system

Abstract

Provide a system. [Solution] a terminal means using sensors to collect infrastructure condition data; a server means for storing the collected data in a database and performing preprocessing; server means for applying a machine learning model to predict the lifespan of the infrastructure using the preprocessed data; a server means for evaluating safety based on predicted lifespan data and for conducting risk assessment taking disaster scenarios into consideration; a server means for optimizing a repair plan based on the risk assessment result; a server means for generating a repair plan as a report and notifying the user of the report; A system including:

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] Please write "Problem to be solved" and "Means to solve the problem" in the following format.

[0005] Conventional infrastructure management systems have difficulty effectively detecting deterioration due to aging and formulating appropriate repair plans. Furthermore, risk assessments of natural disasters such as earthquakes and typhoons are insufficient, resulting in the failure to implement optimal disaster prevention measures to protect human lives and infrastructure. The present invention aims to solve these problems. [Means for solving the problem]

[0006] The present invention solves the above problems by providing a terminal unit that uses sensors to collect infrastructure status data, a server unit that stores the collected data in a database and performs preprocessing, a server unit that applies a machine learning model to predict the infrastructure's lifespan using the preprocessed data, a server unit that evaluates safety based on the predicted lifespan data and performs risk assessment taking disaster scenarios into account, a server unit that optimizes repair plans based on the risk assessment results, and a server unit that generates a repair plan as a report and notifies the user. This makes it possible to efficiently manage infrastructure deterioration, evaluate risks in the event of a natural disaster, and formulate an optimal repair plan.

[0007] "Infrastructure" is a general term for the physical facilities that make up social infrastructure, such as roads, bridges, sewers, and public facilities.

[0008] A "sensor" is a device that detects a physical or chemical condition and outputs that data as an electrical signal.

[0009] "Terminal means" refers to a device or system for collecting infrastructure status data through sensors and transmitting it to a server.

[0010] "Server Means" refers to a centralized computer system for processing and analyzing data, and storing and disseminating results.

[0011] "Database" refers to an electronic recording medium and its management system for organizing and storing collected data and for efficiently searching and using it.

[0012] "Preprocessing" refers to performing initial processing such as deleting duplicate data and filling in missing data in order to improve the reliability of collected data.

[0013] A "machine learning model" refers to an algorithm that uses past data to learn patterns and rules and make predictions about new data.

[0014] "Lifespan prediction" refers to the process of using machine learning models to predict the remaining lifespan of infrastructure.

[0015] "Safety assessment" refers to the process of evaluating the current state based on predicted data and determining risks.

[0016] A "disaster scenario" refers to a model that sets up natural disasters such as earthquakes and typhoons and simulates their impact.

[0017] "Risk assessment" refers to the process of assessing the degree of risk to which infrastructure is exposed based on disaster scenarios.

[0018] "Optimizing repair plans" refers to setting repair priorities based on the results of risk assessments and formulating plans to efficiently allocate limited budgets and resources.

[0019] "Report" refers to a report that documents the evaluation results and repair plans and provides them to users.

[0020] "User" means the person or organization responsible for managing the infrastructure. [Brief explanation of the drawings]

[0021] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4]FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0022] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0024] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0025] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0026] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0027] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0028] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0029] [First embodiment]

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

[0031] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0032] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0033] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0034] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0035] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0036] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0038] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0039] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0040] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0041] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0042] ---

[0043] The infrastructure management system of the present invention is for monitoring the status of various infrastructures, predicting their lifespan and assessing their safety, and formulating optimal repair plans. The system includes the following components:

[0044] 1. Terminal means using sensors to collect infrastructure status data

[0045] 2. Server means to store collected data in a database and perform preprocessing

[0046] 3. A server means for applying machine learning models to predict the lifespan of the infrastructure using pre-processed data.

[0047] 4. Server means for evaluating safety based on predicted lifespan data and conducting risk assessments taking disaster scenarios into account.

[0048] 5. Server method for optimizing repair plans based on risk assessment results

[0049] 6. Server means for generating a repair plan as a report and notifying the user

[0050] As a specific embodiment, the operation of each part of the system will be described.

[0051] Data collection

[0052] The devices use sensors to collect infrastructure condition data, including crack severity, corrosion progress, deformation measurements, etc. For example, sensors on a bridge measure crack width and depth every day and send that data to a server.

[0053] Data accumulation and preprocessing

[0054] The server stores the data sent from the device in a database. It adds a timestamp to the data to clarify which part of the infrastructure the data came from. Next, it performs preprocessing on the data. This includes removing duplicate data and imputing missing data from nearby data or by averaging.

[0055] Application of life prediction model

[0056] The server then inputs the preprocessed data into a machine learning model, which uses historical infrastructure data as training data and predicts the remaining lifespan of the infrastructure from current data. For example, data from road sensors can be used to calculate the remaining lifespan of a road.

[0057] Safety evaluation

[0058] The server evaluates the safety of infrastructure based on predicted lifespan data. The evaluation includes simulations that take into account disaster scenarios such as earthquakes and typhoons. As a result of the safety evaluation, each piece of infrastructure is classified as "low risk," "medium risk," or "high risk."

[0059] optimization

[0060] The server optimizes the repair plan based on the risk assessment results. This optimization uses a mathematical optimization algorithm to set priorities while taking into account budget and resource constraints. For example, when creating a repair plan for multiple bridges in City A, the repairs with the highest urgency are given priority.

[0061] Reports and Notifications

[0062] The server creates a report based on the assessment results and optimized repair plans. The report includes the current status, predicted lifespan, safety assessment, and repair priorities and schedules for each piece of infrastructure. The server generates this report in PDF format and emails it to the user, who can review it and take appropriate measures.

[0063] As a concrete example, sensors on Bridge B in City A collect crack data and send it to a server every day. The server stores the data, performs preprocessing, and then uses a machine learning model to calculate the predicted remaining lifespan of Bridge B. Next, the server evaluates Bridge B's safety by considering disaster scenarios and classifies it as "medium risk." Finally, the server prioritizes Bridge B's repairs compared to other infrastructure and includes it in the next year's repair plan. This repair plan is generated as a report and notified to the city's infrastructure management department.

[0064] In this way, the system efficiently manages infrastructure deterioration, assesses natural disaster risks, and develops optimal repair plans.

[0065] The processing flow will be explained below.

[0066] ---

[0067] Step 1:

[0068] The devices collect infrastructure condition data. Specifically, sensors measure crack width and depth, corrosion progress, deformation measurements, etc. For example, sensors installed on bridges are set to collect data daily.

[0069] Step 2:

[0070] The data collected by the device is sent to a server in real time, and the sent data includes not only the measured physical quantities but also metadata to identify which part of the infrastructure the data was obtained from.

[0071] Step 3:

[0072] The server stores the received data in a database. At this time, it performs preprocessing such as detecting and deleting duplicate data and detecting and filling in missing data. For example, if there are missing measurement data, they are filled in with data from adjacent timestamps or the average value.

[0073] Step 4:

[0074] The server inputs the preprocessed data into a machine learning model to predict the lifespan of the infrastructure. The machine learning model has been trained with training data in advance, and calculates the remaining lifespan based on newly input data. For example, if crack data on a bridge is input, the predicted remaining lifespan of the bridge is calculated.

[0075] Step 5:

[0076] The server evaluates the safety of infrastructure based on predicted lifespan data. The evaluation process involves simulations that take into account disaster scenarios such as earthquakes and typhoons. For example, the simulation evaluates the degree of damage a bridge would sustain in an earthquake.

[0077] Step 6:

[0078] Based on the safety assessment results, the server classifies the risk level (low risk, medium risk, high risk) for each piece of infrastructure. This classification is used to determine the priority of repair plans.

[0079] Step 7:

[0080] The server optimizes the repair plan based on the risk assessment results. It applies mathematical optimization algorithms to prioritize repairs, taking into account budget and resource constraints. For example, the highest-risk bridges are given top priority.

[0081] Step 8:

[0082] The server generates a repair plan as a report and notifies the user. The report includes the current status, predicted lifespan, safety assessment, repair priority and schedule for each infrastructure. The server generates the report in PDF format and sends it to the user by email.

[0083] Step 9:

[0084] Users review the reports and take appropriate measures. Based on the reports, they schedule repair work and allocate budgets. For example, they finalize bridge and road repair plans in line with next year's budget plan.

[0085] Through the above steps, the infrastructure management system of the present invention can realize effective condition monitoring, lifespan prediction, safety assessment, and formulation of optimal repair plans.

[0086] Example 1

[0087] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0088] In managing infrastructure deterioration, it is important to measure deterioration and improve prediction accuracy, to make safety assessments objective, and to develop optimal repair plans. However, current systems lack sufficient data collection and proper data preprocessing, which reduces the accuracy of prediction models and risk assessments. Furthermore, repair plans are inefficient and prone to resource waste.

[0089] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0090] In this invention, the server includes a terminal means using sensors to collect infrastructure status data, a preprocessing means for storing the collected data in a database and deleting duplicate data and completing missing data, a means for applying a machine learning model to predict the infrastructure's lifespan using the preprocessed data, a means for evaluating safety based on the predicted lifespan data and performing a risk assessment taking disaster scenarios into account, an algorithm means for optimizing a repair plan based on the risk assessment results, and a means for generating a repair plan as a report and notifying the user. This enables precise and efficient monitoring of the infrastructure's deterioration status and the formulation of appropriate measures and repair plans to improve safety.

[0091] "Infrastructure" refers to structures and facilities installed to support public safety and daily life benefits, including bridges, roads, tunnels, and water facilities.

[0092] A "sensor" is a device that measures a physical variable and outputs it in the form of an electrical signal or other data. This data is used to monitor the condition of infrastructure.

[0093] The term "terminal means" refers to a device or system for receiving data collected from a sensor and transmitting the data to a server. Specific examples include a data collection device and a communication module.

[0094] "Preprocessing measures" refer to the rudimentary processing performed on collected data, such as removing duplicate data and filling in missing data.

[0095] A "machine learning model" refers to an algorithm that learns patterns from data and uses them to predict or classify future data. Examples include neural networks and support vector machines.

[0096] "Algorithmic means" refers to procedures or computational methods for solving specific problems, especially mathematical methods used to optimize repair plans.

[0097] "Risk assessment" refers to the process of evaluating potential hazards based on infrastructure life data and disaster scenarios.

[0098] "Report" refers to a documented summary of the system's evaluation results and plans, which are communicated to users and used for decision-making.

[0099] The infrastructure management system of the present invention monitors the status of various infrastructures, predicts their lifespan and safety, and formulates optimal repair plans. The system includes the following components:

[0100] 1. Terminal means using sensors to collect infrastructure status data

[0101] 2. Preprocessing means for storing collected data in a database, deleting duplicate data, and filling in missing data.

[0102] 3. A means to apply machine learning models to predict infrastructure lifespan using pre-processed data

[0103] 4. A means of assessing safety based on predicted lifespan data and conducting risk assessments taking disaster scenarios into account.

[0104] 5. Algorithmic means to optimize repair plans based on risk assessment results

[0105] 6. A means of generating a repair plan as a report and notifying the user

[0106] Data collection

[0107] The devices collect infrastructure condition data using sensors. Examples of sensors include sensors that measure cracks, sensors that monitor corrosion, sensors that detect deformation, etc. For example, sensors installed on a bridge measure the width and depth of cracks every day and send the data to a server.

[0108] Data accumulation and preprocessing

[0109] The server receives the data sent from the devices and stores it in a database (e.g., MySQL (registered trademark), PostgreSQL). The data is stored with a timestamp and also includes metadata to clarify which part of the infrastructure it was obtained from. Preprocessing includes removing duplicate data and filling in missing data (e.g., filling in data from neighboring data, filling in the average value).

[0110] Application of life prediction model

[0111] The server inputs the preprocessed data into a machine learning model (e.g., TENSORFLOW®, scikit-learn). The machine learning model uses historical infrastructure data as training data and predicts the remaining lifespan of the infrastructure from current data. For example, data obtained from road sensors can be used to calculate the remaining lifespan of the road.

[0112] Safety evaluation

[0113] The server evaluates the safety of infrastructure based on predicted lifespan data. This evaluation includes simulations (e.g., FEA software) that take into account disaster scenarios such as earthquakes and typhoons. As a result of the safety evaluation, each piece of infrastructure is classified as "low risk," "medium risk," or "high risk."

[0114] Optimizing repair plans

[0115] The server optimizes repair plans based on the risk assessment results. It uses mathematical optimization algorithms (e.g., linear programming and genetic algorithms) to consider budget and resource constraints. For example, when creating repair plans for multiple bridges, the most urgent repairs are prioritized.

[0116] Report generation and notification

[0117] The server creates a report based on the assessment results and optimized repair plans. The report includes the current status, predicted lifespan, safety assessment, and repair priorities and schedules for each piece of infrastructure. The server generates this report in PDF format and emails it to the user, who can review it and take appropriate measures.

[0118] Specific examples

[0119] As a concrete example, sensors on Bridge B in City A collect crack data and send it to a server every day. The server stores the data, performs preprocessing, and then uses a machine learning model to calculate the predicted remaining lifespan of Bridge B. Next, the server evaluates Bridge B's safety by considering disaster scenarios and classifies it as "medium risk." Finally, the server prioritizes Bridge B's repairs compared to other infrastructure and includes it in the next year's repair plan. This repair plan is generated as a report and notified to the city's infrastructure management department.

[0120] Prompt Sentence Examples

[0121] Below are some examples of specific prompts that can be fed into a generative AI model:

[0122] Based on the crack data collected over the past year by sensors installed on Bridge B in City A, calculate the predicted remaining lifespan of Bridge B and evaluate its safety. Also, based on the evaluation results, optimize the repair plan for the next year and generate a report.

[0123] In this way, the system efficiently monitors the condition of infrastructure, assesses the risk of natural disasters, and develops optimal repair plans.

[0124] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0125] Step 1: Data collection

[0126] The devices use sensors to collect infrastructure condition data, with input data including crack width, depth, corrosion progress, and deformation measurements.

[0127] How it works: Sensors installed on the bridge measure crack width and depth every hour and send the condition data to a server in real time. The output is collected infrastructure condition data.

[0128] Step 2: Data accumulation and preprocessing

[0129] The server receives data sent from the terminal and stores it in a database (e.g., MySQL, PostgreSQL). The input is the raw data sent from the terminal.

[0130] What it does: The server adds a timestamp to the data it receives, along with metadata indicating which part of the infrastructure the data came from. It then removes duplicates and imputes missing data with neighboring data or averages. The output is preprocessed, clean data.

[0131] Step 3: Applying the life prediction model

[0132] The server inputs the preprocessed data into a machine learning model (e.g., TensorFlow, scikit-learn), where the input data is the preprocessed infrastructure state data.

[0133] How it works: The server inputs the preprocessed data into a machine learning model, which uses past learning results to predict the remaining lifespan of infrastructure. For example, data on a bridge is used to calculate the bridge's predicted remaining lifespan. The output is the predicted remaining lifespan data.

[0134] Step 4: Safety assessment

[0135] The server evaluates the safety of the infrastructure based on the predicted remaining life data. The input data is the predicted remaining life data.

[0136] Specific operation: Simulations are performed taking into account disaster scenarios (e.g., earthquakes, typhoons) and safety assessments are carried out. As a result, each piece of infrastructure is classified as "low risk," "medium risk," or "high risk." The output is the risk assessment result.

[0137] Step 5: Optimize repair plans

[0138] The server optimizes the repair plan based on the risk assessment results. The input data is the risk assessment results.

[0139] How it works: Using mathematical optimization algorithms (e.g., linear programming, genetic algorithms), it generates repair plans taking into account budget and resource constraints. For example, when planning repairs for multiple bridges, it prioritizes the repairs with the highest urgency. The output is an optimized repair plan.

[0140] Step 6: Generate reports and notifications

[0141] The server generates a report based on the evaluation results and the optimized repair plan. The input data is the optimized repair plan.

[0142] Specific behavior: Generates a report in PDF format containing the current status, predicted lifespan, safety assessment, and repair priorities and schedules for each piece of infrastructure. The server then emails this report to the user (e.g., the city's infrastructure management department). The user can review the report and take appropriate measures. The output is the generated report and a notification email.

[0143] In this way, the system processes and calculates data at each step, and then executes a series of processes until finally notifying the user.

[0144] (Application example 1)

[0145] 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."

[0146] Conventional infrastructure management systems generally collect data using fixed sensors, making it difficult to collect and analyze data in real time from mobile devices. It is also difficult to efficiently monitor the deterioration of road infrastructure and formulate timely repair plans. This has led to problems such as the progression of infrastructure deterioration and an increased risk of accidents and disasters.

[0147] 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.

[0148] In this invention, the server includes terminal means using sensors to collect infrastructure status data, server means for storing the collected data in a database and preprocessing it, server means for applying a machine learning model to predict the infrastructure's lifespan using the preprocessed data, means for evaluating safety based on the predicted lifespan data and conducting risk assessments taking disaster scenarios into account, means for collecting road status data using sensors mounted on vehicles, means for applying a machine learning model to predict the road's lifespan using the collected data, means for evaluating road safety based on the predicted lifespan data and conducting risk assessments taking disaster scenarios into account, means for optimizing road repair plans based on the risk assessment results, and means for generating a repair plan as a report and notifying the vehicle manager. This enables real-time data collection and analysis by vehicles, which are mobile objects, and enables efficient monitoring of the deterioration state of road infrastructure and effective formulation of repair plans at appropriate times.

[0149] "Infrastructure" refers to the physical structures of social infrastructure such as roads, bridges, tunnels, and dams.

[0150] "Condition data" refers to data that describes the physical condition of infrastructure, and includes, for example, information such as the degree of cracking, the progress of corrosion, and deformation measurements.

[0151] "Sensor" refers to a device used to detect and collect infrastructure condition data, including cameras, LIDAR sensors, vibration sensors, etc.

[0152] "Terminal means" refers to a device that uses sensors to collect infrastructure status data and transmits it to a server.

[0153] "Database" refers to a system for efficiently storing and managing collected data.

[0154] "Preprocessing" is the process of preparing data stored in a database so that it can be analyzed, and includes removing duplicate data and filling in missing data.

[0155] "Server Means" refers to a central processing unit for collecting, storing, pre-processing and analyzing data.

[0156] "Machine learning models" refer to algorithms and methods for predicting future deterioration and lifespan of infrastructure based on past data.

[0157] "Lifespan forecasting" refers to the process for predicting the remaining lifespan of infrastructure.

[0158] "Disaster scenarios" refer to hypothetical scenarios used to assess the impact of natural disasters such as earthquakes and typhoons on infrastructure.

[0159] "Risk assessment" refers to the process of assessing the safety and potential risks of infrastructure based on predicted data.

[0160] "Vehicle-mounted sensors" refers to sensors attached to a vehicle to collect roadway condition data.

[0161] "Repair Plan" means a plan containing a schedule of repairs and maintenance required to prevent deterioration of infrastructure.

[0162] "Report" refers to a written summary of the repair plan and the results of the risk assessment.

[0163] "Administrator" means the person or organization responsible for maintaining the infrastructure.

[0164] An embodiment of this invention is a system for collecting condition data on road infrastructure using sensors installed in automobiles, predicting the lifespan of the infrastructure based on that data, and formulating appropriate repair plans.

[0165] Data collection

[0166] The terminal uses the vehicle's onboard camera and LIDAR sensor to collect real-time data on road cracks, holes, deformations, etc. This allows moving vehicles to efficiently collect large-scale road condition data. For example, the LIDAR sensor scans the road surface for irregularities and detects abnormalities.

[0167] Data accumulation and preprocessing

[0168] The server sends the collected data to a cloud server and stores it in a database. The stored data is time-stamped to identify which road section the data comes from. Pre-processing is then performed, including removing duplicate data and filling in missing data. This pre-processing improves the consistency and accuracy of the data.

[0169] Application of life prediction model

[0170] The server applies a machine learning model to the preprocessed data to predict the remaining lifespan of road infrastructure. This machine learning model learns from past road condition data as training data to improve prediction accuracy. Specifically, the model is built using machine learning libraries such as TensorFlow.

[0171] Safety evaluation

[0172] The server performs safety assessments based on predicted lifespan data, taking into account disaster scenarios such as earthquakes and typhoons. This allows the risk level of each road section to be understood and high-risk sections to be identified. For example, disaster scenarios are simulated using MATLAB (registered trademark).

[0173] optimization

[0174] The server then optimizes the road repair plan based on the risk assessment results. This optimization uses a mathematical optimization algorithm to set priorities while taking into account budget and resource constraints. For example, the road sections with the highest urgency are prioritized in the repair plan.

[0175] Reports and Notifications

[0176] The server generates a repair plan as a report and notifies the vehicle manager, which includes the current road condition, predicted lifespan, safety assessment, repair priority and schedule, so that the manager can take appropriate measures.

[0177] Examples of concrete examples and prompts

[0178] For example, while an autonomous vehicle is driving on a highway, its LIDAR sensor will detect cracks in the road and send them to a cloud server in real time. The server will then use the data to optimize highway repair plans and notify the highway manager.

[0179] Example prompt sentence:

[0180] "Identify highway repair needs most with road crack condition data. Evaluate safety and optimize repair plans by considering projected remaining life and disaster scenarios."

[0181] In this way, the present invention enables real-time data collection and analysis from moving vehicles, thereby enabling efficient monitoring of road infrastructure and the formulation of repair plans.

[0182] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0183] Step 1: Data collection

[0184] The device collects road condition data in real time using the car's on-board camera and LIDAR sensor. Specifically, the LIDAR sensor scans the road surface for irregularities and acquires the data. The input is raw data from the sensor, and the output is processed road condition data.

[0185] Step 2: Send data

[0186] The device sends the collected data to the cloud server. The data is time-stamped to identify the location from which it was collected. The input is the status data obtained in the data collection step, and the output is the transmitted data.

[0187] Step 3: Data accumulation and preprocessing

[0188] The server stores the data sent to the cloud in a database. The stored data undergoes preprocessing, such as deleting duplicate data and filling in missing data. Preprocessing improves the consistency and accuracy of the data. The input is the raw data sent, and the output is the preprocessed, clear data.

[0189] Step 4: Applying the life prediction model

[0190] The server applies a machine learning model to the preprocessed data to predict the remaining lifespan of the road. Specifically, it builds a model using a machine learning library such as TensorFlow and inputs data into the model to make predictions. The input is the preprocessed data, and the output is the predicted remaining lifespan data.

[0191] Step 5: Safety Assessment

[0192] The server performs safety assessments based on predicted lifespan data, taking disaster scenarios into account. For example, it uses MATLAB to simulate disaster scenarios such as earthquakes and typhoons and evaluate their impact. The input is lifespan prediction data, and the output is the risk assessment results.

[0193] Step 6: Optimize repair plans

[0194] The server optimizes the repair plan based on the safety assessment results. For optimization, it takes into account resource constraints and uses a mathematical optimization algorithm. For example, it prioritizes the inclusion of high-priority areas in the repair plan. The input is the risk assessment results, and the output is the optimized repair plan.

