System

Abstract

A system is provided.SOLUTION: A system, comprising: means for a user to photograph a risk location of an infrastructure and input and upload a comment; means for a server to store the received photograph and comment in a database and add the photograph and comment to a AI analysis queue; means for a AI model to analyze the photograph and comment to identify a risk level and risk details and generate a proposed crowdfunding measure; and means for the server to notify the user of the generated proposed safety measure and initiate a safety measure if necessary.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] Currently, risks are increasing due to the aging of infrastructure (roads, electricity, gas, water, communications, hospitals, parks, schools, stations, airports, etc.) and an increase in natural disasters, but it is difficult for national and local governments to respond to all of these risks, and measures to prevent risks before they occur are required. However, at present, there is insufficient collection of infrastructure risk information, and there is a lack of a system for quickly formulating appropriate countermeasures, so many potential dangers are being left unattended. Furthermore, there are issues with the transparency and speed of funding. [Means for solving the problem]

[0005] To solve the above problems, we devised a system that provides the following means. First, we provide a means for users to take photos of risky areas in infrastructure, enter comments, and upload them to a server. Next, we provide a means for the server to store the received photos and comments in a database and add them to an AI analysis queue. Finally, we provide a means for an AI model to analyze the photos and comments to identify the risk level and details and generate safety measures. We also provide a means for the server to notify users of the generated safety measures and, if necessary, initiate crowdfunding. Furthermore, we aim to speed up and improve the transparency of infrastructure risk information collection and countermeasures by adding a means for the server to automatically implement the safety measures based on the risk information analyzed by the AI ​​model, a means for the server to set up a crowdfunding link and notify all users, and a means for the server to share with users the status of repairs to risk areas reported by users.

[0006] "User" refers to a person or organization that can take photos of risky areas of infrastructure, enter comments, and upload them to a server.

[0007] "Device" refers to an electronic device used by a user, such as a smartphone or computer, that allows the user to input and upload photos and comments.

[0008] "Server" refers to a computer system that receives, stores, analyzes, and notifies users of data uploaded by the server.

[0009] "Infrastructure" refers to the facilities and equipment that make up the social infrastructure, such as roads, electricity, gas, water, communications, hospitals, parks, schools, stations, and airports.

[0010] "Risk areas" refer to locations where safety issues, such as damage or deterioration of infrastructure, are expected.

[0011] "Comment" refers to text entered by the user as an explanation or supplementary information for the risky area photographed.

[0012] "Database" refers to an information management system in which a server stores information such as photos and comments, making it accessible and searchable.

[0013] "AI analysis queue" refers to a sequence of data that the server manages to analyze received data sequentially.

[0014] "AI model" refers to a system that uses machine learning algorithms to analyze photos and comments to identify risk levels and risk details.

[0015] "Risk level" refers to an evaluation index that indicates the severity of infrastructure risk obtained as a result of analysis by the AI ​​model.

[0016] "Risk details" refers to information that describes specific issues and potential impacts related to risk areas.

[0017] "Safety measures proposal" refers to countermeasures and action plans identified based on analyzed risk information.

[0018] "Crowdfunding" refers to an online fundraising method for collecting funds from users and stakeholders.

[0019] "Link" refers to the web address that allows users to access the Crowdfunding Page.

[0020] "Remediation status" refers to information showing the progress of countermeasures and repairs implemented for reported risk areas. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0029] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0042] The present invention is a system that generates safety measures by collecting risk information related to infrastructure that users use on a daily basis and analyzing it using AI. Below, an embodiment of the present invention will be described in natural language.

[0043] User-generated and uploaded risk information

[0044] When a user discovers a risky area in infrastructure, they take a photo of the area and upload it to the application using a device such as a smartphone or computer. The user also enters a brief comment for the photo, explaining the details of the risk. For example, if a user discovers a large crack in the road, they can take a photo of the crack and enter a comment such as, "There is a large crack. It looks like it could cause a traffic accident," and submit it to the app.

[0045] Data reception and storage by the server

[0046] The server receives the photos and comments sent by users. The received data is stored in a database by the server. The database is an information management system for managing information such as photos and comments, and can efficiently store and search data for later analysis.

[0047] Data analysis using AI models

[0048] The server adds the information stored in the database to an AI analysis queue, which then analyzes it using the AI ​​model. The AI ​​model uses the received photos and comments as input data to perform a risk analysis. As a result of the analysis, the risk level (e.g., "high") and risk details (e.g., "possibility of a traffic accident due to cracks in the road") are identified.

[0049] Generate safety measures

[0050] The server generates safety measures based on the risk information identified by the AI ​​model. These safety measures include specific action plans and countermeasures, such as suggesting that road repairs are necessary.

[0051] User notification and crowdfunding

[0052] The server notifies all users of the safety measures it has created. Users can check the measures through the application. If necessary, the server will also launch a crowdfunding campaign, set up a link to collect funds from users and other interested parties, and notify all users. The crowdfunding page will contain detailed information about the risks and the measures, and funders can make donations through the page.

[0053] Sharing the status of corrections

[0054] The server manages the repair status of risk areas reported by users and shares it with all users. This allows users to check the progress of repairs in real time and understand how the risk areas they reported are being addressed. For example, when repairs to cracks in a road are completed, that information is notified to all users.

[0055] Specific examples

[0056] Specific examples are shown below.

[0057] 1. User action: A user finds a fallen tree in a nearby park, takes a photo of it, and writes a comment saying, "There is a fallen tree in the park. It may cause injury."

[0058] 2. Server processing: The server receives the photos and comments, stores them in a database, and then adds them to the AI ​​analysis queue.

[0059] 3. AI model analysis: The AI ​​model analyzes the photos and comments to identify risk details such as "Risk level: High" and "Fallen trees in the park pose a risk of injury."

[0060] 4. Generation of safety measures: The server generates safety measures such as "removal of fallen trees is required" and notifies all users.

[0061] 5. Crowdfunding: If necessary, the server will start the crowdfunding and send the link to all users.

[0062] 6. Sharing of correction status: When the fallen tree removal work is completed, the information is shared with all users.

[0063] The present invention makes it possible to quickly identify safety risks in infrastructure and take appropriate measures. Furthermore, funds can be raised through crowdfunding with the cooperation of users, and measures can be implemented with high transparency.

[0064] The processing flow will be explained below.

[0065] Step 1:

[0066] When a user discovers a risky area in the infrastructure, they can take a photo of the area using a device such as a smartphone or computer.

[0067] Step 2:

[0068] The user launches a dedicated application and takes a photo and enters a comment along with it. For example, the user might write, "There's a big crack. It could cause a traffic accident."

[0069] Step 3:

[0070] The device sends the entered photo and comment to the server.

[0071] Step 4:

[0072] The server temporarily stores the received photos and comments in a database.

[0073] Step 5:

[0074] The data stored by the server is added to the AI ​​analysis queue and prepared for analysis.

[0075] Step 6:

[0076] The server passes the photo and comment data from the queue to the AI ​​model and begins analysis.

[0077] Step 7:

[0078] The AI ​​model analyzes the photos and comments to identify risk levels, such as "Risk level: High" and "Risk details: Possibility of traffic accident due to cracks in the road."

[0079] Step 8:

[0080] The server generates safety measures based on the analysis results of the AI ​​model, such as "Road repair work is required."

[0081] Step 9:

[0082] The server notifies all users of the generated safety measures and analysis results.

[0083] Step 10:

[0084] If necessary, the server will set up a crowdfunding campaign and send a link to all users, which will include details of the risks and countermeasures.

[0085] Step 11:

[0086] Users can access the crowdfunding page and provide funds, which are then used to repair and improve infrastructure.

[0087] Step 12:

[0088] The server manages the status of risk fixes and shares the progress with all users. When fixes are complete, the server also notifies users of this information.

[0089] Example 1

[0090] 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."

[0091] Currently, risk management for everyday infrastructure is time-consuming and often results in inappropriate responses. There are also issues with efficient sharing of risk information and methods of fundraising. The present invention aims to solve these problems and provide a system that quickly and effectively identifies infrastructure risks and takes appropriate measures.

[0092] 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.

[0093] In this invention, the server includes means for users to take photos of risky areas in infrastructure they use daily, enter comments, and upload them from their terminals, means for the server to store the photos and comments received in a database and add them to an AI analysis queue, means for preprocessing the generated data and for an AI model to analyze the photos and comments to identify the risk level and details, means for automatically generating safety measure proposals based on the identified risk information, means for the server to notify all users of the generated safety measure proposals and start crowdfunding as necessary, and means for managing and notifying the status of repairs to risky areas. This enables quick and effective identification of infrastructure safety risks and enables highly transparent countermeasures and fundraising.

[0094] "User" refers to anyone who uses the system to report infrastructure risks and upload photos and comments.

[0095] "Infrastructure" refers to structures and systems that support the foundations of society, including roads, parks, bridges, etc.

[0096] "Risk points" refer to locations within infrastructure where potential dangers may exist.

[0097] "Photographing" refers to the operation of using a device to leave a visual record.

[0098] "Comment" refers to text information that a user adds to a photograph they have taken.

[0099] "Terminal" refers to the device that a user uses to access the system, such as a smartphone or PC.

[0100] "Upload" refers to the operation of sending data from a terminal to a server.

[0101] "Server" refers to a computer system for managing and processing data received from users.

[0102] A "database" refers to a system for managing and storing information, allowing photos and comments to be efficiently stored and searched.

[0103] "AI analysis queue" refers to a waiting line structure for sequentially analyzing data.

[0104] "Preprocessing" refers to the operations used to convert data into a format suitable for analysis by an AI model.

[0105] "AI model" refers to software that uses machine learning technology to analyze data and identify risk levels and risk details.

[0106] "Risk Level" refers to a classification that indicates the severity of an identified risk.

[0107] "Risk details" refers to information that explains the specific details of an identified risk.

[0108] "Safety measures" refers to specific action plans and countermeasures to be taken in response to identified risks.

[0109] "Crowdfunding" refers to a method of widely raising funds via the Internet to address infrastructure risks.

[0110] "Link" refers to the URL that allows users to access the crowdfunding page.

[0111] "Notification" refers to the operation of the server sending information to the user and informing them.

[0112] "Remediation status" refers to the progress of the actions and corrections taken against the reported risk areas.

[0113] "Management" refers to monitoring the operational status of the entire system and performing necessary operations.

[0114] The present invention is a system that generates safety measures by collecting risk information related to infrastructure that users use on a daily basis and analyzing it using AI. Below, an embodiment of the present invention will be described in natural language.

[0115] Hardware and Software Configuration

[0116] This system includes the devices used by users (smartphones, PCs, etc.) and servers. The backend system uses a database (e.g., MySQL, PostgreSQL) for data management and a machine learning model (e.g., TensorFlow, PyTorch) for AI analysis.

[0117] User-generated and uploaded risk information

[0118] When a user discovers a risky area in the infrastructure, they take a photo of the area using their smartphone or computer. After taking the photo, they launch a dedicated application, select the photo they took, and upload it to the application. The user then enters a comment for the photo, explaining the details of the risk. The photo and comment data are then sent to the server. For example, if a user discovers a large crack in the road, they might enter a comment such as, "There's a large crack. It looks like it could cause a traffic accident."

[0119] Data reception and storage by the server

[0120] The server receives the photos and comments sent by the user as HTTP requests. The server saves the received photo data in a temporary directory and obtains the file path. At the same time, it saves the comment text and the photo file path in the database. This data is later added to the AI ​​analysis queue.

[0121] Data analysis using AI models

[0122] The server detects when new data is added to the database and adds the data to the AI ​​analysis queue. Before the data is passed to the AI ​​model, the server performs the necessary preprocessing. Specifically, it preprocesses the photo data using an image processing library (e.g., OpenCV) and converts the comment text into a format suitable for the NLP model. The preprocessed data is then input into the AI ​​model to identify the risk level and risk details.

[0123] Creation and notification of safety measures

[0124] Based on the risk information identified by the AI ​​model, the server uses a rule-based engine to generate safety measures. The generated safety measures are stored in a database, and the server then notifies all users of the measures. If necessary, a crowdfunding link is also generated and notified to users.

[0125] Sharing the status of corrections

[0126] The server manages the status of risk corrections and updates it regularly. When the corrections are complete, the information is notified to all users, allowing them to check the status of the corrections in real time.

[0127] Specific examples

[0128] Specific examples are shown below.

[0129] User Action: A user finds a fallen tree in a local park, takes a photo of it, and writes a comment saying, "There is a fallen tree in the park. It could cause injury."

[0130] Server processing: The server receives the photos and comments, stores them in a database, and then adds them to the AI ​​analysis queue.

[0131] AI model analysis: The AI ​​model analyzes photos and comments to identify risk levels such as "high" and risk details such as "falling trees in the park pose a risk of injury."

[0132] Generation of safety measures: The server generates safety measures such as "removal of fallen trees is required" and notifies all users.

[0133] Crowdfunding: The server will start the crowdfunding campaign if necessary and send the link to all users.

[0134] Sharing of repair status: When the fallen tree removal work is completed, the information is shared with all users.

[0135] Example prompts to be input to the generative AI model:

[0136] "There is a fallen tree in the park that could cause injury. Please analyze this risk."

[0137] This will enable rapid and effective identification of infrastructure safety risks and enable appropriate countermeasures and funding.

[0138] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0139] Step 1:

[0140] The user takes a photo of the risky part of the infrastructure, enters a comment, and uploads it from the terminal (input: photo and comment of the risky part of the infrastructure. output: sending the photo and comment).

[0141] Specific behavior:

[0142] Users use a smartphone or computer to take photos of risky areas of infrastructure.

[0143] The user launches the application, selects a photo, and proceeds to the upload screen.

[0144] The user enters a comment and details the risk in the text fields.

[0145] The user clicks the "Send" button to send the photo and comments to the server.

[0146] Step 2:

[0147] The server saves the received photos and comments in a database and adds them to the AI ​​analysis queue (input: sent photo and comment data; output: saved in database and added to queue).

[0148] Specific behavior:

[0149] The server receives an HTTP request from the user, which includes the photo data and comment text.

[0150] The server stores the photo data in a temporary directory and obtains the file path.

[0151] The server saves the comment data and the photo file path as a new record in the database.

[0152] Detects when a new record is saved and adds the data to the AI ​​analysis queue.

[0153] Step 3:

[0154] The server preprocesses the data, and the AI ​​model analyzes the photos and comments to identify risk levels and risk details (input: photos and comments stored in the database; output: risk levels and risk details).

[0155] Specific behavior:

[0156] The server preprocesses the photos and comments stored in the database.

[0157] Use an image processing library (e.g. OpenCV) to convert the photo data into an appropriate format.

[0158] Tokenize text data into a format suitable for natural language processing (NLP) models.

[0159] The server inputs the preprocessed data into the AI ​​model for analysis.

[0160] The AI ​​model analyzes photos and comments to identify risk levels (e.g., "High") and risk details (e.g., "Possibility of traffic accident due to cracks in the road").

[0161] Step 4:

[0162] Based on the identified risk information, the server automatically generates safety measures (input: risk level and risk details; output: safety measures).

[0163] Specific behavior:

[0164] The server receives the risk level and risk details returned by the AI ​​model.

[0165] The server uses a rule-based engine to generate risk-informed safety measures.

[0166] For example, if the risk level is "high," it will suggest that "road repair work is needed."

[0167] The generated safety measures are stored in a database.

[0168] Step 5:

[0169] The server notifies all users of the generated safety measures and initiates crowdfunding if necessary (Input: Safety measures. Output: User notification and crowdfunding link).

[0170] Specific behavior:

[0171] The server prepares a communication method (push notification, email, etc.) to notify all users of the generated safety measures.

[0172] The server forms a notification message and sends it with the content "A new security plan has been generated."

[0173] If necessary, the server generates a link to the crowdfunding page and notifies the user.

[0174] Step 6:

[0175] The server manages and notifies the status of risk corrections (input: correction status information; output: correction completion notification).

[0176] Specific behavior:

[0177] The server periodically checks and updates the status of corrections to risk areas.

[0178] Once the correction is complete, the information is recorded in the database.

[0179] The server sends a completion notification of the modification status to all users.

[0180] Users will receive notifications and can see the corrected infrastructure state on their applications.

[0181] (Application example 1)

[0182] 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."

[0183] There is a need to quickly and accurately identify infrastructure risk information and implement safety measures. Road risk information is particularly essential for autonomous vehicles, and risks must be identified in real time and notified to passengers and operation management systems. However, conventional systems can delay risk identification and notification, threatening safety. Furthermore, smooth funding for risk countermeasures is also necessary, but current methods can lack transparency and efficiency.

[0184] 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.

[0185] In this invention, the server includes: a means for a user to take a photo of a risky location in infrastructure, enter a comment, and upload it; a means for the server to store the received photo and comment in a database and add it to an AI analysis queue; a means for an AI model to analyze the photo and comment to identify the risk level and risk details and generate safety measure proposals; a means for analyzing risk information collected from the camera and LiDAR of the autonomous vehicle in real time; a means for notifying passengers and the operation control system of the analysis results and presenting safety measure proposals; and a means for the server to notify the user of the generated safety measure proposals and start crowdfunding if necessary. This enables autonomous vehicles to detect road risks in real time and quickly take safety measures, enabling highly transparent fundraising through crowdfunding.

[0186] "User" refers to a general user who uses the system to photograph and upload infrastructure risk information.

[0187] "Infrastructure" refers to buildings and structures that provide public conveniences, such as roads, parks, and public facilities.

[0188] "Risk areas" are areas of infrastructure that could pose safety problems, such as cracks, sinkholes, or fallen trees.

[0189] "Photography" refers to the act of recording images or videos of risk areas using a smartphone or camera.

[0190] Entering a "comment" is the act of describing the details and circumstances of the risk area in text format.

[0191] "Uploading" is the act of sending photos, videos, and comments you have taken to a server via the Internet.

[0192] A "server" is a computer system for receiving, storing, analyzing, and distributing data.

[0193] "Database" means an information management system for efficiently storing and managing received photos and comments.

[0194] An "AI analysis queue" is a list of data waiting to be analyzed by an AI model.

[0195] The "AI model" is artificial intelligence software that identifies risk levels and risk details based on photos and comments.

[0196] The "risk level" is an index that indicates the degree of danger of a discovered risk location.

[0197] "Risk details" are descriptions of specific problems or dangers that the risk area may cause.

[0198] "Safety measures proposal" is information that proposes specific action plans and measures to be taken in response to identified risks.

[0199] An "autonomous vehicle camera" is a video recording device installed in an autonomous vehicle to capture road conditions in real time.

[0200] "LiDAR" is a sensor that uses laser light to measure the position and distance of an object with high precision.

[0201] "Real-time" means that the processing from data acquisition to analysis and notification is carried out immediately.

[0202] "Passenger" means a user aboard an automated driving vehicle.

[0203] A "traffic management system" is a system for monitoring and controlling the operation status of autonomous vehicles.

[0204] "Notifying" refers to the act of informing users and operation managers of the analysis results and proposed safety measures.

[0205] "Crowdfunding" is a method of raising funds from multiple internet users.

[0206] The present invention is a system for quickly and accurately identifying risk information for infrastructure and taking safety measures. This system involves a process in which a user reports risk locations, an AI model is used to analyze the risks, and safety measures are generated. Specifically, the system is implemented as follows.

[0207] User-generated and uploaded risk information

[0208] When a user discovers a risky area in infrastructure, they take a photo of the area with their smartphone or camera. They then enter details of the risky area as a comment in text format. For example, if a user discovers a large crack in the road, they can take a photo of the crack, enter a comment such as "There is a large crack. It looks like it could cause a traffic accident," and upload it. Any commonly available smartphone or camera will do.

[0209] Data reception and storage by the server

[0210] The server receives photos and comments sent by users and stores them in a database. The database is an information management system for efficiently managing information such as photos and comments, and allows for quick storage and retrieval of data that will later be added to the AI ​​analysis queue. The software used is a relational database management system such as MySQL.

[0211] Data analysis using AI models

[0212] The server adds the information stored in the database to an AI analysis queue, which then analyzes it using an AI model. The AI ​​model is built using machine learning libraries such as TensorFlow. The AI ​​model performs a risk analysis using the received photos and comments as input data. As a result of the analysis, the risk level (e.g., "high") and risk details (e.g., "possibility of a traffic accident due to cracks in the road") are identified.

[0213] Creation and notification of safety measures

[0214] The server generates safety measures based on the risk information identified by the AI ​​model. The safety measures include specific action plans and countermeasures. For example, it may suggest that road repairs are necessary. The generated safety measures are then notified to all users by the server.

[0215] Crowdfunding

[0216] If necessary, the server will initiate crowdfunding, set up a crowdfunding link, and notify all users. The crowdfunding page will contain detailed information about risks and countermeasures, and funders can make donations through the page.

[0217] Sharing the status of corrections

[0218] The server manages the repair status of risk areas reported by users and shares it with all users. This allows users to check the progress of repairs in real time. For example, when repairs to cracks in a road are completed, that information is notified to all users.

[0219] Risk Management for Autonomous Vehicles

[0220] Real-time data from cameras and LiDAR on autonomous vehicles is sent to a server, where risk information is analyzed using an AI model. This analysis information is then sent to passengers and the operation management system, and safety measures such as changing the driving route are implemented.

[0221] Specific examples

[0222] 1. User action: A user discovers a fallen tree in a nearby park, takes a photo of it, writes a comment saying "There is a fallen tree in the park. It may cause injury," and uploads the photo.

[0223] 2. Server processing: The server receives the photos and comments, stores them in a database, and then adds them to the AI ​​analysis queue.

[0224] 3. AI model analysis: The AI ​​model analyzes the photos and comments to identify risk details such as "Risk level: High" and "Fallen trees in the park pose a risk of injury."

[0225] 4. Generation of safety measures: The server generates safety measures such as "removal of fallen trees is required" and notifies all users.

[0226] 5. Crowdfunding: If necessary, the server will start the crowdfunding and send the link to all users.

[0227] 6. Sharing of correction status: When the fallen tree removal work is completed, the information is shared with all users.

[0228] Example prompts for generative AI models:

[0229] "There is a large crack in the center of the road. It is about 10 cm wide. Please analyze the possibility of this causing a traffic accident."

[0230] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0231] Step 1:

[0232] Input: Users take photos of risky areas in infrastructure using a smartphone or camera, enter details of the risk as comments, and upload the photos and comments they have entered.

[0233] How it works: When a user discovers a risky area in infrastructure, they use their camera to take a photo of the risky area, then enter details of the risk (such as the risk of a crack in the photo) as a text comment, and then press a button to upload the photo and comment using a dedicated application.

[0234] Output: The captured photo and the entered comment data are sent to the server.

[0235] Step 2:

[0236] Input: The server receives the photo and comment submitted by the user.

[0237] Operation: The server receives photos and comment data sent by users through a receiving port. Specifically, the server obtains the data using HTTP requests.

