

[0286] Example: Input "data_package_20231001.json" into the AI ​​model and obtain the analysis result "Crack: Severity 2" at coordinates (50,100).

[0287] Step 5:

[0288] The server generates a detailed report based on the analysis results. The report includes timestamps, weather information, and details of identified anomalies, and is provided to the user. The input is the analysis results, and the output is the report.

[0289] Example: Generate a report with the timestamp "2023-10-01 10:00:00", weather data, and anomaly location "(50,100): Crack".

[0290] Step 6:

[0291] The server uses a generative AI model to generate specific advice on repairs and aftercare. The generated advice can be based on the user's skill level and previous repair history. The input is the analysis results and user information, and the output is repair and aftercare advice.

[0292] Example: Generate advice such as "Use epoxy resin and a UV lamp to repair the crack."

[0293] Step 7:

[0294] The server uses an emotion engine to recognize the user's emotional state. The emotion engine analyzes voice data, facial expression data, and operation history to identify the user's emotion. The input is the user's voice data and operation history, and the output is the user's emotional state.

[0295] Example: Determine that the user is feeling anxious based on voice data.

[0296] Step 8:

[0297] The server provides additional support based on the recognized emotional state, for example providing detailed explanations or contact information for experts to a user who is feeling anxious. The input is the user's emotional state, and the output is enhanced support information.

[0298] Example: Providing a detailed repair guide or expert contact information to a user who is concerned.

[0299] Step 9:

[0300] Users can check the report and repair advice from their PC or smartphone and carry out the necessary repair work. This allows them to proceed with the work accurately based on the information provided. The input is the report and advice, and the output is the repair work carried out by the user.

[0301] Example: Check the advice given by the PC and repair the crack using epoxy resin.

[0302] (Application example 2)

[0303] 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."

[0304] In the maintenance of machinery and equipment in factories, early detection of abnormalities and provision of appropriate repair methods are key challenges. Conventional systems take time to identify abnormalities and do not provide support that takes into account the emotional state of the worker, which can reduce the efficiency of maintenance work. This can lead to problems such as increased equipment downtime and reduced productivity. The objective of this invention is to improve the efficiency of factory equipment maintenance, provide early detection of abnormalities, provide appropriate repair methods, and provide support that takes into account the user's emotions.

[0305] 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 collecting image data from factory equipment, means for collecting environmental information, means for integrating the image data and environmental information and assigning a timestamp, means for inputting the collected data into a generative artificial intelligence model and analyzing abnormalities, means for identifying abnormalities and generating a detailed report based on the identified abnormalities, means for generating repair and aftercare advice based on the report, and means for recognizing the user's emotions using an emotion engine and providing appropriate support. This not only enables early detection of abnormalities and appropriate provision of repair methods during factory equipment maintenance, but also enables support that takes into account the emotional state of workers, thereby improving the efficiency and productivity of maintenance work.

[0306] "Image data" refers to visual information captured by devices such as cameras and drones.

[0307] "Weather information" refers to environmental data such as the weather, temperature, humidity, and wind speed at a specific location.

[0308] A "timestamp" is information that indicates the date and time when data was collected or generated.

[0309] A "generative artificial intelligence model" is a computer program that analyzes various data, identifies abnormalities, and generates advice.

[0310] An "abnormal part" refers to a part of machinery or solar power generation equipment that deviates from normal operation or condition.

[0311] "Report" means a detailed report generated based on collected and analyzed data.

[0312] "Repair and aftercare advice" means instructions or recommendations regarding how to repair and follow-up care for identified anomalies.

[0313] The "emotion engine" is an artificial intelligence system that identifies a user's emotional state by analyzing the user's voice data and facial expression data.

[0314] "Means for recognizing user emotions" refers to a method or device that uses an emotion engine to analyze the user's emotional state and provide appropriate support.

[0315] "Appropriate support" refers to assistance measures such as providing more detailed explanations or contact information for experts depending on the user's emotional state.

[0316] This invention is a system for improving the efficiency of maintenance of machinery and equipment in factories. This system collects image data and environmental information, analyzes them using a generative AI model, identifies abnormalities, and provides repair methods. Furthermore, it is possible to recognize the user's emotions using an emotion engine and provide appropriate support.

[0317] Data collection

[0318] The server periodically collects image data from drones and fixed cameras in the factory. It also collects environmental data using sensors and APIs to obtain environmental information such as temperature and humidity. The collected image data and environmental data are time-stamped and integrated into a single data package.

[0319] Data analysis with generative AI

[0320] The server inputs the collected data packages into a generative AI model, which analyzes the image data. The generative AI model uses deep learning to identify abnormalities on the surface or inside the machinery. The analysis results include the location, type, and severity of the abnormalities.

[0321] Reporting and Advice

[0322] The server generates a detailed report based on the analysis results. This report includes a timestamp, environmental information, and details of the abnormality. This report is provided to the user, who can view it from a PC, smartphone, or other device. In addition, the server uses generative AI to generate specific advice on repairs and aftercare, such as how to repair the abnormality and a list of tools that should be used.

[0323] Recognizing user emotions with an emotion engine

[0324] The server uses an emotion engine to recognize the user's emotions. This emotion engine identifies the user's current emotional state by analyzing the user's voice data and facial expression data. For example, if the user is feeling anxious or stressed, the server will provide enhanced advice and support that takes those emotions into account.

[0325] Specific examples

[0326] A specific example of an actual maintenance operation using the system of the present invention will be described below.

[0327] 1. The server activates the drones and camera system at 10:00 AM every day to collect images of the factory machinery and environmental data.

[0328] 2. The collected data is time-stamped, consolidated, and stored as a data package.

[0329] 3. The server inputs the collected data into the generative AI model, which analyzes the image data. The generative AI model identifies abnormalities in the image and returns that information as the analysis result.

[0330] 4. The server generates a report based on the analysis results, including the coordinates of the anomaly, the details of the detection, and the environmental conditions.

[0331] 5. The server uses generative AI to provide repair procedures and aftercare advice.

[0332] 6. The server uses an emotion engine to recognize the user's emotions. For example, it analyzes the voice data when the user connects to the system and determines that the user is feeling anxious.

[0333] 7. The server considers the emotional information obtained by the emotion engine and reinforces appropriate support.

[0334] Prompt Sentence Examples

[0335] Below is an example of a prompt sentence to be input to a generative AI model. This prompt sentence shows how the collected data should be input to the generative AI model:

[0336] Image data and environmental data are integrated and input into a generative AI model. The analysis results include the location, type, and severity of anomalies.

[0337] As described above, the system of the present invention can improve the efficiency of maintenance of factory machinery and equipment and provide support that takes into account the emotions of users.

[0338] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0339] Step 1:

[0340] The server periodically collects image data from drones and fixed cameras in the factory. The drones and fixed cameras acquire high-resolution image data and send it to the server. The input is image data of the machinery and equipment in the factory, and the output is image data stored on the server.

[0341] Step 2:

[0342] The server uses sensors and APIs to obtain environmental information such as temperature and humidity. The environmental data obtained from the sensors includes various data such as temperature, humidity, and wind speed. The same data can also be obtained using APIs. The input is environmental data from the sensors and APIs, and the output is environmental data stored on the server.

[0343] Step 3:

[0344] The server assigns a timestamp to the collected image data and environmental data and creates an integrated data package. The timestamp indicates the date and time the data was collected or generated, and all data is integrated. This process creates a data package in which the date, time, and environmental conditions are clearly associated. The input is image data and environmental data, and the output is an integrated data package.

[0345] Step 4:

[0346] The server inputs the integrated data package into a generative AI model that analyzes the image data. The generative AI model uses deep learning to identify anomalies within the image. The input to the AI ​​model is the integrated data package, and the output is an analysis result that indicates the location, type, and severity of the anomaly.

[0347] Step 5:

[0348] The server generates a detailed report based on the analysis results obtained from the generative AI model. This report includes a timestamp, environmental information, and details of the anomaly. The report is automatically generated and saved for later viewing by the user. The input is the analysis results and environmental data, and the output is a report file.

[0349] Step 6:

[0350] The server uses generative AI to generate repair procedures and aftercare advice for the abnormal area. For example, if the abnormal area is a crack, it will provide advice on using epoxy resin and a UV lamp. The input is the analysis results, and the output is repair and aftercare advice.

[0351] Step 7:

[0352] The server uses an emotion engine to recognize the user's emotions. When the user connects to the system, the server analyzes the voice and facial expression data as input and identifies the user's emotional state. The input is the voice and facial expression data, and the output is the evaluation result of the user's emotional state.

[0353] Step 8:

[0354] The server takes into account the emotional information provided by the emotion engine and provides appropriate support to the user. For example, if the user feels anxious, the server will enhance the support content by providing a detailed explanation or contact information for an expert. The input is the evaluation result of the emotional state, and the output is the enhanced support content.

[0355] 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.

[0356] 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.

[0357] 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.

[0358] [Second embodiment]

[0359] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0360] 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.

[0361] 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).

[0362] 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.

[0363] 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.

[0364] 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).

[0365] 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.

[0366] 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.

[0367] 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.

[0368] 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.

[0369] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0370] 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."

[0371] This invention is a system that automates and streamlines the maintenance of home and small-scale solar power generation facilities. The system collects image data and weather information from the solar power generation facility, analyzes this data using generative AI to identify abnormalities, and provides detailed reports and aftercare advice.

[0372] Data collection

[0373] The server periodically collects image data from drones and fixed cameras installed in homes and small-scale solar power generation facilities. It also collects meteorological data using sensors and APIs to obtain meteorological information. The collected image data and meteorological data are time-stamped and integrated into a single data package.

[0374] Data analysis with generative AI

[0375] The server inputs the collected data package into a generative AI model, which analyzes the image data. The generative AI model uses deep learning to identify abnormalities (e.g., cracks, dirt, and heat generation areas) on the surface and inside of the solar panel. The analysis results include the location, type, and severity of the abnormalities.

[0376] Reporting and Advice

[0377] The server generates a detailed report based on the analysis results. This report includes timestamps, weather information, and details of abnormalities. This report is provided to the user, who can view it from their PC, smartphone, or other device.

[0378] Additionally, the server uses generative AI to generate specific repair and aftercare advice, such as how to fix an abnormality or a list of tools to use.

[0379] Specific examples

[0380] A specific example of an actual maintenance operation using the system of the present invention will be described below.

[0381] 1. The server will start the drone and camera system at 10:00 AM every day to collect images of the solar panels and simultaneously acquire weather data.

[0382] Example: Obtain high-resolution image data from the camera system installed in "panel123" and obtain the current day's weather information from the weather API.

[0383] 2. The collected data is time-stamped, consolidated, and stored as a data package.

[0384] Example: Image data is combined with a timestamp of "2023-10-01 10:00:00" and collected weather data.

[0385] 3. The server inputs the collected data into the generative AI model, which analyzes the image data. The generative AI model identifies abnormalities in the image and returns that information as the analysis result.

[0386] Example: A generative AI model detects a crack at specific coordinates in an image and provides detailed information about it.

[0387] 4. The server generates a report based on the analysis results, including the coordinates of the anomaly, the details of the detection, and weather conditions.

[0388] Example: A report will be generated containing weather data for "2023-10-01 10:00:00" and detailed information on detected cracks.

[0389] 5. The server uses generative AI to provide repair procedures and aftercare advice.

[0390] For example, for detected cracks, an advice is generated recommending the use of epoxy resin and a UV lamp.

[0391] 6. The user checks the report and repair advice on their PC or smartphone and carries out the necessary repair work.

[0392] Example: The user uses the advice provided to repair the crack using epoxy resin.

[0393] As described above, the system of the present invention makes it possible to improve the efficiency of maintenance work for homes and small-scale solar power generation facilities, and to respond quickly and accurately. In addition, the use of generative AI improves the accuracy of identifying abnormalities and the reliability of repair advice.

[0394] The processing flow will be explained below.

[0395] Step 1:

[0396] The server sets up a regular data collection schedule, for example, to launch a data collection task at 10:00 AM every day.

[0397] Step 2:

[0398] The terminal, a drone or fixed camera, is activated to collect image data of the solar panels, taking high-resolution images and saving them.

[0399] Step 3:

[0400] The server retrieves data from weather sensors or APIs to collect weather information, such as temperature, humidity, and weather (sunny, cloudy, rainy, etc.).

[0401] Step 4:

[0402] The server combines the collected image data with weather information and adds a timestamp to indicate when the data was obtained.

[0403] Step 5:

[0404] The server inputs the collected data package into the generative AI model, which then begins analyzing the image data.

[0405] Step 6:

[0406] The server uses the generated AI model to analyze the image data and detect abnormalities, such as cracks, dirt, or heat generation on the surface of a solar panel.

[0407] Step 7:

[0408] The server generates a detailed report based on the detected anomalies, including timestamps, weather information, the location and type of anomaly, and its severity.

[0409] Step 8:

[0410] The server uses the generative AI model to generate repair and aftercare advice. For example, if a crack is found, it will suggest specific steps to repair it and the tools to use.

[0411] Step 9:

[0412] The server generates a report and sends advice to the user, who can then check the report from their PC or smartphone and take any necessary action.

[0413] Step 10:

[0414] The user checks the report provided by the server and performs any necessary repairs or maintenance work, for example, repairing a crack using the suggested method.

[0415] Example 1

[0416] 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."

[0417] Existing inspection and maintenance methods for solar power generation facilities require manual inspection work, which is inefficient and limits the accuracy of identifying and repairing abnormalities. Furthermore, weather and time constraints can make periodic inspections difficult and costly. This results in problems such as a long time before abnormalities are discovered, a decrease in power generation efficiency, and an increased risk of equipment failure.

[0418] 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.

[0419] In this invention, the server includes means for collecting image data from the solar power generation facility using drones and fixed cameras, means for collecting weather information using a weather API or sensors, means for integrating the image data and weather information and attaching a timestamp, means for inputting the collected data package into a generative AI model and analyzing abnormalities, means for generating a detailed report based on the location, type, and severity of the detected abnormalities, and means for generating repair and aftercare advice based on the report using the generative AI model, thereby automating and streamlining the inspection and maintenance process, enabling rapid and accurate identification of abnormalities and appropriate repairs.

[0420] A "drone" is an unmanned aerial vehicle that can be remotely controlled or flown autonomously to collect images and data of a designated area.

[0421] A "fixed camera" is a device that is installed at a specific location and periodically or continuously records still images of a designated object or area.

[0422] A "weather API" is an application programming interface for obtaining weather information via the Internet.

[0423] A "sensor" is a device that detects and measures environmental data such as temperature, humidity, and wind speed, and outputs it as an electrical signal.

[0424] A "timestamp" is data that is used to assign the exact date and time when image data and weather information were recorded or collected.

[0425] A "data package" is a single information unit that integrates image data and meteorological information together with a timestamp.

[0426] A "generative AI model" is an artificial intelligence program that uses deep learning to analyze input data and automatically perform specific tasks (e.g., anomaly detection, report generation, advice provision).

[0427] "Abnormal part" refers to a defective or problematic part of a solar power generation facility that affects its normal operation or performance.

[0428] A "detailed report" is a document generated by the server that includes a timestamp, meteorological information, and analysis results such as the location, type, and severity of anomalies.

[0429] "Repair and aftercare advice" is information that includes specific suggestions on appropriate repair methods, tools to be used, or preventive measures for detected abnormalities.

[0430] This invention is a system for automating and streamlining the inspection and maintenance of solar power generation facilities. The system collects image data of solar panels using drones or fixed cameras, and obtains weather information using weather APIs or sensors. These data are time-stamped, integrated, and processed as a data package. The collected data package is input into a generative AI model, which analyzes abnormalities. A detailed report is generated based on the analysis results, and the generative AI model is used to provide repair and aftercare advice.

[0431] The server collects image data using drones and fixed cameras installed at the solar power generation facilities. The drones take pictures by remote control or autonomous flight, and the fixed cameras capture still images from specific positions, resulting in high-resolution image data.

[0432] To obtain weather information, weather APIs or environmental sensors are used. Weather APIs are application programming interfaces that provide the latest weather information via the Internet, while environmental sensors are devices that collect weather data directly from the local area.

[0433] The system's server timestamps the collected image data and weather information and combines them into a single data package. The data package is stored in a database and input into a generative AI model for analysis. The generative AI model uses deep learning to preprocess the image data (color correction and noise removal), then detects anomalies. The generative AI model analyzes the location, type, and severity of anomalies and returns the analysis results.

