System

Abstract

A system is provided.SOLUTION: A system includes means for extracting data from an existing infrastructure information database, means for collecting real-time data from a sensor or an IoT device and transmitting the collected data to a server, means for inputting the extracted and collected data to an AI model and performing analysis, means for automatically generating a maintenance and repair plan based on the analysis result, means for notifying a user terminal of the generated maintenance and repair plan, means for reporting a work result from a user to the server and recording the result in a database, and means for analyzing the report content and feeding back the result to improvement of the maintenance and repair plan.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] The present invention aims to streamline the enormous amount of manual work required for the maintenance and development of urban infrastructure. Currently, maintenance and development of infrastructure such as roads, buildings, water and sewerage systems, and electricity requires a large amount of manpower and time, and there are many errors and delays in planning and execution of the work. This can reduce the lifespan and performance of the infrastructure, and even lead to serious accidents and problems. The present invention solves these issues and provides a means for achieving faster and more accurate maintenance and development of urban infrastructure. [Means for solving the problem]

[0005] The present invention is a system that solves the above problems by using the following means.

[0006] a means for extracting data from an existing infrastructure information database;

[0007] A means of collecting real-time data from sensors and IoT devices and sending it to a server,

[0008] A means of inputting the extracted and collected data into an AI model for analysis;

[0009] A means for automatically generating maintenance and repair plans based on the analysis results,

[0010] A means for notifying a user terminal of the generated maintenance and repair plan;

[0011] A means for reporting the work results from the user to the server and recording them in a database;

[0012] The report will be analyzed and used as a means of providing feedback to improve maintenance and repair plans.

[0013] This will enable efficient and accurate maintenance and development of urban infrastructure without relying on traditional manual work.

[0014] An "existing infrastructure information database" is an existing database that records information about urban infrastructure such as roads, buildings, water supply and sewerage, and electricity.

[0015] "Means for extracting data" refers to a method or device for extracting necessary information from an existing infrastructure information database.

[0016] A "sensor" is a device that detects physical conditions or changes and outputs that information as an electronic signal.

[0017] An "IoT device" is a device that is connected to the Internet and has the ability to collect and transmit various data.

[0018] "Real-time data" refers to the latest data that instantly reflects the current state of infrastructure.

[0019] "Server" refers to a central processing unit and its associated systems for collecting, storing, analyzing, and notifying data.

[0020] "Means for collecting data" refers to methods or devices for collecting data from sensors or IoT devices and sending it to a server.

[0021] An "AI model" is a model used to analyze data based on machine learning algorithms and deep learning techniques.

[0022] "Means for inputting data and performing analysis" refers to methods or devices for inputting data into an AI model and performing that analysis.

[0023] A "maintenance and development plan" is a plan that specifically outlines the work content and schedule required for the maintenance and development of infrastructure.

[0024] "Means for automatically generating maintenance and repair plans" refers to methods or devices that automatically create optimal maintenance and repair plans based on the analysis results of an AI model.

[0025] A "user terminal" is a terminal such as a computer or smartphone used by a maintenance technician.

[0026] "Notification means" refers to a method or device for sending a message or alert from the server to the user terminal.

[0027] The "means for reporting work results" refers to a method or device for a user to report information about the work completed by the user to the server.

[0028] The "means for recording in a database" refers to a method or device for storing collected work results in a database.

[0029] "Feedback means" refers to methods and devices for analyzing the reported work results and using them to improve future maintenance and repair plans. [Brief explanation of the drawings]

[0030] [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

[0031] 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.

[0032] First, the terms used in the following description will be explained.

[0033] 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).

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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."

[0038] [First embodiment]

[0039] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0040] 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.

[0041] 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).

[0042] 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.

[0043] 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.

[0044] 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.

[0045] 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.

[0046] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0047] 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.

[0048] 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.

[0049] 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.

[0050] 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."

[0051] This invention is a system that efficiently automates a series of tasks related to the maintenance and development of urban infrastructure. This system consists of three main components: a server, a terminal, and a user, which work in conjunction with each other.

[0052] The system is responsible for the following steps:

[0053] 1. Data Collection

[0054] The server extracts the necessary data from an existing infrastructure information database, including information on roads, buildings, water and sewerage systems, and electricity.

[0055] Terminals (sensors and IoT devices) collect real-time data from the site and send it to a server, which reflects the latest infrastructure status.

[0056] 2. Data Analysis

[0057] The server inputs the collected data into an AI model for analysis, which uses deep learning and machine learning algorithms to assess the state of the infrastructure and detect and predict anomalies.

[0058] The analysis includes the degree of deterioration of infrastructure and maintenance priorities. For example, the progression of cracks and the need for repairs can be quantified, enabling specific infrastructure assessments.

[0059] 3. Automatic generation of maintenance and repair plans

[0060] Based on the analysis results obtained from the AI ​​model, the server automatically generates an optimal maintenance plan, which includes details on which infrastructure to maintain, when, and how.

[0061] For example, if it is determined that a particular road section needs repair within a week, the repair method (patch repair, surface scraping / regeneration work, etc.) and a specific schedule will be generated.

[0062] 4. User Notices and Instructions

[0063] The server notifies the user device of the generated maintenance plan via email or in-app notification.

[0064] The user (maintenance staff) receives the notification, checks the plan contents, and prepares for the work, which specifically includes arranging repair materials and adjusting the schedule of workers.

[0065] 5. Work Completion Report and Feedback

[0066] After completing the maintenance work, the user reports the results to the server via the terminal, including details of the work and the date and time of completion.

[0067] The server records the reported work results in a database and provides feedback to improve the next maintenance and repair plan, resulting in more accurate and efficient maintenance and repair.

[0068] Specific examples

[0069] For example, consider a scenario involving the maintenance of major roads in a city.

[0070] 1. Data Collection

[0071] The server collects data on the past maintenance history of roads throughout the city, and sensors installed on the roads collect data on cracks and subsidence in real time and send it to the server.

[0072] 2. Data Analysis

[0073] The server inputs the collected data into an AI model to analyze the road's deterioration, which then assesses the extent of cracks and calculates the need for repairs.

[0074] 3. Automatic generation of maintenance and repair plans

[0075] The server determines whether a specific road section requires urgent repairs based on the extent of the cracks, and then automatically generates a plan with specific repair methods and schedules.

[0076] 4. User Notices and Instructions

[0077] The server notifies the maintenance staff of the generated repair plan.

[0078] The user receives the notification, checks the plan, and arranges for the necessary materials and workers.

[0079] 5. Work Completion Report and Feedback

[0080] After completing the repair work, the user reports the results of the work on the terminal.

[0081] The server records the report in a database and uses it to formulate the next plan.

[0082] In this way, by using the present invention, a system is provided that can efficiently and accurately carry out a series of tasks related to the maintenance and development of urban infrastructure, making it possible to reduce costs and speed up the tasks.

[0083] The processing flow will be explained below.

[0084] Step 1:

[0085] Data collection

[0086] The server extracts the infrastructure's maintenance history and status information from the infrastructure information database using an SQL query, for example, executing a command such as SELECT FROM infrastructure_data WHERE category='road'.

[0087] Step 2:

[0088] Receiving real-time data

[0089] Terminals (sensors and IoT devices) measure the condition of local infrastructure in real time, for example, a sensor detecting the depth of cracks in the road, and send that data to the server via an HTTP POST request.

[0090] Step 3:

[0091] Data Integration

[0092] The server integrates information retrieved from the database with real-time data received from the device. This data is managed in JSON format or as a data frame. The data is formatted using libraries such as Pandas.

[0093] Step 4:

[0094] Data analysis

[0095] The server preprocesses the integrated data before inputting it into the AI ​​model. Specifically, it complements missing data and removes outliers, which allows for accurate analysis.

[0096] The server then inputs the preprocessed data into an AI model for analysis, which uses deep learning or machine learning algorithms to assess the condition of the infrastructure and calculate whether there are any abnormalities or the degree of degradation.

[0097] Step 5:

[0098] Automatic generation of maintenance and repair plans

[0099] The server automatically generates a maintenance plan based on the analysis results of the AI ​​model. For example, if a section of road is cracked, the server will incorporate repair methods (such as patch repairs or surface scraping and restoration work) and a specific schedule into the plan.

[0100] The generated plan is stored in the database using an SQL query, for example with a command like INSERT INTO maintenance_schedule (infrastructure_id, repair_method, schedule_date) VALUES (...).

[0101] Step 6:

[0102] notification

[0103] The server notifies the user device of the generated maintenance plan via email or in-app notification. One method of notification is to send email using the SMTP protocol.

[0104] Step 7:

[0105] User confirmation and preparation

[0106] The user (maintenance staff) receives the notification sent to their terminal, checks the plan, and arranges for repair materials and adjusts the schedule of workers.

[0107] Step 8:

[0108] Work execution

[0109] The user carries out maintenance and repair work based on a plan, the details of which are described in the plan and are carried out accordingly.

[0110] Step 9:

[0111] Work completion report

[0112] After completing the maintenance work, the user inputs the work content and the completion date and time into the terminal and reports it to the server.

[0113] The device sends the work to the server via an HTTP POST request, and the report includes details of the completed work.

[0114] Step 10:

[0115] Database recording and analysis

[0116] The server records the received work reports in a database, for example using an SQL query like INSERT INTO maintenance_reports (infrastructure_id, work_details, completion_date) VALUES (...).

[0117] The server analyzes the report and generates feedback to improve the next maintenance and repair plan, which allows for more accurate planning.

[0118] Through the above processing steps, this system can automate the maintenance and development of urban infrastructure efficiently and accurately.

[0119] Example 1

[0120] 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."

[0121] Traditional methods for maintaining and upgrading urban infrastructure involve a lot of manual work, making them inefficient and time-consuming. It also makes it difficult to prioritize maintenance work and quickly detect abnormalities, which increases the risk of infrastructure deterioration and accidents. Furthermore, the formulation of maintenance plans relies on human judgment and is prone to subjective factors, making optimization difficult. These issues need to be addressed.

[0122] 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.

[0123] In this invention, the server includes a means for extracting data from an existing infrastructure information database, a means for collecting real-time data from sensors and IoT devices and sending it to the server, and a means for preprocessing the extracted and collected data and inputting it into an AI model for analysis. This allows for an accurate understanding of the infrastructure status, automatic generation of efficient maintenance and repair plans, and rapid anomaly detection.

[0124] An "existing infrastructure information database" is a data storage that stores past records and current status data related to urban infrastructure.

[0125] "Sensors and IoT devices" are electronic devices that collect data from the physical environment in real time and send it to a server over a network.

[0126] "Preprocessing" is the process of removing noise from collected data and extracting and shaping the necessary information.

[0127] An "AI model" is a collection of algorithms used to realize artificial intelligence, and here it specifically refers to deep learning models and machine learning algorithms.

[0128] A "maintenance and improvement plan" is a specific plan for predicting deterioration and abnormalities in infrastructure and carrying out repairs and renovations at the appropriate time and in the appropriate manner.

[0129] A "user terminal" is a device such as a computer or smartphone used by a maintenance technician.

[0130] "Feedback" refers to analyzing the results of maintenance work carried out and providing information to be used in planning the next maintenance and repair work.

[0131] This invention is a system that efficiently automates a series of tasks related to the maintenance and development of urban infrastructure. This system consists of three main components: a server, a terminal, and a user, each of which plays a specific role.

[0132] Hardware and Software Configuration

[0133] The server consists of a high-performance computer and is equipped with a database management system (e.g., MySQL), a data processing framework (e.g., PySpark), and a machine learning framework (e.g., TensorFlow or PyTorch).

[0134] Terminals consist of sensors and IoT devices that collect real-time data using wireless communication technologies such as LoRa and Zigbee. Terminals also include smartphones and tablets used by users.

[0135] Users are maintenance personnel and others who connect to the system through a dedicated mobile application.

[0136] What the program does

[0137] The server first extracts data on roads, buildings, water and sewer systems, and electricity from existing infrastructure information databases. It then collects real-time data from on-site sensors and IoT devices and preprocesses it. Preprocessing includes removing noise and extracting necessary information. The preprocessed data is then input into a generative AI model. This AI model uses deep learning and machine learning algorithms to assess the condition of the infrastructure and detect and predict anomalies.

[0138] To illustrate, here's an example prompt:

[0139] "Evaluate the extent of cracking on Section A of a major road in the city. Then calculate the need for repairs."

[0140] Based on the analysis results, the server automatically generates a maintenance and repair plan, which includes details on which infrastructure to maintain and repair, when, and how. For example, it may determine that a specific road section needs repair within a week, and generate the repair method (patching, surface scraping, restoration work, etc.) and schedule.

[0141] The server notifies the user's device of the generated maintenance and repair plan via email or in-app notification. The user receives the notification, checks the plan, and arranges for the necessary materials and workers. After the repair work is completed, the user reports the work results via their device. The server records the reported work results in a database and provides feedback to improve the next maintenance and repair plan.

[0142] In this way, this system can efficiently and accurately carry out a series of tasks related to the maintenance and development of urban infrastructure. Specific data analysis and automatic generation of maintenance plans are performed using machine learning algorithms, resulting in cost reduction and speed.

[0143] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0144] Step 1: Data extraction

[0145] The server extracts data from existing infrastructure information databases. For example, the server retrieves historical maintenance data for roads, buildings, water and sewerage systems, electricity, etc. from a MySQL database. The input for this data extraction is a database query, and the output is a set of extracted infrastructure data.

[0146] Step 2: Real-time data collection

[0147] Terminals (sensors and IoT devices) collect real-time data on-site and send it to a server. For example, sensors installed on roads collect data on cracks and subsidence and send it to a server via wireless communication technology (such as LoRa or Zigbee). The input of this collection is the real-time observation data of the sensors, and the output is the latest infrastructure status data sent to the server.

[0148] Step 3: Data Preprocessing

[0149] The server pre-processes the extracted and collected data, removing noise, extracting necessary information, and shaping the data, for example filtering outliers and scaling the data. The input of this pre-processing is raw data, and the output is pre-processed, clean data.

[0150] Step 4: Input data into the AI ​​model

[0151] The server inputs the preprocessed data into a generative AI model. This AI model uses deep learning frameworks such as TensorFlow and PyTorch. An example prompt is, "Evaluate the degree of cracking on section A of the city's main road. Then, calculate the need for repairs." The input for this data input is the preprocessed data and the prompt, and the output is the analysis results from the AI ​​model.

[0152] Step 5: Automatic generation of maintenance and repair plans

[0153] The server automatically generates a maintenance and repair plan based on the analysis results from the AI ​​model. For example, it may determine that a specific road section requires urgent repairs and generate a repair method (patching, surface scraping, restoration work, etc.) and schedule. The input for this plan generation is the analysis results from the AI ​​model, and the output is a specific maintenance and repair plan.

[0154] Step 6: Maintenance Plan Notification

[0155] The server notifies the user device of the generated maintenance plan. Notification methods include email and in-app notification. For example, a notification may be sent to the maintenance technician's smartphone app. The input of this notification is the maintenance plan, and the output is a notification message sent to the user device.

[0156] Step 7: Prepare and perform maintenance work

[0157] The user (maintenance staff) receives the notification, checks the plan contents, and arranges for the necessary materials and workers. Specifically, they arrange for repair materials and adjust the schedule of workers. The input for this preparation is the notified maintenance and repair plan, and the output is the maintenance work schedule and the material arrangement status.

[0158] Step 8: Report work completed

[0159] After completing maintenance work, the user reports the results to the server via their device. The report includes details of the work and the date and time of completion. For example, the report can be made using a dedicated mobile application. The input of this report is the details of the maintenance work performed, and the output is a work completion report sent to the server.

[0160] Step 9: Record and feedback

[0161] The server records the reported work results in a database and provides feedback to improve the next maintenance plan. For example, it analyzes the reports and adjusts algorithms to improve the accuracy of future maintenance plans. The input to this recording and feedback is the work completion report, and the output is updated database records and improved maintenance plan algorithms.

[0162] (Application example 1)

[0163] 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."

[0164] In large-scale facilities such as logistics centers, it is important to perform infrastructure maintenance and repairs efficiently and quickly. However, with conventional systems, data collection and analysis, and the creation and execution of maintenance plans are often done manually, which is time-consuming and labor-intensive, and prone to human error. Furthermore, there is a lack of tools that enable on-site workers to quickly grasp the situation and make appropriate decisions. To solve these problems, an automated system is needed that can monitor the status of infrastructure in real time and respond quickly and appropriately.

[0165] 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.

[0166] In this invention, the server includes a means for extracting data from an existing infrastructure information database, a means for collecting real-time data from sensors and IoT devices and sending it to the server, and a means for notifying the smart glasses of a maintenance and repair plan based on the analysis results so that the user can visually confirm it. This enables the automation of infrastructure maintenance and repair in logistics centers, making it possible to perform the work efficiently and quickly.

[0167] - The "Infrastructure Information Database" is a database for storing and managing infrastructure data related to facilities such as logistics centers.

[0168] A "sensor" is a device that measures physical or chemical quantities and collects that information as digital data.

[0169] An "IoT device" is a device that has the ability to send and receive data via the Internet and is used to collect environmental data at logistics centers.

[0170] "Real-time data" refers to the latest data that changes every moment and is obtained from sensors and IoT devices.

[0171] A "server" is a central computer that collects, processes, analyzes data, and provides information to other devices and users.

[0172] An "AI model" is an artificial intelligence system that includes algorithms for learning data and predicting analysis results.

[0173] A "deep learning model" is a machine learning model that uses a multi-layer neural network to learn and analyze complex data.

[0174] "Machine learning algorithm" is a general term for algorithms that learn patterns and rules from data.

[0175] A "maintenance and repair plan" is a plan that outlines the content and schedule of work required to maintain the condition of the infrastructure at a logistics center.

[0176] A "user terminal" is a device used to operate the system and receive information.

[0177] "Smart glasses" are wearable devices that have the ability to visually display information and are used by users when working on-site.

[0178] A "database" is a system that structures and stores collected data so that it can be accessed, managed, and analyzed effectively later.

[0179] "Feedback" is the process of improving future maintenance and repair plans based on information obtained from analysis and work results.

[0180] This invention is a system that efficiently automates the maintenance and upkeep of logistics center infrastructure. This system consists of three main components: a server, a terminal, and a user, all of which work in conjunction with each other.

[0181] The server has the function of extracting necessary data from existing infrastructure information databases. Sensors and IoT devices collect real-time data and send it to the server. The server inputs the data into an AI model for analysis. Deep learning models and machine learning algorithms are used for the analysis. Based on this analysis, maintenance and repair plans are automatically generated.

[0182] The generated maintenance and repair plan is sent to the user's device. The user's device may also include smart glasses, allowing the user to visually check the plan. The user receives the notification, checks the plan, and carries out the work. When the repair is complete, the results are reported to the server via the device. The server records the report in a database and provides feedback to improve the next maintenance and repair plan.

[0183] The system's hardware includes various sensors such as temperature, humidity, and vibration sensors, while the software uses AI frameworks such as TensorFlow and PyTorch.

[0184] Data collection, processing, and calculation are carried out as follows: Data collection is carried out by acquiring real-time data from sensors and IoT devices and sending it to a server. Data processing is carried out by the server inputting the data into an AI model and performing preprocessing to make predictions. Data calculation is carried out by analyzing the data based on the patterns learned by the AI ​​model and generating maintenance and repair plans.

[0185] As a concrete example, consider the maintenance of conveyor belts in a logistics center. If data from sensors includes temperature, humidity, and vibration data, a user wearing smart glasses patrols the area and finds any abnormalities. Images of the abnormal areas are collected and sent to a server. The server inputs the data into an AI model and, based on the analysis results, notifies the smart glasses of a maintenance and repair plan, such as, "There is an abnormality in the conveyor belt in section A. Repairs are required. The recommended repair method is to replace the belt."

[0186] An example of an input prompt for a generative AI model is as follows:

[0187] "Based on temperature, humidity, vibration data and image data, determine the degree of deterioration of infrastructure within the logistics center and the necessary repairs."

[0188] This system will enable efficient and rapid maintenance and repair of logistics center infrastructure, improving the accuracy and speed of work.

[0189] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0190] Step 1: Collect data

[0191] The server extracts the necessary data from the existing infrastructure information database. Terminals (sensors and IoT devices) collect real-time data within the logistics center and send it to the server. In this step, data such as temperature, humidity, and vibration are collected. The input is real-time data from the infrastructure information database and sensors, and the output is data integrated within the server. Specifically, the server executes a database query, and the terminals send the collected data as packets.

[0192] Step 2: Preprocessing the data

[0193] The server processes the collected data into a format suitable for the AI ​​model. Specifically, it cleanses, normalizes, and extracts features from the data. The input to this step is integrated real-time data, and the output is preprocessed data. Specifically, it complements missing values ​​in the data and converts values ​​to the required range.

[0194] Step 3: Analyze the data

[0195] The server inputs the preprocessed data into the AI ​​model for analysis. The AI ​​model analyzes the data using deep learning models and machine learning algorithms to assess the condition of the infrastructure. The input for this step is the preprocessed data, and the output is the analysis results regarding the degree of deterioration and the need for repairs. Specifically, the data is fed into the model and the inference results are obtained.

[0196] Step 4: Generate a maintenance plan

[0197] The server automatically generates a maintenance and repair plan based on the analysis results. This plan includes specific repair methods and schedules. The input is the analysis results, and the output is the generated maintenance and repair plan. Specifically, the server creates an optimal rule-based plan based on the analysis results.

[0198] Step 5: Notification

[0199] The server notifies the smart glasses of the generated maintenance plan. The user visually checks the plan and performs the work. The input is the generated maintenance plan, and the output is the plan checked by the user. Specifically, text and images are sent to the smart glasses via the notification system.

[0200] Step 6: Report work completed

[0201] After completing a task, the user reports the results to the server through the smart glasses. The input is the task completion report, and the output is the report data recorded on the server. Specifically, the user inputs and transmits the report content using the operation panel of the smart glasses.