[0238] Output: The received photo and comment data is temporarily stored in local storage and then stored in a database.

[0239] Step 3:

[0240] Input: Retrieve stored photo and comment data from the database.

[0241] How it works: The server uses a database management system to retrieve the stored photo and comment data from the database, using MySQL queries to retrieve the necessary data.

[0242] Output: The retrieved photo and comment data is added to the AI ​​analysis queue to await analysis.

[0243] Step 4:

[0244] Input: Data added to the AI ​​analysis queue awaiting analysis.

[0245] How it works: The server sequentially retrieves data from the AI ​​analysis queue and inputs it into the AI ​​model. The AI ​​model uses neural networks built with TensorFlow and other tools to perform image recognition and text analysis. It identifies risks based on photos and comments, and determines the risk level and risk details.

[0246] Output: The AI ​​model outputs the risk level (e.g., "High") and risk details (e.g., "Possibility of traffic accident due to cracks in the road") as the analysis result.

[0247] Step 5:

[0248] Input: Analysis results from the AI ​​model (risk level and risk details).

[0249] Operation: The server generates safety measures based on the analysis results of the AI ​​model. Specifically, if the risk level is "high," it generates a message suggesting appropriate measures (e.g., "prompt road repairs").

[0250] Output: The generated safety measures are prepared as text data.

[0251] Step 6:

[0252] Input: Generated safety plan.

[0253] Operation: The server notifies all users of this proposed security measure. This can be done via a notification function within the application or by email. A notification is displayed on the client device.

[0254] Output: A notification message that is displayed on the user's terminal.

[0255] Step 7:

[0256] Input: Risk information analyzed by the AI ​​model and generated safety measures.

[0257] Behavior: If necessary, the server will initiate crowdfunding. A crowdfunding page link and information will be generated and posted to all users.

[0258] Output: Crowdfunding page link and notification message.

[0259] Step 8:

[0260] Input: Correction status data.

[0261] How it works: The server manages the repair status of risk areas and shares the progress with all users. When the repair is complete, it notifies all users.

[0262] Output: A message to the user indicating that the fix is ​​complete.

[0263] Examples:

[0264] A user discovers a crack in the road, takes a photo, and enters a comment. The server receives the photo and comment, analyzes it using an AI model, and determines "Risk level: High, Risk details: Possibility of traffic accident due to road crack." It then notifies the user that "Road repair work is required" as a safety measure.

[0265] Example prompts for generative AI models:

[0266] "There is a large crack in the center of the road. It is about 10 cm wide. Please analyze the possibility of this causing a traffic accident."

[0267] 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.

[0268] The present invention is a system that generates safety measures by collecting risk information about infrastructure that users use on a daily basis and analyzing it using AI combined with an emotion engine. This system speeds up responses to risk areas in the infrastructure and adjusts the level of urgency taking into account the user's emotions. Below, an embodiment of the present invention will be described in natural language.

[0269] User-generated and uploaded risk information

[0270] When a user discovers a risky area in infrastructure, they take a photo of the area using a device such as a smartphone or PC. Next, the user launches a dedicated application, enters the photo along with a comment explaining the details of the risk, and sends this data to a server. For example, if a user discovers a fallen tree in a park, they can take a photo of the tree on the spot and enter a comment such as, "There is a fallen tree. It is very dangerous." and send it.

[0271] Data reception and storage by the server

[0272] The server receives the photos and comments sent by users. The received data is stored in a database by the server. The database is an information management system for managing information such as photos and comments, and allows efficient storage and retrieval of data for later analysis.

[0273] Emotion recognition by emotion engine

[0274] The server inputs the comments received from the user into the emotion engine and analyzes the user's emotion. The emotion engine reads the emotion from the user's comment and identifies the emotional state (e.g., "very dangerous"). The emotional state is used to adjust the urgency of the risk level.

[0275] Data analysis using AI models

[0276] The server adds the photos, comments, and emotion data from the emotion engine stored in the database to the AI ​​analysis queue, which then analyzes them using the AI ​​model. The AI ​​model determines the risk level and risk details based on the input data. For example, it generates analysis results such as "Risk level: Very high" and "Fallen trees in the park may pose a serious danger."

[0277] Generate safety measures

[0278] The server generates safety measures based on the risk information identified by the AI ​​model. The safety measures include specific action plans and countermeasure methods, such as "carry out emergency tree removal work." Furthermore, the server takes into account the user's emotional data to adjust the urgency and optimize the measures.

[0279] User notification and crowdfunding

[0280] The server notifies all users of the generated safety measures. Users can check the measures through the application. If necessary, the server also launches a crowdfunding campaign, sets up a link to collect funds from users and related parties, and notifies all users. The crowdfunding page contains risk information and details of the measures, and funders can make donations through the page.

[0281] Sharing the status of corrections

[0282] The server manages the repair status of risk areas reported by users and shares the progress with all users. This allows users to check the progress of repairs in real time and understand how the risk areas they reported are being addressed. For example, when the removal of fallen trees is completed, that information is notified to all users.

[0283] Specific examples

[0284] Specific examples are shown below.

[0285] 1. User action: A user notices a broken window at a nearby school, takes a photo of it, and writes the comment "The window at my school is broken and it's very dangerous."

[0286] 2. Server processing: The server receives the photo and comments, stores them in a database, and then inputs the comments into an emotion engine to analyze the emotion. For example, an emotional state of "very dangerous" is identified.

[0287] 3. AI model analysis: The AI ​​model analyzes the photo and emotion data to identify risk details such as "Risk level: Very high" and "High probability of injury from broken window glass."

[0288] 4. Generation of safety measures: Based on the analysis results, the server generates safety measures such as "carry out emergency window glass replacement work" and notifies all users.

[0289] 5. Crowdfunding: If necessary, the server will start the crowdfunding and send the link to all users.

[0290] 6. Sharing of repair status: When the window glass replacement work is completed, the information is shared with all users.

[0291] The present invention makes it possible to quickly implement infrastructure safety measures that take into account user feelings, and by taking appropriate measures, risks can be managed efficiently and effectively.

[0292] The processing flow will be explained below.

[0293] Step 1:

[0294] When a user discovers a risky area in the infrastructure, they can take a photo of the area using a device such as a smartphone or computer.

[0295] Step 2:

[0296] The user launches a dedicated application and takes a photo and enters a comment detailing the risk. For example, "There is a fallen tree in the park. It is very dangerous."

[0297] Step 3:

[0298] The user sends the completed photo and comment to the server via the application.

[0299] Step 4:

[0300] The server stores the received photos and comments in a database and passes the comments to an emotion engine to analyze the user's emotions.

[0301] Step 5:

[0302] The server receives the emotion data returned by the emotion engine and adds it to the AI ​​analysis queue along with the original data.

[0303] Step 6:

[0304] The server sequentially passes data added to the AI ​​analysis queue to the AI ​​model, which analyzes the risk level and risk details, such as "Risk level: Very high" or "High possibility of injury due to falling trees."

[0305] Step 7:

[0306] The server generates safety measures based on the risk information analyzed by the AI ​​model, such as "implementing emergency tree removal work."

[0307] Step 8:

[0308] The server adjusts the urgency level based on the emotion data and notifies all users of the optimized safety measures, which they can then check through the application.

[0309] Step 9:

[0310] If necessary, the server will set up a crowdfunding campaign and provide a link to all users, which will contain detailed risk information and suggested solutions.

[0311] Step 10:

[0312] Users can access the crowdfunding page and provide funds, which are then used to repair and improve the infrastructure.

[0313] Step 11:

[0314] The server manages the status of risky areas and shares the progress of the repairs with all users. When the repairs are complete, the information is also notified.

[0315] Specific examples

[0316] 1. User action: The user notices a broken window at the school, takes a photo of it, and writes the comment "The window at the school is broken and it is very dangerous."

[0317] 2. Server processing: The server receives the photo and comments, stores them in a database, and then inputs the comments into an emotion engine to analyze the emotion. For example, an emotional state of "very dangerous" is identified.

[0318] 3. Adding emotion data: The server adds the emotion data returned from the emotion engine to the AI ​​analysis queue along with the original data.

[0319] 4. AI model analysis: The AI ​​model analyzes the photo and emotion data to identify risk details such as "Risk level: Very high" and "High probability of injury from broken window glass."

[0320] 5. Generation of safety measures: Based on the analysis results, the server generates safety measures such as "carry out emergency window glass replacement work" and notifies all users.

[0321] 6. Crowdfunding: If necessary, the server will start the crowdfunding and send the link to all users.

[0322] 7. Sharing of repair status: When the window glass replacement work is completed, the information is shared with all users.

[0323] Example 2

[0324] 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."

[0325] Conventional infrastructure risk management systems typically assess risk levels and determine safety measures based solely on user reports. However, these systems do not adequately consider user sentiment or the level of urgency, which can delay emergency measures. Furthermore, limited means of effective crowdfunding make it difficult to raise funds quickly.

[0326] 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.

[0327] In this invention, the server includes a means for uploading photos and comments taken by users of risky areas of infrastructure, a means for storing the photos and comments received by the server in a database and performing sentiment analysis of the comments using an emotion engine, a means for an AI model to analyze the photos, comments, and emotion data to identify the risk level and risk details and generate safety measure proposals, and a means for the server to notify all users of the generated safety measure proposals and start crowdfunding as necessary. This enables rapid risk assessment and generation of countermeasure proposals that take user sentiment into consideration, as well as more effective fundraising through crowdfunding.

[0328] "User" refers to a person who discovers risk areas in the infrastructure and reports that information to the system.

[0329] "Infrastructure" refers to facilities and structures that provide public convenience and safety, and specifically includes roads, bridges, parks, schools, etc.

[0330] "Risk points" refer to parts or conditions in infrastructure that have the potential to cause accidents or damage.

[0331] "Photo" refers to an image that a user visually records of a risk location.

[0332] "Comment" refers to an explanatory text entered by the user about the details and circumstances of the risk area.

[0333] "Upload" refers to the act of a user sending photos and comments from their own device to a server.

[0334] "Server" refers to a computer system that processes and stores data received from users.

[0335] "Database" refers to an information management system that efficiently stores and manages photos and comments received by the server.

[0336] "Emotion engine" refers to software that analyzes and identifies the emotional state of a user's comments.

[0337] "Sentiment analysis" refers to the process of using an emotion engine to read emotions from user comments.

[0338] "AI model" refers to an artificial intelligence algorithm that analyzes photos, comments, and sentiment data to identify risk levels and risk details.

[0339] "Risk level" refers to the severity of the risk identified by the AI ​​model.

[0340] "Risk details" refers to specific information about the risks identified by the AI ​​model.

[0341] "Safety measures plan" refers to a specific action plan for reducing risk that is generated by the server based on risk information.

[0342] "Notification" refers to a means of communicating information to all users about the safety measures that have been created.

[0343] "Crowdfunding" refers to the act of soliciting donations from users and related parties in order to raise the funds necessary to implement proposed safety measures.

[0344] "Link" refers to the URL for accessing the crowdfunding page.

[0345] "Remediation status" refers to the progress of remediation work on reported risk areas.

[0346] The present invention is a system that collects risk information about infrastructure that users use on a daily basis and combines an emotion engine and an AI model. This system is designed to achieve rapid risk response and adjust the urgency level taking into account the user's emotions. An embodiment of this system is described in detail below.

[0347] User-generated and uploaded risk information

[0348] When a user discovers a risky area, they take a photo of the area using a device such as a smartphone or PC. Next, the user launches a dedicated application (e.g., "Risk Report App") and enters a comment explaining the details of the risk along with the photo. The data is then sent to the server.

[0349] For example, if a user discovers a fallen tree in a park, they can take a photo of the tree on the spot and send it with a comment such as, "There's a fallen tree. It's very dangerous."

[0350] Data reception and storage by the server

[0351] The server receives the photos and comments sent by users. The received data is stored in a "risk management database." The database efficiently manages information such as photos and comments and stores the data for later analysis.

[0352] Emotion recognition by emotion engine

[0353] The server inputs the comments received from the user into an emotion engine (e.g., "Emotion AI") to analyze the user's emotions. The emotion engine identifies the user's emotional state (e.g., "very dangerous") from the user's comments. The emotional state is used to adjust the urgency of the risk level.

[0354] Data analysis using AI models

[0355] The server adds the photos, comments, and emotion data stored in the database to an AI analysis queue, which then analyzes them using an AI model (e.g., the "Risk Assessment AI Model"). The AI ​​model identifies the risk level and risk details based on the input data. For example, it generates analysis results such as "Risk level: Very high" and "Fallen trees in the park may pose a serious danger."

[0356] Generate safety measures

[0357] The server generates safety measures based on the risk information identified by the AI ​​model. The safety measures include specific action plans and methods, such as "carry out emergency tree removal work." Furthermore, the server takes into account the user's emotional data to adjust the urgency and optimize the measures.

[0358] User notification and crowdfunding

[0359] The server notifies all users of the generated safety measures. Users can check the measures through the application. If necessary, the server also notifies all users of a link to start crowdfunding and collect funds from users and related parties. The crowdfunding page contains risk information and details of the measures, and funders can make donations through the page.

[0360] Sharing the status of corrections

[0361] The server manages the repair status of risk areas reported by users and shares the progress with all users. This allows users to check the progress of repairs in real time and understand how the risk areas they reported are being addressed. For example, when the removal of fallen trees is completed, that information is notified to all users.

[0362] Specific examples

[0363] Specific examples are shown below.

[0364] 1. User action: A user notices a broken window at a nearby school, takes a photo of it, and writes the comment "The window at my school is broken and it's very dangerous."

[0365] 2. Server processing: The server receives the photo and comments, stores them in a database, and then inputs the comments into an emotion engine to analyze the emotion. For example, an emotional state of "very dangerous" is identified.

[0366] 3. AI model analysis: The AI ​​model analyzes the photo and emotion data to identify risk details such as "Risk level: Very high" and "High probability of injury from broken window glass."

[0367] 4. Generation of safety measures: Based on the analysis results, the server generates safety measures such as "carry out emergency window glass replacement work" and notifies all users.

[0368] 5. Crowdfunding: If necessary, the server will start the crowdfunding and send the link to all users.

[0369] 6. Sharing of repair status: When the window glass replacement work is completed, the information is shared with all users.

[0370] The above is an embodiment of the present invention. This system enables infrastructure safety measures to be implemented quickly while taking into account user emotions, and risk management can be performed efficiently and effectively by taking appropriate measures.

[0371] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0372] Step 1:

[0373] User-generated and uploaded risk information

[0374] How it works: The user takes a photo of a risky area in the infrastructure (e.g., a fallen tree, a broken window) using a smartphone or computer.

[0375] Input: Photo and risk comment.

[0376] Data processing: The user launches a dedicated application and inputs the photograph they took and a comment detailing the risk (e.g., "There is a fallen tree. It is very dangerous."). The application then packages this data.

[0377] Output: Packaged photo and comment data.

[0378] Step 2:

[0379] Data reception and storage by the server

[0380] Operation: The server receives packaged data sent by the user.

[0381] Input: User uploaded photo and comment data.

[0382] Data processing: The server stores the received data in the "risk management database."

[0383] Output: Photo and comment data stored in a database.

[0384] Step 3:

[0385] Emotion analysis of comments using an emotion engine

[0386] How it works: The server inputs the saved comments into the emotion engine for analysis.

[0387] Input: Comments stored in the database.

[0388] Data processing: An emotion engine (e.g., "Emotion AI") analyzes and identifies the user's emotional state (e.g., "very dangerous") from the comments.

[0389] Output: Identified emotional state data.

[0390] Step 4:

[0391] Analyzing risk data with AI models

[0392] How it works: The server adds the photo, comment, and emotion data to the AI ​​analysis queue and analyzes it using the AI ​​model.

[0393] Input: photos, comments, and emotion data.

[0394] Data processing: An AI model (e.g., a "risk assessment AI model") uses this data to identify risk levels and risk details, generating analysis results such as "Risk level: Very high" and "Falling trees in the park could pose a serious risk."

[0395] Output: Risk level and risk details data.

[0396] Step 5:

[0397] Server-generated safety measures

[0398] How it works: The server generates safety measures based on the risk information identified by the AI ​​model.

[0399] Input: Risk level and risk details data.

[0400] Data processing: The server generates safety measures (e.g., "Implement emergency tree removal work") and adjusts the urgency of the measures based on the user's emotional data.

[0401] Output: Generated safety measures.

[0402] Step 6:

[0403] Notification of proposed security measures by the server and start of crowdfunding

[0404] Action: The server notifies all users of the generated security plan.

[0405] Input: Generated safety plan.

[0406] Data processing: Generate a notification message and push it to all users via the application. If necessary, the server will start the crowdfunding campaign and notify all users of the link.

[0407] Output: Notification message and crowdfunding link.

[0408] Step 7:

[0409] Server sharing of revision status

[0410] How it works: The server manages the progress of fixing risk areas reported by users and shares the progress with all users.

[0411] Input: Risk location correction status data.

[0412] Data processing: Updates the management database of the correction status and generates messages that visualize the correction status.

[0413] Output: A message informing you of the fix status.

[0414] (Application example 2)

[0415] 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."

[0416] Currently, many factories place importance on safety management, but the speed from risk detection to response is often slow. Furthermore, on-site workers often find it difficult to accurately judge the seriousness of risks, as the method for reporting risk information is complicated. Furthermore, risk management does not take into account the emotions of workers, and the inability to take appropriate measures increases the risk of accidents and malfunctions. The purpose of this invention is to solve these problems and ensure efficient and rapid safety management within factories.

[0417] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a means for a user to take a photo of a risky location in the infrastructure, enter a comment, and upload it; a means for the server to store the received photo and comment in a database and add it to an AI analysis queue; a means for analyzing the emotion of the comment using an emotion engine; a means for an AI model to analyze the photo and emotion data to identify the risk level and risk details and generate a safety measure plan; a means for the server to notify the user of the generated safety measure plan and start crowdfunding as necessary; and a means for sharing the progress of the safety measure plan with all users. This makes it possible to quickly and accurately analyze risk information within a factory and implement safety measures that take emotions into consideration.

[0418] A "user" is an individual or organization that provides information by discovering risk areas in the infrastructure, taking photos, and adding comments.

[0419] "Server" means a central processing unit for storing and analyzing data received from users, and generating and notifying security measures.

[0420] "Photographs" are image data that visually record risk areas in infrastructure.

[0421] "Comment" is text information that allows the user to add an explanation about the risky part.

[0422] The "database" is a system that efficiently stores information such as received photos and comments, and allows for searching and analysis.

[0423] The "AI analysis queue" is a collection of received data that is waiting to be analyzed by AI in sequence.

[0424] An "emotion engine" is software or a system for identifying emotions from user comments and analyzing their emotional state.

[0425] The "AI model" is an analytical model that uses machine learning or deep learning to identify risk levels and risk details based on received photo and emotion data.

[0426] The "risk level" is an index that indicates the urgency and severity of the risk to the analyzed infrastructure.

[0427] "Risk details" is information that indicates the specific content and scope of impact of the identified risk.

[0428] "Safety measures" are specific countermeasures and action plans to be taken in response to identified risks.

[0429] "Crowdfunding" is a system that widely solicits donors via the Internet in order to raise the funds needed to address risks.

[0430] "Progress" is information that indicates how much progress has been made in correcting risk areas and taking countermeasures.

[0431] This invention is a system for efficient and rapid safety management within factories. This system allows users to take photos of risky areas in infrastructure and send their comments to a server, which then analyzes the data, generates safety measures, and notifies the user. It also includes a function to set up a crowdfunding link as needed and share the progress of correcting risky areas.

[0432] Hardware and software used

[0433] Hardware: Smartphones, smart glasses, PCs, servers

[0434] Software: Google Speech-to-Text API, Hugging Face Transformers (sentiment analysis), TensorFlow or PyTorch (AI model analysis), cloud database system

[0435] Data collection and transmission

[0436] A user (factory worker) uses a smartphone or smart glasses to take a photo of a risky area. For example, if a user discovers a wall that is about to collapse in the factory, they take a photo of it. The user then adds a comment about the risky area by voice or text input. For example, "The wall at the work site is about to collapse. It is very dangerous." Once the photo and comment are prepared, the user sends the data to the server through a dedicated application.

[0437] Data storage and analysis

[0438] The server receives photos and comments sent by users and stores them in a cloud database. It then inputs the comments into an emotion engine (Hugging Face Transformers) to analyze the emotion. For example, it identifies an emotional state such as "very dangerous." After the emotion is identified, the server adds all data, including the emotion data, to an AI analysis queue and analyzes it using an AI model (TensorFlow or PyTorch). The AI ​​model identifies the risk level and risk details based on the photo and emotion data.

[0439] Creation and notification of safety measures

[0440] The server generates specific safety measures based on the results of the AI ​​analysis. For example, it might suggest "dispatch an emergency response team and immediately begin repair work." Based on this, it notifies users and, if necessary, sets up a crowdfunding link and notifies all users. Through this link, donors can provide the funds needed for the countermeasures.

[0441] Share your progress

[0442] The server also has a function to share the progress of risk-point repairs with all users, allowing users to check the progress of countermeasures in real time. For example, when repair work is completed, the information can be notified to all users, allowing them to always be aware of the latest status.

[0443] Example prompt

[0444] Please analyze the risk information for the infrastructure that has been commented as "very dangerous" and provide the risk level and details.

[0445] This invention makes it possible to quickly and accurately analyze risk information within a factory and implement safety measures that take emotions into account, which is expected to ensure the safety of factory workers and improve operational efficiency.

[0446] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0447] Step 1:

[0448] The user takes a photo of a risky area of ​​infrastructure using a smartphone or smart glasses. The user adds a comment about the risk along with the photo by voice input or text input. For example, "This wall is about to collapse and is very dangerous." The input is photo data and comment data, and the output is a set of these data. Specifically, the system works by taking a photo using the device camera and adding a comment using the voice input function.

[0449] Step 2:

[0450] The user launches the dedicated application and sends the photos and comments they have taken to the server. The input is a set of photo data and comment data, and the output is the data sent to the server. Specifically, the user clicks the send button in the application to upload the data to the server via the Internet.

[0451] Step 3:

[0452] The server stores the received photos and comments in a cloud database. The input is the photo data and comment data sent to the server, and the output is the data stored in the cloud database. The specific operation is to use the server's storage system to store the data.

[0453] Step 4:

[0454] The server inputs the saved comment data into an emotion engine (Hugging Face Transformers) to analyze emotions. The input is comment data, and the output is data indicating the emotional state (e.g., "very dangerous"). Specifically, the emotion engine is called and the comment is analyzed using natural language processing techniques.

[0455] Step 5:

[0456] The server adds all data, including emotional state data, to an AI analysis queue and analyzes it using an AI model (TensorFlow or PyTorch). The input is photo data and emotional state data, and the output is data indicating risk level and risk details. Specifically, the AI ​​model is executed and the data is analyzed using a deep learning algorithm.

