System

Abstract

A system is provided.SOLUTION: A system includes means for collecting temperature data of the ground using satellite data, means for analyzing the collected temperature data to calculate stress on a water pipe, means for predicting a risk of water leakage based on the stress data, means for acquiring seismic data and multiplying the seismic data by the temperature data to preferentially specify a water pipe requiring repair, means for creating a repair manual using a generated AI for the specified repair place, and means for creating an efficient water channel map suitable for modern settlements.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] Modern water infrastructure is aging, with insufficient earthquake resistance measures and a decline in the number of waterworks staff becoming problems. Furthermore, the existence of unknown construction companies makes quality control difficult, leading to an increase in customer complaints. Furthermore, it is difficult to identify areas with a high risk of water leakage, making efficient repairs and maintenance difficult. It is necessary to solve these issues and aim to realize sustainable water infrastructure. [Means for solving the problem]

[0005] We will provide a means to predict the risk of water leaks by collecting ground temperature changes using satellite data, analyzing the temperature data, and calculating stress on water pipes. We will also provide a means to acquire earthquake data and combine it with temperature data to prioritize water pipes that need repair, thereby achieving efficient repairs and quality control. We will also provide a means to create specific repair manuals for identified repair locations using generative AI, allowing outsourced workers to work efficiently. We will also provide a means to create efficient waterway maps suitable for modern settlements, optimizing long-term water pipe maintenance plans.

[0006] "Satellite data" refers to data obtained from satellites in the sky, such as information on temperature changes and topography on the Earth's surface.

[0007] "Temperature data" refers to ground temperature information obtained from satellite data and is stored as time-series data.

[0008] "Stress" refers to the physical load on water pipes, especially that caused by sudden temperature changes or earthquakes.

[0009] "Leak risk" refers to the degree to which water may leak due to stress or deterioration of water pipes.

[0010] "Earthquake data" refers to data that includes information such as the magnitude, frequency, and epicenter of past earthquakes in a specific region.

[0011] "Repair" refers to the work of repairing broken or deteriorated water pipes and restoring them to normal condition.

[0012] "Generative AI" refers to a system that uses artificial intelligence technology to automatically generate text and images for repair manuals and other documents.

[0013] A "repair manual" is a document that describes the procedures for repair work, the tools to be used, and precautions to take, and serves as a guideline for workers when carrying out repair work.

[0014] "Outsourced workers" refer to workers who are not full-time employees of the Waterworks Bureau, but are contracted by an outside party to carry out repair work.

[0015] A "waterway map" is a diagram of the layout of water pipes and related facilities, and is used when making maintenance and repair plans.

[0016] A "settlement" refers to an area where people live and dwell, and can range from small villages to urban areas. [Brief explanation of the drawings]

[0017] [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

[0018] 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.

[0019] First, the terms used in the following description will be explained.

[0020] 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).

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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."

[0038] This invention is a system that utilizes satellite data and artificial intelligence technology (generative AI) to efficiently manage and repair water pipes. In this system, the server, terminal, and user each play different roles, and optimal water pipe management is achieved through each processing step. How the present invention is implemented is described in detail below.

[0039] 1. Satellite data acquisition and analysis

[0040] The server periodically obtains ground temperature data from a satellite data provider, collecting time-series data on temperature fluctuations in a specific area. The server then analyzes this temperature data internally to calculate the stress on the water pipes. Stress points are identified using an algorithm that detects sudden changes in temperature data. For example, if a certain area experiences a sudden change in temperature, it can be determined that the water pipes in that area are under high stress.

[0041] 2. Seismic data acquisition and analysis

[0042] The server acquires earthquake data from reliable data sources such as the Earthquake Research Institute. It collects information such as the magnitude, frequency, and epicenter of past earthquakes. It then matches the acquired earthquake data with temperature data to prioritize the locations of water pipes that are most in need of repair. It then assesses the degree of risk to water pipes in the identified area based on vibrations and temperature changes caused by earthquakes.

[0043] 3. Prioritizing repairs

[0044] The server calculates the priority of water pipes that need repair based on information obtained from temperature and earthquake data. The priority is then used to create a list of locations that urgently need repairs, and an appropriate repair plan is created based on the results.

[0045] 4. Generate repair manual

[0046] The server uses generative AI to automatically create a repair manual for each identified repair location. This manual includes repair procedures, necessary tools and parts, and points to note. The generative AI provides specific, easy-to-understand content by referring to past repair data and technical literature. This allows even inexperienced or foreign workers to carry out repair work efficiently.

[0047] 5. Efficient hydrographic charting

[0048] The device uses the surveyed data to create an optimal waterway map suitable for modern settlements. This helps design the optimal layout and routing of water pipes. Based on the layout of new water pipes and plans for replacement, the waterworks bureau can formulate long-term maintenance plans.

[0049] 6. Actual repair work

[0050] Users refer to the provided repair manual to carry out specific repair work on-site. The manual contains text and images, and clearly states specific procedures and important points, making it easy for anyone to understand. This enables waterworks bureaus and subcontractors to carry out repair work efficiently and with high quality.

[0051] Through the above process, the system of the present invention can solve the problems of conventional water pipe management and support the realization of sustainable water infrastructure.

[0052] The processing flow will be explained below.

[0053] Processing Steps

[0054] Step 1:

[0055] The server obtains ground temperature data from a satellite data provider. Specifically, the server periodically sends an API request to receive temperature data for a specified area. The received data is recorded in a database as time-series data.

[0056] Step 2:

[0057] The server analyzes the acquired temperature data and calculates the stress on the water pipes. Specifically, it uses an analysis algorithm to identify points of sudden temperature changes and calculates the degree of stress that these points are putting on the water pipes. These stress points are then listed.

[0058] Step 3:

[0059] The server retrieves earthquake information from earthquake data providers. The earthquake data includes the magnitude, frequency, and epicenter of past earthquakes, and is also retrieved by periodically sending API requests. The earthquake data is stored in a database.

[0060] Step 4:

[0061] The server compares temperature data with earthquake data and performs an analysis. Specifically, it overlays stress points with earthquake data to assess the extent to which water pipes in a specific area are exposed to multiple risks. Based on the results of this analysis, it prioritizes areas that need repair.

[0062] Step 5:

[0063] The server uses generative AI to create repair manuals for each section of water pipe that needs repair. Specifically, it references past repair data and technical literature to automatically generate text and images detailing the appropriate repair procedures, necessary tools, parts, and important points to note.

[0064] Step 6:

[0065] The device uses the analysis data and repair manuals to create an efficient waterway map suitable for modern settlements. Specifically, it designs the optimal layout of water pipes based on repair location data provided by the server, and supports long-term maintenance planning.

[0066] Step 7:

[0067] The user performs the actual repair work while referring to the provided repair manual. Specifically, the user proceeds with the work while looking at the procedures and images described in the manual, and completes the repair of the water pipe using the specified tools and parts.

[0068] Through the above processing steps, a system is realized in which the server, terminals, and users work together to effectively manage and repair water pipes.

[0069] Example 1

[0070] 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."

[0071] Conventional water pipe management systems rely on visual inspections and regular maintenance without properly considering changes in ground temperature or the effects of earthquakes, making it difficult to respond immediately when leaks or damage occur. Furthermore, there is a lack of efficient repair work and specific repair procedures, which means that repair work is highly dependent on the experience and skills of workers, often resulting in variations in the quality and efficiency of repair work. This creates problems that make it difficult to ensure the sustainability and efficient management of water infrastructure.

[0072] 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.

[0073] In this invention, the server includes means for collecting ground temperature changes using satellite data, means for preprocessing the collected temperature data and calculating stress on water pipes, means for identifying stress points using an algorithm for detecting sudden temperature changes, means for acquiring earthquake data and integrating it with temperature data to evaluate the risk of water pipes, means for calculating the priority of water pipes requiring repair based on the temperature data and earthquake data, means for generating prompt sentences using a generative AI model for each identified repair location and creating a repair manual, and means for creating an efficient waterway diagram based on the survey data. This enables risk assessment of water pipes and prioritization of repairs that take temperature changes and the effects of earthquakes into account, enabling efficient and high-quality repair work.

[0074] "Satellite Data" means information about the Earth's surface obtained from artificial satellites in Earth orbit.

[0075] "Temperature data" refers to data that records the ground or air temperature over time in a specific area.

[0076] A "stress point" is a location where a water pipe is subjected to particularly high physical or environmental stress.

[0077] "Earthquake data" refers to data that records information about earthquakes, such as their magnitude, epicenter, and the date and time of occurrence.

[0078] "Risk assessment" is the process of quantitatively assessing the risk of water pipe failure or leakage based on specific conditions and data.

[0079] "Priority" refers to the ranking of water pipes that need repair based on their importance.

[0080] A "generative AI model" is an algorithm that uses artificial intelligence techniques to generate an appropriate output for a specific input.

[0081] A "prompt" is a sentence that describes specific instructions or questions for a generative AI model.

[0082] A "repair manual" is a document that contains specific procedures and instructions for efficiently carrying out water pipe repair work.

[0083] An "efficient waterway diagram" is a drawing that designs the optimal layout and routing of water pipes.

[0084] This invention is a system in which the server, terminal, and user components each play different roles, utilizing satellite data and generative AI models to properly manage and efficiently repair water pipes.

[0085] Server configuration and operation

[0086] The server performs the following actions:

[0087] 1. Acquisition of satellite data

[0088] The server periodically obtains ground temperature data using the API of the satellite data provider. For example, it communicates with a common satellite data provider via API to collect temperature data for a specified area.

[0089] 2. Temperature data preprocessing and analysis

[0090] The server receives the collected temperature data in JSON format, checks for outliers, and performs imputation. After preprocessing, the server analyzes the temperature data and calculates the stress on the water pipes. For example, it uses the least squares method to calculate the temperature change rate and identify stress points if there are sudden changes.

[0091] 3. Seismic data acquisition and analysis

[0092] The server uses the Earthquake Research Institute's API to acquire earthquake data, preprocess it, and integrate it with temperature data to perform risk assessment. For example, historical earthquake data and temperature fluctuation data can be integrated to create a risk map.

[0093] 4. Prioritizing repairs

[0094] The server calculates the priority of water pipes that need repair based on temperature and earthquake data. For example, it comprehensively evaluates stress points due to climate change and earthquake risk, and lists high-priority areas.

[0095] 5. Creating repair manuals using generative AI

[0096] The server uses the generative AI model to generate prompts for each identified repair location and automatically creates a repair manual. For example, a prompt such as "Please tell me the procedure for repairing water pipes due to sudden temperature changes" is input into the generative AI and a manual is created.

[0097] Terminal configuration and operation

[0098] The device uses the data sent from the server to perform the following actions:

[0099] 1. Data Receipt and Analysis

[0100] The terminal receives temperature data, earthquake data, and repair priority list obtained from the server.

[0101] 2. Efficient hydrographic charting

[0102] The terminals then use the data they receive to create efficient waterway maps and use GIS (geographic information system) software to design new pipe layouts and replacement plans. For example, ESRI ArcGIS software is used to design optimal routes.

[0103] User Configuration and Behavior

[0104] The user performs the following actions:

[0105] 1. Refer to the repair manual and carry out the work

[0106] The user refers to the repair manual provided by the server on their terminal and carries out the repair work on site. The repair manual contains specific text and images, and clearly shows, for example, "the procedure for repairing and reassembling a damaged part of a water pipe using specific tools."

[0107] 2. Submitting a work report

[0108] Once the repair work is completed, the user uploads a report and photos of the work to the server, allowing the administrator to check the progress of the work in real time.

[0109] With the above configuration and operation, the system of the present invention realizes efficient management and repair of water pipes taking into account the effects of temperature changes and earthquakes, and supports the realization of sustainable water infrastructure.

[0110] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0111] Step 1:

[0112] Data Acquisition

[0113] The server periodically obtains ground temperature data using the satellite data provider's API. The input is the coordinate data and API key of the specified area, and the output is the temperature data (in JSON format) for that area. The server sends a "GET request" to the API to collect the temperature data.

[0114] Step 2:

[0115] Temperature data preprocessing

[0116] The server receives the acquired temperature data and checks for outliers and missing values. The input is JSON-formatted temperature data, and the output is preprocessed clean data. The server filters outliers and fills in approximate values ​​if necessary.

[0117] Step 3:

[0118] Stress Calculation

[0119] The server analyzes the preprocessed temperature data and calculates the stress on the water pipes. The input is clean data, and the output is the stress calculation result. Specifically, the server quantifies the rapidity of temperature changes, and determines that rapid fluctuations indicate high stress. For example, it calculates the rate of temperature change over the course of a day and calculates a stress score based on that.

[0120] Step 4:

[0121] Identifying stress points

[0122] The server identifies stress points based on the stress score obtained from the temperature data analysis. The input is the stress calculation result, and the output is the location information of the stress points. The area where a sudden temperature change was detected is identified and recorded as geographic information.

[0123] Step 5:

[0124] Seismic data acquisition and preprocessing

[0125] The server retrieves earthquake data using the Earthquake Research Institute's API. The input is the coordinate data of the specified area and the API key, and the output is earthquake data (JSON format). The earthquake data is also preprocessed to check for outliers and missing values.

[0126] Step 6:

[0127] Risk Assessment

[0128] The server integrates preprocessed seismic data with temperature data to assess the risk of water pipes. The inputs are preprocessed seismic data and temperature data, and the output is the risk assessment results. Specifically, a risk map is created using past earthquake data and temperature fluctuation data.

[0129] Step 7:

[0130] Repair prioritization

[0131] The server calculates the priority of water pipes that need repair based on the risk assessment results. The input is the risk assessment results, and the output is a repair priority list. The stress score and risk level are combined to create a list of high-priority areas.

[0132] Step 8:

[0133] Creation of repair manuals

[0134] The server uses a generative AI model to create prompts for each identified repair location and generate a repair manual. The input is the prompt (e.g., "Please tell me the procedure for repairing water pipes due to sudden temperature changes"), and the output is the repair manual. The AI ​​model outputs specific repair procedures based on the prompts.

[0135] Step 9:

[0136] Efficient hydrographic charting

[0137] The terminal creates an efficient hydrographic map based on the data sent from the server. The input is the risk assessment results and repair priority list, and the output is the new hydrographic map. GIS software is used to design the optimal water pipe layout and routing.

[0138] Step 10:

[0139] Repair work

[0140] The user refers to the repair manual and performs specific repair work on-site. The input is the repair manual, and the output is a repair completion report. The user follows the repair procedure and repairs the water pipe using the necessary tools and parts. After the work is completed, the user uploads the report and photos to the server.

[0141] (Application example 1)

[0142] 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."

[0143] Conventional water pipe management systems have difficulty properly detecting and predicting abnormal temperature fluctuations and stress caused by earthquakes, requiring a great deal of time and effort to prioritize repairs and create specific repair procedures. Furthermore, ensuring the quality of repair work requires experienced workers, making efficient work difficult. Furthermore, complex environments such as factories require real-time monitoring of pipe conditions and rapid response, but current systems are inadequate. Therefore, a new management system is needed that monitors temperature fluctuations and vibrations in real time and uses generative AI to present efficient repair procedures.

[0144] 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.

[0145] In this invention, the server includes means for collecting ground temperature changes using satellite data, means for analyzing the collected temperature data to calculate stress on water pipes, means for predicting the risk of water leakage based on the stress data, means for acquiring earthquake data and combining it with temperature data to prioritize water pipes that need repair, means for creating repair manuals for the identified repair locations using generative AI, means for creating efficient waterway maps suitable for modern areas, means for collecting and analyzing sensor data (pipe temperature and vibration) in real time, and means for displaying repair procedures automatically generated using generative AI on a wearable device. This enables efficient and high-quality repair work by quickly and accurately identifying areas that need repair and providing specific repair procedures using generative AI.

[0146] "Satellite data" refers to data obtained from Earth observation satellites, including temperature changes on the Earth's surface and atmosphere, as well as information on topography and the environment.

[0147] "Ground temperature change" refers to the phenomenon in which the temperature of the ground surface or underground in a particular area fluctuates over time.

[0148] "Stress on water pipes" refers to changes in physical loads and pressures on water pipes, especially pressures affected by environmental conditions and external factors.

[0149] "Risk of water leakage" refers to the results of assessing the danger and probability of water leaking from water pipes.

[0150] "Earthquake data" refers to data that includes information such as the magnitude, epicenter, seismic intensity, and vibration pattern of an earthquake.

[0151] A "repair manual" is an instruction document that details repair procedures, precautions, necessary tools and parts, etc. for specified repair areas.

[0152] "Generative AI" refers to artificial intelligence technology that automatically generates new information and suggestions based on large amounts of data and past knowledge.

[0153] "Modern regions" refer to settlements and cities with current living infrastructure and infrastructure.

[0154] A "waterway map" is a map showing the layout, routes, and connection points of water pipes and distribution pipes.

[0155] "Sensor data" refers to physical measurements taken in real time from measuring instruments such as temperature sensors or vibration sensors.

[0156] "Real-time collection" refers to collecting data immediately at the moment it is generated.

[0157] "Analyzing" means analyzing collected data to extract meaningful information.

[0158] A "wearable terminal" is an electronic device worn by a worker that displays information and allows data entry.

[0159] This invention is a system for efficiently managing and repairing pipelines in factories, utilizing satellite data, sensor data, and generative AI technology. Each component is described in detail below.

[0160] 1. Satellite data acquisition and analysis

[0161] The server periodically obtains data on temperature changes on the Earth's surface from Earth observation satellites. This data is obtained using an external satellite data provider. The server analyzes the obtained data to understand the temperature fluctuation patterns around the factory. This temperature data is used to detect sudden temperature changes in specific areas. Python data analysis libraries (e.g., Pandas, NumPy) are used for the analysis.

[0162] 2. Sensor data collection and analysis

[0163] The server collects data in real time from temperature and vibration sensors installed on each pipe in the factory. This sensor data is analyzed immediately by the server. When temperature fluctuations or abnormal vibrations are detected, it indicates that a particular pipe is under high stress. This analysis is performed using machine learning libraries (e.g., Scikit-learn).

[0164] 3. Prioritizing repairs

[0165] The server calculates the priority of pipes that need repair based on information obtained from temperature data and sensor data. This allows for the creation of a repair plan that prioritizes pipes at greatest risk. The calculation is performed using database software (e.g., MySQL®) and an algorithm based on weighted data is applied.

[0166] 4. Automatic generation of repair procedures

[0167] For each identified repair location, the server automatically generates a repair procedure using generative AI. GPT-4 (registered trademark) is used as the generative AI model. This model generates specific repair procedures by referring to past repair data and technical literature. For example, a procedure can be generated by entering a prompt such as the following:

[0168] "Please provide detailed instructions for the following repair. The location is a cooling pipe in Section A in the north of the factory, and the following conditions are present: temperature spikes and strong vibrations. The tools required are a 20mm wrench and a screwdriver."

[0169] 5. Display of repair procedures

[0170] The repair procedures obtained by generative AI are displayed in real time on wearable devices such as smart glasses. Using smart glasses allows workers to check the necessary information while using both hands, improving work efficiency and accuracy. Suitable devices for use include Google® Glass® and Vuzix.

[0171] 6. Actual repair work

[0172] The user performs specific repair work on-site while referring to the repair procedures displayed on the smart glasses. The repair procedures include text and images, and specific steps and points to note are clearly indicated, improving work efficiency and enabling even inexperienced workers to perform high-quality work.

[0173] This system is expected to improve the efficiency of pipeline management within the factory and enable repair work to be carried out quickly and accurately.

[0174] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0175] Step 1:

[0176] The server periodically obtains surface temperature data from an external satellite data provider.

[0177] Input: Temperature data from Earth observation satellites.

[0178] Data processing: Organize the temperature data as time series data.

[0179] Output: A dataset containing temperature variation patterns for a specific region.

[0180] Step 2:

[0181] The server analyzes the acquired temperature data using Python data analysis libraries (Pandas, NumPy) and identifies sudden temperature changes.

[0182] Input: A curated temperature dataset.

[0183] Data processing: Data cleaning and application of algorithms to detect sudden temperature changes.

[0184] Output: A list of points with sudden temperature changes.

[0185] Step 3:

[0186] The server collects data in real time from temperature and vibration sensors installed on each pipe in the factory.

[0187] Input: Real-time data from temperature and vibration sensors.

[0188] Data processing: Data acquisition and format conversion of temperature and vibration data.

[0189] Output: Real-time captured temperature and vibration data.

[0190] Step 4:

[0191] The server uses the Scikit-learn library to analyze sensor data acquired in real time and detect abnormal temperature fluctuations and vibrations.

[0192] Input: Real-time temperature and vibration data.

[0193] Data processing: Anomaly detection using machine learning algorithms.

[0194] Output: A list of areas where abnormal temperature fluctuations and vibrations are occurring.

[0195] Step 5:

[0196] The server combines the acquired temperature and sensor data with seismic data to calculate the priority of pipes that need repair.

[0197] Inputs: temperature data, sensor data, seismic data.

[0198] Data processing: Data integration and application of priority calculation algorithms.

[0199] Output: A prioritized list of pipes needing repair.

[0200] Step 6:

[0201] The server uses generation AI to automatically generate repair procedures for the identified repair areas.

[0202] Inputs: Identified repair area, environmental conditions, tool list.