[0202] Step 7: Feedback

[0203] The server records the reported work results in a database and provides feedback to improve the next maintenance plan. The input is the reported work results data, and the output is an updated maintenance plan. Specific operations include updating the database and retraining the AI ​​model.

[0204] 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.

[0205] This invention utilizes AI technology for the maintenance and development of urban infrastructure, automating traditional manual tasks and combining it with an emotion engine that recognizes user emotions. This system consists of three main components: a server, a terminal, and a user, each of which plays a specific role. Furthermore, by analyzing the user's emotional state and adapting notification content, more effective infrastructure management is achieved.

[0206] The main processing steps of the system are:

[0207] 1. Data Collection

[0208] The server extracts data from the infrastructure information database. The data includes infrastructure information such as roads, buildings, water, sewerage, and electricity. It retrieves the data using an SQL query, for example, SELECT FROM infrastructure_data WHERE category='road'.

[0209] Terminals (sensors and IoT devices) collect real-time data from the site and send it to a server. For example, data on road cracks and subsidence is sent from sensors.

[0210] 2. Data Analysis

[0211] The server inputs the collected data into an AI model for analysis, which includes preprocessing the data to fill in missing data and remove outliers, such as cleaning the data frame using the Pandas library.

[0212] The server then inputs the pre-processed data into an AI model that uses deep learning or machine learning algorithms to assess the condition of the infrastructure and calculate the infrastructure's deterioration status and repair priorities.

[0213] 3. Automatic generation of maintenance and repair plans

[0214] The server automatically generates a maintenance plan based on the analysis results. For example, if it determines that a certain road section needs repair within a certain period of time, it will include the repair method and specific schedule in the plan.

[0215] The generated plan is stored in the database using an SQL query, for example INSERT INTO maintenance_schedule (infrastructure_id, repair_method, schedule_date) VALUES (...).

[0216] 4. Analysis by Emotion Engine

[0217] The device collects the user's voice and facial expression data and sends it to the emotion engine. For example, the device uses a camera or microphone to collect the user's facial expressions and voice and analyzes their emotional state.

[0218] The server receives the analysis results from the emotion engine and identifies the user's emotional state, making it possible to determine whether the user is stressed or relaxed.

[0219] 5. User Notification Adaptation

[0220] Based on the analysis results of the emotion engine, the server customizes the content of the maintenance and repair plan notification according to the user's emotional state. For example, if the user is under high stress, the notification content will be concise and clear, while if the user is relaxed, detailed information will be provided.

[0221] The server sends the notification to the user's device. Possible notification methods include email and in-app notifications. One method is to send email using the SMTP protocol.

[0222] 6. Work execution and reporting

[0223] Users can carry out maintenance and repair work based on the notification, and arrange for the necessary materials and workers in advance to ensure the work proceeds smoothly according to plan.

[0224] After completing the task, the user reports the results to the server via an HTTP POST request, which is then recorded in the database.

[0225] As a concrete example, consider road crack maintenance in a particular area.

[0226] 1. For data collection, the server retrieves past maintenance history from the database, and the terminal (sensor) collects the progress of cracks in real time and sends it to the server.

[0227] 2. In data analysis, the server preprocesses the collected data and inputs it into an AI model for analysis, assessing the severity of cracks and identifying which sections need repairs.

[0228] 3. When automatically generating maintenance and repair plans, the server creates a repair plan based on the results of the AI ​​model and saves it in a database.

[0229] 4. In analysis using an emotion engine, the device collects the user's voice and facial expressions, analyzes them using the emotion engine, and the server receives the results.

[0230] 5. In user notification adaptation, the server customizes the notification content according to the user's emotional state and sends it to the user's terminal.

[0231] 6. Work execution and reporting: The user carries out repair work according to the notification and reports the results after the work is completed.

[0232] These steps enable the system to achieve efficient and accurate infrastructure management and to respond flexibly to the user's emotional state.

[0233] The processing flow will be explained below.

[0234] Step 1:

[0235] Data collection

[0236] The server extracts past maintenance history and status data from the existing infrastructure information database using an SQL query such as SELECT FROM infrastructure_data WHERE category='road'.

[0237] Terminals (sensors and IoT devices) measure the local infrastructure condition (e.g., road cracks and subsidence) in real time and send the data to the server via an HTTP POST request.

[0238] Step 2:

[0239] Real-time data integration

[0240] The server integrates historical data extracted from the database with real-time data sent from the terminal, and uses Python's Pandas library to clean the data, impute missing values, and remove outliers.

[0241] Step 3:

[0242] Data analysis

[0243] The server inputs the preprocessed data into an AI model to analyze the condition of the infrastructure. Deep learning algorithms (e.g., TensorFlow and PyTorch) are used to calculate the state of deterioration of the infrastructure and the priority of repairs. Specifically, the progress of cracks and the rate of subsidence are evaluated.

[0244] Step 4:

[0245] Automatic generation of maintenance and repair plans

[0246] The server automatically generates a maintenance plan based on the analysis results of the AI ​​model. For example, if it determines that a specific road section needs patch repair within a week, it will include the repair method and specific schedule in the plan. The plan is generated in JSON format.

[0247] The server saves the generated maintenance schedule in the database using an SQL query (e.g. INSERT INTO maintenance_schedule (infrastructure_id, repair_method, schedule_date) VALUES (...)).

[0248] Step 5:

[0249] Analysis by emotion engine

[0250] The device collects the user's voice and facial expression data and sends it to the emotion engine. It uses a camera and microphone to capture the user's facial expressions and voice.

[0251] The server analyzes the data sent from the emotion engine and determines the user's emotional state, for example, detecting whether the user is stressed or relaxed, using emotion recognition algorithms.

[0252] Step 6:

[0253] User notification adaptation

[0254] The server customizes the notification content according to the user's emotional state. For example, if the user is in a high-stress state, the notification content is brief and provides only the minimum necessary information. On the other hand, if the user is in a relaxed state, the server provides detailed notification content.

[0255] The server sends notifications to the user's device. Scheduled notifications can be sent via email or in-app notifications. Emails can also be sent using the SMTP protocol.

[0256] Step 7:

[0257] User confirmation and preparation

[0258] The user checks the maintenance and repair plan sent to the terminal and arranges for repair materials and adjusts the schedule of workers based on the plan contents.

[0259] Step 8:

[0260] Work execution

[0261] The user will carry out the maintenance and repair work in accordance with the plan, specifically, carrying out any necessary repairs in an appropriate manner.

[0262] Step 9:

[0263] Work completion report

[0264] After completing the maintenance work, the user inputs the results of the work into the terminal and reports them to the server via an HTTP POST request. The report includes details of the work and the completion date and time.

[0265] Step 10:

[0266] Database recording and analysis

[0267] The server records the received work reports in the database using an SQL query (e.g. INSERT INTO maintenance_reports (infrastructure_id, work_details, completion_date) VALUES (...)).

[0268] The server analyzes the reports and generates feedback to help improve the next maintenance plan, thereby increasing the accuracy and efficiency of maintenance.

[0269] In this way, this system automates the maintenance and development of urban infrastructure efficiently and accurately, while also enabling flexible responses according to the user's emotional state.

[0270] Example 2

[0271] 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."

[0272] Conventional infrastructure management systems require a lot of manual work in collecting infrastructure information, analyzing it, and formulating and executing maintenance and development plans, which can lead to low efficiency. They also lack the ability to respond flexibly to users' emotional states, making effective infrastructure management difficult. Furthermore, insufficient pre-processing of collected data led to problems with the accuracy and reliability of analysis results.

[0273] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0274] In this invention, the server includes a means for extracting data from an existing infrastructure information database, a means for collecting real-time data from sensors and IoT devices and transmitting it to the server, and a means for preprocessing the extracted and collected data by filling in missing data and removing outliers. This improves the accuracy and reliability of data analysis. Furthermore, the server includes a means for automatically generating a maintenance and repair plan based on the analysis results, a means for collecting user voice and facial expression data and transmitting it to an emotion engine, a means for receiving the analysis results from the emotion engine and identifying the user's emotional state, and a means for customizing the content of the maintenance and repair plan notification based on the analysis results and the user's emotional state. This enables flexible responses according to the user's emotional state and achieves effective infrastructure management. The server also includes a means for notifying the user of the generated plan, reporting the user's work results to the server and recording them in a database, and a means for analyzing the report and providing feedback to improve the maintenance and repair plan. This significantly improves the efficiency and effectiveness of infrastructure management.

[0275] An "infrastructure information database" is an information system for storing and managing data related to urban infrastructure.

[0276] A "sensor" is a device that detects changes or conditions in the physical environment and transmits them as digital data.

[0277] An "IoT device" is an electronic device that can connect to other devices and systems via the Internet.

[0278] A "server" is a high-performance computing system for collecting, analyzing, storing, and communicating data.

[0279] An "AI model" is a mathematical model that uses artificial intelligence technology to analyze data and make predictions.

[0280] "Data preprocessing" refers to the process of performing operations such as filling in missing data and removing outliers before data analysis.

[0281] A "maintenance and development plan" is a plan that devisees repair methods and schedules for the maintenance and management of infrastructure.

[0282] A "user terminal" is a device through which a user communicates with a server and receives information.

[0283] The "emotion engine" is a system that analyzes the user's voice and facial expression data to identify their emotional state.

[0284] "Customizing notification content" means adjusting the presentation method and content of information to suit the user's specific situation and requirements.

[0285] An "HTTP POST request" is a type of HTTP protocol that allows a client to send data to a server.

[0286] A "database" is a system for systematically storing and managing digital data.

[0287] The "SMTP protocol" is a communication protocol for sending email.

[0288] "Feedback" is the process of reflecting on execution results and new data in order to improve and optimize the system.

[0289] "Reporting work results" means sending and recording the results of maintenance and repair work performed by the user to the server.

[0290] This invention is a system for improving the efficiency of urban infrastructure maintenance and development and automating manual tasks. It also achieves more effective infrastructure management by taking into account the user's emotional state and responding flexibly. This system consists of three main components: a server, a terminal, and a user.

[0291] The server first extracts the necessary data from an infrastructure information database. This data includes information on roads, buildings, water and sewerage systems, electricity, and other infrastructure. The extracted data is then input into an AI model, where it is analyzed. Missing data is filled in and outliers are removed. This is done using data processing libraries such as Pandas. The preprocessed data is then input into an AI model that includes deep learning and machine learning algorithms to evaluate the condition of the infrastructure.

[0292] The terminal uses sensors and IoT devices to collect real-time data on the site and send it to a server. For example, vibration sensors and cameras on the road detect cracks and subsidence and send the data to the server. The collected data is analyzed on the server to calculate the state of deterioration of the infrastructure and the priority of repairs.

[0293] The server automatically generates a maintenance plan based on the analysis results. For example, if a specific road section needs urgent repairs, the plan will include the repair method and specific schedule. This plan is stored in a database and registered using SQL queries.

[0294] Furthermore, the device collects the user's voice and facial expression data and sends it to the emotion engine. For example, the device can capture the user's facial expressions using a camera and analyze them with the emotion engine. The server receives the analysis results from the emotion engine and identifies the user's emotional state. This makes it possible to determine whether the user is feeling stressed or relaxed.

[0295] Based on the analysis results of the emotion engine, the server customizes the content of the maintenance and repair plan notification according to the user's emotional state. For example, if the user is in a high-stress state, the notification content will be brief, while if the user is relaxed, detailed information will be provided. Notifications are sent from the server to the user's device. Possible notification methods include email and in-app notifications. Sending email using the SMTP protocol is also included.

[0296] The user carries out maintenance work based on the notification content. The necessary materials and workers are arranged according to the plan. After the work is completed, the user reports the work results to the server via their terminal. The report content is sent to the server via an HTTP POST request and recorded in the database. The server analyzes the report content and provides feedback to improve the maintenance plan.

[0297] This allows the system to achieve efficient and accurate infrastructure management and respond flexibly to the user's emotional state.

[0298] As a concrete example, consider the maintenance of cracks on roads in a specific area. The server retrieves past maintenance history from a database, and the terminal (sensor) collects the progress of the cracks in real time and sends it to the server. The data is preprocessed and input into an AI model for analysis, and the severity of the cracks is evaluated. A repair plan is automatically generated based on the analysis results and saved in the database. The user's voice and facial expression data is collected and analyzed by an emotion engine, and the notification content is customized according to the user's emotional state and sent to the user's terminal. The user then carries out the work according to the notification and reports the results after completing the work.

[0299] An example of a prompt to input to a generative AI model is as follows:

[0300] "This system automates infrastructure maintenance in a specific area. First, it retrieves past maintenance information from a database and collects real-time data from sensors. Next, it analyzes this data using an AI model to automatically generate a repair plan. Furthermore, it analyzes the user's emotional state and customizes the content of notifications to achieve more effective management. For example, it can send a simple notification to a user in a stressed state and a detailed notification to a user in a relaxed state. As a concrete example, please consider road crack maintenance and explain the process."

[0301] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0302] Step 1: Data collection

[0303] The server first extracts infrastructure information such as roads, buildings, water supply and sewerage, and electricity from an existing infrastructure information database using an SQL query. For example, the query SELECT FROM infrastructure_data WHERE category='road' is used. This query retrieves data related to a specific infrastructure category.

[0304] The terminal collects real-time data from sensors and IoT devices and sends the data to a server. The sensors detect road cracks and subsidence information in real time and send it to the server using an HTTP POST request. Specific inputs include the sensor ID and measurement data, and the output is sent to the server.

[0305] Step 2: Data Preprocessing

[0306] The server preprocesses the collected data. This preprocessing includes filling in missing data and removing outliers. Specifically, it uses the Pandas library to clean the data frame. For example, it uses df.fillna(0, inplace=True) and filters outliers to improve the quality of the input data. The input for this step is the sensor data and data extracted from the database, and the output is clean data after preprocessing.

[0307] Step 3: Data analysis

[0308] The server inputs the preprocessed data into an AI model for analysis. For example, it uses deep learning and machine learning algorithms built with TensorFlow and Scikit-learn to assess the state of infrastructure deterioration and repair priorities. The input is the preprocessed data, and the output is the infrastructure condition assessment results. This identifies which sections are in urgent need of repair.

[0309] Step 4: Automatic generation of maintenance and repair plans

[0310] The server automatically generates a maintenance and repair plan based on the analysis results of the AI ​​model. For example, if it determines that a specific road section needs repair within a certain period of time, it will include the repair method and specific schedule in the plan. The input for this step is the analysis results of the AI ​​model, and the output is a repair plan. The repair plan is stored in a database and registered using SQL queries.

[0311] Step 5: Analysis by Emotion Engine

[0312] The device collects the user's voice and facial expression data and sends it to the emotion engine. It uses a camera and microphone to capture the user's facial expressions and voice in real time and sends it to an API that analyzes their emotional state. The input here is the user's voice and facial expression data, and the output is the analysis result by the emotion engine.

[0313] The server receives the analysis results from the emotion engine and identifies the user's emotional state, with the input being the analysis results from the emotion engine and the output being a determination of the user's emotional state.

[0314] Step 6: Adapting User Notifications

[0315] The server customizes the notification content for maintenance and repair plans based on the analysis results of the emotion engine according to the user's emotional state. For example, if the user is in a high-stress state, the notification content is brief, while if the user is relaxed, detailed information is provided. The input is the analysis results of the emotion engine and the maintenance and repair plans, and the output is the customized notification content.

[0316] The server sends the notification to the user's device. Possible notification methods include email and in-app notifications, and email may be sent using the SMTP protocol.

[0317] Step 7: Execute and report

[0318] The user performs maintenance and repair work based on the notification. The necessary materials and workers are arranged according to the plan. After completing the work, the user reports the work results to the server from the terminal. The input is the user's work results, and the output is the report to the server. The report is sent via an HTTP POST request and recorded in the database.

[0319] The server analyzes the results of the user's work and provides feedback to improve the maintenance plan. The input is the user's report, and the output is an improved maintenance plan.

[0320] (Application example 2)

[0321] 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."

[0322] In modern infrastructure management, traditional manual maintenance and repair work requires a great deal of time and effort, making efficient management difficult. In addition, notifications are sent without considering the user's feelings, which leaves a psychological burden on the user and prevents optimal work efficiency.

[0323] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for extracting data from an existing infrastructure information database, means for collecting real-time data from sensors and IoT devices and transmitting it to the server, means for inputting the extracted and collected data into an AI model and analyzing it, means for automatically generating a maintenance and repair plan based on the analysis results, means for notifying a user terminal of the generated maintenance and repair plan, means for collecting user voice and facial expression data, analyzing it with an emotion engine, and transmitting it to the server, means for customizing the notification content based on the analysis results of the emotion engine and transmitting it to the user terminal, means for reporting the user's work results to the server and recording them in a database, and means for analyzing the report content and providing feedback to improve the maintenance and repair plan. This enables efficient infrastructure management and provides appropriate notifications according to the user's emotional state, reducing the user's psychological burden and ensuring optimal work efficiency.

[0324] An "existing infrastructure information database" is an existing database for storing data on infrastructure such as roads, buildings, water supply and sewerage systems, and electricity.

[0325] "Sensors and IoT devices" are electronic devices that collect environmental data and status information in real time and send it to a server via a network.

[0326] "Server" means a computer system established to collect, analyze, store, and notify data.

[0327] An "AI model" is a model that includes an artificial intelligence algorithm used to analyze accumulated data and derive useful results.

[0328] "Maintenance and development plan" means a plan that includes the schedule and methods of repair and maintenance work, which is prepared based on the deterioration state of the infrastructure and the priority of repairs.

[0329] A "user terminal" is a device used to receive notifications and reports and perform management tasks, and includes smartphones, tablets, and PCs.

[0330] An "emotion engine" is software and algorithms that analyze a user's voice and facial expressions to recognize their emotional state.

[0331] The "means for customizing notification content" is a method for optimizing notification content and providing personalized information based on the analyzed emotion data.

[0332] "Means for analyzing the report content and providing feedback to improve maintenance and repair plans" refers to a method for analyzing the reported data from users and reflecting it in new maintenance and repair plans.

[0333] This invention is a system for streamlining infrastructure maintenance and repair in logistics centers, combined with a function that recognizes the user's emotional state and adapts the notification content. The system consists of three main components: a server, a terminal, and a user.

[0334] The server extracts data from an existing infrastructure information database. This data includes information such as the safety of shelves in a distribution center and cracks in the floor. It also collects real-time data from sensors and IoT devices and sends it to the server. The collected data is preprocessed using libraries such as Pandas to fill in missing data and remove outliers. The data is then input into an AI model (e.g., a deep learning model or machine learning algorithm) to analyze the infrastructure's deterioration status and repair priorities.

[0335] The server automatically generates a maintenance and repair plan based on the analysis results. This plan includes specific repair methods and schedules and is saved in a database. The generated maintenance and repair plan is then sent to the user's device, which could be a smartphone or tablet.

[0336] Furthermore, the server collects the user's voice and facial expression data and analyzes it using an emotion engine (e.g., Microsoft Azure Emotion API). Based on the analysis results of the emotion engine, the notification content is customized and sent to the user's device. For example, if the user is stressed, a simple notification is sent, and if the user is relaxed, a detailed notification is sent.

[0337] The user performs maintenance and repair work based on the notification and reports the results after completion. The report is sent to the server and recorded in the database. Finally, the server analyzes the report and provides feedback to improve the maintenance and repair plan. This makes future plans more accurate and efficient.

[0338] As a concrete example, consider the case where the safety of shelves in a logistics center has deteriorated. The server retrieves maintenance history from a past database, and sensors collect information on the shelf's condition in real time and send it to the server. The server preprocesses the data, evaluates the shelf's safety using an AI model, and creates a repair plan. The server customizes the notification content based on the user's emotional state and sends it to the user's device. The user then carries out repair work in accordance with the notification and reports the results.

[0339] Example prompt sentence:

[0340] "Check the infrastructure condition in your distribution center. Use sensors and cameras to collect shelf safety data and send it to a server. The server will analyze the data and automatically generate repair plans. Send brief or detailed notifications depending on the emotional state of your staff."

[0341] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0342] Step 1:

[0343] The server extracts the necessary data from an existing infrastructure information database. Specifically, it obtains infrastructure information such as shelves and floors within the logistics center using an SQL query (e.g., SELECT FROM infrastructure_data WHERE category='shelf'). The input is the infrastructure information in the database, and the output is infrastructure data converted into a format that can be processed within the server.

[0344] Step 2:

[0345] Terminals (sensors and IoT devices) collect real-time data from within the logistics center and send it to a server. For example, cracks in the floor and damage to shelves are measured by sensors and sent to the server via wireless communication. The input is environmental data collected in real time, and the output is the raw data sent to the server.

[0346] Step 3:

[0347] The server preprocesses the collected data. Specifically, it cleans the data frame using the Pandas library, imputes missing data (e.g., df.fillna(method='ffill')), and removes outliers. The input is raw data obtained from sensors or databases, and the output is clean data after preprocessing.

[0348] Step 4:

[0349] The server inputs the preprocessed data into the AI ​​model for analysis. Specifically, it uses a deep learning model or machine learning algorithm to analyze the data and evaluate the infrastructure's deterioration status and repair priority. The input is clean data, and the output is infrastructure condition assessment data.

[0350] Step 5:

[0351] The server automatically generates a maintenance plan based on the analysis results. For example, it determines a specific repair method and schedule for a certain shelf section and stores it in the database using an SQL query (e.g., INSERT INTO maintenance_schedule (infrastructure_id, repair_method, schedule_date) VALUES (...)). The input is the infrastructure condition assessment data, and the output is a specific maintenance plan.

[0352] Step 6:

[0353] The device collects the user's voice and facial expression data and sends it to an emotion engine for analysis. Specifically, data is collected using the smartphone's camera and microphone, and emotion analysis is performed using an emotion engine such as Microsoft Azure Emotion API. The input is the user's voice and facial expression data, and the output is the emotion analysis results.