[0195] Step 7: Reporting and Notifications

[0196] The server generates a report based on the optimized repair plan and notifies the administrator. The report includes the current state, predicted lifespan, safety assessment, repair priority and schedule. The input is the optimized repair plan, and the output is the documented information in the report.

[0197] 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.

[0198] ---

[0199] The infrastructure management system of the present invention monitors the status of various infrastructures, predicts their lifespan, assesses their safety, and formulates optimal repair plans, and further includes an emotion engine that recognizes the emotions of users. The system includes the following components:

[0200] 1. Terminal means using sensors to collect infrastructure status data

[0201] 2. Server means to store collected data in a database and perform preprocessing

[0202] 3. A server means for applying machine learning models to predict the lifespan of the infrastructure using pre-processed data.

[0203] 4. Server means for evaluating safety based on predicted lifespan data and conducting risk assessments taking disaster scenarios into account.

[0204] 5. Server method for optimizing repair plans based on risk assessment results

[0205] 6. Server means for generating a repair plan as a report and notifying the user

[0206] 7. Emotion engine that recognizes user emotions and adjusts notification content

[0207] As a specific embodiment, the operation of each part of the system will be described.

[0208] Data collection

[0209] The devices use sensors to collect infrastructure condition data, including the degree of cracking, corrosion progress, deformation measurements, etc. For example, sensors installed on a bridge collect data daily and send it to a server.

[0210] Data accumulation and preprocessing

[0211] The server stores the data sent from the device in a database. It adds a timestamp to the data to clarify which part of the infrastructure the data came from. Next, it performs preprocessing on the data. This includes removing duplicate data and imputing missing data from nearby data or by averaging.

[0212] Application of life prediction model

[0213] The server then inputs the preprocessed data into a machine learning model to predict the infrastructure's lifespan. The machine learning model has been trained with training data in advance and calculates the remaining lifespan based on newly input data. For example, data obtained from road sensors can be used to calculate the remaining lifespan of a road.

[0214] Safety evaluation

[0215] The server evaluates the safety of infrastructure based on predicted lifespan data. The evaluation includes simulations that take into account disaster scenarios such as earthquakes and typhoons. As a result of the safety evaluation, each piece of infrastructure is classified as "low risk," "medium risk," or "high risk."

[0216] optimization

[0217] The server then optimizes the repair plan based on the risk assessment results. It uses a mathematical optimization algorithm to set priorities, taking into account budget and resource constraints. For example, the bridges with the highest risk receive the highest priority.

[0218] Reports and Notifications

[0219] The server creates a report based on the assessment results and the optimized repair plan. The report includes the current status, predicted lifespan, safety assessment, repair priority and schedule for each infrastructure. The server generates this report in PDF format and sends it to the user by email.

[0220] Emotional Engine Adjustment

[0221] The emotion engine installed on the server recognizes the user's emotions. Emotion recognition utilizes the user's operation history and voice input. For example, if the user is feeling stressed, the emotion engine will simplify the content of the notification. In high-stress situations, detailed technical information will be kept to a minimum, and only important information will be conveyed quickly. If the user is in a calm state, the notification will include detailed technical information.

[0222] As a concrete example, sensors collect crack data on Bridge B in City A and send it to a server every day. The server stores the data, performs preprocessing, and then uses a machine learning model to calculate the predicted remaining lifespan of Bridge B. Next, it evaluates the safety of Bridge B by taking disaster scenarios into account and classifies it as "medium risk." Finally, the server prioritizes the repair of Bridge B compared to other infrastructure and includes it in the repair plan for the following year. This repair plan is generated as a report and notified to the city's infrastructure management department. If a management department employee is feeling stressed, the emotion engine can simplify the notification content and present it in an easy-to-understand format.

[0223] In this way, this system not only efficiently manages infrastructure deterioration, assesses natural disaster risks, and develops optimal repair plans, but also improves work efficiency and comprehension by adjusting notification content according to the user's emotional state.

[0224] The processing flow will be explained below.

[0225] ---

[0226] Step 1:

[0227] The devices collect infrastructure condition data. Specifically, sensors measure crack width and depth, corrosion progress, deformation measurements, etc. For example, sensors installed on bridges are set to collect data daily.

[0228] Step 2:

[0229] The data collected by the device is sent to a server in real time, and the sent data includes not only the measured physical quantities but also metadata to identify which part of the infrastructure the data was obtained from.

[0230] Step 3:

[0231] The server stores the received data in a database. At this time, it performs preprocessing such as detecting and deleting duplicate data and detecting and filling in missing data. For example, if there are missing measurement data, they are filled in with data from adjacent timestamps or the average value.

[0232] Step 4:

[0233] The server inputs the preprocessed data into a machine learning model to predict the infrastructure's lifespan. The machine learning model is trained on the training data in advance and calculates the remaining lifespan based on the newly input data. For example, data obtained from road sensors can be used to calculate the remaining lifespan of a road.

[0234] Step 5:

[0235] The server evaluates the safety of infrastructure based on predicted lifespan data. The evaluation process involves simulations that take into account disaster scenarios such as earthquakes and typhoons. For example, the simulation evaluates the degree of damage a bridge would sustain in an earthquake.

[0236] Step 6:

[0237] Based on the safety assessment results, the server classifies the risk level (low risk, medium risk, high risk) for each piece of infrastructure. This classification is used to determine the priority of repair plans.

[0238] Step 7:

[0239] The server optimizes the repair plan based on the risk assessment results. It applies mathematical optimization algorithms to prioritize repairs, taking into account budget and resource constraints. For example, the highest-risk bridges are given top priority.

[0240] Step 8:

[0241] The server generates a repair plan as a report and notifies the user. The report includes the current status, predicted lifespan, safety assessment, repair priority and schedule for each infrastructure. The server generates the report in PDF format and sends it to the user by email.

[0242] Step 9:

[0243] Users review the reports and take appropriate measures. Based on the reports, they schedule repair work and allocate budgets. For example, they finalize bridge and road repair plans in line with next year's budget plan.

[0244] Step 10:

[0245] The emotion engine recognizes the user's emotions. Emotion recognition utilizes the user's operation history and voice input. For example, if the user is feeling stressed, the emotion engine will simplify the notification content.

[0246] Step 11:

[0247] The server adjusts the notification content based on the results of the emotion engine. In stressful situations, the server reduces the amount of detailed technical information and quickly conveys only the important information. On the other hand, when the user is calm, the server provides notifications that include detailed technical information.

[0248] As a concrete example, sensors collect crack data on Bridge B in City A and send it to a server every day. The server stores the data, performs preprocessing, and then uses a machine learning model to calculate the predicted remaining lifespan of Bridge B. Next, it evaluates the safety of Bridge B by taking disaster scenarios into account and classifies it as "medium risk." Finally, the server prioritizes the repair of Bridge B compared to other infrastructure and includes it in the repair plan for the following year. This repair plan is generated as a report and notified to the city's infrastructure management department. If a management department employee is feeling stressed, the emotion engine can simplify the notification content and present it in an easy-to-understand format.

[0249] In this way, this system not only efficiently manages infrastructure deterioration, assesses natural disaster risks, and develops optimal repair plans, but also improves work efficiency and comprehension by adjusting notification content according to the user's emotional state.

[0250] Example 2

[0251] 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."

[0252] While conventional infrastructure management systems can efficiently monitor infrastructure conditions and perform lifespan predictions and risk assessments, they lack the means to reduce the psychological burden on users. As a result, users tend to feel stressed, which can slow their understanding of information and their ability to respond. The present invention aims to solve this problem.

[0253] 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 a terminal means using sensors to collect infrastructure status data, a server means storing the collected data in a database and performing preprocessing, a server means applying a machine learning model to predict the infrastructure's lifespan using the preprocessed data, a server means evaluating safety based on the predicted lifespan data and performing risk assessment taking disaster scenarios into consideration, a server means optimizing a repair plan based on the risk assessment results, a server means generating a repair plan as a report and notifying the user, and a server means having emotion recognition software for recognizing the user's emotions and adjusting the content of the notification. This not only enables appropriate management of infrastructure deterioration and risks, but also reduces the user's psychological burden and enables them to understand information and respond more quickly.

[0254] "Infrastructure" is a general term for facilities that make up the social infrastructure, such as public transportation, water supply, and electricity.

[0255] "Condition Data" means data that describes the physical and functional condition of infrastructure, including measurements of cracks, corrosion, deformation, etc.

[0256] A "sensor" is a measuring device used to collect infrastructure status data, and examples include strain gauges and vibration sensors.

[0257] A "terminal" is a device that temporarily stores data collected from a sensor and transmits it to a server.

[0258] A "server" is a computer system that receives data sent from a terminal and processes and analyzes it.

[0259] A "database" is a software system or hardware used to store and manage collected data in an organized manner.

[0260] "Preprocessing" refers to the process of cleansing and organizing collected data to make it suitable for analysis.

[0261] A "machine learning model" is a mathematical model that uses algorithms to learn from large amounts of data and make future predictions and classifications.

[0262] "Lifespan prediction" refers to predicting the remaining lifespan of infrastructure, specifically estimating the period until failure or deterioration occurs.

[0263] "Safety assessment" is the process of determining the safety of an infrastructure based on its current and predicted state.

[0264] A "disaster scenario" is a model that simulates the impact on infrastructure in the event of a natural disaster such as an earthquake or typhoon.

[0265] "Risk assessment" is the process of determining the degree of risk based on infrastructure life expectancy predictions and disaster scenarios.

[0266] A "repair plan" is a plan for specific construction and work to prevent and repair deterioration and breakdowns in infrastructure.

[0267] A "report" is a document that summarizes the evaluation results and details of the repair plan.

[0268] "User" means a person who uses the infrastructure management system to analyze data and develop and implement repair plans.

[0269] "Emotion recognition software" is software that analyzes a user's emotional state and adjusts the system's response as needed.

[0270] "Notification" refers to the act of a system conveying information to a user, and examples include email and dashboard display.

[0271] The above are definitions of important words included in the claims.

[0272] The infrastructure management system of the present invention monitors the status of various infrastructures, predicts their lifespan, assesses their safety, and formulates optimal repair plans. Furthermore, it is equipped with an emotion engine that recognizes the user's emotions and can adjust the content of notifications. The system includes the following components:

[0273] Data collection

[0274] The device uses sensors (e.g., interlocking strain gauge sensors) to collect infrastructure condition data. These sensors are installed on bridges, roads, etc., and periodically measure the degree of cracking, the progress of corrosion, deformation measurements, etc. For example, a sensor installed on a bridge collects data every day at 9:00 AM and sends this data to a server.

[0275] Data accumulation and preprocessing

[0276] The server stores the data sent from the device in a database (for example, MySQL). The received data is assigned metadata such as time information and sensor location information. Next, the data is preprocessed. This preprocessing includes removing duplicate data and filling in missing data (by guessing from nearby data or by filling in the average).

[0277] Lifespan Prediction

[0278] The server uses the preprocessed data to apply a machine learning model (e.g., a TensorFlow regression model) to predict the infrastructure's lifespan. This model is trained on a large amount of past data and predicts the remaining lifespan based on newly input data. For example, data obtained from road sensors is used to calculate the remaining lifespan of the road.

[0279] Safety evaluation

[0280] Servers undergo a safety assessment based on predicted lifespan data. This process uses simulation tools that take into account disaster scenarios (e.g., earthquakes and typhoons). As a result of the assessment, each piece of infrastructure is classified as "low risk," "medium risk," or "high risk."

[0281] Optimizing repair plans

[0282] The server optimizes the repair plan based on the risk assessment results. This optimization process uses linear programming to set priorities while taking into account budget and resource constraints. For example, bridges with the highest risk are given priority.

[0283] Reporting and Notifications

[0284] The server generates a report based on the assessment results and the optimized repair plan. This report includes the current status, predicted lifespan, safety assessment, repair priority and schedule for each infrastructure. The generated report is created in PDF format and sent to the user.

[0285] Adjusting notification content with an emotion engine

[0286] The emotion engine (emotion recognition software, for example) installed on the server analyzes the user's emotions. It determines the user's stress level based on the user's operation history and voice input, and adjusts the notification content as necessary. For example, if the user is feeling stressed, a concise notification will be provided. On the other hand, if the user is relaxed, a notification including detailed technical information will be provided.

[0287] Prompt Sentence Examples

[0288] Based on the crack data for Bridge B in City A, calculate the bridge's predicted remaining lifespan, conduct a safety assessment taking into account disaster scenarios, and classify it as a medium risk.

[0289] Such prompts are used by the system to accurately understand the requested task and to carry it out appropriately.

[0290] The above is a specific embodiment of the infrastructure management system of the present invention. This system not only efficiently manages infrastructure deterioration and assesses the risk of natural disasters, but also enables the adjustment of notification content according to the user's emotional state, thereby improving work efficiency and comprehension.

[0291] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0292] Step 1: Data collection

[0293] The device uses sensors to collect infrastructure condition data. Specifically, interlocking strain gauge sensors are installed on bridges and roads, and data is collected every day at 9:00 a.m. The data collected by the sensors includes the degree of cracks, the progress of corrosion, and deformation measurements. The collected data is temporarily stored inside the device and then sent to a server.

[0294] Input: Sensor measurement data (cracks, corrosion, deformation)

[0295] Output: Sensor data temporarily stored on the device

[0296] Specific behavior:

[0297] The sensor activates and acquires data

[0298] Temporarily save acquired data on the device

[0299] The device sends data to the server

[0300] Step 2: Data accumulation and preprocessing

[0301] The server stores the data sent from the device in a database (MySQL). The stored data is supplemented with metadata such as the acquisition date and time and the sensor's location information. The data is then preprocessed. This includes deleting duplicate data and filling in missing data by guessing from nearby data or by filling in the average value.

[0302] Input: Sensor data sent from the device

[0303] Output: Preprocessed data

[0304] Specific behavior:

[0305] Store data in a database

[0306] Delete duplicate data

[0307] Imputing missing data

[0308] Step 3: Lifetime prediction

[0309] The server uses the preprocessed data to apply a machine learning model (TensorFlow regression model) to predict the remaining lifespan of the infrastructure. This model is trained on a large amount of past data and predicts the remaining lifespan by inputting new data. For example, data obtained from road sensors is used to calculate the remaining lifespan of the road.

[0310] Input: Preprocessed data

[0311] Output: Estimated lifespan of infrastructure

[0312] Specific behavior:

[0313] Preprocessed data is fed into a machine learning model

[0314] The machine learning model begins processing

[0315] Predict remaining life and store the results in a database

[0316] Step 4: Safety assessment

[0317] Servers undergo a safety assessment based on predicted lifespan data. This process uses a simulation tool (specifically SimScale) that takes into account disaster scenarios such as earthquakes and typhoons. As a result of the safety assessment, each piece of infrastructure is classified as "low risk," "medium risk," or "high risk."

[0318] Input: predicted lifespan data, disaster scenarios

[0319] Output: Risk assessment result (low risk, medium risk, high risk)

[0320] Specific behavior:

[0321] Conduct disaster scenario simulations

[0322] Risk assessment based on predicted lifespan data

[0323] Classified risk assessment results are stored in a database

[0324] Step 5: Optimize repair plans

[0325] The server then optimizes the repair plan based on the risk assessment results. This optimization process uses linear programming to set priorities while taking into account budget and resource constraints. For example, the repair of bridges with the highest risk is prioritized.

[0326] Inputs: Risk assessment results, budget data, resource information

[0327] Output: Optimized repair plan

[0328] Specific behavior:

[0329] Input risk assessment results and budget data into a linear planning tool

[0330] Optimize repair plans

[0331] Repair plans stored in a database

[0332] Step 6: Reporting and Notifications

[0333] The server generates a report based on the assessment results and the optimized repair plan. This report includes the current status, predicted lifespan, safety assessment, repair priority and schedule for each infrastructure. The generated report is created in PDF format and sent to the user.

[0334] Input: Evaluation results, optimized repair plan

[0335] Output: Generated report (PDF format)

[0336] Specific behavior:

[0337] Input the assessment results and repair plan into the report generation tool

[0338] Generate reports in PDF format

[0339] Email a PDF to users

[0340] Step 7: Adjusting notification content with the emotion engine

[0341] The emotion engine (emotion recognition software, for example) installed on the server analyzes the user's emotions. It determines the user's stress level based on the user's operation history and voice input, and adjusts the notification content as necessary. For example, if the user is feeling stressed, the notification content will be concise. If the user is relaxed, the notification will include detailed technical information.

[0342] Input: User operation history, voice data

[0343] Output: Adjusted notification content

[0344] Specific behavior:

[0345] Emotion engine analyzes operation history and voice data

[0346] Determine your stress level

[0347] Adjust the notification content and send it to the user

[0348] The above is a detailed description of the specific flow and operation of each processing step of this system.

[0349] (Application example 2)

[0350] 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."

[0351] Modern infrastructure is aging, making regular monitoring and maintenance essential. However, current systems require a lot of effort to monitor the status of infrastructure, making it difficult to develop efficient maintenance plans. In addition, notification methods that do not take into account the user's emotional state can cause stress to users and result in reduced maintenance efficiency. It is necessary to solve these problems and achieve efficient and effective infrastructure management.

[0352] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes terminal means using sensors to collect infrastructure status data, server means for storing the collected data in a database and performing preprocessing, server means for applying a machine learning model to predict the infrastructure's lifespan using the preprocessed data, server means for evaluating safety based on the predicted lifespan data and performing risk assessment taking disaster scenarios into account, server means for optimizing a repair plan based on the risk assessment results, server means for generating a repair plan as a report and notifying the user, and means having an emotion engine that recognizes the user's emotions and adjusts the notification content. This not only makes it possible to efficiently manage infrastructure deterioration, evaluate the risk of natural disasters, and formulate an optimal repair plan, but also to improve work efficiency and comprehension by adjusting the notification content according to the user's emotional state.

[0353] "Infrastructure" is a general term for the structures and facilities that form the foundation for supporting transportation and public services.

[0354] "Status Data" refers to information collected by sensors that indicates the current state of the infrastructure.

[0355] "Sensor" means a device that measures a physical condition (e.g., crack severity, corrosion progression, deformation measurement, etc.).

[0356] "Terminal means" refers to a device or system that uses sensors to collect infrastructure status data and transmits the data to a server.

[0357] "Database" refers to a computer system for systematically storing and managing collected infrastructure status data.

[0358] "Preprocessing" refers to the preliminary processing of collected data to make it easier to analyze.

[0359] "Server Means" refers to a computer system for processing, storing, predicting and evaluating data.

[0360] A "machine learning model" refers to an algorithm or its implementation that learns patterns from accumulated data and makes predictions based on new data.

[0361] "Predicting lifespan" means estimating the remaining lifespan of an infrastructure based on its current condition data.

[0362] "Evaluating safety" refers to determining the safety of infrastructure based on predicted lifespan data.

[0363] "Risk assessment" means analyzing and evaluating the risk to infrastructure by considering disaster scenarios.

[0364] "Optimizing repair planning" refers to the process of determining the optimal sequence and method of infrastructure repairs based on available resources and budget.

[0365] A "report" refers to a document that summarizes information such as evaluation results and repair plans.

[0366] "Emotion Engine" means an algorithm or software that recognizes a user's emotional state and adjusts notification content accordingly.

[0367] "Notifying the user" refers to transmitting information about the evaluation results and repair plans to the user in an appropriate format.

[0368] This invention relates to a system for efficiently managing infrastructure deterioration, assessing natural disaster risks, and formulating optimal repair plans. Furthermore, it has the function of adjusting notification content according to the user's emotional state.

[0369] System Overview

[0370] The system consists of the following main components:

[0371] 1. Terminal means using sensors to collect infrastructure status data

[0372] 2. Server means to store collected data in a database and perform preprocessing

[0373] 3. A server means for applying machine learning models to predict the lifespan of the infrastructure using pre-processed data.

[0374] 4. Server means for evaluating safety based on predicted lifespan data and conducting risk assessments taking disaster scenarios into account.

[0375] 5. Server method for optimizing repair plans based on risk assessment results

[0376] 6. Server means for generating a repair plan as a report and notifying the user

[0377] 7. A means with an emotion engine that recognizes user emotions and adjusts notification content

[0378] Detailed Description

[0379] Data collection

[0380] The terminal means collects infrastructure status data using various sensors. The sensors acquire data such as the degree of cracking, the progress of corrosion, and deformation measurements. For example, sensors installed on a bridge collect data daily and send the data to a server.

[0381] Data accumulation and preprocessing

[0382] The server stores the data sent from the device in a database. It adds a timestamp to the data to clarify which part of the infrastructure the data came from. Next, it performs preprocessing on the data. This includes removing duplicate data and imputing missing data from nearby data or by averaging.

[0383] Application of life prediction model

[0384] The server inputs the preprocessed data into a machine learning model to predict the lifespan of the infrastructure. The machine learning model has been trained with training data in advance and calculates the remaining lifespan based on newly input data. For example, data obtained from road sensors can be used to calculate the remaining lifespan of a road.

[0385] Safety evaluation

[0386] The server evaluates the safety of infrastructure based on predicted lifespan data. The evaluation includes simulations that take into account disaster scenarios such as earthquakes and typhoons. As a result of the safety evaluation, each piece of infrastructure is classified as "low risk," "medium risk," or "high risk."

[0387] optimization

[0388] The server then optimizes the repair plan based on the risk assessment results. It uses a mathematical optimization algorithm to set priorities, taking into account budget and resource constraints. For example, the bridges with the highest risk receive the highest priority.

[0389] Reports and Notifications

[0390] The server creates a report based on the assessment results and the optimized repair plan. The report includes the current status, predicted lifespan, safety assessment, repair priority and schedule for each infrastructure. The server generates this report in PDF format and sends it to the user by email.

[0391] Emotional Engine Adjustment

[0392] The emotion engine installed on the server recognizes the user's emotions. Emotion recognition utilizes the user's operation history and voice input. For example, if the user is feeling stressed, the emotion engine will simplify the content of the notification. In high-stress situations, detailed technical information will be kept to a minimum, and only important information will be conveyed quickly. If the user is in a calm state, the notification will include detailed technical information.

[0393] Specific examples

[0394] For example, consider a situation where a sensor on Line A in a factory collects data and predicts that the remaining lifespan is less than 50% after 30 days. The safety assessment results are classified as "medium risk" and a repair plan is scheduled for the first week. The emotion engine recognizes the user's stress and sends a simplified notification.

[0395] An example of a prompt for a generative AI model is:

[0396] "Generate a Python program that collects data from sensors installed on factory line A, predicts lifespan, evaluates safety, and optimizes repair plans. Also, include an emotion engine function that simplifies notifications when the user is stressed."

[0397] The above is an embodiment of the present invention.

[0398] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0399] Step 1: Data collection

[0400] The terminal collects infrastructure condition data using various sensors. The sensors acquire data such as the degree of cracks, the progress of corrosion, and deformation measurements. The collected data is temporarily stored on the terminal with a timestamp. The input from the terminal is sensor data, and the output is condition data ready to be preprocessed.