[0457] Step 6:

[0458] The server generates safety measures based on the results of the AI ​​analysis. The input is risk level data and detailed risk data, and the output is specific safety measures (e.g., "Dispatch an emergency response team and immediately begin repair work"). Specific operations involve generating appropriate measures using a predefined algorithm.

[0459] Step 7:

[0460] The server notifies the user of the generated security measure plan and sets a crowdfunding link if necessary. This link is notified to all users. The input is the security measure plan data and the crowdfunding link data, and the output is the notification data sent to the user. Specifically, the server's notification system is used to send the security measure plan and link to the user.

[0461] Step 8:

[0462] The server shares the progress of risky part repairs with all users in real time. The input is repair progress data, and the output is progress notification data for all users. Specifically, the server retrieves the progress from the database and shares it with users using the notification system.

[0463] 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.

[0464] 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.

[0465] 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.

[0466] [Second embodiment]

[0467] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0468] 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.

[0469] 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).

[0470] 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.

[0471] 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.

[0472] 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).

[0473] 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.

[0474] 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.

[0475] 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.

[0476] 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.

[0477] 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.

[0478] 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."

[0479] The present invention is a system that generates safety measures by collecting risk information related to infrastructure that users use on a daily basis and analyzing it using AI. Below, an embodiment of the present invention will be described in natural language.

[0480] User-generated and uploaded risk information

[0481] When a user discovers a risky area in infrastructure, they take a photo of the area and upload it to the application using a device such as a smartphone or computer. The user also enters a brief comment for the photo, explaining the details of the risk. For example, if a user discovers a large crack in the road, they can take a photo of the crack and enter a comment such as, "There is a large crack. It looks like it could cause a traffic accident," and submit it to the app.

[0482] Data reception and storage by the server

[0483] The server receives the photos and comments sent by users. The received data is stored in a database by the server. The database is an information management system for managing information such as photos and comments, and can efficiently store and search data for later analysis.

[0484] Data analysis using AI models

[0485] The server adds the information stored in the database to an AI analysis queue, which then analyzes it using the AI ​​model. The AI ​​model uses the received photos and comments as input data to perform a risk analysis. As a result of the analysis, the risk level (e.g., "high") and risk details (e.g., "possibility of a traffic accident due to cracks in the road") are identified.

[0486] Generate safety measures

[0487] The server generates safety measures based on the risk information identified by the AI ​​model. These safety measures include specific action plans and countermeasures, such as suggesting that road repairs are necessary.

[0488] User notification and crowdfunding

[0489] The server notifies all users of the safety measures it has created. Users can check the measures through the application. If necessary, the server will also launch a crowdfunding campaign, set up a link to collect funds from users and other interested parties, and notify all users. The crowdfunding page will contain detailed information about the risks and the measures, and funders can make donations through the page.

[0490] Sharing the status of corrections

[0491] The server manages the repair status of risk areas reported by users and shares it with all users. This allows users to check the progress of repairs in real time and understand how the risk areas they reported are being addressed. For example, when repairs to cracks in a road are completed, that information is notified to all users.

[0492] Specific examples

[0493] Specific examples are shown below.

[0494] 1. User action: A user finds a fallen tree in a nearby park, takes a photo of it, and writes a comment saying, "There is a fallen tree in the park. It may cause injury."

[0495] 2. Server processing: The server receives the photos and comments, stores them in a database, and then adds them to the AI ​​analysis queue.

[0496] 3. AI model analysis: The AI ​​model analyzes the photos and comments to identify risk details such as "Risk level: High" and "Fallen trees in the park pose a risk of injury."

[0497] 4. Generation of safety measures: The server generates safety measures such as "removal of fallen trees is required" and notifies all users.

[0498] 5. Crowdfunding: If necessary, the server will start the crowdfunding and send the link to all users.

[0499] 6. Sharing of correction status: When the fallen tree removal work is completed, the information is shared with all users.

[0500] The present invention makes it possible to quickly identify safety risks in infrastructure and take appropriate measures. Furthermore, funds can be raised through crowdfunding with the cooperation of users, and measures can be implemented with high transparency.

[0501] The processing flow will be explained below.

[0502] Step 1:

[0503] When a user discovers a risky area in the infrastructure, they can take a photo of the area using a device such as a smartphone or computer.

[0504] Step 2:

[0505] The user launches a dedicated application and takes a photo and enters a comment along with it. For example, "There's a big crack. It could cause a traffic accident."

[0506] Step 3:

[0507] The device sends the entered photo and comment to the server.

[0508] Step 4:

[0509] The server temporarily stores the received photos and comments in a database.

[0510] Step 5:

[0511] The data stored by the server is added to the AI ​​analysis queue and prepared for analysis.

[0512] Step 6:

[0513] The server passes the photo and comment data from the queue to the AI ​​model and begins analysis.

[0514] Step 7:

[0515] The AI ​​model analyzes the photos and comments to identify risk levels, such as "Risk level: High" and "Risk details: Possibility of traffic accident due to cracks in the road."

[0516] Step 8:

[0517] The server generates safety measures based on the analysis results of the AI ​​model, such as "Road repair work is required."

[0518] Step 9:

[0519] The server notifies all users of the generated safety measures and analysis results.

[0520] Step 10:

[0521] If necessary, the server will set up a crowdfunding campaign and send a link to all users, which will include details of the risks and countermeasures.

[0522] Step 11:

[0523] Users can access the crowdfunding page and provide funds, which are then used to repair and improve infrastructure.

[0524] Step 12:

[0525] The server manages the status of risk fixes and shares the progress with all users. When fixes are complete, the server also notifies users of this information.

[0526] Example 1

[0527] 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."

[0528] Currently, risk management for everyday infrastructure is time-consuming and often results in inappropriate responses. There are also issues with efficient sharing of risk information and methods of fundraising. The present invention aims to solve these problems and provide a system that quickly and effectively identifies infrastructure risks and takes appropriate measures.

[0529] 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.

[0530] In this invention, the server includes means for users to take photos of risky areas in infrastructure they use daily, enter comments, and upload them from their terminals, means for the server to store the photos and comments received in a database and add them to an AI analysis queue, means for preprocessing the generated data and for an AI model to analyze the photos and comments to identify the risk level and details, means for automatically generating safety measure proposals based on the identified risk information, means for the server to notify all users of the generated safety measure proposals and start crowdfunding as necessary, and means for managing and notifying the status of repairs to risky areas. This enables quick and effective identification of infrastructure safety risks and enables highly transparent countermeasures and fundraising.

[0531] "User" refers to anyone who uses the system to report infrastructure risks and upload photos and comments.

[0532] "Infrastructure" refers to structures and systems that support the foundations of society, including roads, parks, bridges, etc.

[0533] "Risk points" refer to locations within infrastructure where potential dangers may exist.

[0534] "Photographing" refers to the operation of using a device to leave a visual record.

[0535] "Comment" refers to text information that a user adds to a photograph they have taken.

[0536] "Terminal" refers to the device that a user uses to access the system, such as a smartphone or PC.

[0537] "Upload" refers to the operation of sending data from a terminal to a server.

[0538] "Server" refers to a computer system for managing and processing data received from users.

[0539] A "database" refers to a system for managing and storing information, allowing photos and comments to be efficiently stored and searched.

[0540] "AI analysis queue" refers to a waiting line structure for sequentially analyzing data.

[0541] "Preprocessing" refers to the operations used to convert data into a format suitable for analysis by an AI model.

[0542] "AI model" refers to software that uses machine learning technology to analyze data and identify risk levels and risk details.

[0543] "Risk Level" refers to a classification that indicates the severity of an identified risk.

[0544] "Risk details" refers to information that explains the specific details of an identified risk.

[0545] "Safety measures" refers to specific action plans and countermeasures to be taken in response to identified risks.

[0546] "Crowdfunding" refers to a method of widely raising funds via the Internet to address infrastructure risks.

[0547] "Link" refers to the URL that allows users to access the crowdfunding page.

[0548] "Notification" refers to the operation of the server sending information to the user and informing them.

[0549] "Remediation status" refers to the progress of the actions and corrections taken against the reported risk areas.

[0550] "Management" refers to monitoring the operational status of the entire system and performing necessary operations.

[0551] The present invention is a system that generates safety measures by collecting risk information related to infrastructure that users use on a daily basis and analyzing it using AI. Below, an embodiment of the present invention will be described in natural language.

[0552] Hardware and Software Configuration

[0553] This system includes the devices used by users (smartphones, PCs, etc.) and servers. The backend system uses a database (e.g., MySQL, PostgreSQL) for data management and a machine learning model (e.g., TensorFlow, PyTorch) for AI analysis.

[0554] User-generated and uploaded risk information

[0555] When a user discovers a risky area in the infrastructure, they take a photo of the area using their smartphone or computer. After taking the photo, they launch a dedicated application, select the photo they took, and upload it to the application. The user then enters a comment for the photo, explaining the details of the risk. The photo and comment data are then sent to the server. For example, if a user discovers a large crack in the road, they might enter a comment such as, "There's a large crack. It looks like it could cause a traffic accident."

[0556] Data reception and storage by the server

[0557] The server receives the photos and comments sent by the user as HTTP requests. The server saves the received photo data in a temporary directory and obtains the file path. At the same time, it saves the comment text and the photo file path in the database. This data is later added to the AI ​​analysis queue.

[0558] Data analysis using AI models

[0559] The server detects when new data is added to the database and adds the data to the AI ​​analysis queue. Before the data is passed to the AI ​​model, the server performs the necessary preprocessing. Specifically, it preprocesses the photo data using an image processing library (e.g., OpenCV) and converts the comment text into a format suitable for the NLP model. The preprocessed data is then input into the AI ​​model to identify the risk level and risk details.

[0560] Creation and notification of safety measures

[0561] Based on the risk information identified by the AI ​​model, the server uses a rule-based engine to generate safety measures. The generated safety measures are stored in a database, and the server then notifies all users of the measures. If necessary, a crowdfunding link is also generated and notified to users.

[0562] Sharing the status of corrections

[0563] The server manages the status of risk corrections and updates it regularly. When the corrections are complete, the information is notified to all users, allowing them to check the status of the corrections in real time.

[0564] Specific examples

[0565] Specific examples are shown below.

[0566] User Action: A user finds a fallen tree in a local park, takes a photo of it, and writes a comment saying, "There is a fallen tree in the park. It could cause injury."

[0567] Server processing: The server receives the photos and comments, stores them in a database, and then adds them to the AI ​​analysis queue.

[0568] AI model analysis: The AI ​​model analyzes photos and comments to identify risk levels such as "high" and risk details such as "falling trees in the park pose a risk of injury."

[0569] Generation of safety measures: The server generates safety measures such as "removal of fallen trees is required" and notifies all users.

[0570] Crowdfunding: The server will start the crowdfunding campaign if necessary and send the link to all users.

[0571] Sharing of repair status: When the fallen tree removal work is completed, the information is shared with all users.

[0572] Example prompts to be input to the generative AI model:

[0573] "There is a fallen tree in the park that could cause injury. Please analyze this risk."

[0574] This will enable rapid and effective identification of infrastructure safety risks and enable appropriate countermeasures and funding.

[0575] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0576] Step 1:

[0577] The user takes a photo of the risky part of the infrastructure, enters a comment, and uploads it from the terminal (input: photo and comment of the risky part of the infrastructure. output: sending the photo and comment).

[0578] Specific behavior:

[0579] Users use a smartphone or computer to take photos of risky areas of infrastructure.

[0580] The user launches the application, selects a photo, and proceeds to the upload screen.

[0581] The user enters a comment and details the risk in the text fields.

[0582] The user clicks the "Send" button to send the photo and comments to the server.

[0583] Step 2:

[0584] The server saves the received photos and comments in a database and adds them to the AI ​​analysis queue (input: sent photo and comment data; output: saved in database and added to queue).

[0585] Specific behavior:

[0586] The server receives an HTTP request from the user, which includes the photo data and comment text.

[0587] The server stores the photo data in a temporary directory and obtains the file path.

[0588] The server saves the comment data and the photo file path as a new record in the database.

[0589] Detects when a new record is saved and adds the data to the AI ​​analysis queue.

[0590] Step 3:

[0591] The server preprocesses the data, and the AI ​​model analyzes the photos and comments to identify risk levels and risk details (input: photos and comments stored in the database; output: risk levels and risk details).

[0592] Specific behavior:

[0593] The server preprocesses the photos and comments stored in the database.

[0594] Use an image processing library (e.g. OpenCV) to convert the photo data into an appropriate format.

[0595] Tokenize text data into a format suitable for natural language processing (NLP) models.

[0596] The server inputs the preprocessed data into the AI ​​model for analysis.

[0597] The AI ​​model analyzes photos and comments to identify risk levels (e.g., "High") and risk details (e.g., "Possibility of traffic accident due to cracks in the road").

[0598] Step 4:

[0599] Based on the identified risk information, the server automatically generates safety measures (input: risk level and risk details; output: safety measures).

[0600] Specific behavior:

[0601] The server receives the risk level and risk details returned by the AI ​​model.

[0602] The server uses a rule-based engine to generate risk-informed safety measures.

[0603] For example, if the risk level is "high," it will suggest that "road repair work is needed."

[0604] The generated safety measures are stored in a database.

[0605] Step 5:

[0606] The server notifies all users of the generated safety measures and initiates crowdfunding if necessary (Input: Safety measures. Output: User notification and crowdfunding link).

[0607] Specific behavior:

[0608] The server prepares a communication method (push notification, email, etc.) to notify all users of the generated safety measures.

[0609] The server forms a notification message and sends it with the content "A new security plan has been generated."

[0610] If necessary, the server generates a link to the crowdfunding page and notifies the user.

[0611] Step 6:

[0612] The server manages and notifies the status of risk corrections (input: correction status information; output: correction completion notification).

[0613] Specific behavior:

[0614] The server periodically checks and updates the status of corrections to risk areas.

[0615] Once the correction is complete, the information is recorded in the database.

[0616] The server sends a completion notification of the modification status to all users.

[0617] Users will receive notifications and can see the corrected infrastructure state on their applications.

[0618] (Application example 1)

[0619] 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."

[0620] There is a need to quickly and accurately identify infrastructure risk information and implement safety measures. Road risk information is particularly essential for autonomous vehicles, and risks must be identified in real time and notified to passengers and operation management systems. However, conventional systems can delay risk identification and notification, threatening safety. Furthermore, smooth funding for risk countermeasures is also necessary, but current methods can lack transparency and efficiency.

[0621] 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.

[0622] In this invention, the server includes: a means for a user to take a photo of a risky location in infrastructure, enter a comment, and upload it; a means for the server to store the received photo and comment in a database and add it to an AI analysis queue; a means for an AI model to analyze the photo and comment to identify the risk level and risk details and generate safety measure proposals; a means for analyzing risk information collected from the camera and LiDAR of the autonomous vehicle in real time; a means for notifying passengers and the operation control system of the analysis results and presenting safety measure proposals; and a means for the server to notify the user of the generated safety measure proposals and start crowdfunding if necessary. This enables autonomous vehicles to detect road risks in real time and quickly take safety measures, enabling highly transparent fundraising through crowdfunding.

[0623] "User" refers to a general user who uses the system to photograph and upload infrastructure risk information.

[0624] "Infrastructure" refers to buildings and structures that provide public conveniences, such as roads, parks, and public facilities.

[0625] "Risk areas" are areas of infrastructure that could pose safety problems, such as cracks, sinkholes, or fallen trees.

[0626] "Photography" refers to the act of recording images or videos of risk areas using a smartphone or camera.

[0627] Entering a "comment" is the act of describing the details and circumstances of the risk area in text format.

[0628] "Uploading" is the act of sending photos, videos, and comments you have taken to a server via the Internet.

[0629] A "server" is a computer system for receiving, storing, analyzing, and distributing data.

[0630] "Database" means an information management system for efficiently storing and managing received photos and comments.

[0631] An "AI analysis queue" is a list of data waiting to be analyzed by an AI model.

[0632] The "AI model" is artificial intelligence software that identifies risk levels and risk details based on photos and comments.

[0633] The "risk level" is an index that indicates the degree of danger of a discovered risk location.

[0634] "Risk details" are descriptions of specific problems or dangers that the risk area may cause.

[0635] "Safety measures proposal" is information that proposes specific action plans and measures to be taken in response to identified risks.

[0636] An "autonomous vehicle camera" is a video recording device installed in an autonomous vehicle to capture road conditions in real time.

[0637] "LiDAR" is a sensor that uses laser light to measure the position and distance of an object with high precision.

[0638] "Real-time" means that the processing from data acquisition to analysis and notification is carried out immediately.

[0639] "Passenger" means a user aboard an automated driving vehicle.

[0640] A "traffic management system" is a system for monitoring and controlling the operation status of autonomous vehicles.

[0641] "Notifying" refers to the act of informing users and operation managers of the analysis results and proposed safety measures.

[0642] "Crowdfunding" is a method of raising funds from multiple internet users.

[0643] The present invention is a system for quickly and accurately identifying risk information for infrastructure and taking safety measures. This system involves a process in which a user reports risk locations, an AI model is used to analyze the risks, and safety measures are generated. Specifically, the system is implemented as follows.

[0644] User-generated and uploaded risk information

[0645] When a user discovers a risky area in infrastructure, they take a photo of the area with their smartphone or camera. They then enter details of the risky area as a comment in text format. For example, if a user discovers a large crack in the road, they can take a photo of the crack, enter a comment such as "There is a large crack. It looks like it could cause a traffic accident," and upload it. Any commonly available smartphone or camera will do.

[0646] Data reception and storage by the server

[0647] The server receives photos and comments sent by users and stores them in a database. The database is an information management system for efficiently managing information such as photos and comments, and allows for quick storage and retrieval of data that will later be added to the AI ​​analysis queue. The software used is a relational database management system such as MySQL.

[0648] Data analysis using AI models

[0649] The server adds the information stored in the database to an AI analysis queue, which then analyzes it using an AI model. The AI ​​model is built using machine learning libraries such as TensorFlow. The AI ​​model performs a risk analysis using the received photos and comments as input data. As a result of the analysis, the risk level (e.g., "high") and risk details (e.g., "possibility of a traffic accident due to cracks in the road") are identified.

[0650] Creation and notification of safety measures

[0651] The server generates safety measures based on the risk information identified by the AI ​​model. The safety measures include specific action plans and countermeasures. For example, it may suggest that road repairs are necessary. The generated safety measures are then notified to all users by the server.

[0652] Crowdfunding

[0653] If necessary, the server will initiate crowdfunding, set up a crowdfunding link, and notify all users. The crowdfunding page will contain detailed information about risks and countermeasures, and funders can make donations through the page.

[0654] Sharing the status of corrections

[0655] The server manages the repair status of risk areas reported by users and shares it with all users. This allows users to check the progress of repairs in real time. For example, when repairs to cracks in a road are completed, that information is notified to all users.

[0656] Risk Management for Autonomous Vehicles

[0657] Real-time data from cameras and LiDAR on autonomous vehicles is sent to a server, where risk information is analyzed using an AI model. This analysis information is then sent to passengers and the operation management system, and safety measures such as changing the driving route are implemented.

[0658] Specific examples

[0659] 1. User action: A user discovers a fallen tree in a nearby park, takes a photo of it, writes a comment saying "There is a fallen tree in the park. It may cause injury," and uploads the photo.

[0660] 2. Server processing: The server receives the photos and comments, stores them in a database, and then adds them to the AI ​​analysis queue.

[0661] 3. AI model analysis: The AI ​​model analyzes the photos and comments to identify risk details such as "Risk level: High" and "Fallen trees in the park pose a risk of injury."

[0662] 4. Generation of safety measures: The server generates safety measures such as "removal of fallen trees is required" and notifies all users.

[0663] 5. Crowdfunding: If necessary, the server will start the crowdfunding and send the link to all users.

[0664] 6. Sharing of correction status: When the fallen tree removal work is completed, the information is shared with all users.

[0665] Example prompts for generative AI models:

[0666] "There is a large crack in the center of the road. It is about 10 cm wide. Please analyze the possibility of this causing a traffic accident."

[0667] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0668] Step 1:

[0669] Input: Users take photos of risky areas in infrastructure using a smartphone or camera, enter details of the risk as comments, and upload the photos and comments they have entered.

[0670] How it works: When a user discovers a risky area in infrastructure, they use their camera to take a photo of the risky area, then enter details of the risk (such as the risk of a crack in the photo) as a text comment, and then press a button to upload the photo and comment using a dedicated application.

[0671] Output: The captured photo and the entered comment data are sent to the server.

[0672] Step 2:

[0673] Input: The server receives the photo and comment submitted by the user.

[0674] Operation: The server receives photos and comment data sent by users through a receiving port. Specifically, the server obtains the data using HTTP requests.

[0675] Output: The received photo and comment data is temporarily stored in local storage and then stored in a database.

[0676] Step 3:

[0677] Input: Retrieve stored photo and comment data from the database.

[0678] How it works: The server uses a database management system to retrieve the stored photo and comment data from the database, using MySQL queries to retrieve the necessary data.

[0679] Output: The retrieved photo and comment data is added to the AI ​​analysis queue to await analysis.

[0680] Step 4:

[0681] Input: Data added to the AI ​​analysis queue awaiting analysis.

[0682] How it works: The server sequentially retrieves data from the AI ​​analysis queue and inputs it into the AI ​​model. The AI ​​model uses neural networks built with TensorFlow and other tools to perform image recognition and text analysis. It identifies risks based on photos and comments, and determines the risk level and risk details.

[0683] Output: The AI ​​model outputs the risk level (e.g., "High") and risk details (e.g., "Possibility of traffic accident due to cracks in the road") as the analysis result.

[0684] Step 5:

[0685] Input: Analysis results from the AI ​​model (risk level and risk details).

[0686] Operation: The server generates safety measures based on the analysis results of the AI ​​model. Specifically, if the risk level is "high," it generates a message suggesting appropriate measures (e.g., "prompt road repairs").

[0687] Output: The generated safety measures are prepared as text data.

[0688] Step 6:

[0689] Input: Generated safety plan.

[0690] Operation: The server notifies all users of this proposed security measure. This can be done via a notification function within the application or by email. A notification is displayed on the client device.

[0691] Output: A notification message that is displayed on the user's terminal.

[0692] Step 7:

[0693] Input: Risk information analyzed by the AI ​​model and generated safety measures.

[0694] Behavior: If necessary, the server will initiate crowdfunding. A crowdfunding page link and information will be generated and posted to all users.

[0695] Output: Crowdfunding page link and notification message.

[0696] Step 8:

[0697] Input: Correction status data.

[0698] How it works: The server manages the repair status of risk areas and shares the progress with all users. When the repair is complete, it notifies all users.

[0699] Output: A message to the user indicating that the fix is ​​complete.