[0203] Data processing: Generative AI model (GPT-4) was used to generate instructions based on prompts. "Please tell me in detail the procedure for the next repair. The location is a cooling pipe in Section A in the north of the factory, and the following conditions apply: temperature spike, strong vibration. The tools required are a 20mm wrench and a screwdriver."

[0204] Output: Detailed repair instructions (with text and images).

[0205] Step 7:

[0206] The user displays the generated repair procedure manual on a wearable device such as smart glasses and performs the repair work while referring to it.

[0207] Input: detailed repair instructions.

[0208] Data processing: Converting data into a display format suitable for wearable devices.

[0209] Output: Repair instructions displayed on the smart glasses.

[0210] In this way, the system can monitor temperature fluctuations and vibrations in real time and use generative AI to provide efficient repair procedures.

[0211] 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.

[0212] The present invention is a system for efficiently managing and repairing water pipes by utilizing satellite data, artificial intelligence technology (generative AI), and an emotion engine. This system divides the roles of server, terminal, and user, and each performs different processing steps to achieve optimal water pipe management. Specific embodiments are shown below.

[0213] Satellite data acquisition and analysis

[0214] The server periodically obtains ground temperature change data from a satellite data provider. This data is collected as time-series data of temperature fluctuations in a specific area and stored on the server. The server then analyzes the temperature data and calculates the stress on the water pipes. Stress points are identified using an algorithm that detects sudden changes in temperature data. For example, if a large temperature change occurs in a certain area in a short period of time, it can be determined that the water pipes in that area are under high stress.

[0215] Seismic data acquisition and analysis

[0216] The server retrieves earthquake data from reliable sources, such as seismological research institutes. This data includes information such as the magnitude, frequency, and epicenter of past earthquakes. The server analyzes this earthquake data with temperature data to prioritize water pipes that need repair. Based on earthquake vibrations and temperature changes, the server evaluates the risk of water pipes in a particular area.

[0217] Repair prioritization

[0218] The server uses temperature and earthquake data to create a priority list of water pipes that need repair, and then creates an appropriate repair plan based on this list.

[0219] Generate repair manuals

[0220] The server uses generation AI to automatically generate repair manuals. The generated repair manuals contain repair procedures, necessary tools and parts, and important points to note, all in text and with images. This allows even inexperienced or foreign workers to carry out repair work efficiently.

[0221] Efficient hydrographic charting

[0222] The terminal uses the analysis data from the server to create an efficient waterway map suitable for modern settlements, which the waterworks bureau uses when formulating long-term waterway development plans.

[0223] Emotion engine integration

[0224] The server also integrates an emotion engine to detect the user's emotions in real time while they are working on the repairs. The emotion engine evaluates the user's stress level and satisfaction through facial recognition and voice analysis. For example, if the user expresses high levels of stress, the emotion engine adjusts the instructions in the repair manual to be simpler. Also, if the user expresses high levels of satisfaction, the engine appropriately adjusts the progress of the repair work based on that feedback.

[0225] The actual repair work

[0226] Users refer to the provided repair manual to carry out the actual repair work. The manual contains detailed descriptions of specific procedures, tools, parts, and precautions to be taken, allowing the work to be carried out efficiently and safely. In addition, the emotion engine adjusts work instructions as needed based on real-time evaluations, reducing user stress and improving the quality of work.

[0227] Through the above process, the server, terminals, and users work together to create a system that effectively manages and repairs water pipes.

[0228] The processing flow will be explained below.

[0229] Processing Steps

[0230] Step 1:

[0231] The server obtains ground temperature data from a satellite data provider. Specifically, the server periodically sends an API request to receive temperature data for a specified area. The received data is recorded in a database as time-series data.

[0232] Step 2:

[0233] The server analyzes the acquired temperature data and calculates the stress on the water pipes. Specifically, it uses an analysis algorithm to identify points of sudden temperature changes and calculates the degree of stress that these points are putting on the water pipes. These stress points are then listed.

[0234] Step 3:

[0235] The server retrieves earthquake information from earthquake data providers. The earthquake data includes the magnitude, frequency, and epicenter of past earthquakes, and is also retrieved by periodically sending API requests. The earthquake data is stored in a database.

[0236] Step 4:

[0237] The server then performs an analysis by overlaying temperature data and earthquake data. Specifically, it compares stress points with earthquake data to assess the extent to which water pipes in a particular area are exposed to multiple risks. This allows it to prioritize areas that need repairs.

[0238] Step 5:

[0239] The server uses generative AI to create a repair manual for each prioritized repair area. Specifically, it references past repair data and technical literature to automatically generate text and images detailing the appropriate repair procedures, necessary tools, parts, and important points to note.

[0240] Step 6:

[0241] The device uses data provided by the server to create an efficient waterway map suitable for modern settlements. Specifically, it uses the analysis data to design the optimal layout and route of water pipes, supporting long-term development plans.

[0242] Step 7:

[0243] The server runs an emotion engine to recognize the user's emotions in real time during repair work. The emotion engine detects the user's stress level and satisfaction through facial recognition and voice analysis.

[0244] Step 8:

[0245] The server adjusts the instructions in the repair manual based on the emotion engine's evaluation results. For example, if the user's stress level is high, the instructions are simplified. Also, if the user's satisfaction level is high, the server adjusts the progress of the repair work based on that feedback.

[0246] Step 9:

[0247] The user refers to the provided repair manual and performs the actual repair work. Specifically, the user proceeds with the work while looking at the procedures and images described in the manual, and completes the work using the specified tools and parts. Based on real-time evaluation by the emotion engine, the work instructions are adjusted as needed, reducing user stress and improving work efficiency.

[0248] Through the above processing steps, a system is realized in which the server, terminals, and users work together to effectively manage and repair water pipes.

[0249] Example 2

[0250] 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."

[0251] The management and repair of existing water pipes often relies on human resources, resulting in issues with efficiency and accuracy. Furthermore, there is a lack of methods to properly assess stress caused by external factors such as temperature changes and earthquakes and identify areas that should be prioritized for repair. Furthermore, there is a lack of real-time support to reduce user stress during repair work and improve the quality of work.

[0252] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting ground temperature changes using satellite data, means for analyzing the collected temperature data to calculate stress on water pipes, means for acquiring earthquake data and multiplying it with the temperature data to prioritize water pipes that need repair, means for creating repair manuals for the identified repair locations using a generation AI, and means for monitoring the user's emotions during repair work in real time and dynamically adjusting instructions in the repair manual as necessary. This enables efficient and accurate management and repair of water pipes.

[0253] "Satellite data" is data obtained from artificial satellites to observe the Earth's surface and atmosphere.

[0254] "Temperature change data" is time series data that shows how the ground temperature in a particular area changes over time.

[0255] "Stress on water pipes" refers to the physical loads and pressures that water pipes are subjected to due to external factors such as temperature changes and earthquakes.

[0256] "Water leakage risk" is an evaluation index that indicates the degree of possibility that a water pipe will break and cause a water leak.

[0257] "Earthquake Data" means data containing information on the magnitude, frequency, and epicenters of past and present earthquakes.

[0258] "Water pipes in need of repair" are water pipes that have been identified as being in need of immediate repair due to high stress caused by temperature changes and earthquakes.

[0259] "Generative AI" is a type of artificial intelligence technology that refers to algorithms that generate natural-looking sentences and images based on specific prompts.

[0260] A "repair manual" is a document that describes the procedures required to efficiently carry out water pipe repair work, the tools and parts to be used, and points to note.

[0261] An "efficient waterway map" is a map that optimizes the layout and routing of water pipes and allows for efficient management and maintenance of water supply systems in settlements and cities.

[0262] The "Emotion Engine" is a technology that assesses a user's stress level and satisfaction in real time through facial recognition and voice analysis.

[0263] "User" refers to the worker who actually carries out the water pipe repair work.

[0264] A "server" is a computer system that collects, analyzes, and operates the generated AI.

[0265] A "terminal" is a computer device that creates and displays hydrographic charts based on analysis data from the server.

[0266] This invention is a system that efficiently manages and repairs water pipes by utilizing satellite data, artificial intelligence technology (generative AI), and an emotion engine. This system divides the roles of server, terminal, and user, and each performs different processing steps to achieve optimal water pipe management.

[0267] Satellite data acquisition and analysis

[0268] The server periodically obtains ground temperature change data from a satellite data provider. This data is collected as time-series data of temperature fluctuations in a specific area and stored on the server. The Python scikit-learn library is used to analyze the temperature data and calculate the stress on the water pipes. For example, the server obtains data in JSON format from "https: / / api.satelliteprovider.com / temperature" and converts it into a Pandas data frame. Furthermore, a Z-score is calculated to detect outliers in the data.

[0269] Seismic data acquisition and analysis

[0270] The server retrieves earthquake data from earthquake research institutes and earthquake data providers via API. This data includes information on the magnitude, frequency, and epicenter of past earthquakes. The server combines this data with temperature data and analyzes it to assess the risk to water pipes in a specific area. Specifically, the server downloads earthquake data in CSV format from "https: / / earthquake.usgs.gov / fdsnws / event / 1 / query" and merges it with the temperature data for analysis. Python's NumPy and Pandas are used for the analysis.

[0271] Repair prioritization

[0272] The server generates a list of high-risk water pipes based on temperature and earthquake data. Based on this list, it prioritizes the pipes that need repair and creates a repair plan. Specifically, the server calculates a repair necessity score based on the analysis results and sorts the list in descending order of score. The results are saved in a MySQL database.

[0273] Generate repair manuals

[0274] The server uses a generative AI (e.g., GPT-4) to automatically generate a detailed repair manual. The repair procedure, necessary tools and parts, and precautions are written in text and images. As an example of a specific prompt, "Please generate a repair procedure, including necessary tools, parts, and precautions," is input to GPT-4, and the generated text is formatted in HTML.

[0275] Efficient hydrographic charting

[0276] The terminal uses design software such as AutoCAD to create efficient hydrographic diagrams based on the analysis data received from the server. This enables long-term water pipe maintenance planning. Specifically, the terminal runs an AutoCAD script to draw the hydrographic diagram based on the coordinate data received from the server. The generated diagram is saved as a PDF file.

[0277] Emotion engine integration

[0278] The server integrates an emotion engine (e.g., Affdex API) to monitor the user's emotions in real time while they are working on repairs. It uses facial recognition and voice analysis to evaluate their stress level and satisfaction. Specifically, the server captures the user's webcam footage and microphone input, and performs emotion analysis using the Affdex API. Based on the evaluation results, the content of the repair manual is dynamically adjusted.

[0279] The actual repair work

[0280] The user performs actual repair work by referring to the provided repair manual. If the emotion engine detects the user's stress, the work instructions are adjusted in real time. Specifically, the user follows the specific steps in the repair manual and performs the repair work using specified tools (e.g., pipe wrench, plumbing tape, etc.). If the emotion engine detects stress during the work, the manual instructions may be simplified.

[0281] Through the above steps, a system is realized in which the server, terminals, and users work together to efficiently and effectively manage and repair water pipes.

[0282] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0283] Step 1:

[0284] (Satellite data acquisition)

[0285] The server connects to the satellite data provider's API to periodically obtain data on ground temperature changes in a specific area.

[0286] Input: API endpoint URL, authentication information

[0287] Specific operation: The server retrieves data in JSON format from "https: / / api.satelliteprovider.com / temperature".

[0288] Data processing: Convert the acquired JSON data into a Pandas data frame.

[0289] Output: Formatted temperature change data is obtained.

[0290] Step 2:

[0291] (Temperature data analysis)

[0292] The server analyzes the temperature change data and collects and stores the temperature fluctuations of the ground in a specific area as time-series data.

[0293] Input: Formatted temperature change data

[0294] Specific operation: The server uses Python's scikit-learn library to detect outliers using Z scores.

[0295] Data calculation: Calculate stress points and perform risk assessments for specific areas.

[0296] Output: Stress points on the water pipes are identified.

[0297] Step 3:

[0298] (Acquisition of earthquake data)

[0299] The server obtains earthquake data from earthquake research institutes and earthquake data providers via API.

[0300] Input: API endpoint URL, authentication information

[0301] Specific operation: The server downloads earthquake data in CSV format from "https: / / earthquake.usgs.gov / fdsnws / event / 1 / query".

[0302] Data processing: Convert the downloaded CSV data into a Pandas data frame.

[0303] Output: Formatted seismic data.

[0304] Step 4:

[0305] (Analysis of temperature and seismic data)

[0306] The server combines temperature and earthquake data to assess how much risk water pipes in a particular area are at.

[0307] Input: Formatted temperature data, formatted seismic data

[0308] What happens: The server merges the data using NumPy and Pandas and performs a risk assessment.

[0309] Data calculation: Based on the integrated data, calculate the priority of water pipes that need repair.

[0310] Output: Risk assessment results and a priority list are generated.

[0311] Step 5:

[0312] (Prioritizing repairs)

[0313] Based on the risk assessment results, the server generates a list of water pipes that need repair.

[0314] Input: Risk assessment results, priority list

[0315] Specific operation: The server calculates the repair necessity score and sorts the list by highest score.

[0316] Data processing: Save the list in a MySQL database.

[0317] Output: A list of repair priorities is stored in the database.

[0318] Step 6:

[0319] (Generate repair manual)

[0320] The server automatically generates repair manuals using generative AI (e.g., GPT-4 model).

[0321] Input: Repair requirements, construction details

[0322] Specific action: GPT-4 is given the prompt, "Generate repair instructions, including required tools, parts, and precautions."

[0323] Data calculation: The generated repair manual is formatted into HTML format.

[0324] Output: A detailed repair manual is generated.

[0325] Step 7:

[0326] (Efficient hydrographic charting)

[0327] The terminal creates an efficient hydrographic chart based on the analysis data received from the server.

[0328] Input: Repair priority data, coordinate data

[0329] Specific operation: The terminal draws a hydrographic chart using AutoCAD.

[0330] Data processing: Save the generated hydrographic chart in PDF format.

[0331] Output: An efficient hydrographic chart is generated in a PDF file.

[0332] Step 8:

[0333] (Emotion engine integration)

[0334] The server uses an emotion engine to monitor the user's emotions in real time during repair work.

[0335] Input: User's webcam video and audio data

[0336] Specific operation: The server uses the Affdex API to perform sentiment analysis and evaluate stress levels.

[0337] Data Calculation: Dynamically adjust repair manuals based on the user's stress level.

[0338] Output: Repair instructions tailored to the user's emotional state are provided.

[0339] Step 9:

[0340] (Actual repair work)

[0341] The user performs the actual repair work by referring to the provided repair manual.

[0342] Input: Detailed repair manual, tools used

[0343] Specific operation: The user follows the steps in the manual and performs the repair using the specified tools (e.g., pipe wrench, plumbing tape).

[0344] Data Calculation: If the emotion engine detects stress, it will automatically adjust its instructions.

[0345] Output: Repair work completed and work quality improved.

[0346] (Application example 2)

[0347] 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."

[0348] Conventional water pipe management and repair systems have difficulty efficiently identifying leak risks and prioritizing repairs. Furthermore, the quality of repair work varies depending on the experience and skills of the workers, and workers are subject to significant stress and strain. To address these issues, more accurate analysis and planning is required by utilizing satellite and earthquake data. Furthermore, a new challenge is being faced: analyzing workers' emotions in real time to improve the quality and efficiency of work.

[0349] The specific processing by the specific 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 ground temperature changes using satellite data, means for analyzing the collected temperature data to calculate stress on pipes, means for predicting the risk of water leakage based on the stress data, means for acquiring earthquake data and combining it with temperature data to prioritize pipes in need of repair, means for creating repair manuals for the identified repair locations using generative AI, emotion analysis means for evaluating user emotions in real time when performing repair work based on the manual, and means for creating efficient piping diagrams suitable for modern settlements. This not only efficiently identifies areas in need of repair and provides repair manuals, but also analyzes worker emotions and adjusts instructions, thereby improving work efficiency and quality and reducing user stress.

[0350] "Satellite data" refers to information about the Earth's surface and atmosphere collected from artificial satellites, and is particularly data that can acquire temperature changes and environmental conditions in real time.

[0351] "Temperature data" is information that records changes in the temperature of the earth's surface or an object, and represents temperature fluctuations in a specific area over time.

[0352] "Stress" refers to the physical load or pressure on pipes and equipment, and indicates the risk caused by sudden temperature changes and vibrations in particular.

[0353] "Earthquake data" refers to data that includes information such as the magnitude, epicenter, and frequency of shaking caused by earthquakes.

[0354] "Generative AI" is a type of artificial intelligence technology that has the ability to generate new data and text from given information.

[0355] A "repair manual" is an instruction manual that describes the procedures for carrying out repair work, the necessary tools, parts, and precautions.

[0356] "Emotion analysis" is a technology that assesses a user's emotional state in real time through facial recognition and voice analysis, measuring stress and satisfaction.

[0357] A "piping diagram" is a map showing the layout and connections of water pipes and other pipes, and is created for efficient pipe management and repair planning.

[0358] "User" refers to the worker who actually performs the piping repair work by referring to the provided repair manual.

[0359] The present invention is a system that efficiently manages and repairs pipes by utilizing satellite data, artificial intelligence technology (generative AI), and an emotion engine. Specific embodiments are described below.

[0360] Satellite data acquisition and analysis

[0361] First, the server periodically obtains surface temperature change data from a satellite data provider. This data represents temperature fluctuations in a specific area and is obtained in real time. The server analyzes the temperature data and calculates the stress on the pipes. To do this, an algorithm is used to detect sudden changes in temperature data. For example, if a large temperature change is observed in a certain area in a short period of time, it is determined that the pipes in that area are under high stress.

[0362] Seismic data acquisition and analysis

[0363] The server retrieves earthquake data from reliable sources, such as seismological research institutes. This data includes information on the magnitude, frequency, and epicenter of past earthquakes. The server analyzes the earthquake data together with temperature data to prioritize pipes that need repair. The seismic vibrations and temperature changes are used to assess the risk of pipes in a particular area.

[0364] Repair prioritization

[0365] Based on the analysis results, the server creates a list of pipes that need repair in order of priority, and then creates an appropriate repair plan based on this list.

[0366] Generate repair manuals

[0367] Next, the server uses the generation AI to automatically generate a repair manual. The generated repair manual contains repair procedures, necessary tools and parts, important points to note, and other information in text and images. For example, a manual can be created by inputting the following prompts into the generation AI:

[0368] "Repair the following stress points: [(20, 30), (40, 50), (70, 80)]. Generate detailed instructions including tools, components, and safety notes."

[0369] This will enable even inexperienced workers or foreign workers to carry out repair work efficiently.

[0370] Emotion engine integration

[0371] The server also integrates an emotion engine to detect the user's emotions in real time while they are performing repair work. The emotion engine uses a camera and microphone to recognize the worker's face and analyze their voice. If the work is difficult or indicates high stress, the emotion engine will simplify the instructions in the repair manual. For example, if it determines that the user is experiencing high stress, it will change complex procedures to simpler instructions.

[0372] The actual repair work

[0373] Users refer to the provided repair manual when carrying out actual repair work. Based on real-time evaluations by the emotion engine, work instructions are adjusted as needed, reducing user stress and improving the quality of work. Furthermore, efficient piping diagrams suitable for modern settlements are created and used for long-term maintenance planning.

[0374] In this way, the collaboration between servers, terminals, and users enables efficient pipe management and repair. Specific hardware and software are used for collecting and analyzing each piece of data. Specifically, Apache Spark (registered trademark) is used for data analysis, TENSORFLOW (registered trademark) and PyTorch for AI analysis, and OpenFace and Wav2Vec for emotion analysis.

[0375] The detailed description of the embodiments clarifies the technical scope of the invention, supports the scope of patent protection, and serves as a reference for other users to understand and implement the invention.

[0376] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0377] Step 1:

[0378] The server periodically obtains data on changes in surface temperature over a specific area from a satellite data provider. The input is temperature data from the satellite data provider, and the output is time-series data showing changes in surface temperature. The server stores this data and uses it for further analysis.

[0379] Step 2:

[0380] The server analyzes the acquired temperature data and calculates the stress on the pipe. Specifically, it runs an algorithm that detects sudden changes in the temperature data. The input is ground temperature data, and the output is data indicating stress points on the pipe.

[0381] Step 3:

[0382] The server retrieves earthquake data from a reliable source such as an earthquake research institute. The input is earthquake data including the magnitude, frequency, and epicenter of past earthquakes, and the output is data evaluating the impact of earthquakes. The server uses this data for further analysis.

[0383] Step 4:

[0384] The server analyzes temperature and earthquake data and prioritizes pipes that need repair. The input is temperature and earthquake data, and the output is a list of pipes that need repair and their priorities.

[0385] Step 5:

[0386] The server uses a generative AI to create a repair manual for the identified repair area. Specifically, it inputs the following prompt sentence into the generative AI model:

[0387] "Repair the following stress points: [(20, 30), (40, 50), (70, 80)]. Generate detailed instructions including tools, components, and safety notes."

[0388] The input is a list of repairs (stress points), and the output is a detailed repair manual, including text and images, describing the tools and parts required, and important points to note.

[0389] Step 6:

[0390] The user refers to the repair manual and performs the repair work. The input is the repair manual provided by the server, and the output is the progress of the actual repair work. The user follows the manual and performs the repair work efficiently.

[0391] Step 7:

[0392] During the repair work, the server uses an emotion engine to analyze the user's emotions in real time. Specifically, it uses a camera and microphone to recognize the user's face and analyze their voice. The input is real-time facial images and voice data obtained from the camera and microphone, and the output is data indicating the user's emotional state.

