System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting video information of a monitoring camera in real time; means for pre-processing the collected video information; means for analyzing the pre-processed video information according to a generation AI; means for determining priorities of restoration and delivery destinations of articles based on a result of the analysis; and means for providing the determined priorities and delivery destination information to a user.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] During disasters such as earthquakes, detailed information about the local situation may be lacking, leading to inappropriate prioritization of recovery efforts and distribution of supplies. As a result, limited resources are not used effectively, delaying recovery efforts. Furthermore, inappropriate delivery of supplies can lead to problems such as supplies not reaching the necessary locations. The present invention aims to solve these problems and achieve rapid and efficient disaster response. [Means for solving the problem]

[0005] In order to solve the above-mentioned problems, the present invention provides the following means.

[0006] First, it provides a means of collecting surveillance camera video data in real time, allowing for constant monitoring of the current situation at the disaster site.

[0007] Second, we provide a means to pre-process the collected video data, which removes noise and improves the quality of the data.

[0008] Furthermore, it provides a means for analyzing the pre-processed data using generative AI, which analyzes the number of people, trends in their behavior, and the flow of goods to gain a detailed understanding of the current situation.

[0009] Based on the analysis results, we provide a method to determine restoration priorities and delivery destinations, enabling priority response to be given to areas most in need.

[0010] Finally, it provides a means for providing determined priority and delivery information to the user, allowing local response teams to act quickly.

[0011] Combining these measures will enable rapid and efficient disaster response.

[0012] A "surveillance camera" is a video capture device used to constantly monitor a specific area.

[0013] "Video data" refers to data that includes visual information collected by a surveillance camera.

[0014] "Real-time" refers to data acquisition and processing occurring nearly simultaneously, without delay.

[0015] "Preprocessing" refers to processing the collected data, such as removing noise, to improve the accuracy of the analysis.

[0016] "Generative AI" is an artificial intelligence technology that analyzes large amounts of data and recognizes patterns and trends.

[0017] "Analysis" is the process of examining data in detail and extracting meaningful information.

[0018] "Restoration priority" is a criterion for determining which parts should be addressed and in what order when carrying out restoration work.

[0019] "Goods destination" refers to the specific location or facility to which needed supplies should be sent.

[0020] "User" means a person who uses the System and acts on the information provided.

[0021] A "means" is a method or device for realizing a specific function or process. [Brief explanation of the drawings]

[0022] [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

[0023] 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.

[0024] First, the terms used in the following description will be explained.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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."

[0030] [First embodiment]

[0031] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0032] 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.

[0033] 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).

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0039] 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.

[0040] 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.

[0041] 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.

[0042] 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."

[0043] The present invention relates to a system that collects video data from surveillance cameras in real time, analyzes it using a generative AI, determines restoration priorities and delivery destinations for goods, and provides the results to users. The system of the present invention is specifically implemented as follows.

[0044] overview

[0045] In order to realize a rapid and appropriate response in the event of a disaster, the system of the present invention collects video data from surveillance cameras and analyzes that data using AI. Based on the results of this analysis, recovery priorities and delivery destinations for supplies are determined and provided to the user.

[0046] System configuration

[0047] 1. Surveillance cameras

[0048] The terminals consist of surveillance cameras installed in disaster areas. These cameras collect video data in real time and transmit it to a server.

[0049] 2. Server

[0050] The server receives video data sent from the surveillance camera, and first performs preprocessing on the received data to remove noise.

[0051] The server then analyzes the pre-processed data using generative AI, which focuses on evaluating the number of people, their behavioral trends, and the flow of goods.

[0052] The server runs an algorithm that determines the priority of recovery and the delivery destination of goods based on the analysis results of the generating AI.

[0053] 3. Users

[0054] Users of this system are on-site managers and response teams. They check the information provided by the server and issue instructions for on-site recovery work and delivery of goods.

[0055] Explanation of program processing

[0056] 1. Data Collection

[0057] The server receives video data from multiple surveillance cameras (terminals) in real time and stores it in a database.

[0058] Example: A server receives data every second from cameras installed at major intersections and public facilities in the city.

[0059] 2. Data Preprocessing

[0060] The server performs filtering to remove noise from the collected video data, thereby improving the accuracy of the analysis.

[0061] Example: The server applies a Gaussian filter to reduce unwanted image noise.

[0062] 3. Data Analysis

[0063] The server inputs the preprocessed data into a generative AI to analyze the number of people, behavioral trends, and flow of goods.

[0064] Example: AI detects people and vehicles appearing in video footage and analyzes their location and movement.

[0065] 4. Priority and delivery destination determination

[0066] The server runs an algorithm that determines recovery priorities and delivery destinations for items based on the analysis results obtained from the generation AI.

[0067] For example, AI can detect highly congested roads and determine which roads should be prioritized for restoration, or identify areas where goods are in short supply and prioritize deliveries to those areas.

[0068] 5. Provision of Information

[0069] The server provides the determined priority and delivery destination information to the site manager (user).

[0070] Example: The server uses a RESTful API to send information to the administrator's smartphone or tablet.

[0071] Explanation with concrete examples

[0072] In disaster areas, surveillance cameras installed on major roads and public facilities collect video data and send it to a server. The server preprocesses the received data and analyzes it using generative AI. For example, if a group of people is confirmed in a certain area, the AI ​​will determine that area as a priority destination for delivering food and water. Also, if a particular road is extremely congested, it will be set as the top priority for restoration.

[0073] This information is then sent from the server to the user's device, who then issues instructions to the local response team, ensuring quick and efficient recovery efforts and delivery of supplies.

[0074] The processing flow will be explained below.

[0075] Step 1:

[0076] The server acquires video data in real time from each device (surveillance camera) installed in the disaster area. For example, it collects video every second from surveillance cameras installed at intersections and public facilities and stores it in a database.

[0077] Step 2:

[0078] The server preprocesses the acquired video data, specifically applying a noise reduction filter to the video data to improve image quality, for example, by using a Gaussian filter to reduce unwanted noise.

[0079] Step 3:

[0080] The server then inputs the preprocessed video data into a generative AI, which analyzes the number of people, their behavioral trends, and the flow of goods. Specifically, the AI ​​recognizes people and objects in the video and tracks their location and movement.

[0081] Step 4:

[0082] The server runs an algorithm to determine restoration priorities based on the analysis results obtained from the AI ​​generation. For example, if a particular road is extremely congested, it will be given top priority for restoration.

[0083] Step 5:

[0084] The server determines the delivery destination of the goods based on the analysis results. For example, if the analysis results indicate that there is a shortage of food or water in a certain area, the server sets that area as a priority delivery destination.

[0085] Step 6:

[0086] The server provides the determined recovery priority and delivery destination information to the on-site administrator (user). As a specific example, it sends the information to the administrator's tablet using a RESTful API.

[0087] Step 7:

[0088] The user can review the provided information and issue instructions to the local response team for restoration work and material delivery. For example, the user can review the priority information on the tablet and inform the restoration team of the roads that need to be repaired with the highest priority.

[0089] Step 8:

[0090] The user monitors the progress of the recovery and delivery of goods and modifies instructions as needed. For example, if unexpected difficulties arise along the way, the user responds by issuing new instructions.

[0091] Step 9:

[0092] The server continuously collects new data from the surveillance cameras and repeatedly pre-processes and analyzes it, enabling optimal decisions to be made based on the latest information.

[0093] Example 1

[0094] 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."

[0095] A rapid and appropriate response in the event of a disaster is crucial for preventing damage from spreading and for efficiently advancing recovery. However, conventional methods have the problem of making it difficult to grasp the situation on-site in real time and determine effective recovery priorities and supply delivery destinations. Another issue is the lack of a means to quickly and accurately convey this information to on-site response teams.

[0096] 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.

[0097] In this invention, the server includes: means for collecting surveillance camera video data in real time; means for preprocessing the collected video data; means for analyzing the preprocessed data using a generative AI; means for determining restoration priorities and delivery destinations based on the analysis results; means for providing the determined priorities and delivery destination information to an end-user device; and means for transmitting instructions from the end-user device to a local response team based on the provided information. This enables accurate understanding of the on-site situation in real time and prompt and appropriate determination of restoration priorities and delivery destinations. Furthermore, by quickly communicating this information to relevant parties, the efficiency and accuracy of response can be improved.

[0098] A "surveillance camera" is a device that captures video data of a specific area in real time.

[0099] "Video data" refers to image information captured by a surveillance camera and is typically stored in digital form.

[0100] "Preprocessing" refers to data processing to make subsequent analysis easier, such as removing noise from collected video data or adjusting resolution.

[0101] "Generative AI" is a model that uses artificial intelligence technology to analyze video data and recognize specific patterns.

[0102] "Analysis" refers to data processing to extract specific information (e.g., number of people, behavioral patterns, flow of goods, etc.) based on preprocessed video data.

[0103] "Recovery priority" is an evaluation criterion for determining the order in which recovery work should be carried out in the event of a disaster.

[0104] "Delivery destination of goods" is an indicator for determining to which region or location the required goods should be delivered.

[0105] "End-user devices" refers to devices such as smartphones, tablets, and computers used by local response teams and administrators.

[0106] "Instructions" are messages sent from end-user devices to local response teams with specific action plans and priorities.

[0107] The present invention relates to a system that collects video data from surveillance cameras in real time, analyzes it using a generative AI, determines restoration priorities and delivery destinations for goods, and provides the results to users. The system of the present invention is specifically implemented as follows.

[0108] surveillance cameras

[0109] The device consists of multiple surveillance cameras installed in the disaster area. These cameras capture video data in real time and transmit the data to a server. Specifically, cameras installed at major intersections and public facilities in the city capture real-time video at 30 frames per second and transmit the data securely to the server using AES encryption.

[0110] server

[0111] The server has the function of receiving video data transmitted in real time from multiple surveillance cameras, and then stores the received video data in a database. The stored data also includes metadata such as timestamps and camera IDs.

[0112] The server preprocesses the collected data, including noise reduction using a Gaussian filter and image resolution adjustment, improving image quality and enhancing the accuracy of analysis.

[0113] The server then inputs the preprocessed data into the generative AI, which uses a pre-trained model to send a specific prompt to the model: "Analyze people's movements during a disaster and identify areas that should be prioritized."

[0114] The generative AI model analyzes the number of people, behavioral patterns, and flow of goods in the video. This includes person detection, location tracking, and behavior classification. For example, the generative AI model detects people and vehicles appearing in the video and analyzes their location and movement.

[0115] The server runs an algorithm that determines restoration priorities and delivery destinations based on the analysis results obtained from the generative AI model. For example, it detects highly congested roads and sets them as the highest priority for restoration. It also identifies areas where supplies are in short supply and determines priority delivery destinations for those areas.

[0116] User

[0117] Users are on-site managers and response teams. The server provides the determined priority and delivery destination information to the user's smartphone or tablet via a RESTful API. The user then issues specific instructions to the local response team based on that information. For example, if a group of people is confirmed in a certain area, the user determines that area as a priority destination for the delivery of food and water, and issues specific instructions such as "restore the main roads in area A as the top priority" or "deliver food to area B as a priority."

[0118] This system will enable efficient and rapid disaster response, preventing damage from spreading and contributing to early recovery.

[0119] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0120] Step 1:

[0121] The terminal captures real-time video data of the target area through installed surveillance cameras. Specifically, surveillance cameras installed at major intersections and public facilities in the city generate video at 30 frames per second and send it to a server using AES encryption. The input is the captured raw video data, and the output is the encrypted video data.

[0122] Step 2:

[0123] The server stores the encrypted video data received from the device in a database. The input is encrypted video data, and the output is video data stored in the database. Specifically, the server immediately stores the received data in the database and adds a timestamp and camera ID as metadata.

[0124] Step 3:

[0125] The server performs preprocessing on the stored video data. Specifically, it applies a Gaussian filter to remove noise from the collected video data and adjusts the resolution. The input is the raw video data stored in the database, and the output is preprocessed video data with noise removed. The server stores the data after this preprocessing in another database or cache.

[0126] Step 4:

[0127] The server inputs the preprocessed video data into the generative AI model. It then sends the model a prompt, saying, "Analyze people's movements during a disaster and identify areas that should be prioritized," and begins analysis. The input is the preprocessed video data and the prompt, and the output is the analysis results. The generative AI model performs a detailed analysis of the number of people in the video, their behavioral patterns, and the flow of goods, and returns the results to the server.

[0128] Step 5:

[0129] The server runs an algorithm that determines restoration priorities and delivery destinations for supplies based on the analysis results obtained from the generative AI model. For example, it prioritizes restoration of highly congested roads and creates a priority delivery plan for areas where supplies are in short supply. The input is the analysis results of the generative AI model, and the output is restoration priorities and delivery destination information for supplies.

[0130] Step 6:

[0131] The server provides the determined priority and delivery destination information to the end-user device. Specifically, it uses a RESTful API to send the information to the user's smartphone or tablet. The input is the recovery priority and delivery destination information, and the output is the information sent to the user's end-user device.

[0132] Step 7:

[0133] Based on the information received from the server, the user sends specific instructions to the local response team, such as "Give top priority to restoring the main roads in area A" or "Give priority to delivering food to area B." The input is the information provided by the server, and the output is the specific instructions to the local response team.

[0134] (Application example 1)

[0135] 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."

[0136] In the event of a disaster, a rapid and appropriate response is required, but in many cases, it takes time to grasp the situation on-site, which leads to problems such as delays in recovery work and the delivery of supplies. Furthermore, appropriate resources may not be deployed to the necessary locations, making it difficult to respond efficiently. To resolve these situations, a system is needed that can accurately grasp the situation on-site in real time, clarify priorities, and respond quickly.

[0137] 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.

[0138] In this invention, the server includes means for collecting surveillance camera video data in real time, means for preprocessing the collected video data, means for analyzing the preprocessed data using a generation AI, means for determining restoration priorities and delivery destinations based on the analysis results, means for providing the determined priorities and delivery destination information to a user, means for notifying the user of the analysis results on a mobile information terminal, and means for visually displaying information on restoration work and delivery of goods, thereby enabling restoration work and delivery of goods to be carried out quickly and efficiently.

[0139] A "surveillance camera" is a device installed in a disaster area that collects video data in real time.

[0140] "Preprocessing" is a data processing method for removing noise from collected video data and improving the accuracy of analysis.

[0141] "Generative AI" is an artificial intelligence model that analyzes collected data to assess the number of people, trends in their behavior, and the flow of goods, and to determine recovery priorities and delivery destinations for goods.