[0354] Step 7:

[0355] The server receives the analysis results of the emotion engine and customizes the notification content according to the user's emotional state. For example, if the user is in a stressful state, it prepares a brief notification, and if the user is in a relaxed state, it prepares a detailed notification. The input is the emotion analysis result, and the output is the customized notification content.

[0356] Step 8:

[0357] The server sends the customized notification content to the user device. Specifically, it notifies the user using an in-app notification or email (e.g., sending an email using the SMTP protocol). The input is the customized notification content, and the output is the notification sent to the user device.

[0358] Step 9:

[0359] The user performs maintenance and repair work based on the notification. Specifically, the user performs the necessary repairs according to the procedure manual and records the progress of the work. The input is the notification content, and the output is the completed work results.

[0360] Step 10:

[0361] The user reports the results of their work to the server. Specifically, they send the report via an HTTP POST request through the app. The input is the work result, and the output is the report data recorded in the database.

[0362] 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.

[0363] 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.

[0364] 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.

[0365] [Second embodiment]

[0366] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0367] 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.

[0368] 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).

[0369] 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.

[0370] 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.

[0371] 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).

[0372] 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.

[0373] 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.

[0374] 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.

[0375] 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.

[0376] 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.

[0377] 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."

[0378] This invention is a system that efficiently automates a series of tasks related to the maintenance and development of urban infrastructure. This system consists of three main components: a server, a terminal, and a user, which work in conjunction with each other.

[0379] The system is responsible for the following steps:

[0380] 1. Data Collection

[0381] The server extracts the necessary data from an existing infrastructure information database, including information on roads, buildings, water and sewerage systems, and electricity.

[0382] Terminals (sensors and IoT devices) collect real-time data from the site and send it to a server, which reflects the latest infrastructure status.

[0383] 2. Data Analysis

[0384] The server inputs the collected data into an AI model for analysis, which uses deep learning and machine learning algorithms to assess the state of the infrastructure and detect and predict anomalies.

[0385] The analysis includes the degree of deterioration of infrastructure and maintenance priorities. For example, the progression of cracks and the need for repairs can be quantified, enabling specific infrastructure assessments.

[0386] 3. Automatic generation of maintenance and repair plans

[0387] Based on the analysis results obtained from the AI ​​model, the server automatically generates an optimal maintenance plan, which includes details on which infrastructure to maintain, when, and how.

[0388] For example, if it is determined that a particular road section needs repair within a week, the repair method (patch repair, surface scraping / regeneration work, etc.) and a specific schedule will be generated.

[0389] 4. User Notices and Instructions

[0390] The server notifies the user device of the generated maintenance plan via email or in-app notification.

[0391] The user (maintenance staff) receives the notification, checks the plan contents, and prepares for the work, which specifically includes arranging repair materials and adjusting the schedule of workers.

[0392] 5. Work Completion Report and Feedback

[0393] After completing the maintenance work, the user reports the results to the server via the terminal, including details of the work and the date and time of completion.

[0394] The server records the reported work results in a database and provides feedback to improve the next maintenance and repair plan, resulting in more accurate and efficient maintenance and repair.

[0395] Specific examples

[0396] For example, consider a scenario involving the maintenance of major roads in a city.

[0397] 1. Data Collection

[0398] The server collects data on the past maintenance history of roads throughout the city, and sensors installed on the roads collect data on cracks and subsidence in real time and send it to the server.

[0399] 2. Data Analysis

[0400] The server inputs the collected data into an AI model to analyze the road's deterioration, which then assesses the extent of cracks and calculates the need for repairs.

[0401] 3. Automatic generation of maintenance and repair plans

[0402] The server determines whether a specific road section requires urgent repairs based on the extent of the cracks, and then automatically generates a plan with specific repair methods and schedules.

[0403] 4. User Notices and Instructions

[0404] The server notifies the maintenance staff of the generated repair plan.

[0405] The user receives the notification, checks the plan, and arranges for the necessary materials and workers.

[0406] 5. Work Completion Report and Feedback

[0407] After completing the repair work, the user reports the results of the work on the terminal.

[0408] The server records the report in a database and uses it to formulate the next plan.

[0409] In this way, by using the present invention, a system is provided that can efficiently and accurately carry out a series of tasks related to the maintenance and development of urban infrastructure, making it possible to reduce costs and speed up the tasks.

[0410] The processing flow will be explained below.

[0411] Step 1:

[0412] Data collection

[0413] The server extracts the infrastructure's maintenance history and status information from the infrastructure information database using an SQL query, for example, executing a command such as SELECT FROM infrastructure_data WHERE category='road'.

[0414] Step 2:

[0415] Receiving real-time data

[0416] Terminals (sensors and IoT devices) measure the condition of local infrastructure in real time, for example, a sensor detecting the depth of cracks in the road, and send that data to the server via an HTTP POST request.

[0417] Step 3:

[0418] Data Integration

[0419] The server integrates information retrieved from the database with real-time data received from the device. This data is managed in JSON format or as a data frame. The data is formatted using libraries such as Pandas.

[0420] Step 4:

[0421] Data analysis

[0422] The server preprocesses the integrated data before inputting it into the AI ​​model. Specifically, it complements missing data and removes outliers, which allows for accurate analysis.

[0423] The server then inputs the preprocessed data into an AI model for analysis, which uses deep learning or machine learning algorithms to assess the condition of the infrastructure and calculate whether there are any abnormalities or the degree of degradation.

[0424] Step 5:

[0425] Automatic generation of maintenance and repair plans

[0426] The server automatically generates a maintenance plan based on the analysis results of the AI ​​model. For example, if a section of road is cracked, the server will incorporate repair methods (such as patch repairs or surface scraping and restoration work) and a specific schedule into the plan.

[0427] The generated plan is stored in the database using an SQL query, for example with a command like INSERT INTO maintenance_schedule (infrastructure_id, repair_method, schedule_date) VALUES (...).

[0428] Step 6:

[0429] notification

[0430] The server notifies the user device of the generated maintenance plan via email or in-app notification. One method of notification is to send email using the SMTP protocol.

[0431] Step 7:

[0432] User confirmation and preparation

[0433] The user (maintenance staff) receives the notification sent to their terminal, checks the plan, and arranges for repair materials and adjusts the schedule of workers.

[0434] Step 8:

[0435] Work execution

[0436] The user carries out maintenance and repair work based on a plan, the details of which are described in the plan and are carried out accordingly.

[0437] Step 9:

[0438] Work completion report

[0439] After completing the maintenance work, the user inputs the work content and the completion date and time into the terminal and reports it to the server.

[0440] The device sends the work to the server via an HTTP POST request, and the report includes details of the completed work.

[0441] Step 10:

[0442] Database recording and analysis

[0443] The server records the received work reports in a database, for example using an SQL query like INSERT INTO maintenance_reports (infrastructure_id, work_details, completion_date) VALUES (...).

[0444] The server analyzes the report and generates feedback to improve the next maintenance and repair plan, which allows for more accurate planning.

[0445] Through the above processing steps, this system can automate the maintenance and development of urban infrastructure efficiently and accurately.

[0446] Example 1

[0447] 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."

[0448] Traditional methods for maintaining and upgrading urban infrastructure involve a lot of manual work, making them inefficient and time-consuming. It also makes it difficult to prioritize maintenance work and quickly detect abnormalities, which increases the risk of infrastructure deterioration and accidents. Furthermore, the formulation of maintenance plans relies on human judgment and is prone to subjective factors, making optimization difficult. These issues need to be addressed.

[0449] 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.

[0450] In this invention, the server includes a means for extracting data from an existing infrastructure information database, a means for collecting real-time data from sensors and IoT devices and sending it to the server, and a means for preprocessing the extracted and collected data and inputting it into an AI model for analysis. This allows for an accurate understanding of the infrastructure status, automatic generation of efficient maintenance and repair plans, and rapid anomaly detection.

[0451] An "existing infrastructure information database" is a data storage that stores past records and current status data related to urban infrastructure.

[0452] "Sensors and IoT devices" are electronic devices that collect data from the physical environment in real time and send it to a server over a network.

[0453] "Preprocessing" is the process of removing noise from collected data and extracting and shaping the necessary information.

[0454] An "AI model" is a collection of algorithms used to realize artificial intelligence, and here it specifically refers to deep learning models and machine learning algorithms.

[0455] A "maintenance and improvement plan" is a specific plan for predicting deterioration and abnormalities in infrastructure and carrying out repairs and renovations at the appropriate time and in the appropriate manner.

[0456] A "user terminal" is a device such as a computer or smartphone used by a maintenance technician.

[0457] "Feedback" refers to analyzing the results of maintenance work carried out and providing information to be used in planning the next maintenance and repair work.

[0458] This invention is a system that efficiently automates a series of tasks related to the maintenance and development of urban infrastructure. This system consists of three main components: a server, a terminal, and a user, each of which plays a specific role.

[0459] Hardware and Software Configuration

[0460] The server consists of a high-performance computer and is equipped with a database management system (e.g., MySQL), a data processing framework (e.g., PySpark), and a machine learning framework (e.g., TensorFlow or PyTorch).

[0461] Terminals consist of sensors and IoT devices that collect real-time data using wireless communication technologies such as LoRa and Zigbee. Terminals also include smartphones and tablets used by users.

[0462] Users are maintenance personnel and others who connect to the system through a dedicated mobile application.

[0463] What the program does

[0464] The server first extracts data on roads, buildings, water and sewer systems, and electricity from existing infrastructure information databases. It then collects real-time data from on-site sensors and IoT devices and preprocesses it. Preprocessing includes removing noise and extracting necessary information. The preprocessed data is then input into a generative AI model. This AI model uses deep learning and machine learning algorithms to assess the condition of the infrastructure and detect and predict anomalies.

[0465] To illustrate, here's an example prompt:

[0466] "Evaluate the extent of cracking on Section A of a major road in the city. Then calculate the need for repairs."

[0467] Based on the analysis results, the server automatically generates a maintenance and repair plan, which includes details on which infrastructure to maintain and repair, when, and how. For example, it may determine that a specific road section needs repair within a week, and generate the repair method (patching, surface scraping, restoration work, etc.) and schedule.

[0468] The server notifies the user's device of the generated maintenance and repair plan via email or in-app notification. The user receives the notification, checks the plan, and arranges for the necessary materials and workers. After the repair work is completed, the user reports the work results via their device. The server records the reported work results in a database and provides feedback to improve the next maintenance and repair plan.

[0469] In this way, this system can efficiently and accurately carry out a series of tasks related to the maintenance and development of urban infrastructure. Specific data analysis and automatic generation of maintenance plans are performed using machine learning algorithms, resulting in cost reduction and speed.

[0470] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0471] Step 1: Data extraction

[0472] The server extracts data from existing infrastructure information databases. For example, the server retrieves historical maintenance data for roads, buildings, water and sewerage systems, electricity, etc. from a MySQL database. The input for this data extraction is a database query, and the output is a set of extracted infrastructure data.

[0473] Step 2: Real-time data collection

[0474] Terminals (sensors and IoT devices) collect real-time data on-site and send it to a server. For example, sensors installed on roads collect data on cracks and subsidence and send it to a server via wireless communication technology (such as LoRa or Zigbee). The input of this collection is the real-time observation data of the sensors, and the output is the latest infrastructure status data sent to the server.

[0475] Step 3: Data Preprocessing

[0476] The server pre-processes the extracted and collected data, removing noise, extracting necessary information, and shaping the data, for example filtering outliers and scaling the data. The input of this pre-processing is raw data, and the output is pre-processed, clean data.

[0477] Step 4: Input data into the AI ​​model

[0478] The server inputs the preprocessed data into a generative AI model. This AI model uses deep learning frameworks such as TensorFlow and PyTorch. An example prompt is, "Evaluate the degree of cracking on section A of the city's main road. Then, calculate the need for repairs." The input for this data input is the preprocessed data and the prompt, and the output is the analysis results from the AI ​​model.

[0479] Step 5: Automatic generation of maintenance and repair plans

[0480] The server automatically generates a maintenance and repair plan based on the analysis results from the AI ​​model. For example, it may determine that a specific road section requires urgent repairs and generate a repair method (patching, surface scraping, restoration work, etc.) and schedule. The input for this plan generation is the analysis results from the AI ​​model, and the output is a specific maintenance and repair plan.

[0481] Step 6: Maintenance Plan Notification

[0482] The server notifies the user device of the generated maintenance plan. Notification methods include email and in-app notification. For example, a notification may be sent to the maintenance technician's smartphone app. The input of this notification is the maintenance plan, and the output is a notification message sent to the user device.

[0483] Step 7: Prepare and perform maintenance work

[0484] The user (maintenance staff) receives the notification, checks the plan contents, and arranges for the necessary materials and workers. Specifically, they arrange for repair materials and adjust the schedule of workers. The input for this preparation is the notified maintenance and repair plan, and the output is the maintenance work schedule and the material arrangement status.

[0485] Step 8: Report work completed

[0486] After completing maintenance work, the user reports the results to the server via their device. The report includes details of the work and the date and time of completion. For example, the report can be made using a dedicated mobile application. The input of this report is the details of the maintenance work performed, and the output is a work completion report sent to the server.

[0487] Step 9: Record and feedback

[0488] The server records the reported work results in a database and provides feedback to improve the next maintenance plan. For example, it analyzes the reports and adjusts algorithms to improve the accuracy of future maintenance plans. The input to this recording and feedback is the work completion report, and the output is updated database records and improved maintenance plan algorithms.

[0489] (Application example 1)

[0490] 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."

[0491] In large-scale facilities such as logistics centers, it is important to perform infrastructure maintenance and repairs efficiently and quickly. However, with conventional systems, data collection and analysis, and the creation and execution of maintenance plans are often done manually, which is time-consuming and labor-intensive, and prone to human error. Furthermore, there is a lack of tools that enable on-site workers to quickly grasp the situation and make appropriate decisions. To solve these problems, an automated system is needed that can monitor the status of infrastructure in real time and respond quickly and appropriately.

[0492] 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.

[0493] In this invention, the server includes a means for extracting data from an existing infrastructure information database, a means for collecting real-time data from sensors and IoT devices and sending it to the server, and a means for notifying the smart glasses of a maintenance and repair plan based on the analysis results so that the user can visually confirm it. This enables the automation of infrastructure maintenance and repair in logistics centers, making it possible to perform the work efficiently and quickly.

[0494] - The "Infrastructure Information Database" is a database for storing and managing infrastructure data related to facilities such as logistics centers.

[0495] A "sensor" is a device that measures physical or chemical quantities and collects that information as digital data.

[0496] An "IoT device" is a device that has the ability to send and receive data via the Internet and is used to collect environmental data at logistics centers.

[0497] "Real-time data" refers to the latest data that changes every moment and is obtained from sensors and IoT devices.

[0498] A "server" is a central computer that collects, processes, analyzes data, and provides information to other devices and users.

[0499] An "AI model" is an artificial intelligence system that includes algorithms for learning data and predicting analysis results.

[0500] A "deep learning model" is a machine learning model that uses a multi-layer neural network to learn and analyze complex data.

[0501] "Machine learning algorithm" is a general term for algorithms that learn patterns and rules from data.

[0502] A "maintenance and repair plan" is a plan that outlines the content and schedule of work required to maintain the condition of the infrastructure at a logistics center.

[0503] A "user terminal" is a device used to operate the system and receive information.

[0504] "Smart glasses" are wearable devices that have the ability to visually display information and are used by users when working on-site.

[0505] A "database" is a system that structures and stores collected data so that it can be accessed, managed, and analyzed effectively later.

[0506] "Feedback" is the process of improving future maintenance and repair plans based on information obtained from analysis and work results.

[0507] This invention is a system that efficiently automates the maintenance and upkeep of logistics center infrastructure. This system consists of three main components: a server, a terminal, and a user, all of which work in conjunction with each other.

[0508] The server has the function of extracting necessary data from existing infrastructure information databases. Sensors and IoT devices collect real-time data and send it to the server. The server inputs the data into an AI model for analysis. Deep learning models and machine learning algorithms are used for the analysis. Based on this analysis, maintenance and repair plans are automatically generated.

[0509] The generated maintenance and repair plan is sent to the user's device. The user's device may also include smart glasses, allowing the user to visually check the plan. The user receives the notification, checks the plan, and carries out the work. When the repair is complete, the results are reported to the server via the device. The server records the report in a database and provides feedback to improve the next maintenance and repair plan.

[0510] The system's hardware includes various sensors such as temperature, humidity, and vibration sensors, while the software uses AI frameworks such as TensorFlow and PyTorch.

[0511] Data collection, processing, and calculation are carried out as follows: Data collection is carried out by acquiring real-time data from sensors and IoT devices and sending it to a server. Data processing is carried out by the server inputting the data into an AI model and performing preprocessing to make predictions. Data calculation is carried out by analyzing the data based on the patterns learned by the AI ​​model and generating maintenance and repair plans.

[0512] As a concrete example, consider the maintenance of conveyor belts in a logistics center. If data from sensors includes temperature, humidity, and vibration data, a user wearing smart glasses patrols the area and finds any abnormalities. Images of the abnormal areas are collected and sent to a server. The server inputs the data into an AI model and, based on the analysis results, notifies the smart glasses of a maintenance and repair plan, such as, "There is an abnormality in the conveyor belt in section A. Repairs are required. The recommended repair method is to replace the belt."

[0513] An example of an input prompt for a generative AI model is as follows:

[0514] "Based on temperature, humidity, vibration data and image data, determine the degree of deterioration of infrastructure within the logistics center and the necessary repairs."

[0515] This system will enable efficient and rapid maintenance and repair of logistics center infrastructure, improving the accuracy and speed of work.

[0516] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0517] Step 1: Collect data

[0518] The server extracts the necessary data from the existing infrastructure information database. Terminals (sensors and IoT devices) collect real-time data within the logistics center and send it to the server. In this step, data such as temperature, humidity, and vibration are collected. The input is real-time data from the infrastructure information database and sensors, and the output is data integrated within the server. Specifically, the server executes a database query, and the terminals send the collected data as packets.

[0519] Step 2: Preprocessing the data

[0520] The server processes the collected data into a format suitable for the AI ​​model. Specifically, it cleanses, normalizes, and extracts features from the data. The input to this step is integrated real-time data, and the output is preprocessed data. Specifically, it complements missing values ​​in the data and converts values ​​to the required range.

[0521] Step 3: Analyze the data

[0522] The server inputs the preprocessed data into the AI ​​model for analysis. The AI ​​model analyzes the data using deep learning models and machine learning algorithms to assess the condition of the infrastructure. The input for this step is the preprocessed data, and the output is the analysis results regarding the degree of deterioration and the need for repairs. Specifically, the data is fed into the model and the inference results are obtained.

[0523] Step 4: Generate a maintenance plan

[0524] The server automatically generates a maintenance and repair plan based on the analysis results. This plan includes specific repair methods and schedules. The input is the analysis results, and the output is the generated maintenance and repair plan. Specifically, the server creates an optimal rule-based plan based on the analysis results.

[0525] Step 5: Notification

[0526] The server notifies the smart glasses of the generated maintenance plan. The user visually checks the plan and performs the work. The input is the generated maintenance plan, and the output is the plan checked by the user. Specifically, text and images are sent to the smart glasses via the notification system.

[0527] Step 6: Report work completed

[0528] After completing a task, the user reports the results to the server through the smart glasses. The input is the task completion report, and the output is the report data recorded on the server. Specifically, the user inputs and transmits the report content using the operation panel of the smart glasses.

[0529] Step 7: Feedback

[0530] The server records the reported work results in a database and provides feedback to improve the next maintenance plan. The input is the reported work results data, and the output is an updated maintenance plan. Specific operations include updating the database and retraining the AI ​​model.

[0531] 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.

[0532] This invention utilizes AI technology for the maintenance and development of urban infrastructure, automating traditional manual tasks and combining it with an emotion engine that recognizes user emotions. This system consists of three main components: a server, a terminal, and a user, each of which plays a specific role. Furthermore, by analyzing the user's emotional state and adapting notification content, more effective infrastructure management is achieved.

[0533] The main processing steps of the system are:

[0534] 1. Data Collection

[0535] The server extracts data from the infrastructure information database. The data includes infrastructure information such as roads, buildings, water, sewerage, and electricity. It retrieves the data using an SQL query, for example, SELECT FROM infrastructure_data WHERE category='road'.

[0536] Terminals (sensors and IoT devices) collect real-time data from the site and send it to a server. For example, data on road cracks and subsidence is sent from sensors.

[0537] 2. Data Analysis

[0538] The server inputs the collected data into an AI model for analysis, which includes preprocessing the data to fill in missing data and remove outliers, such as cleaning the data frame using the Pandas library.

[0539] The server then inputs the pre-processed data into an AI model that uses deep learning or machine learning algorithms to assess the condition of the infrastructure and calculate the infrastructure's deterioration status and repair priorities.

[0540] 3. Automatic generation of maintenance and repair plans

[0541] The server automatically generates a maintenance plan based on the analysis results. For example, if it determines that a certain road section needs repair within a certain period of time, it will include the repair method and specific schedule in the plan.

[0542] The generated plan is stored in the database using an SQL query, for example INSERT INTO maintenance_schedule (infrastructure_id, repair_method, schedule_date) VALUES (...).

[0543] 4. Analysis by Emotion Engine

[0544] The device collects the user's voice and facial expression data and sends it to the emotion engine. For example, the device uses a camera or microphone to collect the user's facial expressions and voice and analyzes their emotional state.

[0545] The server receives the analysis results from the emotion engine and identifies the user's emotional state, making it possible to determine whether the user is stressed or relaxed.

[0546] 5. User Notification Adaptation

[0547] Based on the analysis results of the emotion engine, the server customizes the content of the maintenance and repair plan notification according to the user's emotional state. For example, if the user is under high stress, the notification content will be concise and clear, while if the user is relaxed, detailed information will be provided.