[0393] Step 8:

[0394] The server adjusts the instructions in the repair manual based on the user's emotional data. For example, if the user is feeling high stress, it simplifies complex procedures. The input is the user's emotional state, and the output is the adjusted repair manual.

[0395] Step 9:

[0396] The server compiles the final repair results and creates an efficient piping diagram suitable for modern settlements. The input is the repair work results data, and the output is a new piping diagram. This piping diagram is used for long-term maintenance planning.

[0397] 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.

[0398] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0399] 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.

[0400] [Second embodiment]

[0401] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0402] 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.

[0403] 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).

[0404] 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.

[0405] 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.

[0406] 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).

[0407] 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.

[0408] 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.

[0409] 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.

[0410] 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.

[0411] 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.

[0412] 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."

[0413] This invention is a system that utilizes satellite data and artificial intelligence technology (generative AI) to efficiently manage and repair water pipes. In this system, the server, terminal, and user each play different roles, and optimal water pipe management is achieved through each processing step. How the present invention is implemented is described in detail below.

[0414] 1. Satellite data acquisition and analysis

[0415] The server periodically obtains ground temperature data from a satellite data provider, collecting time-series data on temperature fluctuations in a specific area. The server then analyzes this temperature data internally to calculate the stress on the water pipes. Stress points are identified using an algorithm that detects sudden changes in temperature data. For example, if a certain area experiences a sudden change in temperature, it can be determined that the water pipes in that area are under high stress.

[0416] 2. Seismic data acquisition and analysis

[0417] The server acquires earthquake data from reliable data sources such as the Earthquake Research Institute. It collects information such as the magnitude, frequency, and epicenter of past earthquakes. It then matches the acquired earthquake data with temperature data to prioritize the locations of water pipes that are most in need of repair. It then assesses the degree of risk to water pipes in the identified area based on vibrations and temperature changes caused by earthquakes.

[0418] 3. Prioritizing repairs

[0419] The server calculates the priority of water pipes that need repair based on information obtained from temperature and earthquake data. The priority is then used to create a list of locations that urgently need repairs, and an appropriate repair plan is created based on the results.

[0420] 4. Generate repair manual

[0421] The server uses generative AI to automatically create a repair manual for each identified repair location. This manual includes repair procedures, necessary tools and parts, and points to note. The generative AI provides specific, easy-to-understand content by referring to past repair data and technical literature. This allows even inexperienced or foreign workers to carry out repair work efficiently.

[0422] 5. Efficient hydrographic charting

[0423] The device uses the surveyed data to create an optimal waterway map suitable for modern settlements. This helps design the optimal layout and routing of water pipes. Based on the layout of new water pipes and plans for replacement, the waterworks bureau can formulate long-term maintenance plans.

[0424] 6. Actual repair work

[0425] Users refer to the provided repair manual to carry out specific repair work on-site. The manual contains text and images, and clearly states specific procedures and important points, making it easy for anyone to understand. This enables waterworks bureaus and subcontractors to carry out repair work efficiently and with high quality.

[0426] Through the above process, the system of the present invention can solve the problems of conventional water pipe management and support the realization of sustainable water infrastructure.

[0427] The processing flow will be explained below.

[0428] Processing Steps

[0429] Step 1:

[0430] The server obtains ground temperature data from a satellite data provider. Specifically, the server periodically sends an API request to receive temperature data for a specified area. The received data is recorded in a database as time-series data.

[0431] Step 2:

[0432] The server analyzes the acquired temperature data and calculates the stress on the water pipes. Specifically, it uses an analysis algorithm to identify points of sudden temperature changes and calculates the degree of stress that these points are putting on the water pipes. These stress points are then listed.

[0433] Step 3:

[0434] The server retrieves earthquake information from earthquake data providers. The earthquake data includes the magnitude, frequency, and epicenter of past earthquakes, and is also retrieved by periodically sending API requests. The earthquake data is stored in a database.

[0435] Step 4:

[0436] The server compares temperature data with earthquake data and performs an analysis. Specifically, it overlays stress points with earthquake data to assess the extent to which water pipes in a specific area are exposed to multiple risks. Based on the results of this analysis, it prioritizes areas that need repair.

[0437] Step 5:

[0438] The server uses generative AI to create repair manuals for each section of water pipe that needs repair. Specifically, it references past repair data and technical literature to automatically generate text and images detailing the appropriate repair procedures, necessary tools, parts, and important points to note.

[0439] Step 6:

[0440] The device uses the analysis data and repair manuals to create an efficient waterway map suitable for modern settlements. Specifically, it designs the optimal layout of water pipes based on repair location data provided by the server, and supports long-term maintenance planning.

[0441] Step 7:

[0442] The user performs the actual repair work while referring to the provided repair manual. Specifically, the user proceeds with the work while looking at the procedures and images described in the manual, and completes the repair of the water pipe using the specified tools and parts.

[0443] Through the above processing steps, a system is realized in which the server, terminals, and users work together to effectively manage and repair water pipes.

[0444] Example 1

[0445] 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."

[0446] Conventional water pipe management systems rely on visual inspections and regular maintenance without properly considering changes in ground temperature or the effects of earthquakes, making it difficult to respond immediately when leaks or damage occur. Furthermore, there is a lack of efficient repair work and specific repair procedures, which means that repair work is highly dependent on the experience and skills of workers, often resulting in variations in the quality and efficiency of repair work. This creates problems that make it difficult to ensure the sustainability and efficient management of water infrastructure.

[0447] 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.

[0448] In this invention, the server includes means for collecting ground temperature changes using satellite data, means for preprocessing the collected temperature data and calculating stress on water pipes, means for identifying stress points using an algorithm for detecting sudden temperature changes, means for acquiring earthquake data and integrating it with temperature data to evaluate the risk of water pipes, means for calculating the priority of water pipes requiring repair based on the temperature data and earthquake data, means for generating prompt sentences using a generative AI model for each identified repair location and creating a repair manual, and means for creating an efficient waterway diagram based on the survey data. This enables risk assessment of water pipes and prioritization of repairs that take temperature changes and the effects of earthquakes into account, enabling efficient and high-quality repair work.

[0449] "Satellite Data" means information about the Earth's surface obtained from artificial satellites in Earth orbit.

[0450] "Temperature data" refers to data that records the ground or air temperature over time in a specific area.

[0451] A "stress point" is a location where a water pipe is subjected to particularly high physical or environmental stress.

[0452] "Earthquake data" refers to data that records information about earthquakes, such as their magnitude, epicenter, and the date and time of occurrence.

[0453] "Risk assessment" is the process of quantitatively assessing the risk of water pipe failure or leakage based on specific conditions and data.

[0454] "Priority" refers to the ranking of water pipes that need repair based on their importance.

[0455] A "generative AI model" is an algorithm that uses artificial intelligence techniques to generate an appropriate output for a specific input.

[0456] A "prompt" is a sentence that describes specific instructions or questions for a generative AI model.

[0457] A "repair manual" is a document that contains specific procedures and instructions for efficiently carrying out water pipe repair work.

[0458] An "efficient waterway diagram" is a drawing that designs the optimal layout and routing of water pipes.

[0459] This invention is a system in which the server, terminal, and user components each play different roles, utilizing satellite data and generative AI models to properly manage and efficiently repair water pipes.

[0460] Server configuration and operation

[0461] The server performs the following actions:

[0462] 1. Acquisition of satellite data

[0463] The server periodically obtains ground temperature data using the API of the satellite data provider. For example, it communicates with a common satellite data provider via API to collect temperature data for a specified area.

[0464] 2. Temperature data preprocessing and analysis

[0465] The server receives the collected temperature data in JSON format, checks for outliers, and performs imputation. After preprocessing, the server analyzes the temperature data and calculates the stress on the water pipes. For example, it uses the least squares method to calculate the temperature change rate and identify stress points if there are sudden changes.

[0466] 3. Seismic data acquisition and analysis

[0467] The server uses the Earthquake Research Institute's API to acquire earthquake data, preprocess it, and integrate it with temperature data to perform risk assessment. For example, historical earthquake data and temperature fluctuation data can be integrated to create a risk map.

[0468] 4. Prioritizing repairs

[0469] The server calculates the priority of water pipes that need repair based on temperature and earthquake data. For example, it comprehensively evaluates stress points due to climate change and earthquake risk, and lists high-priority areas.

[0470] 5. Creating repair manuals using generative AI

[0471] The server uses the generative AI model to generate prompts for each identified repair location and automatically creates a repair manual. For example, a prompt such as "Please tell me the procedure for repairing water pipes due to sudden temperature changes" is input into the generative AI and a manual is created.

[0472] Terminal configuration and operation

[0473] The device uses the data sent from the server to perform the following actions:

[0474] 1. Data Receipt and Analysis

[0475] The terminal receives temperature data, earthquake data, and repair priority list obtained from the server.

[0476] 2. Efficient hydrographic charting

[0477] The terminals then use the data they receive to create efficient waterway maps and use GIS (geographic information system) software to design new pipe layouts and replacement plans. For example, ESRI ArcGIS software is used to design optimal routes.

[0478] User Configuration and Behavior

[0479] The user performs the following actions:

[0480] 1. Refer to the repair manual and carry out the work

[0481] The user refers to the repair manual provided by the server on their terminal and carries out the repair work on site. The repair manual contains specific text and images, and clearly shows, for example, "the procedure for repairing and reassembling a damaged part of a water pipe using specific tools."

[0482] 2. Submitting a work report

[0483] Once the repair work is completed, the user uploads a report and photos of the work to the server, allowing the administrator to check the progress of the work in real time.

[0484] With the above configuration and operation, the system of the present invention realizes efficient management and repair of water pipes taking into account the effects of temperature changes and earthquakes, and supports the realization of sustainable water infrastructure.

[0485] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0486] Step 1:

[0487] Data Acquisition

[0488] The server periodically obtains ground temperature data using the satellite data provider's API. The input is the coordinate data and API key of the specified area, and the output is the temperature data (in JSON format) for that area. The server sends a "GET request" to the API to collect the temperature data.

[0489] Step 2:

[0490] Temperature data preprocessing

[0491] The server receives the acquired temperature data and checks for outliers and missing values. The input is JSON-formatted temperature data, and the output is preprocessed clean data. The server filters outliers and fills in approximate values ​​if necessary.

[0492] Step 3:

[0493] Stress Calculation

[0494] The server analyzes the preprocessed temperature data and calculates the stress on the water pipes. The input is clean data, and the output is the stress calculation result. Specifically, the server quantifies the rapidity of temperature changes, and determines that rapid fluctuations indicate high stress. For example, it calculates the rate of temperature change over the course of a day and calculates a stress score based on that.

[0495] Step 4:

[0496] Identifying stress points

[0497] The server identifies stress points based on the stress score obtained from the temperature data analysis. The input is the stress calculation result, and the output is the location information of the stress points. The area where a sudden temperature change was detected is identified and recorded as geographic information.

[0498] Step 5:

[0499] Seismic data acquisition and preprocessing

[0500] The server retrieves earthquake data using the Earthquake Research Institute's API. The input is the coordinate data of the specified area and the API key, and the output is earthquake data (JSON format). The earthquake data is also preprocessed to check for outliers and missing values.

[0501] Step 6:

[0502] Risk Assessment

[0503] The server integrates preprocessed seismic data with temperature data to assess the risk of water pipes. The inputs are preprocessed seismic data and temperature data, and the output is the risk assessment results. Specifically, a risk map is created using past earthquake data and temperature fluctuation data.

[0504] Step 7:

[0505] Repair prioritization

[0506] The server calculates the priority of water pipes that need repair based on the risk assessment results. The input is the risk assessment results, and the output is a repair priority list. The stress score and risk level are combined to create a list of high-priority areas.

[0507] Step 8:

[0508] Creation of repair manuals

[0509] The server uses a generative AI model to create prompts for each identified repair location and generate a repair manual. The input is the prompt (e.g., "Please tell me the procedure for repairing water pipes due to sudden temperature changes"), and the output is the repair manual. The AI ​​model outputs specific repair procedures based on the prompts.

[0510] Step 9:

[0511] Efficient hydrographic charting

[0512] The terminal creates an efficient hydrographic map based on the data sent from the server. The input is the risk assessment results and repair priority list, and the output is the new hydrographic map. GIS software is used to design the optimal water pipe layout and routing.

[0513] Step 10:

[0514] Repair work

[0515] The user refers to the repair manual and performs specific repair work on-site. The input is the repair manual, and the output is a repair completion report. The user follows the repair procedure and repairs the water pipe using the necessary tools and parts. After the work is completed, the user uploads the report and photos to the server.

[0516] (Application example 1)

[0517] 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."

[0518] Conventional water pipe management systems have difficulty properly detecting and predicting abnormal temperature fluctuations and stress caused by earthquakes, requiring a great deal of time and effort to prioritize repairs and create specific repair procedures. Furthermore, ensuring the quality of repair work requires experienced workers, making efficient work difficult. Furthermore, complex environments such as factories require real-time monitoring of pipe conditions and rapid response, but current systems are inadequate. Therefore, a new management system is needed that monitors temperature fluctuations and vibrations in real time and uses generative AI to present efficient repair procedures.

[0519] 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.

[0520] In this invention, the server includes means for collecting ground temperature changes using satellite data, means for analyzing the collected temperature data to calculate stress on water pipes, means for predicting the risk of water leakage based on the stress data, means for acquiring earthquake data and combining it with temperature data to prioritize water pipes that need repair, means for creating repair manuals for the identified repair locations using generative AI, means for creating efficient waterway maps suitable for modern areas, means for collecting and analyzing sensor data (pipe temperature and vibration) in real time, and means for displaying repair procedures automatically generated using generative AI on a wearable device. This enables efficient and high-quality repair work by quickly and accurately identifying areas that need repair and providing specific repair procedures using generative AI.

[0521] "Satellite data" refers to data obtained from Earth observation satellites, including temperature changes on the Earth's surface and atmosphere, as well as information on topography and the environment.

[0522] "Ground temperature change" refers to the phenomenon in which the temperature of the ground surface or underground in a particular area fluctuates over time.

[0523] "Stress on water pipes" refers to changes in physical loads and pressures on water pipes, especially pressures affected by environmental conditions and external factors.

[0524] "Risk of water leakage" refers to the results of assessing the danger and probability of water leaking from water pipes.

[0525] "Earthquake data" refers to data that includes information such as the magnitude, epicenter, seismic intensity, and vibration pattern of an earthquake.

[0526] A "repair manual" is an instruction document that details repair procedures, precautions, necessary tools and parts, etc. for specified repair areas.

[0527] "Generative AI" refers to artificial intelligence technology that automatically generates new information and suggestions based on large amounts of data and past knowledge.

[0528] "Modern regions" refer to settlements and cities with current living infrastructure and infrastructure.

[0529] A "waterway map" is a map showing the layout, routes, and connection points of water pipes and distribution pipes.

[0530] "Sensor data" refers to physical measurements taken in real time from measuring instruments such as temperature sensors or vibration sensors.

[0531] "Real-time collection" refers to collecting data immediately at the moment it is generated.

[0532] "Analyzing" means analyzing collected data to extract meaningful information.

[0533] A "wearable terminal" is an electronic device worn by a worker that displays information and allows data entry.

[0534] This invention is a system for efficiently managing and repairing pipelines in factories, utilizing satellite data, sensor data, and generative AI technology. Each component is described in detail below.

[0535] 1. Satellite data acquisition and analysis

[0536] The server periodically obtains data on temperature changes on the Earth's surface from Earth observation satellites. This data is obtained using an external satellite data provider. The server analyzes the obtained data to understand the temperature fluctuation patterns around the factory. This temperature data is used to detect sudden temperature changes in specific areas. Python data analysis libraries (e.g., Pandas, NumPy) are used for the analysis.

[0537] 2. Sensor data collection and analysis

[0538] The server collects data in real time from temperature and vibration sensors installed on each pipe in the factory. This sensor data is analyzed immediately by the server. When temperature fluctuations or abnormal vibrations are detected, it indicates that a particular pipe is under high stress. This analysis is performed using machine learning libraries (e.g., Scikit-learn).

[0539] 3. Prioritizing repairs

[0540] The server calculates the priority of pipes that need repair based on information obtained from temperature and sensor data. This allows it to create a repair plan that prioritizes pipes that are at greatest risk. The calculation is performed using database software (e.g., MySQL) and an algorithm based on the weighting of the data.

[0541] 4. Automatic generation of repair procedures

[0542] For each identified repair location, the server automatically generates a repair procedure using generative AI. GPT-4 is used as the generative AI model. This model generates specific repair procedures by referring to past repair data and technical literature. For example, a procedure can be generated by entering a prompt like the following:

[0543] "Please provide detailed instructions for the following repair. The location is a cooling pipe in Section A in the north of the factory, and the following conditions are present: temperature spikes and strong vibrations. The tools required are a 20mm wrench and a screwdriver."

[0544] 5. Display of repair procedures

[0545] The repair procedures obtained by generative AI are displayed in real time on wearable devices such as smart glasses. Using smart glasses allows workers to check the necessary information while keeping both hands free, improving work efficiency and accuracy. Google Glass or Vuzix are suitable devices for this.

[0546] 6. Actual repair work

[0547] The user performs specific repair work on-site while referring to the repair procedures displayed on the smart glasses. The repair procedures include text and images, and specific steps and points to note are clearly indicated, improving work efficiency and enabling even inexperienced workers to perform high-quality work.

[0548] This system is expected to improve the efficiency of pipeline management within the factory and enable repair work to be carried out quickly and accurately.

[0549] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0550] Step 1:

[0551] The server periodically obtains surface temperature data from an external satellite data provider.

[0552] Input: Temperature data from Earth observation satellites.

[0553] Data processing: Organize the temperature data as time series data.

[0554] Output: A dataset containing temperature variation patterns for a specific region.

[0555] Step 2:

[0556] The server analyzes the acquired temperature data using Python data analysis libraries (Pandas, NumPy) and identifies sudden temperature changes.

[0557] Input: A curated temperature dataset.

[0558] Data processing: Data cleaning and application of algorithms to detect sudden temperature changes.

[0559] Output: A list of points with sudden temperature changes.

[0560] Step 3:

[0561] The server collects data in real time from temperature and vibration sensors installed on each pipe in the factory.

[0562] Input: Real-time data from temperature and vibration sensors.

[0563] Data processing: Data acquisition and format conversion of temperature and vibration data.

[0564] Output: Real-time captured temperature and vibration data.

[0565] Step 4:

[0566] The server uses the Scikit-learn library to analyze sensor data acquired in real time and detect abnormal temperature fluctuations and vibrations.

[0567] Input: Real-time temperature and vibration data.

[0568] Data processing: Anomaly detection using machine learning algorithms.

[0569] Output: A list of areas where abnormal temperature fluctuations and vibrations are occurring.

[0570] Step 5:

[0571] The server combines the acquired temperature and sensor data with seismic data to calculate the priority of pipes that need repair.

[0572] Inputs: temperature data, sensor data, seismic data.

[0573] Data processing: Data integration and application of priority calculation algorithms.

[0574] Output: A prioritized list of pipes needing repair.

[0575] Step 6:

[0576] The server uses generation AI to automatically generate repair procedures for the identified repair areas.

[0577] Inputs: Identified repair area, environmental conditions, tool list.

[0578] Data processing: Generative AI model (GPT-4) was used to generate instructions based on prompts. "Please tell me in detail the procedure for the next repair. The location is a cooling pipe in Section A in the north of the factory, and the following conditions apply: temperature spike, strong vibration. The tools required are a 20mm wrench and a screwdriver."

[0579] Output: Detailed repair instructions (with text and images).

[0580] Step 7:

[0581] The user displays the generated repair procedure manual on a wearable device such as smart glasses and performs the repair work while referring to it.

[0582] Input: detailed repair instructions.

[0583] Data processing: Converting data into a display format suitable for wearable devices.

[0584] Output: Repair instructions displayed on the smart glasses.

[0585] In this way, the system can monitor temperature fluctuations and vibrations in real time and use generative AI to provide efficient repair procedures.

[0586] 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.

[0587] The present invention is a system for efficiently managing and repairing water pipes by utilizing satellite data, artificial intelligence technology (generative AI), and an emotion engine. This system divides the roles of server, terminal, and user, and each performs different processing steps to achieve optimal water pipe management. Specific embodiments are shown below.

[0588] Satellite data acquisition and analysis

[0589] The server periodically obtains ground temperature change data from a satellite data provider. This data is collected as time-series data of temperature fluctuations in a specific area and stored on the server. The server then analyzes the temperature data and calculates the stress on the water pipes. Stress points are identified using an algorithm that detects sudden changes in temperature data. For example, if a large temperature change occurs in a certain area in a short period of time, it can be determined that the water pipes in that area are under high stress.

[0590] Seismic data acquisition and analysis

[0591] The server retrieves earthquake data from reliable sources, such as seismological research institutes. This data includes information such as the magnitude, frequency, and epicenter of past earthquakes. The server analyzes this earthquake data with temperature data to prioritize water pipes that need repair. Based on earthquake vibrations and temperature changes, the server evaluates the risk of water pipes in a particular area.

[0592] Repair prioritization

[0593] The server uses temperature and earthquake data to create a priority list of water pipes that need repair, and then creates an appropriate repair plan based on this list.

[0594] Generate repair manuals

[0595] The server uses generation AI to automatically generate repair manuals. The generated repair manuals contain repair procedures, necessary tools and parts, and important points to note, all in text and with images. This allows even inexperienced or foreign workers to carry out repair work efficiently.