[0142] "Recovery priority" is a criterion for evaluating the urgency of recovery work at a disaster site and determining which work should be given priority.

[0143] "Delivery destination of goods" is information that determines the location to which relief supplies and necessary goods should be delivered.

[0144] "Users" refers to the on-site managers and response teams who use this system.

[0145] A "mobile information terminal" is a portable information processing device such as a smartphone or tablet.

[0146] "Visual display of information on restoration work and goods delivery" is a function that displays the priority and delivery destination of restoration work and goods delivery in a form that is easy for the user to see.

[0147] This invention is a system for realizing a rapid and appropriate response in the event of a disaster. It collects video data from surveillance cameras in real time and analyzes it with a generative AI to determine recovery priorities and delivery destinations for goods, and provides the results to users. This system is specifically implemented as follows.

[0148] System configuration

[0149] 1. Surveillance cameras

[0150] The terminals consist of surveillance cameras installed in disaster areas. These cameras collect video data in real time and transmit it to a server.

[0151] 2. Server

[0152] The server receives video data sent from the surveillance camera, and first pre-processes the received data to remove noise.

[0153] The server then analyzes the pre-processed data using generative AI, which focuses on evaluating the number of people, their behavioral trends, and the flow of goods.

[0154] Based on the analysis results of the generating AI, the server runs an algorithm to determine the priority of recovery and the delivery destination of the goods.

[0155] The server notifies the user's mobile information terminal of the determined priority and delivery destination information.

[0156] 3. Users

[0157] The users are on-site managers and response teams, and receive information provided by the server using mobile information terminals.

[0158] Users can use a dashboard that visually displays recovery efforts and delivery information, and direct local response teams.

[0159] Program processing

[0160] Hardware and Software

[0161] Hardware: surveillance cameras, servers, mobile devices (smartphones and tablets).

[0162] Software: OpenCV library, some_ai_library, Flask server.

[0163] Program Flow

[0164] The server receives video data transmitted in real time from the surveillance cameras and stores it in a database.

[0165] Next, the video data is preprocessed using the OpenCV library, in particular by applying a Gaussian filter to remove noise.

[0166] The pre-processed data is sent to some_ai_library's generative AI model to analyze the number of people, behavioral trends, and flow of goods.

[0167] Based on the analysis results, an algorithm is run to determine restoration priorities and delivery destinations for goods.

[0168] The results are sent to the mobile information terminal, and the user can receive the information via push notifications or a dashboard.

[0169] Specific examples

[0170] For example, if a major earthquake occurs and major roads are closed, the system will analyze video footage from surveillance cameras in various locations in real time. As a result, it will identify evacuation centers where people are gathering and set those locations as priority delivery destinations for supplies. It will also be possible to prioritize reopening roads with heavy traffic. This information will be sent to mobile devices, and users can visually check it on their dashboard.

[0171] Example prompts for generative AI models

[0172] "Analyze surveillance camera footage during a disaster to determine priority recovery efforts and delivery destinations. Pay attention to the number of people, their behavioral trends, and the flow of goods."

[0173] Overview of available systems

[0174] This system will enable a prompt and appropriate response in the event of a disaster, and will realize the efficient distribution of supplies and the streamlining of recovery work. It will also enable users to receive information in real time and give prompt instructions on on-site response.

[0175] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0176] Step 1:

[0177] The server receives video data in real time from surveillance cameras installed in the disaster area. Each surveillance camera transmits video of the scene to the server in streaming format. The input video data is transmitted from the surveillance cameras, and the output is stored in a database.

[0178] Step 2:

[0179] The server preprocesses the received video data. Specifically, it applies a Gaussian filter using the OpenCV library to remove noise. The input is the video data saved in step 1, and the output is preprocessed, clear video data.

[0180] Step 3:

[0181] The preprocessed data is input from the server into the generative AI model. Specifically, some_ai_library is used to perform video analysis and evaluate the number of people, behavioral trends, and flow of goods. The input is the preprocessed data, and the output is the analysis results. An example of a prompt sentence is input to the generative AI: "Analyze surveillance camera footage from the time of the disaster and determine the highest priority recovery work and delivery destinations for goods. Please place emphasis on the number of people, behavioral trends, and flow of goods."

[0182] Step 4:

[0183] The server runs an algorithm to determine restoration priorities and delivery destinations based on the analysis results of the generation AI. The input is the analysis results, and the output is a list of priorities and delivery destinations for the items.

[0184] Step 5:

[0185] The server notifies the user of the determined priority and delivery destination information. Specifically, it uses a RESTful API to send information to the user's mobile information device (smartphone or tablet). The input is a list of priorities and delivery destinations, and the output is a notification sent to the user's mobile information device.

[0186] Step 6:

[0187] Users receive notifications on their devices and use a dashboard that visually displays information on recovery efforts and supply delivery. The input is notifications sent from the server, and the output is a visual display. For example, users can check the priority of evacuation shelters and congested roads through the dashboard and issue instructions to on-site teams.

[0188] 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.

[0189] This invention combines a system that collects surveillance camera video data in real time, analyzes it with generative AI to determine restoration priorities and delivery destinations for supplies, and provides the system to users with an emotion engine that recognizes user emotions, further improving the efficiency and accuracy of disaster response.

[0190] overview

[0191] In order to realize a rapid and appropriate response in the event of a disaster, the system of the present invention collects video data from surveillance cameras and analyzes that data using a generative AI. Based on the results of this analysis, it determines recovery priorities and delivery destinations for goods, taking into account the user's emotional information to make optimal decisions.

[0192] System configuration

[0193] 1. Surveillance cameras

[0194] The terminals consist of surveillance cameras installed in disaster areas. These cameras collect video data in real time and transmit it to a server.

[0195] 2. Server

[0196] The server receives video data sent from the surveillance camera, and first performs preprocessing on the received data to remove noise.

[0197] The server then analyzes the pre-processed data using generative AI, which focuses on evaluating the number of people, their behavioral trends, and the flow of goods.

[0198] The server runs an algorithm that determines the priority of recovery and the delivery destination of goods based on the analysis results of the generating AI.

[0199] The server uses an emotion engine to recognize the user's emotions, reflects them in the analysis results, and makes optimal decisions.

[0200] 3. Users

[0201] Users of this system are on-site managers and response teams. They check the information provided by the server and issue instructions for on-site recovery work and delivery of goods.

[0202] Explanation of program processing

[0203] 1. Data Collection

[0204] The server receives video data from multiple surveillance cameras (terminals) in real time and stores it in a database.

[0205] Example: A server receives data every second from cameras installed at major intersections and public facilities in the city.

[0206] 2. Data Preprocessing

[0207] The server performs filtering to remove noise from the collected video data, thereby improving the accuracy of the analysis.

[0208] Example: The server uses a Gaussian filter to reduce unwanted image noise.

[0209] 3. Data Analysis

[0210] The server inputs the preprocessed data into a generative AI to analyze the number of people, behavioral trends, and flow of goods.

[0211] Example: AI detects people and vehicles appearing in video footage and analyzes their location and movement.

[0212] 4. Emotion recognition

[0213] The server uses an emotion engine that recognizes the user's emotions in real time through an interface with the user.

[0214] Example: Emotional information is collected through facial recognition and voice analysis while the user is viewing information on a tablet.

[0215] 5. Priority and delivery destination determination

[0216] The server runs an algorithm that determines recovery priorities and delivery destinations for items based on the analysis results obtained from the generative AI and the emotional information from the emotion engine.

[0217] For example, AI can detect highly congested roads and determine which roads should be prioritized for restoration, or identify areas where goods are in short supply and prioritize deliveries to those areas.

[0218] 6. Provision of Information

[0219] The server provides the determined restoration priority and delivery destination information to the site administrator (user).

[0220] Example: The server uses a RESTful API to send information to the administrator's smartphone or tablet.

[0221] Explanation with concrete examples

[0222] In disaster areas, surveillance cameras installed on major roads and public facilities collect video data and send it to a server. The server preprocesses the received data and analyzes it using generative AI. For example, if a group of people is confirmed in a certain area, the AI ​​will determine that area as a priority destination for delivering food and water. Also, if a particular road is extremely congested, it will be set as the top priority for restoration.

[0223] At the same time, the emotion engine recognizes the user's emotions and sends them to the server. For example, if the user is feeling stressed, it can respond by speeding up the delivery of supplies to the affected area.

[0224] This information is then sent from the server to the user's device, who then issues instructions to the local response team, ensuring quick and efficient recovery efforts and delivery of supplies.

[0225] The processing flow will be explained below.

[0226] Step 1:

[0227] The server acquires video data in real time from each device (surveillance camera) installed in the disaster area. For example, it collects video every second from surveillance cameras installed at intersections and public facilities and stores it in a database.

[0228] Step 2:

[0229] The server preprocesses the acquired video data, specifically applying a noise reduction filter to the video data to improve image quality, for example, by using a Gaussian filter to reduce unwanted noise.

[0230] Step 3:

[0231] The server then inputs the preprocessed video data into a generative AI, which analyzes the number of people, their behavioral trends, and the flow of goods. For example, the AI ​​can recognize people and vehicles in the video and track their location and movement.

[0232] Step 4:

[0233] The server runs an algorithm to determine restoration priorities based on the analysis results obtained from the AI ​​generation. For example, if a particular road is extremely congested, it will be given top priority for restoration.

[0234] Step 5:

[0235] The server determines the delivery destination of the goods based on the analysis results. For example, if the analysis results indicate that there is a shortage of food or water in a certain area, the server sets that area as a priority delivery destination.

[0236] Step 6:

[0237] The server's emotion engine recognizes the user's emotions in real time through the user interface. This emotion information is then reflected in prioritization and delivery destination decisions. For example, if the user expresses emotions indicating stress or urgency, that information is used to reevaluate the priority.

[0238] Step 7:

[0239] The server provides the determined recovery priority and delivery destination information to the on-site administrator (user). As a specific example, it sends the information to the administrator's tablet or smartphone using a RESTful API.

[0240] Step 8:

[0241] The user can review the provided information and issue instructions to the local response team for restoration work and material delivery. For example, the user can review the priority information on the tablet and inform the restoration team of the roads that need to be repaired with the highest priority.

[0242] Step 9:

[0243] The user monitors the progress of the recovery and delivery of goods and modifies instructions as needed. For example, if unexpected difficulties arise along the way, the user responds by issuing new instructions.

[0244] Step 10:

[0245] The server continuously collects new data from the surveillance cameras and repeatedly pre-processes and analyzes it, enabling optimal decisions to be made based on the latest information.

[0246] Example 2

[0247] 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."

[0248] It is not easy to respond quickly and appropriately in the event of a disaster and accurately determine restoration priorities and delivery destinations. Furthermore, there is a lack of methods for making optimal decisions that take into account users' emotional information. Conventional technologies do not provide effective solutions to these issues, which means that the efficiency and accuracy of disaster response are not sufficiently ensured.

[0249] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting video data from monitoring devices in real time, means for preprocessing the collected video data, means for analyzing the preprocessed data using a generative AI model, means for determining restoration priorities and delivery destinations of goods based on the analysis results, means for recognizing the user's emotions, means for making optimal decisions based on the analysis results including the emotion data, and means for providing the determined priorities and delivery destination information to the user. This enables a quick and appropriate response in the event of a disaster and allows optimal decisions to be made taking the user's emotions into account.

[0250] "Surveillance equipment" is a general term for cameras and other imaging devices installed in disaster areas that collect video data in real time.

[0251] "Video data" refers to real-time images and video information collected by surveillance equipment.

[0252] "Preprocessing" refers to the process of removing noise from collected video data and performing initial data processing to improve the accuracy of analysis.

[0253] A "generative AI model" is an artificial intelligence model used to analyze collected and pre-processed video data to detect and analyze the number of people, behavioral trends, and flow of goods.

[0254] "Analysis results" refers to data derived by the generative AI model, such as the number of people, behavioral trends, and flow of goods.

[0255] "Recovery priority" is a standard for evaluating the importance of areas and infrastructure that require restoration in the event of a disaster, and determining the order in which they should be prioritized.

[0256] "Delivery destination of goods" refers to the location or area where necessary supplies should be delivered in the event of a disaster.

[0257] "Means for recognizing emotions" refers to technology that analyzes emotions in real time from the user's facial expressions, voice, etc., and feeds the results back to the system.

[0258] "Optimal judgment" is a process that comprehensively considers analysis results and emotional data to make the most appropriate decisions regarding recovery operations and delivery of goods.

[0259] "User" refers to administrators and response teams who use this system to respond to disasters.

[0260] This invention is a system for realizing a rapid and appropriate response in the event of a disaster. It collects video data from surveillance equipment in real time, analyzes it using a generative AI model, determines recovery priorities and delivery destinations for supplies, and provides them to users. In addition, by combining it with a means to recognize user emotions, the efficiency and accuracy of disaster response can be further improved.

[0261] System configuration

[0262] monitoring equipment

[0263] The terminals consist of surveillance equipment installed in disaster areas. These surveillance equipment collect video data in real time and transmit it to a server. Specifically, surveillance cameras installed at major intersections and public facilities are used.

[0264] server

[0265] The server receives the video data sent from the surveillance equipment and stores it in a database, typically an RDBMS such as MySQL.

[0266] The server preprocesses the received video data to remove noise, using the Gaussian filtering function of the OpenCV library.

[0267] The server then analyzes the pre-processed data using a generative AI model powered by TensorFlow to analyze the number of people, their behavioral trends, and the flow of goods.

[0268] The server runs an algorithm that determines the priority of recovery and delivery destination based on the analysis results, by integrating the urgency score and emotion recognition results.

[0269] The server uses an emotion engine through the user interface to recognize the user's emotions in real time, using emotion recognition APIs such as Microsoft Azure's Emotion API.

[0270] The server sends the determined priority and delivery information via a RESTful API to provide the user with the information.

[0271] User

[0272] Users are on-site managers and response teams who handle disaster response. They check the information provided by the server using a dedicated application or dashboard, and issue instructions for on-site recovery work and the delivery of supplies.

[0273] Specific examples

[0274] In disaster areas, surveillance cameras installed on major roads and public facilities collect video data and send it to a server. For example, if a group of people is spotted in a certain area, the generative AI model will determine that area as a priority destination for delivering food and water. Also, if a particular road is extremely congested, it will be designated as a top priority for restoration.

[0275] At the same time, the emotion engine recognizes the user's emotions and sends them to the server. While the user is checking information on the tablet, emotional information is collected through facial recognition and voice analysis. For example, if the user is feeling high levels of stress, the system can take action such as speeding up the delivery of supplies to the affected area.