[0401] Step 2: Data accumulation and preprocessing

[0402] The server receives data sent from the terminal and stores it in a database. When storing the data, it adds a timestamp and the origin of the data (which infrastructure and which part it was obtained from). Next, the server performs preprocessing such as deleting duplicate data and filling in missing data. The input is the collected raw data, and the output is the preprocessed, clean data.

[0403] Step 3: Applying the life prediction model

[0404] The server inputs the preprocessed data into a machine learning model to predict the remaining lifespan of the infrastructure. The machine learning model is pre-trained and calculates the remaining lifespan based on the newly preprocessed data. The input is the preprocessed data, and the output is the predicted lifespan data.

[0405] Step 4: Safety assessment

[0406] The server performs simulations that take disaster scenarios into account based on predicted lifespan data and evaluates safety. It classifies the risk level of the infrastructure into "low risk," "medium risk," and "high risk." The input is lifespan data and disaster scenario information, and the output is the results of the safety evaluation.

[0407] Step 5: Optimize repair plans

[0408] The server uses a mathematical optimization algorithm to optimize the repair plan based on the safety assessment results. This includes a process for setting priorities while taking into account budget and resource constraints. The inputs are the safety assessment results and resource information, and the output is an optimized repair plan.

[0409] Step 6: Reporting and Notifications

[0410] The server creates a detailed report based on the evaluation results and optimized repair plans. This report includes the current state of each piece of infrastructure, its predicted lifespan, safety assessment, and repair priorities and schedules. The generated report is emailed to the user in PDF format. The input is the repair plan and evaluation results, and the output is the generated report.

[0411] Step 7: Notification adjustment by emotion engine

[0412] The server uses an emotion engine to recognize the user's emotions. It detects the user's emotional state based on the user's operation history and voice input, and adjusts the notification content accordingly. For example, if the user is feeling stressed, it simplifies the notification content. The input is the user's operation history and voice data, and the output is the adjusted notification content.

[0413] The above is a detailed description of each processing step.

[0414] 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.

[0415] 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.

[0416] 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.

[0417] [Second embodiment]

[0418] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0419] 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.

[0420] 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).

[0421] 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.

[0422] 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.

[0423] 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).

[0424] 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.

[0425] 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.

[0426] 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.

[0427] 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.

[0428] 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.

[0429] 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."

[0430] ---

[0431] The infrastructure management system of the present invention is for monitoring the status of various infrastructures, predicting their lifespan and assessing their safety, and formulating optimal repair plans. The system includes the following components:

[0432] 1. Terminal means using sensors to collect infrastructure status data

[0433] 2. Server means to store collected data in a database and perform preprocessing

[0434] 3. A server means for applying machine learning models to predict the lifespan of the infrastructure using pre-processed data.

[0435] 4. Server means for evaluating safety based on predicted lifespan data and conducting risk assessments taking disaster scenarios into account.

[0436] 5. Server method for optimizing repair plans based on risk assessment results

[0437] 6. Server means for generating a repair plan as a report and notifying the user

[0438] As a specific embodiment, the operation of each part of the system will be described.

[0439] Data collection

[0440] The devices use sensors to collect infrastructure condition data, including crack severity, corrosion progress, deformation measurements, etc. For example, sensors on a bridge measure crack width and depth every day and send that data to a server.

[0441] Data accumulation and preprocessing

[0442] The server stores the data sent from the device in a database. It adds a timestamp to the data to clarify which part of the infrastructure the data came from. Next, it performs preprocessing on the data. This includes removing duplicate data and imputing missing data from nearby data or by averaging.

[0443] Application of life prediction model

[0444] The server then inputs the preprocessed data into a machine learning model, which uses historical infrastructure data as training data and predicts the remaining lifespan of the infrastructure from current data. For example, data from road sensors can be used to calculate the remaining lifespan of a road.

[0445] Safety evaluation

[0446] The server evaluates the safety of infrastructure based on predicted lifespan data. The evaluation includes simulations that take into account disaster scenarios such as earthquakes and typhoons. As a result of the safety evaluation, each piece of infrastructure is classified as "low risk," "medium risk," or "high risk."

[0447] optimization

[0448] The server optimizes the repair plan based on the risk assessment results. This optimization uses a mathematical optimization algorithm to set priorities while taking into account budget and resource constraints. For example, when creating a repair plan for multiple bridges in City A, the repairs with the highest urgency are given priority.

[0449] Reports and Notifications

[0450] The server creates a report based on the assessment results and optimized repair plans. The report includes the current status, predicted lifespan, safety assessment, and repair priorities and schedules for each piece of infrastructure. The server generates this report in PDF format and emails it to the user, who can review it and take appropriate measures.

[0451] As a concrete example, sensors on Bridge B in City A collect crack data and send it to a server every day. The server stores the data, performs preprocessing, and then uses a machine learning model to calculate the predicted remaining lifespan of Bridge B. Next, the server evaluates Bridge B's safety by considering disaster scenarios and classifies it as "medium risk." Finally, the server prioritizes Bridge B's repairs compared to other infrastructure and includes it in the next year's repair plan. This repair plan is generated as a report and notified to the city's infrastructure management department.

[0452] In this way, the system efficiently manages infrastructure deterioration, assesses natural disaster risks, and develops optimal repair plans.

[0453] The processing flow will be explained below.

[0454] ---

[0455] Step 1:

[0456] The devices collect infrastructure condition data. Specifically, sensors measure crack width and depth, corrosion progress, deformation measurements, etc. For example, sensors installed on bridges are set to collect data daily.

[0457] Step 2:

[0458] The data collected by the device is sent to a server in real time, and the sent data includes not only the measured physical quantities but also metadata to identify which part of the infrastructure the data was obtained from.

[0459] Step 3:

[0460] The server stores the received data in a database. At this time, it performs preprocessing such as detecting and deleting duplicate data and detecting and filling in missing data. For example, if there are missing measurement data, they are filled in with data from adjacent timestamps or the average value.

[0461] Step 4:

[0462] The server inputs the preprocessed data into a machine learning model to predict the lifespan of the infrastructure. The machine learning model has been trained with training data in advance, and calculates the remaining lifespan based on newly input data. For example, if crack data on a bridge is input, the predicted remaining lifespan of the bridge is calculated.

[0463] Step 5:

[0464] The server evaluates the safety of infrastructure based on predicted lifespan data. The evaluation process involves simulations that take into account disaster scenarios such as earthquakes and typhoons. For example, the simulation evaluates the degree of damage a bridge would sustain in an earthquake.

[0465] Step 6:

[0466] Based on the safety assessment results, the server classifies the risk level (low risk, medium risk, high risk) for each piece of infrastructure. This classification is used to determine the priority of repair plans.

[0467] Step 7:

[0468] The server optimizes the repair plan based on the risk assessment results. It applies mathematical optimization algorithms to prioritize repairs, taking into account budget and resource constraints. For example, the highest-risk bridges are given top priority.

[0469] Step 8:

[0470] The server generates a repair plan as a report and notifies the user. The report includes the current status, predicted lifespan, safety assessment, repair priority and schedule for each infrastructure. The server generates the report in PDF format and sends it to the user by email.

[0471] Step 9:

[0472] Users review the reports and take appropriate measures. Based on the reports, they schedule repair work and allocate budgets. For example, they finalize bridge and road repair plans in line with next year's budget plan.

[0473] Through the above steps, the infrastructure management system of the present invention can realize effective condition monitoring, lifespan prediction, safety assessment, and formulation of optimal repair plans.

[0474] Example 1

[0475] 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."

[0476] In managing infrastructure deterioration, it is important to measure deterioration and improve prediction accuracy, to make safety assessments objective, and to develop optimal repair plans. However, current systems lack sufficient data collection and proper data preprocessing, which reduces the accuracy of prediction models and risk assessments. Furthermore, repair plans are inefficient and prone to resource waste.

[0477] 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.

[0478] In this invention, the server includes a terminal means using sensors to collect infrastructure status data, a preprocessing means for storing the collected data in a database and deleting duplicate data and completing missing data, a means for applying a machine learning model to predict the infrastructure's lifespan using the preprocessed data, a means for evaluating safety based on the predicted lifespan data and performing a risk assessment taking disaster scenarios into account, an algorithm means for optimizing a repair plan based on the risk assessment results, and a means for generating a repair plan as a report and notifying the user. This enables precise and efficient monitoring of the infrastructure's deterioration status and the formulation of appropriate measures and repair plans to improve safety.

[0479] "Infrastructure" refers to structures and facilities installed to support public safety and daily life benefits, including bridges, roads, tunnels, and water facilities.

[0480] A "sensor" is a device that measures a physical variable and outputs it in the form of an electrical signal or other data. This data is used to monitor the condition of infrastructure.

[0481] The term "terminal means" refers to a device or system for receiving data collected from a sensor and transmitting the data to a server. Specific examples include a data collection device and a communication module.

[0482] "Preprocessing measures" refer to the rudimentary processing performed on collected data, such as removing duplicate data and filling in missing data.

[0483] A "machine learning model" refers to an algorithm that learns patterns from data and uses them to predict or classify future data. Examples include neural networks and support vector machines.

[0484] "Algorithmic means" refers to procedures or computational methods for solving specific problems, especially mathematical methods used to optimize repair plans.

[0485] "Risk assessment" refers to the process of evaluating potential hazards based on infrastructure life data and disaster scenarios.

[0486] "Report" refers to a documented summary of the system's evaluation results and plans, which are communicated to users and used for decision-making.

[0487] The infrastructure management system of the present invention monitors the status of various infrastructures, predicts their lifespan and safety, and formulates optimal repair plans. The system includes the following components:

[0488] 1. Terminal means using sensors to collect infrastructure status data

[0489] 2. Preprocessing means for storing collected data in a database, deleting duplicate data, and filling in missing data.

[0490] 3. A means to apply machine learning models to predict infrastructure lifespan using pre-processed data

[0491] 4. A means of assessing safety based on predicted lifespan data and conducting risk assessments taking disaster scenarios into account.

[0492] 5. Algorithmic means to optimize repair plans based on risk assessment results

[0493] 6. A means of generating a repair plan as a report and notifying the user

[0494] Data collection

[0495] The devices collect infrastructure condition data using sensors. Examples of sensors include sensors that measure cracks, sensors that monitor corrosion, sensors that detect deformation, etc. For example, sensors installed on a bridge measure the width and depth of cracks every day and send the data to a server.

[0496] Data accumulation and preprocessing

[0497] The server receives the data sent from the devices and stores it in a database (e.g., MySQL, PostgreSQL). The data is stored with a timestamp and includes metadata to clarify which part of the infrastructure it was obtained from. Preprocessing includes removing duplicate data and imputing missing data (e.g., imputing from neighboring data or imputing with the average value).

[0498] Application of life prediction model

[0499] The server then inputs the preprocessed data into a machine learning model (e.g., TensorFlow, scikit-learn). The machine learning model uses historical infrastructure data as training data and predicts the remaining lifespan of the infrastructure from current data. For example, data obtained from road sensors can be used to calculate the remaining lifespan of a road.

[0500] Safety evaluation

[0501] The server evaluates the safety of infrastructure based on predicted lifespan data. This evaluation includes simulations (e.g., FEA software) that take into account disaster scenarios such as earthquakes and typhoons. As a result of the safety evaluation, each piece of infrastructure is classified as "low risk," "medium risk," or "high risk."

[0502] Optimizing repair plans

[0503] The server optimizes repair plans based on the risk assessment results. It uses mathematical optimization algorithms (e.g., linear programming and genetic algorithms) to consider budget and resource constraints. For example, when creating repair plans for multiple bridges, the most urgent repairs are prioritized.

[0504] Report generation and notification

[0505] The server creates a report based on the assessment results and optimized repair plans. The report includes the current status, predicted lifespan, safety assessment, and repair priorities and schedules for each piece of infrastructure. The server generates this report in PDF format and emails it to the user, who can review it and take appropriate measures.

[0506] Specific examples

[0507] As a concrete example, sensors on Bridge B in City A collect crack data and send it to a server every day. The server stores the data, performs preprocessing, and then uses a machine learning model to calculate the predicted remaining lifespan of Bridge B. Next, the server evaluates Bridge B's safety by considering disaster scenarios and classifies it as "medium risk." Finally, the server prioritizes Bridge B's repairs compared to other infrastructure and includes it in the next year's repair plan. This repair plan is generated as a report and notified to the city's infrastructure management department.

[0508] Prompt Sentence Examples

[0509] Below are some examples of specific prompts that can be fed into a generative AI model:

[0510] Based on the crack data collected over the past year by sensors installed on Bridge B in City A, calculate the predicted remaining lifespan of Bridge B and evaluate its safety. Also, based on the evaluation results, optimize the repair plan for the next year and generate a report.

[0511] In this way, the system efficiently monitors the condition of infrastructure, assesses the risk of natural disasters, and develops optimal repair plans.

[0512] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0513] Step 1: Data collection

[0514] The devices use sensors to collect infrastructure condition data, with input data including crack width, depth, corrosion progress, and deformation measurements.

[0515] How it works: Sensors installed on the bridge measure crack width and depth every hour and send the condition data to a server in real time. The output is collected infrastructure condition data.

[0516] Step 2: Data accumulation and preprocessing

[0517] The server receives data sent from the terminal and stores it in a database (e.g., MySQL, PostgreSQL). The input is the raw data sent from the terminal.

[0518] What it does: The server adds a timestamp to the data it receives, along with metadata indicating which part of the infrastructure the data came from. It then removes duplicates and imputes missing data with neighboring data or averages. The output is preprocessed, clean data.

[0519] Step 3: Applying the life prediction model

[0520] The server inputs the preprocessed data into a machine learning model (e.g., TensorFlow, scikit-learn), where the input data is the preprocessed infrastructure state data.

[0521] How it works: The server inputs the preprocessed data into a machine learning model, which uses past learning results to predict the remaining lifespan of infrastructure. For example, data on a bridge is used to calculate the bridge's predicted remaining lifespan. The output is the predicted remaining lifespan data.

[0522] Step 4: Safety assessment

[0523] The server evaluates the safety of the infrastructure based on the predicted remaining life data. The input data is the predicted remaining life data.

[0524] Specific operation: Simulations are performed taking into account disaster scenarios (e.g., earthquakes, typhoons) and safety assessments are carried out. As a result, each piece of infrastructure is classified as "low risk," "medium risk," or "high risk." The output is the risk assessment result.

[0525] Step 5: Optimize repair plans

[0526] The server optimizes the repair plan based on the risk assessment results. The input data is the risk assessment results.

[0527] How it works: Using mathematical optimization algorithms (e.g., linear programming, genetic algorithms), it generates repair plans taking into account budget and resource constraints. For example, when planning repairs for multiple bridges, it prioritizes the repairs with the highest urgency. The output is an optimized repair plan.

[0528] Step 6: Generate reports and notifications

[0529] The server generates a report based on the evaluation results and the optimized repair plan. The input data is the optimized repair plan.

[0530] Specific behavior: Generates a report in PDF format containing the current status, predicted lifespan, safety assessment, and repair priorities and schedules for each piece of infrastructure. The server then emails this report to the user (e.g., the city's infrastructure management department). The user can review the report and take appropriate measures. The output is the generated report and a notification email.

[0531] In this way, the system processes and calculates data at each step, and then executes a series of processes until finally notifying the user.

[0532] (Application example 1)

[0533] 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."

[0534] Conventional infrastructure management systems generally collect data using fixed sensors, making it difficult to collect and analyze data in real time from mobile devices. It is also difficult to efficiently monitor the deterioration of road infrastructure and formulate timely repair plans. This has led to problems such as the progression of infrastructure deterioration and an increased risk of accidents and disasters.

[0535] 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.

[0536] In this invention, the server includes terminal means using sensors to collect infrastructure status data, server means for storing the collected data in a database and preprocessing it, server means for applying a machine learning model to predict the infrastructure's lifespan using the preprocessed data, means for evaluating safety based on the predicted lifespan data and conducting risk assessments taking disaster scenarios into account, means for collecting road status data using sensors mounted on vehicles, means for applying a machine learning model to predict the road's lifespan using the collected data, means for evaluating road safety based on the predicted lifespan data and conducting risk assessments taking disaster scenarios into account, means for optimizing road repair plans based on the risk assessment results, and means for generating a repair plan as a report and notifying the vehicle manager. This enables real-time data collection and analysis by vehicles, which are mobile objects, and enables efficient monitoring of the deterioration state of road infrastructure and effective formulation of repair plans at appropriate times.

[0537] "Infrastructure" refers to the physical structures of social infrastructure such as roads, bridges, tunnels, and dams.

[0538] "Condition data" refers to data that describes the physical condition of infrastructure, and includes, for example, information such as the degree of cracking, the progress of corrosion, and deformation measurements.

[0539] "Sensor" refers to a device used to detect and collect infrastructure condition data, including cameras, LIDAR sensors, vibration sensors, etc.

[0540] "Terminal means" refers to a device that uses sensors to collect infrastructure status data and transmits it to a server.

[0541] "Database" refers to a system for efficiently storing and managing collected data.

[0542] "Preprocessing" is the process of preparing data stored in a database so that it can be analyzed, and includes removing duplicate data and filling in missing data.

[0543] "Server Means" refers to a central processing unit for collecting, storing, pre-processing and analyzing data.

[0544] "Machine learning models" refer to algorithms and methods for predicting future deterioration and lifespan of infrastructure based on past data.

[0545] "Lifespan forecasting" refers to the process for predicting the remaining lifespan of infrastructure.

[0546] "Disaster scenarios" refer to hypothetical scenarios used to assess the impact of natural disasters such as earthquakes and typhoons on infrastructure.

[0547] "Risk assessment" refers to the process of assessing the safety and potential risks of infrastructure based on predicted data.

[0548] "Vehicle-mounted sensors" refers to sensors attached to a vehicle to collect roadway condition data.

[0549] "Repair Plan" means a plan containing a schedule of repairs and maintenance required to prevent deterioration of infrastructure.

[0550] "Report" refers to a written summary of the repair plan and the results of the risk assessment.

[0551] "Administrator" means the person or organization responsible for maintaining the infrastructure.

[0552] An embodiment of this invention is a system for collecting condition data on road infrastructure using sensors installed in automobiles, predicting the lifespan of the infrastructure based on that data, and formulating appropriate repair plans.

[0553] Data collection

[0554] The terminal uses the vehicle's onboard camera and LIDAR sensor to collect real-time data on road cracks, holes, deformations, etc. This allows moving vehicles to efficiently collect large-scale road condition data. For example, the LIDAR sensor scans the road surface for irregularities and detects abnormalities.

[0555] Data accumulation and preprocessing

[0556] The server sends the collected data to a cloud server and stores it in a database. The stored data is time-stamped to identify which road section the data comes from. Pre-processing is then performed, including removing duplicate data and filling in missing data. This pre-processing improves the consistency and accuracy of the data.

[0557] Application of life prediction model

[0558] The server applies a machine learning model to the preprocessed data to predict the remaining lifespan of road infrastructure. This machine learning model learns from past road condition data as training data to improve prediction accuracy. Specifically, the model is built using machine learning libraries such as TensorFlow.

[0559] Safety evaluation

[0560] The server performs safety assessments based on predicted lifespan data, taking into account disaster scenarios such as earthquakes and typhoons. This allows the risk level of each road section to be understood and high-risk sections to be identified. For example, disaster scenarios can be simulated using MATLAB or similar software.

[0561] optimization

[0562] The server then optimizes the road repair plan based on the risk assessment results. This optimization uses a mathematical optimization algorithm to set priorities while taking into account budget and resource constraints. For example, the road sections with the highest urgency are prioritized in the repair plan.

[0563] Reports and Notifications

[0564] The server generates a repair plan as a report and notifies the vehicle manager, which includes the current road condition, predicted lifespan, safety assessment, repair priority and schedule, so that the manager can take appropriate measures.

[0565] Examples of concrete examples and prompts

[0566] For example, while an autonomous vehicle is driving on a highway, its LIDAR sensor will detect cracks in the road and send them to a cloud server in real time. The server will then use the data to optimize highway repair plans and notify the highway manager.

[0567] Example prompt sentence:

[0568] "Identify highway repair needs most with road crack condition data. Evaluate safety and optimize repair plans by considering projected remaining life and disaster scenarios."

[0569] In this way, the present invention enables real-time data collection and analysis from moving vehicles, thereby enabling efficient monitoring of road infrastructure and the formulation of repair plans.

[0570] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0571] Step 1: Data collection

[0572] The device collects road condition data in real time using the car's on-board camera and LIDAR sensor. Specifically, the LIDAR sensor scans the road surface for irregularities and acquires the data. The input is raw data from the sensor, and the output is processed road condition data.

[0573] Step 2: Send data

[0574] The device sends the collected data to the cloud server. The data is time-stamped to identify the location from which it was collected. The input is the status data obtained in the data collection step, and the output is the transmitted data.

[0575] Step 3: Data accumulation and preprocessing

[0576] The server stores the data sent to the cloud in a database. The stored data undergoes preprocessing, such as deleting duplicate data and filling in missing data. Preprocessing improves the consistency and accuracy of the data. The input is the raw data sent, and the output is the preprocessed, clear data.

[0577] Step 4: Applying the life prediction model

[0578] The server applies a machine learning model to the preprocessed data to predict the remaining lifespan of the road. Specifically, it builds a model using a machine learning library such as TensorFlow and inputs data into the model to make predictions. The input is the preprocessed data, and the output is the predicted remaining lifespan data.

[0579] Step 5: Safety Assessment

[0580] The server performs safety assessments based on predicted lifespan data, taking disaster scenarios into account. For example, it uses MATLAB to simulate disaster scenarios such as earthquakes and typhoons and evaluate their impact. The input is lifespan prediction data, and the output is the risk assessment results.

[0581] Step 6: Optimize repair plans

[0582] The server optimizes the repair plan based on the safety assessment results. For optimization, it takes into account resource constraints and uses a mathematical optimization algorithm. For example, it prioritizes the inclusion of high-priority areas in the repair plan. The input is the risk assessment results, and the output is the optimized repair plan.

[0583] Step 7: Reporting and Notifications

[0584] The server generates a report based on the optimized repair plan and notifies the administrator. The report includes the current state, predicted lifespan, safety assessment, repair priority and schedule. The input is the optimized repair plan, and the output is the documented information in the report.

[0585] 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.

[0586] ---

[0587] The infrastructure management system of the present invention monitors the status of various infrastructures, predicts their lifespan, assesses their safety, and formulates optimal repair plans, and further includes an emotion engine that recognizes the emotions of users. The system includes the following components:

[0588] 1. Terminal means using sensors to collect infrastructure status data

[0589] 2. Server means to store collected data in a database and perform preprocessing

[0590] 3. A server means for applying machine learning models to predict the lifespan of the infrastructure using pre-processed data.

[0591] 4. Server means for evaluating safety based on predicted lifespan data and conducting risk assessments taking disaster scenarios into account.