[0596] Efficient hydrographic charting

[0597] The terminal uses the analysis data from the server to create an efficient waterway map suitable for modern settlements, which the waterworks bureau uses when formulating long-term waterway development plans.

[0598] Emotion engine integration

[0599] The server also integrates an emotion engine to detect the user's emotions in real time while they are working on the repairs. The emotion engine evaluates the user's stress level and satisfaction through facial recognition and voice analysis. For example, if the user expresses high levels of stress, the emotion engine adjusts the instructions in the repair manual to be simpler. Also, if the user expresses high levels of satisfaction, the engine appropriately adjusts the progress of the repair work based on that feedback.

[0600] The actual repair work

[0601] Users refer to the provided repair manual to carry out the actual repair work. The manual contains detailed descriptions of specific procedures, tools, parts, and precautions to be taken, allowing the work to be carried out efficiently and safely. In addition, the emotion engine adjusts work instructions as needed based on real-time evaluations, reducing user stress and improving the quality of work.

[0602] Through the above process, the server, terminals, and users work together to create a system that effectively manages and repairs water pipes.

[0603] The processing flow will be explained below.

[0604] Processing Steps

[0605] Step 1:

[0606] The server obtains ground temperature data from a satellite data provider. Specifically, the server periodically sends an API request to receive temperature data for a specified area. The received data is recorded in a database as time-series data.

[0607] Step 2:

[0608] The server analyzes the acquired temperature data and calculates the stress on the water pipes. Specifically, it uses an analysis algorithm to identify points of sudden temperature changes and calculates the degree of stress that these points are putting on the water pipes. These stress points are then listed.

[0609] Step 3:

[0610] The server retrieves earthquake information from earthquake data providers. The earthquake data includes the magnitude, frequency, and epicenter of past earthquakes, and is also retrieved by periodically sending API requests. The earthquake data is stored in a database.

[0611] Step 4:

[0612] The server then performs an analysis by overlaying temperature data and earthquake data. Specifically, it compares stress points with earthquake data to assess the extent to which water pipes in a particular area are exposed to multiple risks. This allows it to prioritize areas that need repairs.

[0613] Step 5:

[0614] The server uses generative AI to create a repair manual for each prioritized repair area. Specifically, it references past repair data and technical literature to automatically generate text and images detailing the appropriate repair procedures, necessary tools, parts, and important points to note.

[0615] Step 6:

[0616] The device uses data provided by the server to create an efficient waterway map suitable for modern settlements. Specifically, it uses the analysis data to design the optimal layout and route of water pipes, supporting long-term development plans.

[0617] Step 7:

[0618] The server runs an emotion engine to recognize the user's emotions in real time during repair work. The emotion engine detects the user's stress level and satisfaction through facial recognition and voice analysis.

[0619] Step 8:

[0620] The server adjusts the instructions in the repair manual based on the emotion engine's evaluation results. For example, if the user's stress level is high, the instructions are simplified. Also, if the user's satisfaction level is high, the server adjusts the progress of the repair work based on that feedback.

[0621] Step 9:

[0622] The user refers to the provided repair manual and performs the actual repair work. Specifically, the user proceeds with the work while looking at the procedures and images described in the manual, and completes the work using the specified tools and parts. Based on real-time evaluation by the emotion engine, the work instructions are adjusted as needed, reducing user stress and improving work efficiency.

[0623] Through the above processing steps, a system is realized in which the server, terminals, and users work together to effectively manage and repair water pipes.

[0624] Example 2

[0625] 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."

[0626] The management and repair of existing water pipes often relies on human resources, resulting in issues with efficiency and accuracy. Furthermore, there is a lack of methods to properly assess stress caused by external factors such as temperature changes and earthquakes and identify areas that should be prioritized for repair. Furthermore, there is a lack of real-time support to reduce user stress during repair work and improve the quality of work.

[0627] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting ground temperature changes using satellite data, means for analyzing the collected temperature data to calculate stress on water pipes, means for acquiring earthquake data and multiplying it with the temperature data to prioritize water pipes that need repair, means for creating repair manuals for the identified repair locations using a generation AI, and means for monitoring the user's emotions during repair work in real time and dynamically adjusting instructions in the repair manual as necessary. This enables efficient and accurate management and repair of water pipes.

[0628] "Satellite data" is data obtained from artificial satellites to observe the Earth's surface and atmosphere.

[0629] "Temperature change data" is time series data that shows how the ground temperature in a particular area changes over time.

[0630] "Stress on water pipes" refers to the physical loads and pressures that water pipes are subjected to due to external factors such as temperature changes and earthquakes.

[0631] "Water leakage risk" is an evaluation index that indicates the degree of possibility that a water pipe will break and cause a water leak.

[0632] "Earthquake Data" means data containing information on the magnitude, frequency, and epicenters of past and present earthquakes.

[0633] "Water pipes in need of repair" are water pipes that have been identified as being in need of immediate repair due to high stress caused by temperature changes and earthquakes.

[0634] "Generative AI" is a type of artificial intelligence technology that refers to algorithms that generate natural-looking sentences and images based on specific prompts.

[0635] A "repair manual" is a document that describes the procedures required to efficiently carry out water pipe repair work, the tools and parts to be used, and points to note.

[0636] An "efficient waterway map" is a map that optimizes the layout and routing of water pipes and allows for efficient management and maintenance of water supply systems in settlements and cities.

[0637] The "Emotion Engine" is a technology that assesses a user's stress level and satisfaction in real time through facial recognition and voice analysis.

[0638] "User" refers to the worker who actually carries out the water pipe repair work.

[0639] A "server" is a computer system that collects, analyzes, and operates the generated AI.

[0640] A "terminal" is a computer device that creates and displays hydrographic charts based on analysis data from the server.

[0641] This invention is a system that efficiently manages and repairs water pipes by utilizing satellite data, artificial intelligence technology (generative AI), and an emotion engine. This system divides the roles of server, terminal, and user, and each performs different processing steps to achieve optimal water pipe management.

[0642] Satellite data acquisition and analysis

[0643] The server periodically obtains ground temperature change data from a satellite data provider. This data is collected as time-series data of temperature fluctuations in a specific area and stored on the server. The Python scikit-learn library is used to analyze the temperature data and calculate the stress on the water pipes. For example, the server obtains data in JSON format from "https: / / api.satelliteprovider.com / temperature" and converts it into a Pandas data frame. Furthermore, a Z-score is calculated to detect outliers in the data.

[0644] Seismic data acquisition and analysis

[0645] The server retrieves earthquake data from earthquake research institutes and earthquake data providers via API. This data includes information on the magnitude, frequency, and epicenter of past earthquakes. The server combines this data with temperature data and analyzes it to assess the risk to water pipes in a specific area. Specifically, the server downloads earthquake data in CSV format from "https: / / earthquake.usgs.gov / fdsnws / event / 1 / query" and merges it with the temperature data for analysis. Python's NumPy and Pandas are used for the analysis.

[0646] Repair prioritization

[0647] The server generates a list of high-risk water pipes based on temperature and earthquake data. Based on this list, it prioritizes the pipes that need repair and creates a repair plan. Specifically, the server calculates a repair necessity score based on the analysis results and sorts the list in descending order of score. The results are saved in a MySQL database.

[0648] Generate repair manuals

[0649] The server uses a generative AI (e.g., GPT-4) to automatically generate a detailed repair manual. The repair procedure, necessary tools and parts, and precautions are written in text and images. As an example of a specific prompt, "Please generate a repair procedure, including necessary tools, parts, and precautions," is input to GPT-4, and the generated text is formatted in HTML.

[0650] Efficient hydrographic charting

[0651] The terminal uses design software such as AutoCAD to create efficient hydrographic diagrams based on the analysis data received from the server. This enables long-term water pipe maintenance planning. Specifically, the terminal runs an AutoCAD script to draw the hydrographic diagram based on the coordinate data received from the server. The generated diagram is saved as a PDF file.

[0652] Emotion engine integration

[0653] The server integrates an emotion engine (e.g., Affdex API) to monitor the user's emotions in real time while they are working on repairs. It uses facial recognition and voice analysis to evaluate their stress level and satisfaction. Specifically, the server captures the user's webcam footage and microphone input, and performs emotion analysis using the Affdex API. Based on the evaluation results, the content of the repair manual is dynamically adjusted.

[0654] The actual repair work

[0655] The user performs actual repair work by referring to the provided repair manual. If the emotion engine detects the user's stress, the work instructions are adjusted in real time. Specifically, the user follows the specific steps in the repair manual and performs the repair work using specified tools (e.g., pipe wrench, plumbing tape, etc.). If the emotion engine detects stress during the work, the manual instructions may be simplified.

[0656] Through the above steps, a system is realized in which the server, terminals, and users work together to efficiently and effectively manage and repair water pipes.

[0657] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0658] Step 1:

[0659] (Satellite data acquisition)

[0660] The server connects to the satellite data provider's API to periodically obtain data on ground temperature changes in a specific area.

[0661] Input: API endpoint URL, authentication information

[0662] Specific operation: The server retrieves data in JSON format from "https: / / api.satelliteprovider.com / temperature".

[0663] Data processing: Convert the acquired JSON data into a Pandas data frame.

[0664] Output: Formatted temperature change data is obtained.

[0665] Step 2:

[0666] (Temperature data analysis)

[0667] The server analyzes the temperature change data and collects and stores the temperature fluctuations of the ground in a specific area as time-series data.

[0668] Input: Formatted temperature change data

[0669] Specific operation: The server uses Python's scikit-learn library to detect outliers using Z scores.

[0670] Data calculation: Calculate stress points and perform risk assessments for specific areas.

[0671] Output: Stress points on the water pipes are identified.

[0672] Step 3:

[0673] (Acquisition of earthquake data)

[0674] The server obtains earthquake data from earthquake research institutes and earthquake data providers via API.

[0675] Input: API endpoint URL, authentication information

[0676] Specific operation: The server downloads earthquake data in CSV format from "https: / / earthquake.usgs.gov / fdsnws / event / 1 / query".

[0677] Data processing: Convert the downloaded CSV data into a Pandas data frame.

[0678] Output: Formatted seismic data.

[0679] Step 4:

[0680] (Analysis of temperature and seismic data)

[0681] The server combines temperature and earthquake data to assess how much risk water pipes in a particular area are at.

[0682] Input: Formatted temperature data, formatted seismic data

[0683] What happens: The server merges the data using NumPy and Pandas and performs a risk assessment.

[0684] Data calculation: Based on the integrated data, calculate the priority of water pipes that need repair.

[0685] Output: Risk assessment results and a priority list are generated.

[0686] Step 5:

[0687] (Prioritizing repairs)

[0688] Based on the risk assessment results, the server generates a list of water pipes that need repair.

[0689] Input: Risk assessment results, priority list

[0690] Specific operation: The server calculates the repair necessity score and sorts the list by highest score.

[0691] Data processing: Save the list in a MySQL database.

[0692] Output: A list of repair priorities is stored in the database.

[0693] Step 6:

[0694] (Generate repair manual)

[0695] The server automatically generates repair manuals using generative AI (e.g., GPT-4 model).

[0696] Input: Repair requirements, construction details

[0697] Specific action: GPT-4 is given the prompt, "Generate repair instructions, including required tools, parts, and precautions."

[0698] Data calculation: The generated repair manual is formatted into HTML format.

[0699] Output: A detailed repair manual is generated.

[0700] Step 7:

[0701] (Efficient hydrographic charting)

[0702] The terminal creates an efficient hydrographic chart based on the analysis data received from the server.

[0703] Input: Repair priority data, coordinate data

[0704] Specific operation: The terminal draws a hydrographic chart using AutoCAD.

[0705] Data processing: Save the generated hydrographic chart in PDF format.

[0706] Output: An efficient hydrographic chart is generated in a PDF file.

[0707] Step 8:

[0708] (Emotion engine integration)

[0709] The server uses an emotion engine to monitor the user's emotions in real time during repair work.

[0710] Input: User's webcam video and audio data

[0711] Specific operation: The server uses the Affdex API to perform sentiment analysis and evaluate stress levels.

[0712] Data Calculation: Dynamically adjust repair manuals based on the user's stress level.

[0713] Output: Repair instructions tailored to the user's emotional state are provided.

[0714] Step 9:

[0715] (Actual repair work)

[0716] The user performs the actual repair work by referring to the provided repair manual.

[0717] Input: Detailed repair manual, tools used

[0718] Specific operation: The user follows the steps in the manual and performs the repair using the specified tools (e.g., pipe wrench, plumbing tape).

[0719] Data Calculation: If the emotion engine detects stress, it will automatically adjust its instructions.

[0720] Output: Repair work completed and work quality improved.

[0721] (Application example 2)

[0722] 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."

[0723] Conventional water pipe management and repair systems have difficulty efficiently identifying leak risks and prioritizing repairs. Furthermore, the quality of repair work varies depending on the experience and skills of the workers, and workers are subject to significant stress and strain. To address these issues, more accurate analysis and planning is required by utilizing satellite and earthquake data. Furthermore, a new challenge is being faced: analyzing workers' emotions in real time to improve the quality and efficiency of work.

[0724] The specific processing by the specific 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 ground temperature changes using satellite data, means for analyzing the collected temperature data to calculate stress on pipes, means for predicting the risk of water leakage based on the stress data, means for acquiring earthquake data and combining it with temperature data to prioritize pipes in need of repair, means for creating repair manuals for the identified repair locations using generative AI, emotion analysis means for evaluating user emotions in real time when performing repair work based on the manual, and means for creating efficient piping diagrams suitable for modern settlements. This not only efficiently identifies areas in need of repair and provides repair manuals, but also analyzes worker emotions and adjusts instructions, thereby improving work efficiency and quality and reducing user stress.

[0725] "Satellite data" refers to information about the Earth's surface and atmosphere collected from artificial satellites, and is particularly data that can acquire temperature changes and environmental conditions in real time.

[0726] "Temperature data" is information that records changes in the temperature of the earth's surface or an object, and represents temperature fluctuations in a specific area over time.

[0727] "Stress" refers to the physical load or pressure on pipes and equipment, and indicates the risk caused by sudden temperature changes and vibrations in particular.

[0728] "Earthquake data" refers to data that includes information such as the magnitude, epicenter, and frequency of shaking caused by earthquakes.

[0729] "Generative AI" is a type of artificial intelligence technology that has the ability to generate new data and text from given information.

[0730] A "repair manual" is an instruction manual that describes the procedures for carrying out repair work, the necessary tools, parts, and precautions.

[0731] "Emotion analysis" is a technology that assesses a user's emotional state in real time through facial recognition and voice analysis, measuring stress and satisfaction.

[0732] A "piping diagram" is a map showing the layout and connections of water pipes and other pipes, and is created for efficient pipe management and repair planning.

[0733] "User" refers to the worker who actually performs the piping repair work by referring to the provided repair manual.

[0734] The present invention is a system that efficiently manages and repairs pipes by utilizing satellite data, artificial intelligence technology (generative AI), and an emotion engine. Specific embodiments are described below.

[0735] Satellite data acquisition and analysis

[0736] First, the server periodically obtains surface temperature change data from a satellite data provider. This data represents temperature fluctuations in a specific area and is obtained in real time. The server analyzes the temperature data and calculates the stress on the pipes. To do this, an algorithm is used to detect sudden changes in temperature data. For example, if a large temperature change is observed in a certain area in a short period of time, it is determined that the pipes in that area are under high stress.

[0737] Seismic data acquisition and analysis

[0738] The server retrieves earthquake data from reliable sources, such as seismological research institutes. This data includes information on the magnitude, frequency, and epicenter of past earthquakes. The server analyzes the earthquake data together with temperature data to prioritize pipes that need repair. The seismic vibrations and temperature changes are used to assess the risk of pipes in a particular area.

[0739] Repair prioritization

[0740] Based on the analysis results, the server creates a list of pipes that need repair in order of priority, and then creates an appropriate repair plan based on this list.

[0741] Generate repair manuals

[0742] Next, the server uses the generation AI to automatically generate a repair manual. The generated repair manual contains repair procedures, necessary tools and parts, important points to note, and other information in text and images. For example, a manual can be created by inputting the following prompts into the generation AI:

[0743] "Repair the following stress points: [(20, 30), (40, 50), (70, 80)]. Generate detailed instructions including tools, components, and safety notes."

[0744] This will enable even inexperienced workers or foreign workers to carry out repair work efficiently.

[0745] Emotion engine integration

[0746] The server also integrates an emotion engine to detect the user's emotions in real time while they are performing repair work. The emotion engine uses a camera and microphone to recognize the worker's face and analyze their voice. If the work is difficult or indicates high stress, the emotion engine will simplify the instructions in the repair manual. For example, if it determines that the user is experiencing high stress, it will change complex procedures to simpler instructions.

[0747] The actual repair work

[0748] Users refer to the provided repair manual when carrying out actual repair work. Based on real-time evaluations by the emotion engine, work instructions are adjusted as needed, reducing user stress and improving the quality of work. Furthermore, efficient piping diagrams suitable for modern settlements are created and used for long-term maintenance planning.

[0749] In this way, the collaboration between servers, terminals, and users enables efficient pipe management and repair. Specific hardware and software are used for collecting and analyzing each piece of data. Specifically, Apache Spark is used for data analysis, TensorFlow and PyTorch for AI analysis, and OpenFace and Wav2Vec for sentiment analysis.

[0750] The detailed description of the embodiments clarifies the technical scope of the invention, supports the scope of patent protection, and serves as a reference for other users to understand and implement the invention.

[0751] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0752] Step 1:

[0753] The server periodically obtains data on changes in surface temperature over a specific area from a satellite data provider. The input is temperature data from the satellite data provider, and the output is time-series data showing changes in surface temperature. The server stores this data and uses it for further analysis.

[0754] Step 2:

[0755] The server analyzes the acquired temperature data and calculates the stress on the pipe. Specifically, it runs an algorithm that detects sudden changes in the temperature data. The input is ground temperature data, and the output is data indicating stress points on the pipe.

[0756] Step 3:

[0757] The server retrieves earthquake data from a reliable source such as an earthquake research institute. The input is earthquake data including the magnitude, frequency, and epicenter of past earthquakes, and the output is data evaluating the impact of earthquakes. The server uses this data for further analysis.

[0758] Step 4:

[0759] The server analyzes temperature and earthquake data and prioritizes pipes that need repair. The input is temperature and earthquake data, and the output is a list of pipes that need repair and their priorities.

[0760] Step 5:

[0761] The server uses a generative AI to create a repair manual for the identified repair area. Specifically, it inputs the following prompt sentence into the generative AI model:

[0762] "Repair the following stress points: [(20, 30), (40, 50), (70, 80)]. Generate detailed instructions including tools, components, and safety notes."

[0763] The input is a list of repairs (stress points), and the output is a detailed repair manual, including text and images, describing the tools and parts required, and important points to note.

[0764] Step 6:

[0765] The user refers to the repair manual and performs the repair work. The input is the repair manual provided by the server, and the output is the progress of the actual repair work. The user follows the manual and performs the repair work efficiently.

[0766] Step 7:

[0767] During the repair work, the server uses an emotion engine to analyze the user's emotions in real time. Specifically, it uses a camera and microphone to recognize the user's face and analyze their voice. The input is real-time facial images and voice data obtained from the camera and microphone, and the output is data indicating the user's emotional state.

[0768] Step 8:

[0769] The server adjusts the instructions in the repair manual based on the user's emotional data. For example, if the user is feeling high stress, it simplifies complex procedures. The input is the user's emotional state, and the output is the adjusted repair manual.

[0770] Step 9:

[0771] The server compiles the final repair results and creates an efficient piping diagram suitable for modern settlements. The input is the repair work results data, and the output is a new piping diagram. This piping diagram is used for long-term maintenance planning.

[0772] 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.

[0773] 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.

[0774] 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.

[0775] [Third embodiment]

[0776] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0777] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0778] 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).

[0779] 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.

[0780] 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.

[0781] 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).

[0782] 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.

[0783] 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.

[0784] 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.

[0785] 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.

[0786] 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.

[0787] 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."

[0788] This invention is a system that utilizes satellite data and artificial intelligence technology (generative AI) to efficiently manage and repair water pipes. In this system, the server, terminal, and user each play different roles, and optimal water pipe management is achieved through each processing step. How the present invention is implemented is described in detail below.

[0789] 1. Satellite data acquisition and analysis

[0790] The server periodically obtains ground temperature data from a satellite data provider, collecting time-series data on temperature fluctuations in a specific area. The server then analyzes this temperature data internally to calculate the stress on the water pipes. Stress points are identified using an algorithm that detects sudden changes in temperature data. For example, if a certain area experiences a sudden change in temperature, it can be determined that the water pipes in that area are under high stress.

[0791] 2. Seismic data acquisition and analysis

[0792] The server acquires earthquake data from reliable data sources such as the Earthquake Research Institute. It collects information such as the magnitude, frequency, and epicenter of past earthquakes. It then matches the acquired earthquake data with temperature data to prioritize the locations of water pipes that are most in need of repair. It then assesses the degree of risk to water pipes in the identified area based on vibrations and temperature changes caused by earthquakes.

[0793] 3. Prioritizing repairs

[0794] The server calculates the priority of water pipes that need repair based on information obtained from temperature and earthquake data. The priority is then used to create a list of locations that urgently need repairs, and an appropriate repair plan is created based on the results.