[0434] Based on the analysis results, the server generates a detailed report that includes timestamps, weather information, the location and type of abnormality, and its severity. Furthermore, the server uses a generative AI model to generate repair and aftercare advice based on the report, providing users with information on specific repair procedures and tools to use.

[0435] As a specific example, the server activates a drone at a specified time every morning (for example, 10:00 AM) to collect images of solar panels. A fixed camera also operates at the same time to take still images. At this time, the server sends a request to a weather API to obtain the day's weather information. The collected image data and weather information are integrated with a timestamp and stored in a database. The generative AI model receives this data package as input and detects and analyzes abnormalities. The analysis results are generated as a detailed report including the location, type, and severity of the abnormality. The server generates repair and after-care advice based on this report and provides it to the user. Users can view these reports and advice via their PC or smartphone and carry out appropriate repair work.

[0436] An example of a prompt is:

[0437] "High-resolution image data is acquired from the camera system installed on panel 123, and the weather information for the day is obtained from the weather API."

[0438] "The image data is combined with the timestamp 2023-10-01 10:00:00 and the collected meteorological data."

[0439] "The generative AI model detects cracks at specific coordinates in the image and provides detailed information about them."

[0440] Examples include:

[0441] As a result, using this system will improve the efficiency of maintenance work for solar power generation facilities and enable quick and accurate responses. In particular, the use of a generative AI model is a distinctive feature of this invention, as it improves the accuracy of identifying abnormalities and the reliability of repair advice.

[0442] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0443] Step 1:

[0444] The server starts up the drone and camera system at a specified time every morning (e.g., 10:00 AM) and collects image data of the solar panels. The input is image data from the drone and fixed camera, and the output is high-resolution still image data. Specifically, the server calls the drone's API and sends a flight plan.

[0445] Step 2:

[0446] The server uses the weather API or environmental sensors to obtain the weather information for the day. The input is a request from the weather API and data from the environmental sensors, and the output is weather information such as temperature, humidity, and wind speed. Specifically, the server uses the OpenWeatherMap API to obtain weather information for "Tokyo."

[0447] Step 3:

[0448] The server assigns a timestamp to the collected image data and weather information and integrates them into a single data package. The input is image data and weather information, and the output is a time-stamped data package. Specifically, the image data and weather data with a timestamp of "2023-10-01 10:00:00" are integrated into a single JSON file.

[0449] Step 4:

[0450] The server inputs the data package into the generative AI model and analyzes the anomaly. The input is a time-stamped data package, and the output is an analysis result of the location, type, and severity of the anomaly. Specifically, the server converts the image data into input tensors for the generative AI model and performs analysis using deep learning.

[0451] Step 5:

[0452] The generative AI model performs color correction and noise reduction as preprocessing of image data. The input is image data, and the output is cleaned-up image data. Specifically, the generative AI model applies a Gaussian filter to reduce noise in the image.

[0453] Step 6:

[0454] The generative AI model analyzes the preprocessed image data and detects anomalies (e.g., cracks, stains, and hot spots). The input is the cleaned-up image data, and the output is detailed information about the anomalies. Specifically, the generative AI model detects a crack at a specific coordinate in the image (e.g., (150, 200)) and reports it as "Crack, Severity 3 / 5."

[0455] Step 7:

[0456] The server generates a detailed report based on the analysis results. The input is the analysis results from the generative AI model, and the output is a detailed report including the location, type, and severity of the anomaly. Specifically, the server generates a PDF report including a timestamp, weather information, and information about the detected anomaly.

[0457] Step 8:

[0458] The server uses a generative AI model to generate repair and aftercare advice based on the report. The input is a detailed report, and the output is advice including specific repair procedures and a list of tools to use. Specifically, the generative AI model generates advice in text form, such as "For the detected cracks, we recommend using epoxy resin and a UV lamp."

[0459] Step 9:

[0460] The server sends the generated report and advice to the user's device. The input is a detailed report and advice, and the output is data sent to the user's PC or smartphone. Specifically, the server sends a PDF report and advice in text format to the user's email address.

[0461] Step 10:

[0462] The user checks the report and repair advice via a PC or smartphone and carries out the necessary repair work. The input is the report and advice sent from the server, and the output is the actual repair work. In concrete terms, the user repairs the cracked area using epoxy resin based on the advice provided.

[0463] As described above, by implementing this system, maintenance work for solar power generation facilities can be automated, enabling prompt and accurate responses.

[0464] (Application example 1)

[0465] 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."

[0466] Inspection and maintenance of solar power generation facilities often requires manual checking, which is time-consuming and costly. It is also difficult for users without specialized knowledge to perform maintenance properly. Furthermore, delays in identifying abnormalities can lead to reduced power generation efficiency and serious breakdowns. There is a need for a system that can address these issues quickly and accurately by automating and streamlining the process.

[0467] 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.

[0468] In this invention, the server includes means for collecting image data from the solar power generation facility, means for collecting weather information, means for integrating the image data and weather information and assigning a timestamp, means for inputting the collected data into a generative artificial intelligence model and analyzing abnormalities, means for identifying abnormalities and generating a detailed report based on the identified abnormalities, means for generating repair and aftercare advice based on the report, means for transmitting the report and advice to a user's information terminal, and a mobile machine that autonomously patrols the solar power generation facility within the industrial facility and collects data. This makes it possible to automate and streamline inspection and maintenance of the solar power generation facility.

[0469] A "photovoltaic power generation facility" is a system that includes devices and associated equipment for converting solar light energy into electrical energy.

[0470] "Means for collecting image data" refers to equipment and technology for photographing the condition of solar power generation facilities and saving them as digital images.

[0471] "Means of collecting weather information" refers to sensors and APIs for obtaining environmental data such as temperature, humidity, wind speed, and solar radiation.

[0472] "Means for adding a timestamp" refers to the technology and method for adding date and time information to data.

[0473] A "generative artificial intelligence model" refers to an algorithm or set of computational models that are trained to perform a specific task using machine learning or deep learning.

[0474] "Means for analyzing abnormalities" refers to technology that uses collected image data and weather information to detect and evaluate abnormalities and deterioration in solar power generation equipment.

[0475] "Means for generating a report" refers to the technology and method for creating a document based on the analysis results that details any anomalies and other important information.

[0476] "Means for generating repair and aftercare advice" refers to techniques and methods for generating advice and recommendations regarding necessary repair procedures and maintenance methods based on the results of the analysis.

[0477] "Means for sending to the user's information terminal" refers to communication technology for transferring the generated report or advice to a device such as a smartphone or computer used by the user.

[0478] "Mobile machines that autonomously patrol solar power generation facilities and collect data" refers to automated devices such as self-driving robots and drones that automatically patrol solar power generation facilities within factories and collect image data and weather information.

[0479] The present invention relates to a system for automating and streamlining the inspection and maintenance of solar power generation facilities. The system is intended for use in industrial facilities and autonomously patrols the facilities, identifies abnormalities, and generates reports and advice.

[0480] First, the server runs on the following hardware and software: Drones and fixed cameras are used to collect image data, and API-enabled weather sensors are used to collect weather information. A generative AI model such as YOLOv5 is used for data analysis. This model uses deep learning to identify anomalies in the images.

[0481] The server periodically collects image data from drones and fixed cameras, and simultaneously retrieves weather data from weather sensors and APIs. These data are time-stamped and integrated. This integrated data package is then fed into a generative AI model to identify anomalies.

[0482] The analysis results include the location, type, and severity of the anomaly. The server generates a detailed report based on the analysis results, including a timestamp, weather information, and details of the anomaly. This report is sent to the user's information terminal and can be viewed from a PC or smartphone. The server also uses generative AI to provide repair and aftercare advice, such as how to repair the anomaly and a list of tools that should be used.

[0483] In a specific example, the server launches a drone inside the factory at 10:00 AM every day to collect images of the solar panels. At the same time, it obtains the day's weather information from an external weather API. The collected data is integrated with a timestamp such as "2023-10-01 10:00:00" and input into a generative AI model (e.g., YOLOv5). This model detects cracks at specific coordinates in the image and provides detailed information about them.

[0484] The generated report includes weather data for 2023-10-01 10:00:00 and detailed information about the detected cracks. The server also uses the generative AI to provide repair procedures and aftercare advice, such as recommending the use of epoxy resin and a UV lamp for the detected cracks.

[0485] Example prompt sentence:

[0486] "Image data: capture1.jpg, Weather data: Sunny, 24.5°C, Humidity 60%, Analysis result: Crack detected (coordinates: x=123, y=456), Repair advice: Use epoxy resin."

[0487] This system will improve the efficiency of maintenance work for solar power generation equipment in factories, enabling quick and accurate responses. By utilizing generative AI, the system is characterized by improved accuracy in identifying abnormalities and reliability of repair advice.

[0488] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0489] Step 1:

[0490] The server activates drones and fixed cameras installed at the solar power generation facility and collects image data. Control commands for the facility's cameras and drones are given as input. Specifically, the server sends flight commands to the drones to take photos of the solar panels. The output is high-resolution image data.

[0491] Step 2:

[0492] The server retrieves weather data using an external weather API. As input, it is given the API endpoint URL and any necessary authentication information. Using these, the server sends a request to the API server to retrieve current weather information (e.g., temperature, humidity, solar radiation, etc.). The output is weather data in JSON format.

[0493] Step 3:

[0494] The server integrates the image data and meteorological data and assigns a timestamp to each piece of data. The input is the image data and meteorological data obtained in steps 1 and 2. Specifically, the server combines these pieces of data into a single data package and adds the current date and time information. The output is a data package with a timestamp.

[0495] Step 4:

[0496] The server inputs the integrated data package into a generative AI model (e.g., YOLOv5) to analyze anomalies. The input is a time-stamped data package, and data processing involves image analysis to detect anomalies (e.g., cracks or stains) in the image. The generative AI model identifies the coordinates and type of anomalies and outputs the results. The output is the analysis result of the anomalies.

[0497] Step 5:

[0498] The server generates a detailed report based on the analysis results. The inputs are the analysis results obtained in step 4 and time-stamped weather data. Specifically, the server compiles the analysis results into a text report, listing the location, type, and severity of any anomalies. The output is a detailed report.

[0499] Step 6:

[0500] The server uses generative AI to generate repair and aftercare advice based on the analysis results. The input is the detailed report generated in step 5. Specifically, the server generates advice that lists appropriate repair methods and tools to be used based on the anomaly information in the report. The output is repair and aftercare advice.

[0501] Step 7:

[0502] The server sends the generated report and advice to the user's information device (e.g., a smartphone or PC). The input is the report and advice generated in step 6. Specifically, the server transfers this information to the user's device via email or a dedicated app. The output is the report and advice displayed on the user's device.

[0503] Step 8:

[0504] The user checks the report and advice received from the information terminal and carries out the necessary repair work. The input is the report and advice sent in step 7. In concrete terms, the user repairs the abnormal part using appropriate tools and materials based on the advice provided. The output is the repaired solar power generation equipment.

[0505] 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.

[0506] This invention is a system for streamlining the maintenance of home and small-scale solar power generation facilities. This system collects image data and weather information from the solar power generation facility and identifies abnormalities by analyzing the data using generative AI. In addition, by combining it with an emotion engine, the system recognizes the user's emotions and provides appropriate repair and aftercare advice.

[0507] Data collection

[0508] The server periodically collects image data from drones and fixed cameras installed in homes and small-scale solar power generation facilities. It also collects meteorological data using sensors and APIs to obtain meteorological information. The collected image data and meteorological data are time-stamped and integrated into a single data package.

[0509] Data analysis with generative AI

[0510] The server inputs the collected data package into a generative AI model, which analyzes the image data. The generative AI model uses deep learning to identify abnormalities on the surface and inside of the solar panel. The analysis results include the location, type, and severity of the abnormality.

[0511] Reporting and Advice

[0512] The server generates a detailed report based on the analysis results. This report includes timestamps, weather information, and details of abnormalities. This report is provided to the user, who can view it from their PC, smartphone, or other device.

[0513] Additionally, the server uses generative AI to generate specific repair and aftercare advice, such as how to fix an abnormality or a list of tools to use.

[0514] Recognizing user emotions with an emotion engine

[0515] The server also uses an emotion engine to recognize the user's emotions. This emotion engine identifies the user's current emotional state by analyzing the user's voice data, facial expression data, and operation history. For example, if the user is feeling anxious or stressed, the server can provide enhanced advice and support that takes those emotions into account.

[0516] Specific examples

[0517] A specific example of an actual maintenance operation using the system of the present invention will be described below.

[0518] 1. The server will start the drone and camera system at 10:00 AM every day to collect images of the solar panels and simultaneously acquire weather data.

[0519] Example: Obtain high-resolution image data from the camera system installed in "panel123" and obtain the current day's weather information from the weather API.

[0520] 2. The collected data is time-stamped, consolidated, and stored as a data package.

[0521] Example: Image data is combined with a timestamp of "2023-10-01 10:00:00" and collected weather data.

[0522] 3. The server inputs the collected data into the generative AI model, which analyzes the image data. The generative AI model identifies abnormalities in the image and returns that information as the analysis result.

[0523] Example: A generative AI model detects a crack at specific coordinates in an image and provides detailed information about it.

[0524] 4. The server generates a report based on the analysis results, including the coordinates of the anomaly, the details of the detection, and weather conditions.

[0525] Example: A report will be generated containing weather data for "2023-10-01 10:00:00" and detailed information on detected cracks.

[0526] 5. The server uses generative AI to provide repair procedures and aftercare advice.

[0527] For example, for detected cracks, an advice is generated recommending the use of epoxy resin and a UV lamp.

[0528] 6. The server uses an emotion engine to recognize the user's emotions. For example, it analyzes the voice data when the user connects to the system and determines that the user is feeling anxious.

[0529] Example: Voice analysis detects when a user is speaking in an anxious tone.

[0530] 7. The server takes into account the emotional information obtained by the emotion engine and provides appropriate support enhancements, for example, providing detailed explanations or additional support contacts.

[0531] For example, provide a user who is concerned with the repair process with more detailed instructions or contact information for an expert.

[0532] 8. The user checks the report and repair advice on their PC or smartphone and carries out the necessary repairs. Based on the information obtained from the emotion engine, the user can proceed with the work with peace of mind.

[0533] Example: The user uses the advice provided to repair the crack using epoxy resin.

[0534] As described above, the system of the present invention can improve the efficiency of maintenance of photovoltaic power generation facilities and provide support that takes into consideration the emotions of users.

[0535] The processing flow will be explained below.

[0536] Step 1:

[0537] The server sets up a regular data collection schedule, for example, to launch a data collection task at 10:00 AM every day.

[0538] Step 2:

[0539] The terminal, a drone or fixed camera, is activated to collect image data of the solar panels, taking high-resolution images and saving them.

[0540] Step 3:

[0541] The server retrieves data from weather sensors or APIs to collect weather information, such as temperature, humidity, and weather (sunny, cloudy, rainy, etc.).

[0542] Step 4:

[0543] The server combines the collected image data with weather information and adds a timestamp to indicate when the data was obtained.

[0544] Step 5:

[0545] The server inputs the collected data package into the generative AI model, which then begins analyzing the image data.

[0546] Step 6:

[0547] The server uses the generated AI model to analyze the image data and detect abnormalities, such as cracks, dirt, or heat generation on the surface of a solar panel.

[0548] Step 7:

[0549] The server generates a detailed report based on the detected anomalies, including timestamps, weather information, the location and type of anomaly, and its severity.

[0550] Step 8:

[0551] The server uses the generative AI model to generate repair and aftercare advice. For example, if a crack is found, it will suggest specific steps to repair it and the tools to use.

[0552] Step 9:

[0553] The server uses an emotion engine to recognize the user's emotions, for example, by analyzing the user's voice data, facial expression data, and operation history to determine the user's current emotional state.

[0554] Step 10:

[0555] The server takes emotional information into account and, if the user feels anxious or stressed, enhances the advice and support according to the emotion, for example by providing detailed explanations or additional support contacts.

[0556] Step 11:

[0557] The server generates a report and sends advice to the user, who can then check the report from their PC or smartphone and take any necessary action.

[0558] Step 12:

[0559] The user can check the report provided by the server and carry out the necessary repairs and maintenance work, for example, repairing a crack using the suggested method, and proceed with the work with peace of mind using the additional support suggested by the emotion engine.

[0560] Example 2

[0561] 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."

[0562] In the inspection and maintenance of solar power generation facilities, it is extremely important to quickly and accurately detect abnormalities in the facilities and provide users with appropriate repair and aftercare advice. However, current systems require time and effort to collect and analyze data, and do not take user feelings into consideration, resulting in a lack of appropriate support.