[0548] The server sends the notification to the user's device. Possible notification methods include email and in-app notifications. One method is to send email using the SMTP protocol.

[0549] 6. Work execution and reporting

[0550] Users can carry out maintenance and repair work based on the notification, and arrange for the necessary materials and workers in advance to ensure the work proceeds smoothly according to plan.

[0551] After completing the task, the user reports the results to the server via an HTTP POST request, which is then recorded in the database.

[0552] As a concrete example, consider road crack maintenance in a particular area.

[0553] 1. For data collection, the server retrieves past maintenance history from the database, and the terminal (sensor) collects the progress of cracks in real time and sends it to the server.

[0554] 2. In data analysis, the server preprocesses the collected data and inputs it into an AI model for analysis, assessing the severity of cracks and identifying which sections need repairs.

[0555] 3. When automatically generating maintenance and repair plans, the server creates a repair plan based on the results of the AI ​​model and saves it in a database.

[0556] 4. In analysis using an emotion engine, the device collects the user's voice and facial expressions, analyzes them using the emotion engine, and the server receives the results.

[0557] 5. In user notification adaptation, the server customizes the notification content according to the user's emotional state and sends it to the user's terminal.

[0558] 6. Work execution and reporting: The user carries out repair work according to the notification and reports the results after the work is completed.

[0559] These steps enable the system to achieve efficient and accurate infrastructure management and to respond flexibly to the user's emotional state.

[0560] The processing flow will be explained below.

[0561] Step 1:

[0562] Data collection

[0563] The server extracts past maintenance history and status data from the existing infrastructure information database using an SQL query such as SELECT FROM infrastructure_data WHERE category='road'.

[0564] Terminals (sensors and IoT devices) measure the local infrastructure condition (e.g., road cracks and subsidence) in real time and send the data to the server via an HTTP POST request.

[0565] Step 2:

[0566] Real-time data integration

[0567] The server integrates historical data extracted from the database with real-time data sent from the terminal, and uses Python's Pandas library to clean the data, impute missing values, and remove outliers.

[0568] Step 3:

[0569] Data analysis

[0570] The server inputs the preprocessed data into an AI model to analyze the condition of the infrastructure. Deep learning algorithms (e.g., TensorFlow and PyTorch) are used to calculate the state of deterioration of the infrastructure and the priority of repairs. Specifically, the progress of cracks and the rate of subsidence are evaluated.

[0571] Step 4:

[0572] Automatic generation of maintenance and repair plans

[0573] The server automatically generates a maintenance plan based on the analysis results of the AI ​​model. For example, if it determines that a specific road section needs patch repair within a week, it will include the repair method and specific schedule in the plan. The plan is generated in JSON format.

[0574] The server saves the generated maintenance schedule in the database using an SQL query (e.g. INSERT INTO maintenance_schedule (infrastructure_id, repair_method, schedule_date) VALUES (...)).

[0575] Step 5:

[0576] Analysis by emotion engine

[0577] The device collects the user's voice and facial expression data and sends it to the emotion engine. It uses a camera and microphone to capture the user's facial expressions and voice.

[0578] The server analyzes the data sent from the emotion engine and determines the user's emotional state, for example, detecting whether the user is stressed or relaxed, using emotion recognition algorithms.

[0579] Step 6:

[0580] User notification adaptation

[0581] The server customizes the notification content according to the user's emotional state. For example, if the user is in a high-stress state, the notification content is brief and provides only the minimum necessary information. On the other hand, if the user is in a relaxed state, the server provides detailed notification content.

[0582] The server sends notifications to the user's device. Scheduled notifications can be sent via email or in-app notifications. Emails can also be sent using the SMTP protocol.

[0583] Step 7:

[0584] User confirmation and preparation

[0585] The user checks the maintenance and repair plan sent to the terminal and arranges for repair materials and adjusts the schedule of workers based on the plan contents.

[0586] Step 8:

[0587] Work execution

[0588] The user will carry out the maintenance and repair work in accordance with the plan, specifically, carrying out any necessary repairs in an appropriate manner.

[0589] Step 9:

[0590] Work completion report

[0591] After completing the maintenance work, the user inputs the results of the work into the terminal and reports them to the server via an HTTP POST request. The report includes details of the work and the completion date and time.

[0592] Step 10:

[0593] Database recording and analysis

[0594] The server records the received work reports in the database using an SQL query (e.g. INSERT INTO maintenance_reports (infrastructure_id, work_details, completion_date) VALUES (...)).

[0595] The server analyzes the reports and generates feedback to help improve the next maintenance plan, thereby increasing the accuracy and efficiency of maintenance.

[0596] In this way, this system automates the maintenance and development of urban infrastructure efficiently and accurately, while also enabling flexible responses according to the user's emotional state.

[0597] Example 2

[0598] 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."

[0599] Conventional infrastructure management systems require a lot of manual work in collecting infrastructure information, analyzing it, and formulating and executing maintenance and development plans, which can lead to low efficiency. They also lack the ability to respond flexibly to users' emotional states, making effective infrastructure management difficult. Furthermore, insufficient pre-processing of collected data led to problems with the accuracy and reliability of analysis results.

[0600] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0601] In this invention, the server includes a means for extracting data from an existing infrastructure information database, a means for collecting real-time data from sensors and IoT devices and transmitting it to the server, and a means for preprocessing the extracted and collected data by filling in missing data and removing outliers. This improves the accuracy and reliability of data analysis. Furthermore, the server includes a means for automatically generating a maintenance and repair plan based on the analysis results, a means for collecting user voice and facial expression data and transmitting it to an emotion engine, a means for receiving the analysis results from the emotion engine and identifying the user's emotional state, and a means for customizing the content of the maintenance and repair plan notification based on the analysis results and the user's emotional state. This enables flexible responses according to the user's emotional state and achieves effective infrastructure management. The server also includes a means for notifying the user of the generated plan, reporting the user's work results to the server and recording them in a database, and a means for analyzing the report and providing feedback to improve the maintenance and repair plan. This significantly improves the efficiency and effectiveness of infrastructure management.

[0602] An "infrastructure information database" is an information system for storing and managing data related to urban infrastructure.

[0603] A "sensor" is a device that detects changes or conditions in the physical environment and transmits them as digital data.

[0604] An "IoT device" is an electronic device that can connect to other devices and systems via the Internet.

[0605] A "server" is a high-performance computing system for collecting, analyzing, storing, and communicating data.

[0606] An "AI model" is a mathematical model that uses artificial intelligence technology to analyze data and make predictions.

[0607] "Data preprocessing" refers to the process of performing operations such as filling in missing data and removing outliers before data analysis.

[0608] A "maintenance and development plan" is a plan that devisees repair methods and schedules for the maintenance and management of infrastructure.

[0609] A "user terminal" is a device through which a user communicates with a server and receives information.

[0610] The "emotion engine" is a system that analyzes the user's voice and facial expression data to identify their emotional state.

[0611] "Customizing notification content" means adjusting the presentation method and content of information to suit the user's specific situation and requirements.

[0612] An "HTTP POST request" is a type of HTTP protocol that allows a client to send data to a server.

[0613] A "database" is a system for systematically storing and managing digital data.

[0614] The "SMTP protocol" is a communication protocol for sending email.

[0615] "Feedback" is the process of reflecting on execution results and new data in order to improve and optimize the system.

[0616] "Reporting work results" means sending and recording the results of maintenance and repair work performed by the user to the server.

[0617] This invention is a system for improving the efficiency of urban infrastructure maintenance and development and automating manual tasks. It also achieves more effective infrastructure management by taking into account the user's emotional state and responding flexibly. This system consists of three main components: a server, a terminal, and a user.

[0618] The server first extracts the necessary data from an infrastructure information database. This data includes information on roads, buildings, water and sewerage systems, electricity, and other infrastructure. The extracted data is then input into an AI model, where it is analyzed. Missing data is filled in and outliers are removed. This is done using data processing libraries such as Pandas. The preprocessed data is then input into an AI model that includes deep learning and machine learning algorithms to evaluate the condition of the infrastructure.

[0619] The terminal uses sensors and IoT devices to collect real-time data on the site and send it to a server. For example, vibration sensors and cameras on the road detect cracks and subsidence and send the data to the server. The collected data is analyzed on the server to calculate the state of deterioration of the infrastructure and the priority of repairs.

[0620] The server automatically generates a maintenance plan based on the analysis results. For example, if a specific road section needs urgent repairs, the plan will include the repair method and specific schedule. This plan is stored in a database and registered using SQL queries.

[0621] Furthermore, the device collects the user's voice and facial expression data and sends it to the emotion engine. For example, the device can capture the user's facial expressions using a camera and analyze them with the emotion engine. The server receives the analysis results from the emotion engine and identifies the user's emotional state. This makes it possible to determine whether the user is feeling stressed or relaxed.

[0622] Based on the analysis results of the emotion engine, the server customizes the content of the maintenance and repair plan notification according to the user's emotional state. For example, if the user is in a high-stress state, the notification content will be brief, while if the user is relaxed, detailed information will be provided. Notifications are sent from the server to the user's device. Possible notification methods include email and in-app notifications. Sending email using the SMTP protocol is also included.

[0623] The user carries out maintenance work based on the notification content. The necessary materials and workers are arranged according to the plan. After the work is completed, the user reports the work results to the server via their terminal. The report content is sent to the server via an HTTP POST request and recorded in the database. The server analyzes the report content and provides feedback to improve the maintenance plan.

[0624] This allows the system to achieve efficient and accurate infrastructure management and respond flexibly to the user's emotional state.

[0625] As a concrete example, consider the maintenance of cracks on roads in a specific area. The server retrieves past maintenance history from a database, and the terminal (sensor) collects the progress of the cracks in real time and sends it to the server. The data is preprocessed and input into an AI model for analysis, and the severity of the cracks is evaluated. A repair plan is automatically generated based on the analysis results and saved in the database. The user's voice and facial expression data is collected and analyzed by an emotion engine, and the notification content is customized according to the user's emotional state and sent to the user's terminal. The user then carries out the work according to the notification and reports the results after completing the work.

[0626] An example of a prompt to input to a generative AI model is as follows:

[0627] "This system automates infrastructure maintenance in a specific area. First, it retrieves past maintenance information from a database and collects real-time data from sensors. Next, it analyzes this data using an AI model to automatically generate a repair plan. Furthermore, it analyzes the user's emotional state and customizes the content of notifications to achieve more effective management. For example, it can send a simple notification to a user in a stressed state and a detailed notification to a user in a relaxed state. As a concrete example, please consider road crack maintenance and explain the process."

[0628] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0629] Step 1: Data collection

[0630] The server first extracts infrastructure information such as roads, buildings, water supply and sewerage, and electricity from an existing infrastructure information database using an SQL query. For example, the query SELECT FROM infrastructure_data WHERE category='road' is used. This query retrieves data related to a specific infrastructure category.

[0631] The terminal collects real-time data from sensors and IoT devices and sends the data to a server. The sensors detect road cracks and subsidence information in real time and send it to the server using an HTTP POST request. Specific inputs include the sensor ID and measurement data, and the output is sent to the server.

[0632] Step 2: Data Preprocessing

[0633] The server preprocesses the collected data. This preprocessing includes filling in missing data and removing outliers. Specifically, it uses the Pandas library to clean the data frame. For example, it uses df.fillna(0, inplace=True) and filters outliers to improve the quality of the input data. The input for this step is the sensor data and data extracted from the database, and the output is clean data after preprocessing.

[0634] Step 3: Data analysis

[0635] The server inputs the preprocessed data into an AI model for analysis. For example, it uses deep learning and machine learning algorithms built with TensorFlow and Scikit-learn to assess the state of infrastructure deterioration and repair priorities. The input is the preprocessed data, and the output is the infrastructure condition assessment results. This identifies which sections are in urgent need of repair.

[0636] Step 4: Automatic generation of maintenance and repair plans

[0637] The server automatically generates a maintenance and repair plan based on the analysis results of the AI ​​model. For example, if it determines that a specific road section needs repair within a certain period of time, it will include the repair method and specific schedule in the plan. The input for this step is the analysis results of the AI ​​model, and the output is a repair plan. The repair plan is stored in a database and registered using SQL queries.

[0638] Step 5: Analysis by Emotion Engine

[0639] The device collects the user's voice and facial expression data and sends it to the emotion engine. It uses a camera and microphone to capture the user's facial expressions and voice in real time and sends it to an API that analyzes their emotional state. The input here is the user's voice and facial expression data, and the output is the analysis result by the emotion engine.

[0640] The server receives the analysis results from the emotion engine and identifies the user's emotional state, with the input being the analysis results from the emotion engine and the output being a determination of the user's emotional state.

[0641] Step 6: Adapting User Notifications

[0642] The server customizes the notification content for maintenance and repair plans based on the analysis results of the emotion engine according to the user's emotional state. For example, if the user is in a high-stress state, the notification content is brief, while if the user is relaxed, detailed information is provided. The input is the analysis results of the emotion engine and the maintenance and repair plans, and the output is the customized notification content.

[0643] The server sends the notification to the user's device. Possible notification methods include email and in-app notifications, and email may be sent using the SMTP protocol.

[0644] Step 7: Execute and report

[0645] The user performs maintenance and repair work based on the notification. The necessary materials and workers are arranged according to the plan. After completing the work, the user reports the work results to the server from the terminal. The input is the user's work results, and the output is the report to the server. The report is sent via an HTTP POST request and recorded in the database.

[0646] The server analyzes the results of the user's work and provides feedback to improve the maintenance plan. The input is the user's report, and the output is an improved maintenance plan.

[0647] (Application example 2)

[0648] 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."

[0649] In modern infrastructure management, traditional manual maintenance and repair work requires a great deal of time and effort, making efficient management difficult. In addition, notifications are sent without considering the user's feelings, which leaves a psychological burden on the user and prevents optimal work efficiency.

[0650] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for extracting data from an existing infrastructure information database, means for collecting real-time data from sensors and IoT devices and transmitting it to the server, means for inputting the extracted and collected data into an AI model and analyzing it, means for automatically generating a maintenance and repair plan based on the analysis results, means for notifying a user terminal of the generated maintenance and repair plan, means for collecting user voice and facial expression data, analyzing it with an emotion engine, and transmitting it to the server, means for customizing the notification content based on the analysis results of the emotion engine and transmitting it to the user terminal, means for reporting the user's work results to the server and recording them in a database, and means for analyzing the report content and providing feedback to improve the maintenance and repair plan. This enables efficient infrastructure management and provides appropriate notifications according to the user's emotional state, reducing the user's psychological burden and ensuring optimal work efficiency.

[0651] An "existing infrastructure information database" is an existing database for storing data on infrastructure such as roads, buildings, water supply and sewerage systems, and electricity.

[0652] "Sensors and IoT devices" are electronic devices that collect environmental data and status information in real time and send it to a server via a network.

[0653] "Server" means a computer system established to collect, analyze, store, and notify data.

[0654] An "AI model" is a model that includes an artificial intelligence algorithm used to analyze accumulated data and derive useful results.

[0655] "Maintenance and development plan" means a plan that includes the schedule and methods of repair and maintenance work, which is prepared based on the deterioration state of the infrastructure and the priority of repairs.

[0656] A "user terminal" is a device used to receive notifications and reports and perform management tasks, and includes smartphones, tablets, and PCs.

[0657] An "emotion engine" is software and algorithms that analyze a user's voice and facial expressions to recognize their emotional state.

[0658] The "means for customizing notification content" is a method for optimizing notification content and providing personalized information based on the analyzed emotion data.

[0659] "Means for analyzing the report content and providing feedback to improve maintenance and repair plans" refers to a method for analyzing the reported data from users and reflecting it in new maintenance and repair plans.

[0660] This invention is a system for streamlining infrastructure maintenance and repair in logistics centers, combined with a function that recognizes the user's emotional state and adapts the notification content. The system consists of three main components: a server, a terminal, and a user.

[0661] The server extracts data from an existing infrastructure information database. This data includes information such as the safety of shelves in a distribution center and cracks in the floor. It also collects real-time data from sensors and IoT devices and sends it to the server. The collected data is preprocessed using libraries such as Pandas to fill in missing data and remove outliers. The data is then input into an AI model (e.g., a deep learning model or machine learning algorithm) to analyze the infrastructure's deterioration status and repair priorities.

[0662] The server automatically generates a maintenance and repair plan based on the analysis results. This plan includes specific repair methods and schedules and is saved in a database. The generated maintenance and repair plan is then sent to the user's device, which could be a smartphone or tablet.

[0663] Furthermore, the server collects the user's voice and facial expression data and analyzes it using an emotion engine (e.g., Microsoft Azure Emotion API). Based on the analysis results of the emotion engine, the notification content is customized and sent to the user's device. For example, if the user is stressed, a simple notification is sent, and if the user is relaxed, a detailed notification is sent.

[0664] The user performs maintenance and repair work based on the notification and reports the results after completion. The report is sent to the server and recorded in the database. Finally, the server analyzes the report and provides feedback to improve the maintenance and repair plan. This makes future plans more accurate and efficient.

[0665] As a concrete example, consider the case where the safety of shelves in a logistics center has deteriorated. The server retrieves maintenance history from a past database, and sensors collect information on the shelf's condition in real time and send it to the server. The server preprocesses the data, evaluates the shelf's safety using an AI model, and creates a repair plan. The server customizes the notification content based on the user's emotional state and sends it to the user's device. The user then carries out repair work in accordance with the notification and reports the results.

[0666] Example prompt sentence:

[0667] "Check the infrastructure condition in your distribution center. Use sensors and cameras to collect shelf safety data and send it to a server. The server will analyze the data and automatically generate repair plans. Send brief or detailed notifications depending on the emotional state of your staff."

[0668] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0669] Step 1:

[0670] The server extracts the necessary data from an existing infrastructure information database. Specifically, it obtains infrastructure information such as shelves and floors within the logistics center using an SQL query (e.g., SELECT FROM infrastructure_data WHERE category='shelf'). The input is the infrastructure information in the database, and the output is infrastructure data converted into a format that can be processed within the server.

[0671] Step 2:

[0672] Terminals (sensors and IoT devices) collect real-time data from within the logistics center and send it to a server. For example, cracks in the floor and damage to shelves are measured by sensors and sent to the server via wireless communication. The input is environmental data collected in real time, and the output is the raw data sent to the server.

[0673] Step 3:

[0674] The server preprocesses the collected data. Specifically, it cleans the data frame using the Pandas library, imputes missing data (e.g., df.fillna(method='ffill')), and removes outliers. The input is raw data obtained from sensors or databases, and the output is clean data after preprocessing.

[0675] Step 4:

[0676] The server inputs the preprocessed data into the AI ​​model for analysis. Specifically, it uses a deep learning model or machine learning algorithm to analyze the data and evaluate the infrastructure's deterioration status and repair priority. The input is clean data, and the output is infrastructure condition assessment data.

[0677] Step 5:

[0678] The server automatically generates a maintenance plan based on the analysis results. For example, it determines a specific repair method and schedule for a certain shelf section and stores it in the database using an SQL query (e.g., INSERT INTO maintenance_schedule (infrastructure_id, repair_method, schedule_date) VALUES (...)). The input is the infrastructure condition assessment data, and the output is a specific maintenance plan.

[0679] Step 6:

[0680] The device collects the user's voice and facial expression data and sends it to an emotion engine for analysis. Specifically, data is collected using the smartphone's camera and microphone, and emotion analysis is performed using an emotion engine such as Microsoft Azure Emotion API. The input is the user's voice and facial expression data, and the output is the emotion analysis results.

[0681] Step 7:

[0682] The server receives the analysis results of the emotion engine and customizes the notification content according to the user's emotional state. For example, if the user is in a stressful state, it prepares a brief notification, and if the user is in a relaxed state, it prepares a detailed notification. The input is the emotion analysis result, and the output is the customized notification content.

[0683] Step 8:

[0684] The server sends the customized notification content to the user device. Specifically, it notifies the user using an in-app notification or email (e.g., sending an email using the SMTP protocol). The input is the customized notification content, and the output is the notification sent to the user device.

[0685] Step 9:

[0686] The user performs maintenance and repair work based on the notification. Specifically, the user performs the necessary repairs according to the procedure manual and records the progress of the work. The input is the notification content, and the output is the completed work results.

[0687] Step 10:

[0688] The user reports the results of their work to the server. Specifically, they send the report via an HTTP POST request through the app. The input is the work result, and the output is the report data recorded in the database.

[0689] 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.

[0690] 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.

[0691] 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.

[0692] [Third embodiment]

[0693] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0694] 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.

[0695] 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).

[0696] 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.

[0697] 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.

[0698] 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).

[0699] 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.

[0700] 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.

[0701] 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.

[0702] 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.

[0703] 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.

[0704] 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."

[0705] This invention is a system that efficiently automates a series of tasks related to the maintenance and development of urban infrastructure. This system consists of three main components: a server, a terminal, and a user, which work in conjunction with each other.

[0706] The system is responsible for the following steps:

[0707] 1. Data Collection

[0708] The server extracts the necessary data from an existing infrastructure information database, including information on roads, buildings, water and sewerage systems, and electricity.

[0709] Terminals (sensors and IoT devices) collect real-time data from the site and send it to a server, which reflects the latest infrastructure status.

[0710] 2. Data Analysis

[0711] The server inputs the collected data into an AI model for analysis, which uses deep learning and machine learning algorithms to assess the state of the infrastructure and detect and predict anomalies.

[0712] The analysis includes the degree of deterioration of infrastructure and maintenance priorities. For example, the progression of cracks and the need for repairs can be quantified, enabling specific infrastructure assessments.

[0713] 3. Automatic generation of maintenance and repair plans

[0714] Based on the analysis results obtained from the AI ​​model, the server automatically generates an optimal maintenance plan, which includes details on which infrastructure to maintain, when, and how.

[0715] For example, if it is determined that a particular road section needs repair within a week, the repair method (patch repair, surface scraping / regeneration work, etc.) and a specific schedule will be generated.