[0795] 4. Generate repair manual

[0796] The server uses generative AI to automatically create a repair manual for each identified repair location. This manual includes repair procedures, necessary tools and parts, and points to note. The generative AI provides specific, easy-to-understand content by referring to past repair data and technical literature. This allows even inexperienced or foreign workers to carry out repair work efficiently.

[0797] 5. Efficient hydrographic charting

[0798] The device uses the surveyed data to create an optimal waterway map suitable for modern settlements. This helps design the optimal layout and routing of water pipes. Based on the layout of new water pipes and plans for replacement, the waterworks bureau can formulate long-term maintenance plans.

[0799] 6. Actual repair work

[0800] Users refer to the provided repair manual to carry out specific repair work on-site. The manual contains text and images, and clearly states specific procedures and important points, making it easy for anyone to understand. This enables waterworks bureaus and subcontractors to carry out repair work efficiently and with high quality.

[0801] Through the above process, the system of the present invention can solve the problems of conventional water pipe management and support the realization of sustainable water infrastructure.

[0802] The processing flow will be explained below.

[0803] Processing Steps

[0804] Step 1:

[0805] The server obtains ground temperature data from a satellite data provider. Specifically, the server periodically sends an API request to receive temperature data for a specified area. The received data is recorded in a database as time-series data.

[0806] Step 2:

[0807] The server analyzes the acquired temperature data and calculates the stress on the water pipes. Specifically, it uses an analysis algorithm to identify points of sudden temperature changes and calculates the degree of stress that these points are putting on the water pipes. These stress points are then listed.

[0808] Step 3:

[0809] The server retrieves earthquake information from earthquake data providers. The earthquake data includes the magnitude, frequency, and epicenter of past earthquakes, and is also retrieved by periodically sending API requests. The earthquake data is stored in a database.

[0810] Step 4:

[0811] The server compares temperature data with earthquake data and performs an analysis. Specifically, it overlays stress points with earthquake data to assess the extent to which water pipes in a specific area are exposed to multiple risks. Based on the results of this analysis, it prioritizes areas that need repair.

[0812] Step 5:

[0813] The server uses generative AI to create repair manuals for each section of water pipe that needs repair. Specifically, it references past repair data and technical literature to automatically generate text and images detailing the appropriate repair procedures, necessary tools, parts, and important points to note.

[0814] Step 6:

[0815] The device uses the analysis data and repair manuals to create an efficient waterway map suitable for modern settlements. Specifically, it designs the optimal layout of water pipes based on repair location data provided by the server, and supports long-term maintenance planning.

[0816] Step 7:

[0817] The user performs the actual repair work while referring to the provided repair manual. Specifically, the user proceeds with the work while looking at the procedures and images described in the manual, and completes the repair of the water pipe using the specified tools and parts.

[0818] Through the above processing steps, a system is realized in which the server, terminals, and users work together to effectively manage and repair water pipes.

[0819] Example 1

[0820] 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."

[0821] Conventional water pipe management systems rely on visual inspections and regular maintenance without properly considering changes in ground temperature or the effects of earthquakes, making it difficult to respond immediately when leaks or damage occur. Furthermore, there is a lack of efficient repair work and specific repair procedures, which means that repair work is highly dependent on the experience and skills of workers, often resulting in variations in the quality and efficiency of repair work. This creates problems that make it difficult to ensure the sustainability and efficient management of water infrastructure.

[0822] 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.

[0823] In this invention, the server includes means for collecting ground temperature changes using satellite data, means for preprocessing the collected temperature data and calculating stress on water pipes, means for identifying stress points using an algorithm for detecting sudden temperature changes, means for acquiring earthquake data and integrating it with temperature data to evaluate the risk of water pipes, means for calculating the priority of water pipes requiring repair based on the temperature data and earthquake data, means for generating prompt sentences using a generative AI model for each identified repair location and creating a repair manual, and means for creating an efficient waterway diagram based on the survey data. This enables risk assessment of water pipes and prioritization of repairs that take temperature changes and the effects of earthquakes into account, enabling efficient and high-quality repair work.

[0824] "Satellite Data" means information about the Earth's surface obtained from artificial satellites in Earth orbit.

[0825] "Temperature data" refers to data that records the ground or air temperature over time in a specific area.

[0826] A "stress point" is a location where a water pipe is subjected to particularly high physical or environmental stress.

[0827] "Earthquake data" refers to data that records information about earthquakes, such as their magnitude, epicenter, and the date and time of occurrence.

[0828] "Risk assessment" is the process of quantitatively assessing the risk of water pipe failure or leakage based on specific conditions and data.

[0829] "Priority" refers to the ranking of water pipes that need repair based on their importance.

[0830] A "generative AI model" is an algorithm that uses artificial intelligence techniques to generate an appropriate output for a specific input.

[0831] A "prompt" is a sentence that describes specific instructions or questions for a generative AI model.

[0832] A "repair manual" is a document that contains specific procedures and instructions for efficiently carrying out water pipe repair work.

[0833] An "efficient waterway diagram" is a drawing that designs the optimal layout and routing of water pipes.

[0834] This invention is a system in which the server, terminal, and user components each play different roles, utilizing satellite data and generative AI models to properly manage and efficiently repair water pipes.

[0835] Server configuration and operation

[0836] The server performs the following actions:

[0837] 1. Acquisition of satellite data

[0838] The server periodically obtains ground temperature data using the API of the satellite data provider. For example, it communicates with a common satellite data provider via API to collect temperature data for a specified area.

[0839] 2. Temperature data preprocessing and analysis

[0840] The server receives the collected temperature data in JSON format, checks for outliers, and performs imputation. After preprocessing, the server analyzes the temperature data and calculates the stress on the water pipes. For example, it uses the least squares method to calculate the temperature change rate and identify stress points if there are sudden changes.

[0841] 3. Seismic data acquisition and analysis

[0842] The server uses the Earthquake Research Institute's API to acquire earthquake data, preprocess it, and integrate it with temperature data to perform risk assessment. For example, historical earthquake data and temperature fluctuation data can be integrated to create a risk map.

[0843] 4. Prioritizing repairs

[0844] The server calculates the priority of water pipes that need repair based on temperature and earthquake data. For example, it comprehensively evaluates stress points due to climate change and earthquake risk, and lists high-priority areas.

[0845] 5. Creating repair manuals using generative AI

[0846] The server uses the generative AI model to generate prompts for each identified repair location and automatically creates a repair manual. For example, a prompt such as "Please tell me the procedure for repairing water pipes due to sudden temperature changes" is input into the generative AI and a manual is created.

[0847] Terminal configuration and operation

[0848] The device uses the data sent from the server to perform the following actions:

[0849] 1. Data Receipt and Analysis

[0850] The terminal receives temperature data, earthquake data, and repair priority list obtained from the server.

[0851] 2. Efficient hydrographic charting

[0852] The terminals then use the data they receive to create efficient waterway maps and use GIS (geographic information system) software to design new pipe layouts and replacement plans. For example, ESRI ArcGIS software is used to design optimal routes.

[0853] User Configuration and Behavior

[0854] The user performs the following actions:

[0855] 1. Refer to the repair manual and carry out the work

[0856] The user refers to the repair manual provided by the server on their terminal and carries out the repair work on site. The repair manual contains specific text and images, and clearly shows, for example, "the procedure for repairing and reassembling a damaged part of a water pipe using specific tools."

[0857] 2. Submitting a work report

[0858] Once the repair work is completed, the user uploads a report and photos of the work to the server, allowing the administrator to check the progress of the work in real time.

[0859] With the above configuration and operation, the system of the present invention realizes efficient management and repair of water pipes taking into account the effects of temperature changes and earthquakes, and supports the realization of sustainable water infrastructure.

[0860] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0861] Step 1:

[0862] Data Acquisition

[0863] The server periodically obtains ground temperature data using the satellite data provider's API. The input is the coordinate data and API key of the specified area, and the output is the temperature data (in JSON format) for that area. The server sends a "GET request" to the API to collect the temperature data.

[0864] Step 2:

[0865] Temperature data preprocessing

[0866] The server receives the acquired temperature data and checks for outliers and missing values. The input is JSON-formatted temperature data, and the output is preprocessed clean data. The server filters outliers and fills in approximate values ​​if necessary.

[0867] Step 3:

[0868] Stress Calculation

[0869] The server analyzes the preprocessed temperature data and calculates the stress on the water pipes. The input is clean data, and the output is the stress calculation result. Specifically, the server quantifies the rapidity of temperature changes, and determines that rapid fluctuations indicate high stress. For example, it calculates the rate of temperature change over the course of a day and calculates a stress score based on that.

[0870] Step 4:

[0871] Identifying stress points

[0872] The server identifies stress points based on the stress score obtained from the temperature data analysis. The input is the stress calculation result, and the output is the location information of the stress points. The area where a sudden temperature change was detected is identified and recorded as geographic information.

[0873] Step 5:

[0874] Seismic data acquisition and preprocessing

[0875] The server retrieves earthquake data using the Earthquake Research Institute's API. The input is the coordinate data of the specified area and the API key, and the output is earthquake data (JSON format). The earthquake data is also preprocessed to check for outliers and missing values.

[0876] Step 6:

[0877] Risk Assessment

[0878] The server integrates preprocessed seismic data with temperature data to assess the risk of water pipes. The inputs are preprocessed seismic data and temperature data, and the output is the risk assessment results. Specifically, a risk map is created using past earthquake data and temperature fluctuation data.

[0879] Step 7:

[0880] Repair prioritization

[0881] The server calculates the priority of water pipes that need repair based on the risk assessment results. The input is the risk assessment results, and the output is a repair priority list. The stress score and risk level are combined to create a list of high-priority areas.

[0882] Step 8:

[0883] Creation of repair manuals

[0884] The server uses a generative AI model to create prompts for each identified repair location and generate a repair manual. The input is the prompt (e.g., "Please tell me the procedure for repairing water pipes due to sudden temperature changes"), and the output is the repair manual. The AI ​​model outputs specific repair procedures based on the prompts.

[0885] Step 9:

[0886] Efficient hydrographic charting

[0887] The terminal creates an efficient hydrographic map based on the data sent from the server. The input is the risk assessment results and repair priority list, and the output is the new hydrographic map. GIS software is used to design the optimal water pipe layout and routing.

[0888] Step 10:

[0889] Repair work

[0890] The user refers to the repair manual and performs specific repair work on-site. The input is the repair manual, and the output is a repair completion report. The user follows the repair procedure and repairs the water pipe using the necessary tools and parts. After the work is completed, the user uploads the report and photos to the server.

[0891] (Application example 1)

[0892] 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."

[0893] Conventional water pipe management systems have difficulty properly detecting and predicting abnormal temperature fluctuations and stress caused by earthquakes, requiring a great deal of time and effort to prioritize repairs and create specific repair procedures. Furthermore, ensuring the quality of repair work requires experienced workers, making efficient work difficult. Furthermore, complex environments such as factories require real-time monitoring of pipe conditions and rapid response, but current systems are inadequate. Therefore, a new management system is needed that monitors temperature fluctuations and vibrations in real time and uses generative AI to present efficient repair procedures.

[0894] 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.

[0895] In this invention, the server includes means for collecting ground temperature changes using satellite data, means for analyzing the collected temperature data to calculate stress on water pipes, means for predicting the risk of water leakage based on the stress data, means for acquiring earthquake data and combining it with temperature data to prioritize water pipes that need repair, means for creating repair manuals for the identified repair locations using generative AI, means for creating efficient waterway maps suitable for modern areas, means for collecting and analyzing sensor data (pipe temperature and vibration) in real time, and means for displaying repair procedures automatically generated using generative AI on a wearable device. This enables efficient and high-quality repair work by quickly and accurately identifying areas that need repair and providing specific repair procedures using generative AI.

[0896] "Satellite data" refers to data obtained from Earth observation satellites, including temperature changes on the Earth's surface and atmosphere, as well as information on topography and the environment.

[0897] "Ground temperature change" refers to the phenomenon in which the temperature of the ground surface or underground in a particular area fluctuates over time.

[0898] "Stress on water pipes" refers to changes in physical loads and pressures on water pipes, especially pressures affected by environmental conditions and external factors.

[0899] "Risk of water leakage" refers to the results of assessing the danger and probability of water leaking from water pipes.

[0900] "Earthquake data" refers to data that includes information such as the magnitude, epicenter, seismic intensity, and vibration pattern of an earthquake.

[0901] A "repair manual" is an instruction document that details repair procedures, precautions, necessary tools and parts, etc. for specified repair areas.

[0902] "Generative AI" refers to artificial intelligence technology that automatically generates new information and suggestions based on large amounts of data and past knowledge.

[0903] "Modern regions" refer to settlements and cities with current living infrastructure and infrastructure.

[0904] A "waterway map" is a map showing the layout, routes, and connection points of water pipes and distribution pipes.

[0905] "Sensor data" refers to physical measurements taken in real time from measuring instruments such as temperature sensors or vibration sensors.

[0906] "Real-time collection" refers to collecting data immediately at the moment it is generated.

[0907] "Analyzing" means analyzing collected data to extract meaningful information.

[0908] A "wearable terminal" is an electronic device worn by a worker that displays information and allows data entry.

[0909] This invention is a system for efficiently managing and repairing pipelines in factories, utilizing satellite data, sensor data, and generative AI technology. Each component is described in detail below.

[0910] 1. Satellite data acquisition and analysis

[0911] The server periodically obtains data on temperature changes on the Earth's surface from Earth observation satellites. This data is obtained using an external satellite data provider. The server analyzes the obtained data to understand the temperature fluctuation patterns around the factory. This temperature data is used to detect sudden temperature changes in specific areas. Python data analysis libraries (e.g., Pandas, NumPy) are used for the analysis.

[0912] 2. Sensor data collection and analysis

[0913] The server collects data in real time from temperature and vibration sensors installed on each pipe in the factory. This sensor data is analyzed immediately by the server. When temperature fluctuations or abnormal vibrations are detected, it indicates that a particular pipe is under high stress. This analysis is performed using machine learning libraries (e.g., Scikit-learn).

[0914] 3. Prioritizing repairs

[0915] The server calculates the priority of pipes that need repair based on information obtained from temperature and sensor data. This allows it to create a repair plan that prioritizes pipes that are at greatest risk. The calculation is performed using database software (e.g., MySQL) and an algorithm based on the weighting of the data.

[0916] 4. Automatic generation of repair procedures

[0917] For each identified repair location, the server automatically generates a repair procedure using generative AI. GPT-4 is used as the generative AI model. This model generates specific repair procedures by referring to past repair data and technical literature. For example, a procedure can be generated by entering a prompt like the following:

[0918] "Please provide detailed instructions for the following repair. The location is a cooling pipe in Section A in the north of the factory, and the following conditions are present: temperature spikes and strong vibrations. The tools required are a 20mm wrench and a screwdriver."

[0919] 5. Display of repair procedures

[0920] The repair procedures obtained by generative AI are displayed in real time on wearable devices such as smart glasses. Using smart glasses allows workers to check the necessary information while keeping both hands free, improving work efficiency and accuracy. Google Glass or Vuzix are suitable devices for this.

[0921] 6. Actual repair work

[0922] The user performs specific repair work on-site while referring to the repair procedures displayed on the smart glasses. The repair procedures include text and images, and specific steps and points to note are clearly indicated, improving work efficiency and enabling even inexperienced workers to perform high-quality work.

[0923] This system is expected to improve the efficiency of pipeline management within the factory and enable repair work to be carried out quickly and accurately.

[0924] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0925] Step 1:

[0926] The server periodically obtains surface temperature data from an external satellite data provider.

[0927] Input: Temperature data from Earth observation satellites.

[0928] Data processing: Organize the temperature data as time series data.

[0929] Output: A dataset containing temperature variation patterns for a specific region.

[0930] Step 2:

[0931] The server analyzes the acquired temperature data using Python data analysis libraries (Pandas, NumPy) and identifies sudden temperature changes.

[0932] Input: A curated temperature dataset.

[0933] Data processing: Data cleaning and application of algorithms to detect sudden temperature changes.

[0934] Output: A list of points with sudden temperature changes.

[0935] Step 3:

[0936] The server collects data in real time from temperature and vibration sensors installed on each pipe in the factory.

[0937] Input: Real-time data from temperature and vibration sensors.

[0938] Data processing: Data acquisition and format conversion of temperature and vibration data.

[0939] Output: Real-time captured temperature and vibration data.

[0940] Step 4:

[0941] The server uses the Scikit-learn library to analyze sensor data acquired in real time and detect abnormal temperature fluctuations and vibrations.

[0942] Input: Real-time temperature and vibration data.

[0943] Data processing: Anomaly detection using machine learning algorithms.

[0944] Output: A list of areas where abnormal temperature fluctuations and vibrations are occurring.

[0945] Step 5:

[0946] The server combines the acquired temperature and sensor data with seismic data to calculate the priority of pipes that need repair.

[0947] Inputs: temperature data, sensor data, seismic data.

[0948] Data processing: Data integration and application of priority calculation algorithms.

[0949] Output: A prioritized list of pipes needing repair.

[0950] Step 6:

[0951] The server uses generation AI to automatically generate repair procedures for the identified repair areas.

[0952] Inputs: Identified repair area, environmental conditions, tool list.

[0953] Data processing: Generative AI model (GPT-4) was used to generate instructions based on prompts. "Please tell me in detail the procedure for the next repair. The location is a cooling pipe in Section A in the north of the factory, and the following conditions apply: temperature spike, strong vibration. The tools required are a 20mm wrench and a screwdriver."

[0954] Output: Detailed repair instructions (with text and images).

[0955] Step 7:

[0956] The user displays the generated repair procedure manual on a wearable device such as smart glasses and performs the repair work while referring to it.

[0957] Input: detailed repair instructions.

[0958] Data processing: Converting data into a display format suitable for wearable devices.

[0959] Output: Repair instructions displayed on the smart glasses.

[0960] In this way, the system can monitor temperature fluctuations and vibrations in real time and use generative AI to provide efficient repair procedures.

[0961] 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.

[0962] The present invention is a system for efficiently managing and repairing water pipes by utilizing satellite data, artificial intelligence technology (generative AI), and an emotion engine. This system divides the roles of server, terminal, and user, and each performs different processing steps to achieve optimal water pipe management. Specific embodiments are shown below.

[0963] Satellite data acquisition and analysis

[0964] The server periodically obtains ground temperature change data from a satellite data provider. This data is collected as time-series data of temperature fluctuations in a specific area and stored on the server. The server then analyzes the temperature data and calculates the stress on the water pipes. Stress points are identified using an algorithm that detects sudden changes in temperature data. For example, if a large temperature change occurs in a certain area in a short period of time, it can be determined that the water pipes in that area are under high stress.

[0965] Seismic data acquisition and analysis

[0966] The server retrieves earthquake data from reliable sources, such as seismological research institutes. This data includes information such as the magnitude, frequency, and epicenter of past earthquakes. The server analyzes this earthquake data with temperature data to prioritize water pipes that need repair. Based on earthquake vibrations and temperature changes, the server evaluates the risk of water pipes in a particular area.

[0967] Repair prioritization

[0968] The server uses temperature and earthquake data to create a priority list of water pipes that need repair, and then creates an appropriate repair plan based on this list.

[0969] Generate repair manuals

[0970] The server uses generation AI to automatically generate repair manuals. The generated repair manuals contain repair procedures, necessary tools and parts, and important points to note, all in text and with images. This allows even inexperienced or foreign workers to carry out repair work efficiently.

[0971] Efficient hydrographic charting

[0972] The terminal uses the analysis data from the server to create an efficient waterway map suitable for modern settlements, which the waterworks bureau uses when formulating long-term waterway development plans.

[0973] Emotion engine integration

[0974] The server also integrates an emotion engine to detect the user's emotions in real time while they are working on the repairs. The emotion engine evaluates the user's stress level and satisfaction through facial recognition and voice analysis. For example, if the user expresses high levels of stress, the emotion engine adjusts the instructions in the repair manual to be simpler. Also, if the user expresses high levels of satisfaction, the engine appropriately adjusts the progress of the repair work based on that feedback.

[0975] The actual repair work

[0976] Users refer to the provided repair manual to carry out the actual repair work. The manual contains detailed descriptions of specific procedures, tools, parts, and precautions to be taken, allowing the work to be carried out efficiently and safely. In addition, the emotion engine adjusts work instructions as needed based on real-time evaluations, reducing user stress and improving the quality of work.

[0977] Through the above process, the server, terminals, and users work together to create a system that effectively manages and repairs water pipes.

[0978] The processing flow will be explained below.

[0979] Processing Steps

[0980] Step 1:

[0981] The server obtains ground temperature data from a satellite data provider. Specifically, the server periodically sends an API request to receive temperature data for a specified area. The received data is recorded in a database as time-series data.

[0982] Step 2:

[0983] The server analyzes the acquired temperature data and calculates the stress on the water pipes. Specifically, it uses an analysis algorithm to identify points of sudden temperature changes and calculates the degree of stress that these points are putting on the water pipes. These stress points are then listed.

[0984] Step 3:

[0985] The server retrieves earthquake information from earthquake data providers. The earthquake data includes the magnitude, frequency, and epicenter of past earthquakes, and is also retrieved by periodically sending API requests. The earthquake data is stored in a database.

[0986] Step 4:

[0987] The server then performs an analysis by overlaying temperature data and earthquake data. Specifically, it compares stress points with earthquake data to assess the extent to which water pipes in a particular area are exposed to multiple risks. This allows it to prioritize areas that need repairs.