[0563] 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 collecting image data, means for collecting weather information, means for integrating image data and weather information and assigning a timestamp, means for inputting the collected data into a generative AI model and analyzing abnormalities, means for identifying abnormalities and generating a detailed report based on the identified abnormalities, means for generating repair and aftercare advice based on the report, means for recognizing the user's emotional state, and means for providing additional support based on the recognized emotional state. This makes it possible to quickly and accurately detect abnormalities in the solar power generation equipment and provide the user with appropriate repair and aftercare advice. Furthermore, providing support that takes the user's emotions into consideration reduces the user's anxiety and stress, allowing the work to proceed smoothly.

[0564] "Means for collecting image data" refers to a device or system for acquiring image data from a photovoltaic power generation facility.

[0565] "Means for collecting weather information" refers to devices or systems for acquiring weather data in the surrounding environment of the solar power generation facility.

[0566] The "time stamping means" is a system for adding date and time information to collected image data and meteorological data.

[0567] A "generative artificial intelligence model" is a system that includes a deep learning model for analyzing collected data and automatically detecting abnormalities.

[0568] The "means for analyzing abnormal locations" refers to a method and system for identifying abnormal locations in a photovoltaic power generation facility using image data and meteorological data.

[0569] The "means for generating a detailed report" is a system for creating a report containing detailed information based on the identified abnormality.

[0570] The "means for generating repair and aftercare advice" is a system that uses a generative AI model to provide recommendations regarding repair methods and aftercare.

[0571] The "means for recognizing the user's emotional state" is a technology for identifying the user's emotions by analyzing voice data, facial expression data, and operation history.

[0572] The "means for providing additional support" is a system that provides appropriate advice and support information based on the recognized emotional state of the user.

[0573] This invention is a system for improving the efficiency of inspection and maintenance of solar power generation facilities. This system collects image data and weather information, analyzes them using a generative AI model, identifies abnormalities, and provides appropriate repair and aftercare advice to users. It also has a function to recognize users' emotions and enhance support based on those emotions.

[0574] Data collection

[0575] The server periodically collects image data of the solar power generation facility using drones and fixed cameras. The drones are equipped with an automatic navigation system, and the fixed cameras use high-resolution cameras. Weather information is also collected using sensors and weather APIs. For example, the API can be used to obtain the current day's weather information, and sensors can be used to collect local weather data in real time.

[0576] Data package integration

[0577] The collected image data and meteorological data are each given a timestamp, which clarifies when each piece of data was collected. The server then integrates this data and stores it in a database as a single data package.

[0578] Data analysis with generative AI

[0579] The server inputs the integrated data package into a generative AI model, which uses a deep learning algorithm to analyze the image data and identify abnormalities in the solar panels. The generative AI model outputs the location, type, and severity of the abnormalities as analysis results.

[0580] Reporting and Advice

[0581] The server generates a detailed report based on the analysis results. This report includes timestamps, weather information, and details of any identified anomalies. The report is output in a format that is easy for users to understand and can be viewed on a PC or smartphone. Furthermore, the generative AI provides advice such as specific repair methods and a list of tools to use.

[0582] Recognizing user emotions with an emotion engine

[0583] The server recognizes the user's emotional state using an emotion engine, which analyzes the user's voice data, facial expression data, and operation history to determine whether the user is feeling anxious or stressed.

[0584] Providing enhanced support

[0585] The server provides detailed instructions and additional support contact information based on the user's emotional state, allowing the user to proceed with the task without anxiety. For example, if the server analyzes the voice data when the user connects to the system and determines that the user is feeling anxious, it provides detailed repair guides and contact information for experts.

[0586] Specific examples

[0587] Here is a concrete example:

[0588] 1. The server starts the drone and camera system at 10:00 AM every day to collect images of the solar panels and retrieves the day's weather information from the weather API.

[0589] Example: High-resolution image data is acquired from a camera system installed on "panel123."

[0590] 2. The collected data is given a timestamp "2023-10-01 10:00:00", consolidated, and saved as a data package.

[0591] Example: Integrating image data with meteorological data.

[0592] 3. The server inputs the data package into a generative AI model and analyzes the image data.

[0593] Example: A generative AI model detects a crack at coordinates (50,100) in an image.

[0594] 4. Generate a report based on the analysis results and provide it to the user.

[0595] Example: The report will show the anomaly location as "(50,100): Crack".

[0596] 5. The server uses generative AI to provide specific repair and aftercare advice.

[0597] For example: We recommend using epoxy resin and a UV lamp.

[0598] 6. The server uses an emotion engine to detect anxiety from the user's voice data.

[0599] Example: Analyzing anxious tone.

[0600] 7. Provide users with additional support information to expedite their work.

[0601] Example: Detailed repair guides.

[0602] As described above, the present invention improves the efficiency of maintenance of photovoltaic power generation facilities and provides support that takes into account the emotions of users.

[0603] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0604] Step 1:

[0605] The server activates the drone and fixed camera to collect image data of the solar power plant. The drone is equipped with an automatic navigation system and flies automatically to specified coordinates. The fixed camera uses a high-resolution camera system to capture images at specific times. The input is the operation time and coordinates of the drone and camera system, and the output is the collected high-resolution image file.

[0606] Example: At 10:00 AM, the drone and camera will start up and collect high-resolution image "image_20231001.png" from "panel123."

[0607] Step 2:

[0608] The server collects weather data via weather sensors and weather APIs. The weather sensors measure local temperature, humidity, wind speed, etc. in real time, and obtains the day's weather information from the API. The input is real-time data from the weather sensors and API requests, and the output is a weather information dataset.

[0609] Example: Collect real-time data from weather sensors and weather information obtained from a weather API.

[0610] Step 3:

[0611] The server assigns a timestamp to the collected image data and meteorological data, and integrates them to create a data package. The timestamp indicates the collection time and is used to maintain data consistency. The input is image data and meteorological data, and the output is the integrated data package.

[0612] Example: Create a data package by adding the timestamp "2023-10-01 10:00:00" to the image data "image_20231001.png" and weather data.

[0613] Step 4:

[0614] The server inputs the data package into a generative AI model that analyzes the image data. The generative AI model uses a deep learning algorithm to identify abnormalities in the solar panels. The input is the data package, and the output is the analysis results, including the location, type, and severity of the abnormality.

[0615] Example: Input "data_package_20231001.json" into the AI ​​model and obtain the analysis result "Crack: Severity 2" at coordinates (50,100).

[0616] Step 5:

[0617] The server generates a detailed report based on the analysis results. The report includes timestamps, weather information, and details of identified anomalies, and is provided to the user. The input is the analysis results, and the output is the report.

[0618] Example: Generate a report with the timestamp "2023-10-01 10:00:00", weather data, and anomaly location "(50,100): Crack".

[0619] Step 6:

[0620] The server uses a generative AI model to generate specific advice on repairs and aftercare. The generated advice can be based on the user's skill level and previous repair history. The input is the analysis results and user information, and the output is repair and aftercare advice.

[0621] Example: Generate advice such as "Use epoxy resin and a UV lamp to repair the crack."

[0622] Step 7:

[0623] The server uses an emotion engine to recognize the user's emotional state. The emotion engine analyzes voice data, facial expression data, and operation history to identify the user's emotion. The input is the user's voice data and operation history, and the output is the user's emotional state.

[0624] Example: Determine that the user is feeling anxious based on voice data.

[0625] Step 8:

[0626] The server provides additional support based on the recognized emotional state, for example providing detailed explanations or contact information for experts to a user who is feeling anxious. The input is the user's emotional state, and the output is enhanced support information.

[0627] Example: Providing a detailed repair guide or expert contact information to a user who is concerned.

[0628] Step 9:

[0629] Users can check the report and repair advice from their PC or smartphone and carry out the necessary repair work. This allows them to proceed with the work accurately based on the information provided. The input is the report and advice, and the output is the repair work carried out by the user.

[0630] Example: Check the advice given by the PC and repair the crack using epoxy resin.

[0631] (Application example 2)

[0632] 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."

[0633] In the maintenance of machinery and equipment in factories, early detection of abnormalities and provision of appropriate repair methods are key challenges. Conventional systems take time to identify abnormalities and do not provide support that takes into account the emotional state of the worker, which can reduce the efficiency of maintenance work. This can lead to problems such as increased equipment downtime and reduced productivity. The objective of this invention is to improve the efficiency of factory equipment maintenance, provide early detection of abnormalities, provide appropriate repair methods, and provide support that takes into account the user's emotions.

[0634] 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 collecting image data from factory equipment, means for collecting environmental information, means for integrating the image data and environmental information and assigning a timestamp, means for inputting the collected data into a generative artificial intelligence model and analyzing abnormalities, means for identifying abnormalities and generating a detailed report based on the identified abnormalities, means for generating repair and aftercare advice based on the report, and means for recognizing the user's emotions using an emotion engine and providing appropriate support. This not only enables early detection of abnormalities and appropriate provision of repair methods during factory equipment maintenance, but also enables support that takes into account the emotional state of workers, thereby improving the efficiency and productivity of maintenance work.

[0635] "Image data" refers to visual information captured by devices such as cameras and drones.

[0636] "Weather information" refers to environmental data such as the weather, temperature, humidity, and wind speed at a specific location.

[0637] A "timestamp" is information that indicates the date and time when data was collected or generated.

[0638] A "generative artificial intelligence model" is a computer program that analyzes various data, identifies abnormalities, and generates advice.

[0639] An "abnormal part" refers to a part of machinery or solar power generation equipment that deviates from normal operation or condition.

[0640] "Report" means a detailed report generated based on collected and analyzed data.

[0641] "Repair and aftercare advice" means instructions or recommendations regarding how to repair and follow-up care for identified anomalies.

[0642] The "emotion engine" is an artificial intelligence system that identifies a user's emotional state by analyzing the user's voice data and facial expression data.

[0643] "Means for recognizing user emotions" refers to a method or device that uses an emotion engine to analyze the user's emotional state and provide appropriate support.

[0644] "Appropriate support" refers to assistance measures such as providing more detailed explanations or contact information for experts depending on the user's emotional state.

[0645] This invention is a system for improving the efficiency of maintenance of machinery and equipment in factories. This system collects image data and environmental information, analyzes them using a generative AI model, identifies abnormalities, and provides repair methods. Furthermore, it is possible to recognize the user's emotions using an emotion engine and provide appropriate support.

[0646] Data collection

[0647] The server periodically collects image data from drones and fixed cameras in the factory. It also collects environmental data using sensors and APIs to obtain environmental information such as temperature and humidity. The collected image data and environmental data are time-stamped and integrated into a single data package.

[0648] Data analysis with generative AI

[0649] The server inputs the collected data packages into a generative AI model, which analyzes the image data. The generative AI model uses deep learning to identify abnormalities on the surface or inside the machinery. The analysis results include the location, type, and severity of the abnormalities.

[0650] Reporting and Advice

[0651] The server generates a detailed report based on the analysis results. This report includes a timestamp, environmental information, and details of the abnormality. This report is provided to the user, who can view it from a PC, smartphone, or other device. In addition, the server uses generative AI to generate specific advice on repairs and aftercare, such as how to repair the abnormality and a list of tools that should be used.

[0652] Recognizing user emotions with an emotion engine

[0653] The server uses an emotion engine to recognize the user's emotions. This emotion engine identifies the user's current emotional state by analyzing the user's voice data and facial expression data. For example, if the user is feeling anxious or stressed, the server will provide enhanced advice and support that takes those emotions into account.

[0654] Specific examples

[0655] A specific example of an actual maintenance operation using the system of the present invention will be described below.

[0656] 1. The server activates the drones and camera system at 10:00 AM every day to collect images of the factory machinery and environmental data.

[0657] 2. The collected data is time-stamped, consolidated, and stored as a data package.

[0658] 3. The server inputs the collected data into the generative AI model, which analyzes the image data. The generative AI model identifies abnormalities in the image and returns that information as the analysis result.

[0659] 4. The server generates a report based on the analysis results, including the coordinates of the anomaly, the details of the detection, and the environmental conditions.

[0660] 5. The server uses generative AI to provide repair procedures and aftercare advice.

[0661] 6. The server uses an emotion engine to recognize the user's emotions. For example, it analyzes the voice data when the user connects to the system and determines that the user is feeling anxious.

[0662] 7. The server considers the emotional information obtained by the emotion engine and reinforces appropriate support.

[0663] Prompt Sentence Examples

[0664] Below is an example of a prompt sentence to be input to a generative AI model. This prompt sentence shows how the collected data should be input to the generative AI model:

[0665] Image data and environmental data are integrated and input into a generative AI model. The analysis results include the location, type, and severity of anomalies.

[0666] As described above, the system of the present invention can improve the efficiency of maintenance of factory machinery and equipment and provide support that takes into account the emotions of users.

[0667] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0668] Step 1:

[0669] The server periodically collects image data from drones and fixed cameras in the factory. The drones and fixed cameras acquire high-resolution image data and send it to the server. The input is image data of the machinery and equipment in the factory, and the output is image data stored on the server.

[0670] Step 2:

[0671] The server uses sensors and APIs to obtain environmental information such as temperature and humidity. The environmental data obtained from the sensors includes various data such as temperature, humidity, and wind speed. The same data can also be obtained using APIs. The input is environmental data from the sensors and APIs, and the output is environmental data stored on the server.

[0672] Step 3:

[0673] The server assigns a timestamp to the collected image data and environmental data and creates an integrated data package. The timestamp indicates the date and time the data was collected or generated, and all data is integrated. This process creates a data package in which the date, time, and environmental conditions are clearly associated. The input is image data and environmental data, and the output is an integrated data package.

[0674] Step 4:

[0675] The server inputs the integrated data package into a generative AI model that analyzes the image data. The generative AI model uses deep learning to identify anomalies within the image. The input to the AI ​​model is the integrated data package, and the output is an analysis result that indicates the location, type, and severity of the anomaly.

[0676] Step 5:

[0677] The server generates a detailed report based on the analysis results obtained from the generative AI model. This report includes a timestamp, environmental information, and details of the anomaly. The report is automatically generated and saved for later viewing by the user. The input is the analysis results and environmental data, and the output is a report file.

[0678] Step 6:

[0679] The server uses generative AI to generate repair procedures and aftercare advice for the abnormal area. For example, if the abnormal area is a crack, it will provide advice on using epoxy resin and a UV lamp. The input is the analysis results, and the output is repair and aftercare advice.

[0680] Step 7:

[0681] The server uses an emotion engine to recognize the user's emotions. When the user connects to the system, the server analyzes the voice and facial expression data as input and identifies the user's emotional state. The input is the voice and facial expression data, and the output is the evaluation result of the user's emotional state.

[0682] Step 8:

[0683] The server takes into account the emotional information provided by the emotion engine and provides appropriate support to the user. For example, if the user feels anxious, the server will enhance the support content by providing a detailed explanation or contact information for an expert. The input is the evaluation result of the emotional state, and the output is the enhanced support content.

[0684] 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.

[0685] 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.

[0686] 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.

[0687] [Third embodiment]

[0688] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0689] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0690] 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).

[0691] 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.

[0692] 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.

[0693] 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).

[0694] 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.

[0695] 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.

[0696] 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.

[0697] 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.

[0698] 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.

[0699] 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."

[0700] This invention is a system that automates and streamlines the maintenance of home and small-scale solar power generation facilities. The system collects image data and weather information from the solar power generation facility, analyzes this data using generative AI to identify abnormalities, and provides detailed reports and aftercare advice.

[0701] Data collection

[0702] The server periodically collects image data from drones and fixed cameras installed in homes and small-scale solar power generation facilities. It also collects meteorological data using sensors and APIs to obtain meteorological information. The collected image data and meteorological data are time-stamped and integrated into a single data package.

[0703] Data analysis with generative AI

[0704] The server inputs the collected data package into a generative AI model, which analyzes the image data. The generative AI model uses deep learning to identify abnormalities (e.g., cracks, dirt, and heat generation areas) on the surface and inside of the solar panel. The analysis results include the location, type, and severity of the abnormalities.

[0705] Reporting and Advice

[0706] The server generates a detailed report based on the analysis results. This report includes timestamps, weather information, and details of abnormalities. This report is provided to the user, who can view it from their PC, smartphone, or other device.

[0707] Additionally, the server uses generative AI to generate specific repair and aftercare advice, such as how to fix an abnormality or a list of tools to use.

[0708] Specific examples

[0709] A specific example of an actual maintenance operation using the system of the present invention will be described below.