[0592] 5. Server method for optimizing repair plans based on risk assessment results

[0593] 6. Server means for generating a repair plan as a report and notifying the user

[0594] 7. Emotion engine that recognizes user emotions and adjusts notification content

[0595] As a specific embodiment, the operation of each part of the system will be described.

[0596] Data collection

[0597] The devices use sensors to collect infrastructure condition data, including the degree of cracking, corrosion progress, deformation measurements, etc. For example, sensors installed on a bridge collect data daily and send it to a server.

[0598] Data accumulation and preprocessing

[0599] The server stores the data sent from the device in a database. It adds a timestamp to the data to clarify which part of the infrastructure the data came from. Next, it performs preprocessing on the data. This includes removing duplicate data and imputing missing data from nearby data or by averaging.

[0600] Application of life prediction model

[0601] The server then inputs the preprocessed data into a machine learning model to predict the infrastructure's lifespan. The machine learning model has been trained with training data in advance and calculates the remaining lifespan based on newly input data. For example, data obtained from road sensors can be used to calculate the remaining lifespan of a road.

[0602] Safety evaluation

[0603] The server evaluates the safety of infrastructure based on predicted lifespan data. The evaluation includes simulations that take into account disaster scenarios such as earthquakes and typhoons. As a result of the safety evaluation, each piece of infrastructure is classified as "low risk," "medium risk," or "high risk."

[0604] optimization

[0605] The server then optimizes the repair plan based on the risk assessment results. It uses a mathematical optimization algorithm to set priorities, taking into account budget and resource constraints. For example, the bridges with the highest risk receive the highest priority.

[0606] Reports and Notifications

[0607] The server creates a report based on the assessment results and the optimized repair plan. The report includes the current status, predicted lifespan, safety assessment, repair priority and schedule for each infrastructure. The server generates this report in PDF format and sends it to the user by email.

[0608] Emotional Engine Adjustment

[0609] The emotion engine installed on the server recognizes the user's emotions. Emotion recognition utilizes the user's operation history and voice input. For example, if the user is feeling stressed, the emotion engine will simplify the content of the notification. In high-stress situations, detailed technical information will be kept to a minimum, and only important information will be conveyed quickly. If the user is in a calm state, the notification will include detailed technical information.

[0610] As a concrete example, sensors collect crack data on Bridge B in City A and send it to a server every day. The server stores the data, performs preprocessing, and then uses a machine learning model to calculate the predicted remaining lifespan of Bridge B. Next, it evaluates the safety of Bridge B by taking disaster scenarios into account and classifies it as "medium risk." Finally, the server prioritizes the repair of Bridge B compared to other infrastructure and includes it in the repair plan for the following year. This repair plan is generated as a report and notified to the city's infrastructure management department. If a management department employee is feeling stressed, the emotion engine can simplify the notification content and present it in an easy-to-understand format.

[0611] In this way, this system not only efficiently manages infrastructure deterioration, assesses natural disaster risks, and develops optimal repair plans, but also improves work efficiency and comprehension by adjusting notification content according to the user's emotional state.

[0612] The processing flow will be explained below.

[0613] ---

[0614] Step 1:

[0615] The devices collect infrastructure condition data. Specifically, sensors measure crack width and depth, corrosion progress, deformation measurements, etc. For example, sensors installed on bridges are set to collect data daily.

[0616] Step 2:

[0617] The data collected by the device is sent to a server in real time, and the sent data includes not only the measured physical quantities but also metadata to identify which part of the infrastructure the data was obtained from.

[0618] Step 3:

[0619] The server stores the received data in a database. At this time, it performs preprocessing such as detecting and deleting duplicate data and detecting and filling in missing data. For example, if there are missing measurement data, they are filled in with data from adjacent timestamps or the average value.

[0620] Step 4:

[0621] The server inputs the preprocessed data into a machine learning model to predict the infrastructure's lifespan. The machine learning model is trained on the training data in advance and calculates the remaining lifespan based on the newly input data. For example, data obtained from road sensors can be used to calculate the remaining lifespan of a road.

[0622] Step 5:

[0623] The server evaluates the safety of infrastructure based on predicted lifespan data. The evaluation process involves simulations that take into account disaster scenarios such as earthquakes and typhoons. For example, the simulation evaluates the degree of damage a bridge would sustain in an earthquake.

[0624] Step 6:

[0625] Based on the safety assessment results, the server classifies the risk level (low risk, medium risk, high risk) for each piece of infrastructure. This classification is used to determine the priority of repair plans.

[0626] Step 7:

[0627] The server optimizes the repair plan based on the risk assessment results. It applies mathematical optimization algorithms to prioritize repairs, taking into account budget and resource constraints. For example, the highest-risk bridges are given top priority.

[0628] Step 8:

[0629] The server generates a repair plan as a report and notifies the user. The report includes the current status, predicted lifespan, safety assessment, repair priority and schedule for each infrastructure. The server generates the report in PDF format and sends it to the user by email.

[0630] Step 9:

[0631] Users review the reports and take appropriate measures. Based on the reports, they schedule repair work and allocate budgets. For example, they finalize bridge and road repair plans in line with next year's budget plan.

[0632] Step 10:

[0633] The emotion engine recognizes the user's emotions. Emotion recognition utilizes the user's operation history and voice input. For example, if the user is feeling stressed, the emotion engine will simplify the notification content.

[0634] Step 11:

[0635] The server adjusts the notification content based on the results of the emotion engine. In stressful situations, the server reduces the amount of detailed technical information and quickly conveys only the important information. On the other hand, when the user is calm, the server provides notifications that include detailed technical information.

[0636] As a concrete example, sensors collect crack data on Bridge B in City A and send it to a server every day. The server stores the data, performs preprocessing, and then uses a machine learning model to calculate the predicted remaining lifespan of Bridge B. Next, it evaluates the safety of Bridge B by taking disaster scenarios into account and classifies it as "medium risk." Finally, the server prioritizes the repair of Bridge B compared to other infrastructure and includes it in the repair plan for the following year. This repair plan is generated as a report and notified to the city's infrastructure management department. If a management department employee is feeling stressed, the emotion engine can simplify the notification content and present it in an easy-to-understand format.

[0637] In this way, this system not only efficiently manages infrastructure deterioration, assesses natural disaster risks, and develops optimal repair plans, but also improves work efficiency and comprehension by adjusting notification content according to the user's emotional state.

[0638] Example 2

[0639] 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."

[0640] While conventional infrastructure management systems can efficiently monitor infrastructure conditions and perform lifespan predictions and risk assessments, they lack the means to reduce the psychological burden on users. As a result, users tend to feel stressed, which can slow their understanding of information and their ability to respond. The present invention aims to solve this problem.

[0641] 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 a terminal means using sensors to collect infrastructure status data, a server means storing the collected data in a database and performing preprocessing, a server means applying a machine learning model to predict the infrastructure's lifespan using the preprocessed data, a server means evaluating safety based on the predicted lifespan data and performing risk assessment taking disaster scenarios into consideration, a server means optimizing a repair plan based on the risk assessment results, a server means generating a repair plan as a report and notifying the user, and a server means having emotion recognition software for recognizing the user's emotions and adjusting the content of the notification. This not only enables appropriate management of infrastructure deterioration and risks, but also reduces the user's psychological burden and enables them to understand information and respond more quickly.

[0642] "Infrastructure" is a general term for facilities that make up the social infrastructure, such as public transportation, water supply, and electricity.

[0643] "Condition Data" means data that describes the physical and functional condition of infrastructure, including measurements of cracks, corrosion, deformation, etc.

[0644] A "sensor" is a measuring device used to collect infrastructure status data, and examples include strain gauges and vibration sensors.

[0645] A "terminal" is a device that temporarily stores data collected from a sensor and transmits it to a server.

[0646] A "server" is a computer system that receives data sent from a terminal and processes and analyzes it.

[0647] A "database" is a software system or hardware used to store and manage collected data in an organized manner.

[0648] "Preprocessing" refers to the process of cleansing and organizing collected data to make it suitable for analysis.

[0649] A "machine learning model" is a mathematical model that uses algorithms to learn from large amounts of data and make future predictions and classifications.

[0650] "Lifespan prediction" refers to predicting the remaining lifespan of infrastructure, specifically estimating the period until failure or deterioration occurs.

[0651] "Safety assessment" is the process of determining the safety of an infrastructure based on its current and predicted state.

[0652] A "disaster scenario" is a model that simulates the impact on infrastructure in the event of a natural disaster such as an earthquake or typhoon.

[0653] "Risk assessment" is the process of determining the degree of risk based on infrastructure life expectancy predictions and disaster scenarios.

[0654] A "repair plan" is a plan for specific construction and work to prevent and repair deterioration and breakdowns in infrastructure.

[0655] A "report" is a document that summarizes the evaluation results and details of the repair plan.

[0656] "User" means a person who uses the infrastructure management system to analyze data and develop and implement repair plans.

[0657] "Emotion recognition software" is software that analyzes a user's emotional state and adjusts the system's response as needed.

[0658] "Notification" refers to the act of a system conveying information to a user, and examples include email and dashboard display.

[0659] The above are definitions of important words included in the claims.

[0660] The infrastructure management system of the present invention monitors the status of various infrastructures, predicts their lifespan, assesses their safety, and formulates optimal repair plans. Furthermore, it is equipped with an emotion engine that recognizes the user's emotions and can adjust the content of notifications. The system includes the following components:

[0661] Data collection

[0662] The device uses sensors (e.g., interlocking strain gauge sensors) to collect infrastructure condition data. These sensors are installed on bridges, roads, etc., and periodically measure the degree of cracking, the progress of corrosion, deformation measurements, etc. For example, a sensor installed on a bridge collects data every day at 9:00 AM and sends this data to a server.

[0663] Data accumulation and preprocessing

[0664] The server stores the data sent from the device in a database (for example, MySQL). The received data is assigned metadata such as time information and sensor location information. Next, the data is preprocessed. This preprocessing includes removing duplicate data and filling in missing data (by guessing from nearby data or by filling in the average).

[0665] Lifespan Prediction

[0666] The server uses the preprocessed data to apply a machine learning model (e.g., a TensorFlow regression model) to predict the infrastructure's lifespan. This model is trained on a large amount of past data and predicts the remaining lifespan based on newly input data. For example, data obtained from road sensors is used to calculate the remaining lifespan of the road.

[0667] Safety evaluation

[0668] Servers undergo a safety assessment based on predicted lifespan data. This process uses simulation tools that take into account disaster scenarios (e.g., earthquakes and typhoons). As a result of the assessment, each piece of infrastructure is classified as "low risk," "medium risk," or "high risk."

[0669] Optimizing repair plans

[0670] The server optimizes the repair plan based on the risk assessment results. This optimization process uses linear programming to set priorities while taking into account budget and resource constraints. For example, bridges with the highest risk are given priority.

[0671] Reporting and Notifications

[0672] The server generates a report based on the assessment results and the optimized repair plan. This report includes the current status, predicted lifespan, safety assessment, repair priority and schedule for each infrastructure. The generated report is created in PDF format and sent to the user.

[0673] Adjusting notification content with an emotion engine

[0674] The emotion engine (emotion recognition software, for example) installed on the server analyzes the user's emotions. It determines the user's stress level based on the user's operation history and voice input, and adjusts the notification content as necessary. For example, if the user is feeling stressed, a concise notification will be provided. On the other hand, if the user is relaxed, a notification including detailed technical information will be provided.

[0675] Prompt Sentence Examples

[0676] Based on the crack data for Bridge B in City A, calculate the bridge's predicted remaining lifespan, conduct a safety assessment taking into account disaster scenarios, and classify it as a medium risk.

[0677] Such prompts are used by the system to accurately understand the requested task and to carry it out appropriately.

[0678] The above is a specific embodiment of the infrastructure management system of the present invention. This system not only efficiently manages infrastructure deterioration and assesses the risk of natural disasters, but also enables the adjustment of notification content according to the user's emotional state, thereby improving work efficiency and comprehension.

[0679] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0680] Step 1: Data collection

[0681] The device uses sensors to collect infrastructure condition data. Specifically, interlocking strain gauge sensors are installed on bridges and roads, and data is collected every day at 9:00 a.m. The data collected by the sensors includes the degree of cracks, the progress of corrosion, and deformation measurements. The collected data is temporarily stored inside the device and then sent to a server.

[0682] Input: Sensor measurement data (cracks, corrosion, deformation)

[0683] Output: Sensor data temporarily stored on the device

[0684] Specific behavior:

[0685] The sensor activates and acquires data

[0686] Temporarily save acquired data on the device

[0687] The device sends data to the server

[0688] Step 2: Data accumulation and preprocessing

[0689] The server stores the data sent from the device in a database (MySQL). The stored data is supplemented with metadata such as the acquisition date and time and the sensor's location information. The data is then preprocessed. This includes deleting duplicate data and filling in missing data by guessing from nearby data or by filling in the average value.

[0690] Input: Sensor data sent from the device

[0691] Output: Preprocessed data

[0692] Specific behavior:

[0693] Store data in a database

[0694] Delete duplicate data

[0695] Imputing missing data

[0696] Step 3: Lifetime prediction

[0697] The server uses the preprocessed data to apply a machine learning model (TensorFlow regression model) to predict the remaining lifespan of the infrastructure. This model is trained on a large amount of past data and predicts the remaining lifespan by inputting new data. For example, data obtained from road sensors is used to calculate the remaining lifespan of the road.

[0698] Input: Preprocessed data

[0699] Output: Estimated lifespan of infrastructure

[0700] Specific behavior:

[0701] Preprocessed data is fed into a machine learning model

[0702] The machine learning model begins processing

[0703] Predict remaining life and store the results in a database

[0704] Step 4: Safety assessment

[0705] Servers undergo a safety assessment based on predicted lifespan data. This process uses a simulation tool (specifically SimScale) that takes into account disaster scenarios such as earthquakes and typhoons. As a result of the safety assessment, each piece of infrastructure is classified as "low risk," "medium risk," or "high risk."

[0706] Input: predicted lifespan data, disaster scenarios

[0707] Output: Risk assessment result (low risk, medium risk, high risk)

[0708] Specific behavior:

[0709] Conduct disaster scenario simulations

[0710] Risk assessment based on predicted lifespan data

[0711] Classified risk assessment results are stored in a database

[0712] Step 5: Optimize repair plans

[0713] The server then optimizes the repair plan based on the risk assessment results. This optimization process uses linear programming to set priorities while taking into account budget and resource constraints. For example, the repair of bridges with the highest risk is prioritized.

[0714] Inputs: Risk assessment results, budget data, resource information

[0715] Output: Optimized repair plan

[0716] Specific behavior:

[0717] Input risk assessment results and budget data into a linear planning tool

[0718] Optimize repair plans

[0719] Repair plans stored in a database

[0720] Step 6: Reporting and Notifications

[0721] The server generates a report based on the assessment results and the optimized repair plan. This report includes the current status, predicted lifespan, safety assessment, repair priority and schedule for each infrastructure. The generated report is created in PDF format and sent to the user.

[0722] Input: Evaluation results, optimized repair plan

[0723] Output: Generated report (PDF format)

[0724] Specific behavior:

[0725] Input the assessment results and repair plan into the report generation tool

[0726] Generate reports in PDF format

[0727] Email a PDF to users

[0728] Step 7: Adjusting notification content with the emotion engine

[0729] The emotion engine (emotion recognition software, for example) installed on the server analyzes the user's emotions. It determines the user's stress level based on the user's operation history and voice input, and adjusts the notification content as necessary. For example, if the user is feeling stressed, the notification content will be concise. If the user is relaxed, the notification will include detailed technical information.

[0730] Input: User operation history, voice data

[0731] Output: Adjusted notification content

[0732] Specific behavior:

[0733] Emotion engine analyzes operation history and voice data

[0734] Determine your stress level

[0735] Adjust the notification content and send it to the user

[0736] The above is a detailed description of the specific flow and operation of each processing step of this system.

[0737] (Application example 2)

[0738] 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."

[0739] Modern infrastructure is aging, making regular monitoring and maintenance essential. However, current systems require a lot of effort to monitor the status of infrastructure, making it difficult to develop efficient maintenance plans. In addition, notification methods that do not take into account the user's emotional state can cause stress to users and result in reduced maintenance efficiency. It is necessary to solve these problems and achieve efficient and effective infrastructure management.

[0740] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes terminal means using sensors to collect infrastructure status data, server means for storing the collected data in a database and performing preprocessing, server means for applying a machine learning model to predict the infrastructure's lifespan using the preprocessed data, server means for evaluating safety based on the predicted lifespan data and performing risk assessment taking disaster scenarios into account, server means for optimizing a repair plan based on the risk assessment results, server means for generating a repair plan as a report and notifying the user, and means having an emotion engine that recognizes the user's emotions and adjusts the notification content. This not only makes it possible to efficiently manage infrastructure deterioration, evaluate the risk of natural disasters, and formulate an optimal repair plan, but also to improve work efficiency and comprehension by adjusting the notification content according to the user's emotional state.

[0741] "Infrastructure" is a general term for the structures and facilities that form the foundation for supporting transportation and public services.

[0742] "Status Data" refers to information collected by sensors that indicates the current state of the infrastructure.

[0743] "Sensor" means a device that measures a physical condition (e.g., crack severity, corrosion progression, deformation measurement, etc.).

[0744] "Terminal means" refers to a device or system that uses sensors to collect infrastructure status data and transmits the data to a server.

[0745] "Database" refers to a computer system for systematically storing and managing collected infrastructure status data.

[0746] "Preprocessing" refers to the preliminary processing of collected data to make it easier to analyze.

[0747] "Server Means" refers to a computer system for processing, storing, predicting and evaluating data.

[0748] A "machine learning model" refers to an algorithm or its implementation that learns patterns from accumulated data and makes predictions based on new data.

[0749] "Predicting lifespan" means estimating the remaining lifespan of an infrastructure based on its current condition data.

[0750] "Evaluating safety" refers to determining the safety of infrastructure based on predicted lifespan data.

[0751] "Risk assessment" means analyzing and evaluating the risk to infrastructure by considering disaster scenarios.

[0752] "Optimizing repair planning" refers to the process of determining the optimal sequence and method of infrastructure repairs based on available resources and budget.

[0753] A "report" refers to a document that summarizes information such as evaluation results and repair plans.

[0754] "Emotion Engine" means an algorithm or software that recognizes a user's emotional state and adjusts notification content accordingly.

[0755] "Notifying the user" refers to transmitting information about the evaluation results and repair plans to the user in an appropriate format.

[0756] This invention relates to a system for efficiently managing infrastructure deterioration, assessing natural disaster risks, and formulating optimal repair plans. Furthermore, it has the function of adjusting notification content according to the user's emotional state.

[0757] System Overview

[0758] The system consists of the following main components:

[0759] 1. Terminal means using sensors to collect infrastructure status data

[0760] 2. Server means to store collected data in a database and perform preprocessing

[0761] 3. A server means for applying machine learning models to predict the lifespan of the infrastructure using pre-processed data.

[0762] 4. Server means for evaluating safety based on predicted lifespan data and conducting risk assessments taking disaster scenarios into account.

[0763] 5. Server method for optimizing repair plans based on risk assessment results

[0764] 6. Server means for generating a repair plan as a report and notifying the user

[0765] 7. A means with an emotion engine that recognizes user emotions and adjusts notification content

[0766] Detailed Description

[0767] Data collection

[0768] The terminal means collects infrastructure status data using various sensors. The sensors acquire data such as the degree of cracking, the progress of corrosion, and deformation measurements. For example, sensors installed on a bridge collect data daily and send the data to a server.

[0769] Data accumulation and preprocessing

[0770] The server stores the data sent from the device in a database. It adds a timestamp to the data to clarify which part of the infrastructure the data came from. Next, it performs preprocessing on the data. This includes removing duplicate data and imputing missing data from nearby data or by averaging.

[0771] Application of life prediction model

[0772] The server inputs the preprocessed data into a machine learning model to predict the lifespan of the infrastructure. The machine learning model has been trained with training data in advance and calculates the remaining lifespan based on newly input data. For example, data obtained from road sensors can be used to calculate the remaining lifespan of a road.

[0773] Safety evaluation

[0774] The server evaluates the safety of infrastructure based on predicted lifespan data. The evaluation includes simulations that take into account disaster scenarios such as earthquakes and typhoons. As a result of the safety evaluation, each piece of infrastructure is classified as "low risk," "medium risk," or "high risk."

[0775] optimization

[0776] The server then optimizes the repair plan based on the risk assessment results. It uses a mathematical optimization algorithm to set priorities, taking into account budget and resource constraints. For example, the bridges with the highest risk receive the highest priority.

[0777] Reports and Notifications

[0778] The server creates a report based on the assessment results and the optimized repair plan. The report includes the current status, predicted lifespan, safety assessment, repair priority and schedule for each infrastructure. The server generates this report in PDF format and sends it to the user by email.

[0779] Emotional Engine Adjustment

[0780] The emotion engine installed on the server recognizes the user's emotions. Emotion recognition utilizes the user's operation history and voice input. For example, if the user is feeling stressed, the emotion engine will simplify the content of the notification. In high-stress situations, detailed technical information will be kept to a minimum, and only important information will be conveyed quickly. If the user is in a calm state, the notification will include detailed technical information.

[0781] Specific examples

[0782] For example, consider a situation where a sensor on Line A in a factory collects data and predicts that the remaining lifespan is less than 50% after 30 days. The safety assessment results are classified as "medium risk" and a repair plan is scheduled for the first week. The emotion engine recognizes the user's stress and sends a simplified notification.

[0783] An example of a prompt for a generative AI model is:

[0784] "Generate a Python program that collects data from sensors installed on factory line A, predicts lifespan, evaluates safety, and optimizes repair plans. Also, include an emotion engine function that simplifies notifications when the user is stressed."

[0785] The above is an embodiment of the present invention.

[0786] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0787] Step 1: Data collection

[0788] The terminal collects infrastructure condition data using various sensors. The sensors acquire data such as the degree of cracks, the progress of corrosion, and deformation measurements. The collected data is temporarily stored on the terminal with a timestamp. The input from the terminal is sensor data, and the output is condition data ready to be preprocessed.

[0789] Step 2: Data accumulation and preprocessing

[0790] The server receives data sent from the terminal and stores it in a database. When storing the data, it adds a timestamp and the origin of the data (which infrastructure and which part it was obtained from). Next, the server performs preprocessing such as deleting duplicate data and filling in missing data. The input is the collected raw data, and the output is the preprocessed, clean data.

[0791] Step 3: Applying the life prediction model

[0792] The server inputs the preprocessed data into a machine learning model to predict the remaining lifespan of the infrastructure. The machine learning model is pre-trained and calculates the remaining lifespan based on the newly preprocessed data. The input is the preprocessed data, and the output is the predicted lifespan data.

[0793] Step 4: Safety assessment

[0794] The server performs simulations that take disaster scenarios into account based on predicted lifespan data and evaluates safety. It classifies the risk level of the infrastructure into "low risk," "medium risk," and "high risk." The input is lifespan data and disaster scenario information, and the output is the results of the safety evaluation.