[0716] 4. User Notices and Instructions

[0717] The server notifies the user device of the generated maintenance plan via email or in-app notification.

[0718] The user (maintenance staff) receives the notification, checks the plan contents, and prepares for the work, which specifically includes arranging repair materials and adjusting the schedule of workers.

[0719] 5. Work Completion Report and Feedback

[0720] After completing the maintenance work, the user reports the results to the server via the terminal, including details of the work and the date and time of completion.

[0721] The server records the reported work results in a database and provides feedback to improve the next maintenance and repair plan, resulting in more accurate and efficient maintenance and repair.

[0722] Specific examples

[0723] For example, consider a scenario involving the maintenance of major roads in a city.

[0724] 1. Data Collection

[0725] The server collects data on the past maintenance history of roads throughout the city, and sensors installed on the roads collect data on cracks and subsidence in real time and send it to the server.

[0726] 2. Data Analysis

[0727] The server inputs the collected data into an AI model to analyze the road's deterioration, which then assesses the extent of cracks and calculates the need for repairs.

[0728] 3. Automatic generation of maintenance and repair plans

[0729] The server determines whether a specific road section requires urgent repairs based on the extent of the cracks, and then automatically generates a plan with specific repair methods and schedules.

[0730] 4. User Notices and Instructions

[0731] The server notifies the maintenance staff of the generated repair plan.

[0732] The user receives the notification, checks the plan, and arranges for the necessary materials and workers.

[0733] 5. Work Completion Report and Feedback

[0734] After completing the repair work, the user reports the results of the work on the terminal.

[0735] The server records the report in a database and uses it to formulate the next plan.

[0736] In this way, by using the present invention, a system is provided that can efficiently and accurately carry out a series of tasks related to the maintenance and development of urban infrastructure, making it possible to reduce costs and speed up the tasks.

[0737] The processing flow will be explained below.

[0738] Step 1:

[0739] Data collection

[0740] The server extracts the infrastructure's maintenance history and status information from the infrastructure information database using an SQL query, for example, executing a command such as SELECT FROM infrastructure_data WHERE category='road'.

[0741] Step 2:

[0742] Receiving real-time data

[0743] Terminals (sensors and IoT devices) measure the condition of local infrastructure in real time, for example, a sensor detecting the depth of cracks in the road, and send that data to the server via an HTTP POST request.

[0744] Step 3:

[0745] Data Integration

[0746] The server integrates information retrieved from the database with real-time data received from the device. This data is managed in JSON format or as a data frame. The data is formatted using libraries such as Pandas.

[0747] Step 4:

[0748] Data analysis

[0749] The server preprocesses the integrated data before inputting it into the AI ​​model. Specifically, it complements missing data and removes outliers, which allows for accurate analysis.

[0750] The server then inputs the preprocessed data into an AI model for analysis, which uses deep learning or machine learning algorithms to assess the condition of the infrastructure and calculate whether there are any abnormalities or the degree of degradation.

[0751] Step 5:

[0752] Automatic generation of maintenance and repair plans

[0753] The server automatically generates a maintenance plan based on the analysis results of the AI ​​model. For example, if a section of road is cracked, the server will incorporate repair methods (such as patch repairs or surface scraping and restoration work) and a specific schedule into the plan.

[0754] The generated plan is stored in the database using an SQL query, for example with a command like INSERT INTO maintenance_schedule (infrastructure_id, repair_method, schedule_date) VALUES (...).

[0755] Step 6:

[0756] notification

[0757] The server notifies the user device of the generated maintenance plan via email or in-app notification. One method of notification is to send email using the SMTP protocol.

[0758] Step 7:

[0759] User confirmation and preparation

[0760] The user (maintenance staff) receives the notification sent to their terminal, checks the plan, and arranges for repair materials and adjusts the schedule of workers.

[0761] Step 8:

[0762] Work execution

[0763] The user carries out maintenance and repair work based on a plan, the details of which are described in the plan and are carried out accordingly.

[0764] Step 9:

[0765] Work completion report

[0766] After completing the maintenance work, the user inputs the work content and the completion date and time into the terminal and reports it to the server.

[0767] The device sends the work to the server via an HTTP POST request, and the report includes details of the completed work.

[0768] Step 10:

[0769] Database recording and analysis

[0770] The server records the received work reports in a database, for example using an SQL query like INSERT INTO maintenance_reports (infrastructure_id, work_details, completion_date) VALUES (...).

[0771] The server analyzes the report and generates feedback to improve the next maintenance and repair plan, which allows for more accurate planning.

[0772] Through the above processing steps, this system can automate the maintenance and development of urban infrastructure efficiently and accurately.

[0773] Example 1

[0774] 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."

[0775] Traditional methods for maintaining and upgrading urban infrastructure involve a lot of manual work, making them inefficient and time-consuming. It also makes it difficult to prioritize maintenance work and quickly detect abnormalities, which increases the risk of infrastructure deterioration and accidents. Furthermore, the formulation of maintenance plans relies on human judgment and is prone to subjective factors, making optimization difficult. These issues need to be addressed.

[0776] 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.

[0777] In this invention, the server includes a means for extracting data from an existing infrastructure information database, a means for collecting real-time data from sensors and IoT devices and sending it to the server, and a means for preprocessing the extracted and collected data and inputting it into an AI model for analysis. This allows for an accurate understanding of the infrastructure status, automatic generation of efficient maintenance and repair plans, and rapid anomaly detection.

[0778] An "existing infrastructure information database" is a data storage that stores past records and current status data related to urban infrastructure.

[0779] "Sensors and IoT devices" are electronic devices that collect data from the physical environment in real time and send it to a server over a network.

[0780] "Preprocessing" is the process of removing noise from collected data and extracting and shaping the necessary information.

[0781] An "AI model" is a collection of algorithms used to realize artificial intelligence, and here it specifically refers to deep learning models and machine learning algorithms.

[0782] A "maintenance and improvement plan" is a specific plan for predicting deterioration and abnormalities in infrastructure and carrying out repairs and renovations at the appropriate time and in the appropriate manner.

[0783] A "user terminal" is a device such as a computer or smartphone used by a maintenance technician.

[0784] "Feedback" refers to analyzing the results of maintenance work carried out and providing information to be used in planning the next maintenance and repair work.

[0785] This invention is a system that efficiently automates a series of tasks related to the maintenance and development of urban infrastructure. This system consists of three main components: a server, a terminal, and a user, each of which plays a specific role.

[0786] Hardware and Software Configuration

[0787] The server consists of a high-performance computer and is equipped with a database management system (e.g., MySQL), a data processing framework (e.g., PySpark), and a machine learning framework (e.g., TensorFlow or PyTorch).

[0788] Terminals consist of sensors and IoT devices that collect real-time data using wireless communication technologies such as LoRa and Zigbee. Terminals also include smartphones and tablets used by users.

[0789] Users are maintenance personnel and others who connect to the system through a dedicated mobile application.

[0790] What the program does

[0791] The server first extracts data on roads, buildings, water and sewer systems, and electricity from existing infrastructure information databases. It then collects real-time data from on-site sensors and IoT devices and preprocesses it. Preprocessing includes removing noise and extracting necessary information. The preprocessed data is then input into a generative AI model. This AI model uses deep learning and machine learning algorithms to assess the condition of the infrastructure and detect and predict anomalies.

[0792] To illustrate, here's an example prompt:

[0793] "Evaluate the extent of cracking on Section A of a major road in the city. Then calculate the need for repairs."

[0794] Based on the analysis results, the server automatically generates a maintenance and repair plan, which includes details on which infrastructure to maintain and repair, when, and how. For example, it may determine that a specific road section needs repair within a week, and generate the repair method (patching, surface scraping, restoration work, etc.) and schedule.

[0795] The server notifies the user's device of the generated maintenance and repair plan via email or in-app notification. The user receives the notification, checks the plan, and arranges for the necessary materials and workers. After the repair work is completed, the user reports the work results via their device. The server records the reported work results in a database and provides feedback to improve the next maintenance and repair plan.

[0796] In this way, this system can efficiently and accurately carry out a series of tasks related to the maintenance and development of urban infrastructure. Specific data analysis and automatic generation of maintenance plans are performed using machine learning algorithms, resulting in cost reduction and speed.

[0797] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0798] Step 1: Data extraction

[0799] The server extracts data from existing infrastructure information databases. For example, the server retrieves historical maintenance data for roads, buildings, water and sewerage systems, electricity, etc. from a MySQL database. The input for this data extraction is a database query, and the output is a set of extracted infrastructure data.

[0800] Step 2: Real-time data collection

[0801] Terminals (sensors and IoT devices) collect real-time data on-site and send it to a server. For example, sensors installed on roads collect data on cracks and subsidence and send it to a server via wireless communication technology (such as LoRa or Zigbee). The input of this collection is the real-time observation data of the sensors, and the output is the latest infrastructure status data sent to the server.

[0802] Step 3: Data Preprocessing

[0803] The server pre-processes the extracted and collected data, removing noise, extracting necessary information, and shaping the data, for example filtering outliers and scaling the data. The input of this pre-processing is raw data, and the output is pre-processed, clean data.

[0804] Step 4: Input data into the AI ​​model

[0805] The server inputs the preprocessed data into a generative AI model. This AI model uses deep learning frameworks such as TensorFlow and PyTorch. An example prompt is, "Evaluate the degree of cracking on section A of the city's main road. Then, calculate the need for repairs." The input for this data input is the preprocessed data and the prompt, and the output is the analysis results from the AI ​​model.

[0806] Step 5: Automatic generation of maintenance and repair plans

[0807] The server automatically generates a maintenance and repair plan based on the analysis results from the AI ​​model. For example, it may determine that a specific road section requires urgent repairs and generate a repair method (patching, surface scraping, restoration work, etc.) and schedule. The input for this plan generation is the analysis results from the AI ​​model, and the output is a specific maintenance and repair plan.

[0808] Step 6: Maintenance Plan Notification

[0809] The server notifies the user device of the generated maintenance plan. Notification methods include email and in-app notification. For example, a notification may be sent to the maintenance technician's smartphone app. The input of this notification is the maintenance plan, and the output is a notification message sent to the user device.

[0810] Step 7: Prepare and perform maintenance work

[0811] The user (maintenance staff) receives the notification, checks the plan contents, and arranges for the necessary materials and workers. Specifically, they arrange for repair materials and adjust the schedule of workers. The input for this preparation is the notified maintenance and repair plan, and the output is the maintenance work schedule and the material arrangement status.

[0812] Step 8: Report work completed

[0813] After completing maintenance work, the user reports the results to the server via their device. The report includes details of the work and the date and time of completion. For example, the report can be made using a dedicated mobile application. The input of this report is the details of the maintenance work performed, and the output is a work completion report sent to the server.

[0814] Step 9: Record and feedback

[0815] The server records the reported work results in a database and provides feedback to improve the next maintenance plan. For example, it analyzes the reports and adjusts algorithms to improve the accuracy of future maintenance plans. The input to this recording and feedback is the work completion report, and the output is updated database records and improved maintenance plan algorithms.

[0816] (Application example 1)

[0817] 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."

[0818] In large-scale facilities such as logistics centers, it is important to perform infrastructure maintenance and repairs efficiently and quickly. However, with conventional systems, data collection and analysis, and the creation and execution of maintenance plans are often done manually, which is time-consuming and labor-intensive, and prone to human error. Furthermore, there is a lack of tools that enable on-site workers to quickly grasp the situation and make appropriate decisions. To solve these problems, an automated system is needed that can monitor the status of infrastructure in real time and respond quickly and appropriately.

[0819] 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.

[0820] In this invention, the server includes a means for extracting data from an existing infrastructure information database, a means for collecting real-time data from sensors and IoT devices and sending it to the server, and a means for notifying the smart glasses of a maintenance and repair plan based on the analysis results so that the user can visually confirm it. This enables the automation of infrastructure maintenance and repair in logistics centers, making it possible to perform the work efficiently and quickly.

[0821] - The "Infrastructure Information Database" is a database for storing and managing infrastructure data related to facilities such as logistics centers.

[0822] A "sensor" is a device that measures physical or chemical quantities and collects that information as digital data.

[0823] An "IoT device" is a device that has the ability to send and receive data via the Internet and is used to collect environmental data at logistics centers.

[0824] "Real-time data" refers to the latest data that changes every moment and is obtained from sensors and IoT devices.

[0825] A "server" is a central computer that collects, processes, analyzes data, and provides information to other devices and users.

[0826] An "AI model" is an artificial intelligence system that includes algorithms for learning data and predicting analysis results.

[0827] A "deep learning model" is a machine learning model that uses a multi-layer neural network to learn and analyze complex data.

[0828] "Machine learning algorithm" is a general term for algorithms that learn patterns and rules from data.

[0829] A "maintenance and repair plan" is a plan that outlines the content and schedule of work required to maintain the condition of the infrastructure at a logistics center.

[0830] A "user terminal" is a device used to operate the system and receive information.

[0831] "Smart glasses" are wearable devices that have the ability to visually display information and are used by users when working on-site.

[0832] A "database" is a system that structures and stores collected data so that it can be accessed, managed, and analyzed effectively later.

[0833] "Feedback" is the process of improving future maintenance and repair plans based on information obtained from analysis and work results.

[0834] This invention is a system that efficiently automates the maintenance and upkeep of logistics center infrastructure. This system consists of three main components: a server, a terminal, and a user, all of which work in conjunction with each other.

[0835] The server has the function of extracting necessary data from existing infrastructure information databases. Sensors and IoT devices collect real-time data and send it to the server. The server inputs the data into an AI model for analysis. Deep learning models and machine learning algorithms are used for the analysis. Based on this analysis, maintenance and repair plans are automatically generated.

[0836] The generated maintenance and repair plan is sent to the user's device. The user's device may also include smart glasses, allowing the user to visually check the plan. The user receives the notification, checks the plan, and carries out the work. When the repair is complete, the results are reported to the server via the device. The server records the report in a database and provides feedback to improve the next maintenance and repair plan.

[0837] The system's hardware includes various sensors such as temperature, humidity, and vibration sensors, while the software uses AI frameworks such as TensorFlow and PyTorch.

[0838] Data collection, processing, and calculation are carried out as follows: Data collection is carried out by acquiring real-time data from sensors and IoT devices and sending it to a server. Data processing is carried out by the server inputting the data into an AI model and performing preprocessing to make predictions. Data calculation is carried out by analyzing the data based on the patterns learned by the AI ​​model and generating maintenance and repair plans.

[0839] As a concrete example, consider the maintenance of conveyor belts in a logistics center. If data from sensors includes temperature, humidity, and vibration data, a user wearing smart glasses patrols the area and finds any abnormalities. Images of the abnormal areas are collected and sent to a server. The server inputs the data into an AI model and, based on the analysis results, notifies the smart glasses of a maintenance and repair plan, such as, "There is an abnormality in the conveyor belt in section A. Repairs are required. The recommended repair method is to replace the belt."

[0840] An example of an input prompt for a generative AI model is as follows:

[0841] "Based on temperature, humidity, vibration data and image data, determine the degree of deterioration of infrastructure within the logistics center and the necessary repairs."

[0842] This system will enable efficient and rapid maintenance and repair of logistics center infrastructure, improving the accuracy and speed of work.

[0843] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0844] Step 1: Collect data

[0845] The server extracts the necessary data from the existing infrastructure information database. Terminals (sensors and IoT devices) collect real-time data within the logistics center and send it to the server. In this step, data such as temperature, humidity, and vibration are collected. The input is real-time data from the infrastructure information database and sensors, and the output is data integrated within the server. Specifically, the server executes a database query, and the terminals send the collected data as packets.

[0846] Step 2: Preprocessing the data

[0847] The server processes the collected data into a format suitable for the AI ​​model. Specifically, it cleanses, normalizes, and extracts features from the data. The input to this step is integrated real-time data, and the output is preprocessed data. Specifically, it complements missing values ​​in the data and converts values ​​to the required range.

[0848] Step 3: Analyze the data

[0849] The server inputs the preprocessed data into the AI ​​model for analysis. The AI ​​model analyzes the data using deep learning models and machine learning algorithms to assess the condition of the infrastructure. The input for this step is the preprocessed data, and the output is the analysis results regarding the degree of deterioration and the need for repairs. Specifically, the data is fed into the model and the inference results are obtained.

[0850] Step 4: Generate a maintenance plan

[0851] The server automatically generates a maintenance and repair plan based on the analysis results. This plan includes specific repair methods and schedules. The input is the analysis results, and the output is the generated maintenance and repair plan. Specifically, the server creates an optimal rule-based plan based on the analysis results.

[0852] Step 5: Notification

[0853] The server notifies the smart glasses of the generated maintenance plan. The user visually checks the plan and performs the work. The input is the generated maintenance plan, and the output is the plan checked by the user. Specifically, text and images are sent to the smart glasses via the notification system.

[0854] Step 6: Report work completed

[0855] After completing a task, the user reports the results to the server through the smart glasses. The input is the task completion report, and the output is the report data recorded on the server. Specifically, the user inputs and transmits the report content using the operation panel of the smart glasses.

[0856] Step 7: Feedback

[0857] The server records the reported work results in a database and provides feedback to improve the next maintenance plan. The input is the reported work results data, and the output is an updated maintenance plan. Specific operations include updating the database and retraining the AI ​​model.

[0858] 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.

[0859] This invention utilizes AI technology for the maintenance and development of urban infrastructure, automating traditional manual tasks and combining it with an emotion engine that recognizes user emotions. This system consists of three main components: a server, a terminal, and a user, each of which plays a specific role. Furthermore, by analyzing the user's emotional state and adapting notification content, more effective infrastructure management is achieved.

[0860] The main processing steps of the system are:

[0861] 1. Data Collection

[0862] The server extracts data from the infrastructure information database. The data includes infrastructure information such as roads, buildings, water, sewerage, and electricity. It retrieves the data using an SQL query, for example, SELECT FROM infrastructure_data WHERE category='road'.

[0863] Terminals (sensors and IoT devices) collect real-time data from the site and send it to a server. For example, data on road cracks and subsidence is sent from sensors.

[0864] 2. Data Analysis

[0865] The server inputs the collected data into an AI model for analysis, which includes preprocessing the data to fill in missing data and remove outliers, such as cleaning the data frame using the Pandas library.

[0866] The server then inputs the pre-processed data into an AI model that uses deep learning or machine learning algorithms to assess the condition of the infrastructure and calculate the infrastructure's deterioration status and repair priorities.

[0867] 3. Automatic generation of maintenance and repair plans

[0868] The server automatically generates a maintenance plan based on the analysis results. For example, if it determines that a certain road section needs repair within a certain period of time, it will include the repair method and specific schedule in the plan.

[0869] The generated plan is stored in the database using an SQL query, for example INSERT INTO maintenance_schedule (infrastructure_id, repair_method, schedule_date) VALUES (...).

[0870] 4. Analysis by Emotion Engine

[0871] The device collects the user's voice and facial expression data and sends it to the emotion engine. For example, the device uses a camera or microphone to collect the user's facial expressions and voice and analyzes their emotional state.

[0872] The server receives the analysis results from the emotion engine and identifies the user's emotional state, making it possible to determine whether the user is stressed or relaxed.

[0873] 5. User Notification Adaptation

[0874] Based on the analysis results of the emotion engine, the server customizes the content of the maintenance and repair plan notification according to the user's emotional state. For example, if the user is under high stress, the notification content will be concise and clear, while if the user is relaxed, detailed information will be provided.

[0875] The server sends the notification to the user's device. Possible notification methods include email and in-app notifications. One method is to send email using the SMTP protocol.

[0876] 6. Work execution and reporting

[0877] Users can carry out maintenance and repair work based on the notification, and arrange for the necessary materials and workers in advance to ensure the work proceeds smoothly according to plan.

[0878] After completing the task, the user reports the results to the server via an HTTP POST request, which is then recorded in the database.

[0879] As a concrete example, consider road crack maintenance in a particular area.

[0880] 1. For data collection, the server retrieves past maintenance history from the database, and the terminal (sensor) collects the progress of cracks in real time and sends it to the server.

[0881] 2. In data analysis, the server preprocesses the collected data and inputs it into an AI model for analysis, assessing the severity of cracks and identifying which sections need repairs.

[0882] 3. When automatically generating maintenance and repair plans, the server creates a repair plan based on the results of the AI ​​model and saves it in a database.

[0883] 4. In analysis using an emotion engine, the device collects the user's voice and facial expressions, analyzes them using the emotion engine, and the server receives the results.

[0884] 5. In user notification adaptation, the server customizes the notification content according to the user's emotional state and sends it to the user's terminal.

[0885] 6. Work execution and reporting: The user carries out repair work according to the notification and reports the results after the work is completed.

[0886] These steps enable the system to achieve efficient and accurate infrastructure management and to respond flexibly to the user's emotional state.

[0887] The processing flow will be explained below.

[0888] Step 1:

[0889] Data collection

[0890] The server extracts past maintenance history and status data from the existing infrastructure information database using an SQL query such as SELECT FROM infrastructure_data WHERE category='road'.

[0891] Terminals (sensors and IoT devices) measure the local infrastructure condition (e.g., road cracks and subsidence) in real time and send the data to the server via an HTTP POST request.

[0892] Step 2:

[0893] Real-time data integration

[0894] The server integrates historical data extracted from the database with real-time data sent from the terminal, and uses Python's Pandas library to clean the data, impute missing values, and remove outliers.

[0895] Step 3:

[0896] Data analysis

[0897] The server inputs the preprocessed data into an AI model to analyze the condition of the infrastructure. Deep learning algorithms (e.g., TensorFlow and PyTorch) are used to calculate the state of deterioration of the infrastructure and the priority of repairs. Specifically, the progress of cracks and the rate of subsidence are evaluated.

[0898] Step 4:

[0899] Automatic generation of maintenance and repair plans

[0900] The server automatically generates a maintenance plan based on the analysis results of the AI ​​model. For example, if it determines that a specific road section needs patch repair within a week, it will include the repair method and specific schedule in the plan. The plan is generated in JSON format.