[0710] 1. The server will start the drone and camera system at 10:00 AM every day to collect images of the solar panels and simultaneously acquire weather data.

[0711] Example: Obtain high-resolution image data from the camera system installed in "panel123" and obtain the current day's weather information from the weather API.

[0712] 2. The collected data is time-stamped, consolidated, and stored as a data package.

[0713] Example: Image data is combined with a timestamp of "2023-10-01 10:00:00" and collected weather data.

[0714] 3. The server inputs the collected data into the generative AI model, which analyzes the image data. The generative AI model identifies abnormalities in the image and returns that information as the analysis result.

[0715] Example: A generative AI model detects a crack at specific coordinates in an image and provides detailed information about it.

[0716] 4. The server generates a report based on the analysis results, including the coordinates of the anomaly, the details of the detection, and weather conditions.

[0717] Example: A report will be generated containing weather data for "2023-10-01 10:00:00" and detailed information on detected cracks.

[0718] 5. The server uses generative AI to provide repair procedures and aftercare advice.

[0719] For example, for detected cracks, an advice is generated recommending the use of epoxy resin and a UV lamp.

[0720] 6. The user checks the report and repair advice on their PC or smartphone and carries out the necessary repair work.

[0721] Example: The user uses the advice provided to repair the crack using epoxy resin.

[0722] As described above, the system of the present invention makes it possible to improve the efficiency of maintenance work for homes and small-scale solar power generation facilities, and to respond quickly and accurately. In addition, the use of generative AI improves the accuracy of identifying abnormalities and the reliability of repair advice.

[0723] The processing flow will be explained below.

[0724] Step 1:

[0725] The server sets up a regular data collection schedule, for example, to launch a data collection task at 10:00 AM every day.

[0726] Step 2:

[0727] The terminal, a drone or fixed camera, is activated to collect image data of the solar panels, taking high-resolution images and saving them.

[0728] Step 3:

[0729] The server retrieves data from weather sensors or APIs to collect weather information, such as temperature, humidity, and weather (sunny, cloudy, rainy, etc.).

[0730] Step 4:

[0731] The server combines the collected image data with weather information and adds a timestamp to indicate when the data was obtained.

[0732] Step 5:

[0733] The server inputs the collected data package into the generative AI model, which then begins analyzing the image data.

[0734] Step 6:

[0735] The server uses the generated AI model to analyze the image data and detect abnormalities, such as cracks, dirt, or heat generation on the surface of a solar panel.

[0736] Step 7:

[0737] The server generates a detailed report based on the detected anomalies, including timestamps, weather information, the location and type of anomaly, and its severity.

[0738] Step 8:

[0739] The server uses the generative AI model to generate repair and aftercare advice. For example, if a crack is found, it will suggest specific steps to repair it and the tools to use.

[0740] Step 9:

[0741] The server generates a report and sends advice to the user, who can then check the report from their PC or smartphone and take any necessary action.

[0742] Step 10:

[0743] The user checks the report provided by the server and performs any necessary repairs or maintenance work, for example, repairing a crack using the suggested method.

[0744] Example 1

[0745] 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."

[0746] Existing inspection and maintenance methods for solar power generation facilities require manual inspection work, which is inefficient and limits the accuracy of identifying and repairing abnormalities. Furthermore, weather and time constraints can make periodic inspections difficult and costly. This results in problems such as a long time before abnormalities are discovered, a decrease in power generation efficiency, and an increased risk of equipment failure.

[0747] 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.

[0748] In this invention, the server includes means for collecting image data from the solar power generation facility using drones and fixed cameras, means for collecting weather information using a weather API or sensors, means for integrating the image data and weather information and attaching a timestamp, means for inputting the collected data package into a generative AI model and analyzing abnormalities, means for generating a detailed report based on the location, type, and severity of the detected abnormalities, and means for generating repair and aftercare advice based on the report using the generative AI model, thereby automating and streamlining the inspection and maintenance process, enabling rapid and accurate identification of abnormalities and appropriate repairs.

[0749] A "drone" is an unmanned aerial vehicle that can be remotely controlled or flown autonomously to collect images and data of a designated area.

[0750] A "fixed camera" is a device that is installed at a specific location and periodically or continuously records still images of a designated object or area.

[0751] A "weather API" is an application programming interface for obtaining weather information via the Internet.

[0752] A "sensor" is a device that detects and measures environmental data such as temperature, humidity, and wind speed, and outputs it as an electrical signal.

[0753] A "timestamp" is data that is used to assign the exact date and time when image data and weather information were recorded or collected.

[0754] A "data package" is a single information unit that integrates image data and meteorological information together with a timestamp.

[0755] A "generative AI model" is an artificial intelligence program that uses deep learning to analyze input data and automatically perform specific tasks (e.g., anomaly detection, report generation, advice provision).

[0756] "Abnormal part" refers to a defective or problematic part of a solar power generation facility that affects its normal operation or performance.

[0757] A "detailed report" is a document generated by the server that includes a timestamp, meteorological information, and analysis results such as the location, type, and severity of anomalies.

[0758] "Repair and aftercare advice" is information that includes specific suggestions on appropriate repair methods, tools to be used, or preventive measures for detected abnormalities.

[0759] This invention is a system for automating and streamlining the inspection and maintenance of solar power generation facilities. The system collects image data of solar panels using drones or fixed cameras, and obtains weather information using weather APIs or sensors. These data are time-stamped, integrated, and processed as a data package. The collected data package is input into a generative AI model, which analyzes abnormalities. A detailed report is generated based on the analysis results, and the generative AI model is used to provide repair and aftercare advice.

[0760] The server collects image data using drones and fixed cameras installed at the solar power generation facilities. The drones take pictures by remote control or autonomous flight, and the fixed cameras capture still images from specific positions, resulting in high-resolution image data.

[0761] To obtain weather information, weather APIs or environmental sensors are used. Weather APIs are application programming interfaces that provide the latest weather information via the Internet, while environmental sensors are devices that collect weather data directly from the local area.

[0762] The system's server timestamps the collected image data and weather information and combines them into a single data package. The data package is stored in a database and input into a generative AI model for analysis. The generative AI model uses deep learning to preprocess the image data (color correction and noise removal), then detects anomalies. The generative AI model analyzes the location, type, and severity of anomalies and returns the analysis results.

[0763] Based on the analysis results, the server generates a detailed report that includes timestamps, weather information, the location and type of abnormality, and its severity. Furthermore, the server uses a generative AI model to generate repair and aftercare advice based on the report, providing users with information on specific repair procedures and tools to use.

[0764] As a specific example, the server activates a drone at a specified time every morning (for example, 10:00 AM) to collect images of solar panels. A fixed camera also operates at the same time to take still images. At this time, the server sends a request to a weather API to obtain the day's weather information. The collected image data and weather information are integrated with a timestamp and stored in a database. The generative AI model receives this data package as input and detects and analyzes abnormalities. The analysis results are generated as a detailed report including the location, type, and severity of the abnormality. The server generates repair and after-care advice based on this report and provides it to the user. Users can view these reports and advice via their PC or smartphone and carry out appropriate repair work.

[0765] An example of a prompt is:

[0766] "High-resolution image data is acquired from the camera system installed on panel 123, and the weather information for the day is obtained from the weather API."

[0767] "The image data is combined with the timestamp 2023-10-01 10:00:00 and the collected meteorological data."

[0768] "The generative AI model detects cracks at specific coordinates in the image and provides detailed information about them."

[0769] Examples include:

[0770] As a result, using this system will improve the efficiency of maintenance work for solar power generation facilities and enable quick and accurate responses. In particular, the use of a generative AI model is a distinctive feature of this invention, as it improves the accuracy of identifying abnormalities and the reliability of repair advice.

[0771] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0772] Step 1:

[0773] The server starts up the drone and camera system at a specified time every morning (e.g., 10:00 AM) and collects image data of the solar panels. The input is image data from the drone and fixed camera, and the output is high-resolution still image data. Specifically, the server calls the drone's API and sends a flight plan.

[0774] Step 2:

[0775] The server uses the weather API or environmental sensors to obtain the weather information for the day. The input is a request from the weather API and data from the environmental sensors, and the output is weather information such as temperature, humidity, and wind speed. Specifically, the server uses the OpenWeatherMap API to obtain weather information for "Tokyo."

[0776] Step 3:

[0777] The server assigns a timestamp to the collected image data and weather information and integrates them into a single data package. The input is image data and weather information, and the output is a time-stamped data package. Specifically, the image data and weather data with a timestamp of "2023-10-01 10:00:00" are integrated into a single JSON file.

[0778] Step 4:

[0779] The server inputs the data package into the generative AI model and analyzes the anomaly. The input is a time-stamped data package, and the output is an analysis result of the location, type, and severity of the anomaly. Specifically, the server converts the image data into input tensors for the generative AI model and performs analysis using deep learning.

[0780] Step 5:

[0781] The generative AI model performs color correction and noise reduction as preprocessing of image data. The input is image data, and the output is cleaned-up image data. Specifically, the generative AI model applies a Gaussian filter to reduce noise in the image.

[0782] Step 6:

[0783] The generative AI model analyzes the preprocessed image data and detects anomalies (e.g., cracks, stains, and hot spots). The input is the cleaned-up image data, and the output is detailed information about the anomalies. Specifically, the generative AI model detects a crack at a specific coordinate in the image (e.g., (150, 200)) and reports it as "Crack, Severity 3 / 5."

[0784] Step 7:

[0785] The server generates a detailed report based on the analysis results. The input is the analysis results from the generative AI model, and the output is a detailed report including the location, type, and severity of the anomaly. Specifically, the server generates a PDF report including a timestamp, weather information, and information about the detected anomaly.

[0786] Step 8:

[0787] The server uses a generative AI model to generate repair and aftercare advice based on the report. The input is a detailed report, and the output is advice including specific repair procedures and a list of tools to use. Specifically, the generative AI model generates advice in text form, such as "For the detected cracks, we recommend using epoxy resin and a UV lamp."

[0788] Step 9:

[0789] The server sends the generated report and advice to the user's device. The input is a detailed report and advice, and the output is data sent to the user's PC or smartphone. Specifically, the server sends a PDF report and advice in text format to the user's email address.

[0790] Step 10:

[0791] The user checks the report and repair advice via a PC or smartphone and carries out the necessary repair work. The input is the report and advice sent from the server, and the output is the actual repair work. In concrete terms, the user repairs the cracked area using epoxy resin based on the advice provided.

[0792] As described above, by implementing this system, maintenance work for solar power generation facilities can be automated, enabling prompt and accurate responses.

[0793] (Application example 1)

[0794] 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."

[0795] Inspection and maintenance of solar power generation facilities often requires manual checking, which is time-consuming and costly. It is also difficult for users without specialized knowledge to perform maintenance properly. Furthermore, delays in identifying abnormalities can lead to reduced power generation efficiency and serious breakdowns. There is a need for a system that can address these issues quickly and accurately by automating and streamlining the process.

[0796] 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.

[0797] In this invention, the server includes means for collecting image data from the solar power generation facility, means for collecting weather information, means for integrating the image data and weather information and assigning a timestamp, means for inputting the collected data into a generative artificial intelligence model and analyzing abnormalities, means for identifying abnormalities and generating a detailed report based on the identified abnormalities, means for generating repair and aftercare advice based on the report, means for transmitting the report and advice to a user's information terminal, and a mobile machine that autonomously patrols the solar power generation facility within the industrial facility and collects data. This makes it possible to automate and streamline inspection and maintenance of the solar power generation facility.

[0798] A "photovoltaic power generation facility" is a system that includes devices and associated equipment for converting solar light energy into electrical energy.

[0799] "Means for collecting image data" refers to equipment and technology for photographing the condition of solar power generation facilities and saving them as digital images.

[0800] "Means of collecting weather information" refers to sensors and APIs for obtaining environmental data such as temperature, humidity, wind speed, and solar radiation.

[0801] "Means for adding a timestamp" refers to the technology and method for adding date and time information to data.

[0802] A "generative artificial intelligence model" refers to an algorithm or set of computational models that are trained to perform a specific task using machine learning or deep learning.

[0803] "Means for analyzing abnormalities" refers to technology that uses collected image data and weather information to detect and evaluate abnormalities and deterioration in solar power generation equipment.

[0804] "Means for generating a report" refers to the technology and method for creating a document based on the analysis results that details any anomalies and other important information.

[0805] "Means for generating repair and aftercare advice" refers to techniques and methods for generating advice and recommendations regarding necessary repair procedures and maintenance methods based on the results of the analysis.

[0806] "Means for sending to the user's information terminal" refers to communication technology for transferring the generated report or advice to a device such as a smartphone or computer used by the user.

[0807] "Mobile machines that autonomously patrol solar power generation facilities and collect data" refers to automated devices such as self-driving robots and drones that automatically patrol solar power generation facilities within factories and collect image data and weather information.

[0808] The present invention relates to a system for automating and streamlining the inspection and maintenance of solar power generation facilities. The system is intended for use in industrial facilities and autonomously patrols the facilities, identifies abnormalities, and generates reports and advice.

[0809] First, the server runs on the following hardware and software: Drones and fixed cameras are used to collect image data, and API-enabled weather sensors are used to collect weather information. A generative AI model such as YOLOv5 is used for data analysis. This model uses deep learning to identify anomalies in the images.

[0810] The server periodically collects image data from drones and fixed cameras, and simultaneously retrieves weather data from weather sensors and APIs. These data are time-stamped and integrated. This integrated data package is then fed into a generative AI model to identify anomalies.

[0811] The analysis results include the location, type, and severity of the anomaly. The server generates a detailed report based on the analysis results, including a timestamp, weather information, and details of the anomaly. This report is sent to the user's information terminal and can be viewed from a PC or smartphone. The server also uses generative AI to provide repair and aftercare advice, such as how to repair the anomaly and a list of tools that should be used.

[0812] In a specific example, the server launches a drone inside the factory at 10:00 AM every day to collect images of the solar panels. At the same time, it obtains the day's weather information from an external weather API. The collected data is integrated with a timestamp such as "2023-10-01 10:00:00" and input into a generative AI model (e.g., YOLOv5). This model detects cracks at specific coordinates in the image and provides detailed information about them.

[0813] The generated report includes weather data for 2023-10-01 10:00:00 and detailed information about the detected cracks. The server also uses the generative AI to provide repair procedures and aftercare advice, such as recommending the use of epoxy resin and a UV lamp for the detected cracks.

[0814] Example prompt sentence:

[0815] "Image data: capture1.jpg, Weather data: Sunny, 24.5°C, Humidity 60%, Analysis result: Crack detected (coordinates: x=123, y=456), Repair advice: Use epoxy resin."

[0816] This system will improve the efficiency of maintenance work for solar power generation equipment in factories, enabling quick and accurate responses. By utilizing generative AI, the system is characterized by improved accuracy in identifying abnormalities and reliability of repair advice.

[0817] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0818] Step 1:

[0819] The server activates drones and fixed cameras installed at the solar power generation facility and collects image data. Control commands for the facility's cameras and drones are given as input. Specifically, the server sends flight commands to the drones to take photos of the solar panels. The output is high-resolution image data.

[0820] Step 2:

[0821] The server retrieves weather data using an external weather API. As input, it is given the API endpoint URL and any necessary authentication information. Using these, the server sends a request to the API server to retrieve current weather information (e.g., temperature, humidity, solar radiation, etc.). The output is weather data in JSON format.

[0822] Step 3:

[0823] The server integrates the image data and meteorological data and assigns a timestamp to each piece of data. The input is the image data and meteorological data obtained in steps 1 and 2. Specifically, the server combines these pieces of data into a single data package and adds the current date and time information. The output is a data package with a timestamp.

[0824] Step 4:

[0825] The server inputs the integrated data package into a generative AI model (e.g., YOLOv5) to analyze anomalies. The input is a time-stamped data package, and data processing involves image analysis to detect anomalies (e.g., cracks or stains) in the image. The generative AI model identifies the coordinates and type of anomalies and outputs the results. The output is the analysis result of the anomalies.

[0826] Step 5:

[0827] The server generates a detailed report based on the analysis results. The inputs are the analysis results obtained in step 4 and time-stamped weather data. Specifically, the server compiles the analysis results into a text report, listing the location, type, and severity of any anomalies. The output is a detailed report.

[0828] Step 6:

[0829] The server uses generative AI to generate repair and aftercare advice based on the analysis results. The input is the detailed report generated in step 5. Specifically, the server generates advice that lists appropriate repair methods and tools to be used based on the anomaly information in the report. The output is repair and aftercare advice.