[0276] This information is sent from the server to the user's device, allowing the user to provide specific instructions to the local response team, ensuring that recovery efforts and delivery of supplies are carried out quickly and efficiently.

[0277] Prompt Sentence Examples

[0278] You can use prompts like the following for your generative AI model:

[0279] "Analyze video data from within the city to assess crowds and road congestion."

[0280] "If there is a shortage of goods in a particular area, determine where to prioritize delivery."

[0281] "Based on user sentiment data, please suggest prioritized support measures for high-stress areas."

[0282] This system will enable a rapid and accurate response in the event of a disaster.

[0283] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0284] Step 1: Data collection

[0285] Input: Real-time video data from surveillance equipment.

[0286] How it works: Surveillance devices are installed in disaster areas and capture video data at 30 frames per second, which are then encoded and streamed to a server in real time.

[0287] Output: Real-time video data sent to the server.

[0288] Step 2: Receiving and storing data

[0289] Input: Real-time video data streamed from surveillance equipment.

[0290] Specific operation: The server receives video data sent from multiple surveillance devices and stores it in a database (e.g., MySQL) in H.264 format.

[0291] Output: Raw video data stored in a database.

[0292] Step 3: Preprocessing for noise reduction

[0293] Input: Raw video data stored in a database.

[0294] Specific operation: The server uses the Gaussian filtering function of the OpenCV library to remove noise from the received video data.

[0295] Output: Denoised video data.

[0296] Step 4: Analyzing the video data

[0297] Input: Denoised video data.

[0298] How it works: The server inputs video data into a generative AI model using TensorFlow to analyze the number of people, behavioral trends, and flow of goods. Specifically, it detects people and vehicles in the video and identifies their location information and movement patterns.

[0299] Output: Data on the number of people, behavioral trends, and flow of goods analyzed by the generative AI model.

[0300] Step 5: Performing Emotion Recognition

[0301] Input: Facial expressions and voice data as users interact with tablets and smartphones through the interface.

[0302] Specific operation: The server analyzes the voice and facial expression data collected from tablets and smartphones using emotion recognition APIs such as Microsoft Azure's Emotion API.

[0303] Output: Parsed user emotion data.

[0304] Step 6: Prioritize and route your delivery

[0305] Input: Analysis results from the generative AI model and emotion data obtained from emotion recognition.

[0306] How it works: The server aggregates this data and uses a priority algorithm to determine the priority of recovery and delivery destinations. For example, areas with high urgency scores and high user stress levels are given top priority.

[0307] Output: Priority and item delivery destination decision data.

[0308] Step 7: Provide information

[0309] Input: Priority and item destination determination data.

[0310] Specific operation: The server uses a RESTful API to send notifications to smartphones and tablets, and displays information in real time on a dedicated application or dashboard.

[0311] Output: Priority and delivery information displayed on a smartphone or tablet.

[0312] At each step, the server, terminal, and user work together to enable a rapid and optimal response in the event of a disaster.

[0313] (Application example 2)

[0314] 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."

[0315] Rapid and appropriate recovery efforts and delivery of supplies are extremely important in the event of a disaster. However, current systems have difficulty in determining priorities and delivery locations, fully reflecting user emotions and real-time situations. Furthermore, once priorities and delivery destinations have been determined, there is a lack of a means to quickly and effectively notify local managers and response teams. Therefore, a new system is needed to improve the efficiency and accuracy of disaster response.

[0316] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0317] In this invention, the server includes means for collecting surveillance camera video data in real time, means for preprocessing the collected video data, means for analyzing the preprocessed data using a generative AI, means for determining restoration priorities and delivery destinations, means for providing the restoration priorities and delivery destination information to a user and reflecting the information in the analysis results using an emotion engine that recognizes the user's emotions, and means for notifying a device such as a smartphone or smart glasses of the determined priorities and delivery destination information. This makes it possible to determine optimal restoration work and delivery destinations in real time while reflecting the user's emotions, and to quickly provide related information to a local manager.

[0318] A "surveillance camera" is a device for continuously monitoring a specific location or area and recording and transmitting video data in real time.

[0319] "Video data" refers to data including real-time video images collected by surveillance cameras and related information.

[0320] "Preprocessing" refers to the process of filtering and data cleaning to remove noise from collected video data and improve the accuracy of analysis.

[0321] "Generative AI" is an artificial intelligence technology that learns from large amounts of data and analyzes video data.

[0322] The "emotion engine" is a system that recognizes the user's emotions and reflects that information in the analysis results.

[0323] "Recovery priority" is a criterion for determining which areas and tasks should be given priority when carrying out recovery work after a disaster.

[0324] "Delivery destination of goods" is an address that indicates the location where necessary supplies should be delivered first in the event of a disaster.

[0325] "Users" are the on-site managers and response teams who operate the system and instruct recovery work and delivery of goods.

[0326] "Notification" is the means by which the system communicates analysis results and decisions to the user in real time.

[0327] A "smartphone" is a portable information terminal that has the functionality of a mobile phone and can run a variety of applications.

[0328] "Smart glasses" are a type of wearable device, an electronic device in the shape of glasses that provides visual information to the user.

[0329] This invention is a system for realizing rapid and appropriate recovery efforts and delivery of supplies in the event of a disaster. This system collects video data from surveillance cameras in real time and analyzes it using generative AI and an emotion engine to determine recovery priorities and delivery destinations. It also reflects the user's emotions and quickly provides the analysis results to on-site managers and response teams.

[0330] The server first receives video data from multiple surveillance cameras in real time and stores it in a database. The video data is then filtered in the pre-processing stage to remove noise. A Gaussian filter is applied using a framework such as OpenCV. The pre-processed data is then input into a generative AI model (e.g., TensorFlow or PyTorch) to detect people and objects.

[0331] Based on the analysis results of the Generative AI, the server runs an algorithm to determine restoration priorities and delivery destinations. This algorithm primarily analyzes the number of people, their behavioral trends, and the flow of goods. Furthermore, it collects and analyzes user emotional information through an emotion engine (e.g., Microsoft Azure Face API or Affectiva), which is reflected in the Generative AI's analysis results. This allows for prioritization of restoration efforts and delivery of goods in areas where users are experiencing high levels of stress or anxiety.

[0332] The determined restoration priority and delivery destination information are sent to devices such as smartphones or smart glasses. Based on this notification information, users can instruct on-site restoration work and item delivery. Specifically, information is displayed in real time on the user's smartphone or smart glasses, and notifications can be received by voice or vibration if necessary.

[0333] For example, in disaster areas, surveillance cameras installed on major roads and public facilities collect video data, which is then sent to a server. The server preprocesses the video data and analyzes it using generative AI. If a large number of people are gathered in a certain area, the server will determine that area as a priority destination for the delivery of food and water. Also, if a particular road is extremely congested, the server will set that road as the top priority for restoration. At the same time, the emotion engine will recognize the user's emotions, and if the user is feeling stressed, it can take action such as speeding up the delivery of supplies to that area.

[0334] An example prompt is:

[0335] "I want to build a system that collects surveillance camera footage from disaster areas in real time and analyzes it using generative AI. Based on the results of this analysis, I want to determine recovery priorities and delivery destinations for supplies. I also want to take user sentiment into account when making these decisions. What frameworks and APIs should I use?"

[0336] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0337] Step 1:

[0338] The server receives video data from the surveillance cameras in real time. Each surveillance camera transmits its video data via the Internet, and the server stores it in a database. The input is the video data from the surveillance cameras, and the output is the stored video data that is subjected to pre-processing.

[0339] Step 2:

[0340] The server preprocesses the collected video data. Specifically, it applies a Gaussian filter using OpenCV to remove noise. The input of this process is the stored video data, and the output is the denoised video data.

[0341] Step 3:

[0342] The server inputs the preprocessed data into a generative AI model for analysis. This model is built using TensorFlow and PyTorch and detects the number of people, behavioral trends, and flow of goods. The input for this process is the preprocessed video data, and the output is the data obtained as the analysis results (e.g., number of people, behavioral patterns, and location information of goods).

[0343] Step 4:

[0344] The server runs an algorithm that determines restoration priorities and delivery destinations based on the analysis results. The algorithm evaluates people's density and behavioral patterns to identify high-priority areas and necessary supplies. The input to this process is the analysis results, and the output is a list of restoration priorities and a list of delivery destinations for supplies.

[0345] Step 5:

[0346] The device receives emotional information from the user as input and analyzes it using an emotion engine. The emotion engine (e.g., Microsoft Azure Face API) analyzes the user's level of stress or anxiety from their facial expressions and voice. The input to this process is the user's emotional information, and the output is analyzed emotional data.

[0347] Step 6:

[0348] The server integrates the analysis results from the emotion engine with those from the generation AI and reflects them in the priority determination process. This allows areas where users are feeling high stress to be given a higher priority. The inputs to this process are emotion data and the analysis results from the generation AI, and the output is a recovery priority list that takes emotion into account and a list of delivery destinations for goods.

[0349] Step 7:

[0350] The server notifies the determined recovery priority and delivery destination information to devices such as smartphones and smart glasses. Information is sent in real time using a RESTful API, and various data is displayed on the user's device. The input to this process is a recovery priority list that takes emotions into account and a list of delivery destinations for items, and the output is notification information displayed on the user's device.

[0351] 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.

[0352] 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.

[0353] 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.

[0354] [Second embodiment]

[0355] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0356] 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.

[0357] 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).

[0358] 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.

[0359] 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.

[0360] 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).

[0361] 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.

[0362] 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.

[0363] 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.

[0364] 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.

[0365] 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.

[0366] 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."

[0367] The present invention relates to a system that collects video data from surveillance cameras in real time, analyzes it using a generative AI, determines restoration priorities and delivery destinations for goods, and provides the results to users. The system of the present invention is specifically implemented as follows.

[0368] overview

[0369] In order to realize a rapid and appropriate response in the event of a disaster, the system of the present invention collects video data from surveillance cameras and analyzes that data using AI. Based on the results of this analysis, recovery priorities and delivery destinations for supplies are determined and provided to the user.

[0370] System configuration

[0371] 1. Surveillance cameras

[0372] The terminals consist of surveillance cameras installed in disaster areas. These cameras collect video data in real time and transmit it to a server.

[0373] 2. Server

[0374] The server receives video data sent from the surveillance camera, and first performs preprocessing on the received data to remove noise.

[0375] The server then analyzes the pre-processed data using generative AI, which focuses on evaluating the number of people, their behavioral trends, and the flow of goods.

[0376] The server runs an algorithm that determines the priority of recovery and the delivery destination of goods based on the analysis results of the generating AI.

[0377] 3. Users

[0378] Users of this system are on-site managers and response teams. They check the information provided by the server and issue instructions for on-site recovery work and delivery of goods.

[0379] Explanation of program processing

[0380] 1. Data Collection

[0381] The server receives video data from multiple surveillance cameras (terminals) in real time and stores it in a database.

[0382] Example: A server receives data every second from cameras installed at major intersections and public facilities in the city.

[0383] 2. Data Preprocessing

[0384] The server performs filtering to remove noise from the collected video data, thereby improving the accuracy of the analysis.

[0385] Example: The server applies a Gaussian filter to reduce unwanted image noise.

[0386] 3. Data Analysis

[0387] The server inputs the preprocessed data into a generative AI to analyze the number of people, behavioral trends, and flow of goods.

[0388] Example: AI detects people and vehicles appearing in video footage and analyzes their location and movement.

[0389] 4. Priority and delivery destination determination

[0390] The server runs an algorithm that determines recovery priorities and delivery destinations for items based on the analysis results obtained from the generation AI.

[0391] For example, AI can detect highly congested roads and determine which roads should be prioritized for restoration, or identify areas where goods are in short supply and prioritize deliveries to those areas.

[0392] 5. Provision of Information

[0393] The server provides the determined priority and delivery destination information to the site manager (user).

[0394] Example: The server uses a RESTful API to send information to the administrator's smartphone or tablet.

[0395] Explanation with concrete examples

[0396] In disaster areas, surveillance cameras installed on major roads and public facilities collect video data and send it to a server. The server preprocesses the received data and analyzes it using generative AI. For example, if a group of people is confirmed in a certain area, the AI ​​will determine that area as a priority destination for delivering food and water. Also, if a particular road is extremely congested, it will be set as the top priority for restoration.

[0397] This information is then sent from the server to the user's device, who then issues instructions to the local response team, ensuring quick and efficient recovery efforts and delivery of supplies.

[0398] The processing flow will be explained below.

[0399] Step 1:

[0400] The server acquires video data in real time from each device (surveillance camera) installed in the disaster area. For example, it collects video every second from surveillance cameras installed at intersections and public facilities and stores it in a database.

[0401] Step 2:

[0402] The server preprocesses the acquired video data, specifically applying a noise reduction filter to the video data to improve image quality, for example, by using a Gaussian filter to reduce unwanted noise.

[0403] Step 3:

[0404] The server then inputs the preprocessed video data into a generative AI, which analyzes the number of people, their behavioral trends, and the flow of goods. Specifically, the AI ​​recognizes people and objects in the video and tracks their location and movement.

[0405] Step 4:

[0406] The server runs an algorithm to determine restoration priorities based on the analysis results obtained from the AI ​​generation. For example, if a particular road is extremely congested, it will be given top priority for restoration.

[0407] Step 5:

[0408] The server determines the delivery destination of the goods based on the analysis results. For example, if the analysis results indicate that there is a shortage of food or water in a certain area, the server sets that area as a priority delivery destination.

[0409] Step 6:

[0410] The server provides the determined recovery priority and delivery destination information to the on-site administrator (user). As a specific example, it sends the information to the administrator's tablet using a RESTful API.

[0411] Step 7:

[0412] The user can review the provided information and issue instructions to the local response team for restoration work and material delivery. For example, the user can review the priority information on the tablet and inform the restoration team of the roads that need to be repaired with the highest priority.

[0413] Step 8:

[0414] The user monitors the progress of the recovery and delivery of goods and modifies instructions as needed. For example, if unexpected difficulties arise along the way, the user responds by issuing new instructions.

[0415] Step 9:

[0416] The server continuously collects new data from the surveillance cameras and repeatedly pre-processes and analyzes it, enabling optimal decisions to be made based on the latest information.

[0417] Example 1

[0418] 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."

[0419] A rapid and appropriate response in the event of a disaster is crucial for preventing damage from spreading and for efficiently advancing recovery. However, conventional methods have the problem of making it difficult to grasp the situation on-site in real time and determine effective recovery priorities and supply delivery destinations. Another issue is the lack of a means to quickly and accurately convey this information to on-site response teams.