[0988] Step 5:

[0989] The server uses generative AI to create a repair manual for each prioritized repair area. Specifically, it references past repair data and technical literature to automatically generate text and images detailing the appropriate repair procedures, necessary tools, parts, and important points to note.

[0990] Step 6:

[0991] The device uses data provided by the server to create an efficient waterway map suitable for modern settlements. Specifically, it uses the analysis data to design the optimal layout and route of water pipes, supporting long-term development plans.

[0992] Step 7:

[0993] The server runs an emotion engine to recognize the user's emotions in real time during repair work. The emotion engine detects the user's stress level and satisfaction through facial recognition and voice analysis.

[0994] Step 8:

[0995] The server adjusts the instructions in the repair manual based on the emotion engine's evaluation results. For example, if the user's stress level is high, the instructions are simplified. Also, if the user's satisfaction level is high, the server adjusts the progress of the repair work based on that feedback.

[0996] Step 9:

[0997] The user refers to the provided repair manual and performs the actual repair work. Specifically, the user proceeds with the work while looking at the procedures and images described in the manual, and completes the work using the specified tools and parts. Based on real-time evaluation by the emotion engine, the work instructions are adjusted as needed, reducing user stress and improving work efficiency.

[0998] Through the above processing steps, a system is realized in which the server, terminals, and users work together to effectively manage and repair water pipes.

[0999] Example 2

[1000] 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."

[1001] The management and repair of existing water pipes often relies on human resources, resulting in issues with efficiency and accuracy. Furthermore, there is a lack of methods to properly assess stress caused by external factors such as temperature changes and earthquakes and identify areas that should be prioritized for repair. Furthermore, there is a lack of real-time support to reduce user stress during repair work and improve the quality of work.

[1002] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting ground temperature changes using satellite data, means for analyzing the collected temperature data to calculate stress on water pipes, means for acquiring earthquake data and multiplying it with the temperature data to prioritize water pipes that need repair, means for creating repair manuals for the identified repair locations using a generation AI, and means for monitoring the user's emotions during repair work in real time and dynamically adjusting instructions in the repair manual as necessary. This enables efficient and accurate management and repair of water pipes.

[1003] "Satellite data" is data obtained from artificial satellites to observe the Earth's surface and atmosphere.

[1004] "Temperature change data" is time series data that shows how the ground temperature in a particular area changes over time.

[1005] "Stress on water pipes" refers to the physical loads and pressures that water pipes are subjected to due to external factors such as temperature changes and earthquakes.

[1006] "Water leakage risk" is an evaluation index that indicates the degree of possibility that a water pipe will break and cause a water leak.

[1007] "Earthquake Data" means data containing information on the magnitude, frequency, and epicenters of past and present earthquakes.

[1008] "Water pipes in need of repair" are water pipes that have been identified as being in need of immediate repair due to high stress caused by temperature changes and earthquakes.

[1009] "Generative AI" is a type of artificial intelligence technology that refers to algorithms that generate natural-looking sentences and images based on specific prompts.

[1010] A "repair manual" is a document that describes the procedures required to efficiently carry out water pipe repair work, the tools and parts to be used, and points to note.

[1011] An "efficient waterway map" is a map that optimizes the layout and routing of water pipes and allows for efficient management and maintenance of water supply systems in settlements and cities.

[1012] The "Emotion Engine" is a technology that assesses a user's stress level and satisfaction in real time through facial recognition and voice analysis.

[1013] "User" refers to the worker who actually carries out the water pipe repair work.

[1014] A "server" is a computer system that collects, analyzes, and operates the generated AI.

[1015] A "terminal" is a computer device that creates and displays hydrographic charts based on analysis data from the server.

[1016] This invention is a system that efficiently manages and repairs water pipes by utilizing satellite data, artificial intelligence technology (generative AI), and an emotion engine. This system divides the roles of server, terminal, and user, and each performs different processing steps to achieve optimal water pipe management.

[1017] Satellite data acquisition and analysis

[1018] The server periodically obtains ground temperature change data from a satellite data provider. This data is collected as time-series data of temperature fluctuations in a specific area and stored on the server. The Python scikit-learn library is used to analyze the temperature data and calculate the stress on the water pipes. For example, the server obtains data in JSON format from "https: / / api.satelliteprovider.com / temperature" and converts it into a Pandas data frame. Furthermore, a Z-score is calculated to detect outliers in the data.

[1019] Seismic data acquisition and analysis

[1020] The server retrieves earthquake data from earthquake research institutes and earthquake data providers via API. This data includes information on the magnitude, frequency, and epicenter of past earthquakes. The server combines this data with temperature data and analyzes it to assess the risk to water pipes in a specific area. Specifically, the server downloads earthquake data in CSV format from "https: / / earthquake.usgs.gov / fdsnws / event / 1 / query" and merges it with the temperature data for analysis. Python's NumPy and Pandas are used for the analysis.

[1021] Repair prioritization

[1022] The server generates a list of high-risk water pipes based on temperature and earthquake data. Based on this list, it prioritizes the pipes that need repair and creates a repair plan. Specifically, the server calculates a repair necessity score based on the analysis results and sorts the list in descending order of score. The results are saved in a MySQL database.

[1023] Generate repair manuals

[1024] The server uses a generative AI (e.g., GPT-4) to automatically generate a detailed repair manual. The repair procedure, necessary tools and parts, and precautions are written in text and images. As an example of a specific prompt, "Please generate a repair procedure, including necessary tools, parts, and precautions," is input to GPT-4, and the generated text is formatted in HTML.

[1025] Efficient hydrographic charting

[1026] The terminal uses design software such as AutoCAD to create efficient hydrographic diagrams based on the analysis data received from the server. This enables long-term water pipe maintenance planning. Specifically, the terminal runs an AutoCAD script to draw the hydrographic diagram based on the coordinate data received from the server. The generated diagram is saved as a PDF file.

[1027] Emotion engine integration

[1028] The server integrates an emotion engine (e.g., Affdex API) to monitor the user's emotions in real time while they are working on repairs. It uses facial recognition and voice analysis to evaluate their stress level and satisfaction. Specifically, the server captures the user's webcam footage and microphone input, and performs emotion analysis using the Affdex API. Based on the evaluation results, the content of the repair manual is dynamically adjusted.

[1029] The actual repair work

[1030] The user performs actual repair work by referring to the provided repair manual. If the emotion engine detects the user's stress, the work instructions are adjusted in real time. Specifically, the user follows the specific steps in the repair manual and performs the repair work using specified tools (e.g., pipe wrench, plumbing tape, etc.). If the emotion engine detects stress during the work, the manual instructions may be simplified.

[1031] Through the above steps, a system is realized in which the server, terminals, and users work together to efficiently and effectively manage and repair water pipes.

[1032] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1033] Step 1:

[1034] (Satellite data acquisition)

[1035] The server connects to the satellite data provider's API to periodically obtain data on ground temperature changes in a specific area.

[1036] Input: API endpoint URL, authentication information

[1037] Specific operation: The server retrieves data in JSON format from "https: / / api.satelliteprovider.com / temperature".

[1038] Data processing: Convert the acquired JSON data into a Pandas data frame.

[1039] Output: Formatted temperature change data is obtained.

[1040] Step 2:

[1041] (Temperature data analysis)

[1042] The server analyzes the temperature change data and collects and stores the temperature fluctuations of the ground in a specific area as time-series data.

[1043] Input: Formatted temperature change data

[1044] Specific operation: The server uses Python's scikit-learn library to detect outliers using Z scores.

[1045] Data calculation: Calculate stress points and perform risk assessments for specific areas.

[1046] Output: Stress points on the water pipes are identified.

[1047] Step 3:

[1048] (Acquisition of earthquake data)

[1049] The server obtains earthquake data from earthquake research institutes and earthquake data providers via API.

[1050] Input: API endpoint URL, authentication information

[1051] Specific operation: The server downloads earthquake data in CSV format from "https: / / earthquake.usgs.gov / fdsnws / event / 1 / query".

[1052] Data processing: Convert the downloaded CSV data into a Pandas data frame.

[1053] Output: Formatted seismic data.

[1054] Step 4:

[1055] (Analysis of temperature and seismic data)

[1056] The server combines temperature and earthquake data to assess how much risk water pipes in a particular area are at.

[1057] Input: Formatted temperature data, formatted seismic data

[1058] What happens: The server merges the data using NumPy and Pandas and performs a risk assessment.

[1059] Data calculation: Based on the integrated data, calculate the priority of water pipes that need repair.

[1060] Output: Risk assessment results and a priority list are generated.

[1061] Step 5:

[1062] (Prioritizing repairs)

[1063] Based on the risk assessment results, the server generates a list of water pipes that need repair.

[1064] Input: Risk assessment results, priority list

[1065] Specific operation: The server calculates the repair necessity score and sorts the list by highest score.

[1066] Data processing: Save the list in a MySQL database.

[1067] Output: A list of repair priorities is stored in the database.

[1068] Step 6:

[1069] (Generate repair manual)

[1070] The server automatically generates repair manuals using generative AI (e.g., GPT-4 model).

[1071] Input: Repair requirements, construction details

[1072] Specific action: GPT-4 is given the prompt, "Generate repair instructions, including required tools, parts, and precautions."

[1073] Data calculation: The generated repair manual is formatted into HTML format.

[1074] Output: A detailed repair manual is generated.

[1075] Step 7:

[1076] (Efficient hydrographic charting)

[1077] The terminal creates an efficient hydrographic chart based on the analysis data received from the server.

[1078] Input: Repair priority data, coordinate data

[1079] Specific operation: The terminal draws a hydrographic chart using AutoCAD.

[1080] Data processing: Save the generated hydrographic chart in PDF format.

[1081] Output: An efficient hydrographic chart is generated in a PDF file.

[1082] Step 8:

[1083] (Emotion engine integration)

[1084] The server uses an emotion engine to monitor the user's emotions in real time during repair work.

[1085] Input: User's webcam video and audio data

[1086] Specific operation: The server uses the Affdex API to perform sentiment analysis and evaluate stress levels.

[1087] Data Calculation: Dynamically adjust repair manuals based on the user's stress level.

[1088] Output: Repair instructions tailored to the user's emotional state are provided.

[1089] Step 9:

[1090] (Actual repair work)

[1091] The user performs the actual repair work by referring to the provided repair manual.

[1092] Input: Detailed repair manual, tools used

[1093] Specific operation: The user follows the steps in the manual and performs the repair using the specified tools (e.g., pipe wrench, plumbing tape).

[1094] Data Calculation: If the emotion engine detects stress, it will automatically adjust its instructions.

[1095] Output: Repair work completed and work quality improved.

[1096] (Application example 2)

[1097] 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."

[1098] Conventional water pipe management and repair systems have difficulty efficiently identifying leak risks and prioritizing repairs. Furthermore, the quality of repair work varies depending on the experience and skills of the workers, and workers are subject to significant stress and strain. To address these issues, more accurate analysis and planning is required by utilizing satellite and earthquake data. Furthermore, a new challenge is being faced: analyzing workers' emotions in real time to improve the quality and efficiency of work.

[1099] The specific processing by the specific 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 ground temperature changes using satellite data, means for analyzing the collected temperature data to calculate stress on pipes, means for predicting the risk of water leakage based on the stress data, means for acquiring earthquake data and combining it with temperature data to prioritize pipes in need of repair, means for creating repair manuals for the identified repair locations using generative AI, emotion analysis means for evaluating user emotions in real time when performing repair work based on the manual, and means for creating efficient piping diagrams suitable for modern settlements. This not only efficiently identifies areas in need of repair and provides repair manuals, but also analyzes worker emotions and adjusts instructions, thereby improving work efficiency and quality and reducing user stress.

[1100] "Satellite data" refers to information about the Earth's surface and atmosphere collected from artificial satellites, and is particularly data that can acquire temperature changes and environmental conditions in real time.

[1101] "Temperature data" is information that records changes in the temperature of the earth's surface or an object, and represents temperature fluctuations in a specific area over time.

[1102] "Stress" refers to the physical load or pressure on pipes and equipment, and indicates the risk caused by sudden temperature changes and vibrations in particular.

[1103] "Earthquake data" refers to data that includes information such as the magnitude, epicenter, and frequency of shaking caused by earthquakes.

[1104] "Generative AI" is a type of artificial intelligence technology that has the ability to generate new data and text from given information.

[1105] A "repair manual" is an instruction manual that describes the procedures for carrying out repair work, the necessary tools, parts, and precautions.

[1106] "Emotion analysis" is a technology that assesses a user's emotional state in real time through facial recognition and voice analysis, measuring stress and satisfaction.

[1107] A "piping diagram" is a map showing the layout and connections of water pipes and other pipes, and is created for efficient pipe management and repair planning.

[1108] "User" refers to the worker who actually performs the piping repair work by referring to the provided repair manual.

[1109] The present invention is a system that efficiently manages and repairs pipes by utilizing satellite data, artificial intelligence technology (generative AI), and an emotion engine. Specific embodiments are described below.

[1110] Satellite data acquisition and analysis

[1111] First, the server periodically obtains surface temperature change data from a satellite data provider. This data represents temperature fluctuations in a specific area and is obtained in real time. The server analyzes the temperature data and calculates the stress on the pipes. To do this, an algorithm is used to detect sudden changes in temperature data. For example, if a large temperature change is observed in a certain area in a short period of time, it is determined that the pipes in that area are under high stress.

[1112] Seismic data acquisition and analysis

[1113] The server retrieves earthquake data from reliable sources, such as seismological research institutes. This data includes information on the magnitude, frequency, and epicenter of past earthquakes. The server analyzes the earthquake data together with temperature data to prioritize pipes that need repair. The seismic vibrations and temperature changes are used to assess the risk of pipes in a particular area.

[1114] Repair prioritization

[1115] Based on the analysis results, the server creates a list of pipes that need repair in order of priority, and then creates an appropriate repair plan based on this list.

[1116] Generate repair manuals

[1117] Next, the server uses the generation AI to automatically generate a repair manual. The generated repair manual contains repair procedures, necessary tools and parts, important points to note, and other information in text and images. For example, a manual can be created by inputting the following prompts into the generation AI:

[1118] "Repair the following stress points: [(20, 30), (40, 50), (70, 80)]. Generate detailed instructions including tools, components, and safety notes."

[1119] This will enable even inexperienced workers or foreign workers to carry out repair work efficiently.

[1120] Emotion engine integration

[1121] The server also integrates an emotion engine to detect the user's emotions in real time while they are performing repair work. The emotion engine uses a camera and microphone to recognize the worker's face and analyze their voice. If the work is difficult or indicates high stress, the emotion engine will simplify the instructions in the repair manual. For example, if it determines that the user is experiencing high stress, it will change complex procedures to simpler instructions.

[1122] The actual repair work

[1123] Users refer to the provided repair manual when carrying out actual repair work. Based on real-time evaluations by the emotion engine, work instructions are adjusted as needed, reducing user stress and improving the quality of work. Furthermore, efficient piping diagrams suitable for modern settlements are created and used for long-term maintenance planning.

[1124] In this way, the collaboration between servers, terminals, and users enables efficient pipe management and repair. Specific hardware and software are used for collecting and analyzing each piece of data. Specifically, Apache Spark is used for data analysis, TensorFlow and PyTorch for AI analysis, and OpenFace and Wav2Vec for sentiment analysis.

[1125] The detailed description of the embodiments clarifies the technical scope of the invention, supports the scope of patent protection, and serves as a reference for other users to understand and implement the invention.

[1126] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1127] Step 1:

[1128] The server periodically obtains data on changes in surface temperature over a specific area from a satellite data provider. The input is temperature data from the satellite data provider, and the output is time-series data showing changes in surface temperature. The server stores this data and uses it for further analysis.

[1129] Step 2:

[1130] The server analyzes the acquired temperature data and calculates the stress on the pipe. Specifically, it runs an algorithm that detects sudden changes in the temperature data. The input is ground temperature data, and the output is data indicating stress points on the pipe.

[1131] Step 3:

[1132] The server retrieves earthquake data from a reliable source such as an earthquake research institute. The input is earthquake data including the magnitude, frequency, and epicenter of past earthquakes, and the output is data evaluating the impact of earthquakes. The server uses this data for further analysis.

[1133] Step 4:

[1134] The server analyzes temperature and earthquake data and prioritizes pipes that need repair. The input is temperature and earthquake data, and the output is a list of pipes that need repair and their priorities.

[1135] Step 5:

[1136] The server uses a generative AI to create a repair manual for the identified repair area. Specifically, it inputs the following prompt sentence into the generative AI model:

[1137] "Repair the following stress points: [(20, 30), (40, 50), (70, 80)]. Generate detailed instructions including tools, components, and safety notes."

[1138] The input is a list of repairs (stress points), and the output is a detailed repair manual, including text and images, describing the tools and parts required, and important points to note.

[1139] Step 6:

[1140] The user refers to the repair manual and performs the repair work. The input is the repair manual provided by the server, and the output is the progress of the actual repair work. The user follows the manual and performs the repair work efficiently.

[1141] Step 7:

[1142] During the repair work, the server uses an emotion engine to analyze the user's emotions in real time. Specifically, it uses a camera and microphone to recognize the user's face and analyze their voice. The input is real-time facial images and voice data obtained from the camera and microphone, and the output is data indicating the user's emotional state.

[1143] Step 8:

[1144] The server adjusts the instructions in the repair manual based on the user's emotional data. For example, if the user is feeling high stress, it simplifies complex procedures. The input is the user's emotional state, and the output is the adjusted repair manual.

[1145] Step 9:

[1146] The server compiles the final repair results and creates an efficient piping diagram suitable for modern settlements. The input is the repair work results data, and the output is a new piping diagram. This piping diagram is used for long-term maintenance planning.

[1147] 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.

[1148] 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.

[1149] 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.

[1150] [Fourth embodiment]

[1151] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1152] 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.

[1153] 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).

[1154] 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.

[1155] 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.

[1156] 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).

[1157] 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.

[1158] 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.

[1159] 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.

[1160] 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.

[1161] 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.

[1162] 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.

[1163] 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."

[1164] This invention is a system that utilizes satellite data and artificial intelligence technology (generative AI) to efficiently manage and repair water pipes. In this system, the server, terminal, and user each play different roles, and optimal water pipe management is achieved through each processing step. How the present invention is implemented is described in detail below.

[1165] 1. Satellite data acquisition and analysis

[1166] The server periodically obtains ground temperature data from a satellite data provider, collecting time-series data on temperature fluctuations in a specific area. The server then analyzes this temperature data internally to calculate the stress on the water pipes. Stress points are identified using an algorithm that detects sudden changes in temperature data. For example, if a certain area experiences a sudden change in temperature, it can be determined that the water pipes in that area are under high stress.

[1167] 2. Seismic data acquisition and analysis

[1168] The server acquires earthquake data from reliable data sources such as the Earthquake Research Institute. It collects information such as the magnitude, frequency, and epicenter of past earthquakes. It then matches the acquired earthquake data with temperature data to prioritize the locations of water pipes that are most in need of repair. It then assesses the degree of risk to water pipes in the identified area based on vibrations and temperature changes caused by earthquakes.

[1169] 3. Prioritizing repairs

[1170] The server calculates the priority of water pipes that need repair based on information obtained from temperature and earthquake data. The priority is then used to create a list of locations that urgently need repairs, and an appropriate repair plan is created based on the results.

[1171] 4. Generate repair manual

[1172] The server uses generative AI to automatically create a repair manual for each identified repair location. This manual includes repair procedures, necessary tools and parts, and points to note. The generative AI provides specific, easy-to-understand content by referring to past repair data and technical literature. This allows even inexperienced or foreign workers to carry out repair work efficiently.

[1173] 5. Efficient hydrographic charting

[1174] The device uses the surveyed data to create an optimal waterway map suitable for modern settlements. This helps design the optimal layout and routing of water pipes. Based on the layout of new water pipes and plans for replacement, the waterworks bureau can formulate long-term maintenance plans.

[1175] 6. Actual repair work

[1176] Users refer to the provided repair manual to carry out specific repair work on-site. The manual contains text and images, and clearly states specific procedures and important points, making it easy for anyone to understand. This enables waterworks bureaus and subcontractors to carry out repair work efficiently and with high quality.

[1177] Through the above process, the system of the present invention can solve the problems of conventional water pipe management and support the realization of sustainable water infrastructure.

[1178] The processing flow will be explained below.

[1179] Processing Steps

[1180] Step 1:

[1181] The server obtains ground temperature data from a satellite data provider. Specifically, the server periodically sends an API request to receive temperature data for a specified area. The received data is recorded in a database as time-series data.

[1182] Step 2:

[1183] The server analyzes the acquired temperature data and calculates the stress on the water pipes. Specifically, it uses an analysis algorithm to identify points of sudden temperature changes and calculates the degree of stress that these points are putting on the water pipes. These stress points are then listed.

[1184] Step 3:

[1185] The server retrieves earthquake information from earthquake data providers. The earthquake data includes the magnitude, frequency, and epicenter of past earthquakes, and is also retrieved by periodically sending API requests. The earthquake data is stored in a database.

[1186] Step 4:

[1187] The server compares temperature data with earthquake data and performs an analysis. Specifically, it overlays stress points with earthquake data to assess the extent to which water pipes in a specific area are exposed to multiple risks. Based on the results of this analysis, it prioritizes areas that need repair.