[0830] Step 7:

[0831] The server sends the generated report and advice to the user's information device (e.g., a smartphone or PC). The input is the report and advice generated in step 6. Specifically, the server transfers this information to the user's device via email or a dedicated app. The output is the report and advice displayed on the user's device.

[0832] Step 8:

[0833] The user checks the report and advice received from the information terminal and carries out the necessary repair work. The input is the report and advice sent in step 7. In concrete terms, the user repairs the abnormal part using appropriate tools and materials based on the advice provided. The output is the repaired solar power generation equipment.

[0834] 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.

[0835] This invention is a system for streamlining the maintenance of home and small-scale solar power generation facilities. This system collects image data and weather information from the solar power generation facility and identifies abnormalities by analyzing the data using generative AI. In addition, by combining it with an emotion engine, the system recognizes the user's emotions and provides appropriate repair and aftercare advice.

[0836] Data collection

[0837] The server periodically collects image data from drones and fixed cameras installed in homes and small-scale solar power generation facilities. It also collects meteorological data using sensors and APIs to obtain meteorological information. The collected image data and meteorological data are time-stamped and integrated into a single data package.

[0838] Data analysis with generative AI

[0839] The server inputs the collected data package into a generative AI model, which analyzes the image data. The generative AI model uses deep learning to identify abnormalities on the surface and inside of the solar panel. The analysis results include the location, type, and severity of the abnormality.

[0840] Reporting and Advice

[0841] The server generates a detailed report based on the analysis results. This report includes timestamps, weather information, and details of abnormalities. This report is provided to the user, who can view it from their PC, smartphone, or other device.

[0842] Additionally, the server uses generative AI to generate specific repair and aftercare advice, such as how to fix an abnormality or a list of tools to use.

[0843] Recognizing user emotions with an emotion engine

[0844] The server also uses an emotion engine to recognize the user's emotions. This emotion engine identifies the user's current emotional state by analyzing the user's voice data, facial expression data, and operation history. For example, if the user is feeling anxious or stressed, the server can provide enhanced advice and support that takes those emotions into account.

[0845] Specific examples

[0846] A specific example of an actual maintenance operation using the system of the present invention will be described below.

[0847] 1. The server will start the drone and camera system at 10:00 AM every day to collect images of the solar panels and simultaneously acquire weather data.

[0848] Example: Obtain high-resolution image data from the camera system installed in "panel123" and obtain the current day's weather information from the weather API.

[0849] 2. The collected data is time-stamped, consolidated, and stored as a data package.

[0850] Example: Image data is combined with a timestamp of "2023-10-01 10:00:00" and collected weather data.

[0851] 3. The server inputs the collected data into the generative AI model, which analyzes the image data. The generative AI model identifies abnormalities in the image and returns that information as the analysis result.

[0852] Example: A generative AI model detects a crack at specific coordinates in an image and provides detailed information about it.

[0853] 4. The server generates a report based on the analysis results, including the coordinates of the anomaly, the details of the detection, and weather conditions.

[0854] Example: A report will be generated containing weather data for "2023-10-01 10:00:00" and detailed information on detected cracks.

[0855] 5. The server uses generative AI to provide repair procedures and aftercare advice.

[0856] For example, for detected cracks, an advice is generated recommending the use of epoxy resin and a UV lamp.

[0857] 6. The server uses an emotion engine to recognize the user's emotions. For example, it analyzes the voice data when the user connects to the system and determines that the user is feeling anxious.

[0858] Example: Voice analysis detects when a user is speaking in an anxious tone.

[0859] 7. The server takes into account the emotional information obtained by the emotion engine and provides appropriate support enhancements, for example, providing detailed explanations or additional support contacts.

[0860] For example, provide a user who is concerned with the repair process with more detailed instructions or contact information for an expert.

[0861] 8. The user checks the report and repair advice on their PC or smartphone and carries out the necessary repairs. Based on the information obtained from the emotion engine, the user can proceed with the work with peace of mind.

[0862] Example: The user uses the advice provided to repair the crack using epoxy resin.

[0863] As described above, the system of the present invention can improve the efficiency of maintenance of photovoltaic power generation facilities and provide support that takes into consideration the emotions of users.

[0864] The processing flow will be explained below.

[0865] Step 1:

[0866] The server sets up a regular data collection schedule, for example, to launch a data collection task at 10:00 AM every day.

[0867] Step 2:

[0868] The terminal, a drone or fixed camera, is activated to collect image data of the solar panels, taking high-resolution images and saving them.

[0869] Step 3:

[0870] The server retrieves data from weather sensors or APIs to collect weather information, such as temperature, humidity, and weather (sunny, cloudy, rainy, etc.).

[0871] Step 4:

[0872] The server combines the collected image data with weather information and adds a timestamp to indicate when the data was obtained.

[0873] Step 5:

[0874] The server inputs the collected data package into the generative AI model, which then begins analyzing the image data.

[0875] Step 6:

[0876] The server uses the generated AI model to analyze the image data and detect abnormalities, such as cracks, dirt, or heat generation on the surface of a solar panel.

[0877] Step 7:

[0878] The server generates a detailed report based on the detected anomalies, including timestamps, weather information, the location and type of anomaly, and its severity.

[0879] Step 8:

[0880] The server uses the generative AI model to generate repair and aftercare advice. For example, if a crack is found, it will suggest specific steps to repair it and the tools to use.

[0881] Step 9:

[0882] The server uses an emotion engine to recognize the user's emotions, for example, by analyzing the user's voice data, facial expression data, and operation history to determine the user's current emotional state.

[0883] Step 10:

[0884] The server takes emotional information into account and, if the user feels anxious or stressed, enhances the advice and support according to the emotion, for example by providing detailed explanations or additional support contacts.

[0885] Step 11:

[0886] The server generates a report and sends advice to the user, who can then check the report from their PC or smartphone and take any necessary action.

[0887] Step 12:

[0888] The user can check the report provided by the server and carry out the necessary repairs and maintenance work, for example, repairing a crack using the suggested method, and proceed with the work with peace of mind using the additional support suggested by the emotion engine.

[0889] Example 2

[0890] 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."

[0891] In the inspection and maintenance of solar power generation facilities, it is extremely important to quickly and accurately detect abnormalities in the facilities and provide users with appropriate repair and aftercare advice. However, current systems require time and effort to collect and analyze data, and do not take user feelings into consideration, resulting in a lack of appropriate support.

[0892] 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 collecting image data, means for collecting weather information, means for integrating image data and weather information and assigning a timestamp, means for inputting the collected data into a generative AI model and analyzing abnormalities, means for identifying abnormalities and generating a detailed report based on the identified abnormalities, means for generating repair and aftercare advice based on the report, means for recognizing the user's emotional state, and means for providing additional support based on the recognized emotional state. This makes it possible to quickly and accurately detect abnormalities in the solar power generation equipment and provide the user with appropriate repair and aftercare advice. Furthermore, providing support that takes the user's emotions into consideration reduces the user's anxiety and stress, allowing the work to proceed smoothly.

[0893] "Means for collecting image data" refers to a device or system for acquiring image data from a photovoltaic power generation facility.

[0894] "Means for collecting weather information" refers to devices or systems for acquiring weather data in the surrounding environment of the solar power generation facility.

[0895] The "time stamping means" is a system for adding date and time information to collected image data and meteorological data.

[0896] A "generative artificial intelligence model" is a system that includes a deep learning model for analyzing collected data and automatically detecting abnormalities.

[0897] The "means for analyzing abnormal locations" refers to a method and system for identifying abnormal locations in a photovoltaic power generation facility using image data and meteorological data.

[0898] The "means for generating a detailed report" is a system for creating a report containing detailed information based on the identified abnormality.

[0899] The "means for generating repair and aftercare advice" is a system that uses a generative AI model to provide recommendations regarding repair methods and aftercare.

[0900] The "means for recognizing the user's emotional state" is a technology for identifying the user's emotions by analyzing voice data, facial expression data, and operation history.

[0901] The "means for providing additional support" is a system that provides appropriate advice and support information based on the recognized emotional state of the user.

[0902] This invention is a system for improving the efficiency of inspection and maintenance of solar power generation facilities. This system collects image data and weather information, analyzes them using a generative AI model, identifies abnormalities, and provides appropriate repair and aftercare advice to users. It also has a function to recognize users' emotions and enhance support based on those emotions.

[0903] Data collection

[0904] The server periodically collects image data of the solar power generation facility using drones and fixed cameras. The drones are equipped with an automatic navigation system, and the fixed cameras use high-resolution cameras. Weather information is also collected using sensors and weather APIs. For example, the API can be used to obtain the current day's weather information, and sensors can be used to collect local weather data in real time.

[0905] Data package integration

[0906] The collected image data and meteorological data are each given a timestamp, which clarifies when each piece of data was collected. The server then integrates this data and stores it in a database as a single data package.

[0907] Data analysis with generative AI

[0908] The server inputs the integrated data package into a generative AI model, which uses a deep learning algorithm to analyze the image data and identify abnormalities in the solar panels. The generative AI model outputs the location, type, and severity of the abnormalities as analysis results.

[0909] Reporting and Advice

[0910] The server generates a detailed report based on the analysis results. This report includes timestamps, weather information, and details of any identified anomalies. The report is output in a format that is easy for users to understand and can be viewed on a PC or smartphone. Furthermore, the generative AI provides advice such as specific repair methods and a list of tools to use.

[0911] Recognizing user emotions with an emotion engine

[0912] The server recognizes the user's emotional state using an emotion engine, which analyzes the user's voice data, facial expression data, and operation history to determine whether the user is feeling anxious or stressed.

[0913] Providing enhanced support

[0914] The server provides detailed instructions and additional support contact information based on the user's emotional state, allowing the user to proceed with the task without anxiety. For example, if the server analyzes the voice data when the user connects to the system and determines that the user is feeling anxious, it provides detailed repair guides and contact information for experts.

[0915] Specific examples

[0916] Here is a concrete example:

[0917] 1. The server starts the drone and camera system at 10:00 AM every day to collect images of the solar panels and retrieves the day's weather information from the weather API.

[0918] Example: High-resolution image data is acquired from a camera system installed on "panel123."

[0919] 2. The collected data is given a timestamp "2023-10-01 10:00:00", consolidated, and saved as a data package.

[0920] Example: Integrating image data with meteorological data.

[0921] 3. The server inputs the data package into a generative AI model and analyzes the image data.

[0922] Example: A generative AI model detects a crack at coordinates (50,100) in an image.

[0923] 4. Generate a report based on the analysis results and provide it to the user.

[0924] Example: The report will show the anomaly location as "(50,100): Crack".

[0925] 5. The server uses generative AI to provide specific repair and aftercare advice.

[0926] For example: We recommend using epoxy resin and a UV lamp.

[0927] 6. The server uses an emotion engine to detect anxiety from the user's voice data.

[0928] Example: Analyzing anxious tone.

[0929] 7. Provide users with additional support information to expedite their work.

[0930] Example: Detailed repair guides.

[0931] As described above, the present invention improves the efficiency of maintenance of photovoltaic power generation facilities and provides support that takes into account the emotions of users.

[0932] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0933] Step 1:

[0934] The server activates the drone and fixed camera to collect image data of the solar power plant. The drone is equipped with an automatic navigation system and flies automatically to specified coordinates. The fixed camera uses a high-resolution camera system to capture images at specific times. The input is the operation time and coordinates of the drone and camera system, and the output is the collected high-resolution image file.

[0935] Example: At 10:00 AM, the drone and camera will start up and collect high-resolution image "image_20231001.png" from "panel123."

[0936] Step 2:

[0937] The server collects weather data via weather sensors and weather APIs. The weather sensors measure local temperature, humidity, wind speed, etc. in real time, and obtains the day's weather information from the API. The input is real-time data from the weather sensors and API requests, and the output is a weather information dataset.

[0938] Example: Collect real-time data from weather sensors and weather information obtained from a weather API.

[0939] Step 3:

[0940] The server assigns a timestamp to the collected image data and meteorological data, and integrates them to create a data package. The timestamp indicates the collection time and is used to maintain data consistency. The input is image data and meteorological data, and the output is the integrated data package.

[0941] Example: Create a data package by adding the timestamp "2023-10-01 10:00:00" to the image data "image_20231001.png" and weather data.

[0942] Step 4:

[0943] The server inputs the data package into a generative AI model that analyzes the image data. The generative AI model uses a deep learning algorithm to identify abnormalities in the solar panels. The input is the data package, and the output is the analysis results, including the location, type, and severity of the abnormality.

[0944] Example: Input "data_package_20231001.json" into the AI ​​model and obtain the analysis result "Crack: Severity 2" at coordinates (50,100).

[0945] Step 5:

[0946] The server generates a detailed report based on the analysis results. The report includes timestamps, weather information, and details of identified anomalies, and is provided to the user. The input is the analysis results, and the output is the report.

[0947] Example: Generate a report with the timestamp "2023-10-01 10:00:00", weather data, and anomaly location "(50,100): Crack".

[0948] Step 6:

[0949] The server uses a generative AI model to generate specific advice on repairs and aftercare. The generated advice can be based on the user's skill level and previous repair history. The input is the analysis results and user information, and the output is repair and aftercare advice.

[0950] Example: Generate advice such as "Use epoxy resin and a UV lamp to repair the crack."

[0951] Step 7:

[0952] The server uses an emotion engine to recognize the user's emotional state. The emotion engine analyzes voice data, facial expression data, and operation history to identify the user's emotion. The input is the user's voice data and operation history, and the output is the user's emotional state.

[0953] Example: Determine that the user is feeling anxious based on voice data.

[0954] Step 8:

[0955] The server provides additional support based on the recognized emotional state, for example providing detailed explanations or contact information for experts to a user who is feeling anxious. The input is the user's emotional state, and the output is enhanced support information.

[0956] Example: Providing a detailed repair guide or expert contact information to a user who is concerned.

[0957] Step 9:

[0958] Users can check the report and repair advice from their PC or smartphone and carry out the necessary repair work. This allows them to proceed with the work accurately based on the information provided. The input is the report and advice, and the output is the repair work carried out by the user.

[0959] Example: Check the advice given by the PC and repair the crack using epoxy resin.

[0960] (Application example 2)

[0961] 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."

[0962] In the maintenance of machinery and equipment in factories, early detection of abnormalities and provision of appropriate repair methods are key challenges. Conventional systems take time to identify abnormalities and do not provide support that takes into account the emotional state of the worker, which can reduce the efficiency of maintenance work. This can lead to problems such as increased equipment downtime and reduced productivity. The objective of this invention is to improve the efficiency of factory equipment maintenance, provide early detection of abnormalities, provide appropriate repair methods, and provide support that takes into account the user's emotions.

[0963] 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 collecting image data from factory equipment, means for collecting environmental information, means for integrating the image data and environmental information and assigning a timestamp, means for inputting the collected data into a generative artificial intelligence model and analyzing abnormalities, means for identifying abnormalities and generating a detailed report based on the identified abnormalities, means for generating repair and aftercare advice based on the report, and means for recognizing the user's emotions using an emotion engine and providing appropriate support. This not only enables early detection of abnormalities and appropriate provision of repair methods during factory equipment maintenance, but also enables support that takes into account the emotional state of workers, thereby improving the efficiency and productivity of maintenance work.

[0964] "Image data" refers to visual information captured by devices such as cameras and drones.

[0965] "Weather information" refers to environmental data such as the weather, temperature, humidity, and wind speed at a specific location.

[0966] A "timestamp" is information that indicates the date and time when data was collected or generated.

[0967] A "generative artificial intelligence model" is a computer program that analyzes various data, identifies abnormalities, and generates advice.

[0968] An "abnormal part" refers to a part of machinery or solar power generation equipment that deviates from normal operation or condition.

[0969] "Report" means a detailed report generated based on collected and analyzed data.

[0970] "Repair and aftercare advice" means instructions or recommendations regarding how to repair and follow-up care for identified anomalies.

[0971] The "emotion engine" is an artificial intelligence system that identifies a user's emotional state by analyzing the user's voice data and facial expression data.

[0972] "Means for recognizing user emotions" refers to a method or device that uses an emotion engine to analyze the user's emotional state and provide appropriate support.

[0973] "Appropriate support" refers to assistance measures such as providing more detailed explanations or contact information for experts depending on the user's emotional state.

[0974] This invention is a system for improving the efficiency of maintenance of machinery and equipment in factories. This system collects image data and environmental information, analyzes them using a generative AI model, identifies abnormalities, and provides repair methods. Furthermore, it is possible to recognize the user's emotions using an emotion engine and provide appropriate support.