[0795] Step 5: Optimize repair plans

[0796] The server uses a mathematical optimization algorithm to optimize the repair plan based on the safety assessment results. This includes a process for setting priorities while taking into account budget and resource constraints. The inputs are the safety assessment results and resource information, and the output is an optimized repair plan.

[0797] Step 6: Reporting and Notifications

[0798] The server creates a detailed report based on the evaluation results and optimized repair plans. This report includes the current state of each piece of infrastructure, its predicted lifespan, safety assessment, and repair priorities and schedules. The generated report is emailed to the user in PDF format. The input is the repair plan and evaluation results, and the output is the generated report.

[0799] Step 7: Notification adjustment by emotion engine

[0800] The server uses an emotion engine to recognize the user's emotions. It detects the user's emotional state based on the user's operation history and voice input, and adjusts the notification content accordingly. For example, if the user is feeling stressed, it simplifies the notification content. The input is the user's operation history and voice data, and the output is the adjusted notification content.

[0801] The above is a detailed description of each processing step.

[0802] 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.

[0803] 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.

[0804] 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.

[0805] [Third embodiment]

[0806] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0807] 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.

[0808] 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).

[0809] 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.

[0810] 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.

[0811] 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).

[0812] 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.

[0813] 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.

[0814] 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.

[0815] 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.

[0816] 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.

[0817] 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."

[0818] ---

[0819] The infrastructure management system of the present invention is for monitoring the status of various infrastructures, predicting their lifespan and assessing their safety, and formulating optimal repair plans. The system includes the following components:

[0820] 1. Terminal means using sensors to collect infrastructure status data

[0821] 2. Server means to store collected data in a database and perform preprocessing

[0822] 3. A server means for applying machine learning models to predict the lifespan of the infrastructure using pre-processed data.

[0823] 4. Server means for evaluating safety based on predicted lifespan data and conducting risk assessments taking disaster scenarios into account.

[0824] 5. Server method for optimizing repair plans based on risk assessment results

[0825] 6. Server means for generating a repair plan as a report and notifying the user

[0826] As a specific embodiment, the operation of each part of the system will be described.

[0827] Data collection

[0828] The devices use sensors to collect infrastructure condition data, including crack severity, corrosion progress, deformation measurements, etc. For example, sensors on a bridge measure crack width and depth every day and send that data to a server.

[0829] Data accumulation and preprocessing

[0830] The server stores the data sent from the device in a database. It adds a timestamp to the data to clarify which part of the infrastructure the data came from. Next, it performs preprocessing on the data. This includes removing duplicate data and imputing missing data from nearby data or by averaging.

[0831] Application of life prediction model

[0832] The server then inputs the preprocessed data into a machine learning model, which uses historical infrastructure data as training data and predicts the remaining lifespan of the infrastructure from current data. For example, data from road sensors can be used to calculate the remaining lifespan of a road.

[0833] Safety evaluation

[0834] The server evaluates the safety of infrastructure based on predicted lifespan data. The evaluation includes simulations that take into account disaster scenarios such as earthquakes and typhoons. As a result of the safety evaluation, each piece of infrastructure is classified as "low risk," "medium risk," or "high risk."

[0835] optimization

[0836] The server optimizes the repair plan based on the risk assessment results. This optimization uses a mathematical optimization algorithm to set priorities while taking into account budget and resource constraints. For example, when creating a repair plan for multiple bridges in City A, the repairs with the highest urgency are given priority.

[0837] Reports and Notifications

[0838] The server creates a report based on the assessment results and optimized repair plans. The report includes the current status, predicted lifespan, safety assessment, and repair priorities and schedules for each piece of infrastructure. The server generates this report in PDF format and emails it to the user, who can review it and take appropriate measures.

[0839] As a concrete example, sensors on Bridge B in City A collect crack data and send it to a server every day. The server stores the data, performs preprocessing, and then uses a machine learning model to calculate the predicted remaining lifespan of Bridge B. Next, the server evaluates Bridge B's safety by considering disaster scenarios and classifies it as "medium risk." Finally, the server prioritizes Bridge B's repairs compared to other infrastructure and includes it in the next year's repair plan. This repair plan is generated as a report and notified to the city's infrastructure management department.

[0840] In this way, the system efficiently manages infrastructure deterioration, assesses natural disaster risks, and develops optimal repair plans.

[0841] The processing flow will be explained below.

[0842] ---

[0843] Step 1:

[0844] The devices collect infrastructure condition data. Specifically, sensors measure crack width and depth, corrosion progress, deformation measurements, etc. For example, sensors installed on bridges are set to collect data daily.

[0845] Step 2:

[0846] The data collected by the device is sent to a server in real time, and the sent data includes not only the measured physical quantities but also metadata to identify which part of the infrastructure the data was obtained from.

[0847] Step 3:

[0848] The server stores the received data in a database. At this time, it performs preprocessing such as detecting and deleting duplicate data and detecting and filling in missing data. For example, if there are missing measurement data, they are filled in with data from adjacent timestamps or the average value.

[0849] Step 4:

[0850] The server inputs the preprocessed data into a machine learning model to predict the lifespan of the infrastructure. The machine learning model has been trained with training data in advance, and calculates the remaining lifespan based on newly input data. For example, if crack data on a bridge is input, the predicted remaining lifespan of the bridge is calculated.

[0851] Step 5:

[0852] The server evaluates the safety of infrastructure based on predicted lifespan data. The evaluation process involves simulations that take into account disaster scenarios such as earthquakes and typhoons. For example, the simulation evaluates the degree of damage a bridge would sustain in an earthquake.

[0853] Step 6:

[0854] Based on the safety assessment results, the server classifies the risk level (low risk, medium risk, high risk) for each piece of infrastructure. This classification is used to determine the priority of repair plans.

[0855] Step 7:

[0856] The server optimizes the repair plan based on the risk assessment results. It applies mathematical optimization algorithms to prioritize repairs, taking into account budget and resource constraints. For example, the highest-risk bridges are given top priority.

[0857] Step 8:

[0858] The server generates a repair plan as a report and notifies the user. The report includes the current status, predicted lifespan, safety assessment, repair priority and schedule for each infrastructure. The server generates the report in PDF format and sends it to the user by email.

[0859] Step 9:

[0860] Users review the reports and take appropriate measures. Based on the reports, they schedule repair work and allocate budgets. For example, they finalize bridge and road repair plans in line with next year's budget plan.

[0861] Through the above steps, the infrastructure management system of the present invention can realize effective condition monitoring, lifespan prediction, safety assessment, and formulation of optimal repair plans.

[0862] Example 1

[0863] 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."

[0864] In managing infrastructure deterioration, it is important to measure deterioration and improve prediction accuracy, to make safety assessments objective, and to develop optimal repair plans. However, current systems lack sufficient data collection and proper data preprocessing, which reduces the accuracy of prediction models and risk assessments. Furthermore, repair plans are inefficient and prone to resource waste.

[0865] 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.

[0866] In this invention, the server includes a terminal means using sensors to collect infrastructure status data, a preprocessing means for storing the collected data in a database and deleting duplicate data and completing missing data, a means for applying a machine learning model to predict the infrastructure's lifespan using the preprocessed data, a means for evaluating safety based on the predicted lifespan data and performing a risk assessment taking disaster scenarios into account, an algorithm means for optimizing a repair plan based on the risk assessment results, and a means for generating a repair plan as a report and notifying the user. This enables precise and efficient monitoring of the infrastructure's deterioration status and the formulation of appropriate measures and repair plans to improve safety.

[0867] "Infrastructure" refers to structures and facilities installed to support public safety and daily life benefits, including bridges, roads, tunnels, and water facilities.

[0868] A "sensor" is a device that measures a physical variable and outputs it in the form of an electrical signal or other data. This data is used to monitor the condition of infrastructure.

[0869] The term "terminal means" refers to a device or system for receiving data collected from a sensor and transmitting the data to a server. Specific examples include a data collection device and a communication module.

[0870] "Preprocessing measures" refer to the rudimentary processing performed on collected data, such as removing duplicate data and filling in missing data.

[0871] A "machine learning model" refers to an algorithm that learns patterns from data and uses them to predict or classify future data. Examples include neural networks and support vector machines.

[0872] "Algorithmic means" refers to procedures or computational methods for solving specific problems, especially mathematical methods used to optimize repair plans.

[0873] "Risk assessment" refers to the process of evaluating potential hazards based on infrastructure life data and disaster scenarios.

[0874] "Report" refers to a documented summary of the system's evaluation results and plans, which are communicated to users and used for decision-making.

[0875] The infrastructure management system of the present invention monitors the status of various infrastructures, predicts their lifespan and safety, and formulates optimal repair plans. The system includes the following components:

[0876] 1. Terminal means using sensors to collect infrastructure status data

[0877] 2. Preprocessing means for storing collected data in a database, deleting duplicate data, and filling in missing data.

[0878] 3. A means to apply machine learning models to predict infrastructure lifespan using pre-processed data

[0879] 4. A means of assessing safety based on predicted lifespan data and conducting risk assessments taking disaster scenarios into account.

[0880] 5. Algorithmic means to optimize repair plans based on risk assessment results

[0881] 6. A means of generating a repair plan as a report and notifying the user

[0882] Data collection

[0883] The devices collect infrastructure condition data using sensors. Examples of sensors include sensors that measure cracks, sensors that monitor corrosion, sensors that detect deformation, etc. For example, sensors installed on a bridge measure the width and depth of cracks every day and send the data to a server.

[0884] Data accumulation and preprocessing

[0885] The server receives the data sent from the devices and stores it in a database (e.g., MySQL, PostgreSQL). The data is stored with a timestamp and includes metadata to clarify which part of the infrastructure it was obtained from. Preprocessing includes removing duplicate data and imputing missing data (e.g., imputing from neighboring data or imputing with the average value).

[0886] Application of life prediction model

[0887] The server then inputs the preprocessed data into a machine learning model (e.g., TensorFlow, scikit-learn). The machine learning model uses historical infrastructure data as training data and predicts the remaining lifespan of the infrastructure from current data. For example, data obtained from road sensors can be used to calculate the remaining lifespan of a road.

[0888] Safety evaluation

[0889] The server evaluates the safety of infrastructure based on predicted lifespan data. This evaluation includes simulations (e.g., FEA software) that take into account disaster scenarios such as earthquakes and typhoons. As a result of the safety evaluation, each piece of infrastructure is classified as "low risk," "medium risk," or "high risk."

[0890] Optimizing repair plans

[0891] The server optimizes repair plans based on the risk assessment results. It uses mathematical optimization algorithms (e.g., linear programming and genetic algorithms) to consider budget and resource constraints. For example, when creating repair plans for multiple bridges, the most urgent repairs are prioritized.

[0892] Report generation and notification

[0893] The server creates a report based on the assessment results and optimized repair plans. The report includes the current status, predicted lifespan, safety assessment, and repair priorities and schedules for each piece of infrastructure. The server generates this report in PDF format and emails it to the user, who can review it and take appropriate measures.

[0894] Specific examples

[0895] As a concrete example, sensors on Bridge B in City A collect crack data and send it to a server every day. The server stores the data, performs preprocessing, and then uses a machine learning model to calculate the predicted remaining lifespan of Bridge B. Next, the server evaluates Bridge B's safety by considering disaster scenarios and classifies it as "medium risk." Finally, the server prioritizes Bridge B's repairs compared to other infrastructure and includes it in the next year's repair plan. This repair plan is generated as a report and notified to the city's infrastructure management department.

[0896] Prompt Sentence Examples

[0897] Below are some examples of specific prompts that can be fed into a generative AI model:

[0898] Based on the crack data collected over the past year by sensors installed on Bridge B in City A, calculate the predicted remaining lifespan of Bridge B and evaluate its safety. Also, based on the evaluation results, optimize the repair plan for the next year and generate a report.

[0899] In this way, the system efficiently monitors the condition of infrastructure, assesses the risk of natural disasters, and develops optimal repair plans.

[0900] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0901] Step 1: Data collection

[0902] The devices use sensors to collect infrastructure condition data, with input data including crack width, depth, corrosion progress, and deformation measurements.

[0903] How it works: Sensors installed on the bridge measure crack width and depth every hour and send the condition data to a server in real time. The output is collected infrastructure condition data.

[0904] Step 2: Data accumulation and preprocessing

[0905] The server receives data sent from the terminal and stores it in a database (e.g., MySQL, PostgreSQL). The input is the raw data sent from the terminal.

[0906] What it does: The server adds a timestamp to the data it receives, along with metadata indicating which part of the infrastructure the data came from. It then removes duplicates and imputes missing data with neighboring data or averages. The output is preprocessed, clean data.

[0907] Step 3: Applying the life prediction model

[0908] The server inputs the preprocessed data into a machine learning model (e.g., TensorFlow, scikit-learn), where the input data is the preprocessed infrastructure state data.

[0909] How it works: The server inputs the preprocessed data into a machine learning model, which uses past learning results to predict the remaining lifespan of infrastructure. For example, data on a bridge is used to calculate the bridge's predicted remaining lifespan. The output is the predicted remaining lifespan data.

[0910] Step 4: Safety assessment

[0911] The server evaluates the safety of the infrastructure based on the predicted remaining life data. The input data is the predicted remaining life data.

[0912] Specific operation: Simulations are performed taking into account disaster scenarios (e.g., earthquakes, typhoons) and safety assessments are carried out. As a result, each piece of infrastructure is classified as "low risk," "medium risk," or "high risk." The output is the risk assessment result.

[0913] Step 5: Optimize repair plans

[0914] The server optimizes the repair plan based on the risk assessment results. The input data is the risk assessment results.

[0915] How it works: Using mathematical optimization algorithms (e.g., linear programming, genetic algorithms), it generates repair plans taking into account budget and resource constraints. For example, when planning repairs for multiple bridges, it prioritizes the repairs with the highest urgency. The output is an optimized repair plan.

[0916] Step 6: Generate reports and notifications

[0917] The server generates a report based on the evaluation results and the optimized repair plan. The input data is the optimized repair plan.

[0918] Specific behavior: Generates a report in PDF format containing the current status, predicted lifespan, safety assessment, and repair priorities and schedules for each piece of infrastructure. The server then emails this report to the user (e.g., the city's infrastructure management department). The user can review the report and take appropriate measures. The output is the generated report and a notification email.

[0919] In this way, the system processes and calculates data at each step, and then executes a series of processes until finally notifying the user.

[0920] (Application example 1)

[0921] 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."

[0922] Conventional infrastructure management systems generally collect data using fixed sensors, making it difficult to collect and analyze data in real time from mobile devices. It is also difficult to efficiently monitor the deterioration of road infrastructure and formulate timely repair plans. This has led to problems such as the progression of infrastructure deterioration and an increased risk of accidents and disasters.

[0923] 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.

[0924] In this invention, the server includes terminal means using sensors to collect infrastructure status data, server means for storing the collected data in a database and preprocessing it, server means for applying a machine learning model to predict the infrastructure's lifespan using the preprocessed data, means for evaluating safety based on the predicted lifespan data and conducting risk assessments taking disaster scenarios into account, means for collecting road status data using sensors mounted on vehicles, means for applying a machine learning model to predict the road's lifespan using the collected data, means for evaluating road safety based on the predicted lifespan data and conducting risk assessments taking disaster scenarios into account, means for optimizing road repair plans based on the risk assessment results, and means for generating a repair plan as a report and notifying the vehicle manager. This enables real-time data collection and analysis by vehicles, which are mobile objects, and enables efficient monitoring of the deterioration state of road infrastructure and effective formulation of repair plans at appropriate times.

[0925] "Infrastructure" refers to the physical structures of social infrastructure such as roads, bridges, tunnels, and dams.

[0926] "Condition data" refers to data that describes the physical condition of infrastructure, and includes, for example, information such as the degree of cracking, the progress of corrosion, and deformation measurements.

[0927] "Sensor" refers to a device used to detect and collect infrastructure condition data, including cameras, LIDAR sensors, vibration sensors, etc.

[0928] "Terminal means" refers to a device that uses sensors to collect infrastructure status data and transmits it to a server.

[0929] "Database" refers to a system for efficiently storing and managing collected data.

[0930] "Preprocessing" is the process of preparing data stored in a database so that it can be analyzed, and includes removing duplicate data and filling in missing data.

[0931] "Server Means" refers to a central processing unit for collecting, storing, pre-processing and analyzing data.

[0932] "Machine learning models" refer to algorithms and methods for predicting future deterioration and lifespan of infrastructure based on past data.

[0933] "Lifespan forecasting" refers to the process for predicting the remaining lifespan of infrastructure.

[0934] "Disaster scenarios" refer to hypothetical scenarios used to assess the impact of natural disasters such as earthquakes and typhoons on infrastructure.

[0935] "Risk assessment" refers to the process of assessing the safety and potential risks of infrastructure based on predicted data.

[0936] "Vehicle-mounted sensors" refers to sensors attached to a vehicle to collect roadway condition data.

[0937] "Repair Plan" means a plan containing a schedule of repairs and maintenance required to prevent deterioration of infrastructure.

[0938] "Report" refers to a written summary of the repair plan and the results of the risk assessment.

[0939] "Administrator" means the person or organization responsible for maintaining the infrastructure.

[0940] An embodiment of this invention is a system for collecting condition data on road infrastructure using sensors installed in automobiles, predicting the lifespan of the infrastructure based on that data, and formulating appropriate repair plans.

[0941] Data collection

[0942] The terminal uses the vehicle's onboard camera and LIDAR sensor to collect real-time data on road cracks, holes, deformations, etc. This allows moving vehicles to efficiently collect large-scale road condition data. For example, the LIDAR sensor scans the road surface for irregularities and detects abnormalities.

[0943] Data accumulation and preprocessing

[0944] The server sends the collected data to a cloud server and stores it in a database. The stored data is time-stamped to identify which road section the data comes from. Pre-processing is then performed, including removing duplicate data and filling in missing data. This pre-processing improves the consistency and accuracy of the data.

[0945] Application of life prediction model

[0946] The server applies a machine learning model to the preprocessed data to predict the remaining lifespan of road infrastructure. This machine learning model learns from past road condition data as training data to improve prediction accuracy. Specifically, the model is built using machine learning libraries such as TensorFlow.

[0947] Safety evaluation

[0948] The server performs safety assessments based on predicted lifespan data, taking into account disaster scenarios such as earthquakes and typhoons. This allows the risk level of each road section to be understood and high-risk sections to be identified. For example, disaster scenarios can be simulated using MATLAB or similar software.

[0949] optimization

[0950] The server then optimizes the road repair plan based on the risk assessment results. This optimization uses a mathematical optimization algorithm to set priorities while taking into account budget and resource constraints. For example, the road sections with the highest urgency are prioritized in the repair plan.

[0951] Reports and Notifications

[0952] The server generates a repair plan as a report and notifies the vehicle manager, which includes the current road condition, predicted lifespan, safety assessment, repair priority and schedule, so that the manager can take appropriate measures.

[0953] Examples of concrete examples and prompts

[0954] For example, while an autonomous vehicle is driving on a highway, its LIDAR sensor will detect cracks in the road and send them to a cloud server in real time. The server will then use the data to optimize highway repair plans and notify the highway manager.

[0955] Example prompt sentence:

[0956] "Identify highway repair needs most with road crack condition data. Evaluate safety and optimize repair plans by considering projected remaining life and disaster scenarios."

[0957] In this way, the present invention enables real-time data collection and analysis from moving vehicles, thereby enabling efficient monitoring of road infrastructure and the formulation of repair plans.

[0958] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0959] Step 1: Data collection

[0960] The device collects road condition data in real time using the car's on-board camera and LIDAR sensor. Specifically, the LIDAR sensor scans the road surface for irregularities and acquires the data. The input is raw data from the sensor, and the output is processed road condition data.

[0961] Step 2: Send data

[0962] The device sends the collected data to the cloud server. The data is time-stamped to identify the location from which it was collected. The input is the status data obtained in the data collection step, and the output is the transmitted data.

[0963] Step 3: Data accumulation and preprocessing

[0964] The server stores the data sent to the cloud in a database. The stored data undergoes preprocessing, such as deleting duplicate data and filling in missing data. Preprocessing improves the consistency and accuracy of the data. The input is the raw data sent, and the output is the preprocessed, clear data.

[0965] Step 4: Applying the life prediction model

[0966] The server applies a machine learning model to the preprocessed data to predict the remaining lifespan of the road. Specifically, it builds a model using a machine learning library such as TensorFlow and inputs data into the model to make predictions. The input is the preprocessed data, and the output is the predicted remaining lifespan data.

[0967] Step 5: Safety Assessment

[0968] The server performs safety assessments based on predicted lifespan data, taking disaster scenarios into account. For example, it uses MATLAB to simulate disaster scenarios such as earthquakes and typhoons and evaluate their impact. The input is lifespan prediction data, and the output is the risk assessment results.

[0969] Step 6: Optimize repair plans

[0970] The server optimizes the repair plan based on the safety assessment results. For optimization, it takes into account resource constraints and uses a mathematical optimization algorithm. For example, it prioritizes the inclusion of high-priority areas in the repair plan. The input is the risk assessment results, and the output is the optimized repair plan.

[0971] Step 7: Reporting and Notifications

[0972] The server generates a report based on the optimized repair plan and notifies the administrator. The report includes the current state, predicted lifespan, safety assessment, repair priority and schedule. The input is the optimized repair plan, and the output is the documented information in the report.

[0973] 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.

[0974] ---

[0975] The infrastructure management system of the present invention monitors the status of various infrastructures, predicts their lifespan, assesses their safety, and formulates optimal repair plans, and further includes an emotion engine that recognizes the emotions of users. The system includes the following components:

[0976] 1. Terminal means using sensors to collect infrastructure status data

[0977] 2. Server means to store collected data in a database and perform preprocessing

[0978] 3. A server means for applying machine learning models to predict the lifespan of the infrastructure using pre-processed data.

[0979] 4. Server means for evaluating safety based on predicted lifespan data and conducting risk assessments taking disaster scenarios into account.

[0980] 5. Server method for optimizing repair plans based on risk assessment results

[0981] 6. Server means for generating a repair plan as a report and notifying the user

[0982] 7. Emotion engine that recognizes user emotions and adjusts notification content

[0983] As a specific embodiment, the operation of each part of the system will be described.

[0984] Data collection

[0985] The devices use sensors to collect infrastructure condition data, including the degree of cracking, corrosion progress, deformation measurements, etc. For example, sensors installed on a bridge collect data daily and send it to a server.

[0986] Data accumulation and preprocessing

[0987] The server stores the data sent from the device in a database. It adds a timestamp to the data to clarify which part of the infrastructure the data came from. Next, it performs preprocessing on the data. This includes removing duplicate data and imputing missing data from nearby data or by averaging.

[0988] Application of life prediction model

[0989] The server then inputs the preprocessed data into a machine learning model to predict the infrastructure's lifespan. The machine learning model has been trained with training data in advance and calculates the remaining lifespan based on newly input data. For example, data obtained from road sensors can be used to calculate the remaining lifespan of a road.