[1188] Step 5:

[1189] The server uses generative AI to create repair manuals for each section of water pipe that needs repair. Specifically, it references past repair data and technical literature to automatically generate text and images detailing the appropriate repair procedures, necessary tools, parts, and important points to note.

[1190] Step 6:

[1191] The device uses the analysis data and repair manuals to create an efficient waterway map suitable for modern settlements. Specifically, it designs the optimal layout of water pipes based on repair location data provided by the server, and supports long-term maintenance planning.

[1192] Step 7:

[1193] The user performs the actual repair work while referring to the provided repair manual. Specifically, the user proceeds with the work while looking at the procedures and images described in the manual, and completes the repair of the water pipe using the specified tools and parts.

[1194] Through the above processing steps, a system is realized in which the server, terminals, and users work together to effectively manage and repair water pipes.

[1195] Example 1

[1196] 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."

[1197] Conventional water pipe management systems rely on visual inspections and regular maintenance without properly considering changes in ground temperature or the effects of earthquakes, making it difficult to respond immediately when leaks or damage occur. Furthermore, there is a lack of efficient repair work and specific repair procedures, which means that repair work is highly dependent on the experience and skills of workers, often resulting in variations in the quality and efficiency of repair work. This creates problems that make it difficult to ensure the sustainability and efficient management of water infrastructure.

[1198] 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.

[1199] In this invention, the server includes means for collecting ground temperature changes using satellite data, means for preprocessing the collected temperature data and calculating stress on water pipes, means for identifying stress points using an algorithm for detecting sudden temperature changes, means for acquiring earthquake data and integrating it with temperature data to evaluate the risk of water pipes, means for calculating the priority of water pipes requiring repair based on the temperature data and earthquake data, means for generating prompt sentences using a generative AI model for each identified repair location and creating a repair manual, and means for creating an efficient waterway diagram based on the survey data. This enables risk assessment of water pipes and prioritization of repairs that take temperature changes and the effects of earthquakes into account, enabling efficient and high-quality repair work.

[1200] "Satellite Data" means information about the Earth's surface obtained from artificial satellites in Earth orbit.

[1201] "Temperature data" refers to data that records the ground or air temperature over time in a specific area.

[1202] A "stress point" is a location where a water pipe is subjected to particularly high physical or environmental stress.

[1203] "Earthquake data" refers to data that records information about earthquakes, such as their magnitude, epicenter, and the date and time of occurrence.

[1204] "Risk assessment" is the process of quantitatively assessing the risk of water pipe failure or leakage based on specific conditions and data.

[1205] "Priority" refers to the ranking of water pipes that need repair based on their importance.

[1206] A "generative AI model" is an algorithm that uses artificial intelligence techniques to generate an appropriate output for a specific input.

[1207] A "prompt" is a sentence that describes specific instructions or questions for a generative AI model.

[1208] A "repair manual" is a document that contains specific procedures and instructions for efficiently carrying out water pipe repair work.

[1209] An "efficient waterway diagram" is a drawing that designs the optimal layout and routing of water pipes.

[1210] This invention is a system in which the server, terminal, and user components each play different roles, utilizing satellite data and generative AI models to properly manage and efficiently repair water pipes.

[1211] Server configuration and operation

[1212] The server performs the following actions:

[1213] 1. Acquisition of satellite data

[1214] The server periodically obtains ground temperature data using the API of the satellite data provider. For example, it communicates with a common satellite data provider via API to collect temperature data for a specified area.

[1215] 2. Temperature data preprocessing and analysis

[1216] The server receives the collected temperature data in JSON format, checks for outliers, and performs imputation. After preprocessing, the server analyzes the temperature data and calculates the stress on the water pipes. For example, it uses the least squares method to calculate the temperature change rate and identify stress points if there are sudden changes.

[1217] 3. Seismic data acquisition and analysis

[1218] The server uses the Earthquake Research Institute's API to acquire earthquake data, preprocess it, and integrate it with temperature data to perform risk assessment. For example, historical earthquake data and temperature fluctuation data can be integrated to create a risk map.

[1219] 4. Prioritizing repairs

[1220] The server calculates the priority of water pipes that need repair based on temperature and earthquake data. For example, it comprehensively evaluates stress points due to climate change and earthquake risk, and lists high-priority areas.

[1221] 5. Creating repair manuals using generative AI

[1222] The server uses the generative AI model to generate prompts for each identified repair location and automatically creates a repair manual. For example, a prompt such as "Please tell me the procedure for repairing water pipes due to sudden temperature changes" is input into the generative AI and a manual is created.

[1223] Terminal configuration and operation

[1224] The device uses the data sent from the server to perform the following actions:

[1225] 1. Data Receipt and Analysis

[1226] The terminal receives temperature data, earthquake data, and repair priority list obtained from the server.

[1227] 2. Efficient hydrographic charting

[1228] The terminals then use the data they receive to create efficient waterway maps and use GIS (geographic information system) software to design new pipe layouts and replacement plans. For example, ESRI ArcGIS software is used to design optimal routes.

[1229] User Configuration and Behavior

[1230] The user performs the following actions:

[1231] 1. Refer to the repair manual and carry out the work

[1232] The user refers to the repair manual provided by the server on their terminal and carries out the repair work on site. The repair manual contains specific text and images, and clearly shows, for example, "the procedure for repairing and reassembling a damaged part of a water pipe using specific tools."

[1233] 2. Submitting a work report

[1234] Once the repair work is completed, the user uploads a report and photos of the work to the server, allowing the administrator to check the progress of the work in real time.

[1235] With the above configuration and operation, the system of the present invention realizes efficient management and repair of water pipes taking into account the effects of temperature changes and earthquakes, and supports the realization of sustainable water infrastructure.

[1236] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1237] Step 1:

[1238] Data Acquisition

[1239] The server periodically obtains ground temperature data using the satellite data provider's API. The input is the coordinate data and API key of the specified area, and the output is the temperature data (in JSON format) for that area. The server sends a "GET request" to the API to collect the temperature data.

[1240] Step 2:

[1241] Temperature data preprocessing

[1242] The server receives the acquired temperature data and checks for outliers and missing values. The input is JSON-formatted temperature data, and the output is preprocessed clean data. The server filters outliers and fills in approximate values ​​if necessary.

[1243] Step 3:

[1244] Stress Calculation

[1245] The server analyzes the preprocessed temperature data and calculates the stress on the water pipes. The input is clean data, and the output is the stress calculation result. Specifically, the server quantifies the rapidity of temperature changes, and determines that rapid fluctuations indicate high stress. For example, it calculates the rate of temperature change over the course of a day and calculates a stress score based on that.

[1246] Step 4:

[1247] Identifying stress points

[1248] The server identifies stress points based on the stress score obtained from the temperature data analysis. The input is the stress calculation result, and the output is the location information of the stress points. The area where a sudden temperature change was detected is identified and recorded as geographic information.

[1249] Step 5:

[1250] Seismic data acquisition and preprocessing

[1251] The server retrieves earthquake data using the Earthquake Research Institute's API. The input is the coordinate data of the specified area and the API key, and the output is earthquake data (JSON format). The earthquake data is also preprocessed to check for outliers and missing values.

[1252] Step 6:

[1253] Risk Assessment

[1254] The server integrates preprocessed seismic data with temperature data to assess the risk of water pipes. The inputs are preprocessed seismic data and temperature data, and the output is the risk assessment results. Specifically, a risk map is created using past earthquake data and temperature fluctuation data.

[1255] Step 7:

[1256] Repair prioritization

[1257] The server calculates the priority of water pipes that need repair based on the risk assessment results. The input is the risk assessment results, and the output is a repair priority list. The stress score and risk level are combined to create a list of high-priority areas.

[1258] Step 8:

[1259] Creation of repair manuals

[1260] The server uses a generative AI model to create prompts for each identified repair location and generate a repair manual. The input is the prompt (e.g., "Please tell me the procedure for repairing water pipes due to sudden temperature changes"), and the output is the repair manual. The AI ​​model outputs specific repair procedures based on the prompts.

[1261] Step 9:

[1262] Efficient hydrographic charting

[1263] The terminal creates an efficient hydrographic map based on the data sent from the server. The input is the risk assessment results and repair priority list, and the output is the new hydrographic map. GIS software is used to design the optimal water pipe layout and routing.

[1264] Step 10:

[1265] Repair work

[1266] The user refers to the repair manual and performs specific repair work on-site. The input is the repair manual, and the output is a repair completion report. The user follows the repair procedure and repairs the water pipe using the necessary tools and parts. After the work is completed, the user uploads the report and photos to the server.

[1267] (Application example 1)

[1268] 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."

[1269] Conventional water pipe management systems have difficulty properly detecting and predicting abnormal temperature fluctuations and stress caused by earthquakes, requiring a great deal of time and effort to prioritize repairs and create specific repair procedures. Furthermore, ensuring the quality of repair work requires experienced workers, making efficient work difficult. Furthermore, complex environments such as factories require real-time monitoring of pipe conditions and rapid response, but current systems are inadequate. Therefore, a new management system is needed that monitors temperature fluctuations and vibrations in real time and uses generative AI to present efficient repair procedures.

[1270] 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.

[1271] In this invention, the server includes means for collecting ground temperature changes using satellite data, means for analyzing the collected temperature data to calculate stress on water pipes, means for predicting the risk of water leakage based on the stress data, means for acquiring earthquake data and combining it with temperature data to prioritize water pipes that need repair, means for creating repair manuals for the identified repair locations using generative AI, means for creating efficient waterway maps suitable for modern areas, means for collecting and analyzing sensor data (pipe temperature and vibration) in real time, and means for displaying repair procedures automatically generated using generative AI on a wearable device. This enables efficient and high-quality repair work by quickly and accurately identifying areas that need repair and providing specific repair procedures using generative AI.

[1272] "Satellite data" refers to data obtained from Earth observation satellites, including temperature changes on the Earth's surface and atmosphere, as well as information on topography and the environment.

[1273] "Ground temperature change" refers to the phenomenon in which the temperature of the ground surface or underground in a particular area fluctuates over time.

[1274] "Stress on water pipes" refers to changes in physical loads and pressures on water pipes, especially pressures affected by environmental conditions and external factors.

[1275] "Risk of water leakage" refers to the results of assessing the danger and probability of water leaking from water pipes.

[1276] "Earthquake data" refers to data that includes information such as the magnitude, epicenter, seismic intensity, and vibration pattern of an earthquake.

[1277] A "repair manual" is an instruction document that details repair procedures, precautions, necessary tools and parts, etc. for specified repair areas.

[1278] "Generative AI" refers to artificial intelligence technology that automatically generates new information and suggestions based on large amounts of data and past knowledge.

[1279] "Modern regions" refer to settlements and cities with current living infrastructure and infrastructure.

[1280] A "waterway map" is a map showing the layout, routes, and connection points of water pipes and distribution pipes.

[1281] "Sensor data" refers to physical measurements taken in real time from measuring instruments such as temperature sensors or vibration sensors.

[1282] "Real-time collection" refers to collecting data immediately at the moment it is generated.

[1283] "Analyzing" means analyzing collected data to extract meaningful information.

[1284] A "wearable terminal" is an electronic device worn by a worker that displays information and allows data entry.

[1285] This invention is a system for efficiently managing and repairing pipelines in factories, utilizing satellite data, sensor data, and generative AI technology. Each component is described in detail below.

[1286] 1. Satellite data acquisition and analysis

[1287] The server periodically obtains data on temperature changes on the Earth's surface from Earth observation satellites. This data is obtained using an external satellite data provider. The server analyzes the obtained data to understand the temperature fluctuation patterns around the factory. This temperature data is used to detect sudden temperature changes in specific areas. Python data analysis libraries (e.g., Pandas, NumPy) are used for the analysis.

[1288] 2. Sensor data collection and analysis

[1289] The server collects data in real time from temperature and vibration sensors installed on each pipe in the factory. This sensor data is analyzed immediately by the server. When temperature fluctuations or abnormal vibrations are detected, it indicates that a particular pipe is under high stress. This analysis is performed using machine learning libraries (e.g., Scikit-learn).

[1290] 3. Prioritizing repairs

[1291] The server calculates the priority of pipes that need repair based on information obtained from temperature and sensor data. This allows it to create a repair plan that prioritizes pipes that are at greatest risk. The calculation is performed using database software (e.g., MySQL) and an algorithm based on the weighting of the data.

[1292] 4. Automatic generation of repair procedures

[1293] For each identified repair location, the server automatically generates a repair procedure using generative AI. GPT-4 is used as the generative AI model. This model generates specific repair procedures by referring to past repair data and technical literature. For example, a procedure can be generated by entering a prompt like the following:

[1294] "Please provide detailed instructions for the following repair. The location is a cooling pipe in Section A in the north of the factory, and the following conditions are present: temperature spikes and strong vibrations. The tools required are a 20mm wrench and a screwdriver."

[1295] 5. Display of repair procedures

[1296] The repair procedures obtained by generative AI are displayed in real time on wearable devices such as smart glasses. Using smart glasses allows workers to check the necessary information while keeping both hands free, improving work efficiency and accuracy. Google Glass or Vuzix are suitable devices for this.

[1297] 6. Actual repair work

[1298] The user performs specific repair work on-site while referring to the repair procedures displayed on the smart glasses. The repair procedures include text and images, and specific steps and points to note are clearly indicated, improving work efficiency and enabling even inexperienced workers to perform high-quality work.

[1299] This system is expected to improve the efficiency of pipeline management within the factory and enable repair work to be carried out quickly and accurately.

[1300] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1301] Step 1:

[1302] The server periodically obtains surface temperature data from an external satellite data provider.

[1303] Input: Temperature data from Earth observation satellites.

[1304] Data processing: Organize the temperature data as time series data.

[1305] Output: A dataset containing temperature variation patterns for a specific region.

[1306] Step 2:

[1307] The server analyzes the acquired temperature data using Python data analysis libraries (Pandas, NumPy) and identifies sudden temperature changes.

[1308] Input: A curated temperature dataset.

[1309] Data processing: Data cleaning and application of algorithms to detect sudden temperature changes.

[1310] Output: A list of points with sudden temperature changes.

[1311] Step 3:

[1312] The server collects data in real time from temperature and vibration sensors installed on each pipe in the factory.

[1313] Input: Real-time data from temperature and vibration sensors.

[1314] Data processing: Data acquisition and format conversion of temperature and vibration data.

[1315] Output: Real-time captured temperature and vibration data.

[1316] Step 4:

[1317] The server uses the Scikit-learn library to analyze sensor data acquired in real time and detect abnormal temperature fluctuations and vibrations.

[1318] Input: Real-time temperature and vibration data.

[1319] Data processing: Anomaly detection using machine learning algorithms.

[1320] Output: A list of areas where abnormal temperature fluctuations and vibrations are occurring.

[1321] Step 5:

[1322] The server combines the acquired temperature and sensor data with seismic data to calculate the priority of pipes that need repair.

[1323] Inputs: temperature data, sensor data, seismic data.

[1324] Data processing: Data integration and application of priority calculation algorithms.

[1325] Output: A prioritized list of pipes needing repair.

[1326] Step 6:

[1327] The server uses generation AI to automatically generate repair procedures for the identified repair areas.

[1328] Inputs: Identified repair area, environmental conditions, tool list.

[1329] Data processing: Generative AI model (GPT-4) was used to generate instructions based on prompts. "Please tell me in detail the procedure for the next repair. The location is a cooling pipe in Section A in the north of the factory, and the following conditions apply: temperature spike, strong vibration. The tools required are a 20mm wrench and a screwdriver."

[1330] Output: Detailed repair instructions (with text and images).

[1331] Step 7:

[1332] The user displays the generated repair procedure manual on a wearable device such as smart glasses and performs the repair work while referring to it.

[1333] Input: detailed repair instructions.

[1334] Data processing: Converting data into a display format suitable for wearable devices.

[1335] Output: Repair instructions displayed on the smart glasses.

[1336] In this way, the system can monitor temperature fluctuations and vibrations in real time and use generative AI to provide efficient repair procedures.

[1337] 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.

[1338] The present invention is a system for efficiently managing and repairing water pipes by utilizing satellite data, artificial intelligence technology (generative AI), and an emotion engine. This system divides the roles of server, terminal, and user, and each performs different processing steps to achieve optimal water pipe management. Specific embodiments are shown below.

[1339] Satellite data acquisition and analysis

[1340] The server periodically obtains ground temperature change data from a satellite data provider. This data is collected as time-series data of temperature fluctuations in a specific area and stored on the server. The server then analyzes the temperature data and calculates the stress on the water pipes. Stress points are identified using an algorithm that detects sudden changes in temperature data. For example, if a large temperature change occurs in a certain area in a short period of time, it can be determined that the water pipes in that area are under high stress.

[1341] Seismic data acquisition and analysis

[1342] The server retrieves earthquake data from reliable sources, such as seismological research institutes. This data includes information such as the magnitude, frequency, and epicenter of past earthquakes. The server analyzes this earthquake data with temperature data to prioritize water pipes that need repair. Based on earthquake vibrations and temperature changes, the server evaluates the risk of water pipes in a particular area.

[1343] Repair prioritization

[1344] The server uses temperature and earthquake data to create a priority list of water pipes that need repair, and then creates an appropriate repair plan based on this list.

[1345] Generate repair manuals

[1346] The server uses generation AI to automatically generate repair manuals. The generated repair manuals contain repair procedures, necessary tools and parts, and important points to note, all in text and with images. This allows even inexperienced or foreign workers to carry out repair work efficiently.

[1347] Efficient hydrographic charting

[1348] The terminal uses the analysis data from the server to create an efficient waterway map suitable for modern settlements, which the waterworks bureau uses when formulating long-term waterway development plans.

[1349] Emotion engine integration

[1350] The server also integrates an emotion engine to detect the user's emotions in real time while they are working on the repairs. The emotion engine evaluates the user's stress level and satisfaction through facial recognition and voice analysis. For example, if the user expresses high levels of stress, the emotion engine adjusts the instructions in the repair manual to be simpler. Also, if the user expresses high levels of satisfaction, the engine appropriately adjusts the progress of the repair work based on that feedback.

[1351] The actual repair work

[1352] Users refer to the provided repair manual to carry out the actual repair work. The manual contains detailed descriptions of specific procedures, tools, parts, and precautions to be taken, allowing the work to be carried out efficiently and safely. In addition, the emotion engine adjusts work instructions as needed based on real-time evaluations, reducing user stress and improving the quality of work.

[1353] Through the above process, the server, terminals, and users work together to create a system that effectively manages and repairs water pipes.

[1354] The processing flow will be explained below.

[1355] Processing Steps

[1356] Step 1:

[1357] The server obtains ground temperature data from a satellite data provider. Specifically, the server periodically sends an API request to receive temperature data for a specified area. The received data is recorded in a database as time-series data.

[1358] Step 2:

[1359] The server analyzes the acquired temperature data and calculates the stress on the water pipes. Specifically, it uses an analysis algorithm to identify points of sudden temperature changes and calculates the degree of stress that these points are putting on the water pipes. These stress points are then listed.

[1360] Step 3:

[1361] The server retrieves earthquake information from earthquake data providers. The earthquake data includes the magnitude, frequency, and epicenter of past earthquakes, and is also retrieved by periodically sending API requests. The earthquake data is stored in a database.

[1362] Step 4:

[1363] The server then performs an analysis by overlaying temperature data and earthquake data. Specifically, it compares stress points with earthquake data to assess the extent to which water pipes in a particular area are exposed to multiple risks. This allows it to prioritize areas that need repairs.

[1364] Step 5:

[1365] The server uses generative AI to create a repair manual for each prioritized repair area. Specifically, it references past repair data and technical literature to automatically generate text and images detailing the appropriate repair procedures, necessary tools, parts, and important points to note.

[1366] Step 6:

[1367] The device uses data provided by the server to create an efficient waterway map suitable for modern settlements. Specifically, it uses the analysis data to design the optimal layout and route of water pipes, supporting long-term development plans.

[1368] Step 7:

[1369] The server runs an emotion engine to recognize the user's emotions in real time during repair work. The emotion engine detects the user's stress level and satisfaction through facial recognition and voice analysis.

[1370] Step 8:

[1371] The server adjusts the instructions in the repair manual based on the emotion engine's evaluation results. For example, if the user's stress level is high, the instructions are simplified. Also, if the user's satisfaction level is high, the server adjusts the progress of the repair work based on that feedback.

[1372] Step 9:

[1373] The user refers to the provided repair manual and performs the actual repair work. Specifically, the user proceeds with the work while looking at the procedures and images described in the manual, and completes the work using the specified tools and parts. Based on real-time evaluation by the emotion engine, the work instructions are adjusted as needed, reducing user stress and improving work efficiency.

[1374] Through the above processing steps, a system is realized in which the server, terminals, and users work together to effectively manage and repair water pipes.

[1375] Example 2

[1376] 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."

[1377] The management and repair of existing water pipes often relies on human resources, resulting in issues with efficiency and accuracy. Furthermore, there is a lack of methods to properly assess stress caused by external factors such as temperature changes and earthquakes and identify areas that should be prioritized for repair. Furthermore, there is a lack of real-time support to reduce user stress during repair work and improve the quality of work.

[1378] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting ground temperature changes using satellite data, means for analyzing the collected temperature data to calculate stress on water pipes, means for acquiring earthquake data and multiplying it with the temperature data to prioritize water pipes that need repair, means for creating repair manuals for the identified repair locations using a generation AI, and means for monitoring the user's emotions during repair work in real time and dynamically adjusting instructions in the repair manual as necessary. This enables efficient and accurate management and repair of water pipes.