[0975] Data collection

[0976] The server periodically collects image data from drones and fixed cameras in the factory. It also collects environmental data using sensors and APIs to obtain environmental information such as temperature and humidity. The collected image data and environmental data are time-stamped and integrated into a single data package.

[0977] Data analysis with generative AI

[0978] The server inputs the collected data packages into a generative AI model, which analyzes the image data. The generative AI model uses deep learning to identify abnormalities on the surface or inside the machinery. The analysis results include the location, type, and severity of the abnormalities.

[0979] Reporting and Advice

[0980] The server generates a detailed report based on the analysis results. This report includes a timestamp, environmental information, and details of the abnormality. This report is provided to the user, who can view it from a PC, smartphone, or other device. In addition, the server uses generative AI to generate specific advice on repairs and aftercare, such as how to repair the abnormality and a list of tools that should be used.

[0981] Recognizing user emotions with an emotion engine

[0982] The server uses an emotion engine to recognize the user's emotions. This emotion engine identifies the user's current emotional state by analyzing the user's voice data and facial expression data. For example, if the user is feeling anxious or stressed, the server will provide enhanced advice and support that takes those emotions into account.

[0983] Specific examples

[0984] A specific example of an actual maintenance operation using the system of the present invention will be described below.

[0985] 1. The server activates the drones and camera system at 10:00 AM every day to collect images of the factory machinery and environmental data.

[0986] 2. The collected data is time-stamped, consolidated, and stored as a data package.

[0987] 3. The server inputs the collected data into the generative AI model, which analyzes the image data. The generative AI model identifies abnormalities in the image and returns that information as the analysis result.

[0988] 4. The server generates a report based on the analysis results, including the coordinates of the anomaly, the details of the detection, and the environmental conditions.

[0989] 5. The server uses generative AI to provide repair procedures and aftercare advice.

[0990] 6. The server uses an emotion engine to recognize the user's emotions. For example, it analyzes the voice data when the user connects to the system and determines that the user is feeling anxious.

[0991] 7. The server considers the emotional information obtained by the emotion engine and reinforces appropriate support.

[0992] Prompt Sentence Examples

[0993] Below is an example of a prompt sentence to be input to a generative AI model. This prompt sentence shows how the collected data should be input to the generative AI model:

[0994] Image data and environmental data are integrated and input into a generative AI model. The analysis results include the location, type, and severity of anomalies.

[0995] As described above, the system of the present invention can improve the efficiency of maintenance of factory machinery and equipment and provide support that takes into account the emotions of users.

[0996] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0997] Step 1:

[0998] The server periodically collects image data from drones and fixed cameras in the factory. The drones and fixed cameras acquire high-resolution image data and send it to the server. The input is image data of the machinery and equipment in the factory, and the output is image data stored on the server.

[0999] Step 2:

[1000] The server uses sensors and APIs to obtain environmental information such as temperature and humidity. The environmental data obtained from the sensors includes various data such as temperature, humidity, and wind speed. The same data can also be obtained using APIs. The input is environmental data from the sensors and APIs, and the output is environmental data stored on the server.

[1001] Step 3:

[1002] The server assigns a timestamp to the collected image data and environmental data and creates an integrated data package. The timestamp indicates the date and time the data was collected or generated, and all data is integrated. This process creates a data package in which the date, time, and environmental conditions are clearly associated. The input is image data and environmental data, and the output is an integrated data package.

[1003] Step 4:

[1004] The server inputs the integrated data package into a generative AI model that analyzes the image data. The generative AI model uses deep learning to identify anomalies within the image. The input to the AI ​​model is the integrated data package, and the output is an analysis result that indicates the location, type, and severity of the anomaly.

[1005] Step 5:

[1006] The server generates a detailed report based on the analysis results obtained from the generative AI model. This report includes a timestamp, environmental information, and details of the anomaly. The report is automatically generated and saved for later viewing by the user. The input is the analysis results and environmental data, and the output is a report file.

[1007] Step 6:

[1008] The server uses generative AI to generate repair procedures and aftercare advice for the abnormal area. For example, if the abnormal area is a crack, it will provide advice on using epoxy resin and a UV lamp. The input is the analysis results, and the output is repair and aftercare advice.

[1009] Step 7:

[1010] The server uses an emotion engine to recognize the user's emotions. When the user connects to the system, the server analyzes the voice and facial expression data as input and identifies the user's emotional state. The input is the voice and facial expression data, and the output is the evaluation result of the user's emotional state.

[1011] Step 8:

[1012] The server takes into account the emotional information provided by the emotion engine and provides appropriate support to the user. For example, if the user feels anxious, the server will enhance the support content by providing a detailed explanation or contact information for an expert. The input is the evaluation result of the emotional state, and the output is the enhanced support content.

[1013] 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.

[1014] 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.

[1015] 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.

[1016] [Fourth embodiment]

[1017] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1018] 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.

[1019] 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).

[1020] 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.

[1021] 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.

[1022] 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).

[1023] 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.

[1024] 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.

[1025] 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.

[1026] 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.

[1027] 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.

[1028] 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.

[1029] 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."

[1030] This invention is a system that automates and streamlines the maintenance of home and small-scale solar power generation facilities. The system collects image data and weather information from the solar power generation facility, analyzes this data using generative AI to identify abnormalities, and provides detailed reports and aftercare advice.

[1031] Data collection

[1032] The server periodically collects image data from drones and fixed cameras installed in homes and small-scale solar power generation facilities. It also collects meteorological data using sensors and APIs to obtain meteorological information. The collected image data and meteorological data are time-stamped and integrated into a single data package.

[1033] Data analysis with generative AI

[1034] The server inputs the collected data package into a generative AI model, which analyzes the image data. The generative AI model uses deep learning to identify abnormalities (e.g., cracks, dirt, and heat generation areas) on the surface and inside of the solar panel. The analysis results include the location, type, and severity of the abnormalities.

[1035] Reporting and Advice

[1036] The server generates a detailed report based on the analysis results. This report includes timestamps, weather information, and details of abnormalities. This report is provided to the user, who can view it from their PC, smartphone, or other device.

[1037] Additionally, the server uses generative AI to generate specific repair and aftercare advice, such as how to fix an abnormality or a list of tools to use.

[1038] Specific examples

[1039] A specific example of an actual maintenance operation using the system of the present invention will be described below.

[1040] 1. The server will start the drone and camera system at 10:00 AM every day to collect images of the solar panels and simultaneously acquire weather data.

[1041] Example: Obtain high-resolution image data from the camera system installed in "panel123" and obtain the current day's weather information from the weather API.

[1042] 2. The collected data is time-stamped, consolidated, and stored as a data package.

[1043] Example: Image data is combined with a timestamp of "2023-10-01 10:00:00" and collected weather data.

[1044] 3. The server inputs the collected data into the generative AI model, which analyzes the image data. The generative AI model identifies abnormalities in the image and returns that information as the analysis result.

[1045] Example: A generative AI model detects a crack at specific coordinates in an image and provides detailed information about it.

[1046] 4. The server generates a report based on the analysis results, including the coordinates of the anomaly, the details of the detection, and weather conditions.

[1047] Example: A report will be generated containing weather data for "2023-10-01 10:00:00" and detailed information on detected cracks.

[1048] 5. The server uses generative AI to provide repair procedures and aftercare advice.

[1049] For example, for detected cracks, an advice is generated recommending the use of epoxy resin and a UV lamp.

[1050] 6. The user checks the report and repair advice on their PC or smartphone and carries out the necessary repair work.

[1051] Example: The user uses the advice provided to repair the crack using epoxy resin.

[1052] As described above, the system of the present invention makes it possible to improve the efficiency of maintenance work for homes and small-scale solar power generation facilities, and to respond quickly and accurately. In addition, the use of generative AI improves the accuracy of identifying abnormalities and the reliability of repair advice.

[1053] The processing flow will be explained below.

[1054] Step 1:

[1055] The server sets up a regular data collection schedule, for example, to launch a data collection task at 10:00 AM every day.

[1056] Step 2:

[1057] The terminal, a drone or fixed camera, is activated to collect image data of the solar panels, taking high-resolution images and saving them.

[1058] Step 3:

[1059] The server retrieves data from weather sensors or APIs to collect weather information, such as temperature, humidity, and weather (sunny, cloudy, rainy, etc.).

[1060] Step 4:

[1061] The server combines the collected image data with weather information and adds a timestamp to indicate when the data was obtained.

[1062] Step 5:

[1063] The server inputs the collected data package into the generative AI model, which then begins analyzing the image data.

[1064] Step 6:

[1065] The server uses the generated AI model to analyze the image data and detect abnormalities, such as cracks, dirt, or heat generation on the surface of a solar panel.

[1066] Step 7:

[1067] The server generates a detailed report based on the detected anomalies, including timestamps, weather information, the location and type of anomaly, and its severity.

[1068] Step 8:

[1069] The server uses the generative AI model to generate repair and aftercare advice. For example, if a crack is found, it will suggest specific steps to repair it and the tools to use.

[1070] Step 9:

[1071] The server generates a report and sends advice to the user, who can then check the report from their PC or smartphone and take any necessary action.

[1072] Step 10:

[1073] The user checks the report provided by the server and performs any necessary repairs or maintenance work, for example, repairing a crack using the suggested method.

[1074] Example 1

[1075] 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."

[1076] Existing inspection and maintenance methods for solar power generation facilities require manual inspection work, which is inefficient and limits the accuracy of identifying and repairing abnormalities. Furthermore, weather and time constraints can make periodic inspections difficult and costly. This results in problems such as a long time before abnormalities are discovered, a decrease in power generation efficiency, and an increased risk of equipment failure.

[1077] 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.

[1078] In this invention, the server includes means for collecting image data from the solar power generation facility using drones and fixed cameras, means for collecting weather information using a weather API or sensors, means for integrating the image data and weather information and attaching a timestamp, means for inputting the collected data package into a generative AI model and analyzing abnormalities, means for generating a detailed report based on the location, type, and severity of the detected abnormalities, and means for generating repair and aftercare advice based on the report using the generative AI model, thereby automating and streamlining the inspection and maintenance process, enabling rapid and accurate identification of abnormalities and appropriate repairs.

[1079] A "drone" is an unmanned aerial vehicle that can be remotely controlled or flown autonomously to collect images and data of a designated area.

[1080] A "fixed camera" is a device that is installed at a specific location and periodically or continuously records still images of a designated object or area.

[1081] A "weather API" is an application programming interface for obtaining weather information via the Internet.

[1082] A "sensor" is a device that detects and measures environmental data such as temperature, humidity, and wind speed, and outputs it as an electrical signal.

[1083] A "timestamp" is data that is used to assign the exact date and time when image data and weather information were recorded or collected.

[1084] A "data package" is a single information unit that integrates image data and meteorological information together with a timestamp.

[1085] A "generative AI model" is an artificial intelligence program that uses deep learning to analyze input data and automatically perform specific tasks (e.g., anomaly detection, report generation, advice provision).

[1086] "Abnormal part" refers to a defective or problematic part of a solar power generation facility that affects its normal operation or performance.

[1087] A "detailed report" is a document generated by the server that includes a timestamp, meteorological information, and analysis results such as the location, type, and severity of anomalies.

[1088] "Repair and aftercare advice" is information that includes specific suggestions on appropriate repair methods, tools to be used, or preventive measures for detected abnormalities.

[1089] This invention is a system for automating and streamlining the inspection and maintenance of solar power generation facilities. The system collects image data of solar panels using drones or fixed cameras, and obtains weather information using weather APIs or sensors. These data are time-stamped, integrated, and processed as a data package. The collected data package is input into a generative AI model, which analyzes abnormalities. A detailed report is generated based on the analysis results, and the generative AI model is used to provide repair and aftercare advice.

[1090] The server collects image data using drones and fixed cameras installed at the solar power generation facilities. The drones take pictures by remote control or autonomous flight, and the fixed cameras capture still images from specific positions, resulting in high-resolution image data.

[1091] To obtain weather information, weather APIs or environmental sensors are used. Weather APIs are application programming interfaces that provide the latest weather information via the Internet, while environmental sensors are devices that collect weather data directly from the local area.

[1092] The system's server timestamps the collected image data and weather information and combines them into a single data package. The data package is stored in a database and input into a generative AI model for analysis. The generative AI model uses deep learning to preprocess the image data (color correction and noise removal), then detects anomalies. The generative AI model analyzes the location, type, and severity of anomalies and returns the analysis results.

[1093] Based on the analysis results, the server generates a detailed report that includes timestamps, weather information, the location and type of abnormality, and its severity. Furthermore, the server uses a generative AI model to generate repair and aftercare advice based on the report, providing users with information on specific repair procedures and tools to use.

[1094] As a specific example, the server activates a drone at a specified time every morning (for example, 10:00 AM) to collect images of solar panels. A fixed camera also operates at the same time to take still images. At this time, the server sends a request to a weather API to obtain the day's weather information. The collected image data and weather information are integrated with a timestamp and stored in a database. The generative AI model receives this data package as input and detects and analyzes abnormalities. The analysis results are generated as a detailed report including the location, type, and severity of the abnormality. The server generates repair and after-care advice based on this report and provides it to the user. Users can view these reports and advice via their PC or smartphone and carry out appropriate repair work.

[1095] An example of a prompt is:

[1096] "High-resolution image data is acquired from the camera system installed on panel 123, and the weather information for the day is obtained from the weather API."

[1097] "The image data is combined with the timestamp 2023-10-01 10:00:00 and the collected meteorological data."

[1098] "The generative AI model detects cracks at specific coordinates in the image and provides detailed information about them."

[1099] Examples include:

[1100] As a result, using this system will improve the efficiency of maintenance work for solar power generation facilities and enable quick and accurate responses. In particular, the use of a generative AI model is a distinctive feature of this invention, as it improves the accuracy of identifying abnormalities and the reliability of repair advice.

[1101] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1102] Step 1:

[1103] The server starts up the drone and camera system at a specified time every morning (e.g., 10:00 AM) and collects image data of the solar panels. The input is image data from the drone and fixed camera, and the output is high-resolution still image data. Specifically, the server calls the drone's API and sends a flight plan.

[1104] Step 2:

[1105] The server uses the weather API or environmental sensors to obtain the weather information for the day. The input is a request from the weather API and data from the environmental sensors, and the output is weather information such as temperature, humidity, and wind speed. Specifically, the server uses the OpenWeatherMap API to obtain weather information for "Tokyo."

[1106] Step 3:

[1107] The server assigns a timestamp to the collected image data and weather information and integrates them into a single data package. The input is image data and weather information, and the output is a time-stamped data package. Specifically, the image data and weather data with a timestamp of "2023-10-01 10:00:00" are integrated into a single JSON file.

[1108] Step 4:

[1109] The server inputs the data package into the generative AI model and analyzes the anomaly. The input is a time-stamped data package, and the output is an analysis result of the location, type, and severity of the anomaly. Specifically, the server converts the image data into input tensors for the generative AI model and performs analysis using deep learning.

[1110] Step 5:

[1111] The generative AI model performs color correction and noise reduction as preprocessing of image data. The input is image data, and the output is cleaned-up image data. Specifically, the generative AI model applies a Gaussian filter to reduce noise in the image.

[1112] Step 6:

[1113] The generative AI model analyzes the preprocessed image data and detects anomalies (e.g., cracks, stains, and hot spots). The input is the cleaned-up image data, and the output is detailed information about the anomalies. Specifically, the generative AI model detects a crack at a specific coordinate in the image (e.g., (150, 200)) and reports it as "Crack, Severity 3 / 5."

[1114] Step 7:

[1115] The server generates a detailed report based on the analysis results. The input is the analysis results from the generative AI model, and the output is a detailed report including the location, type, and severity of the anomaly. Specifically, the server generates a PDF report including a timestamp, weather information, and information about the detected anomaly.

[1116] Step 8:

[1117] The server uses a generative AI model to generate repair and aftercare advice based on the report. The input is a detailed report, and the output is advice including specific repair procedures and a list of tools to use. Specifically, the generative AI model generates advice in text form, such as "For the detected cracks, we recommend using epoxy resin and a UV lamp."

[1118] Step 9:

[1119] The server sends the generated report and advice to the user's device. The input is a detailed report and advice, and the output is data sent to the user's PC or smartphone. Specifically, the server sends a PDF report and advice in text format to the user's email address.