[0420] 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.

[0421] In this invention, the server includes: means for collecting surveillance camera video data in real time; means for preprocessing the collected video data; means for analyzing the preprocessed data using a generative AI; means for determining restoration priorities and delivery destinations based on the analysis results; means for providing the determined priorities and delivery destination information to an end-user device; and means for transmitting instructions from the end-user device to a local response team based on the provided information. This enables accurate understanding of the on-site situation in real time and prompt and appropriate determination of restoration priorities and delivery destinations. Furthermore, by quickly communicating this information to relevant parties, the efficiency and accuracy of response can be improved.

[0422] A "surveillance camera" is a device that captures video data of a specific area in real time.

[0423] "Video data" refers to image information captured by a surveillance camera and is typically stored in digital form.

[0424] "Preprocessing" refers to data processing to make subsequent analysis easier, such as removing noise from collected video data or adjusting resolution.

[0425] "Generative AI" is a model that uses artificial intelligence technology to analyze video data and recognize specific patterns.

[0426] "Analysis" refers to data processing to extract specific information (e.g., number of people, behavioral patterns, flow of goods, etc.) based on preprocessed video data.

[0427] "Recovery priority" is an evaluation criterion for determining the order in which recovery work should be carried out in the event of a disaster.

[0428] "Delivery destination of goods" is an indicator for determining to which region or location the required goods should be delivered.

[0429] "End-user devices" refers to devices such as smartphones, tablets, and computers used by local response teams and administrators.

[0430] "Instructions" are messages sent from end-user devices to local response teams with specific action plans and priorities.

[0431] The present invention relates to a system that collects video data from surveillance cameras in real time, analyzes it using a generative AI, determines restoration priorities and delivery destinations for goods, and provides the results to users. The system of the present invention is specifically implemented as follows.

[0432] surveillance cameras

[0433] The device consists of multiple surveillance cameras installed in the disaster area. These cameras capture video data in real time and transmit the data to a server. Specifically, cameras installed at major intersections and public facilities in the city capture real-time video at 30 frames per second and transmit the data securely to the server using AES encryption.

[0434] server

[0435] The server has the function of receiving video data transmitted in real time from multiple surveillance cameras, and then stores the received video data in a database. The stored data also includes metadata such as timestamps and camera IDs.

[0436] The server preprocesses the collected data, including noise reduction using a Gaussian filter and image resolution adjustment, improving image quality and enhancing the accuracy of analysis.

[0437] The server then inputs the preprocessed data into the generative AI, which uses a pre-trained model to send a specific prompt to the model: "Analyze people's movements during a disaster and identify areas that should be prioritized."

[0438] The generative AI model analyzes the number of people, behavioral patterns, and flow of goods in the video. This includes person detection, location tracking, and behavior classification. For example, the generative AI model detects people and vehicles appearing in the video and analyzes their location and movement.

[0439] The server runs an algorithm that determines restoration priorities and delivery destinations based on the analysis results obtained from the generative AI model. For example, it detects highly congested roads and sets them as the highest priority for restoration. It also identifies areas where supplies are in short supply and determines priority delivery destinations for those areas.

[0440] User

[0441] Users are on-site managers and response teams. The server provides the determined priority and delivery destination information to the user's smartphone or tablet via a RESTful API. The user then issues specific instructions to the local response team based on that information. For example, if a group of people is confirmed in a certain area, the user determines that area as a priority destination for the delivery of food and water, and issues specific instructions such as "restore the main roads in area A as the top priority" or "deliver food to area B as a priority."

[0442] This system will enable efficient and rapid disaster response, preventing damage from spreading and contributing to early recovery.

[0443] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0444] Step 1:

[0445] The terminal captures real-time video data of the target area through installed surveillance cameras. Specifically, surveillance cameras installed at major intersections and public facilities in the city generate video at 30 frames per second and send it to a server using AES encryption. The input is the captured raw video data, and the output is the encrypted video data.

[0446] Step 2:

[0447] The server stores the encrypted video data received from the device in a database. The input is encrypted video data, and the output is video data stored in the database. Specifically, the server immediately stores the received data in the database and adds a timestamp and camera ID as metadata.

[0448] Step 3:

[0449] The server performs preprocessing on the stored video data. Specifically, it applies a Gaussian filter to remove noise from the collected video data and adjusts the resolution. The input is the raw video data stored in the database, and the output is preprocessed video data with noise removed. The server stores the data after this preprocessing in another database or cache.

[0450] Step 4:

[0451] The server inputs the preprocessed video data into the generative AI model. It then sends the model a prompt, saying, "Analyze people's movements during a disaster and identify areas that should be prioritized," and begins analysis. The input is the preprocessed video data and the prompt, and the output is the analysis results. The generative AI model performs a detailed analysis of the number of people in the video, their behavioral patterns, and the flow of goods, and returns the results to the server.

[0452] Step 5:

[0453] The server runs an algorithm that determines restoration priorities and delivery destinations for supplies based on the analysis results obtained from the generative AI model. For example, it prioritizes restoration of highly congested roads and creates a priority delivery plan for areas where supplies are in short supply. The input is the analysis results of the generative AI model, and the output is restoration priorities and delivery destination information for supplies.

[0454] Step 6:

[0455] The server provides the determined priority and delivery destination information to the end-user device. Specifically, it uses a RESTful API to send the information to the user's smartphone or tablet. The input is the recovery priority and delivery destination information, and the output is the information sent to the user's end-user device.

[0456] Step 7:

[0457] Based on the information received from the server, the user sends specific instructions to the local response team, such as "Give top priority to restoring the main roads in area A" or "Give priority to delivering food to area B." The input is the information provided by the server, and the output is the specific instructions to the local response team.

[0458] (Application example 1)

[0459] 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."

[0460] In the event of a disaster, a rapid and appropriate response is required, but in many cases, it takes time to grasp the situation on-site, which leads to problems such as delays in recovery work and the delivery of supplies. Furthermore, appropriate resources may not be deployed to the necessary locations, making it difficult to respond efficiently. To resolve these situations, a system is needed that can accurately grasp the situation on-site in real time, clarify priorities, and respond quickly.

[0461] 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.

[0462] In this invention, the server includes means for collecting surveillance camera video data in real time, means for preprocessing the collected video data, means for analyzing the preprocessed data using a generation AI, means for determining restoration priorities and delivery destinations based on the analysis results, means for providing the determined priorities and delivery destination information to a user, means for notifying the user of the analysis results on a mobile information terminal, and means for visually displaying information on restoration work and delivery of goods, thereby enabling restoration work and delivery of goods to be carried out quickly and efficiently.

[0463] A "surveillance camera" is a device installed in a disaster area that collects video data in real time.

[0464] "Preprocessing" is a data processing method for removing noise from collected video data and improving the accuracy of analysis.

[0465] "Generative AI" is an artificial intelligence model that analyzes collected data to assess the number of people, trends in their behavior, and the flow of goods, and to determine recovery priorities and delivery destinations for goods.

[0466] "Recovery priority" is a criterion for evaluating the urgency of recovery work at a disaster site and determining which work should be given priority.

[0467] "Delivery destination of goods" is information that determines the location to which relief supplies and necessary goods should be delivered.

[0468] "Users" refers to the on-site managers and response teams who use this system.

[0469] A "mobile information terminal" is a portable information processing device such as a smartphone or tablet.

[0470] "Visual display of information on restoration work and goods delivery" is a function that displays the priority and delivery destination of restoration work and goods delivery in a form that is easy for the user to see.

[0471] This invention is a system for realizing a rapid and appropriate response in the event of a disaster. It collects video data from surveillance cameras in real time and analyzes it with a generative AI to determine recovery priorities and delivery destinations for goods, and provides the results to users. This system is specifically implemented as follows.

[0472] System configuration

[0473] 1. Surveillance cameras

[0474] The terminals consist of surveillance cameras installed in disaster areas. These cameras collect video data in real time and transmit it to a server.

[0475] 2. Server

[0476] The server receives video data sent from the surveillance camera, and first pre-processes the received data to remove noise.

[0477] The server then analyzes the pre-processed data using generative AI, which focuses on evaluating the number of people, their behavioral trends, and the flow of goods.

[0478] Based on the analysis results of the generating AI, the server runs an algorithm to determine the priority of recovery and the delivery destination of the goods.

[0479] The server notifies the user's mobile information terminal of the determined priority and delivery destination information.

[0480] 3. Users

[0481] The users are on-site managers and response teams, and receive information provided by the server using mobile information terminals.

[0482] Users can use a dashboard that visually displays recovery efforts and delivery information, and direct local response teams.

[0483] Program processing

[0484] Hardware and Software

[0485] Hardware: surveillance cameras, servers, mobile devices (smartphones and tablets).

[0486] Software: OpenCV library, some_ai_library, Flask server.

[0487] Program Flow

[0488] The server receives video data transmitted in real time from the surveillance cameras and stores it in a database.

[0489] Next, the video data is preprocessed using the OpenCV library, in particular by applying a Gaussian filter to remove noise.

[0490] The pre-processed data is sent to some_ai_library's generative AI model to analyze the number of people, behavioral trends, and flow of goods.

[0491] Based on the analysis results, an algorithm is run to determine restoration priorities and delivery destinations for goods.

[0492] The results are sent to the mobile information terminal, and the user can receive the information via push notifications or a dashboard.

[0493] Specific examples

[0494] For example, if a major earthquake occurs and major roads are closed, the system will analyze video footage from surveillance cameras in various locations in real time. As a result, it will identify evacuation centers where people are gathering and set those locations as priority delivery destinations for supplies. It will also be possible to prioritize reopening roads with heavy traffic. This information will be sent to mobile devices, and users can visually check it on their dashboard.

[0495] Example prompts for generative AI models

[0496] "Analyze surveillance camera footage during a disaster to determine priority recovery efforts and delivery destinations. Pay attention to the number of people, their behavioral trends, and the flow of goods."

[0497] Overview of available systems

[0498] This system will enable a prompt and appropriate response in the event of a disaster, and will realize the efficient distribution of supplies and the streamlining of recovery work. It will also enable users to receive information in real time and give prompt instructions on on-site response.

[0499] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0500] Step 1:

[0501] The server receives video data in real time from surveillance cameras installed in the disaster area. Each surveillance camera transmits video of the scene to the server in streaming format. The input video data is transmitted from the surveillance cameras, and the output is stored in a database.

[0502] Step 2:

[0503] The server preprocesses the received video data. Specifically, it applies a Gaussian filter using the OpenCV library to remove noise. The input is the video data saved in step 1, and the output is preprocessed, clear video data.

[0504] Step 3:

[0505] The preprocessed data is input from the server into the generative AI model. Specifically, some_ai_library is used to perform video analysis and evaluate the number of people, behavioral trends, and flow of goods. The input is the preprocessed data, and the output is the analysis results. An example of a prompt sentence is input to the generative AI: "Analyze surveillance camera footage from the time of the disaster and determine the highest priority recovery work and delivery destinations for goods. Please place emphasis on the number of people, behavioral trends, and flow of goods."

[0506] Step 4:

[0507] The server runs an algorithm to determine restoration priorities and delivery destinations based on the analysis results of the generation AI. The input is the analysis results, and the output is a list of priorities and delivery destinations for the items.

[0508] Step 5:

[0509] The server notifies the user of the determined priority and delivery destination information. Specifically, it uses a RESTful API to send information to the user's mobile information device (smartphone or tablet). The input is a list of priorities and delivery destinations, and the output is a notification sent to the user's mobile information device.

[0510] Step 6:

[0511] Users receive notifications on their devices and use a dashboard that visually displays information on recovery efforts and supply delivery. The input is notifications sent from the server, and the output is a visual display. For example, users can check the priority of evacuation shelters and congested roads through the dashboard and issue instructions to on-site teams.

[0512] 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.

[0513] This invention combines a system that collects surveillance camera video data in real time, analyzes it with generative AI to determine restoration priorities and delivery destinations for supplies, and provides the system to users with an emotion engine that recognizes user emotions, further improving the efficiency and accuracy of disaster response.

[0514] overview

[0515] In order to realize a rapid and appropriate response in the event of a disaster, the system of the present invention collects video data from surveillance cameras and analyzes that data using a generative AI. Based on the results of this analysis, it determines recovery priorities and delivery destinations for goods, taking into account the user's emotional information to make optimal decisions.

[0516] System configuration

[0517] 1. Surveillance cameras

[0518] The terminals consist of surveillance cameras installed in disaster areas. These cameras collect video data in real time and transmit it to a server.

[0519] 2. Server

[0520] The server receives video data sent from the surveillance camera, and first performs preprocessing on the received data to remove noise.

[0521] The server then analyzes the pre-processed data using generative AI, which focuses on evaluating the number of people, their behavioral trends, and the flow of goods.

[0522] The server runs an algorithm that determines the priority of recovery and the delivery destination of goods based on the analysis results of the generating AI.

[0523] The server uses an emotion engine to recognize the user's emotions, reflects them in the analysis results, and makes optimal decisions.

[0524] 3. Users

[0525] Users of this system are on-site managers and response teams. They check the information provided by the server and issue instructions for on-site recovery work and delivery of goods.

[0526] Explanation of program processing

[0527] 1. Data Collection

[0528] The server receives video data from multiple surveillance cameras (terminals) in real time and stores it in a database.

[0529] Example: A server receives data every second from cameras installed at major intersections and public facilities in the city.

[0530] 2. Data Preprocessing

[0531] The server performs filtering to remove noise from the collected video data, thereby improving the accuracy of the analysis.

[0532] Example: The server uses a Gaussian filter to reduce unwanted image noise.

[0533] 3. Data Analysis

[0534] The server inputs the preprocessed data into a generative AI to analyze the number of people, behavioral trends, and flow of goods.

[0535] Example: AI detects people and vehicles appearing in video footage and analyzes their location and movement.

[0536] 4. Emotion recognition

[0537] The server uses an emotion engine that recognizes the user's emotions in real time through an interface with the user.

[0538] Example: Emotional information is collected through facial recognition and voice analysis while the user is viewing information on a tablet.

[0539] 5. Priority and delivery destination determination

[0540] The server runs an algorithm that determines recovery priorities and delivery destinations for items based on the analysis results obtained from the generative AI and the emotional information from the emotion engine.

[0541] For example, AI can detect highly congested roads and determine which roads should be prioritized for restoration, or identify areas where goods are in short supply and prioritize deliveries to those areas.