[0700] Examples:

[0701] A user discovers a crack in the road, takes a photo, and enters a comment. The server receives the photo and comment, analyzes it using an AI model, and determines "Risk level: High, Risk details: Possibility of traffic accident due to road crack." It then notifies the user that "Road repair work is required" as a safety measure.

[0702] Example prompts for generative AI models:

[0703] "There is a large crack in the center of the road. It is about 10 cm wide. Please analyze the possibility of this causing a traffic accident."

[0704] 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.

[0705] The present invention is a system that generates safety measures by collecting risk information about infrastructure that users use on a daily basis and analyzing it using AI combined with an emotion engine. This system speeds up responses to risk areas in the infrastructure and adjusts the level of urgency taking into account the user's emotions. Below, an embodiment of the present invention will be described in natural language.

[0706] User-generated and uploaded risk information

[0707] When a user discovers a risky area in infrastructure, they take a photo of the area using a device such as a smartphone or PC. Next, the user launches a dedicated application, enters the photo along with a comment explaining the details of the risk, and sends this data to a server. For example, if a user discovers a fallen tree in a park, they can take a photo of the tree on the spot and enter a comment such as, "There is a fallen tree. It is very dangerous." and send it.

[0708] Data reception and storage by the server

[0709] The server receives the photos and comments sent by users. The received data is stored in a database by the server. The database is an information management system for managing information such as photos and comments, and allows efficient storage and retrieval of data for later analysis.

[0710] Emotion recognition by emotion engine

[0711] The server inputs the comments received from the user into the emotion engine and analyzes the user's emotion. The emotion engine reads the emotion from the user's comment and identifies the emotional state (e.g., "very dangerous"). The emotional state is used to adjust the urgency of the risk level.

[0712] Data analysis using AI models

[0713] The server adds the photos, comments, and emotion data from the emotion engine stored in the database to the AI ​​analysis queue, which then analyzes them using the AI ​​model. The AI ​​model determines the risk level and risk details based on the input data. For example, it generates analysis results such as "Risk level: Very high" and "Fallen trees in the park may pose a serious danger."

[0714] Generate safety measures

[0715] The server generates safety measures based on the risk information identified by the AI ​​model. The safety measures include specific action plans and countermeasure methods, such as "carry out emergency tree removal work." Furthermore, the server takes into account the user's emotional data to adjust the urgency and optimize the measures.

[0716] User notification and crowdfunding

[0717] The server notifies all users of the generated safety measures. Users can check the measures through the application. If necessary, the server also launches a crowdfunding campaign, sets up a link to collect funds from users and related parties, and notifies all users. The crowdfunding page contains risk information and details of the measures, and funders can make donations through the page.

[0718] Sharing the status of corrections

[0719] The server manages the repair status of risk areas reported by users and shares the progress with all users. This allows users to check the progress of repairs in real time and understand how the risk areas they reported are being addressed. For example, when the removal of fallen trees is completed, that information is notified to all users.

[0720] Specific examples

[0721] Specific examples are shown below.

[0722] 1. User action: A user notices a broken window at a nearby school, takes a photo of it, and writes the comment "The window at my school is broken and it's very dangerous."

[0723] 2. Server processing: The server receives the photo and comments, stores them in a database, and then inputs the comments into an emotion engine to analyze the emotion. For example, an emotional state of "very dangerous" is identified.

[0724] 3. AI model analysis: The AI ​​model analyzes the photo and emotion data to identify risk details such as "Risk level: Very high" and "High probability of injury from broken window glass."

[0725] 4. Generation of safety measures: Based on the analysis results, the server generates safety measures such as "carry out emergency window glass replacement work" and notifies all users.

[0726] 5. Crowdfunding: If necessary, the server will start the crowdfunding and send the link to all users.

[0727] 6. Sharing of repair status: When the window glass replacement work is completed, the information is shared with all users.

[0728] The present invention makes it possible to quickly implement infrastructure safety measures that take into account user feelings, and by taking appropriate measures, risks can be managed efficiently and effectively.

[0729] The processing flow will be explained below.

[0730] Step 1:

[0731] When a user discovers a risky area in the infrastructure, they can take a photo of the area using a device such as a smartphone or computer.

[0732] Step 2:

[0733] The user launches a dedicated application and takes a photo and enters a comment detailing the risk. For example, "There is a fallen tree in the park. It is very dangerous."

[0734] Step 3:

[0735] The user sends the completed photo and comment to the server via the application.

[0736] Step 4:

[0737] The server stores the received photos and comments in a database and passes the comments to an emotion engine to analyze the user's emotions.

[0738] Step 5:

[0739] The server receives the emotion data returned by the emotion engine and adds it to the AI ​​analysis queue along with the original data.

[0740] Step 6:

[0741] The server sequentially passes data added to the AI ​​analysis queue to the AI ​​model, which analyzes the risk level and risk details, such as "Risk level: Very high" or "High possibility of injury due to falling trees."

[0742] Step 7:

[0743] The server generates safety measures based on the risk information analyzed by the AI ​​model, such as "implementing emergency tree removal work."

[0744] Step 8:

[0745] The server adjusts the urgency level based on the emotion data and notifies all users of the optimized safety measures, which they can then check through the application.

[0746] Step 9:

[0747] If necessary, the server will set up a crowdfunding campaign and provide a link to all users, which will contain detailed risk information and suggested solutions.

[0748] Step 10:

[0749] Users can access the crowdfunding page and provide funds, which are then used to repair and improve the infrastructure.

[0750] Step 11:

[0751] The server manages the status of risky areas and shares the progress of the repairs with all users. When the repairs are complete, the information is also notified.

[0752] Specific examples

[0753] 1. User action: The user notices a broken window at the school, takes a photo of it, and writes the comment "The window at the school is broken and it is very dangerous."

[0754] 2. Server processing: The server receives the photo and comments, stores them in a database, and then inputs the comments into an emotion engine to analyze the emotion. For example, an emotional state of "very dangerous" is identified.

[0755] 3. Adding emotion data: The server adds the emotion data returned from the emotion engine to the AI ​​analysis queue along with the original data.

[0756] 4. AI model analysis: The AI ​​model analyzes the photo and emotion data to identify risk details such as "Risk level: Very high" and "High probability of injury from broken window glass."

[0757] 5. Generation of safety measures: Based on the analysis results, the server generates safety measures such as "carry out emergency window glass replacement work" and notifies all users.

[0758] 6. Crowdfunding: If necessary, the server will start the crowdfunding and send the link to all users.

[0759] 7. Sharing of repair status: When the window glass replacement work is completed, the information is shared with all users.

[0760] Example 2

[0761] 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."

[0762] Conventional infrastructure risk management systems typically assess risk levels and determine safety measures based solely on user reports. However, these systems do not adequately consider user sentiment or the level of urgency, which can delay emergency measures. Furthermore, limited means of effective crowdfunding make it difficult to raise funds quickly.

[0763] 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.

[0764] In this invention, the server includes a means for uploading photos and comments taken by users of risky areas of infrastructure, a means for storing the photos and comments received by the server in a database and performing sentiment analysis of the comments using an emotion engine, a means for an AI model to analyze the photos, comments, and emotion data to identify the risk level and risk details and generate safety measure proposals, and a means for the server to notify all users of the generated safety measure proposals and start crowdfunding as necessary. This enables rapid risk assessment and generation of countermeasure proposals that take user sentiment into consideration, as well as more effective fundraising through crowdfunding.

[0765] "User" refers to a person who discovers risk areas in the infrastructure and reports that information to the system.

[0766] "Infrastructure" refers to facilities and structures that provide public convenience and safety, and specifically includes roads, bridges, parks, schools, etc.

[0767] "Risk points" refer to parts or conditions in infrastructure that have the potential to cause accidents or damage.

[0768] "Photo" refers to an image that a user visually records of a risk location.

[0769] "Comment" refers to an explanatory text entered by the user about the details and circumstances of the risk area.

[0770] "Upload" refers to the act of a user sending photos and comments from their own device to a server.

[0771] "Server" refers to a computer system that processes and stores data received from users.

[0772] "Database" refers to an information management system that efficiently stores and manages photos and comments received by the server.

[0773] "Emotion engine" refers to software that analyzes and identifies the emotional state of a user's comments.

[0774] "Sentiment analysis" refers to the process of using an emotion engine to read emotions from user comments.

[0775] "AI model" refers to an artificial intelligence algorithm that analyzes photos, comments, and sentiment data to identify risk levels and risk details.

[0776] "Risk level" refers to the severity of the risk identified by the AI ​​model.

[0777] "Risk details" refers to specific information about the risks identified by the AI ​​model.

[0778] "Safety measures plan" refers to a specific action plan for reducing risk that is generated by the server based on risk information.

[0779] "Notification" refers to a means of communicating information to all users about the safety measures that have been created.

[0780] "Crowdfunding" refers to the act of soliciting donations from users and related parties in order to raise the funds necessary to implement proposed safety measures.

[0781] "Link" refers to the URL for accessing the crowdfunding page.

[0782] "Remediation status" refers to the progress of remediation work on reported risk areas.

[0783] The present invention is a system that collects risk information about infrastructure that users use on a daily basis and combines an emotion engine and an AI model. This system is designed to achieve rapid risk response and adjust the urgency level taking into account the user's emotions. An embodiment of this system is described in detail below.

[0784] User-generated and uploaded risk information

[0785] When a user discovers a risky area, they take a photo of the area using a device such as a smartphone or PC. Next, the user launches a dedicated application (e.g., "Risk Report App") and enters a comment explaining the details of the risk along with the photo. The data is then sent to the server.

[0786] For example, if a user discovers a fallen tree in a park, they can take a photo of the tree on the spot and send it with a comment such as, "There's a fallen tree. It's very dangerous."

[0787] Data reception and storage by the server

[0788] The server receives the photos and comments sent by users. The received data is stored in a "risk management database." The database efficiently manages information such as photos and comments and stores the data for later analysis.

[0789] Emotion recognition by emotion engine

[0790] The server inputs the comments received from the user into an emotion engine (e.g., "Emotion AI") to analyze the user's emotions. The emotion engine identifies the user's emotional state (e.g., "very dangerous") from the user's comments. The emotional state is used to adjust the urgency of the risk level.

[0791] Data analysis using AI models

[0792] The server adds the photos, comments, and emotion data stored in the database to an AI analysis queue, which then analyzes them using an AI model (e.g., the "Risk Assessment AI Model"). The AI ​​model identifies the risk level and risk details based on the input data. For example, it generates analysis results such as "Risk level: Very high" and "Fallen trees in the park may pose a serious danger."

[0793] Generate safety measures

[0794] The server generates safety measures based on the risk information identified by the AI ​​model. The safety measures include specific action plans and methods, such as "carry out emergency tree removal work." Furthermore, the server takes into account the user's emotional data to adjust the urgency and optimize the measures.

[0795] User notification and crowdfunding

[0796] The server notifies all users of the generated safety measures. Users can check the measures through the application. If necessary, the server also notifies all users of a link to start crowdfunding and collect funds from users and related parties. The crowdfunding page contains risk information and details of the measures, and funders can make donations through the page.

[0797] Sharing the status of corrections

[0798] The server manages the repair status of risk areas reported by users and shares the progress with all users. This allows users to check the progress of repairs in real time and understand how the risk areas they reported are being addressed. For example, when the removal of fallen trees is completed, that information is notified to all users.

[0799] Specific examples

[0800] Specific examples are shown below.

[0801] 1. User action: A user notices a broken window at a nearby school, takes a photo of it, and writes the comment "The window at my school is broken and it's very dangerous."

[0802] 2. Server processing: The server receives the photo and comments, stores them in a database, and then inputs the comments into an emotion engine to analyze the emotion. For example, an emotional state of "very dangerous" is identified.

[0803] 3. AI model analysis: The AI ​​model analyzes the photo and emotion data to identify risk details such as "Risk level: Very high" and "High probability of injury from broken window glass."

[0804] 4. Generation of safety measures: Based on the analysis results, the server generates safety measures such as "carry out emergency window glass replacement work" and notifies all users.

[0805] 5. Crowdfunding: If necessary, the server will start the crowdfunding and send the link to all users.

[0806] 6. Sharing of repair status: When the window glass replacement work is completed, the information is shared with all users.

[0807] The above is an embodiment of the present invention. This system enables infrastructure safety measures to be implemented quickly while taking into account user emotions, and risk management can be performed efficiently and effectively by taking appropriate measures.

[0808] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0809] Step 1:

[0810] User-generated and uploaded risk information

[0811] How it works: The user takes a photo of a risky area in the infrastructure (e.g., a fallen tree, a broken window) using a smartphone or computer.

[0812] Input: Photo and risk comment.

[0813] Data processing: The user launches a dedicated application and inputs the photograph they took and a comment detailing the risk (e.g., "There is a fallen tree. It is very dangerous."). The application then packages this data.

[0814] Output: Packaged photo and comment data.

[0815] Step 2:

[0816] Data reception and storage by the server

[0817] Operation: The server receives packaged data sent by the user.

[0818] Input: User uploaded photo and comment data.

[0819] Data processing: The server stores the received data in the "risk management database."

[0820] Output: Photo and comment data stored in a database.

[0821] Step 3:

[0822] Emotion analysis of comments using an emotion engine

[0823] How it works: The server inputs the saved comments into the emotion engine for analysis.

[0824] Input: Comments stored in the database.

[0825] Data processing: An emotion engine (e.g., "Emotion AI") analyzes and identifies the user's emotional state (e.g., "very dangerous") from the comments.

[0826] Output: Identified emotional state data.

[0827] Step 4:

[0828] Analyzing risk data with AI models

[0829] How it works: The server adds the photo, comment, and emotion data to the AI ​​analysis queue and analyzes it using the AI ​​model.

[0830] Input: photos, comments, and emotion data.

[0831] Data processing: An AI model (e.g., a "risk assessment AI model") uses this data to identify risk levels and risk details, generating analysis results such as "Risk level: Very high" and "Falling trees in the park could pose a serious risk."

[0832] Output: Risk level and risk details data.

[0833] Step 5:

[0834] Server-generated safety measures

[0835] How it works: The server generates safety measures based on the risk information identified by the AI ​​model.

[0836] Input: Risk level and risk details data.

[0837] Data processing: The server generates safety measures (e.g., "Implement emergency tree removal work") and adjusts the urgency of the measures based on the user's emotional data.

[0838] Output: Generated safety measures.

[0839] Step 6:

[0840] Notification of proposed security measures by the server and start of crowdfunding

[0841] Action: The server notifies all users of the generated security plan.

[0842] Input: Generated safety measures.

[0843] Data processing: Generate a notification message and push it to all users via the application. If necessary, the server will start the crowdfunding campaign and notify all users of the link.

[0844] Output: Notification message and crowdfunding link.

[0845] Step 7:

[0846] Server sharing of revision status

[0847] How it works: The server manages the progress of fixing risk areas reported by users and shares the progress with all users.

[0848] Input: Risk location correction status data.

[0849] Data processing: Updates the management database of the correction status and generates messages that visualize the correction status.

[0850] Output: A message informing you of the fix status.

[0851] (Application example 2)

[0852] 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."

[0853] Currently, many factories place importance on safety management, but the speed from risk detection to response is often slow. Furthermore, on-site workers often find it difficult to accurately judge the seriousness of risks, as the method for reporting risk information is complicated. Furthermore, risk management does not take into account the emotions of workers, and the inability to take appropriate measures increases the risk of accidents and malfunctions. The purpose of this invention is to solve these problems and ensure efficient and rapid safety management within factories.

[0854] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a means for a user to take a photo of a risky location in the infrastructure, enter a comment, and upload it; a means for the server to store the received photo and comment in a database and add it to an AI analysis queue; a means for analyzing the emotion of the comment using an emotion engine; a means for an AI model to analyze the photo and emotion data to identify the risk level and risk details and generate a safety measure plan; a means for the server to notify the user of the generated safety measure plan and start crowdfunding as necessary; and a means for sharing the progress of the safety measure plan with all users. This makes it possible to quickly and accurately analyze risk information within a factory and implement safety measures that take emotions into consideration.

[0855] A "user" is an individual or organization that provides information by discovering risk areas in the infrastructure, taking photos, and adding comments.

[0856] "Server" means a central processing unit for storing and analyzing data received from users, and generating and notifying security measures.

[0857] "Photographs" are image data that visually record risk areas in infrastructure.

[0858] "Comment" is text information that allows the user to add an explanation about the risky part.

[0859] The "database" is a system that efficiently stores information such as received photos and comments, and allows for searching and analysis.

[0860] The "AI analysis queue" is a collection of received data that is waiting to be analyzed by AI in sequence.

[0861] An "emotion engine" is software or a system for identifying emotions from user comments and analyzing their emotional state.

[0862] The "AI model" is an analytical model that uses machine learning or deep learning to identify risk levels and risk details based on received photo and emotion data.

[0863] The "risk level" is an index that indicates the urgency and severity of the risk to the analyzed infrastructure.

[0864] "Risk details" is information that indicates the specific content and scope of impact of the identified risk.

[0865] "Safety measures" are specific countermeasures and action plans to be taken in response to identified risks.

[0866] "Crowdfunding" is a system that widely solicits donors via the Internet in order to raise the funds needed to address risks.

[0867] "Progress" is information that indicates how much progress has been made in correcting risk areas and taking countermeasures.

[0868] This invention is a system for efficient and rapid safety management within factories. This system allows users to take photos of risky areas in infrastructure and send their comments to a server, which then analyzes the data, generates safety measures, and notifies the user. It also includes a function to set up a crowdfunding link as needed and share the progress of correcting risky areas.

[0869] Hardware and software used

[0870] Hardware: Smartphones, smart glasses, PCs, servers

[0871] Software: Google Speech-to-Text API, Hugging Face Transformers (sentiment analysis), TensorFlow or PyTorch (AI model analysis), cloud database system

[0872] Data collection and transmission

[0873] A user (factory worker) uses a smartphone or smart glasses to take a photo of a risky area. For example, if a user discovers a wall that is about to collapse in the factory, they take a photo of it. The user then adds a comment about the risky area by voice or text input. For example, "The wall at the work site is about to collapse. It is very dangerous." Once the photo and comment are prepared, the user sends the data to the server through a dedicated application.

[0874] Data storage and analysis

[0875] The server receives photos and comments sent by users and stores them in a cloud database. It then inputs the comments into an emotion engine (Hugging Face Transformers) to analyze the emotion. For example, it identifies an emotional state such as "very dangerous." After the emotion is identified, the server adds all data, including the emotion data, to an AI analysis queue and analyzes it using an AI model (TensorFlow or PyTorch). The AI ​​model identifies the risk level and risk details based on the photo and emotion data.

[0876] Creation and notification of safety measures

[0877] The server generates specific safety measures based on the results of the AI ​​analysis. For example, it might suggest "dispatch an emergency response team and immediately begin repair work." Based on this, it notifies users and, if necessary, sets up a crowdfunding link and notifies all users. Through this link, donors can provide the funds needed for the countermeasures.

[0878] Share your progress

[0879] The server also has a function to share the progress of risk-point repairs with all users, allowing users to check the progress of countermeasures in real time. For example, when repair work is completed, the information can be notified to all users, allowing them to always be aware of the latest status.

[0880] Example prompt

[0881] Please analyze the risk information for the infrastructure that has been commented as "very dangerous" and provide the risk level and details.

[0882] This invention makes it possible to quickly and accurately analyze risk information within a factory and implement safety measures that take emotions into account, which is expected to ensure the safety of factory workers and improve operational efficiency.

[0883] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0884] Step 1:

[0885] The user takes a photo of a risky area of ​​infrastructure using a smartphone or smart glasses. The user adds a comment about the risk along with the photo by voice input or text input. For example, "This wall is about to collapse and is very dangerous." The input is photo data and comment data, and the output is a set of these data. Specifically, the system works by taking a photo using the device camera and adding a comment using the voice input function.

[0886] Step 2:

[0887] The user launches the dedicated application and sends the photos and comments they have taken to the server. The input is a set of photo data and comment data, and the output is the data sent to the server. Specifically, the user clicks the send button in the application to upload the data to the server via the Internet.

[0888] Step 3:

[0889] The server stores the received photos and comments in a cloud database. The input is the photo data and comment data sent to the server, and the output is the data stored in the cloud database. The specific operation is to use the server's storage system to store the data.

[0890] Step 4:

[0891] The server inputs the saved comment data into an emotion engine (Hugging Face Transformers) to analyze emotions. The input is comment data, and the output is data indicating the emotional state (e.g., "very dangerous"). Specifically, the emotion engine is called and the comment is analyzed using natural language processing techniques.

[0892] Step 5:

[0893] The server adds all data, including emotional state data, to an AI analysis queue and analyzes it using an AI model (TensorFlow or PyTorch). The input is photo data and emotional state data, and the output is data indicating risk level and risk details. Specifically, the AI ​​model is executed and the data is analyzed using a deep learning algorithm.

[0894] Step 6:

[0895] The server generates safety measures based on the results of the AI ​​analysis. The input is risk level data and detailed risk data, and the output is specific safety measures (e.g., "Dispatch an emergency response team and immediately begin repair work"). Specific operations involve generating appropriate measures using a predefined algorithm.

[0896] Step 7:

[0897] The server notifies the user of the generated security measure plan and sets a crowdfunding link if necessary. This link is notified to all users. The input is the security measure plan data and the crowdfunding link data, and the output is the notification data sent to the user. Specifically, the server's notification system is used to send the security measure plan and link to the user.

[0898] Step 8:

[0899] The server shares the progress of risky part repairs with all users in real time. The input is repair progress data, and the output is progress notification data for all users. Specifically, the server retrieves the progress from the database and shares it with users using the notification system.

[0900] 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.

[0901] 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.

[0902] 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.

[0903] [Third embodiment]

[0904] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0905] 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.

[0906] 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).

[0907] 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.

[0908] 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.

[0909] 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).

[0910] 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.

[0911] 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.

[0912] 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.

[0913] 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.

[0914] 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.

[0915] 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."

[0916] The present invention is a system that generates safety measures by collecting risk information related to infrastructure that users use on a daily basis and analyzing it using AI. Below, an embodiment of the present invention will be described in natural language.

[0917] User-generated and uploaded risk information

[0918] When a user discovers a risky area in infrastructure, they take a photo of the area and upload it to the application using a device such as a smartphone or computer. The user also enters a brief comment for the photo, explaining the details of the risk. For example, if a user discovers a large crack in the road, they can take a photo of the crack and enter a comment such as, "There is a large crack. It looks like it could cause a traffic accident," and submit it to the app.

[0919] Data reception and storage by the server

[0920] The server receives the photos and comments sent by users. The received data is stored in a database by the server. The database is an information management system for managing information such as photos and comments, and can efficiently store and search data for later analysis.