[1120] Step 10:

[1121] The user checks the report and repair advice via a PC or smartphone and carries out the necessary repair work. The input is the report and advice sent from the server, and the output is the actual repair work. In concrete terms, the user repairs the cracked area using epoxy resin based on the advice provided.

[1122] As described above, by implementing this system, maintenance work for solar power generation facilities can be automated, enabling prompt and accurate responses.

[1123] (Application example 1)

[1124] 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."

[1125] Inspection and maintenance of solar power generation facilities often requires manual checking, which is time-consuming and costly. It is also difficult for users without specialized knowledge to perform maintenance properly. Furthermore, delays in identifying abnormalities can lead to reduced power generation efficiency and serious breakdowns. There is a need for a system that can address these issues quickly and accurately by automating and streamlining the process.

[1126] 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.

[1127] In this invention, the server includes means for collecting image data from the solar power generation facility, means for collecting weather information, means for integrating the image data and weather information and assigning a timestamp, means for inputting the collected data into a generative artificial intelligence model and analyzing abnormalities, means for identifying abnormalities and generating a detailed report based on the identified abnormalities, means for generating repair and aftercare advice based on the report, means for transmitting the report and advice to a user's information terminal, and a mobile machine that autonomously patrols the solar power generation facility within the industrial facility and collects data. This makes it possible to automate and streamline inspection and maintenance of the solar power generation facility.

[1128] A "photovoltaic power generation facility" is a system that includes devices and associated equipment for converting solar light energy into electrical energy.

[1129] "Means for collecting image data" refers to equipment and technology for photographing the condition of solar power generation facilities and saving them as digital images.

[1130] "Means of collecting weather information" refers to sensors and APIs for obtaining environmental data such as temperature, humidity, wind speed, and solar radiation.

[1131] "Means for adding a timestamp" refers to the technology and method for adding date and time information to data.

[1132] A "generative artificial intelligence model" refers to an algorithm or set of computational models that are trained to perform a specific task using machine learning or deep learning.

[1133] "Means for analyzing abnormalities" refers to technology that uses collected image data and weather information to detect and evaluate abnormalities and deterioration in solar power generation equipment.

[1134] "Means for generating a report" refers to the technology and method for creating a document based on the analysis results that details any anomalies and other important information.

[1135] "Means for generating repair and aftercare advice" refers to techniques and methods for generating advice and recommendations regarding necessary repair procedures and maintenance methods based on the results of the analysis.

[1136] "Means for sending to the user's information terminal" refers to communication technology for transferring the generated report or advice to a device such as a smartphone or computer used by the user.

[1137] "Mobile machines that autonomously patrol solar power generation facilities and collect data" refers to automated devices such as self-driving robots and drones that automatically patrol solar power generation facilities within factories and collect image data and weather information.

[1138] The present invention relates to a system for automating and streamlining the inspection and maintenance of solar power generation facilities. The system is intended for use in industrial facilities and autonomously patrols the facilities, identifies abnormalities, and generates reports and advice.

[1139] First, the server runs on the following hardware and software: Drones and fixed cameras are used to collect image data, and API-enabled weather sensors are used to collect weather information. A generative AI model such as YOLOv5 is used for data analysis. This model uses deep learning to identify anomalies in the images.

[1140] The server periodically collects image data from drones and fixed cameras, and simultaneously retrieves weather data from weather sensors and APIs. These data are time-stamped and integrated. This integrated data package is then fed into a generative AI model to identify anomalies.

[1141] The analysis results include the location, type, and severity of the anomaly. The server generates a detailed report based on the analysis results, including a timestamp, weather information, and details of the anomaly. This report is sent to the user's information terminal and can be viewed from a PC or smartphone. The server also uses generative AI to provide repair and aftercare advice, such as how to repair the anomaly and a list of tools that should be used.

[1142] In a specific example, the server launches a drone inside the factory at 10:00 AM every day to collect images of the solar panels. At the same time, it obtains the day's weather information from an external weather API. The collected data is integrated with a timestamp such as "2023-10-01 10:00:00" and input into a generative AI model (e.g., YOLOv5). This model detects cracks at specific coordinates in the image and provides detailed information about them.

[1143] The generated report includes weather data for 2023-10-01 10:00:00 and detailed information about the detected cracks. The server also uses the generative AI to provide repair procedures and aftercare advice, such as recommending the use of epoxy resin and a UV lamp for the detected cracks.

[1144] Example prompt sentence:

[1145] "Image data: capture1.jpg, Weather data: Sunny, 24.5°C, Humidity 60%, Analysis result: Crack detected (coordinates: x=123, y=456), Repair advice: Use epoxy resin."

[1146] This system will improve the efficiency of maintenance work for solar power generation equipment in factories, enabling quick and accurate responses. By utilizing generative AI, the system is characterized by improved accuracy in identifying abnormalities and reliability of repair advice.

[1147] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1148] Step 1:

[1149] The server activates drones and fixed cameras installed at the solar power generation facility and collects image data. Control commands for the facility's cameras and drones are given as input. Specifically, the server sends flight commands to the drones to take photos of the solar panels. The output is high-resolution image data.

[1150] Step 2:

[1151] The server retrieves weather data using an external weather API. As input, it is given the API endpoint URL and any necessary authentication information. Using these, the server sends a request to the API server to retrieve current weather information (e.g., temperature, humidity, solar radiation, etc.). The output is weather data in JSON format.

[1152] Step 3:

[1153] The server integrates the image data and meteorological data and assigns a timestamp to each piece of data. The input is the image data and meteorological data obtained in steps 1 and 2. Specifically, the server combines these pieces of data into a single data package and adds the current date and time information. The output is a data package with a timestamp.

[1154] Step 4:

[1155] The server inputs the integrated data package into a generative AI model (e.g., YOLOv5) to analyze anomalies. The input is a time-stamped data package, and data processing involves image analysis to detect anomalies (e.g., cracks or stains) in the image. The generative AI model identifies the coordinates and type of anomalies and outputs the results. The output is the analysis result of the anomalies.

[1156] Step 5:

[1157] The server generates a detailed report based on the analysis results. The inputs are the analysis results obtained in step 4 and time-stamped weather data. Specifically, the server compiles the analysis results into a text report, listing the location, type, and severity of any anomalies. The output is a detailed report.

[1158] Step 6:

[1159] The server uses generative AI to generate repair and aftercare advice based on the analysis results. The input is the detailed report generated in step 5. Specifically, the server generates advice that lists appropriate repair methods and tools to be used based on the anomaly information in the report. The output is repair and aftercare advice.

[1160] Step 7:

[1161] The server sends the generated report and advice to the user's information device (e.g., a smartphone or PC). The input is the report and advice generated in step 6. Specifically, the server transfers this information to the user's device via email or a dedicated app. The output is the report and advice displayed on the user's device.

[1162] Step 8:

[1163] The user checks the report and advice received from the information terminal and carries out the necessary repair work. The input is the report and advice sent in step 7. In concrete terms, the user repairs the abnormal part using appropriate tools and materials based on the advice provided. The output is the repaired solar power generation equipment.

[1164] 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.

[1165] This invention is a system for streamlining the maintenance of home and small-scale solar power generation facilities. This system collects image data and weather information from the solar power generation facility and identifies abnormalities by analyzing the data using generative AI. In addition, by combining it with an emotion engine, the system recognizes the user's emotions and provides appropriate repair and aftercare advice.

[1166] Data collection

[1167] The server periodically collects image data from drones and fixed cameras installed in homes and small-scale solar power generation facilities. It also collects meteorological data using sensors and APIs to obtain meteorological information. The collected image data and meteorological data are time-stamped and integrated into a single data package.

[1168] Data analysis with generative AI

[1169] The server inputs the collected data package into a generative AI model, which analyzes the image data. The generative AI model uses deep learning to identify abnormalities on the surface and inside of the solar panel. The analysis results include the location, type, and severity of the abnormality.

[1170] Reporting and Advice

[1171] The server generates a detailed report based on the analysis results. This report includes timestamps, weather information, and details of abnormalities. This report is provided to the user, who can view it from their PC, smartphone, or other device.

[1172] Additionally, the server uses generative AI to generate specific repair and aftercare advice, such as how to fix an abnormality or a list of tools to use.

[1173] Recognizing user emotions with an emotion engine

[1174] The server also uses an emotion engine to recognize the user's emotions. This emotion engine identifies the user's current emotional state by analyzing the user's voice data, facial expression data, and operation history. For example, if the user is feeling anxious or stressed, the server can provide enhanced advice and support that takes those emotions into account.

[1175] Specific examples

[1176] A specific example of an actual maintenance operation using the system of the present invention will be described below.

[1177] 1. The server will start the drone and camera system at 10:00 AM every day to collect images of the solar panels and simultaneously acquire weather data.

[1178] Example: Obtain high-resolution image data from the camera system installed in "panel123" and obtain the current day's weather information from the weather API.

[1179] 2. The collected data is time-stamped, consolidated, and stored as a data package.

[1180] Example: Image data is combined with a timestamp of "2023-10-01 10:00:00" and collected weather data.

[1181] 3. The server inputs the collected data into the generative AI model, which analyzes the image data. The generative AI model identifies abnormalities in the image and returns that information as the analysis result.

[1182] Example: A generative AI model detects a crack at specific coordinates in an image and provides detailed information about it.

[1183] 4. The server generates a report based on the analysis results, including the coordinates of the anomaly, the details of the detection, and weather conditions.

[1184] Example: A report will be generated containing weather data for "2023-10-01 10:00:00" and detailed information on detected cracks.

[1185] 5. The server uses generative AI to provide repair procedures and aftercare advice.

[1186] For example, for detected cracks, an advice is generated recommending the use of epoxy resin and a UV lamp.

[1187] 6. The server uses an emotion engine to recognize the user's emotions. For example, it analyzes the voice data when the user connects to the system and determines that the user is feeling anxious.

[1188] Example: Voice analysis detects when a user is speaking in an anxious tone.

[1189] 7. The server takes into account the emotional information obtained by the emotion engine and provides appropriate support enhancements, for example, providing detailed explanations or additional support contacts.

[1190] For example, provide a user who is concerned with the repair process with more detailed instructions or contact information for an expert.

[1191] 8. The user checks the report and repair advice on their PC or smartphone and carries out the necessary repairs. Based on the information obtained from the emotion engine, the user can proceed with the work with peace of mind.

[1192] Example: The user uses the advice provided to repair the crack using epoxy resin.

[1193] As described above, the system of the present invention can improve the efficiency of maintenance of photovoltaic power generation facilities and provide support that takes into consideration the emotions of users.

[1194] The processing flow will be explained below.

[1195] Step 1:

[1196] The server sets up a regular data collection schedule, for example, to launch a data collection task at 10:00 AM every day.

[1197] Step 2:

[1198] The terminal, a drone or fixed camera, is activated to collect image data of the solar panels, taking high-resolution images and saving them.

[1199] Step 3:

[1200] The server retrieves data from weather sensors or APIs to collect weather information, such as temperature, humidity, and weather (sunny, cloudy, rainy, etc.).

[1201] Step 4:

[1202] The server combines the collected image data with weather information and adds a timestamp to indicate when the data was obtained.

[1203] Step 5:

[1204] The server inputs the collected data package into the generative AI model, which then begins analyzing the image data.

[1205] Step 6:

[1206] The server uses the generated AI model to analyze the image data and detect abnormalities, such as cracks, dirt, or heat generation on the surface of a solar panel.

[1207] Step 7:

[1208] The server generates a detailed report based on the detected anomalies, including timestamps, weather information, the location and type of anomaly, and its severity.

[1209] Step 8:

[1210] The server uses the generative AI model to generate repair and aftercare advice. For example, if a crack is found, it will suggest specific steps to repair it and the tools to use.

[1211] Step 9:

[1212] The server uses an emotion engine to recognize the user's emotions, for example, by analyzing the user's voice data, facial expression data, and operation history to determine the user's current emotional state.

[1213] Step 10:

[1214] The server takes emotional information into account and, if the user feels anxious or stressed, enhances the advice and support according to the emotion, for example by providing detailed explanations or additional support contacts.

[1215] Step 11:

[1216] The server generates a report and sends advice to the user, who can then check the report from their PC or smartphone and take any necessary action.

[1217] Step 12:

[1218] The user can check the report provided by the server and carry out the necessary repairs and maintenance work, for example, repairing a crack using the suggested method, and proceed with the work with peace of mind using the additional support suggested by the emotion engine.

[1219] Example 2

[1220] 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."

[1221] In the inspection and maintenance of solar power generation facilities, it is extremely important to quickly and accurately detect abnormalities in the facilities and provide users with appropriate repair and aftercare advice. However, current systems require time and effort to collect and analyze data, and do not take user feelings into consideration, resulting in a lack of appropriate support.

[1222] 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 collecting image data, means for collecting weather information, means for integrating image data and weather information and assigning a timestamp, means for inputting the collected data into a generative AI model and analyzing abnormalities, means for identifying abnormalities and generating a detailed report based on the identified abnormalities, means for generating repair and aftercare advice based on the report, means for recognizing the user's emotional state, and means for providing additional support based on the recognized emotional state. This makes it possible to quickly and accurately detect abnormalities in the solar power generation equipment and provide the user with appropriate repair and aftercare advice. Furthermore, providing support that takes the user's emotions into consideration reduces the user's anxiety and stress, allowing the work to proceed smoothly.

[1223] "Means for collecting image data" refers to a device or system for acquiring image data from a photovoltaic power generation facility.

[1224] "Means for collecting weather information" refers to devices or systems for acquiring weather data in the surrounding environment of the solar power generation facility.

[1225] The "time stamping means" is a system for adding date and time information to collected image data and meteorological data.

[1226] A "generative artificial intelligence model" is a system that includes a deep learning model for analyzing collected data and automatically detecting abnormalities.

[1227] The "means for analyzing abnormal locations" refers to a method and system for identifying abnormal locations in a photovoltaic power generation facility using image data and meteorological data.

[1228] The "means for generating a detailed report" is a system for creating a report containing detailed information based on the identified abnormality.

[1229] The "means for generating repair and aftercare advice" is a system that uses a generative AI model to provide recommendations regarding repair methods and aftercare.

[1230] The "means for recognizing the user's emotional state" is a technology for identifying the user's emotions by analyzing voice data, facial expression data, and operation history.

[1231] The "means for providing additional support" is a system that provides appropriate advice and support information based on the recognized emotional state of the user.

[1232] This invention is a system for improving the efficiency of inspection and maintenance of solar power generation facilities. This system collects image data and weather information, analyzes them using a generative AI model, identifies abnormalities, and provides appropriate repair and aftercare advice to users. It also has a function to recognize users' emotions and enhance support based on those emotions.

[1233] Data collection

[1234] The server periodically collects image data of the solar power generation facility using drones and fixed cameras. The drones are equipped with an automatic navigation system, and the fixed cameras use high-resolution cameras. Weather information is also collected using sensors and weather APIs. For example, the API can be used to obtain the current day's weather information, and sensors can be used to collect local weather data in real time.

[1235] Data package integration

[1236] The collected image data and meteorological data are each given a timestamp, which clarifies when each piece of data was collected. The server then integrates this data and stores it in a database as a single data package.

[1237] Data analysis with generative AI

[1238] The server inputs the integrated data package into a generative AI model, which uses a deep learning algorithm to analyze the image data and identify abnormalities in the solar panels. The generative AI model outputs the location, type, and severity of the abnormalities as analysis results.

[1239] Reporting and Advice

[1240] The server generates a detailed report based on the analysis results. This report includes timestamps, weather information, and details of any identified anomalies. The report is output in a format that is easy for users to understand and can be viewed on a PC or smartphone. Furthermore, the generative AI provides advice such as specific repair methods and a list of tools to use.

[1241] Recognizing user emotions with an emotion engine

[1242] The server recognizes the user's emotional state using an emotion engine, which analyzes the user's voice data, facial expression data, and operation history to determine whether the user is feeling anxious or stressed.

[1243] Providing enhanced support

[1244] The server provides detailed instructions and additional support contact information based on the user's emotional state, allowing the user to proceed with the task without anxiety. For example, if the server analyzes the voice data when the user connects to the system and determines that the user is feeling anxious, it provides detailed repair guides and contact information for experts.

[1245] Specific examples

[1246] Here is a concrete example:

[1247] 1. The server starts the drone and camera system at 10:00 AM every day to collect images of the solar panels and retrieves the day's weather information from the weather API.

[1248] Example: High-resolution image data is acquired from a camera system installed on "panel123."

[1249] 2. The collected data is given a timestamp "2023-10-01 10:00:00", consolidated, and saved as a data package.