[0542] 6. Provision of Information

[0543] The server provides the determined restoration priority and delivery destination information to the site administrator (user).

[0544] Example: The server uses a RESTful API to send information to the administrator's smartphone or tablet.

[0545] Explanation with concrete examples

[0546] In disaster areas, surveillance cameras installed on major roads and public facilities collect video data and send it to a server. The server preprocesses the received data and analyzes it using generative AI. For example, if a group of people is confirmed in a certain area, the AI ​​will determine that area as a priority destination for delivering food and water. Also, if a particular road is extremely congested, it will be set as the top priority for restoration.

[0547] At the same time, the emotion engine recognizes the user's emotions and sends them to the server. For example, if the user is feeling stressed, it can respond by speeding up the delivery of supplies to the affected area.

[0548] This information is then sent from the server to the user's device, who then issues instructions to the local response team, ensuring quick and efficient recovery efforts and delivery of supplies.

[0549] The processing flow will be explained below.

[0550] Step 1:

[0551] The server acquires video data in real time from each device (surveillance camera) installed in the disaster area. For example, it collects video every second from surveillance cameras installed at intersections and public facilities and stores it in a database.

[0552] Step 2:

[0553] The server preprocesses the acquired video data, specifically applying a noise reduction filter to the video data to improve image quality, for example, by using a Gaussian filter to reduce unwanted noise.

[0554] Step 3:

[0555] The server then inputs the preprocessed video data into a generative AI, which analyzes the number of people, their behavioral trends, and the flow of goods. For example, the AI ​​can recognize people and vehicles in the video and track their location and movement.

[0556] Step 4:

[0557] The server runs an algorithm to determine restoration priorities based on the analysis results obtained from the AI ​​generation. For example, if a particular road is extremely congested, it will be given top priority for restoration.

[0558] Step 5:

[0559] The server determines the delivery destination of the goods based on the analysis results. For example, if the analysis results indicate that there is a shortage of food or water in a certain area, the server sets that area as a priority delivery destination.

[0560] Step 6:

[0561] The server's emotion engine recognizes the user's emotions in real time through the user interface. This emotion information is then reflected in prioritization and delivery destination decisions. For example, if the user expresses emotions indicating stress or urgency, that information is used to reevaluate the priority.

[0562] Step 7:

[0563] The server provides the determined recovery priority and delivery destination information to the on-site administrator (user). As a specific example, it sends the information to the administrator's tablet or smartphone using a RESTful API.

[0564] Step 8:

[0565] The user can review the provided information and issue instructions to the local response team for restoration work and material delivery. For example, the user can review the priority information on the tablet and inform the restoration team of the roads that need to be repaired with the highest priority.

[0566] Step 9:

[0567] The user monitors the progress of the recovery and delivery of goods and modifies instructions as needed. For example, if unexpected difficulties arise along the way, the user responds by issuing new instructions.

[0568] Step 10:

[0569] The server continuously collects new data from the surveillance cameras and repeatedly pre-processes and analyzes it, enabling optimal decisions to be made based on the latest information.

[0570] Example 2

[0571] 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."

[0572] It is not easy to respond quickly and appropriately in the event of a disaster and accurately determine restoration priorities and delivery destinations. Furthermore, there is a lack of methods for making optimal decisions that take into account users' emotional information. Conventional technologies do not provide effective solutions to these issues, which means that the efficiency and accuracy of disaster response are not sufficiently ensured.

[0573] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting video data from monitoring devices in real time, means for preprocessing the collected video data, means for analyzing the preprocessed data using a generative AI model, means for determining restoration priorities and delivery destinations of goods based on the analysis results, means for recognizing the user's emotions, means for making optimal decisions based on the analysis results including the emotion data, and means for providing the determined priorities and delivery destination information to the user. This enables a quick and appropriate response in the event of a disaster and allows optimal decisions to be made taking the user's emotions into account.

[0574] "Surveillance equipment" is a general term for cameras and other imaging devices installed in disaster areas that collect video data in real time.

[0575] "Video data" refers to real-time images and video information collected by surveillance equipment.

[0576] "Preprocessing" refers to the process of removing noise from collected video data and performing initial data processing to improve the accuracy of analysis.

[0577] A "generative AI model" is an artificial intelligence model used to analyze collected and pre-processed video data to detect and analyze the number of people, behavioral trends, and flow of goods.

[0578] "Analysis results" refers to data derived by the generative AI model, such as the number of people, behavioral trends, and flow of goods.

[0579] "Recovery priority" is a standard for evaluating the importance of areas and infrastructure that require restoration in the event of a disaster, and determining the order in which they should be prioritized.

[0580] "Delivery destination of goods" refers to the location or area where necessary supplies should be delivered in the event of a disaster.

[0581] "Means for recognizing emotions" refers to technology that analyzes emotions in real time from the user's facial expressions, voice, etc., and feeds the results back to the system.

[0582] "Optimal judgment" is a process that comprehensively considers analysis results and emotional data to make the most appropriate decisions regarding recovery operations and delivery of goods.

[0583] "User" refers to administrators and response teams who use this system to respond to disasters.

[0584] This invention is a system for realizing a rapid and appropriate response in the event of a disaster. It collects video data from surveillance equipment in real time, analyzes it using a generative AI model, determines recovery priorities and delivery destinations for supplies, and provides them to users. In addition, by combining it with a means to recognize user emotions, the efficiency and accuracy of disaster response can be further improved.

[0585] System configuration

[0586] monitoring equipment

[0587] The terminals consist of surveillance equipment installed in disaster areas. These surveillance equipment collect video data in real time and transmit it to a server. Specifically, surveillance cameras installed at major intersections and public facilities are used.

[0588] server

[0589] The server receives the video data sent from the surveillance equipment and stores it in a database, typically an RDBMS such as MySQL.

[0590] The server preprocesses the received video data to remove noise, using the Gaussian filtering function of the OpenCV library.

[0591] The server then analyzes the pre-processed data using a generative AI model powered by TensorFlow to analyze the number of people, their behavioral trends, and the flow of goods.

[0592] The server runs an algorithm that determines the priority of recovery and delivery destination based on the analysis results, by integrating the urgency score and emotion recognition results.

[0593] The server uses an emotion engine through the user interface to recognize the user's emotions in real time, using emotion recognition APIs such as Microsoft Azure's Emotion API.

[0594] The server sends the determined priority and delivery information via a RESTful API to provide the user with the information.

[0595] User

[0596] Users are on-site managers and response teams who handle disaster response. They check the information provided by the server using a dedicated application or dashboard, and issue instructions for on-site recovery work and the delivery of supplies.

[0597] Specific examples

[0598] In disaster areas, surveillance cameras installed on major roads and public facilities collect video data and send it to a server. For example, if a group of people is spotted in a certain area, the generative AI model will determine that area as a priority destination for delivering food and water. Also, if a particular road is extremely congested, it will be designated as a top priority for restoration.

[0599] At the same time, the emotion engine recognizes the user's emotions and sends them to the server. While the user is checking information on the tablet, emotional information is collected through facial recognition and voice analysis. For example, if the user is feeling high levels of stress, the system can take action such as speeding up the delivery of supplies to the affected area.

[0600] This information is sent from the server to the user's device, allowing the user to provide specific instructions to the local response team, ensuring that recovery efforts and delivery of supplies are carried out quickly and efficiently.

[0601] Prompt Sentence Examples

[0602] You can use prompts like the following for your generative AI model:

[0603] "Analyze video data from within the city to assess crowds and road congestion."

[0604] "If there is a shortage of goods in a particular area, determine where to prioritize delivery."

[0605] "Based on user sentiment data, please suggest prioritized support measures for high-stress areas."

[0606] This system will enable a rapid and accurate response in the event of a disaster.

[0607] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0608] Step 1: Data collection

[0609] Input: Real-time video data from surveillance equipment.

[0610] How it works: Surveillance devices are installed in disaster areas and capture video data at 30 frames per second, which are then encoded and streamed to a server in real time.

[0611] Output: Real-time video data sent to the server.

[0612] Step 2: Receiving and storing data

[0613] Input: Real-time video data streamed from surveillance equipment.

[0614] Specific operation: The server receives video data sent from multiple surveillance devices and stores it in a database (e.g., MySQL) in H.264 format.

[0615] Output: Raw video data stored in a database.

[0616] Step 3: Preprocessing for noise reduction

[0617] Input: Raw video data stored in a database.

[0618] Specific operation: The server uses the Gaussian filtering function of the OpenCV library to remove noise from the received video data.

[0619] Output: Denoised video data.

[0620] Step 4: Analyzing the video data

[0621] Input: Denoised video data.

[0622] How it works: The server inputs video data into a generative AI model using TensorFlow to analyze the number of people, behavioral trends, and flow of goods. Specifically, it detects people and vehicles in the video and identifies their location information and movement patterns.

[0623] Output: Data on the number of people, behavioral trends, and flow of goods analyzed by the generative AI model.

[0624] Step 5: Performing Emotion Recognition

[0625] Input: Facial expressions and voice data as users interact with tablets and smartphones through the interface.

[0626] Specific operation: The server analyzes the voice and facial expression data collected from tablets and smartphones using emotion recognition APIs such as Microsoft Azure's Emotion API.

[0627] Output: Parsed user emotion data.

[0628] Step 6: Prioritize and route your delivery

[0629] Input: Analysis results from the generative AI model and emotion data obtained from emotion recognition.

[0630] How it works: The server aggregates this data and uses a priority algorithm to determine the priority of recovery and delivery destinations. For example, areas with high urgency scores and high user stress levels are given top priority.

[0631] Output: Priority and item delivery destination decision data.

[0632] Step 7: Provide information

[0633] Input: Priority and item destination determination data.

[0634] Specific operation: The server uses a RESTful API to send notifications to smartphones and tablets, and displays information in real time on a dedicated application or dashboard.

[0635] Output: Priority and delivery information displayed on a smartphone or tablet.

[0636] At each step, the server, terminal, and user work together to enable a rapid and optimal response in the event of a disaster.

[0637] (Application example 2)

[0638] 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."

[0639] Rapid and appropriate recovery efforts and delivery of supplies are extremely important in the event of a disaster. However, current systems have difficulty in determining priorities and delivery locations, fully reflecting user emotions and real-time situations. Furthermore, once priorities and delivery destinations have been determined, there is a lack of a means to quickly and effectively notify local managers and response teams. Therefore, a new system is needed to improve the efficiency and accuracy of disaster response.

[0640] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0641] In this invention, the server includes means for collecting surveillance camera video data in real time, means for preprocessing the collected video data, means for analyzing the preprocessed data using a generative AI, means for determining restoration priorities and delivery destinations, means for providing the restoration priorities and delivery destination information to a user and reflecting the information in the analysis results using an emotion engine that recognizes the user's emotions, and means for notifying a device such as a smartphone or smart glasses of the determined priorities and delivery destination information. This makes it possible to determine optimal restoration work and delivery destinations in real time while reflecting the user's emotions, and to quickly provide related information to a local manager.

[0642] A "surveillance camera" is a device for continuously monitoring a specific location or area and recording and transmitting video data in real time.

[0643] "Video data" refers to data including real-time video images collected by surveillance cameras and related information.

[0644] "Preprocessing" refers to the process of filtering and data cleaning to remove noise from collected video data and improve the accuracy of analysis.

[0645] "Generative AI" is an artificial intelligence technology that learns from large amounts of data and analyzes video data.

[0646] The "emotion engine" is a system that recognizes the user's emotions and reflects that information in the analysis results.

[0647] "Recovery priority" is a criterion for determining which areas and tasks should be given priority when carrying out recovery work after a disaster.

[0648] "Delivery destination of goods" is an address that indicates the location where necessary supplies should be delivered first in the event of a disaster.

[0649] "Users" are the on-site managers and response teams who operate the system and instruct recovery work and delivery of goods.

[0650] "Notification" is the means by which the system communicates analysis results and decisions to the user in real time.

[0651] A "smartphone" is a portable information terminal that has the functionality of a mobile phone and can run a variety of applications.

[0652] "Smart glasses" are a type of wearable device, an electronic device in the shape of glasses that provides visual information to the user.

[0653] This invention is a system for realizing rapid and appropriate recovery efforts and delivery of supplies in the event of a disaster. This system collects video data from surveillance cameras in real time and analyzes it using generative AI and an emotion engine to determine recovery priorities and delivery destinations. It also reflects the user's emotions and quickly provides the analysis results to on-site managers and response teams.

[0654] The server first receives video data from multiple surveillance cameras in real time and stores it in a database. The video data is then filtered in the pre-processing stage to remove noise. A Gaussian filter is applied using a framework such as OpenCV. The pre-processed data is then input into a generative AI model (e.g., TensorFlow or PyTorch) to detect people and objects.

[0655] Based on the analysis results of the Generative AI, the server runs an algorithm to determine restoration priorities and delivery destinations. This algorithm primarily analyzes the number of people, their behavioral trends, and the flow of goods. Furthermore, it collects and analyzes user emotional information through an emotion engine (e.g., Microsoft Azure Face API or Affectiva), which is reflected in the Generative AI's analysis results. This allows for prioritization of restoration efforts and delivery of goods in areas where users are experiencing high levels of stress or anxiety.

[0656] The determined restoration priority and delivery destination information are sent to devices such as smartphones or smart glasses. Based on this notification information, users can instruct on-site restoration work and item delivery. Specifically, information is displayed in real time on the user's smartphone or smart glasses, and notifications can be received by voice or vibration if necessary.

[0657] For example, in disaster areas, surveillance cameras installed on major roads and public facilities collect video data, which is then sent to a server. The server preprocesses the video data and analyzes it using generative AI. If a large number of people are gathered in a certain area, the server will determine that area as a priority destination for the delivery of food and water. Also, if a particular road is extremely congested, the server will set that road as the top priority for restoration. At the same time, the emotion engine will recognize the user's emotions, and if the user is feeling stressed, it can take action such as speeding up the delivery of supplies to that area.

[0658] An example prompt is:

[0659] "I want to build a system that collects surveillance camera footage from disaster areas in real time and analyzes it using generative AI. Based on the results of this analysis, I want to determine recovery priorities and delivery destinations for supplies. I also want to take user sentiment into account when making these decisions. What frameworks and APIs should I use?"

[0660] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0661] Step 1:

[0662] The server receives video data from the surveillance cameras in real time. Each surveillance camera transmits its video data via the Internet, and the server stores it in a database. The input is the video data from the surveillance cameras, and the output is the stored video data that is subjected to pre-processing.