[0921] Data analysis using AI models

[0922] The server adds the information stored in the database to an AI analysis queue, which then analyzes it using the AI ​​model. The AI ​​model uses the received photos and comments as input data to perform a risk analysis. As a result of the analysis, the risk level (e.g., "high") and risk details (e.g., "possibility of a traffic accident due to cracks in the road") are identified.

[0923] Generate safety measures

[0924] The server generates safety measures based on the risk information identified by the AI ​​model. These safety measures include specific action plans and countermeasures, such as suggesting that road repairs are necessary.

[0925] User notification and crowdfunding

[0926] The server notifies all users of the safety measures it has created. Users can check the measures through the application. If necessary, the server will also launch a crowdfunding campaign, set up a link to collect funds from users and other interested parties, and notify all users. The crowdfunding page will contain detailed information about the risks and the measures, and funders can make donations through the page.

[0927] Sharing the status of corrections

[0928] The server manages the repair status of risk areas reported by users and shares it with all users. This allows users to check the progress of repairs in real time and understand how the risk areas they reported are being addressed. For example, when repairs to cracks in a road are completed, that information is notified to all users.

[0929] Specific examples

[0930] Specific examples are shown below.

[0931] 1. User action: A user finds a fallen tree in a nearby park, takes a photo of it, and writes a comment saying, "There is a fallen tree in the park. It may cause injury."

[0932] 2. Server processing: The server receives the photos and comments, stores them in a database, and then adds them to the AI ​​analysis queue.

[0933] 3. AI model analysis: The AI ​​model analyzes the photos and comments to identify risk details such as "Risk level: High" and "Fallen trees in the park pose a risk of injury."

[0934] 4. Generation of safety measures: The server generates safety measures such as "removal of fallen trees is required" and notifies all users.

[0935] 5. Crowdfunding: If necessary, the server will start the crowdfunding and send the link to all users.

[0936] 6. Sharing of correction status: When the fallen tree removal work is completed, the information is shared with all users.

[0937] The present invention makes it possible to quickly identify safety risks in infrastructure and take appropriate measures. Furthermore, funds can be raised through crowdfunding with the cooperation of users, and measures can be implemented with high transparency.

[0938] The processing flow will be explained below.

[0939] Step 1:

[0940] When a user discovers a risky area in the infrastructure, they can take a photo of the area using a device such as a smartphone or computer.

[0941] Step 2:

[0942] The user launches a dedicated application and takes a photo and enters a comment along with it. For example, the user might write, "There's a big crack. It could cause a traffic accident."

[0943] Step 3:

[0944] The device sends the entered photo and comment to the server.

[0945] Step 4:

[0946] The server temporarily stores the received photos and comments in a database.

[0947] Step 5:

[0948] The data stored by the server is added to the AI ​​analysis queue and prepared for analysis.

[0949] Step 6:

[0950] The server passes the photo and comment data from the queue to the AI ​​model and begins analysis.

[0951] Step 7:

[0952] The AI ​​model analyzes the photos and comments to identify risk levels, such as "Risk level: High" and "Risk details: Possibility of traffic accident due to cracks in the road."

[0953] Step 8:

[0954] The server generates safety measures based on the analysis results of the AI ​​model, such as "Road repair work is required."

[0955] Step 9:

[0956] The server notifies all users of the generated safety measures and analysis results.

[0957] Step 10:

[0958] If necessary, the server will set up a crowdfunding campaign and send a link to all users, which will include details of the risks and countermeasures.

[0959] Step 11:

[0960] Users can access the crowdfunding page and provide funds, which are then used to repair and improve infrastructure.

[0961] Step 12:

[0962] The server manages the status of risk fixes and shares the progress with all users. When fixes are complete, the server also notifies users of this information.

[0963] Example 1

[0964] 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."

[0965] Currently, risk management for everyday infrastructure is time-consuming and often results in inappropriate responses. There are also issues with efficient sharing of risk information and methods of fundraising. The present invention aims to solve these problems and provide a system that quickly and effectively identifies infrastructure risks and takes appropriate measures.

[0966] 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.

[0967] In this invention, the server includes means for users to take photos of risky areas in infrastructure they use daily, enter comments, and upload them from their terminals, means for the server to store the photos and comments received in a database and add them to an AI analysis queue, means for preprocessing the generated data and for an AI model to analyze the photos and comments to identify the risk level and details, means for automatically generating safety measure proposals based on the identified risk information, means for the server to notify all users of the generated safety measure proposals and start crowdfunding as necessary, and means for managing and notifying the status of repairs to risky areas. This enables quick and effective identification of infrastructure safety risks and enables highly transparent countermeasures and fundraising.

[0968] "User" refers to anyone who uses the system to report infrastructure risks and upload photos and comments.

[0969] "Infrastructure" refers to structures and systems that support the foundations of society, including roads, parks, bridges, etc.

[0970] "Risk points" refer to locations within infrastructure where potential dangers may exist.

[0971] "Photographing" refers to the operation of using a device to leave a visual record.

[0972] "Comment" refers to text information that a user adds to a photograph they have taken.

[0973] "Terminal" refers to the device that a user uses to access the system, such as a smartphone or PC.

[0974] "Upload" refers to the operation of sending data from a terminal to a server.

[0975] "Server" refers to a computer system for managing and processing data received from users.

[0976] A "database" refers to a system for managing and storing information, allowing photos and comments to be efficiently stored and searched.

[0977] "AI analysis queue" refers to a waiting line structure for sequentially analyzing data.

[0978] "Preprocessing" refers to the operations used to convert data into a format suitable for analysis by an AI model.

[0979] "AI model" refers to software that uses machine learning technology to analyze data and identify risk levels and risk details.

[0980] "Risk Level" refers to a classification that indicates the severity of an identified risk.

[0981] "Risk details" refers to information that explains the specific details of an identified risk.

[0982] "Safety measures" refers to specific action plans and countermeasures to be taken in response to identified risks.

[0983] "Crowdfunding" refers to a method of widely raising funds via the Internet to address infrastructure risks.

[0984] "Link" refers to the URL that allows users to access the crowdfunding page.

[0985] "Notification" refers to the operation of the server sending information to the user and informing them.

[0986] "Remediation status" refers to the progress of the actions and corrections taken against the reported risk areas.

[0987] "Management" refers to monitoring the operational status of the entire system and performing necessary operations.

[0988] The present invention is a system that generates safety measures by collecting risk information related to infrastructure that users use on a daily basis and analyzing it using AI. Below, an embodiment of the present invention will be described in natural language.

[0989] Hardware and Software Configuration

[0990] This system includes the devices used by users (smartphones, PCs, etc.) and servers. The backend system uses a database (e.g., MySQL, PostgreSQL) for data management and a machine learning model (e.g., TensorFlow, PyTorch) for AI analysis.

[0991] User-generated and uploaded risk information

[0992] When a user discovers a risky area in the infrastructure, they take a photo of the area using their smartphone or computer. After taking the photo, they launch a dedicated application, select the photo they took, and upload it to the application. The user then enters a comment for the photo, explaining the details of the risk. The photo and comment data are then sent to the server. For example, if a user discovers a large crack in the road, they might enter a comment such as, "There's a large crack. It looks like it could cause a traffic accident."

[0993] Data reception and storage by the server

[0994] The server receives the photos and comments sent by the user as HTTP requests. The server saves the received photo data in a temporary directory and obtains the file path. At the same time, it saves the comment text and the photo file path in the database. This data is later added to the AI ​​analysis queue.

[0995] Data analysis using AI models

[0996] The server detects when new data is added to the database and adds the data to the AI ​​analysis queue. Before the data is passed to the AI ​​model, the server performs the necessary preprocessing. Specifically, it preprocesses the photo data using an image processing library (e.g., OpenCV) and converts the comment text into a format suitable for the NLP model. The preprocessed data is then input into the AI ​​model to identify the risk level and risk details.

[0997] Creation and notification of safety measures

[0998] Based on the risk information identified by the AI ​​model, the server uses a rule-based engine to generate safety measures. The generated safety measures are stored in a database, and the server then notifies all users of the measures. If necessary, a crowdfunding link is also generated and notified to users.

[0999] Sharing the status of corrections

[1000] The server manages the status of risk corrections and updates it regularly. When the corrections are complete, the information is notified to all users, allowing them to check the status of the corrections in real time.

[1001] Specific examples

[1002] Specific examples are shown below.

[1003] User Action: A user finds a fallen tree in a local park, takes a photo of it, and writes a comment saying, "There is a fallen tree in the park. It could cause injury."

[1004] Server processing: The server receives the photos and comments, stores them in a database, and then adds them to the AI ​​analysis queue.

[1005] AI model analysis: The AI ​​model analyzes photos and comments to identify risk levels such as "high" and risk details such as "falling trees in the park pose a risk of injury."

[1006] Generation of safety measures: The server generates safety measures such as "removal of fallen trees is required" and notifies all users.

[1007] Crowdfunding: The server will start the crowdfunding campaign if necessary and send the link to all users.

[1008] Sharing of repair status: When the fallen tree removal work is completed, the information is shared with all users.

[1009] Example prompts to be input to the generative AI model:

[1010] "There is a fallen tree in the park that could cause injury. Please analyze this risk."

[1011] This will enable rapid and effective identification of infrastructure safety risks and enable appropriate countermeasures and funding.

[1012] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1013] Step 1:

[1014] The user takes a photo of the risky part of the infrastructure, enters a comment, and uploads it from the terminal (input: photo and comment of the risky part of the infrastructure. output: sending the photo and comment).

[1015] Specific behavior:

[1016] Users use a smartphone or computer to take photos of risky areas of infrastructure.

[1017] The user launches the application, selects a photo, and proceeds to the upload screen.

[1018] The user enters a comment and details the risk in the text fields.

[1019] The user clicks the "Send" button to send the photo and comments to the server.

[1020] Step 2:

[1021] The server saves the received photos and comments in a database and adds them to the AI ​​analysis queue (input: sent photo and comment data; output: saved in database and added to queue).

[1022] Specific behavior:

[1023] The server receives an HTTP request from the user, which includes the photo data and comment text.

[1024] The server stores the photo data in a temporary directory and obtains the file path.

[1025] The server saves the comment data and the photo file path as a new record in the database.

[1026] Detects when a new record is saved and adds the data to the AI ​​analysis queue.

[1027] Step 3:

[1028] The server preprocesses the data, and the AI ​​model analyzes the photos and comments to identify risk levels and risk details (input: photos and comments stored in the database; output: risk levels and risk details).

[1029] Specific behavior:

[1030] The server preprocesses the photos and comments stored in the database.

[1031] Use an image processing library (e.g. OpenCV) to convert the photo data into an appropriate format.

[1032] Tokenize text data into a format suitable for natural language processing (NLP) models.

[1033] The server inputs the preprocessed data into the AI ​​model for analysis.

[1034] The AI ​​model analyzes photos and comments to identify risk levels (e.g., "High") and risk details (e.g., "Possibility of traffic accident due to cracks in the road").

[1035] Step 4:

[1036] Based on the identified risk information, the server automatically generates safety measures (input: risk level and risk details; output: safety measures).

[1037] Specific behavior:

[1038] The server receives the risk level and risk details returned by the AI ​​model.

[1039] The server uses a rule-based engine to generate risk-informed safety measures.

[1040] For example, if the risk level is "high," it will suggest that "road repair work is needed."

[1041] The generated safety measures are stored in a database.

[1042] Step 5:

[1043] The server notifies all users of the generated safety measures and initiates crowdfunding if necessary (Input: Safety measures. Output: User notification and crowdfunding link).

[1044] Specific behavior:

[1045] The server prepares a communication method (push notification, email, etc.) to notify all users of the generated safety measures.

[1046] The server forms a notification message and sends it with the content "A new security plan has been generated."

[1047] If necessary, the server generates a link to the crowdfunding page and notifies the user.

[1048] Step 6:

[1049] The server manages and notifies the status of risk corrections (input: correction status information; output: correction completion notification).

[1050] Specific behavior:

[1051] The server periodically checks and updates the status of corrections to risk areas.

[1052] Once the correction is complete, the information is recorded in the database.

[1053] The server sends a completion notification of the modification status to all users.

[1054] Users will receive notifications and can see the corrected infrastructure state on their applications.

[1055] (Application example 1)

[1056] 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."

[1057] There is a need to quickly and accurately identify infrastructure risk information and implement safety measures. Road risk information is particularly essential for autonomous vehicles, and risks must be identified in real time and notified to passengers and operation management systems. However, conventional systems can delay risk identification and notification, threatening safety. Furthermore, smooth funding for risk countermeasures is also necessary, but current methods can lack transparency and efficiency.

[1058] 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.

[1059] In this invention, the server includes: a means for a user to take a photo of a risky location in infrastructure, enter a comment, and upload it; a means for the server to store the received photo and comment in a database and add it to an AI analysis queue; a means for an AI model to analyze the photo and comment to identify the risk level and risk details and generate safety measure proposals; a means for analyzing risk information collected from the camera and LiDAR of the autonomous vehicle in real time; a means for notifying passengers and the operation control system of the analysis results and presenting safety measure proposals; and a means for the server to notify the user of the generated safety measure proposals and start crowdfunding if necessary. This enables autonomous vehicles to detect road risks in real time and quickly take safety measures, enabling highly transparent fundraising through crowdfunding.

[1060] "User" refers to a general user who uses the system to photograph and upload infrastructure risk information.

[1061] "Infrastructure" refers to buildings and structures that provide public conveniences, such as roads, parks, and public facilities.

[1062] "Risk areas" are areas of infrastructure that could pose safety problems, such as cracks, sinkholes, or fallen trees.

[1063] "Photography" refers to the act of recording images or videos of risk areas using a smartphone or camera.

[1064] Entering a "comment" is the act of describing the details and circumstances of the risk area in text format.

[1065] "Uploading" is the act of sending photos, videos, and comments you have taken to a server via the Internet.

[1066] A "server" is a computer system for receiving, storing, analyzing, and distributing data.

[1067] "Database" means an information management system for efficiently storing and managing received photos and comments.

[1068] An "AI analysis queue" is a list of data waiting to be analyzed by an AI model.

[1069] The "AI model" is artificial intelligence software that identifies risk levels and risk details based on photos and comments.

[1070] The "risk level" is an index that indicates the degree of danger of a discovered risk location.

[1071] "Risk details" are descriptions of specific problems or dangers that the risk area may cause.

[1072] "Safety measures proposal" is information that proposes specific action plans and measures to be taken in response to identified risks.

[1073] An "autonomous vehicle camera" is a video recording device installed in an autonomous vehicle to capture road conditions in real time.

[1074] "LiDAR" is a sensor that uses laser light to measure the position and distance of an object with high precision.

[1075] "Real-time" means that the processing from data acquisition to analysis and notification is carried out immediately.

[1076] "Passenger" means a user aboard an automated driving vehicle.

[1077] A "traffic management system" is a system for monitoring and controlling the operation status of autonomous vehicles.

[1078] "Notifying" refers to the act of informing users and operation managers of the analysis results and proposed safety measures.

[1079] "Crowdfunding" is a method of raising funds from multiple internet users.

[1080] The present invention is a system for quickly and accurately identifying risk information for infrastructure and taking safety measures. This system involves a process in which a user reports risk locations, an AI model is used to analyze the risks, and safety measures are generated. Specifically, the system is implemented as follows.

[1081] User-generated and uploaded risk information

[1082] When a user discovers a risky area in infrastructure, they take a photo of the area with their smartphone or camera. They then enter details of the risky area as a comment in text format. For example, if a user discovers a large crack in the road, they can take a photo of the crack, enter a comment such as "There is a large crack. It looks like it could cause a traffic accident," and upload it. Any commonly available smartphone or camera will do.

[1083] Data reception and storage by the server

[1084] The server receives photos and comments sent by users and stores them in a database. The database is an information management system for efficiently managing information such as photos and comments, and allows for quick storage and retrieval of data that will later be added to the AI ​​analysis queue. The software used is a relational database management system such as MySQL.

[1085] Data analysis using AI models

[1086] The server adds the information stored in the database to an AI analysis queue, which then analyzes it using an AI model. The AI ​​model is built using machine learning libraries such as TensorFlow. The AI ​​model performs a risk analysis using the received photos and comments as input data. As a result of the analysis, the risk level (e.g., "high") and risk details (e.g., "possibility of a traffic accident due to cracks in the road") are identified.

[1087] Creation and notification of safety measures

[1088] The server generates safety measures based on the risk information identified by the AI ​​model. The safety measures include specific action plans and countermeasures. For example, it may suggest that road repairs are necessary. The generated safety measures are then notified to all users by the server.

[1089] Crowdfunding

[1090] If necessary, the server will initiate crowdfunding, set up a crowdfunding link, and notify all users. The crowdfunding page will contain detailed information about risks and countermeasures, and funders can make donations through the page.

[1091] Sharing the status of corrections

[1092] The server manages the repair status of risk areas reported by users and shares it with all users. This allows users to check the progress of repairs in real time. For example, when repairs to cracks in a road are completed, that information is notified to all users.

[1093] Risk Management for Autonomous Vehicles

[1094] Real-time data from cameras and LiDAR on autonomous vehicles is sent to a server, where risk information is analyzed using an AI model. This analysis information is then sent to passengers and the operation management system, and safety measures such as changing the driving route are implemented.

[1095] Specific examples

[1096] 1. User action: A user discovers a fallen tree in a nearby park, takes a photo of it, writes a comment saying "There is a fallen tree in the park. It may cause injury," and uploads the photo.

[1097] 2. Server processing: The server receives the photos and comments, stores them in a database, and then adds them to the AI ​​analysis queue.

[1098] 3. AI model analysis: The AI ​​model analyzes the photos and comments to identify risk details such as "Risk level: High" and "Fallen trees in the park pose a risk of injury."

[1099] 4. Generation of safety measures: The server generates safety measures such as "removal of fallen trees is required" and notifies all users.

[1100] 5. Crowdfunding: If necessary, the server will start the crowdfunding and send the link to all users.

[1101] 6. Sharing of correction status: When the fallen tree removal work is completed, the information is shared with all users.

[1102] Example prompts for generative AI models:

[1103] "There is a large crack in the center of the road. It is about 10 cm wide. Please analyze the possibility of this causing a traffic accident."

[1104] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1105] Step 1:

[1106] Input: Users take photos of risky areas in infrastructure using a smartphone or camera, enter details of the risk as comments, and upload the photos and comments they have entered.

[1107] How it works: When a user discovers a risky area in infrastructure, they use their camera to take a photo of the risky area, then enter details of the risk (such as the risk of a crack in the photo) as a text comment, and then press a button to upload the photo and comment using a dedicated application.

[1108] Output: The captured photo and the entered comment data are sent to the server.

[1109] Step 2:

[1110] Input: The server receives the photo and comment submitted by the user.

[1111] Operation: The server receives photos and comment data sent by users through a receiving port. Specifically, the server obtains the data using HTTP requests.

[1112] Output: The received photo and comment data is temporarily stored in local storage and then stored in a database.

[1113] Step 3:

[1114] Input: Retrieve stored photo and comment data from the database.

[1115] How it works: The server uses a database management system to retrieve the stored photo and comment data from the database, using MySQL queries to retrieve the necessary data.

[1116] Output: The retrieved photo and comment data is added to the AI ​​analysis queue to await analysis.

[1117] Step 4:

[1118] Input: Data added to the AI ​​analysis queue awaiting analysis.

[1119] How it works: The server sequentially retrieves data from the AI ​​analysis queue and inputs it into the AI ​​model. The AI ​​model uses neural networks built with TensorFlow and other tools to perform image recognition and text analysis. It identifies risks based on photos and comments, and determines the risk level and risk details.

[1120] Output: The AI ​​model outputs the risk level (e.g., "High") and risk details (e.g., "Possibility of traffic accident due to cracks in the road") as the analysis result.

[1121] Step 5:

[1122] Input: Analysis results from the AI ​​model (risk level and risk details).

[1123] Operation: The server generates safety measures based on the analysis results of the AI ​​model. Specifically, if the risk level is "high," it generates a message suggesting appropriate measures (e.g., "prompt road repairs").

[1124] Output: The generated safety measures are prepared as text data.

[1125] Step 6:

[1126] Input: Generated safety plan.

[1127] Operation: The server notifies all users of this proposed security measure. This can be done via a notification function within the application or by email. A notification is displayed on the client device.

[1128] Output: A notification message that is displayed on the user's terminal.

[1129] Step 7:

[1130] Input: Risk information analyzed by the AI ​​model and generated safety measures.

[1131] Behavior: If necessary, the server will initiate crowdfunding. A crowdfunding page link and information will be generated and posted to all users.

[1132] Output: Crowdfunding page link and notification message.

[1133] Step 8:

[1134] Input: Correction status data.

[1135] How it works: The server manages the repair status of risk areas and shares the progress with all users. When the repair is complete, it notifies all users.

[1136] Output: A message to the user indicating that the fix is ​​complete.

[1137] Examples:

[1138] A user discovers a crack in the road, takes a photo, and enters a comment. The server receives the photo and comment, analyzes it using an AI model, and determines "Risk level: High, Risk details: Possibility of traffic accident due to road crack." It then notifies the user that "Road repair work is required" as a safety measure.

[1139] Example prompts for generative AI models:

[1140] "There is a large crack in the center of the road. It is about 10 cm wide. Please analyze the possibility of this causing a traffic accident."

[1141] 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.

[1142] The present invention is a system that generates safety measures by collecting risk information about infrastructure that users use on a daily basis and analyzing it using AI combined with an emotion engine. This system speeds up responses to risk areas in the infrastructure and adjusts the level of urgency taking into account the user's emotions. Below, an embodiment of the present invention will be described in natural language.

[1143] User-generated and uploaded risk information

[1144] When a user discovers a risky area in infrastructure, they take a photo of the area using a device such as a smartphone or PC. Next, the user launches a dedicated application, enters the photo along with a comment explaining the details of the risk, and sends this data to a server. For example, if a user discovers a fallen tree in a park, they can take a photo of the tree on the spot and enter a comment such as, "There is a fallen tree. It is very dangerous." and send it.

[1145] Data reception and storage by the server

[1146] The server receives the photos and comments sent by users. The received data is stored in a database by the server. The database is an information management system for managing information such as photos and comments, and allows efficient storage and retrieval of data for later analysis.

[1147] Emotion recognition by emotion engine

[1148] The server inputs the comments received from the user into the emotion engine and analyzes the user's emotion. The emotion engine reads the emotion from the user's comment and identifies the emotional state (e.g., "very dangerous"). The emotional state is used to adjust the urgency of the risk level.

[1149] Data analysis using AI models

[1150] The server adds the photos, comments, and emotion data from the emotion engine stored in the database to the AI ​​analysis queue, which then analyzes them using the AI ​​model. The AI ​​model determines the risk level and risk details based on the input data. For example, it generates analysis results such as "Risk level: Very high" and "Fallen trees in the park may pose a serious danger."