[0901] The server saves the generated maintenance schedule in the database using an SQL query (e.g. INSERT INTO maintenance_schedule (infrastructure_id, repair_method, schedule_date) VALUES (...)).

[0902] Step 5:

[0903] Analysis by emotion engine

[0904] The device collects the user's voice and facial expression data and sends it to the emotion engine. It uses a camera and microphone to capture the user's facial expressions and voice.

[0905] The server analyzes the data sent from the emotion engine and determines the user's emotional state, for example, detecting whether the user is stressed or relaxed, using emotion recognition algorithms.

[0906] Step 6:

[0907] User notification adaptation

[0908] The server customizes the notification content according to the user's emotional state. For example, if the user is in a high-stress state, the notification content is brief and provides only the minimum necessary information. On the other hand, if the user is in a relaxed state, the server provides detailed notification content.

[0909] The server sends notifications to the user's device. Scheduled notifications can be sent via email or in-app notifications. Emails can also be sent using the SMTP protocol.

[0910] Step 7:

[0911] User confirmation and preparation

[0912] The user checks the maintenance and repair plan sent to the terminal and arranges for repair materials and adjusts the schedule of workers based on the plan contents.

[0913] Step 8:

[0914] Work execution

[0915] The user will carry out the maintenance and repair work in accordance with the plan, specifically, carrying out any necessary repairs in an appropriate manner.

[0916] Step 9:

[0917] Work completion report

[0918] After completing the maintenance work, the user inputs the results of the work into the terminal and reports them to the server via an HTTP POST request. The report includes details of the work and the completion date and time.

[0919] Step 10:

[0920] Database recording and analysis

[0921] The server records the received work reports in the database using an SQL query (e.g. INSERT INTO maintenance_reports (infrastructure_id, work_details, completion_date) VALUES (...)).

[0922] The server analyzes the reports and generates feedback to help improve the next maintenance plan, thereby increasing the accuracy and efficiency of maintenance.

[0923] In this way, this system automates the maintenance and development of urban infrastructure efficiently and accurately, while also enabling flexible responses according to the user's emotional state.

[0924] Example 2

[0925] 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."

[0926] Conventional infrastructure management systems require a lot of manual work in collecting infrastructure information, analyzing it, and formulating and executing maintenance and development plans, which can lead to low efficiency. They also lack the ability to respond flexibly to users' emotional states, making effective infrastructure management difficult. Furthermore, insufficient pre-processing of collected data led to problems with the accuracy and reliability of analysis results.

[0927] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0928] In this invention, the server includes a means for extracting data from an existing infrastructure information database, a means for collecting real-time data from sensors and IoT devices and transmitting it to the server, and a means for preprocessing the extracted and collected data by filling in missing data and removing outliers. This improves the accuracy and reliability of data analysis. Furthermore, the server includes a means for automatically generating a maintenance and repair plan based on the analysis results, a means for collecting user voice and facial expression data and transmitting it to an emotion engine, a means for receiving the analysis results from the emotion engine and identifying the user's emotional state, and a means for customizing the content of the maintenance and repair plan notification based on the analysis results and the user's emotional state. This enables flexible responses according to the user's emotional state and achieves effective infrastructure management. The server also includes a means for notifying the user of the generated plan, reporting the user's work results to the server and recording them in a database, and a means for analyzing the report and providing feedback to improve the maintenance and repair plan. This significantly improves the efficiency and effectiveness of infrastructure management.

[0929] An "infrastructure information database" is an information system for storing and managing data related to urban infrastructure.

[0930] A "sensor" is a device that detects changes or conditions in the physical environment and transmits them as digital data.

[0931] An "IoT device" is an electronic device that can connect to other devices and systems via the Internet.

[0932] A "server" is a high-performance computing system for collecting, analyzing, storing, and communicating data.

[0933] An "AI model" is a mathematical model that uses artificial intelligence technology to analyze data and make predictions.

[0934] "Data preprocessing" refers to the process of performing operations such as filling in missing data and removing outliers before data analysis.

[0935] A "maintenance and development plan" is a plan that devisees repair methods and schedules for the maintenance and management of infrastructure.

[0936] A "user terminal" is a device through which a user communicates with a server and receives information.

[0937] The "emotion engine" is a system that analyzes the user's voice and facial expression data to identify their emotional state.

[0938] "Customizing notification content" means adjusting the presentation method and content of information to suit the user's specific situation and requirements.

[0939] An "HTTP POST request" is a type of HTTP protocol that allows a client to send data to a server.

[0940] A "database" is a system for systematically storing and managing digital data.

[0941] The "SMTP protocol" is a communication protocol for sending email.

[0942] "Feedback" is the process of reflecting on execution results and new data in order to improve and optimize the system.

[0943] "Reporting work results" means sending and recording the results of maintenance and repair work performed by the user to the server.

[0944] This invention is a system for improving the efficiency of urban infrastructure maintenance and development and automating manual tasks. It also achieves more effective infrastructure management by taking into account the user's emotional state and responding flexibly. This system consists of three main components: a server, a terminal, and a user.

[0945] The server first extracts the necessary data from an infrastructure information database. This data includes information on roads, buildings, water and sewerage systems, electricity, and other infrastructure. The extracted data is then input into an AI model, where it is analyzed. Missing data is filled in and outliers are removed. This is done using data processing libraries such as Pandas. The preprocessed data is then input into an AI model that includes deep learning and machine learning algorithms to evaluate the condition of the infrastructure.

[0946] The terminal uses sensors and IoT devices to collect real-time data on the site and send it to a server. For example, vibration sensors and cameras on the road detect cracks and subsidence and send the data to the server. The collected data is analyzed on the server to calculate the state of deterioration of the infrastructure and the priority of repairs.

[0947] The server automatically generates a maintenance plan based on the analysis results. For example, if a specific road section needs urgent repairs, the plan will include the repair method and specific schedule. This plan is stored in a database and registered using SQL queries.

[0948] Furthermore, the device collects the user's voice and facial expression data and sends it to the emotion engine. For example, the device can capture the user's facial expressions using a camera and analyze them with the emotion engine. The server receives the analysis results from the emotion engine and identifies the user's emotional state. This makes it possible to determine whether the user is feeling stressed or relaxed.

[0949] Based on the analysis results of the emotion engine, the server customizes the content of the maintenance and repair plan notification according to the user's emotional state. For example, if the user is in a high-stress state, the notification content will be brief, while if the user is relaxed, detailed information will be provided. Notifications are sent from the server to the user's device. Possible notification methods include email and in-app notifications. Sending email using the SMTP protocol is also included.

[0950] The user carries out maintenance work based on the notification content. The necessary materials and workers are arranged according to the plan. After the work is completed, the user reports the work results to the server via their terminal. The report content is sent to the server via an HTTP POST request and recorded in the database. The server analyzes the report content and provides feedback to improve the maintenance plan.

[0951] This allows the system to achieve efficient and accurate infrastructure management and respond flexibly to the user's emotional state.

[0952] As a concrete example, consider the maintenance of cracks on roads in a specific area. The server retrieves past maintenance history from a database, and the terminal (sensor) collects the progress of the cracks in real time and sends it to the server. The data is preprocessed and input into an AI model for analysis, and the severity of the cracks is evaluated. A repair plan is automatically generated based on the analysis results and saved in the database. The user's voice and facial expression data is collected and analyzed by an emotion engine, and the notification content is customized according to the user's emotional state and sent to the user's terminal. The user then carries out the work according to the notification and reports the results after completing the work.

[0953] An example of a prompt to input to a generative AI model is as follows:

[0954] "This system automates infrastructure maintenance in a specific area. First, it retrieves past maintenance information from a database and collects real-time data from sensors. Next, it analyzes this data using an AI model to automatically generate a repair plan. Furthermore, it analyzes the user's emotional state and customizes the content of notifications to achieve more effective management. For example, it can send a simple notification to a user in a stressed state and a detailed notification to a user in a relaxed state. As a concrete example, please consider road crack maintenance and explain the process."

[0955] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0956] Step 1: Data collection

[0957] The server first extracts infrastructure information such as roads, buildings, water supply and sewerage, and electricity from an existing infrastructure information database using an SQL query. For example, the query SELECT FROM infrastructure_data WHERE category='road' is used. This query retrieves data related to a specific infrastructure category.

[0958] The terminal collects real-time data from sensors and IoT devices and sends the data to a server. The sensors detect road cracks and subsidence information in real time and send it to the server using an HTTP POST request. Specific inputs include the sensor ID and measurement data, and the output is sent to the server.

[0959] Step 2: Data Preprocessing

[0960] The server preprocesses the collected data. This preprocessing includes filling in missing data and removing outliers. Specifically, it uses the Pandas library to clean the data frame. For example, it uses df.fillna(0, inplace=True) and filters outliers to improve the quality of the input data. The input for this step is the sensor data and data extracted from the database, and the output is clean data after preprocessing.

[0961] Step 3: Data analysis

[0962] The server inputs the preprocessed data into an AI model for analysis. For example, it uses deep learning and machine learning algorithms built with TensorFlow and Scikit-learn to assess the state of infrastructure deterioration and repair priorities. The input is the preprocessed data, and the output is the infrastructure condition assessment results. This identifies which sections are in urgent need of repair.

[0963] Step 4: Automatic generation of maintenance and repair plans

[0964] The server automatically generates a maintenance and repair plan based on the analysis results of the AI ​​model. For example, if it determines that a specific road section needs repair within a certain period of time, it will include the repair method and specific schedule in the plan. The input for this step is the analysis results of the AI ​​model, and the output is a repair plan. The repair plan is stored in a database and registered using SQL queries.

[0965] Step 5: Analysis by Emotion Engine

[0966] The device collects the user's voice and facial expression data and sends it to the emotion engine. It uses a camera and microphone to capture the user's facial expressions and voice in real time and sends it to an API that analyzes their emotional state. The input here is the user's voice and facial expression data, and the output is the analysis result by the emotion engine.

[0967] The server receives the analysis results from the emotion engine and identifies the user's emotional state, with the input being the analysis results from the emotion engine and the output being a determination of the user's emotional state.

[0968] Step 6: Adapting User Notifications

[0969] The server customizes the notification content for maintenance and repair plans based on the analysis results of the emotion engine according to the user's emotional state. For example, if the user is in a high-stress state, the notification content is brief, while if the user is relaxed, detailed information is provided. The input is the analysis results of the emotion engine and the maintenance and repair plans, and the output is the customized notification content.

[0970] The server sends the notification to the user's device. Possible notification methods include email and in-app notifications, and email may be sent using the SMTP protocol.

[0971] Step 7: Execute and report

[0972] The user performs maintenance and repair work based on the notification. The necessary materials and workers are arranged according to the plan. After completing the work, the user reports the work results to the server from the terminal. The input is the user's work results, and the output is the report to the server. The report is sent via an HTTP POST request and recorded in the database.

[0973] The server analyzes the results of the user's work and provides feedback to improve the maintenance plan. The input is the user's report, and the output is an improved maintenance plan.

[0974] (Application example 2)

[0975] 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."

[0976] In modern infrastructure management, traditional manual maintenance and repair work requires a great deal of time and effort, making efficient management difficult. In addition, notifications are sent without considering the user's feelings, which leaves a psychological burden on the user and prevents optimal work efficiency.

[0977] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for extracting data from an existing infrastructure information database, means for collecting real-time data from sensors and IoT devices and transmitting it to the server, means for inputting the extracted and collected data into an AI model and analyzing it, means for automatically generating a maintenance and repair plan based on the analysis results, means for notifying a user terminal of the generated maintenance and repair plan, means for collecting user voice and facial expression data, analyzing it with an emotion engine, and transmitting it to the server, means for customizing the notification content based on the analysis results of the emotion engine and transmitting it to the user terminal, means for reporting the user's work results to the server and recording them in a database, and means for analyzing the report content and providing feedback to improve the maintenance and repair plan. This enables efficient infrastructure management and provides appropriate notifications according to the user's emotional state, reducing the user's psychological burden and ensuring optimal work efficiency.

[0978] An "existing infrastructure information database" is an existing database for storing data on infrastructure such as roads, buildings, water supply and sewerage systems, and electricity.

[0979] "Sensors and IoT devices" are electronic devices that collect environmental data and status information in real time and send it to a server via a network.

[0980] "Server" means a computer system established to collect, analyze, store, and notify data.

[0981] An "AI model" is a model that includes an artificial intelligence algorithm used to analyze accumulated data and derive useful results.

[0982] "Maintenance and development plan" means a plan that includes the schedule and methods of repair and maintenance work, which is prepared based on the deterioration state of the infrastructure and the priority of repairs.

[0983] A "user terminal" is a device used to receive notifications and reports and perform management tasks, and includes smartphones, tablets, and PCs.

[0984] An "emotion engine" is software and algorithms that analyze a user's voice and facial expressions to recognize their emotional state.

[0985] The "means for customizing notification content" is a method for optimizing notification content and providing personalized information based on the analyzed emotion data.

[0986] "Means for analyzing the report content and providing feedback to improve maintenance and repair plans" refers to a method for analyzing the reported data from users and reflecting it in new maintenance and repair plans.

[0987] This invention is a system for streamlining infrastructure maintenance and repair in logistics centers, combined with a function that recognizes the user's emotional state and adapts the notification content. The system consists of three main components: a server, a terminal, and a user.

[0988] The server extracts data from an existing infrastructure information database. This data includes information such as the safety of shelves in a distribution center and cracks in the floor. It also collects real-time data from sensors and IoT devices and sends it to the server. The collected data is preprocessed using libraries such as Pandas to fill in missing data and remove outliers. The data is then input into an AI model (e.g., a deep learning model or machine learning algorithm) to analyze the infrastructure's deterioration status and repair priorities.

[0989] The server automatically generates a maintenance and repair plan based on the analysis results. This plan includes specific repair methods and schedules and is saved in a database. The generated maintenance and repair plan is then sent to the user's device, which could be a smartphone or tablet.

[0990] Furthermore, the server collects the user's voice and facial expression data and analyzes it using an emotion engine (e.g., Microsoft Azure Emotion API). Based on the analysis results of the emotion engine, the notification content is customized and sent to the user's device. For example, if the user is stressed, a simple notification is sent, and if the user is relaxed, a detailed notification is sent.

[0991] The user performs maintenance and repair work based on the notification and reports the results after completion. The report is sent to the server and recorded in the database. Finally, the server analyzes the report and provides feedback to improve the maintenance and repair plan. This makes future plans more accurate and efficient.

[0992] As a concrete example, consider the case where the safety of shelves in a logistics center has deteriorated. The server retrieves maintenance history from a past database, and sensors collect information on the shelf's condition in real time and send it to the server. The server preprocesses the data, evaluates the shelf's safety using an AI model, and creates a repair plan. The server customizes the notification content based on the user's emotional state and sends it to the user's device. The user then carries out repair work in accordance with the notification and reports the results.

[0993] Example prompt sentence:

[0994] "Check the infrastructure condition in your distribution center. Use sensors and cameras to collect shelf safety data and send it to a server. The server will analyze the data and automatically generate repair plans. Send brief or detailed notifications depending on the emotional state of your staff."

[0995] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0996] Step 1:

[0997] The server extracts the necessary data from an existing infrastructure information database. Specifically, it obtains infrastructure information such as shelves and floors within the logistics center using an SQL query (e.g., SELECT FROM infrastructure_data WHERE category='shelf'). The input is the infrastructure information in the database, and the output is infrastructure data converted into a format that can be processed within the server.

[0998] Step 2:

[0999] Terminals (sensors and IoT devices) collect real-time data from within the logistics center and send it to a server. For example, cracks in the floor and damage to shelves are measured by sensors and sent to the server via wireless communication. The input is environmental data collected in real time, and the output is the raw data sent to the server.

[1000] Step 3:

[1001] The server preprocesses the collected data. Specifically, it cleans the data frame using the Pandas library, imputes missing data (e.g., df.fillna(method='ffill')), and removes outliers. The input is raw data obtained from sensors or databases, and the output is clean data after preprocessing.

[1002] Step 4:

[1003] The server inputs the preprocessed data into the AI ​​model for analysis. Specifically, it uses a deep learning model or machine learning algorithm to analyze the data and evaluate the infrastructure's deterioration status and repair priority. The input is clean data, and the output is infrastructure condition assessment data.

[1004] Step 5:

[1005] The server automatically generates a maintenance plan based on the analysis results. For example, it determines a specific repair method and schedule for a certain shelf section and stores it in the database using an SQL query (e.g., INSERT INTO maintenance_schedule (infrastructure_id, repair_method, schedule_date) VALUES (...)). The input is the infrastructure condition assessment data, and the output is a specific maintenance plan.

[1006] Step 6:

[1007] The device collects the user's voice and facial expression data and sends it to an emotion engine for analysis. Specifically, data is collected using the smartphone's camera and microphone, and emotion analysis is performed using an emotion engine such as Microsoft Azure Emotion API. The input is the user's voice and facial expression data, and the output is the emotion analysis results.

[1008] Step 7:

[1009] The server receives the analysis results of the emotion engine and customizes the notification content according to the user's emotional state. For example, if the user is in a stressful state, it prepares a brief notification, and if the user is in a relaxed state, it prepares a detailed notification. The input is the emotion analysis result, and the output is the customized notification content.

[1010] Step 8:

[1011] The server sends the customized notification content to the user device. Specifically, it notifies the user using an in-app notification or email (e.g., sending an email using the SMTP protocol). The input is the customized notification content, and the output is the notification sent to the user device.

[1012] Step 9:

[1013] The user performs maintenance and repair work based on the notification. Specifically, the user performs the necessary repairs according to the procedure manual and records the progress of the work. The input is the notification content, and the output is the completed work results.

[1014] Step 10:

[1015] The user reports the results of their work to the server. Specifically, they send the report via an HTTP POST request through the app. The input is the work result, and the output is the report data recorded in the database.

[1016] 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.

[1017] 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.

[1018] 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.

[1019] [Fourth embodiment]

[1020] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1021] 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.

[1022] 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).

[1023] 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.

[1024] 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.

[1025] 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).

[1026] 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.

[1027] 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.

[1028] 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.

[1029] 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.

[1030] 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.

[1031] 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.

[1032] 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."

[1033] This invention is a system that efficiently automates a series of tasks related to the maintenance and development of urban infrastructure. This system consists of three main components: a server, a terminal, and a user, which work in conjunction with each other.

[1034] The system is responsible for the following steps:

[1035] 1. Data Collection

[1036] The server extracts the necessary data from an existing infrastructure information database, including information on roads, buildings, water and sewerage systems, and electricity.

[1037] Terminals (sensors and IoT devices) collect real-time data from the site and send it to a server, which reflects the latest infrastructure status.

[1038] 2. Data Analysis

[1039] The server inputs the collected data into an AI model for analysis, which uses deep learning and machine learning algorithms to assess the state of the infrastructure and detect and predict anomalies.

[1040] The analysis includes the degree of deterioration of infrastructure and maintenance priorities. For example, the progression of cracks and the need for repairs can be quantified, enabling specific infrastructure assessments.

[1041] 3. Automatic generation of maintenance and repair plans

[1042] Based on the analysis results obtained from the AI ​​model, the server automatically generates an optimal maintenance plan, which includes details on which infrastructure to maintain, when, and how.

[1043] For example, if it is determined that a particular road section needs repair within a week, the repair method (patch repair, surface scraping / regeneration work, etc.) and a specific schedule will be generated.

[1044] 4. User Notices and Instructions

[1045] The server notifies the user device of the generated maintenance plan via email or in-app notification.

[1046] The user (maintenance staff) receives the notification, checks the plan contents, and prepares for the work, which specifically includes arranging repair materials and adjusting the schedule of workers.

[1047] 5. Work Completion Report and Feedback

[1048] After completing the maintenance work, the user reports the results to the server via the terminal, including details of the work and the date and time of completion.

[1049] The server records the reported work results in a database and provides feedback to improve the next maintenance and repair plan, resulting in more accurate and efficient maintenance and repair.

[1050] Specific examples

[1051] For example, consider a scenario involving the maintenance of major roads in a city.

[1052] 1. Data Collection

[1053] The server collects data on the past maintenance history of roads throughout the city, and sensors installed on the roads collect data on cracks and subsidence in real time and send it to the server.

[1054] 2. Data Analysis

[1055] The server inputs the collected data into an AI model to analyze the road's deterioration, which then assesses the extent of cracks and calculates the need for repairs.

[1056] 3. Automatic generation of maintenance and repair plans

[1057] The server determines whether a specific road section requires urgent repairs based on the extent of the cracks, and then automatically generates a plan with specific repair methods and schedules.

[1058] 4. User Notices and Instructions

[1059] The server notifies the maintenance staff of the generated repair plan.

[1060] The user receives the notification, checks the plan, and arranges for the necessary materials and workers.

[1061] 5. Work Completion Report and Feedback

[1062] After completing the repair work, the user reports the results of the work on the terminal.

[1063] The server records the report in a database and uses it to formulate the next plan.

[1064] In this way, by using the present invention, a system is provided that can efficiently and accurately carry out a series of tasks related to the maintenance and development of urban infrastructure, making it possible to reduce costs and speed up the tasks.

[1065] The processing flow will be explained below.

[1066] Step 1:

[1067] Data collection

[1068] The server extracts the infrastructure's maintenance history and status information from the infrastructure information database using an SQL query, for example, executing a command such as SELECT FROM infrastructure_data WHERE category='road'.

[1069] Step 2:

[1070] Receiving real-time data

[1071] Terminals (sensors and IoT devices) measure the condition of local infrastructure in real time, for example, a sensor detecting the depth of cracks in the road, and send that data to the server via an HTTP POST request.

[1072] Step 3:

[1073] Data Integration

[1074] The server integrates information retrieved from the database with real-time data received from the device. This data is managed in JSON format or as a data frame. The data is formatted using libraries such as Pandas.