[0990] Safety evaluation

[0991] The server evaluates the safety of infrastructure based on predicted lifespan data. The evaluation includes simulations that take into account disaster scenarios such as earthquakes and typhoons. As a result of the safety evaluation, each piece of infrastructure is classified as "low risk," "medium risk," or "high risk."

[0992] optimization

[0993] The server then optimizes the repair plan based on the risk assessment results. It uses a mathematical optimization algorithm to set priorities, taking into account budget and resource constraints. For example, the bridges with the highest risk receive the highest priority.

[0994] Reports and Notifications

[0995] The server creates a report based on the assessment results and the optimized repair plan. The report includes the current status, predicted lifespan, safety assessment, repair priority and schedule for each infrastructure. The server generates this report in PDF format and sends it to the user by email.

[0996] Emotional Engine Adjustment

[0997] The emotion engine installed on the server recognizes the user's emotions. Emotion recognition utilizes the user's operation history and voice input. For example, if the user is feeling stressed, the emotion engine will simplify the content of the notification. In high-stress situations, detailed technical information will be kept to a minimum, and only important information will be conveyed quickly. If the user is in a calm state, the notification will include detailed technical information.

[0998] As a concrete example, sensors collect crack data on Bridge B in City A and send it to a server every day. The server stores the data, performs preprocessing, and then uses a machine learning model to calculate the predicted remaining lifespan of Bridge B. Next, it evaluates the safety of Bridge B by taking disaster scenarios into account and classifies it as "medium risk." Finally, the server prioritizes the repair of Bridge B compared to other infrastructure and includes it in the repair plan for the following year. This repair plan is generated as a report and notified to the city's infrastructure management department. If a management department employee is feeling stressed, the emotion engine can simplify the notification content and present it in an easy-to-understand format.

[0999] In this way, this system not only efficiently manages infrastructure deterioration, assesses natural disaster risks, and develops optimal repair plans, but also improves work efficiency and comprehension by adjusting notification content according to the user's emotional state.

[1000] The processing flow will be explained below.

[1001] ---

[1002] Step 1:

[1003] The devices collect infrastructure condition data. Specifically, sensors measure crack width and depth, corrosion progress, deformation measurements, etc. For example, sensors installed on bridges are set to collect data daily.

[1004] Step 2:

[1005] The data collected by the device is sent to a server in real time, and the sent data includes not only the measured physical quantities but also metadata to identify which part of the infrastructure the data was obtained from.

[1006] Step 3:

[1007] The server stores the received data in a database. At this time, it performs preprocessing such as detecting and deleting duplicate data and detecting and filling in missing data. For example, if there are missing measurement data, they are filled in with data from adjacent timestamps or the average value.

[1008] Step 4:

[1009] The server inputs the preprocessed data into a machine learning model to predict the infrastructure's lifespan. The machine learning model is trained on the training data in advance and calculates the remaining lifespan based on the newly input data. For example, data obtained from road sensors can be used to calculate the remaining lifespan of a road.

[1010] Step 5:

[1011] The server evaluates the safety of infrastructure based on predicted lifespan data. The evaluation process involves simulations that take into account disaster scenarios such as earthquakes and typhoons. For example, the simulation evaluates the degree of damage a bridge would sustain in an earthquake.

[1012] Step 6:

[1013] Based on the safety assessment results, the server classifies the risk level (low risk, medium risk, high risk) for each piece of infrastructure. This classification is used to determine the priority of repair plans.

[1014] Step 7:

[1015] The server optimizes the repair plan based on the risk assessment results. It applies mathematical optimization algorithms to prioritize repairs, taking into account budget and resource constraints. For example, the highest-risk bridges are given top priority.

[1016] Step 8:

[1017] The server generates a repair plan as a report and notifies the user. The report includes the current status, predicted lifespan, safety assessment, repair priority and schedule for each infrastructure. The server generates the report in PDF format and sends it to the user by email.

[1018] Step 9:

[1019] Users review the reports and take appropriate measures. Based on the reports, they schedule repair work and allocate budgets. For example, they finalize bridge and road repair plans in line with next year's budget plan.

[1020] Step 10:

[1021] The emotion engine recognizes the user's emotions. Emotion recognition utilizes the user's operation history and voice input. For example, if the user is feeling stressed, the emotion engine will simplify the notification content.

[1022] Step 11:

[1023] The server adjusts the notification content based on the results of the emotion engine. In stressful situations, the server reduces the amount of detailed technical information and quickly conveys only the important information. On the other hand, when the user is calm, the server provides notifications that include detailed technical information.

[1024] As a concrete example, sensors collect crack data on Bridge B in City A and send it to a server every day. The server stores the data, performs preprocessing, and then uses a machine learning model to calculate the predicted remaining lifespan of Bridge B. Next, it evaluates the safety of Bridge B by taking disaster scenarios into account and classifies it as "medium risk." Finally, the server prioritizes the repair of Bridge B compared to other infrastructure and includes it in the repair plan for the following year. This repair plan is generated as a report and notified to the city's infrastructure management department. If a management department employee is feeling stressed, the emotion engine can simplify the notification content and present it in an easy-to-understand format.

[1025] In this way, this system not only efficiently manages infrastructure deterioration, assesses natural disaster risks, and develops optimal repair plans, but also improves work efficiency and comprehension by adjusting notification content according to the user's emotional state.

[1026] Example 2

[1027] 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."

[1028] While conventional infrastructure management systems can efficiently monitor infrastructure conditions and perform lifespan predictions and risk assessments, they lack the means to reduce the psychological burden on users. As a result, users tend to feel stressed, which can slow their understanding of information and their ability to respond. The present invention aims to solve this problem.

[1029] 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 a terminal means using sensors to collect infrastructure status data, a server means storing the collected data in a database and performing preprocessing, a server means applying a machine learning model to predict the infrastructure's lifespan using the preprocessed data, a server means evaluating safety based on the predicted lifespan data and performing risk assessment taking disaster scenarios into consideration, a server means optimizing a repair plan based on the risk assessment results, a server means generating a repair plan as a report and notifying the user, and a server means having emotion recognition software for recognizing the user's emotions and adjusting the content of the notification. This not only enables appropriate management of infrastructure deterioration and risks, but also reduces the user's psychological burden and enables them to understand information and respond more quickly.

[1030] "Infrastructure" is a general term for facilities that make up the social infrastructure, such as public transportation, water supply, and electricity.

[1031] "Condition Data" means data that describes the physical and functional condition of infrastructure, including measurements of cracks, corrosion, deformation, etc.

[1032] A "sensor" is a measuring device used to collect infrastructure status data, and examples include strain gauges and vibration sensors.

[1033] A "terminal" is a device that temporarily stores data collected from a sensor and transmits it to a server.

[1034] A "server" is a computer system that receives data sent from a terminal and processes and analyzes it.

[1035] A "database" is a software system or hardware used to store and manage collected data in an organized manner.

[1036] "Preprocessing" refers to the process of cleansing and organizing collected data to make it suitable for analysis.

[1037] A "machine learning model" is a mathematical model that uses algorithms to learn from large amounts of data and make future predictions and classifications.

[1038] "Lifespan prediction" refers to predicting the remaining lifespan of infrastructure, specifically estimating the period until failure or deterioration occurs.

[1039] "Safety assessment" is the process of determining the safety of an infrastructure based on its current and predicted state.

[1040] A "disaster scenario" is a model that simulates the impact on infrastructure in the event of a natural disaster such as an earthquake or typhoon.

[1041] "Risk assessment" is the process of determining the degree of risk based on infrastructure life expectancy predictions and disaster scenarios.

[1042] A "repair plan" is a plan for specific construction and work to prevent and repair deterioration and breakdowns in infrastructure.

[1043] A "report" is a document that summarizes the evaluation results and details of the repair plan.

[1044] "User" means a person who uses the infrastructure management system to analyze data and develop and implement repair plans.

[1045] "Emotion recognition software" is software that analyzes a user's emotional state and adjusts the system's response as needed.

[1046] "Notification" refers to the act of a system conveying information to a user, and examples include email and dashboard display.

[1047] The above are definitions of important words included in the claims.

[1048] The infrastructure management system of the present invention monitors the status of various infrastructures, predicts their lifespan, assesses their safety, and formulates optimal repair plans. Furthermore, it is equipped with an emotion engine that recognizes the user's emotions and can adjust the content of notifications. The system includes the following components:

[1049] Data collection

[1050] The device uses sensors (e.g., interlocking strain gauge sensors) to collect infrastructure condition data. These sensors are installed on bridges, roads, etc., and periodically measure the degree of cracking, the progress of corrosion, deformation measurements, etc. For example, a sensor installed on a bridge collects data every day at 9:00 AM and sends this data to a server.

[1051] Data accumulation and preprocessing

[1052] The server stores the data sent from the device in a database (for example, MySQL). The received data is assigned metadata such as time information and sensor location information. Next, the data is preprocessed. This preprocessing includes removing duplicate data and filling in missing data (by guessing from nearby data or by filling in the average).

[1053] Lifespan Prediction

[1054] The server uses the preprocessed data to apply a machine learning model (e.g., a TensorFlow regression model) to predict the infrastructure's lifespan. This model is trained on a large amount of past data and predicts the remaining lifespan based on newly input data. For example, data obtained from road sensors is used to calculate the remaining lifespan of the road.

[1055] Safety evaluation

[1056] Servers undergo a safety assessment based on predicted lifespan data. This process uses simulation tools that take into account disaster scenarios (e.g., earthquakes and typhoons). As a result of the assessment, each piece of infrastructure is classified as "low risk," "medium risk," or "high risk."

[1057] Optimizing repair plans

[1058] The server optimizes the repair plan based on the risk assessment results. This optimization process uses linear programming to set priorities while taking into account budget and resource constraints. For example, bridges with the highest risk are given priority.

[1059] Reporting and Notifications

[1060] The server generates a report based on the assessment results and the optimized repair plan. This report includes the current status, predicted lifespan, safety assessment, repair priority and schedule for each infrastructure. The generated report is created in PDF format and sent to the user.

[1061] Adjusting notification content with an emotion engine

[1062] The emotion engine (emotion recognition software, for example) installed on the server analyzes the user's emotions. It determines the user's stress level based on the user's operation history and voice input, and adjusts the notification content as necessary. For example, if the user is feeling stressed, a concise notification will be provided. On the other hand, if the user is relaxed, a notification including detailed technical information will be provided.

[1063] Prompt Sentence Examples

[1064] Based on the crack data for Bridge B in City A, calculate the bridge's predicted remaining lifespan, conduct a safety assessment taking into account disaster scenarios, and classify it as a medium risk.

[1065] Such prompts are used by the system to accurately understand the requested task and to carry it out appropriately.

[1066] The above is a specific embodiment of the infrastructure management system of the present invention. This system not only efficiently manages infrastructure deterioration and assesses the risk of natural disasters, but also enables the adjustment of notification content according to the user's emotional state, thereby improving work efficiency and comprehension.

[1067] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1068] Step 1: Data collection

[1069] The device uses sensors to collect infrastructure condition data. Specifically, interlocking strain gauge sensors are installed on bridges and roads, and data is collected every day at 9:00 a.m. The data collected by the sensors includes the degree of cracks, the progress of corrosion, and deformation measurements. The collected data is temporarily stored inside the device and then sent to a server.

[1070] Input: Sensor measurement data (cracks, corrosion, deformation)

[1071] Output: Sensor data temporarily stored on the device

[1072] Specific behavior:

[1073] The sensor activates and acquires data

[1074] Temporarily save acquired data on the device

[1075] The device sends data to the server

[1076] Step 2: Data accumulation and preprocessing

[1077] The server stores the data sent from the device in a database (MySQL). The stored data is supplemented with metadata such as the acquisition date and time and the sensor's location information. The data is then preprocessed. This includes deleting duplicate data and filling in missing data by guessing from nearby data or by filling in the average value.

[1078] Input: Sensor data sent from the device

[1079] Output: Preprocessed data

[1080] Specific behavior:

[1081] Store data in a database

[1082] Delete duplicate data

[1083] Imputing missing data

[1084] Step 3: Lifetime prediction

[1085] The server uses the preprocessed data to apply a machine learning model (TensorFlow regression model) to predict the remaining lifespan of the infrastructure. This model is trained on a large amount of past data and predicts the remaining lifespan by inputting new data. For example, data obtained from road sensors is used to calculate the remaining lifespan of the road.

[1086] Input: Preprocessed data

[1087] Output: Estimated lifespan of infrastructure

[1088] Specific behavior:

[1089] Preprocessed data is fed into a machine learning model

[1090] The machine learning model begins processing

[1091] Predict remaining life and store the results in a database

[1092] Step 4: Safety assessment

[1093] Servers undergo a safety assessment based on predicted lifespan data. This process uses a simulation tool (specifically SimScale) that takes into account disaster scenarios such as earthquakes and typhoons. As a result of the safety assessment, each piece of infrastructure is classified as "low risk," "medium risk," or "high risk."

[1094] Input: predicted lifespan data, disaster scenarios

[1095] Output: Risk assessment result (low risk, medium risk, high risk)

[1096] Specific behavior:

[1097] Conduct disaster scenario simulations

[1098] Risk assessment based on predicted lifespan data

[1099] Classified risk assessment results are stored in a database

[1100] Step 5: Optimize repair plans

[1101] The server then optimizes the repair plan based on the risk assessment results. This optimization process uses linear programming to set priorities while taking into account budget and resource constraints. For example, the repair of bridges with the highest risk is prioritized.

[1102] Inputs: Risk assessment results, budget data, resource information

[1103] Output: Optimized repair plan

[1104] Specific behavior:

[1105] Input risk assessment results and budget data into a linear planning tool

[1106] Optimize repair plans

[1107] Repair plans stored in a database

[1108] Step 6: Reporting and Notifications

[1109] The server generates a report based on the assessment results and the optimized repair plan. This report includes the current status, predicted lifespan, safety assessment, repair priority and schedule for each infrastructure. The generated report is created in PDF format and sent to the user.

[1110] Input: Evaluation results, optimized repair plan

[1111] Output: Generated report (PDF format)

[1112] Specific behavior:

[1113] Input the assessment results and repair plan into the report generation tool

[1114] Generate reports in PDF format

[1115] Email a PDF to users

[1116] Step 7: Adjusting notification content with the emotion engine

[1117] The emotion engine (emotion recognition software, for example) installed on the server analyzes the user's emotions. It determines the user's stress level based on the user's operation history and voice input, and adjusts the notification content as necessary. For example, if the user is feeling stressed, the notification content will be concise. If the user is relaxed, the notification will include detailed technical information.

[1118] Input: User operation history, voice data

[1119] Output: Adjusted notification content

[1120] Specific behavior:

[1121] Emotion engine analyzes operation history and voice data

[1122] Determine your stress level

[1123] Adjust the notification content and send it to the user

[1124] The above is a detailed description of the specific flow and operation of each processing step of this system.

[1125] (Application example 2)

[1126] 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."

[1127] Modern infrastructure is aging, making regular monitoring and maintenance essential. However, current systems require a lot of effort to monitor the status of infrastructure, making it difficult to develop efficient maintenance plans. In addition, notification methods that do not take into account the user's emotional state can cause stress to users and result in reduced maintenance efficiency. It is necessary to solve these problems and achieve efficient and effective infrastructure management.

[1128] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes terminal means using sensors to collect infrastructure status data, server means for storing the collected data in a database and performing preprocessing, server means for applying a machine learning model to predict the infrastructure's lifespan using the preprocessed data, server means for evaluating safety based on the predicted lifespan data and performing risk assessment taking disaster scenarios into account, server means for optimizing a repair plan based on the risk assessment results, server means for generating a repair plan as a report and notifying the user, and means having an emotion engine that recognizes the user's emotions and adjusts the notification content. This not only makes it possible to efficiently manage infrastructure deterioration, evaluate the risk of natural disasters, and formulate an optimal repair plan, but also to improve work efficiency and comprehension by adjusting the notification content according to the user's emotional state.

[1129] "Infrastructure" is a general term for the structures and facilities that form the foundation for supporting transportation and public services.

[1130] "Status Data" refers to information collected by sensors that indicates the current state of the infrastructure.

[1131] "Sensor" means a device that measures a physical condition (e.g., crack severity, corrosion progression, deformation measurement, etc.).

[1132] "Terminal means" refers to a device or system that uses sensors to collect infrastructure status data and transmits the data to a server.

[1133] "Database" refers to a computer system for systematically storing and managing collected infrastructure status data.

[1134] "Preprocessing" refers to the preliminary processing of collected data to make it easier to analyze.

[1135] "Server Means" refers to a computer system for processing, storing, predicting and evaluating data.

[1136] A "machine learning model" refers to an algorithm or its implementation that learns patterns from accumulated data and makes predictions based on new data.

[1137] "Predicting lifespan" means estimating the remaining lifespan of an infrastructure based on its current condition data.

[1138] "Evaluating safety" refers to determining the safety of infrastructure based on predicted lifespan data.

[1139] "Risk assessment" means analyzing and evaluating the risk to infrastructure by considering disaster scenarios.

[1140] "Optimizing repair planning" refers to the process of determining the optimal sequence and method of infrastructure repairs based on available resources and budget.

[1141] A "report" refers to a document that summarizes information such as evaluation results and repair plans.

[1142] "Emotion Engine" means an algorithm or software that recognizes a user's emotional state and adjusts notification content accordingly.

[1143] "Notifying the user" refers to transmitting information about the evaluation results and repair plans to the user in an appropriate format.

[1144] This invention relates to a system for efficiently managing infrastructure deterioration, assessing natural disaster risks, and formulating optimal repair plans. Furthermore, it has the function of adjusting notification content according to the user's emotional state.

[1145] System Overview

[1146] The system consists of the following main components:

[1147] 1. Terminal means using sensors to collect infrastructure status data

[1148] 2. Server means to store collected data in a database and perform preprocessing

[1149] 3. A server means for applying machine learning models to predict the lifespan of the infrastructure using pre-processed data.

[1150] 4. Server means for evaluating safety based on predicted lifespan data and conducting risk assessments taking disaster scenarios into account.

[1151] 5. Server method for optimizing repair plans based on risk assessment results

[1152] 6. Server means for generating a repair plan as a report and notifying the user

[1153] 7. A means with an emotion engine that recognizes user emotions and adjusts notification content

[1154] Detailed Description

[1155] Data collection

[1156] The terminal means collects infrastructure status data using various sensors. The sensors acquire data such as the degree of cracking, the progress of corrosion, and deformation measurements. For example, sensors installed on a bridge collect data daily and send the data to a server.

[1157] Data accumulation and preprocessing

[1158] The server stores the data sent from the device in a database. It adds a timestamp to the data to clarify which part of the infrastructure the data came from. Next, it performs preprocessing on the data. This includes removing duplicate data and imputing missing data from nearby data or by averaging.

[1159] Application of life prediction model

[1160] The server inputs the preprocessed data into a machine learning model to predict the lifespan of the infrastructure. The machine learning model has been trained with training data in advance and calculates the remaining lifespan based on newly input data. For example, data obtained from road sensors can be used to calculate the remaining lifespan of a road.

[1161] Safety evaluation

[1162] The server evaluates the safety of infrastructure based on predicted lifespan data. The evaluation includes simulations that take into account disaster scenarios such as earthquakes and typhoons. As a result of the safety evaluation, each piece of infrastructure is classified as "low risk," "medium risk," or "high risk."

[1163] optimization

[1164] The server then optimizes the repair plan based on the risk assessment results. It uses a mathematical optimization algorithm to set priorities, taking into account budget and resource constraints. For example, the bridges with the highest risk receive the highest priority.

[1165] Reports and Notifications

[1166] The server creates a report based on the assessment results and the optimized repair plan. The report includes the current status, predicted lifespan, safety assessment, repair priority and schedule for each infrastructure. The server generates this report in PDF format and sends it to the user by email.

[1167] Emotional Engine Adjustment

[1168] The emotion engine installed on the server recognizes the user's emotions. Emotion recognition utilizes the user's operation history and voice input. For example, if the user is feeling stressed, the emotion engine will simplify the content of the notification. In high-stress situations, detailed technical information will be kept to a minimum, and only important information will be conveyed quickly. If the user is in a calm state, the notification will include detailed technical information.

[1169] Specific examples

[1170] For example, consider a situation where a sensor on Line A in a factory collects data and predicts that the remaining lifespan is less than 50% after 30 days. The safety assessment results are classified as "medium risk" and a repair plan is scheduled for the first week. The emotion engine recognizes the user's stress and sends a simplified notification.

[1171] An example of a prompt for a generative AI model is:

[1172] "Generate a Python program that collects data from sensors installed on factory line A, predicts lifespan, evaluates safety, and optimizes repair plans. Also, include an emotion engine function that simplifies notifications when the user is stressed."

[1173] The above is an embodiment of the present invention.

[1174] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1175] Step 1: Data collection

[1176] The terminal collects infrastructure condition data using various sensors. The sensors acquire data such as the degree of cracks, the progress of corrosion, and deformation measurements. The collected data is temporarily stored on the terminal with a timestamp. The input from the terminal is sensor data, and the output is condition data ready to be preprocessed.

[1177] Step 2: Data accumulation and preprocessing

[1178] The server receives data sent from the terminal and stores it in a database. When storing the data, it adds a timestamp and the origin of the data (which infrastructure and which part it was obtained from). Next, the server performs preprocessing such as deleting duplicate data and filling in missing data. The input is the collected raw data, and the output is the preprocessed, clean data.

[1179] Step 3: Applying the life prediction model

[1180] The server inputs the preprocessed data into a machine learning model to predict the remaining lifespan of the infrastructure. The machine learning model is pre-trained and calculates the remaining lifespan based on the newly preprocessed data. The input is the preprocessed data, and the output is the predicted lifespan data.

[1181] Step 4: Safety assessment

[1182] The server performs simulations that take disaster scenarios into account based on predicted lifespan data and evaluates safety. It classifies the risk level of the infrastructure into "low risk," "medium risk," and "high risk." The input is lifespan data and disaster scenario information, and the output is the results of the safety evaluation.

[1183] Step 5: Optimize repair plans

[1184] The server uses a mathematical optimization algorithm to optimize the repair plan based on the safety assessment results. This includes a process for setting priorities while taking into account budget and resource constraints. The inputs are the safety assessment results and resource information, and the output is an optimized repair plan.

[1185] Step 6: Reporting and Notifications

[1186] The server creates a detailed report based on the evaluation results and optimized repair plans. This report includes the current state of each piece of infrastructure, its predicted lifespan, safety assessment, and repair priorities and schedules. The generated report is emailed to the user in PDF format. The input is the repair plan and evaluation results, and the output is the generated report.

[1187] Step 7: Notification adjustment by emotion engine

[1188] The server uses an emotion engine to recognize the user's emotions. It detects the user's emotional state based on the user's operation history and voice input, and adjusts the notification content accordingly. For example, if the user is feeling stressed, it simplifies the notification content. The input is the user's operation history and voice data, and the output is the adjusted notification content.

[1189] The above is a detailed description of each processing step.

[1190] 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.

[1191] 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.

[1192] 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.