[1250] Example: Integrating image data with meteorological data.

[1251] 3. The server inputs the data package into a generative AI model and analyzes the image data.

[1252] Example: A generative AI model detects a crack at coordinates (50,100) in an image.

[1253] 4. Generate a report based on the analysis results and provide it to the user.

[1254] Example: The report will show the anomaly location as "(50,100): Crack".

[1255] 5. The server uses generative AI to provide specific repair and aftercare advice.

[1256] For example: We recommend using epoxy resin and a UV lamp.

[1257] 6. The server uses an emotion engine to detect anxiety from the user's voice data.

[1258] Example: Analyzing anxious tone.

[1259] 7. Provide users with additional support information to expedite their work.

[1260] Example: Detailed repair guides.

[1261] As described above, the present invention improves the efficiency of maintenance of photovoltaic power generation facilities and provides support that takes into account the emotions of users.

[1262] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1263] Step 1:

[1264] The server activates the drone and fixed camera to collect image data of the solar power plant. The drone is equipped with an automatic navigation system and flies automatically to specified coordinates. The fixed camera uses a high-resolution camera system to capture images at specific times. The input is the operation time and coordinates of the drone and camera system, and the output is the collected high-resolution image file.

[1265] Example: At 10:00 AM, the drone and camera will start up and collect high-resolution image "image_20231001.png" from "panel123."

[1266] Step 2:

[1267] The server collects weather data via weather sensors and weather APIs. The weather sensors measure local temperature, humidity, wind speed, etc. in real time, and obtains the day's weather information from the API. The input is real-time data from the weather sensors and API requests, and the output is a weather information dataset.

[1268] Example: Collect real-time data from weather sensors and weather information obtained from a weather API.

[1269] Step 3:

[1270] The server assigns a timestamp to the collected image data and meteorological data, and integrates them to create a data package. The timestamp indicates the collection time and is used to maintain data consistency. The input is image data and meteorological data, and the output is the integrated data package.

[1271] Example: Create a data package by adding the timestamp "2023-10-01 10:00:00" to the image data "image_20231001.png" and weather data.

[1272] Step 4:

[1273] The server inputs the data package into a generative AI model that analyzes the image data. The generative AI model uses a deep learning algorithm to identify abnormalities in the solar panels. The input is the data package, and the output is the analysis results, including the location, type, and severity of the abnormality.

[1274] Example: Input "data_package_20231001.json" into the AI ​​model and obtain the analysis result "Crack: Severity 2" at coordinates (50,100).

[1275] Step 5:

[1276] The server generates a detailed report based on the analysis results. The report includes timestamps, weather information, and details of identified anomalies, and is provided to the user. The input is the analysis results, and the output is the report.

[1277] Example: Generate a report with the timestamp "2023-10-01 10:00:00", weather data, and anomaly location "(50,100): Crack".

[1278] Step 6:

[1279] The server uses a generative AI model to generate specific advice on repairs and aftercare. The generated advice can be based on the user's skill level and previous repair history. The input is the analysis results and user information, and the output is repair and aftercare advice.

[1280] Example: Generate advice such as "Use epoxy resin and a UV lamp to repair the crack."

[1281] Step 7:

[1282] The server uses an emotion engine to recognize the user's emotional state. The emotion engine analyzes voice data, facial expression data, and operation history to identify the user's emotion. The input is the user's voice data and operation history, and the output is the user's emotional state.

[1283] Example: Determine that the user is feeling anxious based on voice data.

[1284] Step 8:

[1285] The server provides additional support based on the recognized emotional state, for example providing detailed explanations or contact information for experts to a user who is feeling anxious. The input is the user's emotional state, and the output is enhanced support information.

[1286] Example: Providing a detailed repair guide or expert contact information to a user who is concerned.

[1287] Step 9:

[1288] Users can check the report and repair advice from their PC or smartphone and carry out the necessary repair work. This allows them to proceed with the work accurately based on the information provided. The input is the report and advice, and the output is the repair work carried out by the user.

[1289] Example: Check the advice given by the PC and repair the crack using epoxy resin.

[1290] (Application example 2)

[1291] 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."

[1292] In the maintenance of machinery and equipment in factories, early detection of abnormalities and provision of appropriate repair methods are key challenges. Conventional systems take time to identify abnormalities and do not provide support that takes into account the emotional state of the worker, which can reduce the efficiency of maintenance work. This can lead to problems such as increased equipment downtime and reduced productivity. The objective of this invention is to improve the efficiency of factory equipment maintenance, provide early detection of abnormalities, provide appropriate repair methods, and provide support that takes into account the user's emotions.

[1293] 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 collecting image data from factory equipment, means for collecting environmental information, means for integrating the image data and environmental information and assigning a timestamp, means for inputting the collected data into a generative artificial intelligence model and analyzing abnormalities, means for identifying abnormalities and generating a detailed report based on the identified abnormalities, means for generating repair and aftercare advice based on the report, and means for recognizing the user's emotions using an emotion engine and providing appropriate support. This not only enables early detection of abnormalities and appropriate provision of repair methods during factory equipment maintenance, but also enables support that takes into account the emotional state of workers, thereby improving the efficiency and productivity of maintenance work.

[1294] "Image data" refers to visual information captured by devices such as cameras and drones.

[1295] "Weather information" refers to environmental data such as the weather, temperature, humidity, and wind speed at a specific location.

[1296] A "timestamp" is information that indicates the date and time when data was collected or generated.

[1297] A "generative artificial intelligence model" is a computer program that analyzes various data, identifies abnormalities, and generates advice.

[1298] An "abnormal part" refers to a part of machinery or solar power generation equipment that deviates from normal operation or condition.

[1299] "Report" means a detailed report generated based on collected and analyzed data.

[1300] "Repair and aftercare advice" means instructions or recommendations regarding how to repair and follow-up care for identified anomalies.

[1301] The "emotion engine" is an artificial intelligence system that identifies a user's emotional state by analyzing the user's voice data and facial expression data.

[1302] "Means for recognizing user emotions" refers to a method or device that uses an emotion engine to analyze the user's emotional state and provide appropriate support.

[1303] "Appropriate support" refers to assistance measures such as providing more detailed explanations or contact information for experts depending on the user's emotional state.

[1304] This invention is a system for improving the efficiency of maintenance of machinery and equipment in factories. This system collects image data and environmental information, analyzes them using a generative AI model, identifies abnormalities, and provides repair methods. Furthermore, it is possible to recognize the user's emotions using an emotion engine and provide appropriate support.

[1305] Data collection

[1306] The server periodically collects image data from drones and fixed cameras in the factory. It also collects environmental data using sensors and APIs to obtain environmental information such as temperature and humidity. The collected image data and environmental data are time-stamped and integrated into a single data package.

[1307] Data analysis with generative AI

[1308] The server inputs the collected data packages into a generative AI model, which analyzes the image data. The generative AI model uses deep learning to identify abnormalities on the surface or inside the machinery. The analysis results include the location, type, and severity of the abnormalities.

[1309] Reporting and Advice

[1310] The server generates a detailed report based on the analysis results. This report includes a timestamp, environmental information, and details of the abnormality. This report is provided to the user, who can view it from a PC, smartphone, or other device. In addition, the server uses generative AI to generate specific advice on repairs and aftercare, such as how to repair the abnormality and a list of tools that should be used.

[1311] Recognizing user emotions with an emotion engine

[1312] The server uses an emotion engine to recognize the user's emotions. This emotion engine identifies the user's current emotional state by analyzing the user's voice data and facial expression data. For example, if the user is feeling anxious or stressed, the server will provide enhanced advice and support that takes those emotions into account.

[1313] Specific examples

[1314] A specific example of an actual maintenance operation using the system of the present invention will be described below.

[1315] 1. The server activates the drones and camera system at 10:00 AM every day to collect images of the factory machinery and environmental data.

[1316] 2. The collected data is time-stamped, consolidated, and stored as a data package.

[1317] 3. The server inputs the collected data into the generative AI model, which analyzes the image data. The generative AI model identifies abnormalities in the image and returns that information as the analysis result.

[1318] 4. The server generates a report based on the analysis results, including the coordinates of the anomaly, the details of the detection, and the environmental conditions.

[1319] 5. The server uses generative AI to provide repair procedures and aftercare advice.

[1320] 6. The server uses an emotion engine to recognize the user's emotions. For example, it analyzes the voice data when the user connects to the system and determines that the user is feeling anxious.

[1321] 7. The server considers the emotional information obtained by the emotion engine and reinforces appropriate support.

[1322] Prompt Sentence Examples

[1323] Below is an example of a prompt sentence to be input to a generative AI model. This prompt sentence shows how the collected data should be input to the generative AI model:

[1324] Image data and environmental data are integrated and input into a generative AI model. The analysis results include the location, type, and severity of anomalies.

[1325] As described above, the system of the present invention can improve the efficiency of maintenance of factory machinery and equipment and provide support that takes into account the emotions of users.

[1326] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1327] Step 1:

[1328] The server periodically collects image data from drones and fixed cameras in the factory. The drones and fixed cameras acquire high-resolution image data and send it to the server. The input is image data of the machinery and equipment in the factory, and the output is image data stored on the server.

[1329] Step 2:

[1330] The server uses sensors and APIs to obtain environmental information such as temperature and humidity. The environmental data obtained from the sensors includes various data such as temperature, humidity, and wind speed. The same data can also be obtained using APIs. The input is environmental data from the sensors and APIs, and the output is environmental data stored on the server.

[1331] Step 3:

[1332] The server assigns a timestamp to the collected image data and environmental data and creates an integrated data package. The timestamp indicates the date and time the data was collected or generated, and all data is integrated. This process creates a data package in which the date, time, and environmental conditions are clearly associated. The input is image data and environmental data, and the output is an integrated data package.

[1333] Step 4:

[1334] The server inputs the integrated data package into a generative AI model that analyzes the image data. The generative AI model uses deep learning to identify anomalies within the image. The input to the AI ​​model is the integrated data package, and the output is an analysis result that indicates the location, type, and severity of the anomaly.

[1335] Step 5:

[1336] The server generates a detailed report based on the analysis results obtained from the generative AI model. This report includes a timestamp, environmental information, and details of the anomaly. The report is automatically generated and saved for later viewing by the user. The input is the analysis results and environmental data, and the output is a report file.

[1337] Step 6:

[1338] The server uses generative AI to generate repair procedures and aftercare advice for the abnormal area. For example, if the abnormal area is a crack, it will provide advice on using epoxy resin and a UV lamp. The input is the analysis results, and the output is repair and aftercare advice.

[1339] Step 7:

[1340] The server uses an emotion engine to recognize the user's emotions. When the user connects to the system, the server analyzes the voice and facial expression data as input and identifies the user's emotional state. The input is the voice and facial expression data, and the output is the evaluation result of the user's emotional state.

[1341] Step 8:

[1342] The server takes into account the emotional information provided by the emotion engine and provides appropriate support to the user. For example, if the user feels anxious, the server will enhance the support content by providing a detailed explanation or contact information for an expert. The input is the evaluation result of the emotional state, and the output is the enhanced support content.

[1343] 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.

[1344] 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.

[1345] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1346] 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.

[1347] 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.

[1348] 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.

[1349] 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).

[1350] 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.

[1351] 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."

[1352] 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.

[1353] 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).

[1354] 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.

[1355] 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.

[1356] 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.

[1357] 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.

[1358] 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.

[1359] 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.

[1360] 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.

[1361] 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.

[1362] 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.

[1363] 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.

[1364] The following is further disclosed regarding the above embodiment.

[1365] (Claim 1)

[1366] To carry out inspection and maintenance of solar power generation equipment,

[1367] means for collecting image data from the solar power generation facility;

[1368] a means for collecting meteorological information;

[1369] means for integrating image data and meteorological information and assigning a time stamp;

[1370] A means for inputting the collected data into a generative artificial intelligence model and analyzing abnormalities;

[1371] A means for identifying anomalies and generating detailed reports based on the anomalies;

[1372] means for generating repair and aftercare advice based on the report;

[1373] A system including:

[1374] (Claim 2)

[1375] 2. The system according to claim 1, further comprising means for identifying the abnormal location by image analysis.

[1376] (Claim 3)

[1377] 10. The system of claim 1, further comprising means for generating said repair and aftercare advice by a generative artificial intelligence model.

[1378] "Example 1"

[1379] (Claim 1)

[1380] a means for collecting image data from the solar power installation using drones and fixed cameras;

[1381] A means of collecting weather information using a weather API or sensor;

[1382] means for integrating and time-stamping image data and meteorological information;

[1383] A means of inputting the collected data package into a generative AI model and analyzing abnormalities;

[1384] A means for generating a detailed report of the location, type, and severity of detected anomalies;

[1385] a means for generating repair and aftercare advice based on the report using a generative AI model;

[1386] A system including:

[1387] (Claim 2)

[1388] The system according to claim 1, wherein in analyzing the abnormal location, the generative AI model is provided with means for performing preprocessing of image data for color correction and noise removal.

[1389] (Claim 3)

[1390] 10. The system of claim 1, further comprising means for generating said repair and aftercare advice including specific application tool recommendations.

[1391] "Application Example 1"

[1392] (Claim 1)

[1393] To carry out inspection and maintenance of solar power generation equipment,

[1394] means for collecting image data from the solar power generation facility;

[1395] a means for collecting meteorological information;

[1396] means for integrating image data and meteorological information and assigning a time stamp;

[1397] A means for inputting the collected data into a generative artificial intelligence model and analyzing abnormalities;

[1398] A means for identifying anomalies and generating detailed reports based on the anomalies;

[1399] means for generating repair and aftercare advice based on the report;

[1400] means for transmitting the report and advice to a user's information terminal;

[1401] A means including a mobile machine that autonomously patrols solar power generation facilities within an industrial facility and collects data;

[1402] A system including:

[1403] (Claim 2)

[1404] 2. The system according to claim 1, further comprising means for identifying the abnormal location by image analysis.

[1405] (Claim 3)

[1406] 10. The system of claim 1, further comprising means for generating said repair and aftercare advice by a generative artificial intelligence model.

[1407] "Example 2: Combining Emotion Engines"

[1408] (Claim 1)

[1409] To carry out inspection and maintenance of solar power generation equipment,

[1410] means for collecting image data;

[1411] a means for collecting meteorological information;

[1412] means for integrating image data and meteorological information and assigning a time stamp;

[1413] A means for inputting the collected data into a generative artificial intelligence model and analyzing abnormalities;

[1414] A means for identifying anomalies and generating detailed reports based on the anomalies;

[1415] means for generating repair and aftercare advice based on the report;

[1416] means for recognizing the emotional state of a user;

[1417] a means of providing additional support based on the perceived emotional state;

[1418] A system including:

[1419] (Claim 2)

[1420] 2. The system according to claim 1, further comprising means for identifying the abnormal location by image analysis.

[1421] (Claim 3)

[1422] 10. The system of claim 1, further comprising means for generating said repair and aftercare advice by a generative artificial intelligence model.

[1423] "Application example 2 when combining emotion engines"

[1424] (Claim 1)

[1425] To carry out inspection and maintenance of solar power generation equipment,

[1426] means for collecting image data from the solar power generation facility;

[1427] a means for collecting meteorological information;

[1428] means for integrating image data and meteorological information and assigning a time stamp;

[1429] A means for inputting the collected data into a generative artificial intelligence model and analyzing abnormalities;

[1430] A means for identifying anomalies and generating detailed reports based on the anomalies;

[1431] means for generating repair and aftercare advice based on the report;

[1432] A means for recognizing a user's emotions using an emotion engine and providing appropriate support;

[1433] A system including:

[1434] (Claim 2)

[1435] 2. The system according to claim 1, further comprising means for identifying the abnormal location by image analysis.

[1436] (Claim 3)

[1437] 10. The system of claim 1, further comprising means for generating said repair and aftercare advice by a generative artificial intelligence model. [Explanation of symbols]

[1438] 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. To carry out inspection and maintenance of solar power generation equipment, means for collecting image data from the solar power generation facility; a means for collecting meteorological information; means for integrating image data and meteorological information and assigning a time stamp; A means for inputting the collected data into a generative artificial intelligence model and analyzing abnormalities; A means for identifying anomalies and generating detailed reports based on the anomalies; means for generating repair and aftercare advice based on the report; A system including:

2. The system according to claim 1, further comprising means for identifying the abnormal portion by image analysis.

3. 10. The system of claim 1, further comprising means for generating said repair and aftercare advice by a generative artificial intelligence model.

Images