[1075] Step 4:

[1076] Data analysis

[1077] The server preprocesses the integrated data before inputting it into the AI ​​model. Specifically, it complements missing data and removes outliers, which allows for accurate analysis.

[1078] The server then inputs the preprocessed data into an AI model for analysis, which uses deep learning or machine learning algorithms to assess the condition of the infrastructure and calculate whether there are any abnormalities or the degree of degradation.

[1079] Step 5:

[1080] Automatic generation of maintenance and repair plans

[1081] The server automatically generates a maintenance plan based on the analysis results of the AI ​​model. For example, if a section of road is cracked, the server will incorporate repair methods (such as patch repairs or surface scraping and restoration work) and a specific schedule into the plan.

[1082] The generated plan is stored in the database using an SQL query, for example with a command like INSERT INTO maintenance_schedule (infrastructure_id, repair_method, schedule_date) VALUES (...).

[1083] Step 6:

[1084] notification

[1085] The server notifies the user device of the generated maintenance plan via email or in-app notification. One method of notification is to send email using the SMTP protocol.

[1086] Step 7:

[1087] User confirmation and preparation

[1088] The user (maintenance staff) receives the notification sent to their terminal, checks the plan, and arranges for repair materials and adjusts the schedule of workers.

[1089] Step 8:

[1090] Work execution

[1091] The user carries out maintenance and repair work based on a plan, the details of which are described in the plan and are carried out accordingly.

[1092] Step 9:

[1093] Work completion report

[1094] After completing the maintenance work, the user inputs the work content and the completion date and time into the terminal and reports it to the server.

[1095] The device sends the work to the server via an HTTP POST request, and the report includes details of the completed work.

[1096] Step 10:

[1097] Database recording and analysis

[1098] The server records the received work reports in a database, for example using an SQL query like INSERT INTO maintenance_reports (infrastructure_id, work_details, completion_date) VALUES (...).

[1099] The server analyzes the report and generates feedback to improve the next maintenance and repair plan, which allows for more accurate planning.

[1100] Through the above processing steps, this system can automate the maintenance and development of urban infrastructure efficiently and accurately.

[1101] Example 1

[1102] 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."

[1103] Traditional methods for maintaining and upgrading urban infrastructure involve a lot of manual work, making them inefficient and time-consuming. It also makes it difficult to prioritize maintenance work and quickly detect abnormalities, which increases the risk of infrastructure deterioration and accidents. Furthermore, the formulation of maintenance plans relies on human judgment and is prone to subjective factors, making optimization difficult. These issues need to be addressed.

[1104] 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.

[1105] In this invention, the server includes a means for extracting data from an existing infrastructure information database, a means for collecting real-time data from sensors and IoT devices and sending it to the server, and a means for preprocessing the extracted and collected data and inputting it into an AI model for analysis. This allows for an accurate understanding of the infrastructure status, automatic generation of efficient maintenance and repair plans, and rapid anomaly detection.

[1106] An "existing infrastructure information database" is a data storage that stores past records and current status data related to urban infrastructure.

[1107] "Sensors and IoT devices" are electronic devices that collect data from the physical environment in real time and send it to a server over a network.

[1108] "Preprocessing" is the process of removing noise from collected data and extracting and shaping the necessary information.

[1109] An "AI model" is a collection of algorithms used to realize artificial intelligence, and here it specifically refers to deep learning models and machine learning algorithms.

[1110] A "maintenance and improvement plan" is a specific plan for predicting deterioration and abnormalities in infrastructure and carrying out repairs and renovations at the appropriate time and in the appropriate manner.

[1111] A "user terminal" is a device such as a computer or smartphone used by a maintenance technician.

[1112] "Feedback" refers to analyzing the results of maintenance work carried out and providing information to be used in planning the next maintenance and repair work.

[1113] This invention is a system that efficiently automates a series of tasks related to the maintenance and development of urban infrastructure. This system consists of three main components: a server, a terminal, and a user, each of which plays a specific role.

[1114] Hardware and Software Configuration

[1115] The server consists of a high-performance computer and is equipped with a database management system (e.g., MySQL), a data processing framework (e.g., PySpark), and a machine learning framework (e.g., TensorFlow or PyTorch).

[1116] Terminals consist of sensors and IoT devices that collect real-time data using wireless communication technologies such as LoRa and Zigbee. Terminals also include smartphones and tablets used by users.

[1117] Users are maintenance personnel and others who connect to the system through a dedicated mobile application.

[1118] What the program does

[1119] The server first extracts data on roads, buildings, water and sewer systems, and electricity from existing infrastructure information databases. It then collects real-time data from on-site sensors and IoT devices and preprocesses it. Preprocessing includes removing noise and extracting necessary information. The preprocessed data is then input into a generative AI model. This AI model uses deep learning and machine learning algorithms to assess the condition of the infrastructure and detect and predict anomalies.

[1120] To illustrate, here's an example prompt:

[1121] "Evaluate the extent of cracking on Section A of a major road in the city. Then calculate the need for repairs."

[1122] Based on the analysis results, the server automatically generates a maintenance and repair plan, which includes details on which infrastructure to maintain and repair, when, and how. For example, it may determine that a specific road section needs repair within a week, and generate the repair method (patching, surface scraping, restoration work, etc.) and schedule.

[1123] The server notifies the user's device of the generated maintenance and repair plan via email or in-app notification. The user receives the notification, checks the plan, and arranges for the necessary materials and workers. After the repair work is completed, the user reports the work results via their device. The server records the reported work results in a database and provides feedback to improve the next maintenance and repair plan.

[1124] In this way, this system can efficiently and accurately carry out a series of tasks related to the maintenance and development of urban infrastructure. Specific data analysis and automatic generation of maintenance plans are performed using machine learning algorithms, resulting in cost reduction and speed.

[1125] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1126] Step 1: Data extraction

[1127] The server extracts data from existing infrastructure information databases. For example, the server retrieves historical maintenance data for roads, buildings, water and sewerage systems, electricity, etc. from a MySQL database. The input for this data extraction is a database query, and the output is a set of extracted infrastructure data.

[1128] Step 2: Real-time data collection

[1129] Terminals (sensors and IoT devices) collect real-time data on-site and send it to a server. For example, sensors installed on roads collect data on cracks and subsidence and send it to a server via wireless communication technology (such as LoRa or Zigbee). The input of this collection is the real-time observation data of the sensors, and the output is the latest infrastructure status data sent to the server.

[1130] Step 3: Data Preprocessing

[1131] The server pre-processes the extracted and collected data, removing noise, extracting necessary information, and shaping the data, for example filtering outliers and scaling the data. The input of this pre-processing is raw data, and the output is pre-processed, clean data.

[1132] Step 4: Input data into the AI ​​model

[1133] The server inputs the preprocessed data into a generative AI model. This AI model uses deep learning frameworks such as TensorFlow and PyTorch. An example prompt is, "Evaluate the degree of cracking on section A of the city's main road. Then, calculate the need for repairs." The input for this data input is the preprocessed data and the prompt, and the output is the analysis results from the AI ​​model.

[1134] Step 5: Automatic generation of maintenance and repair plans

[1135] The server automatically generates a maintenance and repair plan based on the analysis results from the AI ​​model. For example, it may determine that a specific road section requires urgent repairs and generate a repair method (patching, surface scraping, restoration work, etc.) and schedule. The input for this plan generation is the analysis results from the AI ​​model, and the output is a specific maintenance and repair plan.

[1136] Step 6: Maintenance Plan Notification

[1137] The server notifies the user device of the generated maintenance plan. Notification methods include email and in-app notification. For example, a notification may be sent to the maintenance technician's smartphone app. The input of this notification is the maintenance plan, and the output is a notification message sent to the user device.

[1138] Step 7: Prepare and perform maintenance work

[1139] The user (maintenance staff) receives the notification, checks the plan contents, and arranges for the necessary materials and workers. Specifically, they arrange for repair materials and adjust the schedule of workers. The input for this preparation is the notified maintenance and repair plan, and the output is the maintenance work schedule and the material arrangement status.

[1140] Step 8: Report work completed

[1141] After completing maintenance work, the user reports the results to the server via their device. The report includes details of the work and the date and time of completion. For example, the report can be made using a dedicated mobile application. The input of this report is the details of the maintenance work performed, and the output is a work completion report sent to the server.

[1142] Step 9: Record and feedback

[1143] The server records the reported work results in a database and provides feedback to improve the next maintenance plan. For example, it analyzes the reports and adjusts algorithms to improve the accuracy of future maintenance plans. The input to this recording and feedback is the work completion report, and the output is updated database records and improved maintenance plan algorithms.

[1144] (Application example 1)

[1145] 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."

[1146] In large-scale facilities such as logistics centers, it is important to perform infrastructure maintenance and repairs efficiently and quickly. However, with conventional systems, data collection and analysis, and the creation and execution of maintenance plans are often done manually, which is time-consuming and labor-intensive, and prone to human error. Furthermore, there is a lack of tools that enable on-site workers to quickly grasp the situation and make appropriate decisions. To solve these problems, an automated system is needed that can monitor the status of infrastructure in real time and respond quickly and appropriately.

[1147] 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.

[1148] In this invention, the server includes a means for extracting data from an existing infrastructure information database, a means for collecting real-time data from sensors and IoT devices and sending it to the server, and a means for notifying the smart glasses of a maintenance and repair plan based on the analysis results so that the user can visually confirm it. This enables the automation of infrastructure maintenance and repair in logistics centers, making it possible to perform the work efficiently and quickly.

[1149] - The "Infrastructure Information Database" is a database for storing and managing infrastructure data related to facilities such as logistics centers.

[1150] A "sensor" is a device that measures physical or chemical quantities and collects that information as digital data.

[1151] An "IoT device" is a device that has the ability to send and receive data via the Internet and is used to collect environmental data at logistics centers.

[1152] "Real-time data" refers to the latest data that changes every moment and is obtained from sensors and IoT devices.

[1153] A "server" is a central computer that collects, processes, analyzes data, and provides information to other devices and users.

[1154] An "AI model" is an artificial intelligence system that includes algorithms for learning data and predicting analysis results.

[1155] A "deep learning model" is a machine learning model that uses a multi-layer neural network to learn and analyze complex data.

[1156] "Machine learning algorithm" is a general term for algorithms that learn patterns and rules from data.

[1157] A "maintenance and repair plan" is a plan that outlines the content and schedule of work required to maintain the condition of the infrastructure at a logistics center.

[1158] A "user terminal" is a device used to operate the system and receive information.

[1159] "Smart glasses" are wearable devices that have the ability to visually display information and are used by users when working on-site.

[1160] A "database" is a system that structures and stores collected data so that it can be accessed, managed, and analyzed effectively later.

[1161] "Feedback" is the process of improving future maintenance and repair plans based on information obtained from analysis and work results.

[1162] This invention is a system that efficiently automates the maintenance and upkeep of logistics center infrastructure. This system consists of three main components: a server, a terminal, and a user, all of which work in conjunction with each other.

[1163] The server has the function of extracting necessary data from existing infrastructure information databases. Sensors and IoT devices collect real-time data and send it to the server. The server inputs the data into an AI model for analysis. Deep learning models and machine learning algorithms are used for the analysis. Based on this analysis, maintenance and repair plans are automatically generated.

[1164] The generated maintenance and repair plan is sent to the user's device. The user's device may also include smart glasses, allowing the user to visually check the plan. The user receives the notification, checks the plan, and carries out the work. When the repair is complete, the results are reported to the server via the device. The server records the report in a database and provides feedback to improve the next maintenance and repair plan.

[1165] The system's hardware includes various sensors such as temperature, humidity, and vibration sensors, while the software uses AI frameworks such as TensorFlow and PyTorch.

[1166] Data collection, processing, and calculation are carried out as follows: Data collection is carried out by acquiring real-time data from sensors and IoT devices and sending it to a server. Data processing is carried out by the server inputting the data into an AI model and performing preprocessing to make predictions. Data calculation is carried out by analyzing the data based on the patterns learned by the AI ​​model and generating maintenance and repair plans.

[1167] As a concrete example, consider the maintenance of conveyor belts in a logistics center. If data from sensors includes temperature, humidity, and vibration data, a user wearing smart glasses patrols the area and finds any abnormalities. Images of the abnormal areas are collected and sent to a server. The server inputs the data into an AI model and, based on the analysis results, notifies the smart glasses of a maintenance and repair plan, such as, "There is an abnormality in the conveyor belt in section A. Repairs are required. The recommended repair method is to replace the belt."

[1168] An example of an input prompt for a generative AI model is as follows:

[1169] "Based on temperature, humidity, vibration data and image data, determine the degree of deterioration of infrastructure within the logistics center and the necessary repairs."

[1170] This system will enable efficient and rapid maintenance and repair of logistics center infrastructure, improving the accuracy and speed of work.

[1171] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1172] Step 1: Collect data

[1173] The server extracts the necessary data from the existing infrastructure information database. Terminals (sensors and IoT devices) collect real-time data within the logistics center and send it to the server. In this step, data such as temperature, humidity, and vibration are collected. The input is real-time data from the infrastructure information database and sensors, and the output is data integrated within the server. Specifically, the server executes a database query, and the terminals send the collected data as packets.

[1174] Step 2: Preprocessing the data

[1175] The server processes the collected data into a format suitable for the AI ​​model. Specifically, it cleanses, normalizes, and extracts features from the data. The input to this step is integrated real-time data, and the output is preprocessed data. Specifically, it complements missing values ​​in the data and converts values ​​to the required range.

[1176] Step 3: Analyze the data

[1177] The server inputs the preprocessed data into the AI ​​model for analysis. The AI ​​model analyzes the data using deep learning models and machine learning algorithms to assess the condition of the infrastructure. The input for this step is the preprocessed data, and the output is the analysis results regarding the degree of deterioration and the need for repairs. Specifically, the data is fed into the model and the inference results are obtained.

[1178] Step 4: Generate a maintenance plan

[1179] The server automatically generates a maintenance and repair plan based on the analysis results. This plan includes specific repair methods and schedules. The input is the analysis results, and the output is the generated maintenance and repair plan. Specifically, the server creates an optimal rule-based plan based on the analysis results.

[1180] Step 5: Notification

[1181] The server notifies the smart glasses of the generated maintenance plan. The user visually checks the plan and performs the work. The input is the generated maintenance plan, and the output is the plan checked by the user. Specifically, text and images are sent to the smart glasses via the notification system.

[1182] Step 6: Report work completed

[1183] After completing a task, the user reports the results to the server through the smart glasses. The input is the task completion report, and the output is the report data recorded on the server. Specifically, the user inputs and transmits the report content using the operation panel of the smart glasses.

[1184] Step 7: Feedback

[1185] The server records the reported work results in a database and provides feedback to improve the next maintenance plan. The input is the reported work results data, and the output is an updated maintenance plan. Specific operations include updating the database and retraining the AI ​​model.

[1186] 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.

[1187] This invention utilizes AI technology for the maintenance and development of urban infrastructure, automating traditional manual tasks and combining it with an emotion engine that recognizes user emotions. This system consists of three main components: a server, a terminal, and a user, each of which plays a specific role. Furthermore, by analyzing the user's emotional state and adapting notification content, more effective infrastructure management is achieved.

[1188] The main processing steps of the system are:

[1189] 1. Data Collection

[1190] The server extracts data from the infrastructure information database. The data includes infrastructure information such as roads, buildings, water, sewerage, and electricity. It retrieves the data using an SQL query, for example, SELECT FROM infrastructure_data WHERE category='road'.

[1191] Terminals (sensors and IoT devices) collect real-time data from the site and send it to a server. For example, data on road cracks and subsidence is sent from sensors.

[1192] 2. Data Analysis

[1193] The server inputs the collected data into an AI model for analysis, which includes preprocessing the data to fill in missing data and remove outliers, such as cleaning the data frame using the Pandas library.

[1194] The server then inputs the pre-processed data into an AI model that uses deep learning or machine learning algorithms to assess the condition of the infrastructure and calculate the infrastructure's deterioration status and repair priorities.

[1195] 3. Automatic generation of maintenance and repair plans

[1196] The server automatically generates a maintenance plan based on the analysis results. For example, if it determines that a certain road section needs repair within a certain period of time, it will include the repair method and specific schedule in the plan.

[1197] The generated plan is stored in the database using an SQL query, for example INSERT INTO maintenance_schedule (infrastructure_id, repair_method, schedule_date) VALUES (...).

[1198] 4. Analysis by Emotion Engine

[1199] The device collects the user's voice and facial expression data and sends it to the emotion engine. For example, the device uses a camera or microphone to collect the user's facial expressions and voice and analyzes their emotional state.

[1200] The server receives the analysis results from the emotion engine and identifies the user's emotional state, making it possible to determine whether the user is stressed or relaxed.

[1201] 5. User Notification Adaptation

[1202] Based on the analysis results of the emotion engine, the server customizes the content of the maintenance and repair plan notification according to the user's emotional state. For example, if the user is under high stress, the notification content will be concise and clear, while if the user is relaxed, detailed information will be provided.

[1203] The server sends the notification to the user's device. Possible notification methods include email and in-app notifications. One method is to send email using the SMTP protocol.

[1204] 6. Work execution and reporting

[1205] Users can carry out maintenance and repair work based on the notification, and arrange for the necessary materials and workers in advance to ensure the work proceeds smoothly according to plan.

[1206] After completing the task, the user reports the results to the server via an HTTP POST request, which is then recorded in the database.

[1207] As a concrete example, consider road crack maintenance in a particular area.

[1208] 1. For data collection, the server retrieves past maintenance history from the database, and the terminal (sensor) collects the progress of cracks in real time and sends it to the server.

[1209] 2. In data analysis, the server preprocesses the collected data and inputs it into an AI model for analysis, assessing the severity of cracks and identifying which sections need repairs.

[1210] 3. When automatically generating maintenance and repair plans, the server creates a repair plan based on the results of the AI ​​model and saves it in a database.

[1211] 4. In analysis using an emotion engine, the device collects the user's voice and facial expressions, analyzes them using the emotion engine, and the server receives the results.

[1212] 5. In user notification adaptation, the server customizes the notification content according to the user's emotional state and sends it to the user's terminal.

[1213] 6. Work execution and reporting: The user carries out repair work according to the notification and reports the results after the work is completed.

[1214] These steps enable the system to achieve efficient and accurate infrastructure management and to respond flexibly to the user's emotional state.

[1215] The processing flow will be explained below.

[1216] Step 1:

[1217] Data collection

[1218] The server extracts past maintenance history and status data from the existing infrastructure information database using an SQL query such as SELECT FROM infrastructure_data WHERE category='road'.

[1219] Terminals (sensors and IoT devices) measure the local infrastructure condition (e.g., road cracks and subsidence) in real time and send the data to the server via an HTTP POST request.

[1220] Step 2:

[1221] Real-time data integration

[1222] The server integrates historical data extracted from the database with real-time data sent from the terminal, and uses Python's Pandas library to clean the data, impute missing values, and remove outliers.

[1223] Step 3:

[1224] Data analysis

[1225] The server inputs the preprocessed data into an AI model to analyze the condition of the infrastructure. Deep learning algorithms (e.g., TensorFlow and PyTorch) are used to calculate the state of deterioration of the infrastructure and the priority of repairs. Specifically, the progress of cracks and the rate of subsidence are evaluated.

[1226] Step 4:

[1227] Automatic generation of maintenance and repair plans

[1228] The server automatically generates a maintenance plan based on the analysis results of the AI ​​model. For example, if it determines that a specific road section needs patch repair within a week, it will include the repair method and specific schedule in the plan. The plan is generated in JSON format.

[1229] The server saves the generated maintenance schedule in the database using an SQL query (e.g. INSERT INTO maintenance_schedule (infrastructure_id, repair_method, schedule_date) VALUES (...)).

[1230] Step 5:

[1231] Analysis by emotion engine

[1232] The device collects the user's voice and facial expression data and sends it to the emotion engine. It uses a camera and microphone to capture the user's facial expressions and voice.

[1233] The server analyzes the data sent from the emotion engine and determines the user's emotional state, for example, detecting whether the user is stressed or relaxed, using emotion recognition algorithms.

[1234] Step 6:

[1235] User notification adaptation

[1236] The server customizes the notification content according to the user's emotional state. For example, if the user is in a high-stress state, the notification content is brief and provides only the minimum necessary information. On the other hand, if the user is in a relaxed state, the server provides detailed notification content.

[1237] The server sends notifications to the user's device. Scheduled notifications can be sent via email or in-app notifications. Emails can also be sent using the SMTP protocol.

[1238] Step 7:

[1239] User confirmation and preparation

[1240] The user checks the maintenance and repair plan sent to the terminal and arranges for repair materials and adjusts the schedule of workers based on the plan contents.

[1241] Step 8:

[1242] Work execution

[1243] The user will carry out the maintenance and repair work in accordance with the plan, specifically, carrying out any necessary repairs in an appropriate manner.

[1244] Step 9:

[1245] Work completion report

[1246] After completing the maintenance work, the user inputs the results of the work into the terminal and reports them to the server via an HTTP POST request. The report includes details of the work and the completion date and time.

[1247] Step 10:

[1248] Database recording and analysis

[1249] The server records the received work reports in the database using an SQL query (e.g. INSERT INTO maintenance_reports (infrastructure_id, work_details, completion_date) VALUES (...)).

[1250] The server analyzes the reports and generates feedback to help improve the next maintenance plan, thereby increasing the accuracy and efficiency of maintenance.

[1251] In this way, this system automates the maintenance and development of urban infrastructure efficiently and accurately, while also enabling flexible responses according to the user's emotional state.

[1252] Example 2

[1253] 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."

[1254] Conventional infrastructure management systems require a lot of manual work in collecting infrastructure information, analyzing it, and formulating and executing maintenance and development plans, which can lead to low efficiency. They also lack the ability to respond flexibly to users' emotional states, making effective infrastructure management difficult. Furthermore, insufficient pre-processing of collected data led to problems with the accuracy and reliability of analysis results.