[1193] [Fourth embodiment]

[1194] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1195] 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.

[1196] 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).

[1197] 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.

[1198] 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.

[1199] 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).

[1200] 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.

[1201] 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.

[1202] 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.

[1203] 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.

[1204] 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.

[1205] 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.

[1206] 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."

[1207] ---

[1208] The infrastructure management system of the present invention is for monitoring the status of various infrastructures, predicting their lifespan and assessing their safety, and formulating optimal repair plans. The system includes the following components:

[1209] 1. Terminal means using sensors to collect infrastructure status data

[1210] 2. Server means to store collected data in a database and perform preprocessing

[1211] 3. A server means for applying machine learning models to predict the lifespan of the infrastructure using pre-processed data.

[1212] 4. Server means for evaluating safety based on predicted lifespan data and conducting risk assessments taking disaster scenarios into account.

[1213] 5. Server method for optimizing repair plans based on risk assessment results

[1214] 6. Server means for generating a repair plan as a report and notifying the user

[1215] As a specific embodiment, the operation of each part of the system will be described.

[1216] Data collection

[1217] The devices use sensors to collect infrastructure condition data, including crack severity, corrosion progress, deformation measurements, etc. For example, sensors on a bridge measure crack width and depth every day and send that data to a server.

[1218] Data accumulation and preprocessing

[1219] The server stores the data sent from the device in a database. It adds a timestamp to the data to clarify which part of the infrastructure the data came from. Next, it performs preprocessing on the data. This includes removing duplicate data and imputing missing data from nearby data or by averaging.

[1220] Application of life prediction model

[1221] The server then inputs the preprocessed data into a machine learning model, which uses historical infrastructure data as training data and predicts the remaining lifespan of the infrastructure from current data. For example, data from road sensors can be used to calculate the remaining lifespan of a road.

[1222] Safety evaluation

[1223] The server evaluates the safety of infrastructure based on predicted lifespan data. The evaluation includes simulations that take into account disaster scenarios such as earthquakes and typhoons. As a result of the safety evaluation, each piece of infrastructure is classified as "low risk," "medium risk," or "high risk."

[1224] optimization

[1225] The server optimizes the repair plan based on the risk assessment results. This optimization uses a mathematical optimization algorithm to set priorities while taking into account budget and resource constraints. For example, when creating a repair plan for multiple bridges in City A, the repairs with the highest urgency are given priority.

[1226] Reports and Notifications

[1227] The server creates a report based on the assessment results and optimized repair plans. The report includes the current status, predicted lifespan, safety assessment, and repair priorities and schedules for each piece of infrastructure. The server generates this report in PDF format and emails it to the user, who can review it and take appropriate measures.

[1228] As a concrete example, sensors on Bridge B in City A collect crack data and send it to a server every day. The server stores the data, performs preprocessing, and then uses a machine learning model to calculate the predicted remaining lifespan of Bridge B. Next, the server evaluates Bridge B's safety by considering disaster scenarios and classifies it as "medium risk." Finally, the server prioritizes Bridge B's repairs compared to other infrastructure and includes it in the next year's repair plan. This repair plan is generated as a report and notified to the city's infrastructure management department.

[1229] In this way, the system efficiently manages infrastructure deterioration, assesses natural disaster risks, and develops optimal repair plans.

[1230] The processing flow will be explained below.

[1231] ---

[1232] Step 1:

[1233] The devices collect infrastructure condition data. Specifically, sensors measure crack width and depth, corrosion progress, deformation measurements, etc. For example, sensors installed on bridges are set to collect data daily.

[1234] Step 2:

[1235] The data collected by the device is sent to a server in real time, and the sent data includes not only the measured physical quantities but also metadata to identify which part of the infrastructure the data was obtained from.

[1236] Step 3:

[1237] The server stores the received data in a database. At this time, it performs preprocessing such as detecting and deleting duplicate data and detecting and filling in missing data. For example, if there are missing measurement data, they are filled in with data from adjacent timestamps or the average value.

[1238] Step 4:

[1239] The server inputs the preprocessed data into a machine learning model to predict the lifespan of the infrastructure. The machine learning model has been trained with training data in advance, and calculates the remaining lifespan based on newly input data. For example, if crack data on a bridge is input, the predicted remaining lifespan of the bridge is calculated.

[1240] Step 5:

[1241] The server evaluates the safety of infrastructure based on predicted lifespan data. The evaluation process involves simulations that take into account disaster scenarios such as earthquakes and typhoons. For example, the simulation evaluates the degree of damage a bridge would sustain in an earthquake.

[1242] Step 6:

[1243] Based on the safety assessment results, the server classifies the risk level (low risk, medium risk, high risk) for each piece of infrastructure. This classification is used to determine the priority of repair plans.

[1244] Step 7:

[1245] The server optimizes the repair plan based on the risk assessment results. It applies mathematical optimization algorithms to prioritize repairs, taking into account budget and resource constraints. For example, the highest-risk bridges are given top priority.

[1246] Step 8:

[1247] The server generates a repair plan as a report and notifies the user. The report includes the current status, predicted lifespan, safety assessment, repair priority and schedule for each infrastructure. The server generates the report in PDF format and sends it to the user by email.

[1248] Step 9:

[1249] Users review the reports and take appropriate measures. Based on the reports, they schedule repair work and allocate budgets. For example, they finalize bridge and road repair plans in line with next year's budget plan.

[1250] Through the above steps, the infrastructure management system of the present invention can realize effective condition monitoring, lifespan prediction, safety assessment, and formulation of optimal repair plans.

[1251] Example 1

[1252] 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."

[1253] In managing infrastructure deterioration, it is important to measure deterioration and improve prediction accuracy, to make safety assessments objective, and to develop optimal repair plans. However, current systems lack sufficient data collection and proper data preprocessing, which reduces the accuracy of prediction models and risk assessments. Furthermore, repair plans are inefficient and prone to resource waste.

[1254] 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.

[1255] In this invention, the server includes a terminal means using sensors to collect infrastructure status data, a preprocessing means for storing the collected data in a database and deleting duplicate data and completing missing data, a means for applying a machine learning model to predict the infrastructure's lifespan using the preprocessed data, a means for evaluating safety based on the predicted lifespan data and performing a risk assessment taking disaster scenarios into account, an algorithm means for optimizing a repair plan based on the risk assessment results, and a means for generating a repair plan as a report and notifying the user. This enables precise and efficient monitoring of the infrastructure's deterioration status and the formulation of appropriate measures and repair plans to improve safety.

[1256] "Infrastructure" refers to structures and facilities installed to support public safety and daily life benefits, including bridges, roads, tunnels, and water facilities.

[1257] A "sensor" is a device that measures a physical variable and outputs it in the form of an electrical signal or other data. This data is used to monitor the condition of infrastructure.

[1258] The term "terminal means" refers to a device or system for receiving data collected from a sensor and transmitting the data to a server. Specific examples include a data collection device and a communication module.

[1259] "Preprocessing measures" refer to the rudimentary processing performed on collected data, such as removing duplicate data and filling in missing data.

[1260] A "machine learning model" refers to an algorithm that learns patterns from data and uses them to predict or classify future data. Examples include neural networks and support vector machines.

[1261] "Algorithmic means" refers to procedures or computational methods for solving specific problems, especially mathematical methods used to optimize repair plans.

[1262] "Risk assessment" refers to the process of evaluating potential hazards based on infrastructure life data and disaster scenarios.

[1263] "Report" refers to a documented summary of the system's evaluation results and plans, which are communicated to users and used for decision-making.

[1264] The infrastructure management system of the present invention monitors the status of various infrastructures, predicts their lifespan and safety, and formulates optimal repair plans. The system includes the following components:

[1265] 1. Terminal means using sensors to collect infrastructure status data

[1266] 2. Preprocessing means for storing collected data in a database, deleting duplicate data, and filling in missing data.

[1267] 3. A means to apply machine learning models to predict infrastructure lifespan using pre-processed data

[1268] 4. A means of assessing safety based on predicted lifespan data and conducting risk assessments taking disaster scenarios into account.

[1269] 5. Algorithmic means to optimize repair plans based on risk assessment results

[1270] 6. A means of generating a repair plan as a report and notifying the user

[1271] Data collection

[1272] The devices collect infrastructure condition data using sensors. Examples of sensors include sensors that measure cracks, sensors that monitor corrosion, sensors that detect deformation, etc. For example, sensors installed on a bridge measure the width and depth of cracks every day and send the data to a server.

[1273] Data accumulation and preprocessing

[1274] The server receives the data sent from the devices and stores it in a database (e.g., MySQL, PostgreSQL). The data is stored with a timestamp and includes metadata to clarify which part of the infrastructure it was obtained from. Preprocessing includes removing duplicate data and imputing missing data (e.g., imputing from neighboring data or imputing with the average value).

[1275] Application of life prediction model

[1276] The server then inputs the preprocessed data into a machine learning model (e.g., TensorFlow, scikit-learn). The machine learning model uses historical infrastructure data as training data and predicts the remaining lifespan of the infrastructure from current data. For example, data obtained from road sensors can be used to calculate the remaining lifespan of a road.

[1277] Safety evaluation

[1278] The server evaluates the safety of infrastructure based on predicted lifespan data. This evaluation includes simulations (e.g., FEA software) that take into account disaster scenarios such as earthquakes and typhoons. As a result of the safety evaluation, each piece of infrastructure is classified as "low risk," "medium risk," or "high risk."

[1279] Optimizing repair plans

[1280] The server optimizes repair plans based on the risk assessment results. It uses mathematical optimization algorithms (e.g., linear programming and genetic algorithms) to consider budget and resource constraints. For example, when creating repair plans for multiple bridges, the most urgent repairs are prioritized.

[1281] Report generation and notification

[1282] The server creates a report based on the assessment results and optimized repair plans. The report includes the current status, predicted lifespan, safety assessment, and repair priorities and schedules for each piece of infrastructure. The server generates this report in PDF format and emails it to the user, who can review it and take appropriate measures.

[1283] Specific examples

[1284] As a concrete example, sensors on Bridge B in City A collect crack data and send it to a server every day. The server stores the data, performs preprocessing, and then uses a machine learning model to calculate the predicted remaining lifespan of Bridge B. Next, the server evaluates Bridge B's safety by considering disaster scenarios and classifies it as "medium risk." Finally, the server prioritizes Bridge B's repairs compared to other infrastructure and includes it in the next year's repair plan. This repair plan is generated as a report and notified to the city's infrastructure management department.

[1285] Prompt Sentence Examples

[1286] Below are some examples of specific prompts that can be fed into a generative AI model:

[1287] Based on the crack data collected over the past year by sensors installed on Bridge B in City A, calculate the predicted remaining lifespan of Bridge B and evaluate its safety. Also, based on the evaluation results, optimize the repair plan for the next year and generate a report.

[1288] In this way, the system efficiently monitors the condition of infrastructure, assesses the risk of natural disasters, and develops optimal repair plans.

[1289] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1290] Step 1: Data collection

[1291] The devices use sensors to collect infrastructure condition data, with input data including crack width, depth, corrosion progress, and deformation measurements.

[1292] How it works: Sensors installed on the bridge measure crack width and depth every hour and send the condition data to a server in real time. The output is collected infrastructure condition data.

[1293] Step 2: Data accumulation and preprocessing

[1294] The server receives data sent from the terminal and stores it in a database (e.g., MySQL, PostgreSQL). The input is the raw data sent from the terminal.

[1295] What it does: The server adds a timestamp to the data it receives, along with metadata indicating which part of the infrastructure the data came from. It then removes duplicates and imputes missing data with neighboring data or averages. The output is preprocessed, clean data.

[1296] Step 3: Applying the life prediction model

[1297] The server inputs the preprocessed data into a machine learning model (e.g., TensorFlow, scikit-learn), where the input data is the preprocessed infrastructure state data.

[1298] How it works: The server inputs the preprocessed data into a machine learning model, which uses past learning results to predict the remaining lifespan of infrastructure. For example, data on a bridge is used to calculate the bridge's predicted remaining lifespan. The output is the predicted remaining lifespan data.

[1299] Step 4: Safety assessment

[1300] The server evaluates the safety of the infrastructure based on the predicted remaining life data. The input data is the predicted remaining life data.

[1301] Specific operation: Simulations are performed taking into account disaster scenarios (e.g., earthquakes, typhoons) and safety assessments are carried out. As a result, each piece of infrastructure is classified as "low risk," "medium risk," or "high risk." The output is the risk assessment result.

[1302] Step 5: Optimize repair plans

[1303] The server optimizes the repair plan based on the risk assessment results. The input data is the risk assessment results.

[1304] How it works: Using mathematical optimization algorithms (e.g., linear programming, genetic algorithms), it generates repair plans taking into account budget and resource constraints. For example, when planning repairs for multiple bridges, it prioritizes the repairs with the highest urgency. The output is an optimized repair plan.

[1305] Step 6: Generate reports and notifications

[1306] The server generates a report based on the evaluation results and the optimized repair plan. The input data is the optimized repair plan.

[1307] Specific behavior: Generates a report in PDF format containing the current status, predicted lifespan, safety assessment, and repair priorities and schedules for each piece of infrastructure. The server then emails this report to the user (e.g., the city's infrastructure management department). The user can review the report and take appropriate measures. The output is the generated report and a notification email.

[1308] In this way, the system processes and calculates data at each step, and then executes a series of processes until finally notifying the user.

[1309] (Application example 1)

[1310] 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."

[1311] Conventional infrastructure management systems generally collect data using fixed sensors, making it difficult to collect and analyze data in real time from mobile devices. It is also difficult to efficiently monitor the deterioration of road infrastructure and formulate timely repair plans. This has led to problems such as the progression of infrastructure deterioration and an increased risk of accidents and disasters.

[1312] 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.

[1313] In this invention, the server includes terminal means using sensors to collect infrastructure status data, server means for storing the collected data in a database and preprocessing it, server means for applying a machine learning model to predict the infrastructure's lifespan using the preprocessed data, means for evaluating safety based on the predicted lifespan data and conducting risk assessments taking disaster scenarios into account, means for collecting road status data using sensors mounted on vehicles, means for applying a machine learning model to predict the road's lifespan using the collected data, means for evaluating road safety based on the predicted lifespan data and conducting risk assessments taking disaster scenarios into account, means for optimizing road repair plans based on the risk assessment results, and means for generating a repair plan as a report and notifying the vehicle manager. This enables real-time data collection and analysis by vehicles, which are mobile objects, and enables efficient monitoring of the deterioration state of road infrastructure and effective formulation of repair plans at appropriate times.

[1314] "Infrastructure" refers to the physical structures of social infrastructure such as roads, bridges, tunnels, and dams.

[1315] "Condition data" refers to data that describes the physical condition of infrastructure, and includes, for example, information such as the degree of cracking, the progress of corrosion, and deformation measurements.

[1316] "Sensor" refers to a device used to detect and collect infrastructure condition data, including cameras, LIDAR sensors, vibration sensors, etc.

[1317] "Terminal means" refers to a device that uses sensors to collect infrastructure status data and transmits it to a server.

[1318] "Database" refers to a system for efficiently storing and managing collected data.

[1319] "Preprocessing" is the process of preparing data stored in a database so that it can be analyzed, and includes removing duplicate data and filling in missing data.

[1320] "Server Means" refers to a central processing unit for collecting, storing, pre-processing and analyzing data.

[1321] "Machine learning models" refer to algorithms and methods for predicting future deterioration and lifespan of infrastructure based on past data.

[1322] "Lifespan forecasting" refers to the process for predicting the remaining lifespan of infrastructure.

[1323] "Disaster scenarios" refer to hypothetical scenarios used to assess the impact of natural disasters such as earthquakes and typhoons on infrastructure.

[1324] "Risk assessment" refers to the process of assessing the safety and potential risks of infrastructure based on predicted data.

[1325] "Vehicle-mounted sensors" refers to sensors attached to a vehicle to collect roadway condition data.

[1326] "Repair Plan" means a plan containing a schedule of repairs and maintenance required to prevent deterioration of infrastructure.

[1327] "Report" refers to a written summary of the repair plan and the results of the risk assessment.

[1328] "Administrator" means the person or organization responsible for maintaining the infrastructure.

[1329] An embodiment of this invention is a system for collecting condition data on road infrastructure using sensors installed in automobiles, predicting the lifespan of the infrastructure based on that data, and formulating appropriate repair plans.

[1330] Data collection

[1331] The terminal uses the vehicle's onboard camera and LIDAR sensor to collect real-time data on road cracks, holes, deformations, etc. This allows moving vehicles to efficiently collect large-scale road condition data. For example, the LIDAR sensor scans the road surface for irregularities and detects abnormalities.

[1332] Data accumulation and preprocessing

[1333] The server sends the collected data to a cloud server and stores it in a database. The stored data is time-stamped to identify which road section the data comes from. Pre-processing is then performed, including removing duplicate data and filling in missing data. This pre-processing improves the consistency and accuracy of the data.

[1334] Application of life prediction model

[1335] The server applies a machine learning model to the preprocessed data to predict the remaining lifespan of road infrastructure. This machine learning model learns from past road condition data as training data to improve prediction accuracy. Specifically, the model is built using machine learning libraries such as TensorFlow.

[1336] Safety evaluation

[1337] The server performs safety assessments based on predicted lifespan data, taking into account disaster scenarios such as earthquakes and typhoons. This allows the risk level of each road section to be understood and high-risk sections to be identified. For example, disaster scenarios can be simulated using MATLAB or similar software.

[1338] optimization

[1339] The server then optimizes the road repair plan based on the risk assessment results. This optimization uses a mathematical optimization algorithm to set priorities while taking into account budget and resource constraints. For example, the road sections with the highest urgency are prioritized in the repair plan.

[1340] Reports and Notifications

[1341] The server generates a repair plan as a report and notifies the vehicle manager, which includes the current road condition, predicted lifespan, safety assessment, repair priority and schedule, so that the manager can take appropriate measures.

[1342] Examples of concrete examples and prompts

[1343] For example, while an autonomous vehicle is driving on a highway, its LIDAR sensor will detect cracks in the road and send them to a cloud server in real time. The server will then use the data to optimize highway repair plans and notify the highway manager.

[1344] Example prompt sentence:

[1345] "Identify highway repair needs most with road crack condition data. Evaluate safety and optimize repair plans by considering projected remaining life and disaster scenarios."

[1346] In this way, the present invention enables real-time data collection and analysis from moving vehicles, thereby enabling efficient monitoring of road infrastructure and the formulation of repair plans.

[1347] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1348] Step 1: Data collection

[1349] The device collects road condition data in real time using the car's on-board camera and LIDAR sensor. Specifically, the LIDAR sensor scans the road surface for irregularities and acquires the data. The input is raw data from the sensor, and the output is processed road condition data.

[1350] Step 2: Send data

[1351] The device sends the collected data to the cloud server. The data is time-stamped to identify the location from which it was collected. The input is the status data obtained in the data collection step, and the output is the transmitted data.

[1352] Step 3: Data accumulation and preprocessing

[1353] The server stores the data sent to the cloud in a database. The stored data undergoes preprocessing, such as deleting duplicate data and filling in missing data. Preprocessing improves the consistency and accuracy of the data. The input is the raw data sent, and the output is the preprocessed, clear data.

[1354] Step 4: Applying the life prediction model

[1355] The server applies a machine learning model to the preprocessed data to predict the remaining lifespan of the road. Specifically, it builds a model using a machine learning library such as TensorFlow and inputs data into the model to make predictions. The input is the preprocessed data, and the output is the predicted remaining lifespan data.

[1356] Step 5: Safety Assessment

[1357] The server performs safety assessments based on predicted lifespan data, taking disaster scenarios into account. For example, it uses MATLAB to simulate disaster scenarios such as earthquakes and typhoons and evaluate their impact. The input is lifespan prediction data, and the output is the risk assessment results.

[1358] Step 6: Optimize repair plans

[1359] The server optimizes the repair plan based on the safety assessment results. For optimization, it takes into account resource constraints and uses a mathematical optimization algorithm. For example, it prioritizes the inclusion of high-priority areas in the repair plan. The input is the risk assessment results, and the output is the optimized repair plan.

[1360] Step 7: Reporting and Notifications

[1361] The server generates a report based on the optimized repair plan and notifies the administrator. The report includes the current state, predicted lifespan, safety assessment, repair priority and schedule. The input is the optimized repair plan, and the output is the documented information in the report.

[1362] 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.

[1363] ---

[1364] The infrastructure management system of the present invention monitors the status of various infrastructures, predicts their lifespan, assesses their safety, and formulates optimal repair plans, and further includes an emotion engine that recognizes the emotions of users. The system includes the following components:

[1365] 1. Terminal means using sensors to collect infrastructure status data

[1366] 2. Server means to store collected data in a database and perform preprocessing

[1367] 3. A server means for applying machine learning models to predict the lifespan of the infrastructure using pre-processed data.

[1368] 4. Server means for evaluating safety based on predicted lifespan data and conducting risk assessments taking disaster scenarios into account.

[1369] 5. Server method for optimizing repair plans based on risk assessment results

[1370] 6. Server means for generating a repair plan as a report and notifying the user

[1371] 7. Emotion engine that recognizes user emotions and adjusts notification content

[1372] As a specific embodiment, the operation of each part of the system will be described.

[1373] Data collection

[1374] The devices use sensors to collect infrastructure condition data, including the degree of cracking, corrosion progress, deformation measurements, etc. For example, sensors installed on a bridge collect data daily and send it to a server.

[1375] Data accumulation and preprocessing

[1376] The server stores the data sent from the device in a database. It adds a timestamp to the data to clarify which part of the infrastructure the data came from. Next, it performs preprocessing on the data. This includes removing duplicate data and imputing missing data from nearby data or by averaging.

[1377] Application of life prediction model

[1378] The server then inputs the preprocessed data into a machine learning model to predict the infrastructure's lifespan. The machine learning model has been trained with training data in advance and calculates the remaining lifespan based on newly input data. For example, data obtained from road sensors can be used to calculate the remaining lifespan of a road.

[1379] Safety evaluation

[1380] The server evaluates the safety of infrastructure based on predicted lifespan data. The evaluation includes simulations that take into account disaster scenarios such as earthquakes and typhoons. As a result of the safety evaluation, each piece of infrastructure is classified as "low risk," "medium risk," or "high risk."

[1381] optimization

[1382] The server then optimizes the repair plan based on the risk assessment results. It uses a mathematical optimization algorithm to set priorities, taking into account budget and resource constraints. For example, the bridges with the highest risk receive the highest priority.

[1383] Reports and Notifications

[1384] The server creates a report based on the assessment results and the optimized repair plan. The report includes the current status, predicted lifespan, safety assessment, repair priority and schedule for each infrastructure. The server generates this report in PDF format and sends it to the user by email.

[1385] Emotional Engine Adjustment

[1386] The emotion engine installed on the server recognizes the user's emotions. Emotion recognition utilizes the user's operation history and voice input. For example, if the user is feeling stressed, the emotion engine will simplify the content of the notification. In high-stress situations, detailed technical information will be kept to a minimum, and only important information will be conveyed quickly. If the user is in a calm state, the notification will include detailed technical information.