[0663] Step 2:

[0664] The server preprocesses the collected video data. Specifically, it applies a Gaussian filter using OpenCV to remove noise. The input of this process is the stored video data, and the output is the denoised video data.

[0665] Step 3:

[0666] The server inputs the preprocessed data into a generative AI model for analysis. This model is built using TensorFlow and PyTorch and detects the number of people, behavioral trends, and flow of goods. The input for this process is the preprocessed video data, and the output is the data obtained as the analysis results (e.g., number of people, behavioral patterns, and location information of goods).

[0667] Step 4:

[0668] The server runs an algorithm that determines restoration priorities and delivery destinations based on the analysis results. The algorithm evaluates people's density and behavioral patterns to identify high-priority areas and necessary supplies. The input to this process is the analysis results, and the output is a list of restoration priorities and a list of delivery destinations for supplies.

[0669] Step 5:

[0670] The device receives emotional information from the user as input and analyzes it using an emotion engine. The emotion engine (e.g., Microsoft Azure Face API) analyzes the user's level of stress or anxiety from their facial expressions and voice. The input to this process is the user's emotional information, and the output is analyzed emotional data.

[0671] Step 6:

[0672] The server integrates the analysis results from the emotion engine with those from the generation AI and reflects them in the priority determination process. This allows areas where users are feeling high stress to be given a higher priority. The inputs to this process are emotion data and the analysis results from the generation AI, and the output is a recovery priority list that takes emotion into account and a list of delivery destinations for goods.

[0673] Step 7:

[0674] The server notifies the determined recovery priority and delivery destination information to devices such as smartphones and smart glasses. Information is sent in real time using a RESTful API, and various data is displayed on the user's device. The input to this process is a recovery priority list that takes emotions into account and a list of delivery destinations for items, and the output is notification information displayed on the user's device.

[0675] 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.

[0676] 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.

[0677] 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.

[0678] [Third embodiment]

[0679] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0680] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0681] 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).

[0682] 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.

[0683] 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.

[0684] 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).

[0685] 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.

[0686] 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.

[0687] 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.

[0688] 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.

[0689] 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.

[0690] 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."

[0691] The present invention relates to a system that collects video data from surveillance cameras in real time, analyzes it using a generative AI, determines restoration priorities and delivery destinations for goods, and provides the results to users. The system of the present invention is specifically implemented as follows.

[0692] overview

[0693] In order to realize a rapid and appropriate response in the event of a disaster, the system of the present invention collects video data from surveillance cameras and analyzes that data using AI. Based on the results of this analysis, recovery priorities and delivery destinations for supplies are determined and provided to the user.

[0694] System configuration

[0695] 1. Surveillance cameras

[0696] The terminals consist of surveillance cameras installed in disaster areas. These cameras collect video data in real time and transmit it to a server.

[0697] 2. Server

[0698] The server receives video data sent from the surveillance camera, and first performs preprocessing on the received data to remove noise.

[0699] The server then analyzes the pre-processed data using generative AI, which focuses on evaluating the number of people, their behavioral trends, and the flow of goods.

[0700] The server runs an algorithm that determines the priority of recovery and the delivery destination of goods based on the analysis results of the generating AI.

[0701] 3. Users

[0702] Users of this system are on-site managers and response teams. They check the information provided by the server and issue instructions for on-site recovery work and delivery of goods.

[0703] Explanation of program processing

[0704] 1. Data Collection

[0705] The server receives video data from multiple surveillance cameras (terminals) in real time and stores it in a database.

[0706] Example: A server receives data every second from cameras installed at major intersections and public facilities in the city.

[0707] 2. Data Preprocessing

[0708] The server performs filtering to remove noise from the collected video data, thereby improving the accuracy of the analysis.

[0709] Example: The server applies a Gaussian filter to reduce unwanted image noise.

[0710] 3. Data Analysis

[0711] The server inputs the preprocessed data into a generative AI to analyze the number of people, behavioral trends, and flow of goods.

[0712] Example: AI detects people and vehicles appearing in video footage and analyzes their location and movement.

[0713] 4. Priority and delivery destination determination

[0714] The server runs an algorithm that determines recovery priorities and delivery destinations for items based on the analysis results obtained from the generation AI.

[0715] For example, AI can detect highly congested roads and determine which roads should be prioritized for restoration, or identify areas where goods are in short supply and prioritize deliveries to those areas.

[0716] 5. Provision of Information

[0717] The server provides the determined priority and delivery destination information to the site manager (user).

[0718] Example: The server uses a RESTful API to send information to the administrator's smartphone or tablet.

[0719] Explanation with concrete examples

[0720] In disaster areas, surveillance cameras installed on major roads and public facilities collect video data and send it to a server. The server preprocesses the received data and analyzes it using generative AI. For example, if a group of people is confirmed in a certain area, the AI ​​will determine that area as a priority destination for delivering food and water. Also, if a particular road is extremely congested, it will be set as the top priority for restoration.

[0721] This information is then sent from the server to the user's device, who then issues instructions to the local response team, ensuring quick and efficient recovery efforts and delivery of supplies.

[0722] The processing flow will be explained below.

[0723] Step 1:

[0724] The server acquires video data in real time from each device (surveillance camera) installed in the disaster area. For example, it collects video every second from surveillance cameras installed at intersections and public facilities and stores it in a database.

[0725] Step 2:

[0726] The server preprocesses the acquired video data, specifically applying a noise reduction filter to the video data to improve image quality, for example, by using a Gaussian filter to reduce unwanted noise.

[0727] Step 3:

[0728] The server then inputs the preprocessed video data into a generative AI, which analyzes the number of people, their behavioral trends, and the flow of goods. Specifically, the AI ​​recognizes people and objects in the video and tracks their location and movement.

[0729] Step 4:

[0730] The server runs an algorithm to determine restoration priorities based on the analysis results obtained from the AI ​​generation. For example, if a particular road is extremely congested, it will be given top priority for restoration.

[0731] Step 5:

[0732] The server determines the delivery destination of the goods based on the analysis results. For example, if the analysis results indicate that there is a shortage of food or water in a certain area, the server sets that area as a priority delivery destination.

[0733] Step 6:

[0734] The server provides the determined recovery priority and delivery destination information to the on-site administrator (user). As a specific example, it sends the information to the administrator's tablet using a RESTful API.

[0735] Step 7:

[0736] The user can review the provided information and issue instructions to the local response team for restoration work and material delivery. For example, the user can review the priority information on the tablet and inform the restoration team of the roads that need to be repaired with the highest priority.

[0737] Step 8:

[0738] The user monitors the progress of the recovery and delivery of goods and modifies instructions as needed. For example, if unexpected difficulties arise along the way, the user responds by issuing new instructions.

[0739] Step 9:

[0740] The server continuously collects new data from the surveillance cameras and repeatedly pre-processes and analyzes it, enabling optimal decisions to be made based on the latest information.

[0741] Example 1

[0742] 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."

[0743] A rapid and appropriate response in the event of a disaster is crucial for preventing damage from spreading and for efficiently advancing recovery. However, conventional methods have the problem of making it difficult to grasp the situation on-site in real time and determine effective recovery priorities and supply delivery destinations. Another issue is the lack of a means to quickly and accurately convey this information to on-site response teams.

[0744] 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.

[0745] In this invention, the server includes: means for collecting surveillance camera video data in real time; means for preprocessing the collected video data; means for analyzing the preprocessed data using a generative AI; means for determining restoration priorities and delivery destinations based on the analysis results; means for providing the determined priorities and delivery destination information to an end-user device; and means for transmitting instructions from the end-user device to a local response team based on the provided information. This enables accurate understanding of the on-site situation in real time and prompt and appropriate determination of restoration priorities and delivery destinations. Furthermore, by quickly communicating this information to relevant parties, the efficiency and accuracy of response can be improved.

[0746] A "surveillance camera" is a device that captures video data of a specific area in real time.

[0747] "Video data" refers to image information captured by a surveillance camera and is typically stored in digital form.

[0748] "Preprocessing" refers to data processing to make subsequent analysis easier, such as removing noise from collected video data or adjusting resolution.

[0749] "Generative AI" is a model that uses artificial intelligence technology to analyze video data and recognize specific patterns.

[0750] "Analysis" refers to data processing to extract specific information (e.g., number of people, behavioral patterns, flow of goods, etc.) based on preprocessed video data.

[0751] "Recovery priority" is an evaluation criterion for determining the order in which recovery work should be carried out in the event of a disaster.

[0752] "Delivery destination of goods" is an indicator for determining to which region or location the required goods should be delivered.

[0753] "End-user devices" refers to devices such as smartphones, tablets, and computers used by local response teams and administrators.

[0754] "Instructions" are messages sent from end-user devices to local response teams with specific action plans and priorities.

[0755] The present invention relates to a system that collects video data from surveillance cameras in real time, analyzes it using a generative AI, determines restoration priorities and delivery destinations for goods, and provides the results to users. The system of the present invention is specifically implemented as follows.

[0756] surveillance cameras

[0757] The device consists of multiple surveillance cameras installed in the disaster area. These cameras capture video data in real time and transmit the data to a server. Specifically, cameras installed at major intersections and public facilities in the city capture real-time video at 30 frames per second and transmit the data securely to the server using AES encryption.

[0758] server

[0759] The server has the function of receiving video data transmitted in real time from multiple surveillance cameras, and then stores the received video data in a database. The stored data also includes metadata such as timestamps and camera IDs.

[0760] The server preprocesses the collected data, including noise reduction using a Gaussian filter and image resolution adjustment, improving image quality and enhancing the accuracy of analysis.

[0761] The server then inputs the preprocessed data into the generative AI, which uses a pre-trained model to send a specific prompt to the model: "Analyze people's movements during a disaster and identify areas that should be prioritized."

[0762] The generative AI model analyzes the number of people, behavioral patterns, and flow of goods in the video. This includes person detection, location tracking, and behavior classification. For example, the generative AI model detects people and vehicles appearing in the video and analyzes their location and movement.

[0763] The server runs an algorithm that determines restoration priorities and delivery destinations based on the analysis results obtained from the generative AI model. For example, it detects highly congested roads and sets them as the highest priority for restoration. It also identifies areas where supplies are in short supply and determines priority delivery destinations for those areas.

[0764] User

[0765] Users are on-site managers and response teams. The server provides the determined priority and delivery destination information to the user's smartphone or tablet via a RESTful API. The user then issues specific instructions to the local response team based on that information. For example, if a group of people is confirmed in a certain area, the user determines that area as a priority destination for the delivery of food and water, and issues specific instructions such as "restore the main roads in area A as the top priority" or "deliver food to area B as a priority."

[0766] This system will enable efficient and rapid disaster response, preventing damage from spreading and contributing to early recovery.

[0767] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0768] Step 1:

[0769] The terminal captures real-time video data of the target area through installed surveillance cameras. Specifically, surveillance cameras installed at major intersections and public facilities in the city generate video at 30 frames per second and send it to a server using AES encryption. The input is the captured raw video data, and the output is the encrypted video data.

[0770] Step 2:

[0771] The server stores the encrypted video data received from the device in a database. The input is encrypted video data, and the output is video data stored in the database. Specifically, the server immediately stores the received data in the database and adds a timestamp and camera ID as metadata.

[0772] Step 3:

[0773] The server performs preprocessing on the stored video data. Specifically, it applies a Gaussian filter to remove noise from the collected video data and adjusts the resolution. The input is the raw video data stored in the database, and the output is preprocessed video data with noise removed. The server stores the data after this preprocessing in another database or cache.

[0774] Step 4:

[0775] The server inputs the preprocessed video data into the generative AI model. It then sends the model a prompt, saying, "Analyze people's movements during a disaster and identify areas that should be prioritized," and begins analysis. The input is the preprocessed video data and the prompt, and the output is the analysis results. The generative AI model performs a detailed analysis of the number of people in the video, their behavioral patterns, and the flow of goods, and returns the results to the server.

[0776] Step 5:

[0777] The server runs an algorithm that determines restoration priorities and delivery destinations for supplies based on the analysis results obtained from the generative AI model. For example, it prioritizes restoration of highly congested roads and creates a priority delivery plan for areas where supplies are in short supply. The input is the analysis results of the generative AI model, and the output is restoration priorities and delivery destination information for supplies.

[0778] Step 6:

[0779] The server provides the determined priority and delivery destination information to the end-user device. Specifically, it uses a RESTful API to send the information to the user's smartphone or tablet. The input is the recovery priority and delivery destination information, and the output is the information sent to the user's end-user device.

[0780] Step 7:

[0781] Based on the information received from the server, the user sends specific instructions to the local response team, such as "Give top priority to restoring the main roads in area A" or "Give priority to delivering food to area B." The input is the information provided by the server, and the output is the specific instructions to the local response team.

[0782] (Application example 1)

[0783] 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."

[0784] In the event of a disaster, a rapid and appropriate response is required, but in many cases, it takes time to grasp the situation on-site, which leads to problems such as delays in recovery work and the delivery of supplies. Furthermore, appropriate resources may not be deployed to the necessary locations, making it difficult to respond efficiently. To resolve these situations, a system is needed that can accurately grasp the situation on-site in real time, clarify priorities, and respond quickly.

[0785] 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.

[0786] In this invention, the server includes means for collecting surveillance camera video data in real time, means for preprocessing the collected video data, means for analyzing the preprocessed data using a generation AI, means for determining restoration priorities and delivery destinations based on the analysis results, means for providing the determined priorities and delivery destination information to a user, means for notifying the user of the analysis results on a mobile information terminal, and means for visually displaying information on restoration work and delivery of goods, thereby enabling restoration work and delivery of goods to be carried out quickly and efficiently.

[0787] A "surveillance camera" is a device installed in a disaster area that collects video data in real time.

[0788] "Preprocessing" is a data processing method for removing noise from collected video data and improving the accuracy of analysis.

[0789] "Generative AI" is an artificial intelligence model that analyzes collected data to assess the number of people, trends in their behavior, and the flow of goods, and to determine recovery priorities and delivery destinations for goods.

[0790] "Recovery priority" is a criterion for evaluating the urgency of recovery work at a disaster site and determining which work should be given priority.

[0791] "Delivery destination of goods" is information that determines the location to which relief supplies and necessary goods should be delivered.

[0792] "Users" refers to the on-site managers and response teams who use this system.

[0793] A "mobile information terminal" is a portable information processing device such as a smartphone or tablet.

[0794] "Visual display of information on restoration work and goods delivery" is a function that displays the priority and delivery destination of restoration work and goods delivery in a form that is easy for the user to see.