[1151] Generate safety measures

[1152] The server generates safety measures based on the risk information identified by the AI ​​model. The safety measures include specific action plans and countermeasure methods, such as "carry out emergency tree removal work." Furthermore, the server takes into account the user's emotional data to adjust the urgency and optimize the measures.

[1153] User notification and crowdfunding

[1154] The server notifies all users of the generated safety measures. Users can check the measures through the application. If necessary, the server also launches a crowdfunding campaign, sets up a link to collect funds from users and related parties, and notifies all users. The crowdfunding page contains risk information and details of the measures, and funders can make donations through the page.

[1155] Sharing the status of corrections

[1156] The server manages the repair status of risk areas reported by users and shares the progress with all users. This allows users to check the progress of repairs in real time and understand how the risk areas they reported are being addressed. For example, when the removal of fallen trees is completed, that information is notified to all users.

[1157] Specific examples

[1158] Specific examples are shown below.

[1159] 1. User action: A user notices a broken window at a nearby school, takes a photo of it, and writes the comment "The window at my school is broken and it's very dangerous."

[1160] 2. Server processing: The server receives the photo and comments, stores them in a database, and then inputs the comments into an emotion engine to analyze the emotion. For example, an emotional state of "very dangerous" is identified.

[1161] 3. AI model analysis: The AI ​​model analyzes the photo and emotion data to identify risk details such as "Risk level: Very high" and "High probability of injury from broken window glass."

[1162] 4. Generation of safety measures: Based on the analysis results, the server generates safety measures such as "carry out emergency window glass replacement work" and notifies all users.

[1163] 5. Crowdfunding: If necessary, the server will start the crowdfunding and send the link to all users.

[1164] 6. Sharing of repair status: When the window glass replacement work is completed, the information is shared with all users.

[1165] The present invention makes it possible to quickly implement infrastructure safety measures that take into account user feelings, and by taking appropriate measures, risks can be managed efficiently and effectively.

[1166] The processing flow will be explained below.

[1167] Step 1:

[1168] When a user discovers a risky area in the infrastructure, they can take a photo of the area using a device such as a smartphone or computer.

[1169] Step 2:

[1170] The user launches a dedicated application and takes a photo and enters a comment detailing the risk. For example, "There is a fallen tree in the park. It is very dangerous."

[1171] Step 3:

[1172] The user sends the completed photo and comment to the server via the application.

[1173] Step 4:

[1174] The server stores the received photos and comments in a database and passes the comments to an emotion engine to analyze the user's emotions.

[1175] Step 5:

[1176] The server receives the emotion data returned by the emotion engine and adds it to the AI ​​analysis queue along with the original data.

[1177] Step 6:

[1178] The server sequentially passes data added to the AI ​​analysis queue to the AI ​​model, which analyzes the risk level and risk details, such as "Risk level: Very high" or "High possibility of injury due to falling trees."

[1179] Step 7:

[1180] The server generates safety measures based on the risk information analyzed by the AI ​​model, such as "implementing emergency tree removal work."

[1181] Step 8:

[1182] The server adjusts the urgency level based on the emotion data and notifies all users of the optimized safety measures, which they can then check through the application.

[1183] Step 9:

[1184] If necessary, the server will set up a crowdfunding campaign and provide a link to all users, which will contain detailed risk information and suggested solutions.

[1185] Step 10:

[1186] Users can access the crowdfunding page and provide funds, which are then used to repair and improve the infrastructure.

[1187] Step 11:

[1188] The server manages the status of risky areas and shares the progress of the repairs with all users. When the repairs are complete, the information is also notified.

[1189] Specific examples

[1190] 1. User action: The user notices a broken window at the school, takes a photo of it, and writes the comment "The window at the school is broken and it is very dangerous."

[1191] 2. Server processing: The server receives the photo and comments, stores them in a database, and then inputs the comments into an emotion engine to analyze the emotion. For example, an emotional state of "very dangerous" is identified.

[1192] 3. Adding emotion data: The server adds the emotion data returned from the emotion engine to the AI ​​analysis queue along with the original data.

[1193] 4. AI model analysis: The AI ​​model analyzes the photo and emotion data to identify risk details such as "Risk level: Very high" and "High probability of injury from broken window glass."

[1194] 5. Generation of safety measures: Based on the analysis results, the server generates safety measures such as "carry out emergency window glass replacement work" and notifies all users.

[1195] 6. Crowdfunding: If necessary, the server will start the crowdfunding and send the link to all users.

[1196] 7. Sharing of repair status: When the window glass replacement work is completed, the information is shared with all users.

[1197] Example 2

[1198] 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."

[1199] Conventional infrastructure risk management systems typically assess risk levels and determine safety measures based solely on user reports. However, these systems do not adequately consider user sentiment or the level of urgency, which can delay emergency measures. Furthermore, limited means of effective crowdfunding make it difficult to raise funds quickly.

[1200] 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.

[1201] In this invention, the server includes a means for uploading photos and comments taken by users of risky areas of infrastructure, a means for storing the photos and comments received by the server in a database and performing sentiment analysis of the comments using an emotion engine, a means for an AI model to analyze the photos, comments, and emotion data to identify the risk level and risk details and generate safety measure proposals, and a means for the server to notify all users of the generated safety measure proposals and start crowdfunding as necessary. This enables rapid risk assessment and generation of countermeasure proposals that take user sentiment into consideration, as well as more effective fundraising through crowdfunding.

[1202] "User" refers to a person who discovers risk areas in the infrastructure and reports that information to the system.

[1203] "Infrastructure" refers to facilities and structures that provide public convenience and safety, and specifically includes roads, bridges, parks, schools, etc.

[1204] "Risk points" refer to parts or conditions in infrastructure that have the potential to cause accidents or damage.

[1205] "Photo" refers to an image that a user visually records of a risk location.

[1206] "Comment" refers to an explanatory text entered by the user about the details and circumstances of the risk area.

[1207] "Upload" refers to the act of a user sending photos and comments from their own device to a server.

[1208] "Server" refers to a computer system that processes and stores data received from users.

[1209] "Database" refers to an information management system that efficiently stores and manages photos and comments received by the server.

[1210] "Emotion engine" refers to software that analyzes and identifies the emotional state of a user's comments.

[1211] "Sentiment analysis" refers to the process of using an emotion engine to read emotions from user comments.

[1212] "AI model" refers to an artificial intelligence algorithm that analyzes photos, comments, and sentiment data to identify risk levels and risk details.

[1213] "Risk level" refers to the severity of the risk identified by the AI ​​model.

[1214] "Risk details" refers to specific information about the risks identified by the AI ​​model.

[1215] "Safety measures plan" refers to a specific action plan for reducing risk that is generated by the server based on risk information.

[1216] "Notification" refers to a means of communicating information to all users about the safety measures that have been created.

[1217] "Crowdfunding" refers to the act of soliciting donations from users and related parties in order to raise the funds necessary to implement proposed safety measures.

[1218] "Link" refers to the URL for accessing the crowdfunding page.

[1219] "Remediation status" refers to the progress of remediation work on reported risk areas.

[1220] The present invention is a system that collects risk information about infrastructure that users use on a daily basis and combines an emotion engine and an AI model. This system is designed to achieve rapid risk response and adjust the urgency level taking into account the user's emotions. An embodiment of this system is described in detail below.

[1221] User-generated and uploaded risk information

[1222] When a user discovers a risky area, they take a photo of the area using a device such as a smartphone or PC. Next, the user launches a dedicated application (e.g., "Risk Report App") and enters a comment explaining the details of the risk along with the photo. The data is then sent to the server.

[1223] For example, if a user discovers a fallen tree in a park, they can take a photo of the tree on the spot and send it with a comment such as, "There's a fallen tree. It's very dangerous."

[1224] Data reception and storage by the server

[1225] The server receives the photos and comments sent by users. The received data is stored in a "risk management database." The database efficiently manages information such as photos and comments and stores the data for later analysis.

[1226] Emotion recognition by emotion engine

[1227] The server inputs the comments received from the user into an emotion engine (e.g., "Emotion AI") to analyze the user's emotions. The emotion engine identifies the user's emotional state (e.g., "very dangerous") from the user's comments. The emotional state is used to adjust the urgency of the risk level.

[1228] Data analysis using AI models

[1229] The server adds the photos, comments, and emotion data stored in the database to an AI analysis queue, which then analyzes them using an AI model (e.g., the "Risk Assessment AI Model"). The AI ​​model identifies the risk level and risk details based on the input data. For example, it generates analysis results such as "Risk level: Very high" and "Fallen trees in the park may pose a serious danger."

[1230] Generate safety measures

[1231] The server generates safety measures based on the risk information identified by the AI ​​model. The safety measures include specific action plans and methods, such as "carry out emergency tree removal work." Furthermore, the server takes into account the user's emotional data to adjust the urgency and optimize the measures.

[1232] User notification and crowdfunding

[1233] The server notifies all users of the generated safety measures. Users can check the measures through the application. If necessary, the server also notifies all users of a link to start crowdfunding and collect funds from users and related parties. The crowdfunding page contains risk information and details of the measures, and funders can make donations through the page.

[1234] Sharing the status of corrections

[1235] The server manages the repair status of risk areas reported by users and shares the progress with all users. This allows users to check the progress of repairs in real time and understand how the risk areas they reported are being addressed. For example, when the removal of fallen trees is completed, that information is notified to all users.

[1236] Specific examples

[1237] Specific examples are shown below.

[1238] 1. User action: A user notices a broken window at a nearby school, takes a photo of it, and writes the comment "The window at my school is broken and it's very dangerous."

[1239] 2. Server processing: The server receives the photo and comments, stores them in a database, and then inputs the comments into an emotion engine to analyze the emotion. For example, an emotional state of "very dangerous" is identified.

[1240] 3. AI model analysis: The AI ​​model analyzes the photo and emotion data to identify risk details such as "Risk level: Very high" and "High probability of injury from broken window glass."

[1241] 4. Generation of safety measures: Based on the analysis results, the server generates safety measures such as "carry out emergency window glass replacement work" and notifies all users.

[1242] 5. Crowdfunding: If necessary, the server will start the crowdfunding and send the link to all users.

[1243] 6. Sharing of repair status: When the window glass replacement work is completed, the information is shared with all users.

[1244] The above is an embodiment of the present invention. This system enables infrastructure safety measures to be implemented quickly while taking into account user emotions, and risk management can be performed efficiently and effectively by taking appropriate measures.

[1245] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1246] Step 1:

[1247] User-generated and uploaded risk information

[1248] How it works: The user takes a photo of a risky area in the infrastructure (e.g., a fallen tree, a broken window) using a smartphone or computer.

[1249] Input: Photo and risk comment.

[1250] Data processing: The user launches a dedicated application and inputs the photograph they took and a comment detailing the risk (e.g., "There is a fallen tree. It is very dangerous."). The application then packages this data.

[1251] Output: Packaged photo and comment data.

[1252] Step 2:

[1253] Data reception and storage by the server

[1254] Operation: The server receives packaged data sent by the user.

[1255] Input: User uploaded photo and comment data.

[1256] Data processing: The server stores the received data in the "risk management database."

[1257] Output: Photo and comment data stored in a database.

[1258] Step 3:

[1259] Emotion analysis of comments using an emotion engine

[1260] How it works: The server inputs the saved comments into the emotion engine for analysis.

[1261] Input: Comments stored in the database.

[1262] Data processing: An emotion engine (e.g., "Emotion AI") analyzes and identifies the user's emotional state (e.g., "very dangerous") from the comments.

[1263] Output: Identified emotional state data.

[1264] Step 4:

[1265] Analyzing risk data with AI models

[1266] How it works: The server adds the photo, comment, and emotion data to the AI ​​analysis queue and analyzes it using the AI ​​model.

[1267] Input: photos, comments, and emotion data.

[1268] Data processing: An AI model (e.g., a "risk assessment AI model") uses this data to identify risk levels and risk details, generating analysis results such as "Risk level: Very high" and "Falling trees in the park could pose a serious risk."

[1269] Output: Risk level and risk details data.

[1270] Step 5:

[1271] Server-generated safety measures

[1272] How it works: The server generates safety measures based on the risk information identified by the AI ​​model.

[1273] Input: Risk level and risk details data.

[1274] Data processing: The server generates safety measures (e.g., "Implement emergency tree removal work") and adjusts the urgency of the measures based on the user's emotional data.

[1275] Output: Generated safety measures.

[1276] Step 6:

[1277] Notification of proposed security measures by the server and start of crowdfunding

[1278] Action: The server notifies all users of the generated security plan.

[1279] Input: Generated safety plan.

[1280] Data processing: Generate a notification message and push it to all users via the application. If necessary, the server will start the crowdfunding campaign and notify all users of the link.

[1281] Output: Notification message and crowdfunding link.

[1282] Step 7:

[1283] Server sharing of revision status

[1284] How it works: The server manages the progress of fixing risk areas reported by users and shares the progress with all users.

[1285] Input: Risk location correction status data.

[1286] Data processing: Updates the management database of the correction status and generates messages that visualize the correction status.

[1287] Output: A message informing you of the fix status.

[1288] (Application example 2)

[1289] 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."

[1290] Currently, many factories place importance on safety management, but the speed from risk detection to response is often slow. Furthermore, on-site workers often find it difficult to accurately judge the seriousness of risks, as the method for reporting risk information is complicated. Furthermore, risk management does not take into account the emotions of workers, and the inability to take appropriate measures increases the risk of accidents and malfunctions. The purpose of this invention is to solve these problems and ensure efficient and rapid safety management within factories.

[1291] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a means for a user to take a photo of a risky location in the infrastructure, enter a comment, and upload it; a means for the server to store the received photo and comment in a database and add it to an AI analysis queue; a means for analyzing the emotion of the comment using an emotion engine; a means for an AI model to analyze the photo and emotion data to identify the risk level and risk details and generate a safety measure plan; a means for the server to notify the user of the generated safety measure plan and start crowdfunding as necessary; and a means for sharing the progress of the safety measure plan with all users. This makes it possible to quickly and accurately analyze risk information within a factory and implement safety measures that take emotions into consideration.

[1292] A "user" is an individual or organization that provides information by discovering risk areas in the infrastructure, taking photos, and adding comments.

[1293] "Server" means a central processing unit for storing and analyzing data received from users, and generating and notifying security measures.

[1294] "Photographs" are image data that visually record risk areas in infrastructure.

[1295] "Comment" is text information that allows the user to add an explanation about the risky part.

[1296] The "database" is a system that efficiently stores information such as received photos and comments, and allows for searching and analysis.

[1297] The "AI analysis queue" is a collection of received data that is waiting to be analyzed by AI in sequence.

[1298] An "emotion engine" is software or a system for identifying emotions from user comments and analyzing their emotional state.

[1299] The "AI model" is an analytical model that uses machine learning or deep learning to identify risk levels and risk details based on received photo and emotion data.

[1300] The "risk level" is an index that indicates the urgency and severity of the risk to the analyzed infrastructure.

[1301] "Risk details" is information that indicates the specific content and scope of impact of the identified risk.

[1302] "Safety measures" are specific countermeasures and action plans to be taken in response to identified risks.

[1303] "Crowdfunding" is a system that widely solicits donors via the Internet in order to raise the funds needed to address risks.

[1304] "Progress" is information that indicates how much progress has been made in correcting risk areas and taking countermeasures.

[1305] This invention is a system for efficient and rapid safety management within factories. This system allows users to take photos of risky areas in infrastructure and send their comments to a server, which then analyzes the data, generates safety measures, and notifies the user. It also includes a function to set up a crowdfunding link as needed and share the progress of correcting risky areas.

[1306] Hardware and software used

[1307] Hardware: Smartphones, smart glasses, PCs, servers

[1308] Software: Google Speech-to-Text API, Hugging Face Transformers (sentiment analysis), TensorFlow or PyTorch (AI model analysis), cloud database system

[1309] Data collection and transmission

[1310] A user (factory worker) uses a smartphone or smart glasses to take a photo of a risky area. For example, if a user discovers a wall that is about to collapse in the factory, they take a photo of it. The user then adds a comment about the risky area by voice or text input. For example, "The wall at the work site is about to collapse. It is very dangerous." Once the photo and comment are prepared, the user sends the data to the server through a dedicated application.

[1311] Data storage and analysis

[1312] The server receives photos and comments sent by users and stores them in a cloud database. It then inputs the comments into an emotion engine (Hugging Face Transformers) to analyze the emotion. For example, it identifies an emotional state such as "very dangerous." After the emotion is identified, the server adds all data, including the emotion data, to an AI analysis queue and analyzes it using an AI model (TensorFlow or PyTorch). The AI ​​model identifies the risk level and risk details based on the photo and emotion data.

[1313] Creation and notification of safety measures

[1314] The server generates specific safety measures based on the results of the AI ​​analysis. For example, it might suggest "dispatch an emergency response team and immediately begin repair work." Based on this, it notifies users and, if necessary, sets up a crowdfunding link and notifies all users. Through this link, donors can provide the funds needed for the countermeasures.

[1315] Share your progress

[1316] The server also has a function to share the progress of risk-point repairs with all users, allowing users to check the progress of countermeasures in real time. For example, when repair work is completed, the information can be notified to all users, allowing them to always be aware of the latest status.

[1317] Example prompt

[1318] Please analyze the risk information for the infrastructure that has been commented as "very dangerous" and provide the risk level and details.

[1319] This invention makes it possible to quickly and accurately analyze risk information within a factory and implement safety measures that take emotions into account, which is expected to ensure the safety of factory workers and improve operational efficiency.

[1320] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1321] Step 1:

[1322] The user takes a photo of a risky area of ​​infrastructure using a smartphone or smart glasses. The user adds a comment about the risk along with the photo by voice input or text input. For example, "This wall is about to collapse and is very dangerous." The input is photo data and comment data, and the output is a set of these data. Specifically, the system works by taking a photo using the device camera and adding a comment using the voice input function.

[1323] Step 2:

[1324] The user launches the dedicated application and sends the photos and comments they have taken to the server. The input is a set of photo data and comment data, and the output is the data sent to the server. Specifically, the user clicks the send button in the application to upload the data to the server via the Internet.

[1325] Step 3:

[1326] The server stores the received photos and comments in a cloud database. The input is the photo data and comment data sent to the server, and the output is the data stored in the cloud database. The specific operation is to use the server's storage system to store the data.

[1327] Step 4:

[1328] The server inputs the saved comment data into an emotion engine (Hugging Face Transformers) to analyze emotions. The input is comment data, and the output is data indicating the emotional state (e.g., "very dangerous"). Specifically, the emotion engine is called and the comment is analyzed using natural language processing techniques.

[1329] Step 5:

[1330] The server adds all data, including emotional state data, to an AI analysis queue and analyzes it using an AI model (TensorFlow or PyTorch). The input is photo data and emotional state data, and the output is data indicating risk level and risk details. Specifically, the AI ​​model is executed and the data is analyzed using a deep learning algorithm.

[1331] Step 6:

[1332] The server generates safety measures based on the results of the AI ​​analysis. The input is risk level data and detailed risk data, and the output is specific safety measures (e.g., "Dispatch an emergency response team and immediately begin repair work"). Specific operations involve generating appropriate measures using a predefined algorithm.

[1333] Step 7:

[1334] The server notifies the user of the generated security measure plan and sets a crowdfunding link if necessary. This link is notified to all users. The input is the security measure plan data and the crowdfunding link data, and the output is the notification data sent to the user. Specifically, the server's notification system is used to send the security measure plan and link to the user.

[1335] Step 8:

[1336] The server shares the progress of risky part repairs with all users in real time. The input is repair progress data, and the output is progress notification data for all users. Specifically, the server retrieves the progress from the database and shares it with users using the notification system.

[1337] 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.

[1338] 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.

[1339] 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.

[1340] [Fourth embodiment]

[1341] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1342] 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.

[1343] 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).

[1344] 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.

[1345] 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.

[1346] 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).

[1347] 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.

[1348] 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.

[1349] 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.

[1350] 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.

[1351] 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.

[1352] 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.

[1353] 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."

[1354] The present invention is a system that generates safety measures by collecting risk information related to infrastructure that users use on a daily basis and analyzing it using AI. Below, an embodiment of the present invention will be described in natural language.

[1355] User-generated and uploaded risk information

[1356] When a user discovers a risky area in infrastructure, they take a photo of the area and upload it to the application using a device such as a smartphone or computer. The user also enters a brief comment for the photo, explaining the details of the risk. For example, if a user discovers a large crack in the road, they can take a photo of the crack and enter a comment such as, "There is a large crack. It looks like it could cause a traffic accident," and submit it to the app.

[1357] Data reception and storage by the server

[1358] The server receives the photos and comments sent by users. The received data is stored in a database by the server. The database is an information management system for managing information such as photos and comments, and can efficiently store and search data for later analysis.

[1359] Data analysis using AI models

[1360] The server adds the information stored in the database to an AI analysis queue, which then analyzes it using the AI ​​model. The AI ​​model uses the received photos and comments as input data to perform a risk analysis. As a result of the analysis, the risk level (e.g., "high") and risk details (e.g., "possibility of a traffic accident due to cracks in the road") are identified.

[1361] Generate safety measures

[1362] The server generates safety measures based on the risk information identified by the AI ​​model. These safety measures include specific action plans and countermeasures, such as suggesting that road repairs are necessary.

[1363] User notification and crowdfunding

[1364] The server notifies all users of the safety measures it has created. Users can check the measures through the application. If necessary, the server will also launch a crowdfunding campaign, set up a link to collect funds from users and other interested parties, and notify all users. The crowdfunding page will contain detailed information about the risks and the measures, and funders can make donations through the page.

[1365] Sharing the status of corrections

[1366] The server manages the repair status of risk areas reported by users and shares it with all users. This allows users to check the progress of repairs in real time and understand how the risk areas they reported are being addressed. For example, when repairs to cracks in a road are completed, that information is notified to all users.

[1367] Specific examples

[1368] Specific examples are shown below.

[1369] 1. User action: A user finds a fallen tree in a nearby park, takes a photo of it, and writes a comment saying, "There is a fallen tree in the park. It may cause injury."

[1370] 2. Server processing: The server receives the photos and comments, stores them in a database, and then adds them to the AI ​​analysis queue.

[1371] 3. AI model analysis: The AI ​​model analyzes the photos and comments to identify risk details such as "Risk level: High" and "Fallen trees in the park pose a risk of injury."

[1372] 4. Generation of safety measures: The server generates safety measures such as "removal of fallen trees is required" and notifies all users.

[1373] 5. Crowdfunding: If necessary, the server will start the crowdfunding and send the link to all users.

[1374] 6. Sharing of correction status: When the fallen tree removal work is completed, the information is shared with all users.

[1375] The present invention makes it possible to quickly identify safety risks in infrastructure and take appropriate measures. Furthermore, funds can be raised through crowdfunding with the cooperation of users, and measures can be implemented with high transparency.

[1376] The processing flow will be explained below.