[1387] As a concrete example, sensors collect crack data on Bridge B in City A and send it to a server every day. The server stores the data, performs preprocessing, and then uses a machine learning model to calculate the predicted remaining lifespan of Bridge B. Next, it evaluates the safety of Bridge B by taking disaster scenarios into account and classifies it as "medium risk." Finally, the server prioritizes the repair of Bridge B compared to other infrastructure and includes it in the repair plan for the following year. This repair plan is generated as a report and notified to the city's infrastructure management department. If a management department employee is feeling stressed, the emotion engine can simplify the notification content and present it in an easy-to-understand format.

[1388] In this way, this system not only efficiently manages infrastructure deterioration, assesses natural disaster risks, and develops optimal repair plans, but also improves work efficiency and comprehension by adjusting notification content according to the user's emotional state.

[1389] The processing flow will be explained below.

[1390] ---

[1391] Step 1:

[1392] The devices collect infrastructure condition data. Specifically, sensors measure crack width and depth, corrosion progress, deformation measurements, etc. For example, sensors installed on bridges are set to collect data daily.

[1393] Step 2:

[1394] The data collected by the device is sent to a server in real time, and the sent data includes not only the measured physical quantities but also metadata to identify which part of the infrastructure the data was obtained from.

[1395] Step 3:

[1396] The server stores the received data in a database. At this time, it performs preprocessing such as detecting and deleting duplicate data and detecting and filling in missing data. For example, if there are missing measurement data, they are filled in with data from adjacent timestamps or the average value.

[1397] Step 4:

[1398] The server inputs the preprocessed data into a machine learning model to predict the infrastructure's lifespan. The machine learning model is trained on the training data in advance and calculates the remaining lifespan based on the newly input data. For example, data obtained from road sensors can be used to calculate the remaining lifespan of a road.

[1399] Step 5:

[1400] The server evaluates the safety of infrastructure based on predicted lifespan data. The evaluation process involves simulations that take into account disaster scenarios such as earthquakes and typhoons. For example, the simulation evaluates the degree of damage a bridge would sustain in an earthquake.

[1401] Step 6:

[1402] Based on the safety assessment results, the server classifies the risk level (low risk, medium risk, high risk) for each piece of infrastructure. This classification is used to determine the priority of repair plans.

[1403] Step 7:

[1404] The server optimizes the repair plan based on the risk assessment results. It applies mathematical optimization algorithms to prioritize repairs, taking into account budget and resource constraints. For example, the highest-risk bridges are given top priority.

[1405] Step 8:

[1406] The server generates a repair plan as a report and notifies the user. The report includes the current status, predicted lifespan, safety assessment, repair priority and schedule for each infrastructure. The server generates the report in PDF format and sends it to the user by email.

[1407] Step 9:

[1408] Users review the reports and take appropriate measures. Based on the reports, they schedule repair work and allocate budgets. For example, they finalize bridge and road repair plans in line with next year's budget plan.

[1409] Step 10:

[1410] The emotion engine recognizes the user's emotions. Emotion recognition utilizes the user's operation history and voice input. For example, if the user is feeling stressed, the emotion engine will simplify the notification content.

[1411] Step 11:

[1412] The server adjusts the notification content based on the results of the emotion engine. In stressful situations, the server reduces the amount of detailed technical information and quickly conveys only the important information. On the other hand, when the user is calm, the server provides notifications that include detailed technical information.

[1413] As a concrete example, sensors collect crack data on Bridge B in City A and send it to a server every day. The server stores the data, performs preprocessing, and then uses a machine learning model to calculate the predicted remaining lifespan of Bridge B. Next, it evaluates the safety of Bridge B by taking disaster scenarios into account and classifies it as "medium risk." Finally, the server prioritizes the repair of Bridge B compared to other infrastructure and includes it in the repair plan for the following year. This repair plan is generated as a report and notified to the city's infrastructure management department. If a management department employee is feeling stressed, the emotion engine can simplify the notification content and present it in an easy-to-understand format.

[1414] In this way, this system not only efficiently manages infrastructure deterioration, assesses natural disaster risks, and develops optimal repair plans, but also improves work efficiency and comprehension by adjusting notification content according to the user's emotional state.

[1415] Example 2

[1416] 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."

[1417] While conventional infrastructure management systems can efficiently monitor infrastructure conditions and perform lifespan predictions and risk assessments, they lack the means to reduce the psychological burden on users. As a result, users tend to feel stressed, which can slow their understanding of information and their ability to respond. The present invention aims to solve this problem.

[1418] 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 a terminal means using sensors to collect infrastructure status data, a server means storing the collected data in a database and performing preprocessing, a server means applying a machine learning model to predict the infrastructure's lifespan using the preprocessed data, a server means evaluating safety based on the predicted lifespan data and performing risk assessment taking disaster scenarios into consideration, a server means optimizing a repair plan based on the risk assessment results, a server means generating a repair plan as a report and notifying the user, and a server means having emotion recognition software for recognizing the user's emotions and adjusting the content of the notification. This not only enables appropriate management of infrastructure deterioration and risks, but also reduces the user's psychological burden and enables them to understand information and respond more quickly.

[1419] "Infrastructure" is a general term for facilities that make up the social infrastructure, such as public transportation, water supply, and electricity.

[1420] "Condition Data" means data that describes the physical and functional condition of infrastructure, including measurements of cracks, corrosion, deformation, etc.

[1421] A "sensor" is a measuring device used to collect infrastructure status data, and examples include strain gauges and vibration sensors.

[1422] A "terminal" is a device that temporarily stores data collected from a sensor and transmits it to a server.

[1423] A "server" is a computer system that receives data sent from a terminal and processes and analyzes it.

[1424] A "database" is a software system or hardware used to store and manage collected data in an organized manner.

[1425] "Preprocessing" refers to the process of cleansing and organizing collected data to make it suitable for analysis.

[1426] A "machine learning model" is a mathematical model that uses algorithms to learn from large amounts of data and make future predictions and classifications.

[1427] "Lifespan prediction" refers to predicting the remaining lifespan of infrastructure, specifically estimating the period until failure or deterioration occurs.

[1428] "Safety assessment" is the process of determining the safety of an infrastructure based on its current and predicted state.

[1429] A "disaster scenario" is a model that simulates the impact on infrastructure in the event of a natural disaster such as an earthquake or typhoon.

[1430] "Risk assessment" is the process of determining the degree of risk based on infrastructure life expectancy predictions and disaster scenarios.

[1431] A "repair plan" is a plan for specific construction and work to prevent and repair deterioration and breakdowns in infrastructure.

[1432] A "report" is a document that summarizes the evaluation results and details of the repair plan.

[1433] "User" means a person who uses the infrastructure management system to analyze data and develop and implement repair plans.

[1434] "Emotion recognition software" is software that analyzes a user's emotional state and adjusts the system's response as needed.

[1435] "Notification" refers to the act of a system conveying information to a user, and examples include email and dashboard display.

[1436] The above are definitions of important words included in the claims.

[1437] The infrastructure management system of the present invention monitors the status of various infrastructures, predicts their lifespan, assesses their safety, and formulates optimal repair plans. Furthermore, it is equipped with an emotion engine that recognizes the user's emotions and can adjust the content of notifications. The system includes the following components:

[1438] Data collection

[1439] The device uses sensors (e.g., interlocking strain gauge sensors) to collect infrastructure condition data. These sensors are installed on bridges, roads, etc., and periodically measure the degree of cracking, the progress of corrosion, deformation measurements, etc. For example, a sensor installed on a bridge collects data every day at 9:00 AM and sends this data to a server.

[1440] Data accumulation and preprocessing

[1441] The server stores the data sent from the device in a database (for example, MySQL). The received data is assigned metadata such as time information and sensor location information. Next, the data is preprocessed. This preprocessing includes removing duplicate data and filling in missing data (by guessing from nearby data or by filling in the average).

[1442] Lifespan Prediction

[1443] The server uses the preprocessed data to apply a machine learning model (e.g., a TensorFlow regression model) to predict the infrastructure's lifespan. This model is trained on a large amount of past data and predicts the remaining lifespan based on newly input data. For example, data obtained from road sensors is used to calculate the remaining lifespan of the road.

[1444] Safety evaluation

[1445] Servers undergo a safety assessment based on predicted lifespan data. This process uses simulation tools that take into account disaster scenarios (e.g., earthquakes and typhoons). As a result of the assessment, each piece of infrastructure is classified as "low risk," "medium risk," or "high risk."

[1446] Optimizing repair plans

[1447] The server optimizes the repair plan based on the risk assessment results. This optimization process uses linear programming to set priorities while taking into account budget and resource constraints. For example, bridges with the highest risk are given priority.

[1448] Reporting and Notifications

[1449] The server generates a report based on the assessment results and the optimized repair plan. This report includes the current status, predicted lifespan, safety assessment, repair priority and schedule for each infrastructure. The generated report is created in PDF format and sent to the user.

[1450] Adjusting notification content with an emotion engine

[1451] The emotion engine (emotion recognition software, for example) installed on the server analyzes the user's emotions. It determines the user's stress level based on the user's operation history and voice input, and adjusts the notification content as necessary. For example, if the user is feeling stressed, a concise notification will be provided. On the other hand, if the user is relaxed, a notification including detailed technical information will be provided.

[1452] Prompt Sentence Examples

[1453] Based on the crack data for Bridge B in City A, calculate the bridge's predicted remaining lifespan, conduct a safety assessment taking into account disaster scenarios, and classify it as a medium risk.

[1454] Such prompts are used by the system to accurately understand the requested task and to carry it out appropriately.

[1455] The above is a specific embodiment of the infrastructure management system of the present invention. This system not only efficiently manages infrastructure deterioration and assesses the risk of natural disasters, but also enables the adjustment of notification content according to the user's emotional state, thereby improving work efficiency and comprehension.

[1456] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1457] Step 1: Data collection

[1458] The device uses sensors to collect infrastructure condition data. Specifically, interlocking strain gauge sensors are installed on bridges and roads, and data is collected every day at 9:00 a.m. The data collected by the sensors includes the degree of cracks, the progress of corrosion, and deformation measurements. The collected data is temporarily stored inside the device and then sent to a server.

[1459] Input: Sensor measurement data (cracks, corrosion, deformation)

[1460] Output: Sensor data temporarily stored on the device

[1461] Specific behavior:

[1462] The sensor activates and acquires data

[1463] Temporarily save acquired data on the device

[1464] The device sends data to the server

[1465] Step 2: Data accumulation and preprocessing

[1466] The server stores the data sent from the device in a database (MySQL). The stored data is supplemented with metadata such as the acquisition date and time and the sensor's location information. The data is then preprocessed. This includes deleting duplicate data and filling in missing data by guessing from nearby data or by filling in the average value.

[1467] Input: Sensor data sent from the device

[1468] Output: Preprocessed data

[1469] Specific behavior:

[1470] Store data in a database

[1471] Delete duplicate data

[1472] Imputing missing data

[1473] Step 3: Lifetime prediction

[1474] The server uses the preprocessed data to apply a machine learning model (TensorFlow regression model) to predict the remaining lifespan of the infrastructure. This model is trained on a large amount of past data and predicts the remaining lifespan by inputting new data. For example, data obtained from road sensors is used to calculate the remaining lifespan of the road.

[1475] Input: Preprocessed data

[1476] Output: Estimated lifespan of infrastructure

[1477] Specific behavior:

[1478] Preprocessed data is fed into a machine learning model

[1479] The machine learning model begins processing

[1480] Predict remaining life and store the results in a database

[1481] Step 4: Safety assessment

[1482] Servers undergo a safety assessment based on predicted lifespan data. This process uses a simulation tool (specifically SimScale) that takes into account disaster scenarios such as earthquakes and typhoons. As a result of the safety assessment, each piece of infrastructure is classified as "low risk," "medium risk," or "high risk."

[1483] Input: predicted lifespan data, disaster scenarios

[1484] Output: Risk assessment result (low risk, medium risk, high risk)

[1485] Specific behavior:

[1486] Conduct disaster scenario simulations

[1487] Risk assessment based on predicted lifespan data

[1488] Classified risk assessment results are stored in a database

[1489] Step 5: Optimize repair plans

[1490] The server then optimizes the repair plan based on the risk assessment results. This optimization process uses linear programming to set priorities while taking into account budget and resource constraints. For example, the repair of bridges with the highest risk is prioritized.

[1491] Inputs: Risk assessment results, budget data, resource information

[1492] Output: Optimized repair plan

[1493] Specific behavior:

[1494] Input risk assessment results and budget data into a linear planning tool

[1495] Optimize repair plans

[1496] Repair plans stored in a database

[1497] Step 6: Reporting and Notifications

[1498] The server generates a report based on the assessment results and the optimized repair plan. This report includes the current status, predicted lifespan, safety assessment, repair priority and schedule for each infrastructure. The generated report is created in PDF format and sent to the user.

[1499] Input: Evaluation results, optimized repair plan

[1500] Output: Generated report (PDF format)

[1501] Specific behavior:

[1502] Input the assessment results and repair plan into the report generation tool

[1503] Generate reports in PDF format

[1504] Email a PDF to users

[1505] Step 7: Adjusting notification content with the emotion engine

[1506] The emotion engine (emotion recognition software, for example) installed on the server analyzes the user's emotions. It determines the user's stress level based on the user's operation history and voice input, and adjusts the notification content as necessary. For example, if the user is feeling stressed, the notification content will be concise. If the user is relaxed, the notification will include detailed technical information.

[1507] Input: User operation history, voice data

[1508] Output: Adjusted notification content

[1509] Specific behavior:

[1510] Emotion engine analyzes operation history and voice data

[1511] Determine your stress level

[1512] Adjust the notification content and send it to the user

[1513] The above is a detailed description of the specific flow and operation of each processing step of this system.

[1514] (Application example 2)

[1515] 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."

[1516] Modern infrastructure is aging, making regular monitoring and maintenance essential. However, current systems require a lot of effort to monitor the status of infrastructure, making it difficult to develop efficient maintenance plans. In addition, notification methods that do not take into account the user's emotional state can cause stress to users and result in reduced maintenance efficiency. It is necessary to solve these problems and achieve efficient and effective infrastructure management.

[1517] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes terminal means using sensors to collect infrastructure status data, server means for storing the collected data in a database and performing preprocessing, server means for applying a machine learning model to predict the infrastructure's lifespan using the preprocessed data, server means for evaluating safety based on the predicted lifespan data and performing risk assessment taking disaster scenarios into account, server means for optimizing a repair plan based on the risk assessment results, server means for generating a repair plan as a report and notifying the user, and means having an emotion engine that recognizes the user's emotions and adjusts the notification content. This not only makes it possible to efficiently manage infrastructure deterioration, evaluate the risk of natural disasters, and formulate an optimal repair plan, but also to improve work efficiency and comprehension by adjusting the notification content according to the user's emotional state.

[1518] "Infrastructure" is a general term for the structures and facilities that form the foundation for supporting transportation and public services.

[1519] "Status Data" refers to information collected by sensors that indicates the current state of the infrastructure.

[1520] "Sensor" means a device that measures a physical condition (e.g., crack severity, corrosion progression, deformation measurement, etc.).

[1521] "Terminal means" refers to a device or system that uses sensors to collect infrastructure status data and transmits the data to a server.

[1522] "Database" refers to a computer system for systematically storing and managing collected infrastructure status data.

[1523] "Preprocessing" refers to the preliminary processing of collected data to make it easier to analyze.

[1524] "Server Means" refers to a computer system for processing, storing, predicting and evaluating data.

[1525] A "machine learning model" refers to an algorithm or its implementation that learns patterns from accumulated data and makes predictions based on new data.

[1526] "Predicting lifespan" means estimating the remaining lifespan of an infrastructure based on its current condition data.

[1527] "Evaluating safety" refers to determining the safety of infrastructure based on predicted lifespan data.

[1528] "Risk assessment" means analyzing and evaluating the risk to infrastructure by considering disaster scenarios.

[1529] "Optimizing repair planning" refers to the process of determining the optimal sequence and method of infrastructure repairs based on available resources and budget.

[1530] A "report" refers to a document that summarizes information such as evaluation results and repair plans.

[1531] "Emotion Engine" means an algorithm or software that recognizes a user's emotional state and adjusts notification content accordingly.

[1532] "Notifying the user" refers to transmitting information about the evaluation results and repair plans to the user in an appropriate format.

[1533] This invention relates to a system for efficiently managing infrastructure deterioration, assessing natural disaster risks, and formulating optimal repair plans. Furthermore, it has the function of adjusting notification content according to the user's emotional state.

[1534] System Overview

[1535] The system consists of the following main components:

[1536] 1. Terminal means using sensors to collect infrastructure status data

[1537] 2. Server means to store collected data in a database and perform preprocessing

[1538] 3. A server means for applying machine learning models to predict the lifespan of the infrastructure using pre-processed data.

[1539] 4. Server means for evaluating safety based on predicted lifespan data and conducting risk assessments taking disaster scenarios into account.

[1540] 5. Server method for optimizing repair plans based on risk assessment results

[1541] 6. Server means for generating a repair plan as a report and notifying the user

[1542] 7. A means with an emotion engine that recognizes user emotions and adjusts notification content

[1543] Detailed Description

[1544] Data collection

[1545] The terminal means collects infrastructure status data using various sensors. The sensors acquire data such as the degree of cracking, the progress of corrosion, and deformation measurements. For example, sensors installed on a bridge collect data daily and send the data to a server.

[1546] Data accumulation and preprocessing

[1547] The server stores the data sent from the device in a database. It adds a timestamp to the data to clarify which part of the infrastructure the data came from. Next, it performs preprocessing on the data. This includes removing duplicate data and imputing missing data from nearby data or by averaging.

[1548] Application of life prediction model

[1549] The server inputs the preprocessed data into a machine learning model to predict the lifespan of the infrastructure. The machine learning model has been trained with training data in advance and calculates the remaining lifespan based on newly input data. For example, data obtained from road sensors can be used to calculate the remaining lifespan of a road.

[1550] Safety evaluation

[1551] The server evaluates the safety of infrastructure based on predicted lifespan data. The evaluation includes simulations that take into account disaster scenarios such as earthquakes and typhoons. As a result of the safety evaluation, each piece of infrastructure is classified as "low risk," "medium risk," or "high risk."

[1552] optimization

[1553] The server then optimizes the repair plan based on the risk assessment results. It uses a mathematical optimization algorithm to set priorities, taking into account budget and resource constraints. For example, the bridges with the highest risk receive the highest priority.

[1554] Reports and Notifications

[1555] The server creates a report based on the assessment results and the optimized repair plan. The report includes the current status, predicted lifespan, safety assessment, repair priority and schedule for each infrastructure. The server generates this report in PDF format and sends it to the user by email.

[1556] Emotional Engine Adjustment

[1557] The emotion engine installed on the server recognizes the user's emotions. Emotion recognition utilizes the user's operation history and voice input. For example, if the user is feeling stressed, the emotion engine will simplify the content of the notification. In high-stress situations, detailed technical information will be kept to a minimum, and only important information will be conveyed quickly. If the user is in a calm state, the notification will include detailed technical information.

[1558] Specific examples

[1559] For example, consider a situation where a sensor on Line A in a factory collects data and predicts that the remaining lifespan is less than 50% after 30 days. The safety assessment results are classified as "medium risk" and a repair plan is scheduled for the first week. The emotion engine recognizes the user's stress and sends a simplified notification.

[1560] An example of a prompt for a generative AI model is:

[1561] "Generate a Python program that collects data from sensors installed on factory line A, predicts lifespan, evaluates safety, and optimizes repair plans. Also, include an emotion engine function that simplifies notifications when the user is stressed."

[1562] The above is an embodiment of the present invention.

[1563] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1564] Step 1: Data collection

[1565] The terminal collects infrastructure condition data using various sensors. The sensors acquire data such as the degree of cracks, the progress of corrosion, and deformation measurements. The collected data is temporarily stored on the terminal with a timestamp. The input from the terminal is sensor data, and the output is condition data ready to be preprocessed.

[1566] Step 2: Data accumulation and preprocessing

[1567] The server receives data sent from the terminal and stores it in a database. When storing the data, it adds a timestamp and the origin of the data (which infrastructure and which part it was obtained from). Next, the server performs preprocessing such as deleting duplicate data and filling in missing data. The input is the collected raw data, and the output is the preprocessed, clean data.

[1568] Step 3: Applying the life prediction model

[1569] The server inputs the preprocessed data into a machine learning model to predict the remaining lifespan of the infrastructure. The machine learning model is pre-trained and calculates the remaining lifespan based on the newly preprocessed data. The input is the preprocessed data, and the output is the predicted lifespan data.

[1570] Step 4: Safety assessment

[1571] The server performs simulations that take disaster scenarios into account based on predicted lifespan data and evaluates safety. It classifies the risk level of the infrastructure into "low risk," "medium risk," and "high risk." The input is lifespan data and disaster scenario information, and the output is the results of the safety evaluation.

[1572] Step 5: Optimize repair plans

[1573] The server uses a mathematical optimization algorithm to optimize the repair plan based on the safety assessment results. This includes a process for setting priorities while taking into account budget and resource constraints. The inputs are the safety assessment results and resource information, and the output is an optimized repair plan.

[1574] Step 6: Reporting and Notifications

[1575] The server creates a detailed report based on the evaluation results and optimized repair plans. This report includes the current state of each piece of infrastructure, its predicted lifespan, safety assessment, and repair priorities and schedules. The generated report is emailed to the user in PDF format. The input is the repair plan and evaluation results, and the output is the generated report.

[1576] Step 7: Notification adjustment by emotion engine

[1577] The server uses an emotion engine to recognize the user's emotions. It detects the user's emotional state based on the user's operation history and voice input, and adjusts the notification content accordingly. For example, if the user is feeling stressed, it simplifies the notification content. The input is the user's operation history and voice data, and the output is the adjusted notification content.

[1578] The above is a detailed description of each processing step.

[1579] 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.

[1580] 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.

[1581] 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.

[1582] 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.

[1583] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1584] 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.

[1585] 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).

[1586] 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.

[1587] 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."

[1588] 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.

[1589] 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).

[1590] 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.

[1591] 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.

[1592] 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.

[1593] 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.

[1594] 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.

[1595] 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.

[1596] 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.

[1597] 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.

[1598] 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.

[1599] 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.

[1600] The follo...

Claims

1. a terminal means using sensors to collect infrastructure condition data; a server means for storing the collected data in a database and performing preprocessing; server means for applying a machine learning model to predict the lifespan of the infrastructure using the preprocessed data; a server means for evaluating safety based on predicted lifespan data and for conducting risk assessment taking disaster scenarios into consideration; a server means for optimizing a repair plan based on the risk assessment result; a server means for generating a repair plan as a report and notifying the user of the report; A system including:

2. The system of claim 1 , wherein the sensors collect measurements of crack severity, corrosion progression, and deformation.

3. The system of claim 1 , wherein the preprocessing includes removing duplicate data and imputing missing data.

Images