[0795] This invention is a system for realizing a rapid and appropriate response in the event of a disaster. It collects video data from surveillance cameras in real time and analyzes it with a generative AI to determine recovery priorities and delivery destinations for goods, and provides the results to users. This system is specifically implemented as follows.

[0796] System configuration

[0797] 1. Surveillance cameras

[0798] The terminals consist of surveillance cameras installed in disaster areas. These cameras collect video data in real time and transmit it to a server.

[0799] 2. Server

[0800] The server receives video data sent from the surveillance camera, and first pre-processes the received data to remove noise.

[0801] The server then analyzes the pre-processed data using generative AI, which focuses on evaluating the number of people, their behavioral trends, and the flow of goods.

[0802] Based on the analysis results of the generating AI, the server runs an algorithm to determine the priority of recovery and the delivery destination of the goods.

[0803] The server notifies the user's mobile information terminal of the determined priority and delivery destination information.

[0804] 3. Users

[0805] The users are on-site managers and response teams, and receive information provided by the server using mobile information terminals.

[0806] Users can use a dashboard that visually displays recovery efforts and delivery information, and direct local response teams.

[0807] Program processing

[0808] Hardware and Software

[0809] Hardware: surveillance cameras, servers, mobile devices (smartphones and tablets).

[0810] Software: OpenCV library, some_ai_library, Flask server.

[0811] Program Flow

[0812] The server receives video data transmitted in real time from the surveillance cameras and stores it in a database.

[0813] Next, the video data is preprocessed using the OpenCV library, in particular by applying a Gaussian filter to remove noise.

[0814] The pre-processed data is sent to some_ai_library's generative AI model to analyze the number of people, behavioral trends, and flow of goods.

[0815] Based on the analysis results, an algorithm is run to determine restoration priorities and delivery destinations for goods.

[0816] The results are sent to the mobile information terminal, and the user can receive the information via push notifications or a dashboard.

[0817] Specific examples

[0818] For example, if a major earthquake occurs and major roads are closed, the system will analyze video footage from surveillance cameras in various locations in real time. As a result, it will identify evacuation centers where people are gathering and set those locations as priority delivery destinations for supplies. It will also be possible to prioritize reopening roads with heavy traffic. This information will be sent to mobile devices, and users can visually check it on their dashboard.

[0819] Example prompts for generative AI models

[0820] "Analyze surveillance camera footage during a disaster to determine priority recovery efforts and delivery destinations. Pay attention to the number of people, their behavioral trends, and the flow of goods."

[0821] Overview of available systems

[0822] This system will enable a prompt and appropriate response in the event of a disaster, and will realize the efficient distribution of supplies and the streamlining of recovery work. It will also enable users to receive information in real time and give prompt instructions on on-site response.

[0823] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0824] Step 1:

[0825] The server receives video data in real time from surveillance cameras installed in the disaster area. Each surveillance camera transmits video of the scene to the server in streaming format. The input video data is transmitted from the surveillance cameras, and the output is stored in a database.

[0826] Step 2:

[0827] The server preprocesses the received video data. Specifically, it applies a Gaussian filter using the OpenCV library to remove noise. The input is the video data saved in step 1, and the output is preprocessed, clear video data.

[0828] Step 3:

[0829] The preprocessed data is input from the server into the generative AI model. Specifically, some_ai_library is used to perform video analysis and evaluate the number of people, behavioral trends, and flow of goods. The input is the preprocessed data, and the output is the analysis results. An example of a prompt sentence is input to the generative AI: "Analyze surveillance camera footage from the time of the disaster and determine the highest priority recovery work and delivery destinations for goods. Please place emphasis on the number of people, behavioral trends, and flow of goods."

[0830] Step 4:

[0831] The server runs an algorithm to determine restoration priorities and delivery destinations based on the analysis results of the generation AI. The input is the analysis results, and the output is a list of priorities and delivery destinations for the items.

[0832] Step 5:

[0833] The server notifies the user of the determined priority and delivery destination information. Specifically, it uses a RESTful API to send information to the user's mobile information device (smartphone or tablet). The input is a list of priorities and delivery destinations, and the output is a notification sent to the user's mobile information device.

[0834] Step 6:

[0835] Users receive notifications on their devices and use a dashboard that visually displays information on recovery efforts and supply delivery. The input is notifications sent from the server, and the output is a visual display. For example, users can check the priority of evacuation shelters and congested roads through the dashboard and issue instructions to on-site teams.

[0836] 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.

[0837] This invention combines a system that collects surveillance camera video data in real time, analyzes it with generative AI to determine restoration priorities and delivery destinations for supplies, and provides the system to users with an emotion engine that recognizes user emotions, further improving the efficiency and accuracy of disaster response.

[0838] overview

[0839] In order to realize a rapid and appropriate response in the event of a disaster, the system of the present invention collects video data from surveillance cameras and analyzes that data using a generative AI. Based on the results of this analysis, it determines recovery priorities and delivery destinations for goods, taking into account the user's emotional information to make optimal decisions.

[0840] System configuration

[0841] 1. Surveillance cameras

[0842] The terminals consist of surveillance cameras installed in disaster areas. These cameras collect video data in real time and transmit it to a server.

[0843] 2. Server

[0844] The server receives video data sent from the surveillance camera, and first performs preprocessing on the received data to remove noise.

[0845] The server then analyzes the pre-processed data using generative AI, which focuses on evaluating the number of people, their behavioral trends, and the flow of goods.

[0846] The server runs an algorithm that determines the priority of recovery and the delivery destination of goods based on the analysis results of the generating AI.

[0847] The server uses an emotion engine to recognize the user's emotions, reflects them in the analysis results, and makes optimal decisions.

[0848] 3. Users

[0849] Users of this system are on-site managers and response teams. They check the information provided by the server and issue instructions for on-site recovery work and delivery of goods.

[0850] Explanation of program processing

[0851] 1. Data Collection

[0852] The server receives video data from multiple surveillance cameras (terminals) in real time and stores it in a database.

[0853] Example: A server receives data every second from cameras installed at major intersections and public facilities in the city.

[0854] 2. Data Preprocessing

[0855] The server performs filtering to remove noise from the collected video data, thereby improving the accuracy of the analysis.

[0856] Example: The server uses a Gaussian filter to reduce unwanted image noise.

[0857] 3. Data Analysis

[0858] The server inputs the preprocessed data into a generative AI to analyze the number of people, behavioral trends, and flow of goods.

[0859] Example: AI detects people and vehicles appearing in video footage and analyzes their location and movement.

[0860] 4. Emotion recognition

[0861] The server uses an emotion engine that recognizes the user's emotions in real time through an interface with the user.

[0862] Example: Emotional information is collected through facial recognition and voice analysis while the user is viewing information on a tablet.

[0863] 5. Priority and delivery destination determination

[0864] The server runs an algorithm that determines recovery priorities and delivery destinations for items based on the analysis results obtained from the generative AI and the emotional information from the emotion engine.

[0865] For example, AI can detect highly congested roads and determine which roads should be prioritized for restoration, or identify areas where goods are in short supply and prioritize deliveries to those areas.

[0866] 6. Provision of Information

[0867] The server provides the determined restoration priority and delivery destination information to the site administrator (user).

[0868] Example: The server uses a RESTful API to send information to the administrator's smartphone or tablet.

[0869] Explanation with concrete examples

[0870] In disaster areas, surveillance cameras installed on major roads and public facilities collect video data and send it to a server. The server preprocesses the received data and analyzes it using generative AI. For example, if a group of people is confirmed in a certain area, the AI ​​will determine that area as a priority destination for delivering food and water. Also, if a particular road is extremely congested, it will be set as the top priority for restoration.

[0871] At the same time, the emotion engine recognizes the user's emotions and sends them to the server. For example, if the user is feeling stressed, it can respond by speeding up the delivery of supplies to the affected area.

[0872] This information is then sent from the server to the user's device, who then issues instructions to the local response team, ensuring quick and efficient recovery efforts and delivery of supplies.

[0873] The processing flow will be explained below.

[0874] Step 1:

[0875] The server acquires video data in real time from each device (surveillance camera) installed in the disaster area. For example, it collects video every second from surveillance cameras installed at intersections and public facilities and stores it in a database.

[0876] Step 2:

[0877] The server preprocesses the acquired video data, specifically applying a noise reduction filter to the video data to improve image quality, for example, by using a Gaussian filter to reduce unwanted noise.

[0878] Step 3:

[0879] The server then inputs the preprocessed video data into a generative AI, which analyzes the number of people, their behavioral trends, and the flow of goods. For example, the AI ​​can recognize people and vehicles in the video and track their location and movement.

[0880] Step 4:

[0881] The server runs an algorithm to determine restoration priorities based on the analysis results obtained from the AI ​​generation. For example, if a particular road is extremely congested, it will be given top priority for restoration.

[0882] Step 5:

[0883] The server determines the delivery destination of the goods based on the analysis results. For example, if the analysis results indicate that there is a shortage of food or water in a certain area, the server sets that area as a priority delivery destination.

[0884] Step 6:

[0885] The server's emotion engine recognizes the user's emotions in real time through the user interface. This emotion information is then reflected in prioritization and delivery destination decisions. For example, if the user expresses emotions indicating stress or urgency, that information is used to reevaluate the priority.

[0886] Step 7:

[0887] The server provides the determined recovery priority and delivery destination information to the on-site administrator (user). As a specific example, it sends the information to the administrator's tablet or smartphone using a RESTful API.

[0888] Step 8:

[0889] The user can review the provided information and issue instructions to the local response team for restoration work and material delivery. For example, the user can review the priority information on the tablet and inform the restoration team of the roads that need to be repaired with the highest priority.

[0890] Step 9:

[0891] The user monitors the progress of the recovery and delivery of goods and modifies instructions as needed. For example, if unexpected difficulties arise along the way, the user responds by issuing new instructions.

[0892] Step 10:

[0893] The server continuously collects new data from the surveillance cameras and repeatedly pre-processes and analyzes it, enabling optimal decisions to be made based on the latest information.

[0894] Example 2

[0895] 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."

[0896] It is not easy to respond quickly and appropriately in the event of a disaster and accurately determine restoration priorities and delivery destinations. Furthermore, there is a lack of methods for making optimal decisions that take into account users' emotional information. Conventional technologies do not provide effective solutions to these issues, which means that the efficiency and accuracy of disaster response are not sufficiently ensured.

[0897] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting video data from monitoring devices in real time, means for preprocessing the collected video data, means for analyzing the preprocessed data using a generative AI model, means for determining restoration priorities and delivery destinations of goods based on the analysis results, means for recognizing the user's emotions, means for making optimal decisions based on the analysis results including the emotion data, and means for providing the determined priorities and delivery destination information to the user. This enables a quick and appropriate response in the event of a disaster and allows optimal decisions to be made taking the user's emotions into account.

[0898] "Surveillance equipment" is a general term for cameras and other imaging devices installed in disaster areas that collect video data in real time.

[0899] "Video data" refers to real-time images and video information collected by surveillance equipment.

[0900] "Preprocessing" refers to the process of removing noise from collected video data and performing initial data processing to improve the accuracy of analysis.

[0901] A "generative AI model" is an artificial intelligence model used to analyze collected and pre-processed video data to detect and analyze the number of people, behavioral trends, and flow of goods.

[0902] "Analysis results" refers to data derived by the generative AI model, such as the number of people, behavioral trends, and flow of goods.

[0903] "Recovery priority" is a standard for evaluating the importance of areas and infrastructure that require restoration in the event of a disaster, and determining the order in which they should be prioritized.

[0904] "Delivery destination of goods" refers to the location or area where necessary supplies should be delivered in the event of a disaster.

[0905] "Means for recognizing emotions" refers to technology that analyzes emotions in real time from the user's facial expressions, voice, etc., and feeds the results back to the system.

[0906] "Optimal judgment" is a process that comprehensively considers analysis results and emotional data to make the most appropriate decisions regarding recovery operations and delivery of goods.

[0907] "User" refers to administrators and response teams who use this system to respond to disasters.

[0908] This invention is a system for realizing a rapid and appropriate response in the event of a disaster. It collects video data from surveillance equipment in real time, analyzes it using a generative AI model, determines recovery priorities and delivery destinations for supplies, and provides them to users. In addition, by combining it with a means to recognize user emotions, the efficiency and accuracy of disaster response can be further improved.

[0909] System configuration

[0910] monitoring equipment

[0911] The terminals consist of surveillance equipment installed in disaster areas. These surveillance equipment collect video data in real time and transmit it to a server. Specifically, surveillance cameras installed at major intersections and public facilities are used.

[0912] server

[0913] The server receives the video data sent from the surveillance equipment and stores it in a database, typically an RDBMS such as MySQL.

[0914] The server preprocesses the received video data to remove noise, using the Gaussian filtering function of the OpenCV library.

[0915] The server then analyzes the pre-processed data using a generative AI model powered by TensorFlow to analyze the number of people, their behavioral trends, and the flow of goods.

[0916] The server runs an algorithm that determines the priority of recovery and delivery destination based on the analysis results, by integrating the urgency score and emotion recognition results.

[0917] The server uses an emotion engine through the user interface to recognize the user's emotions in real time, using emotion recognition APIs such as Microsoft Azure's Emotion API.

[0918] The server sends the determined priority and delivery information via a RESTful API to provide the user with the information.

[0919] User

[0920] Users are on-site managers and response teams who handle disaster response. They check the information provided by the server using a dedicated application or dashboard, and issue instructions for on-site recovery work and the delivery of supplies.

[0921] Specific examples

[0922] In disaster areas, surveillance cameras installed on major roads and public facilities collect video data and send it to a server. For example, if a group of people is spotted in a certain area, the generative AI model will determine that area as a priority destination for delivering food and water. Also, if a particular road is extremely congested, it will be designated as a top priority for restoration.

[0923] At the same time, the emotion engine recognizes the user's emotions and sends them to the server. While the user is checking information on the tablet, emotional information is collected through facial recognition and voice analysis. For example, if the user is feeling high levels of stress, the system can take action such as speeding up the delivery of supplies to the affected area.

[0924] This information is sent from the server to the user's device, allowing the user to provide specific instructions to the local response team, ensuring that recovery efforts and delivery of supplies are carried out quickly and efficiently.

[0925] Prompt Sentence Examples

[0926] You can use prompts like the following for your generative AI model:

[0927] "Analyze video data from within the city to assess crowds and road congestion."

[0928] "If there is a shortage of goods in a particular area, determine where to prioritize delivery."