[1255] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1256] In this invention, the server includes a means for extracting data from an existing infrastructure information database, a means for collecting real-time data from sensors and IoT devices and transmitting it to the server, and a means for preprocessing the extracted and collected data by filling in missing data and removing outliers. This improves the accuracy and reliability of data analysis. Furthermore, the server includes a means for automatically generating a maintenance and repair plan based on the analysis results, a means for collecting user voice and facial expression data and transmitting it to an emotion engine, a means for receiving the analysis results from the emotion engine and identifying the user's emotional state, and a means for customizing the content of the maintenance and repair plan notification based on the analysis results and the user's emotional state. This enables flexible responses according to the user's emotional state and achieves effective infrastructure management. The server also includes a means for notifying the user of the generated plan, reporting the user's work results to the server and recording them in a database, and a means for analyzing the report and providing feedback to improve the maintenance and repair plan. This significantly improves the efficiency and effectiveness of infrastructure management.

[1257] An "infrastructure information database" is an information system for storing and managing data related to urban infrastructure.

[1258] A "sensor" is a device that detects changes or conditions in the physical environment and transmits them as digital data.

[1259] An "IoT device" is an electronic device that can connect to other devices and systems via the Internet.

[1260] A "server" is a high-performance computing system for collecting, analyzing, storing, and communicating data.

[1261] An "AI model" is a mathematical model that uses artificial intelligence technology to analyze data and make predictions.

[1262] "Data preprocessing" refers to the process of performing operations such as filling in missing data and removing outliers before data analysis.

[1263] A "maintenance and development plan" is a plan that devisees repair methods and schedules for the maintenance and management of infrastructure.

[1264] A "user terminal" is a device through which a user communicates with a server and receives information.

[1265] The "emotion engine" is a system that analyzes the user's voice and facial expression data to identify their emotional state.

[1266] "Customizing notification content" means adjusting the presentation method and content of information to suit the user's specific situation and requirements.

[1267] An "HTTP POST request" is a type of HTTP protocol that allows a client to send data to a server.

[1268] A "database" is a system for systematically storing and managing digital data.

[1269] The "SMTP protocol" is a communication protocol for sending email.

[1270] "Feedback" is the process of reflecting on execution results and new data in order to improve and optimize the system.

[1271] "Reporting work results" means sending and recording the results of maintenance and repair work performed by the user to the server.

[1272] This invention is a system for improving the efficiency of urban infrastructure maintenance and development and automating manual tasks. It also achieves more effective infrastructure management by taking into account the user's emotional state and responding flexibly. This system consists of three main components: a server, a terminal, and a user.

[1273] The server first extracts the necessary data from an infrastructure information database. This data includes information on roads, buildings, water and sewerage systems, electricity, and other infrastructure. The extracted data is then input into an AI model, where it is analyzed. Missing data is filled in and outliers are removed. This is done using data processing libraries such as Pandas. The preprocessed data is then input into an AI model that includes deep learning and machine learning algorithms to evaluate the condition of the infrastructure.

[1274] The terminal uses sensors and IoT devices to collect real-time data on the site and send it to a server. For example, vibration sensors and cameras on the road detect cracks and subsidence and send the data to the server. The collected data is analyzed on the server to calculate the state of deterioration of the infrastructure and the priority of repairs.

[1275] The server automatically generates a maintenance plan based on the analysis results. For example, if a specific road section needs urgent repairs, the plan will include the repair method and specific schedule. This plan is stored in a database and registered using SQL queries.

[1276] Furthermore, the device collects the user's voice and facial expression data and sends it to the emotion engine. For example, the device can capture the user's facial expressions using a camera and analyze them with the emotion engine. The server receives the analysis results from the emotion engine and identifies the user's emotional state. This makes it possible to determine whether the user is feeling stressed or relaxed.

[1277] Based on the analysis results of the emotion engine, the server customizes the content of the maintenance and repair plan notification according to the user's emotional state. For example, if the user is in a high-stress state, the notification content will be brief, while if the user is relaxed, detailed information will be provided. Notifications are sent from the server to the user's device. Possible notification methods include email and in-app notifications. Sending email using the SMTP protocol is also included.

[1278] The user carries out maintenance work based on the notification content. The necessary materials and workers are arranged according to the plan. After the work is completed, the user reports the work results to the server via their terminal. The report content is sent to the server via an HTTP POST request and recorded in the database. The server analyzes the report content and provides feedback to improve the maintenance plan.

[1279] This allows the system to achieve efficient and accurate infrastructure management and respond flexibly to the user's emotional state.

[1280] As a concrete example, consider the maintenance of cracks on roads in a specific area. The server retrieves past maintenance history from a database, and the terminal (sensor) collects the progress of the cracks in real time and sends it to the server. The data is preprocessed and input into an AI model for analysis, and the severity of the cracks is evaluated. A repair plan is automatically generated based on the analysis results and saved in the database. The user's voice and facial expression data is collected and analyzed by an emotion engine, and the notification content is customized according to the user's emotional state and sent to the user's terminal. The user then carries out the work according to the notification and reports the results after completing the work.

[1281] An example of a prompt to input to a generative AI model is as follows:

[1282] "This system automates infrastructure maintenance in a specific area. First, it retrieves past maintenance information from a database and collects real-time data from sensors. Next, it analyzes this data using an AI model to automatically generate a repair plan. Furthermore, it analyzes the user's emotional state and customizes the content of notifications to achieve more effective management. For example, it can send a simple notification to a user in a stressed state and a detailed notification to a user in a relaxed state. As a concrete example, please consider road crack maintenance and explain the process."

[1283] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1284] Step 1: Data collection

[1285] The server first extracts infrastructure information such as roads, buildings, water supply and sewerage, and electricity from an existing infrastructure information database using an SQL query. For example, the query SELECT FROM infrastructure_data WHERE category='road' is used. This query retrieves data related to a specific infrastructure category.

[1286] The terminal collects real-time data from sensors and IoT devices and sends the data to a server. The sensors detect road cracks and subsidence information in real time and send it to the server using an HTTP POST request. Specific inputs include the sensor ID and measurement data, and the output is sent to the server.

[1287] Step 2: Data Preprocessing

[1288] The server preprocesses the collected data. This preprocessing includes filling in missing data and removing outliers. Specifically, it uses the Pandas library to clean the data frame. For example, it uses df.fillna(0, inplace=True) and filters outliers to improve the quality of the input data. The input for this step is the sensor data and data extracted from the database, and the output is clean data after preprocessing.

[1289] Step 3: Data analysis

[1290] The server inputs the preprocessed data into an AI model for analysis. For example, it uses deep learning and machine learning algorithms built with TensorFlow and Scikit-learn to assess the state of infrastructure deterioration and repair priorities. The input is the preprocessed data, and the output is the infrastructure condition assessment results. This identifies which sections are in urgent need of repair.

[1291] Step 4: Automatic generation of maintenance and repair plans

[1292] The server automatically generates a maintenance and repair plan based on the analysis results of the AI ​​model. For example, if it determines that a specific road section needs repair within a certain period of time, it will include the repair method and specific schedule in the plan. The input for this step is the analysis results of the AI ​​model, and the output is a repair plan. The repair plan is stored in a database and registered using SQL queries.

[1293] Step 5: Analysis by Emotion Engine

[1294] The device collects the user's voice and facial expression data and sends it to the emotion engine. It uses a camera and microphone to capture the user's facial expressions and voice in real time and sends it to an API that analyzes their emotional state. The input here is the user's voice and facial expression data, and the output is the analysis result by the emotion engine.

[1295] The server receives the analysis results from the emotion engine and identifies the user's emotional state, with the input being the analysis results from the emotion engine and the output being a determination of the user's emotional state.

[1296] Step 6: Adapting User Notifications

[1297] The server customizes the notification content for maintenance and repair plans based on the analysis results of the emotion engine according to the user's emotional state. For example, if the user is in a high-stress state, the notification content is brief, while if the user is relaxed, detailed information is provided. The input is the analysis results of the emotion engine and the maintenance and repair plans, and the output is the customized notification content.

[1298] The server sends the notification to the user's device. Possible notification methods include email and in-app notifications, and email may be sent using the SMTP protocol.

[1299] Step 7: Execute and report

[1300] The user performs maintenance and repair work based on the notification. The necessary materials and workers are arranged according to the plan. After completing the work, the user reports the work results to the server from the terminal. The input is the user's work results, and the output is the report to the server. The report is sent via an HTTP POST request and recorded in the database.

[1301] The server analyzes the results of the user's work and provides feedback to improve the maintenance plan. The input is the user's report, and the output is an improved maintenance plan.

[1302] (Application example 2)

[1303] 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."

[1304] In modern infrastructure management, traditional manual maintenance and repair work requires a great deal of time and effort, making efficient management difficult. In addition, notifications are sent without considering the user's feelings, which leaves a psychological burden on the user and prevents optimal work efficiency.

[1305] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for extracting data from an existing infrastructure information database, means for collecting real-time data from sensors and IoT devices and transmitting it to the server, means for inputting the extracted and collected data into an AI model and analyzing it, means for automatically generating a maintenance and repair plan based on the analysis results, means for notifying a user terminal of the generated maintenance and repair plan, means for collecting user voice and facial expression data, analyzing it with an emotion engine, and transmitting it to the server, means for customizing the notification content based on the analysis results of the emotion engine and transmitting it to the user terminal, means for reporting the user's work results to the server and recording them in a database, and means for analyzing the report content and providing feedback to improve the maintenance and repair plan. This enables efficient infrastructure management and provides appropriate notifications according to the user's emotional state, reducing the user's psychological burden and ensuring optimal work efficiency.

[1306] An "existing infrastructure information database" is an existing database for storing data on infrastructure such as roads, buildings, water supply and sewerage systems, and electricity.

[1307] "Sensors and IoT devices" are electronic devices that collect environmental data and status information in real time and send it to a server via a network.

[1308] "Server" means a computer system established to collect, analyze, store, and notify data.

[1309] An "AI model" is a model that includes an artificial intelligence algorithm used to analyze accumulated data and derive useful results.

[1310] "Maintenance and development plan" means a plan that includes the schedule and methods of repair and maintenance work, which is prepared based on the deterioration state of the infrastructure and the priority of repairs.

[1311] A "user terminal" is a device used to receive notifications and reports and perform management tasks, and includes smartphones, tablets, and PCs.

[1312] An "emotion engine" is software and algorithms that analyze a user's voice and facial expressions to recognize their emotional state.

[1313] The "means for customizing notification content" is a method for optimizing notification content and providing personalized information based on the analyzed emotion data.

[1314] "Means for analyzing the report content and providing feedback to improve maintenance and repair plans" refers to a method for analyzing the reported data from users and reflecting it in new maintenance and repair plans.

[1315] This invention is a system for streamlining infrastructure maintenance and repair in logistics centers, combined with a function that recognizes the user's emotional state and adapts the notification content. The system consists of three main components: a server, a terminal, and a user.

[1316] The server extracts data from an existing infrastructure information database. This data includes information such as the safety of shelves in a distribution center and cracks in the floor. It also collects real-time data from sensors and IoT devices and sends it to the server. The collected data is preprocessed using libraries such as Pandas to fill in missing data and remove outliers. The data is then input into an AI model (e.g., a deep learning model or machine learning algorithm) to analyze the infrastructure's deterioration status and repair priorities.

[1317] The server automatically generates a maintenance and repair plan based on the analysis results. This plan includes specific repair methods and schedules and is saved in a database. The generated maintenance and repair plan is then sent to the user's device, which could be a smartphone or tablet.

[1318] Furthermore, the server collects the user's voice and facial expression data and analyzes it using an emotion engine (e.g., Microsoft Azure Emotion API). Based on the analysis results of the emotion engine, the notification content is customized and sent to the user's device. For example, if the user is stressed, a simple notification is sent, and if the user is relaxed, a detailed notification is sent.

[1319] The user performs maintenance and repair work based on the notification and reports the results after completion. The report is sent to the server and recorded in the database. Finally, the server analyzes the report and provides feedback to improve the maintenance and repair plan. This makes future plans more accurate and efficient.

[1320] As a concrete example, consider the case where the safety of shelves in a logistics center has deteriorated. The server retrieves maintenance history from a past database, and sensors collect information on the shelf's condition in real time and send it to the server. The server preprocesses the data, evaluates the shelf's safety using an AI model, and creates a repair plan. The server customizes the notification content based on the user's emotional state and sends it to the user's device. The user then carries out repair work in accordance with the notification and reports the results.

[1321] Example prompt sentence:

[1322] "Check the infrastructure condition in your distribution center. Use sensors and cameras to collect shelf safety data and send it to a server. The server will analyze the data and automatically generate repair plans. Send brief or detailed notifications depending on the emotional state of your staff."

[1323] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1324] Step 1:

[1325] The server extracts the necessary data from an existing infrastructure information database. Specifically, it obtains infrastructure information such as shelves and floors within the logistics center using an SQL query (e.g., SELECT FROM infrastructure_data WHERE category='shelf'). The input is the infrastructure information in the database, and the output is infrastructure data converted into a format that can be processed within the server.

[1326] Step 2:

[1327] Terminals (sensors and IoT devices) collect real-time data from within the logistics center and send it to a server. For example, cracks in the floor and damage to shelves are measured by sensors and sent to the server via wireless communication. The input is environmental data collected in real time, and the output is the raw data sent to the server.

[1328] Step 3:

[1329] The server preprocesses the collected data. Specifically, it cleans the data frame using the Pandas library, imputes missing data (e.g., df.fillna(method='ffill')), and removes outliers. The input is raw data obtained from sensors or databases, and the output is clean data after preprocessing.

[1330] Step 4:

[1331] The server inputs the preprocessed data into the AI ​​model for analysis. Specifically, it uses a deep learning model or machine learning algorithm to analyze the data and evaluate the infrastructure's deterioration status and repair priority. The input is clean data, and the output is infrastructure condition assessment data.

[1332] Step 5:

[1333] The server automatically generates a maintenance plan based on the analysis results. For example, it determines a specific repair method and schedule for a certain shelf section and stores it in the database using an SQL query (e.g., INSERT INTO maintenance_schedule (infrastructure_id, repair_method, schedule_date) VALUES (...)). The input is the infrastructure condition assessment data, and the output is a specific maintenance plan.

[1334] Step 6:

[1335] The device collects the user's voice and facial expression data and sends it to an emotion engine for analysis. Specifically, data is collected using the smartphone's camera and microphone, and emotion analysis is performed using an emotion engine such as Microsoft Azure Emotion API. The input is the user's voice and facial expression data, and the output is the emotion analysis results.

[1336] Step 7:

[1337] The server receives the analysis results of the emotion engine and customizes the notification content according to the user's emotional state. For example, if the user is in a stressful state, it prepares a brief notification, and if the user is in a relaxed state, it prepares a detailed notification. The input is the emotion analysis result, and the output is the customized notification content.

[1338] Step 8:

[1339] The server sends the customized notification content to the user device. Specifically, it notifies the user using an in-app notification or email (e.g., sending an email using the SMTP protocol). The input is the customized notification content, and the output is the notification sent to the user device.

[1340] Step 9:

[1341] The user performs maintenance and repair work based on the notification. Specifically, the user performs the necessary repairs according to the procedure manual and records the progress of the work. The input is the notification content, and the output is the completed work results.

[1342] Step 10:

[1343] The user reports the results of their work to the server. Specifically, they send the report via an HTTP POST request through the app. The input is the work result, and the output is the report data recorded in the database.

[1344] 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.

[1345] 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.

[1346] 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.

[1347] 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.

[1348] 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.

[1349] 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.

[1350] 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).

[1351] 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, motorcycles, and other devices, 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.

[1352] 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."

[1353] 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.

[1354] 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).

[1355] 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.

[1356] 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.

[1357] 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.

[1358] 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.

[1359] 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.

[1360] 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.

[1361] 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.

[1362] 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.

[1363] 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.

[1364] 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.

[1365] The following is further disclosed regarding the above embodiment.

[1366] (Claim 1)

[1367] a means for extracting data from an existing infrastructure information database;

[1368] A means of collecting real-time data from sensors and IoT devices and sending it to a server,

[1369] A means of inputting the extracted and collected data into an AI model for analysis;

[1370] A means for automatically generating maintenance and repair plans based on the analysis results,

[1371] A means for notifying a user terminal of the generated maintenance and repair plan;

[1372] A means for reporting the work results from the user to the server and recording them in a database;

[1373] A means of analyzing the report and providing feedback to improve maintenance and repair plans,

[1374] A system including:

[1375] (Claim 2)

[1376] 2. The system according to claim 1, wherein the data collection means acquires information on roads, buildings, water supply and sewerage, electricity, etc.

[1377] (Claim 3)

[1378] 10. The system of claim 1, wherein the AI ​​model comprises a deep learning model or a machine learning algorithm.

[1379] "Example 1"

[1380] (Claim 1)

[1381] a means for extracting data from an existing infrastructure information database;

[1382] A means of collecting real-time data from sensors and IoT devices and sending it to a server,

[1383] A means to preprocess the extracted and collected data, input it into an AI model, and perform analysis.

[1384] A means of using machine learning frameworks as AI models;

[1385] A means for automatically generating maintenance and repair plans based on the analysis results,

[1386] A means for notifying a user terminal of the generated maintenance and repair plan;

[1387] A means for reporting the work results from the user to the server and recording them in a database;

[1388] A means of analyzing the report and providing feedback to improve maintenance and repair plans,

[1389] A system including:

[1390] (Claim 2)

[1391] 2. The system according to claim 1, wherein the data collection means acquires information on transportation infrastructure, buildings, public facilities, power supply systems, etc.

[1392] (Claim 3)

[1393] 10. The system of claim 1, wherein the AI ​​model comprises a deep learning model or a machine learning algorithm.

[1394] "Application Example 1"

[1395] (Claim 1)

[1396] a means for extracting data from an existing infrastructure information database;

[1397] A means of collecting real-time data from sensors and IoT devices and sending it to a server,

[1398] A means of inputting the extracted and collected data into an AI model for analysis;

[1399] A means for automatically generating maintenance and repair plans based on the analysis results,

[1400] A means for notifying a user terminal of the generated maintenance and repair plan;

[1401] A means for reporting the work results from the user to the server and recording them in a database;

[1402] A means of analyzing the report and providing feedback to improve maintenance and repair plans,

[1403] A means for notifying the smart glasses of a maintenance and repair plan based on the analysis results so that the user can visually confirm it;

[1404] A system including:

[1405] (Claim 2)

[1406] 2. The system according to claim 1, wherein the data collection means acquires information on logistics bases, electronic devices, transportation equipment, energy supply equipment, etc.

[1407] (Claim 3)

[1408] 10. The system of claim 1, wherein the AI ​​model comprises a deep learning model or a machine learning algorithm.

[1409] "Example 2: Combining Emotion Engines"

[1410] (Claim 1)

[1411] a means for extracting data from an existing infrastructure information database;

[1412] A means of collecting real-time data from sensors and IoT devices and sending it to a server,

[1413] A means of inputting the extracted and collected data into an AI model for analysis;

[1414] As a data preprocessing step, a method for filling in missing data and removing outliers is provided.

[1415] A means for automatically generating maintenance and repair plans based on the analysis results,

[1416] A means for collecting user voice and facial expression data and transmitting the data to the emotion engine;

[1417] means for receiving the analysis results from the emotion engine and identifying the emotional state of the user;

[1418] A means for customizing the content of maintenance and servicing notifications based on the analysis results and the user's emotional state;

[1419] A means for notifying a user terminal of the generated maintenance and repair plan;

[1420] A means for reporting the work results from the user to the server and recording them in a database;

[1421] A means of analyzing the report and providing feedback to improve maintenance and repair plans,

[1422] A system including:

[1423] (Claim 2)

[1424] 2. The system according to claim 1, wherein the data collection means acquires infrastructure information such as roads, buildings, water supply and sewerage, and electricity.

[1425] (Claim 3)

[1426] 10. The system of claim 1, wherein the AI ​​model comprises a deep learning algorithm or a machine learning algorithm.

[1427] "Application example 2 when combining emotion engines"

[1428] (Claim 1)

[1429] a means for extracting data from an existing infrastructure information database;

[1430] A means of collecting real-time data from sensors and IoT devices and sending it to a server,

[1431] A means of inputting the extracted and collected data into an AI model for analysis;

[1432] A means for automatically generating maintenance and repair plans based on the analysis results,

[1433] A means for notifying a user terminal of the generated maintenance and repair plan;

[1434] A means for collecting user voice and facial expression data, analyzing it with an emotion engine, and sending it to a server;

[1435] a means for customizing notification content based on the analysis result of the emotion engine and transmitting the customized notification content to the user terminal;

[1436] A means for reporting the work results from the user to the server and recording them in a database;

[1437] A means of analyzing the report and providing feedback to improve maintenance and repair plans,

[1438] A system including:

[1439] (Claim 2)

[1440] 2. The system according to claim 1, wherein the data collection means acquires information on roads, buildings, water supply and sewerage, electricity, etc.

[1441] (Claim 3)

[1442] 10. The system of claim 1, wherein the AI ​​model comprises a deep learning model or a machine learning algorithm. [Explanation of symbols]

[1443] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for extracting data from an existing infrastructure information database; A means of collecting real-time data from sensors and IoT devices and sending it to a server, A means of inputting the extracted and collected data into an AI model for analysis; A means for automatically generating a maintenance and repair plan based on the analysis results; a means for notifying a user terminal of the generated maintenance and repair plan; A means for reporting the work results from the user to the server and recording them in a database; A means of analyzing the reports and providing feedback to improve maintenance and repair plans; A system including:

2. 2. The system according to claim 1, wherein the data collection means acquires information on roads, buildings, water and sewerage systems, electricity, and the like.

3. 10. The system of claim 1, wherein the AI ​​model comprises a deep learning model or a machine learning algorithm.

Images