[1377] Step 1:

[1378] When a user discovers a risky area in the infrastructure, they can take a photo of the area using a device such as a smartphone or computer.

[1379] Step 2:

[1380] The user launches a dedicated application and takes a photo and enters a comment along with it. For example, the user might write, "There's a big crack. It could cause a traffic accident."

[1381] Step 3:

[1382] The device sends the entered photo and comment to the server.

[1383] Step 4:

[1384] The server temporarily stores the received photos and comments in a database.

[1385] Step 5:

[1386] The data stored by the server is added to the AI ​​analysis queue and prepared for analysis.

[1387] Step 6:

[1388] The server passes the photo and comment data from the queue to the AI ​​model and begins analysis.

[1389] Step 7:

[1390] The AI ​​model analyzes the photos and comments to identify risk levels, such as "Risk level: High" and "Risk details: Possibility of traffic accident due to cracks in the road."

[1391] Step 8:

[1392] The server generates safety measures based on the analysis results of the AI ​​model, such as "Road repair work is required."

[1393] Step 9:

[1394] The server notifies all users of the generated safety measures and analysis results.

[1395] Step 10:

[1396] If necessary, the server will set up a crowdfunding campaign and send a link to all users, which will include details of the risks and countermeasures.

[1397] Step 11:

[1398] Users can access the crowdfunding page and provide funds, which are then used to repair and improve infrastructure.

[1399] Step 12:

[1400] The server manages the status of risk fixes and shares the progress with all users. When fixes are complete, the server also notifies users of this information.

[1401] Example 1

[1402] 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."

[1403] Currently, risk management for everyday infrastructure is time-consuming and often results in inappropriate responses. There are also issues with efficient sharing of risk information and methods of fundraising. The present invention aims to solve these problems and provide a system that quickly and effectively identifies infrastructure risks and takes appropriate measures.

[1404] 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.

[1405] In this invention, the server includes means for users to take photos of risky areas in infrastructure they use daily, enter comments, and upload them from their terminals, means for the server to store the photos and comments received in a database and add them to an AI analysis queue, means for preprocessing the generated data and for an AI model to analyze the photos and comments to identify the risk level and details, means for automatically generating safety measure proposals based on the identified risk information, means for the server to notify all users of the generated safety measure proposals and start crowdfunding as necessary, and means for managing and notifying the status of repairs to risky areas. This enables quick and effective identification of infrastructure safety risks and enables highly transparent countermeasures and fundraising.

[1406] "User" refers to anyone who uses the system to report infrastructure risks and upload photos and comments.

[1407] "Infrastructure" refers to structures and systems that support the foundations of society, including roads, parks, bridges, etc.

[1408] "Risk points" refer to locations within infrastructure where potential dangers may exist.

[1409] "Photographing" refers to the operation of using a device to leave a visual record.

[1410] "Comment" refers to text information that a user adds to a photograph they have taken.

[1411] "Terminal" refers to the device that a user uses to access the system, such as a smartphone or PC.

[1412] "Upload" refers to the operation of sending data from a terminal to a server.

[1413] "Server" refers to a computer system for managing and processing data received from users.

[1414] A "database" refers to a system for managing and storing information, allowing photos and comments to be efficiently stored and searched.

[1415] "AI analysis queue" refers to a waiting line structure for sequentially analyzing data.

[1416] "Preprocessing" refers to the operations used to convert data into a format suitable for analysis by an AI model.

[1417] "AI model" refers to software that uses machine learning technology to analyze data and identify risk levels and risk details.

[1418] "Risk Level" refers to a classification that indicates the severity of an identified risk.

[1419] "Risk details" refers to information that explains the specific details of an identified risk.

[1420] "Safety measures" refers to specific action plans and countermeasures to be taken in response to identified risks.

[1421] "Crowdfunding" refers to a method of widely raising funds via the Internet to address infrastructure risks.

[1422] "Link" refers to the URL that allows users to access the crowdfunding page.

[1423] "Notification" refers to the operation of the server sending information to the user and informing them.

[1424] "Remediation status" refers to the progress of the actions and corrections taken against the reported risk areas.

[1425] "Management" refers to monitoring the operational status of the entire system and performing necessary operations.

[1426] The present invention is a system that generates safety measures by collecting risk information related to infrastructure that users use on a daily basis and analyzing it using AI. Below, an embodiment of the present invention will be described in natural language.

[1427] Hardware and Software Configuration

[1428] This system includes the devices used by users (smartphones, PCs, etc.) and servers. The backend system uses a database (e.g., MySQL, PostgreSQL) for data management and a machine learning model (e.g., TensorFlow, PyTorch) for AI analysis.

[1429] User-generated and uploaded risk information

[1430] When a user discovers a risky area in the infrastructure, they take a photo of the area using their smartphone or computer. After taking the photo, they launch a dedicated application, select the photo they took, and upload it to the application. The user then enters a comment for the photo, explaining the details of the risk. The photo and comment data are then sent to the server. For example, if a user discovers a large crack in the road, they might enter a comment such as, "There's a large crack. It looks like it could cause a traffic accident."

[1431] Data reception and storage by the server

[1432] The server receives the photos and comments sent by the user as HTTP requests. The server saves the received photo data in a temporary directory and obtains the file path. At the same time, it saves the comment text and the photo file path in the database. This data is later added to the AI ​​analysis queue.

[1433] Data analysis using AI models

[1434] The server detects when new data is added to the database and adds the data to the AI ​​analysis queue. Before the data is passed to the AI ​​model, the server performs the necessary preprocessing. Specifically, it preprocesses the photo data using an image processing library (e.g., OpenCV) and converts the comment text into a format suitable for the NLP model. The preprocessed data is then input into the AI ​​model to identify the risk level and risk details.

[1435] Creation and notification of safety measures

[1436] Based on the risk information identified by the AI ​​model, the server uses a rule-based engine to generate safety measures. The generated safety measures are stored in a database, and the server then notifies all users of the measures. If necessary, a crowdfunding link is also generated and notified to users.

[1437] Sharing the status of corrections

[1438] The server manages the status of risk corrections and updates it regularly. When the corrections are complete, the information is notified to all users, allowing them to check the status of the corrections in real time.

[1439] Specific examples

[1440] Specific examples are shown below.

[1441] User Action: A user finds a fallen tree in a local park, takes a photo of it, and writes a comment saying, "There is a fallen tree in the park. It could cause injury."

[1442] Server processing: The server receives the photos and comments, stores them in a database, and then adds them to the AI ​​analysis queue.

[1443] AI model analysis: The AI ​​model analyzes photos and comments to identify risk levels such as "high" and risk details such as "falling trees in the park pose a risk of injury."

[1444] Generation of safety measures: The server generates safety measures such as "removal of fallen trees is required" and notifies all users.

[1445] Crowdfunding: The server will start the crowdfunding campaign if necessary and send the link to all users.

[1446] Sharing of repair status: When the fallen tree removal work is completed, the information is shared with all users.

[1447] Example prompts to be input to the generative AI model:

[1448] "There is a fallen tree in the park that could cause injury. Please analyze this risk."

[1449] This will enable rapid and effective identification of infrastructure safety risks and enable appropriate countermeasures and funding.

[1450] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1451] Step 1:

[1452] The user takes a photo of the risky part of the infrastructure, enters a comment, and uploads it from the terminal (input: photo and comment of the risky part of the infrastructure. output: sending the photo and comment).

[1453] Specific behavior:

[1454] Users use a smartphone or computer to take photos of risky areas of infrastructure.

[1455] The user launches the application, selects a photo, and proceeds to the upload screen.

[1456] The user enters a comment and details the risk in the text fields.

[1457] The user clicks the "Send" button to send the photo and comments to the server.

[1458] Step 2:

[1459] The server saves the received photos and comments in a database and adds them to the AI ​​analysis queue (input: sent photo and comment data; output: saved in database and added to queue).

[1460] Specific behavior:

[1461] The server receives an HTTP request from the user, which includes the photo data and comment text.

[1462] The server stores the photo data in a temporary directory and obtains the file path.

[1463] The server saves the comment data and the photo file path as a new record in the database.

[1464] Detects when a new record is saved and adds the data to the AI ​​analysis queue.

[1465] Step 3:

[1466] The server preprocesses the data, and the AI ​​model analyzes the photos and comments to identify risk levels and risk details (input: photos and comments stored in the database; output: risk levels and risk details).

[1467] Specific behavior:

[1468] The server preprocesses the photos and comments stored in the database.

[1469] Use an image processing library (e.g. OpenCV) to convert the photo data into an appropriate format.

[1470] Tokenize text data into a format suitable for natural language processing (NLP) models.

[1471] The server inputs the preprocessed data into the AI ​​model for analysis.

[1472] The AI ​​model analyzes photos and comments to identify risk levels (e.g., "High") and risk details (e.g., "Possibility of traffic accident due to cracks in the road").

[1473] Step 4:

[1474] Based on the identified risk information, the server automatically generates safety measures (input: risk level and risk details; output: safety measures).

[1475] Specific behavior:

[1476] The server receives the risk level and risk details returned by the AI ​​model.

[1477] The server uses a rule-based engine to generate risk-informed safety measures.

[1478] For example, if the risk level is "high," it will suggest that "road repair work is needed."

[1479] The generated safety measures are stored in a database.

[1480] Step 5:

[1481] The server notifies all users of the generated safety measures and initiates crowdfunding if necessary (Input: Safety measures. Output: User notification and crowdfunding link).

[1482] Specific behavior:

[1483] The server prepares a communication method (push notification, email, etc.) to notify all users of the generated safety measures.

[1484] The server forms a notification message and sends it with the content "A new security plan has been generated."

[1485] If necessary, the server generates a link to the crowdfunding page and notifies the user.

[1486] Step 6:

[1487] The server manages and notifies the status of risk corrections (input: correction status information; output: correction completion notification).

[1488] Specific behavior:

[1489] The server periodically checks and updates the status of corrections to risk areas.

[1490] Once the correction is complete, the information is recorded in the database.

[1491] The server sends a completion notification of the modification status to all users.

[1492] Users will receive notifications and can see the corrected infrastructure state on their applications.

[1493] (Application example 1)

[1494] 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."

[1495] There is a need to quickly and accurately identify infrastructure risk information and implement safety measures. Road risk information is particularly essential for autonomous vehicles, and risks must be identified in real time and notified to passengers and operation management systems. However, conventional systems can delay risk identification and notification, threatening safety. Furthermore, smooth funding for risk countermeasures is also necessary, but current methods can lack transparency and efficiency.

[1496] 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.

[1497] In this invention, the server includes: a means for a user to take a photo of a risky location in infrastructure, enter a comment, and upload it; a means for the server to store the received photo and comment in a database and add it to an AI analysis queue; a means for an AI model to analyze the photo and comment to identify the risk level and risk details and generate safety measure proposals; a means for analyzing risk information collected from the camera and LiDAR of the autonomous vehicle in real time; a means for notifying passengers and the operation control system of the analysis results and presenting safety measure proposals; and a means for the server to notify the user of the generated safety measure proposals and start crowdfunding if necessary. This enables autonomous vehicles to detect road risks in real time and quickly take safety measures, enabling highly transparent fundraising through crowdfunding.

[1498] "User" refers to a general user who uses the system to photograph and upload infrastructure risk information.

[1499] "Infrastructure" refers to buildings and structures that provide public conveniences, such as roads, parks, and public facilities.

[1500] "Risk areas" are areas of infrastructure that could pose safety problems, such as cracks, sinkholes, or fallen trees.

[1501] "Photography" refers to the act of recording images or videos of risk areas using a smartphone or camera.

[1502] Entering a "comment" is the act of describing the details and circumstances of the risk area in text format.

[1503] "Uploading" is the act of sending photos, videos, and comments you have taken to a server via the Internet.

[1504] A "server" is a computer system for receiving, storing, analyzing, and distributing data.

[1505] "Database" means an information management system for efficiently storing and managing received photos and comments.

[1506] An "AI analysis queue" is a list of data waiting to be analyzed by an AI model.

[1507] The "AI model" is artificial intelligence software that identifies risk levels and risk details based on photos and comments.

[1508] The "risk level" is an index that indicates the degree of danger of a discovered risk location.

[1509] "Risk details" are descriptions of specific problems or dangers that the risk area may cause.

[1510] "Safety measures proposal" is information that proposes specific action plans and measures to be taken in response to identified risks.

[1511] An "autonomous vehicle camera" is a video recording device installed in an autonomous vehicle to capture road conditions in real time.

[1512] "LiDAR" is a sensor that uses laser light to measure the position and distance of an object with high precision.

[1513] "Real-time" means that the processing from data acquisition to analysis and notification is carried out immediately.

[1514] "Passenger" means a user aboard an automated driving vehicle.

[1515] A "traffic management system" is a system for monitoring and controlling the operation status of autonomous vehicles.

[1516] "Notifying" refers to the act of informing users and operation managers of the analysis results and proposed safety measures.

[1517] "Crowdfunding" is a method of raising funds from multiple internet users.

[1518] The present invention is a system for quickly and accurately identifying risk information for infrastructure and taking safety measures. This system involves a process in which a user reports risk locations, an AI model is used to analyze the risks, and safety measures are generated. Specifically, the system is implemented as follows.

[1519] User-generated and uploaded risk information

[1520] When a user discovers a risky area in infrastructure, they take a photo of the area with their smartphone or camera. They then enter details of the risky area as a comment in text format. For example, if a user discovers a large crack in the road, they can take a photo of the crack, enter a comment such as "There is a large crack. It looks like it could cause a traffic accident," and upload it. Any commonly available smartphone or camera will do.

[1521] Data reception and storage by the server

[1522] The server receives photos and comments sent by users and stores them in a database. The database is an information management system for efficiently managing information such as photos and comments, and allows for quick storage and retrieval of data that will later be added to the AI ​​analysis queue. The software used is a relational database management system such as MySQL.

[1523] Data analysis using AI models

[1524] The server adds the information stored in the database to an AI analysis queue, which then analyzes it using an AI model. The AI ​​model is built using machine learning libraries such as TensorFlow. The AI ​​model performs a risk analysis using the received photos and comments as input data. As a result of the analysis, the risk level (e.g., "high") and risk details (e.g., "possibility of a traffic accident due to cracks in the road") are identified.

[1525] Creation and notification of safety measures

[1526] The server generates safety measures based on the risk information identified by the AI ​​model. The safety measures include specific action plans and countermeasures. For example, it may suggest that road repairs are necessary. The generated safety measures are then notified to all users by the server.

[1527] Crowdfunding

[1528] If necessary, the server will initiate crowdfunding, set up a crowdfunding link, and notify all users. The crowdfunding page will contain detailed information about risks and countermeasures, and funders can make donations through the page.

[1529] Sharing the status of corrections

[1530] The server manages the repair status of risk areas reported by users and shares it with all users. This allows users to check the progress of repairs in real time. For example, when repairs to cracks in a road are completed, that information is notified to all users.

[1531] Risk Management for Autonomous Vehicles

[1532] Real-time data from cameras and LiDAR on autonomous vehicles is sent to a server, where risk information is analyzed using an AI model. This analysis information is then sent to passengers and the operation management system, and safety measures such as changing the driving route are implemented.

[1533] Specific examples

[1534] 1. User action: A user discovers a fallen tree in a nearby park, takes a photo of it, writes a comment saying "There is a fallen tree in the park. It may cause injury," and uploads the photo.

[1535] 2. Server processing: The server receives the photos and comments, stores them in a database, and then adds them to the AI ​​analysis queue.

[1536] 3. AI model analysis: The AI ​​model analyzes the photos and comments to identify risk details such as "Risk level: High" and "Fallen trees in the park pose a risk of injury."

[1537] 4. Generation of safety measures: The server generates safety measures such as "removal of fallen trees is required" and notifies all users.

[1538] 5. Crowdfunding: If necessary, the server will start the crowdfunding and send the link to all users.

[1539] 6. Sharing of correction status: When the fallen tree removal work is completed, the information is shared with all users.

[1540] Example prompts for generative AI models:

[1541] "There is a large crack in the center of the road. It is about 10 cm wide. Please analyze the possibility of this causing a traffic accident."

[1542] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1543] Step 1:

[1544] Input: Users take photos of risky areas in infrastructure using a smartphone or camera, enter details of the risk as comments, and upload the photos and comments they have entered.

[1545] How it works: When a user discovers a risky area in infrastructure, they use their camera to take a photo of the risky area, then enter details of the risk (such as the risk of a crack in the photo) as a text comment, and then press a button to upload the photo and comment using a dedicated application.

[1546] Output: The captured photo and the entered comment data are sent to the server.

[1547] Step 2:

[1548] Input: The server receives the photo and comment submitted by the user.

[1549] Operation: The server receives photos and comment data sent by users through a receiving port. Specifically, the server obtains the data using HTTP requests.

[1550] Output: The received photo and comment data is temporarily stored in local storage and then stored in a database.

[1551] Step 3:

[1552] Input: Retrieve stored photo and comment data from the database.

[1553] How it works: The server uses a database management system to retrieve the stored photo and comment data from the database, using MySQL queries to retrieve the necessary data.

[1554] Output: The retrieved photo and comment data is added to the AI ​​analysis queue to await analysis.

[1555] Step 4:

[1556] Input: Data added to the AI ​​analysis queue awaiting analysis.

[1557] How it works: The server sequentially retrieves data from the AI ​​analysis queue and inputs it into the AI ​​model. The AI ​​model uses neural networks built with TensorFlow and other tools to perform image recognition and text analysis. It identifies risks based on photos and comments, and determines the risk level and risk details.

[1558] Output: The AI ​​model outputs the risk level (e.g., "High") and risk details (e.g., "Possibility of traffic accident due to cracks in the road") as the analysis result.

[1559] Step 5:

[1560] Input: Analysis results from the AI ​​model (risk level and risk details).

[1561] Operation: The server generates safety measures based on the analysis results of the AI ​​model. Specifically, if the risk level is "high," it generates a message suggesting appropriate measures (e.g., "prompt road repairs").

[1562] Output: The generated safety measures are prepared as text data.

[1563] Step 6:

[1564] Input: Generated safety measures.

[1565] Operation: The server notifies all users of this proposed security measure. This can be done via a notification function within the application or by email. A notification is displayed on the client device.

[1566] Output: A notification message that is displayed on the user's terminal.

[1567] Step 7:

[1568] Input: Risk information analyzed by the AI ​​model and generated safety measures.

[1569] Behavior: If necessary, the server will initiate crowdfunding. A crowdfunding page link and information will be generated and posted to all users.

[1570] Output: Crowdfunding page link and notification message.

[1571] Step 8:

[1572] Input: Correction status data.

[1573] How it works: The server manages the repair status of risk areas and shares the progress with all users. When the repair is complete, it notifies all users.

[1574] Output: A message to the user indicating that the fix is ​​complete.

[1575] Examples:

[1576] A user discovers a crack in the road, takes a photo, and enters a comment. The server receives the photo and comment, analyzes it using an AI model, and determines "Risk level: High, Risk details: Possibility of traffic accident due to road crack." It then notifies the user that "Road repair work is required" as a safety measure.

[1577] Example prompts for generative AI models:

[1578] "There is a large crack in the center of the road. It is about 10 cm wide. Please analyze the possibility of this causing a traffic accident."

[1579] 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.

[1580] The present invention is a system that generates safety measures by collecting risk information about infrastructure that users use on a daily basis and analyzing it using AI combined with an emotion engine. This system speeds up responses to risk areas in the infrastructure and adjusts the level of urgency taking into account the user's emotions. Below, an embodiment of the present invention will be described in natural language.

[1581] User-generated and uploaded risk information

[1582] When a user discovers a risky area in infrastructure, they take a photo of the area using a device such as a smartphone or PC. Next, the user launches a dedicated application, enters the photo along with a comment explaining the details of the risk, and sends this data to a server. For example, if a user discovers a fallen tree in a park, they can take a photo of the tree on the spot and enter a comment such as, "There is a fallen tree. It is very dangerous." and send it.

[1583] Data reception and storage by the server

[1584] The server receives the photos and comments sent by users. The received data is stored in a database by the server. The database is an information management system for managing information such as photos and comments, and allows efficient storage and retrieval of data for later analysis.

[1585] Emotion recognition by emotion engine

[1586] The server inputs the comments received from the user into the emotion engine and analyzes the user's emotion. The emotion engine reads the emotion from the user's comment and identifies the emotional state (e.g., "very dangerous"). The emotional state is used to adjust the urgency of the risk level.

[1587] Data analysis using AI models

[1588] The server adds the photos, comments, and emotion data from the emotion engine stored in the database to the AI ​​analysis queue, which then analyzes them using the AI ​​model. The AI ​​model determines the risk level and risk details based on the input data. For example, it generates analysis results such as "Risk level: Very high" and "Fallen trees in the park may pose a serious danger."

[1589] Generate safety measures

[1590] The server generates safety measures based on the risk information identified by the AI ​​model. The safety measures include specific action plans and countermeasure methods, such as "carry out emergency tree removal work." Furthermore, the server takes into account the user's emotional data to adjust the urgency and optimize the measures.

[1591] User notification and crowdfunding

[1592] The server notifies all users of the generated safety measures. Users can check the measures through the application. If necessary, the server also launches a crowdfunding campaign, sets up a link to collect funds from users and related parties, and notifies all users. The crowdfunding page contains risk information and details of the measures, and funders can make donations through the page.

[1593] Sharing the status of corrections

[1594] The server manages the repair status of risk areas reported by users and shares the progress with all users. This allows users to check the progress of repairs in real time and understand how the risk areas they reported are being addressed. For example, when the removal of fallen trees is completed, that information is notified to all users.

[1595] Specific examples

[1596] Specific examples are shown below.

[1597] 1. User action: A user notices a broken window at a nearby school, takes a photo of it, and writes the comment "The window at my school is broken and it's very dangerous."

[1598] 2. Server processing: The server receives the photo and comments, stores them in a database, and then inputs the comments into an emotion engine to analyze the emotion. For example, an emotional state of "very dangerous" is identified.

[1599] 3. AI model analysis: The AI ​​model analyzes the photo and emotion data to identify risk details such as "Risk level: Very high" and "High probability of injury from broken window glass."

[1600] 4. Generation of safety measures: Based on the analysis results, the server generates safety measures such as "carry out emergency window glass replacement work" and notifies all users.

[1601] 5. Crowdfunding: If necessary, the server will start the crowdfunding and send the link to all users.

[1602] 6. Sharing of repair status: When the window glass replacement work is completed, the information is shared with all users.

[1603] The present invention makes it possible to quickly implement infrastructure safety measures that take into account user feelings, and by taking appropriate measures, risks can be managed efficiently and effectively.

[1604] The processing flow will be explained below.

[1605] Step 1:

[1606] When a user discovers a risky area in the infrastructure, they can take a photo of the area using a device such as a smartphone or computer.

[1607] Step 2:

[1608] The user launches a dedicated application and takes a photo and enters a comment detailing the risk. For example, "There is a fallen tree in the park. It is very dangerous."