[1379] "Satellite data" is data obtained from artificial satellites to observe the Earth's surface and atmosphere.

[1380] "Temperature change data" is time series data that shows how the ground temperature in a particular area changes over time.

[1381] "Stress on water pipes" refers to the physical loads and pressures that water pipes are subjected to due to external factors such as temperature changes and earthquakes.

[1382] "Water leakage risk" is an evaluation index that indicates the degree of possibility that a water pipe will break and cause a water leak.

[1383] "Earthquake Data" means data containing information on the magnitude, frequency, and epicenters of past and present earthquakes.

[1384] "Water pipes in need of repair" are water pipes that have been identified as being in need of immediate repair due to high stress caused by temperature changes and earthquakes.

[1385] "Generative AI" is a type of artificial intelligence technology that refers to algorithms that generate natural-looking sentences and images based on specific prompts.

[1386] A "repair manual" is a document that describes the procedures required to efficiently carry out water pipe repair work, the tools and parts to be used, and points to note.

[1387] An "efficient waterway map" is a map that optimizes the layout and routing of water pipes and allows for efficient management and maintenance of water supply systems in settlements and cities.

[1388] The "Emotion Engine" is a technology that assesses a user's stress level and satisfaction in real time through facial recognition and voice analysis.

[1389] "User" refers to the worker who actually carries out the water pipe repair work.

[1390] A "server" is a computer system that collects, analyzes, and operates the generated AI.

[1391] A "terminal" is a computer device that creates and displays hydrographic charts based on analysis data from the server.

[1392] This invention is a system that efficiently manages and repairs water pipes by utilizing satellite data, artificial intelligence technology (generative AI), and an emotion engine. This system divides the roles of server, terminal, and user, and each performs different processing steps to achieve optimal water pipe management.

[1393] Satellite data acquisition and analysis

[1394] The server periodically obtains ground temperature change data from a satellite data provider. This data is collected as time-series data of temperature fluctuations in a specific area and stored on the server. The Python scikit-learn library is used to analyze the temperature data and calculate the stress on the water pipes. For example, the server obtains data in JSON format from "https: / / api.satelliteprovider.com / temperature" and converts it into a Pandas data frame. Furthermore, a Z-score is calculated to detect outliers in the data.

[1395] Seismic data acquisition and analysis

[1396] The server retrieves earthquake data from earthquake research institutes and earthquake data providers via API. This data includes information on the magnitude, frequency, and epicenter of past earthquakes. The server combines this data with temperature data and analyzes it to assess the risk to water pipes in a specific area. Specifically, the server downloads earthquake data in CSV format from "https: / / earthquake.usgs.gov / fdsnws / event / 1 / query" and merges it with the temperature data for analysis. Python's NumPy and Pandas are used for the analysis.

[1397] Repair prioritization

[1398] The server generates a list of high-risk water pipes based on temperature and earthquake data. Based on this list, it prioritizes the pipes that need repair and creates a repair plan. Specifically, the server calculates a repair necessity score based on the analysis results and sorts the list in descending order of score. The results are saved in a MySQL database.

[1399] Generate repair manuals

[1400] The server uses a generative AI (e.g., GPT-4) to automatically generate a detailed repair manual. The repair procedure, necessary tools and parts, and precautions are written in text and images. As an example of a specific prompt, "Please generate a repair procedure, including necessary tools, parts, and precautions," is input to GPT-4, and the generated text is formatted in HTML.

[1401] Efficient hydrographic charting

[1402] The terminal uses design software such as AutoCAD to create efficient hydrographic diagrams based on the analysis data received from the server. This enables long-term water pipe maintenance planning. Specifically, the terminal runs an AutoCAD script to draw the hydrographic diagram based on the coordinate data received from the server. The generated diagram is saved as a PDF file.

[1403] Emotion engine integration

[1404] The server integrates an emotion engine (e.g., Affdex API) to monitor the user's emotions in real time while they are working on repairs. It uses facial recognition and voice analysis to evaluate their stress level and satisfaction. Specifically, the server captures the user's webcam footage and microphone input, and performs emotion analysis using the Affdex API. Based on the evaluation results, the content of the repair manual is dynamically adjusted.

[1405] The actual repair work

[1406] The user performs actual repair work by referring to the provided repair manual. If the emotion engine detects the user's stress, the work instructions are adjusted in real time. Specifically, the user follows the specific steps in the repair manual and performs the repair work using specified tools (e.g., pipe wrench, plumbing tape, etc.). If the emotion engine detects stress during the work, the manual instructions may be simplified.

[1407] Through the above steps, a system is realized in which the server, terminals, and users work together to efficiently and effectively manage and repair water pipes.

[1408] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1409] Step 1:

[1410] (Satellite data acquisition)

[1411] The server connects to the satellite data provider's API to periodically obtain data on ground temperature changes in a specific area.

[1412] Input: API endpoint URL, authentication information

[1413] Specific operation: The server retrieves data in JSON format from "https: / / api.satelliteprovider.com / temperature".

[1414] Data processing: Convert the acquired JSON data into a Pandas data frame.

[1415] Output: Formatted temperature change data is obtained.

[1416] Step 2:

[1417] (Temperature data analysis)

[1418] The server analyzes the temperature change data and collects and stores the temperature fluctuations of the ground in a specific area as time-series data.

[1419] Input: Formatted temperature change data

[1420] Specific operation: The server uses Python's scikit-learn library to detect outliers using Z scores.

[1421] Data calculation: Calculate stress points and perform risk assessments for specific areas.

[1422] Output: Stress points on the water pipes are identified.

[1423] Step 3:

[1424] (Acquisition of earthquake data)

[1425] The server obtains earthquake data from earthquake research institutes and earthquake data providers via API.

[1426] Input: API endpoint URL, authentication information

[1427] Specific operation: The server downloads earthquake data in CSV format from "https: / / earthquake.usgs.gov / fdsnws / event / 1 / query".

[1428] Data processing: Convert the downloaded CSV data into a Pandas data frame.

[1429] Output: Formatted seismic data.

[1430] Step 4:

[1431] (Analysis of temperature and seismic data)

[1432] The server combines temperature and earthquake data to assess how much risk water pipes in a particular area are at.

[1433] Input: Formatted temperature data, formatted seismic data

[1434] What happens: The server merges the data using NumPy and Pandas and performs a risk assessment.

[1435] Data calculation: Based on the integrated data, calculate the priority of water pipes that need repair.

[1436] Output: Risk assessment results and a priority list are generated.

[1437] Step 5:

[1438] (Prioritizing repairs)

[1439] Based on the risk assessment results, the server generates a list of water pipes that need repair.

[1440] Input: Risk assessment results, priority list

[1441] Specific operation: The server calculates the repair necessity score and sorts the list by highest score.

[1442] Data processing: Save the list in a MySQL database.

[1443] Output: A list of repair priorities is stored in the database.

[1444] Step 6:

[1445] (Generate repair manual)

[1446] The server automatically generates repair manuals using generative AI (e.g., GPT-4 model).

[1447] Input: Repair requirements, construction details

[1448] Specific action: GPT-4 is given the prompt, "Generate repair instructions, including required tools, parts, and precautions."

[1449] Data calculation: The generated repair manual is formatted into HTML format.

[1450] Output: A detailed repair manual is generated.

[1451] Step 7:

[1452] (Efficient hydrographic charting)

[1453] The terminal creates an efficient hydrographic chart based on the analysis data received from the server.

[1454] Input: Repair priority data, coordinate data

[1455] Specific operation: The terminal draws a hydrographic chart using AutoCAD.

[1456] Data processing: Save the generated hydrographic chart in PDF format.

[1457] Output: An efficient hydrographic chart is generated in a PDF file.

[1458] Step 8:

[1459] (Emotion engine integration)

[1460] The server uses an emotion engine to monitor the user's emotions in real time during repair work.

[1461] Input: User's webcam video and audio data

[1462] Specific operation: The server uses the Affdex API to perform sentiment analysis and evaluate stress levels.

[1463] Data Calculation: Dynamically adjust repair manuals based on the user's stress level.

[1464] Output: Repair instructions tailored to the user's emotional state are provided.

[1465] Step 9:

[1466] (Actual repair work)

[1467] The user performs the actual repair work by referring to the provided repair manual.

[1468] Input: Detailed repair manual, tools used

[1469] Specific operation: The user follows the steps in the manual and performs the repair using the specified tools (e.g., pipe wrench, plumbing tape).

[1470] Data Calculation: If the emotion engine detects stress, it will automatically adjust its instructions.

[1471] Output: Repair work completed and work quality improved.

[1472] (Application example 2)

[1473] 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."

[1474] Conventional water pipe management and repair systems have difficulty efficiently identifying leak risks and prioritizing repairs. Furthermore, the quality of repair work varies depending on the experience and skills of the workers, and workers are subject to significant stress and strain. To address these issues, more accurate analysis and planning is required by utilizing satellite and earthquake data. Furthermore, a new challenge is being faced: analyzing workers' emotions in real time to improve the quality and efficiency of work.

[1475] The specific processing by the specific 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 ground temperature changes using satellite data, means for analyzing the collected temperature data to calculate stress on pipes, means for predicting the risk of water leakage based on the stress data, means for acquiring earthquake data and combining it with temperature data to prioritize pipes in need of repair, means for creating repair manuals for the identified repair locations using generative AI, emotion analysis means for evaluating user emotions in real time when performing repair work based on the manual, and means for creating efficient piping diagrams suitable for modern settlements. This not only efficiently identifies areas in need of repair and provides repair manuals, but also analyzes worker emotions and adjusts instructions, thereby improving work efficiency and quality and reducing user stress.

[1476] "Satellite data" refers to information about the Earth's surface and atmosphere collected from artificial satellites, and is particularly data that can acquire temperature changes and environmental conditions in real time.

[1477] "Temperature data" is information that records changes in the temperature of the earth's surface or an object, and represents temperature fluctuations in a specific area over time.

[1478] "Stress" refers to the physical load or pressure on pipes and equipment, and indicates the risk caused by sudden temperature changes and vibrations in particular.

[1479] "Earthquake data" refers to data that includes information such as the magnitude, epicenter, and frequency of shaking caused by earthquakes.

[1480] "Generative AI" is a type of artificial intelligence technology that has the ability to generate new data and text from given information.

[1481] A "repair manual" is an instruction manual that describes the procedures for carrying out repair work, the necessary tools, parts, and precautions.

[1482] "Emotion analysis" is a technology that assesses a user's emotional state in real time through facial recognition and voice analysis, measuring stress and satisfaction.

[1483] A "piping diagram" is a map showing the layout and connections of water pipes and other pipes, and is created for efficient pipe management and repair planning.

[1484] "User" refers to the worker who actually performs the piping repair work by referring to the provided repair manual.

[1485] The present invention is a system that efficiently manages and repairs pipes by utilizing satellite data, artificial intelligence technology (generative AI), and an emotion engine. Specific embodiments are described below.

[1486] Satellite data acquisition and analysis

[1487] First, the server periodically obtains surface temperature change data from a satellite data provider. This data represents temperature fluctuations in a specific area and is obtained in real time. The server analyzes the temperature data and calculates the stress on the pipes. To do this, an algorithm is used to detect sudden changes in temperature data. For example, if a large temperature change is observed in a certain area in a short period of time, it is determined that the pipes in that area are under high stress.

[1488] Seismic data acquisition and analysis

[1489] The server retrieves earthquake data from reliable sources, such as seismological research institutes. This data includes information on the magnitude, frequency, and epicenter of past earthquakes. The server analyzes the earthquake data together with temperature data to prioritize pipes that need repair. The seismic vibrations and temperature changes are used to assess the risk of pipes in a particular area.

[1490] Repair prioritization

[1491] Based on the analysis results, the server creates a list of pipes that need repair in order of priority, and then creates an appropriate repair plan based on this list.

[1492] Generate repair manuals

[1493] Next, the server uses the generation AI to automatically generate a repair manual. The generated repair manual contains repair procedures, necessary tools and parts, important points to note, and other information in text and images. For example, a manual can be created by inputting the following prompts into the generation AI:

[1494] "Repair the following stress points: [(20, 30), (40, 50), (70, 80)]. Generate detailed instructions including tools, components, and safety notes."

[1495] This will enable even inexperienced workers or foreign workers to carry out repair work efficiently.

[1496] Emotion engine integration

[1497] The server also integrates an emotion engine to detect the user's emotions in real time while they are performing repair work. The emotion engine uses a camera and microphone to recognize the worker's face and analyze their voice. If the work is difficult or indicates high stress, the emotion engine will simplify the instructions in the repair manual. For example, if it determines that the user is experiencing high stress, it will change complex procedures to simpler instructions.

[1498] The actual repair work

[1499] Users refer to the provided repair manual when carrying out actual repair work. Based on real-time evaluations by the emotion engine, work instructions are adjusted as needed, reducing user stress and improving the quality of work. Furthermore, efficient piping diagrams suitable for modern settlements are created and used for long-term maintenance planning.

[1500] In this way, the collaboration between servers, terminals, and users enables efficient pipe management and repair. Specific hardware and software are used for collecting and analyzing each piece of data. Specifically, Apache Spark is used for data analysis, TensorFlow and PyTorch for AI analysis, and OpenFace and Wav2Vec for sentiment analysis.

[1501] The detailed description of the embodiments clarifies the technical scope of the invention, supports the scope of patent protection, and serves as a reference for other users to understand and implement the invention.

[1502] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1503] Step 1:

[1504] The server periodically obtains data on changes in surface temperature over a specific area from a satellite data provider. The input is temperature data from the satellite data provider, and the output is time-series data showing changes in surface temperature. The server stores this data and uses it for further analysis.

[1505] Step 2:

[1506] The server analyzes the acquired temperature data and calculates the stress on the pipe. Specifically, it runs an algorithm that detects sudden changes in the temperature data. The input is ground temperature data, and the output is data indicating stress points on the pipe.

[1507] Step 3:

[1508] The server retrieves earthquake data from a reliable source such as an earthquake research institute. The input is earthquake data including the magnitude, frequency, and epicenter of past earthquakes, and the output is data evaluating the impact of earthquakes. The server uses this data for further analysis.

[1509] Step 4:

[1510] The server analyzes temperature and earthquake data and prioritizes pipes that need repair. The input is temperature and earthquake data, and the output is a list of pipes that need repair and their priorities.

[1511] Step 5:

[1512] The server uses a generative AI to create a repair manual for the identified repair area. Specifically, it inputs the following prompt sentence into the generative AI model:

[1513] "Repair the following stress points: [(20, 30), (40, 50), (70, 80)]. Generate detailed instructions including tools, components, and safety notes."

[1514] The input is a list of repairs (stress points), and the output is a detailed repair manual, including text and images, describing the tools and parts required, and important points to note.

[1515] Step 6:

[1516] The user refers to the repair manual and performs the repair work. The input is the repair manual provided by the server, and the output is the progress of the actual repair work. The user follows the manual and performs the repair work efficiently.

[1517] Step 7:

[1518] During the repair work, the server uses an emotion engine to analyze the user's emotions in real time. Specifically, it uses a camera and microphone to recognize the user's face and analyze their voice. The input is real-time facial images and voice data obtained from the camera and microphone, and the output is data indicating the user's emotional state.

[1519] Step 8:

[1520] The server adjusts the instructions in the repair manual based on the user's emotional data. For example, if the user is feeling high stress, it simplifies complex procedures. The input is the user's emotional state, and the output is the adjusted repair manual.

[1521] Step 9:

[1522] The server compiles the final repair results and creates an efficient piping diagram suitable for modern settlements. The input is the repair work results data, and the output is a new piping diagram. This piping diagram is used for long-term maintenance planning.

[1523] 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.

[1524] 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.

[1525] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1526] 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.

[1527] FIG. 9 illustrates 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 behaviors 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.

[1528] 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.

[1529] 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).

[1530] 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.

[1531] 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."

[1532] 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.

[1533] 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).

[1534] 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.

[1535] 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.

[1536] 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.

[1537] 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.

[1538] 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.

[1539] 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.

[1540] 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.

[1541] 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.

[1542] 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.

[1543] 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.

[1544] The following is further disclosed regarding the above embodiment.

[1545] (Claim 1)

[1546] means for collecting ground temperature changes using satellite data;

[1547] a means for analyzing the collected temperature data to calculate stress on the water pipes;

[1548] A method for predicting the risk of water leakage based on stress data;

[1549] A method to acquire earthquake data and combine it with temperature data to prioritize the water pipes that need repair.

[1550] A means for creating a repair manual for the identified repair location using generative AI;

[1551] A means of producing efficient hydrographic maps suitable for modern settlements;

[1552] A system including:

[1553] (Claim 2)

[1554] 2. The system of claim 1, wherein the repair manual includes text and images, enabling outsourced workers to work efficiently.

[1555] (Claim 3)

[1556] 10. The system of claim 1, wherein the system periodically obtains data from satellite data providers and seismological research institutes.

[1557] "Example 1"

[1558] (Claim 1)

[1559] means for collecting ground temperature changes using satellite data;

[1560] a means for preprocessing the collected temperature data and calculating stress on the water pipes;

[1561] means for identifying stress points using an algorithm that detects rapid temperature changes;

[1562] A means of acquiring seismic data and integrating it with temperature data to assess the risk to water pipes;

[1563] a means for calculating the priority of water pipes requiring repair based on temperature data and earthquake data;

[1564] A means for generating prompt sentences using a generative AI model for each identified repair location and creating a repair manual;

[1565] A means of producing efficient hydrographic charts based on survey data;

[1566] A system including:

[1567] (Claim 2)

[1568] 10. The system of claim 1, wherein the repair manual includes text and images to enable workers to work efficiently.

[1569] (Claim 3)

[1570] 10. The system of claim 1, wherein the system periodically acquires data from satellite data providers and laboratories, preprocesses the data, and analyzes it.

[1571] "Application Example 1"

[1572] (Claim 1)

[1573] means for collecting ground temperature changes using satellite data;

[1574] a means for analyzing the collected temperature data to calculate stress on the water pipes;

[1575] A method for predicting the risk of water leakage based on stress data;

[1576] A method to acquire earthquake data and combine it with temperature data to prioritize the water pipes that need repair.

[1577] A means for creating a repair manual for the identified repair location using generative AI;

[1578] A means of producing efficient hydrographic charts suitable for modern regions;

[1579] A means of collecting and analyzing sensor data (pipe temperature and vibration) in real time,

[1580] A means for displaying repair procedures automatically generated using the generation AI on a wearable device;

[1581] A system including:

[1582] (Claim 2)

[1583] 2. The system of claim 1, wherein the repair manual includes text and images, enabling outsourced workers to work efficiently.

[1584] (Claim 3)

[1585] 10. The system of claim 1, wherein the system periodically obtains data from satellite data providers and seismological research institutes.

[1586] "Example 2: Combining Emotion Engines"

[1587] (Claim 1)

[1588] means for collecting ground temperature changes using satellite data;

[1589] a means for analyzing the collected temperature data to calculate stress on the water pipes;

[1590] A method for predicting the risk of water leakage based on stress data;

[1591] A method to acquire earthquake data and combine it with temperature data to prioritize the water pipes that need repair.

[1592] A means for creating a repair manual for the identified repair location using generative AI;

[1593] A means of producing efficient hydrographic maps suitable for modern settlements;

[1594] a means for monitoring the user's emotions during the repair work in real time and dynamically adjusting the instructions in the repair manual as needed;

[1595] A system including:

[1596] (Claim 2)

[1597] 10. The system of claim 1, wherein the repair manual includes text and images to enable workers to work efficiently.

[1598] (Claim 3)

[1599] 10. The system of claim 1, wherein the system periodically obtains data from data providers and laboratories.

[1600] "Application example 2 when combining emotion engines"

[1601] (Claim 1)

[1602] means for collecting ground temperature changes using satellite data;

[1603] a means for analyzing the collected temperature data to calculate stress on the piping;

[1604] A method for predicting the risk of water leakage based on stress data;

[1605] A method for acquiring earthquake data and combining it with temperature data to prioritize the identification of pipes that need repair, and

[1606] A means for creating a repair manual for the identified repair location using generative AI;

[1607] an emotion analysis means for evaluating the emotion of a user in real time when the user is performing repair work based on the manual;

[1608] A means of creating efficient plumbing diagrams suitable for modern settlements;

[1609] A system including:

[1610] (Claim 2)

[1611] 2. The system of claim 1, wherein the system reduces user stress by adjusting instructions in the repair manual based on emotion analysis.

[1612] (Claim 3)

[1613] 10. The system of claim 1, wherein the system periodically obtains data from satellite data providers and seismological research institutes. [Explanation of symbols]

[1614] 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. means for collecting ground temperature changes using satellite data; a means for analyzing the collected temperature data to calculate stress on the water pipes; A method for predicting the risk of water leakage based on stress data; A method to acquire earthquake data and combine it with temperature data to prioritize the water pipes that need repair. A means for creating a repair manual for the identified repair location using generative AI; A means of producing efficient hydrographic maps suitable for modern settlements; A system including:

2. 2. The system according to claim 1, wherein the repair manual includes text and images, enabling outsourced workers to work efficiently.

3. 10. The system of claim 1, wherein the system periodically obtains data from satellite data providers and seismological research institutes.

Images