[1609] Step 3:

[1610] The user sends the completed photo and comment to the server via the application.

[1611] Step 4:

[1612] The server stores the received photos and comments in a database and passes the comments to an emotion engine to analyze the user's emotions.

[1613] Step 5:

[1614] The server receives the emotion data returned by the emotion engine and adds it to the AI ​​analysis queue along with the original data.

[1615] Step 6:

[1616] The server sequentially passes data added to the AI ​​analysis queue to the AI ​​model, which analyzes the risk level and risk details, such as "Risk level: Very high" or "High possibility of injury due to falling trees."

[1617] Step 7:

[1618] The server generates safety measures based on the risk information analyzed by the AI ​​model, such as "implementing emergency tree removal work."

[1619] Step 8:

[1620] The server adjusts the urgency level based on the emotion data and notifies all users of the optimized safety measures, which they can then check through the application.

[1621] Step 9:

[1622] If necessary, the server will set up a crowdfunding campaign and provide a link to all users, which will contain detailed risk information and suggested solutions.

[1623] Step 10:

[1624] Users can access the crowdfunding page and provide funds, which are then used to repair and improve the infrastructure.

[1625] Step 11:

[1626] The server manages the status of risky areas and shares the progress of the repairs with all users. When the repairs are complete, the information is also notified.

[1627] Specific examples

[1628] 1. User action: The user notices a broken window at the school, takes a photo of it, and writes the comment "The window at the school is broken and it is very dangerous."

[1629] 2. Server processing: The server receives the photo and comments, stores them in a database, and then inputs the comments into an emotion engine to analyze the emotion. For example, an emotional state of "very dangerous" is identified.

[1630] 3. Adding emotion data: The server adds the emotion data returned from the emotion engine to the AI ​​analysis queue along with the original data.

[1631] 4. AI model analysis: The AI ​​model analyzes the photo and emotion data to identify risk details such as "Risk level: Very high" and "High probability of injury from broken window glass."

[1632] 5. Generation of safety measures: Based on the analysis results, the server generates safety measures such as "carry out emergency window glass replacement work" and notifies all users.

[1633] 6. Crowdfunding: If necessary, the server will start the crowdfunding and send the link to all users.

[1634] 7. Sharing of repair status: When the window glass replacement work is completed, the information is shared with all users.

[1635] Example 2

[1636] 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."

[1637] Conventional infrastructure risk management systems typically assess risk levels and determine safety measures based solely on user reports. However, these systems do not adequately consider user sentiment or the level of urgency, which can delay emergency measures. Furthermore, limited means of effective crowdfunding make it difficult to raise funds quickly.

[1638] 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.

[1639] In this invention, the server includes a means for uploading photos and comments taken by users of risky areas of infrastructure, a means for storing the photos and comments received by the server in a database and performing sentiment analysis of the comments using an emotion engine, a means for an AI model to analyze the photos, comments, and emotion data to identify the risk level and risk details and generate safety measure proposals, and a means for the server to notify all users of the generated safety measure proposals and start crowdfunding as necessary. This enables rapid risk assessment and generation of countermeasure proposals that take user sentiment into consideration, as well as more effective fundraising through crowdfunding.

[1640] "User" refers to a person who discovers risk areas in the infrastructure and reports that information to the system.

[1641] "Infrastructure" refers to facilities and structures that provide public convenience and safety, and specifically includes roads, bridges, parks, schools, etc.

[1642] "Risk points" refer to parts or conditions in infrastructure that have the potential to cause accidents or damage.

[1643] "Photo" refers to an image that a user visually records of a risk location.

[1644] "Comment" refers to an explanatory text entered by the user about the details and circumstances of the risk area.

[1645] "Upload" refers to the act of a user sending photos and comments from their own device to a server.

[1646] "Server" refers to a computer system that processes and stores data received from users.

[1647] "Database" refers to an information management system that efficiently stores and manages photos and comments received by the server.

[1648] "Emotion engine" refers to software that analyzes and identifies the emotional state of a user's comments.

[1649] "Sentiment analysis" refers to the process of using an emotion engine to read emotions from user comments.

[1650] "AI model" refers to an artificial intelligence algorithm that analyzes photos, comments, and sentiment data to identify risk levels and risk details.

[1651] "Risk level" refers to the severity of the risk identified by the AI ​​model.

[1652] "Risk details" refers to specific information about the risks identified by the AI ​​model.

[1653] "Safety measures plan" refers to a specific action plan for reducing risk that is generated by the server based on risk information.

[1654] "Notification" refers to a means of communicating information to all users about the safety measures that have been created.

[1655] "Crowdfunding" refers to the act of soliciting donations from users and related parties in order to raise the funds necessary to implement proposed safety measures.

[1656] "Link" refers to the URL for accessing the crowdfunding page.

[1657] "Remediation status" refers to the progress of remediation work on reported risk areas.

[1658] The present invention is a system that collects risk information about infrastructure that users use on a daily basis and combines an emotion engine and an AI model. This system is designed to achieve rapid risk response and adjust the urgency level taking into account the user's emotions. An embodiment of this system is described in detail below.

[1659] User-generated and uploaded risk information

[1660] When a user discovers a risky area, they take a photo of the area using a device such as a smartphone or PC. Next, the user launches a dedicated application (e.g., "Risk Report App") and enters a comment explaining the details of the risk along with the photo. The data is then sent to the server.

[1661] For example, if a user discovers a fallen tree in a park, they can take a photo of the tree on the spot and send it with a comment such as, "There's a fallen tree. It's very dangerous."

[1662] Data reception and storage by the server

[1663] The server receives the photos and comments sent by users. The received data is stored in a "risk management database." The database efficiently manages information such as photos and comments and stores the data for later analysis.

[1664] Emotion recognition by emotion engine

[1665] The server inputs the comments received from the user into an emotion engine (e.g., "Emotion AI") to analyze the user's emotions. The emotion engine identifies the user's emotional state (e.g., "very dangerous") from the user's comments. The emotional state is used to adjust the urgency of the risk level.

[1666] Data analysis using AI models

[1667] The server adds the photos, comments, and emotion data stored in the database to an AI analysis queue, which then analyzes them using an AI model (e.g., the "Risk Assessment AI Model"). The AI ​​model identifies the risk level and risk details based on the input data. For example, it generates analysis results such as "Risk level: Very high" and "Fallen trees in the park may pose a serious danger."

[1668] Generate safety measures

[1669] The server generates safety measures based on the risk information identified by the AI ​​model. The safety measures include specific action plans and methods, such as "carry out emergency tree removal work." Furthermore, the server takes into account the user's emotional data to adjust the urgency and optimize the measures.

[1670] User notification and crowdfunding

[1671] The server notifies all users of the generated safety measures. Users can check the measures through the application. If necessary, the server also notifies all users of a link to start crowdfunding and collect funds from users and related parties. The crowdfunding page contains risk information and details of the measures, and funders can make donations through the page.

[1672] Sharing the status of corrections

[1673] The server manages the repair status of risk areas reported by users and shares the progress with all users. This allows users to check the progress of repairs in real time and understand how the risk areas they reported are being addressed. For example, when the removal of fallen trees is completed, that information is notified to all users.

[1674] Specific examples

[1675] Specific examples are shown below.

[1676] 1. User action: A user notices a broken window at a nearby school, takes a photo of it, and writes the comment "The window at my school is broken and it's very dangerous."

[1677] 2. Server processing: The server receives the photo and comments, stores them in a database, and then inputs the comments into an emotion engine to analyze the emotion. For example, an emotional state of "very dangerous" is identified.

[1678] 3. AI model analysis: The AI ​​model analyzes the photo and emotion data to identify risk details such as "Risk level: Very high" and "High probability of injury from broken window glass."

[1679] 4. Generation of safety measures: Based on the analysis results, the server generates safety measures such as "carry out emergency window glass replacement work" and notifies all users.

[1680] 5. Crowdfunding: If necessary, the server will start the crowdfunding and send the link to all users.

[1681] 6. Sharing of repair status: When the window glass replacement work is completed, the information is shared with all users.

[1682] The above is an embodiment of the present invention. This system enables infrastructure safety measures to be implemented quickly while taking into account user emotions, and risk management can be performed efficiently and effectively by taking appropriate measures.

[1683] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1684] Step 1:

[1685] User-generated and uploaded risk information

[1686] How it works: The user takes a photo of a risky area in the infrastructure (e.g., a fallen tree, a broken window) using a smartphone or computer.

[1687] Input: Photo and risk comment.

[1688] Data processing: The user launches a dedicated application and inputs the photograph they took and a comment detailing the risk (e.g., "There is a fallen tree. It is very dangerous."). The application then packages this data.

[1689] Output: Packaged photo and comment data.

[1690] Step 2:

[1691] Data reception and storage by the server

[1692] Operation: The server receives packaged data sent by the user.

[1693] Input: User uploaded photo and comment data.

[1694] Data processing: The server stores the received data in the "risk management database."

[1695] Output: Photo and comment data stored in a database.

[1696] Step 3:

[1697] Emotion analysis of comments using an emotion engine

[1698] How it works: The server inputs the saved comments into the emotion engine for analysis.

[1699] Input: Comments stored in the database.

[1700] Data processing: An emotion engine (e.g., "Emotion AI") analyzes and identifies the user's emotional state (e.g., "very dangerous") from the comments.

[1701] Output: Identified emotional state data.

[1702] Step 4:

[1703] Analyzing risk data with AI models

[1704] How it works: The server adds the photo, comment, and emotion data to the AI ​​analysis queue and analyzes it using the AI ​​model.

[1705] Input: photos, comments, and emotion data.

[1706] Data processing: An AI model (e.g., a "risk assessment AI model") uses this data to identify risk levels and risk details, generating analysis results such as "Risk level: Very high" and "Falling trees in the park could pose a serious risk."

[1707] Output: Risk level and risk details data.

[1708] Step 5:

[1709] Server-generated safety measures

[1710] How it works: The server generates safety measures based on the risk information identified by the AI ​​model.

[1711] Input: Risk level and risk details data.

[1712] Data processing: The server generates safety measures (e.g., "Implement emergency tree removal work") and adjusts the urgency of the measures based on the user's emotional data.

[1713] Output: Generated safety measures.

[1714] Step 6:

[1715] Notification of proposed security measures by the server and start of crowdfunding

[1716] Action: The server notifies all users of the generated security plan.

[1717] Input: Generated safety plan.

[1718] Data processing: Generate a notification message and push it to all users via the application. If necessary, the server will start the crowdfunding campaign and notify all users of the link.

[1719] Output: Notification message and crowdfunding link.

[1720] Step 7:

[1721] Server sharing of revision status

[1722] How it works: The server manages the progress of fixing risk areas reported by users and shares the progress with all users.

[1723] Input: Risk location correction status data.

[1724] Data processing: Updates the management database of the correction status and generates messages that visualize the correction status.

[1725] Output: A message informing you of the fix status.

[1726] (Application example 2)

[1727] 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."

[1728] Currently, many factories place importance on safety management, but the speed from risk detection to response is often slow. Furthermore, on-site workers often find it difficult to accurately judge the seriousness of risks, as the method for reporting risk information is complicated. Furthermore, risk management does not take into account the emotions of workers, and the inability to take appropriate measures increases the risk of accidents and malfunctions. The purpose of this invention is to solve these problems and ensure efficient and rapid safety management within factories.

[1729] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a means for a user to take a photo of a risky location in the infrastructure, enter a comment, and upload it; a means for the server to store the received photo and comment in a database and add it to an AI analysis queue; a means for analyzing the emotion of the comment using an emotion engine; a means for an AI model to analyze the photo and emotion data to identify the risk level and risk details and generate a safety measure plan; a means for the server to notify the user of the generated safety measure plan and start crowdfunding as necessary; and a means for sharing the progress of the safety measure plan with all users. This makes it possible to quickly and accurately analyze risk information within a factory and implement safety measures that take emotions into consideration.

[1730] A "user" is an individual or organization that provides information by discovering risk areas in the infrastructure, taking photos, and adding comments.

[1731] "Server" means a central processing unit for storing and analyzing data received from users, and generating and notifying security measures.

[1732] "Photographs" are image data that visually record risk areas in infrastructure.

[1733] "Comment" is text information that allows the user to add an explanation about the risky part.

[1734] The "database" is a system that efficiently stores information such as received photos and comments, and allows for searching and analysis.

[1735] The "AI analysis queue" is a collection of received data that is waiting to be analyzed by AI in sequence.

[1736] An "emotion engine" is software or a system for identifying emotions from user comments and analyzing their emotional state.

[1737] The "AI model" is an analytical model that uses machine learning or deep learning to identify risk levels and risk details based on received photo and emotion data.

[1738] The "risk level" is an index that indicates the urgency and severity of the risk to the analyzed infrastructure.

[1739] "Risk details" is information that indicates the specific content and scope of impact of the identified risk.

[1740] "Safety measures" are specific countermeasures and action plans to be taken in response to identified risks.

[1741] "Crowdfunding" is a system that widely solicits donors via the Internet in order to raise the funds needed to address risks.

[1742] "Progress" is information that indicates how much progress has been made in correcting risk areas and taking countermeasures.

[1743] This invention is a system for efficient and rapid safety management within factories. This system allows users to take photos of risky areas in infrastructure and send their comments to a server, which then analyzes the data, generates safety measures, and notifies the user. It also includes a function to set up a crowdfunding link as needed and share the progress of correcting risky areas.

[1744] Hardware and software used

[1745] Hardware: Smartphones, smart glasses, PCs, servers

[1746] Software: Google Speech-to-Text API, Hugging Face Transformers (sentiment analysis), TensorFlow or PyTorch (AI model analysis), cloud database system

[1747] Data collection and transmission

[1748] A user (factory worker) uses a smartphone or smart glasses to take a photo of a risky area. For example, if a user discovers a wall that is about to collapse in the factory, they take a photo of it. The user then adds a comment about the risky area by voice or text input. For example, "The wall at the work site is about to collapse. It is very dangerous." Once the photo and comment are prepared, the user sends the data to the server through a dedicated application.

[1749] Data storage and analysis

[1750] The server receives photos and comments sent by users and stores them in a cloud database. It then inputs the comments into an emotion engine (Hugging Face Transformers) to analyze the emotion. For example, it identifies an emotional state such as "very dangerous." After the emotion is identified, the server adds all data, including the emotion data, to an AI analysis queue and analyzes it using an AI model (TensorFlow or PyTorch). The AI ​​model identifies the risk level and risk details based on the photo and emotion data.

[1751] Creation and notification of safety measures

[1752] The server generates specific safety measures based on the results of the AI ​​analysis. For example, it might suggest "dispatch an emergency response team and immediately begin repair work." Based on this, it notifies users and, if necessary, sets up a crowdfunding link and notifies all users. Through this link, donors can provide the funds needed for the countermeasures.

[1753] Share your progress

[1754] The server also has a function to share the progress of risk-point repairs with all users, allowing users to check the progress of countermeasures in real time. For example, when repair work is completed, the information can be notified to all users, allowing them to always be aware of the latest status.

[1755] Example prompt

[1756] Please analyze the risk information for the infrastructure that has been commented as "very dangerous" and provide the risk level and details.

[1757] This invention makes it possible to quickly and accurately analyze risk information within a factory and implement safety measures that take emotions into account, which is expected to ensure the safety of factory workers and improve operational efficiency.

[1758] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1759] Step 1:

[1760] The user takes a photo of a risky area of ​​infrastructure using a smartphone or smart glasses. The user adds a comment about the risk along with the photo by voice input or text input. For example, "This wall is about to collapse and is very dangerous." The input is photo data and comment data, and the output is a set of these data. Specifically, the system works by taking a photo using the device camera and adding a comment using the voice input function.

[1761] Step 2:

[1762] The user launches the dedicated application and sends the photos and comments they have taken to the server. The input is a set of photo data and comment data, and the output is the data sent to the server. Specifically, the user clicks the send button in the application to upload the data to the server via the Internet.

[1763] Step 3:

[1764] The server stores the received photos and comments in a cloud database. The input is the photo data and comment data sent to the server, and the output is the data stored in the cloud database. The specific operation is to use the server's storage system to store the data.

[1765] Step 4:

[1766] The server inputs the saved comment data into an emotion engine (Hugging Face Transformers) to analyze emotions. The input is comment data, and the output is data indicating the emotional state (e.g., "very dangerous"). Specifically, the emotion engine is called and the comment is analyzed using natural language processing techniques.

[1767] Step 5:

[1768] The server adds all data, including emotional state data, to an AI analysis queue and analyzes it using an AI model (TensorFlow or PyTorch). The input is photo data and emotional state data, and the output is data indicating risk level and risk details. Specifically, the AI ​​model is executed and the data is analyzed using a deep learning algorithm.

[1769] Step 6:

[1770] The server generates safety measures based on the results of the AI ​​analysis. The input is risk level data and detailed risk data, and the output is specific safety measures (e.g., "Dispatch an emergency response team and immediately begin repair work"). Specific operations involve generating appropriate measures using a predefined algorithm.

[1771] Step 7:

[1772] The server notifies the user of the generated security measure plan and sets a crowdfunding link if necessary. This link is notified to all users. The input is the security measure plan data and the crowdfunding link data, and the output is the notification data sent to the user. Specifically, the server's notification system is used to send the security measure plan and link to the user.

[1773] Step 8:

[1774] The server shares the progress of risky part repairs with all users in real time. The input is repair progress data, and the output is progress notification data for all users. Specifically, the server retrieves the progress from the database and shares it with users using the notification system.

[1775] 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.

[1776] 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.

[1777] 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.

[1778] 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.

[1779] 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.

[1780] 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.

[1781] 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).

[1782] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1783] 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."

[1784] 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.

[1785] 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).

[1786] 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.

[1787] 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.

[1788] 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.

[1789] 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.

[1790] 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.

[1791] 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.

[1792] 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.

[1793] 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.

[1794] 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.

[1795] 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.

[1796] The following is further disclosed regarding the above embodiment.

[1797] (Claim 1)

[1798] A means for users to take photos of risky areas of infrastructure, enter comments, and upload them.

[1799] The server stores the received photos and comments in a database and adds them to the AI ​​analysis queue.

[1800] The AI ​​model analyzes photos and comments to identify risk levels and details, and generates safety measures.

[1801] A means for the server to notify the user of the generated safety measures and start crowdfunding if necessary;

[1802] A system including:

[1803] (Claim 2)

[1804] The system of claim 1, further comprising means for automatically implementing safety measures based on the risk information analyzed by the AI ​​model.

[1805] (Claim 3)

[1806] 10. The system of claim 1, further comprising means for the server to set up a crowdfunding link and notify all users.

[1807] (Claim 4)

[1808] 2. The system according to claim 1, further comprising means for the server to share with the user the status of correction of the risk portion reported by the user.

[1809] "Example 1"

[1810] (Claim 1)

[1811] A method for users to take photos of risky areas in the infrastructure they use on a daily basis, enter comments, and upload them from their devices.

[1812] The server stores the received photos and comments in a database and adds them to the AI ​​analysis queue.

[1813] A means to pre-process the generated data and allow AI models to analyze photos and comments to identify risk levels and risk details;

[1814] A means for automatically generating safety measures based on the identified risk information;

[1815] The server notifies all users of the generated safety measures and initiates crowdfunding if necessary.

[1816] A means of managing and communicating the status of risk remediation;

[1817] A system including:

[1818] (Claim 2)

[1819] The system of claim 1, which automatically implements safety measures based on risk information analyzed by the AI ​​model.

[1820] (Claim 3)

[1821] The system according to claim 1, wherein the server sets up a crowdfunding link and notifies all users.

[1822] "Application Example 1"

[1823] (Claim 1)

[1824] A means for users to take photos of risky areas of infrastructure, enter comments, and upload them.

[1825] The server stores the received photos and comments in a database and adds them to the AI ​​analysis queue.

[1826] The AI ​​model analyzes photos and comments to identify risk levels and details, and generates safety measures.

[1827] A means of analyzing risk information collected from cameras and LiDAR in autonomous vehicles in real time,

[1828] A means of notifying passengers and operation control systems of the analysis results and presenting safety measures,

[1829] A means for the server to notify the user of the generated safety measures and start crowdfunding if necessary;

[1830] A system including:

[1831] (Claim 2)

[1832] The system of claim 1, further comprising means for automatically implementing safety measures based on the risk information analyzed by the AI ​​model.

[1833] (Claim 3)

[1834] 10. The system of claim 1, further comprising means for the server to set up a crowdfunding link and notify all users.

[1835] "Example 2: Combining Emotion Engines"

[1836] (Claim 1)

[1837] A means for users to upload photos and comments of risk areas of infrastructure they have taken;

[1838] A means for storing the photos and comments received by the server in a database and performing emotion analysis of the comments using an emotion engine;

[1839] A means by which an AI model analyzes photos, comments, and sentiment data to identify risk levels and risk details and generate safety recommendations; and

[1840] The server notifies all users of the generated safety measures and initiates crowdfunding if necessary.

[1841] A system including:

[1842] (Claim 2)

[1843] 10. The system of claim 1, further comprising means for automatically implementing safety measures based on the risk information and emotion data analyzed by the AI ​​model.

[1844] (Claim 3)

[1845] 10. The system of claim 1, further comprising means for the server to set up a crowdfunding link and notify all users.

[1846] "Application example 2 when combining emotion engines"

[1847] (Claim 1)

[1848] A means for users to take photos of risky areas of infrastructure, enter comments, and upload them.

[1849] The server stores the received photos and comments in a database and adds them to the AI ​​analysis queue.

[1850] a means for analyzing the sentiment of the comments using an emotion engine;

[1851] A means for an AI model to analyze photos and emotion data to identify risk levels and details, and generate safety measures;

[1852] A means for the server to notify the user of the generated safety measures and start crowdfunding if necessary;

[1853] A means to share the progress of safety measures with all users, and

[1854] A system including:

[1855] (Claim 2)

[1856] The system of claim 1, further comprising means for automatically implementing safety measures based on the risk information analyzed by the AI ​​model.

[1857] (Claim 3)

[1858] 10. The system of claim 1, further comprising means for the server to set up a crowdfunding link and notify all users. [Explanation of symbols]

[1859] 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 users to take photos of risky areas of infrastructure, enter comments, and upload them. The server stores the received photos and comments in a database and adds them to the AI ​​analysis queue. The AI ​​model analyzes photos and comments to identify risk levels and details, and generates safety measures. A means for the server to notify the user of the generated safety measures and start crowdfunding if necessary; A system including:

2. The system of claim 1 , further comprising means for automatically implementing safety measures based on the risk information analyzed by the AI ​​model.

3. The system of claim 1 , further comprising means for the server to set up a crowdfunding link and notify all users.

4. The system according to claim 1 , further comprising means for the server to share with the user the status of correction of the risk portion reported by the user.

Images