[0929] "Based on user sentiment data, please suggest prioritized support measures for high-stress areas."

[0930] This system will enable a rapid and accurate response in the event of a disaster.

[0931] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0932] Step 1: Data collection

[0933] Input: Real-time video data from surveillance equipment.

[0934] How it works: Surveillance devices are installed in disaster areas and capture video data at 30 frames per second, which are then encoded and streamed to a server in real time.

[0935] Output: Real-time video data sent to the server.

[0936] Step 2: Receiving and storing data

[0937] Input: Real-time video data streamed from surveillance equipment.

[0938] Specific operation: The server receives video data sent from multiple surveillance devices and stores it in a database (e.g., MySQL) in H.264 format.

[0939] Output: Raw video data stored in a database.

[0940] Step 3: Preprocessing for noise reduction

[0941] Input: Raw video data stored in a database.

[0942] Specific operation: The server uses the Gaussian filtering function of the OpenCV library to remove noise from the received video data.

[0943] Output: Denoised video data.

[0944] Step 4: Analyzing the video data

[0945] Input: Denoised video data.

[0946] How it works: The server inputs video data into a generative AI model using TensorFlow to analyze the number of people, behavioral trends, and flow of goods. Specifically, it detects people and vehicles in the video and identifies their location information and movement patterns.

[0947] Output: Data on the number of people, behavioral trends, and flow of goods analyzed by the generative AI model.

[0948] Step 5: Performing Emotion Recognition

[0949] Input: Facial expressions and voice data as users interact with tablets and smartphones through the interface.

[0950] Specific operation: The server analyzes the voice and facial expression data collected from tablets and smartphones using emotion recognition APIs such as Microsoft Azure's Emotion API.

[0951] Output: Parsed user emotion data.

[0952] Step 6: Prioritize and route your delivery

[0953] Input: Analysis results from the generative AI model and emotion data obtained from emotion recognition.

[0954] How it works: The server aggregates this data and uses a priority algorithm to determine the priority of recovery and delivery destinations. For example, areas with high urgency scores and high user stress levels are given top priority.

[0955] Output: Priority and item delivery destination decision data.

[0956] Step 7: Provide information

[0957] Input: Priority and item destination determination data.

[0958] Specific operation: The server uses a RESTful API to send notifications to smartphones and tablets, and displays information in real time on a dedicated application or dashboard.

[0959] Output: Priority and delivery information displayed on a smartphone or tablet.

[0960] At each step, the server, terminal, and user work together to enable a rapid and optimal response in the event of a disaster.

[0961] (Application example 2)

[0962] 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."

[0963] Rapid and appropriate recovery efforts and delivery of supplies are extremely important in the event of a disaster. However, current systems have difficulty in determining priorities and delivery locations, fully reflecting user emotions and real-time situations. Furthermore, once priorities and delivery destinations have been determined, there is a lack of a means to quickly and effectively notify local managers and response teams. Therefore, a new system is needed to improve the efficiency and accuracy of disaster response.

[0964] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0965] In this invention, the server includes means for collecting surveillance camera video data in real time, means for preprocessing the collected video data, means for analyzing the preprocessed data using a generative AI, means for determining restoration priorities and delivery destinations, means for providing the restoration priorities and delivery destination information to a user and reflecting the information in the analysis results using an emotion engine that recognizes the user's emotions, and means for notifying a device such as a smartphone or smart glasses of the determined priorities and delivery destination information. This makes it possible to determine optimal restoration work and delivery destinations in real time while reflecting the user's emotions, and to quickly provide related information to a local manager.

[0966] A "surveillance camera" is a device for continuously monitoring a specific location or area and recording and transmitting video data in real time.

[0967] "Video data" refers to data including real-time video images collected by surveillance cameras and related information.

[0968] "Preprocessing" refers to the process of filtering and data cleaning to remove noise from collected video data and improve the accuracy of analysis.

[0969] "Generative AI" is an artificial intelligence technology that learns from large amounts of data and analyzes video data.

[0970] The "emotion engine" is a system that recognizes the user's emotions and reflects that information in the analysis results.

[0971] "Recovery priority" is a criterion for determining which areas and tasks should be given priority when carrying out recovery work after a disaster.

[0972] "Delivery destination of goods" is an address that indicates the location where necessary supplies should be delivered first in the event of a disaster.

[0973] "Users" are the on-site managers and response teams who operate the system and instruct recovery work and delivery of goods.

[0974] "Notification" is the means by which the system communicates analysis results and decisions to the user in real time.

[0975] A "smartphone" is a portable information terminal that has the functionality of a mobile phone and can run a variety of applications.

[0976] "Smart glasses" are a type of wearable device, an electronic device in the shape of glasses that provides visual information to the user.

[0977] This invention is a system for realizing rapid and appropriate recovery efforts and delivery of supplies in the event of a disaster. This system collects video data from surveillance cameras in real time and analyzes it using generative AI and an emotion engine to determine recovery priorities and delivery destinations. It also reflects the user's emotions and quickly provides the analysis results to on-site managers and response teams.

[0978] The server first receives video data from multiple surveillance cameras in real time and stores it in a database. The video data is then filtered in the pre-processing stage to remove noise. A Gaussian filter is applied using a framework such as OpenCV. The pre-processed data is then input into a generative AI model (e.g., TensorFlow or PyTorch) to detect people and objects.

[0979] Based on the analysis results of the Generative AI, the server runs an algorithm to determine restoration priorities and delivery destinations. This algorithm primarily analyzes the number of people, their behavioral trends, and the flow of goods. Furthermore, it collects and analyzes user emotional information through an emotion engine (e.g., Microsoft Azure Face API or Affectiva), which is reflected in the Generative AI's analysis results. This allows for prioritization of restoration efforts and delivery of goods in areas where users are experiencing high levels of stress or anxiety.

[0980] The determined restoration priority and delivery destination information are sent to devices such as smartphones or smart glasses. Based on this notification information, users can instruct on-site restoration work and item delivery. Specifically, information is displayed in real time on the user's smartphone or smart glasses, and notifications can be received by voice or vibration if necessary.

[0981] For example, in disaster areas, surveillance cameras installed on major roads and public facilities collect video data, which is then sent to a server. The server preprocesses the video data and analyzes it using generative AI. If a large number of people are gathered in a certain area, the server will determine that area as a priority destination for the delivery of food and water. Also, if a particular road is extremely congested, the server will set that road as the top priority for restoration. At the same time, the emotion engine will recognize the user's emotions, and if the user is feeling stressed, it can take action such as speeding up the delivery of supplies to that area.

[0982] An example prompt is:

[0983] "I want to build a system that collects surveillance camera footage from disaster areas in real time and analyzes it using generative AI. Based on the results of this analysis, I want to determine recovery priorities and delivery destinations for supplies. I also want to take user sentiment into account when making these decisions. What frameworks and APIs should I use?"

[0984] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0985] Step 1:

[0986] The server receives video data from the surveillance cameras in real time. Each surveillance camera transmits its video data via the Internet, and the server stores it in a database. The input is the video data from the surveillance cameras, and the output is the stored video data that is subjected to pre-processing.

[0987] Step 2:

[0988] The server preprocesses the collected video data. Specifically, it applies a Gaussian filter using OpenCV to remove noise. The input of this process is the stored video data, and the output is the denoised video data.

[0989] Step 3:

[0990] The server inputs the preprocessed data into a generative AI model for analysis. This model is built using TensorFlow and PyTorch and detects the number of people, behavioral trends, and flow of goods. The input for this process is the preprocessed video data, and the output is the data obtained as the analysis results (e.g., number of people, behavioral patterns, and location information of goods).

[0991] Step 4:

[0992] The server runs an algorithm that determines restoration priorities and delivery destinations based on the analysis results. The algorithm evaluates people's density and behavioral patterns to identify high-priority areas and necessary supplies. The input to this process is the analysis results, and the output is a list of restoration priorities and a list of delivery destinations for supplies.

[0993] Step 5:

[0994] The device receives emotional information from the user as input and analyzes it using an emotion engine. The emotion engine (e.g., Microsoft Azure Face API) analyzes the user's level of stress or anxiety from their facial expressions and voice. The input to this process is the user's emotional information, and the output is analyzed emotional data.

[0995] Step 6:

[0996] The server integrates the analysis results from the emotion engine with those from the generation AI and reflects them in the priority determination process. This allows areas where users are feeling high stress to be given a higher priority. The inputs to this process are emotion data and the analysis results from the generation AI, and the output is a recovery priority list that takes emotion into account and a list of delivery destinations for goods.

[0997] Step 7:

[0998] The server notifies the determined recovery priority and delivery destination information to devices such as smartphones and smart glasses. Information is sent in real time using a RESTful API, and various data is displayed on the user's device. The input to this process is a recovery priority list that takes emotions into account and a list of delivery destinations for items, and the output is notification information displayed on the user's device.

[0999] 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.

[1000] 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.

[1001] 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.

[1002] [Fourth embodiment]

[1003] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1004] 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.

[1005] 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).

[1006] 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.

[1007] 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.

[1008] 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).

[1009] 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.

[1010] 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.

[1011] 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.

[1012] 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.

[1013] 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.

[1014] 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.

[1015] 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."

[1016] The present invention relates to a system that collects video data from surveillance cameras in real time, analyzes it using a generative AI, determines restoration priorities and delivery destinations for goods, and provides the results to users. The system of the present invention is specifically implemented as follows.

[1017] overview

[1018] In order to realize a rapid and appropriate response in the event of a disaster, the system of the present invention collects video data from surveillance cameras and analyzes that data using AI. Based on the results of this analysis, recovery priorities and delivery destinations for supplies are determined and provided to the user.

[1019] System configuration

[1020] 1. Surveillance cameras

[1021] The terminals consist of surveillance cameras installed in disaster areas. These cameras collect video data in real time and transmit it to a server.

[1022] 2. Server

[1023] The server receives video data sent from the surveillance camera, and first performs preprocessing on the received data to remove noise.

[1024] The server then analyzes the pre-processed data using generative AI, which focuses on evaluating the number of people, their behavioral trends, and the flow of goods.

[1025] The server runs an algorithm that determines the priority of recovery and the delivery destination of goods based on the analysis results of the generating AI.

[1026] 3. Users

[1027] Users of this system are on-site managers and response teams. They check the information provided by the server and issue instructions for on-site recovery work and delivery of goods.

[1028] Explanation of program processing

[1029] 1. Data Collection

[1030] The server receives video data from multiple surveillance cameras (terminals) in real time and stores it in a database.

[1031] Example: A server receives data every second from cameras installed at major intersections and public facilities in the city.

[1032] 2. Data Preprocessing

[1033] The server performs filtering to remove noise from the collected video data, thereby improving the accuracy of the analysis.

[1034] Example: The server applies a Gaussian filter to reduce unwanted image noise.

[1035] 3. Data Analysis

[1036] The server inputs the preprocessed data into a generative AI to analyze the number of people, behavioral trends, and flow of goods.

[1037] Example: AI detects people and vehicles appearing in video footage and analyzes their location and movement.

[1038] 4. Priority and delivery destination determination

[1039] The server runs an algorithm that determines recovery priorities and delivery destinations for items based on the analysis results obtained from the generation AI.

[1040] For example, AI can detect highly congested roads and determine which roads should be prioritized for restoration, or identify areas where goods are in short supply and prioritize deliveries to those areas.

[1041] 5. Provision of Information

[1042] The server provides the determined priority and delivery destination information to the site manager (user).

[1043] Example: The server uses a RESTful API to send information to the administrator's smartphone or tablet.

[1044] Explanation with concrete examples

[1045] In disaster areas, surveillance cameras installed on major roads and public facilities collect video data and send it to a server. The server preprocesses the received data and analyzes it using generative AI. For example, if a group of people is confirmed in a certain area, the AI ​​will determine that area as a priority destination for delivering food and water. Also, if a particular road is extremely congested, it will be set as the top priority for restoration.

[1046] This information is then sent from the server to the user's device, who then issues instructions to the local response team, ensuring quick and efficient recovery efforts and delivery of supplies.

[1047] The processing flow will be explained below.

[1048] Step 1:

[1049] The server acquires video data in real time from each device (surveillance camera) installed in the disaster area. For example, it collects video every second from surveillance cameras installed at intersections and public facilities and stores it in a database.

[1050] Step 2:

[1051] The server preprocesses the acquired video data, specifically applying a noise reduction filter to the video data to improve image quality, for example, by using a Gaussian filter to reduce unwanted noise.

[1052] Step 3:

[1053] The server then inputs the preprocessed video data into a generative AI, which analyzes the number of people, their behavioral trends, and the flow of goods. Specifically, the AI ​​recognizes people and objects in the video and tracks their location and movement.

[1054] Step 4:

[1055] The server runs an algorithm to determine restoration priorities based on the analysis results obtained from the AI ​​generation. For example, if a particular road is extremely congested, it will be given top priority for restoration.

[1056] Step 5:

[1057] The server determines the delivery destination of the goods based on the analysis results. For example, if the analysis results indicate that there is a shortage of food or water in a certain area, the server sets that area as a priority delivery destination.

[1058] Step 6:

[1059] The server provides the determined recovery priority and delivery destination information to the on-site administrator (user). As a specific example, it sends the information to the administrator's tablet using a RESTful API.

[1060] Step 7:

[1061] The user can review the provided information and issue instructions to the local response team for restoration work and material delivery. For example, the user can review the priority information on the tablet and inform the restoration team of the roads that need to be repaired with the highest priority.

[1062] Step 8:

[1063] The user monitors the progress of the recovery and delivery of goods and modifies instructions as needed. For example, if unexpected difficulties arise along the way, the user responds by issuing new instructions.

[1064] Step 9:

[1065] The server continuously collects new data from the surveillance cameras and repeatedly pre-processes and analyzes it, enabling optimal decisions to be made based on the latest information.

[1066] Example 1

[1067] 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."

[1068] A rapid and appropriate response in the event of a disaster is crucial for preventing damage from spreading and for efficiently advancing recovery. However, conventional methods have the problem of making it difficult to grasp the situation on-site in real time and determine effective recovery priorities and supply delivery destinations. Another issue is the lack of a means to quickly and accurately convey this information to on-site response teams.

[1069] 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.

[1070] In this invention, the server includes: means for collecting surveillance camera video data in real time; means for preprocessing the collected video data; means for analyzing the preprocessed data using a generative AI; means for determining restoration priorities and delivery destinations based on the analysis results; means for providing the determined priorities and delivery destination information to an end-user device; and means for transmitting instructions from the end-user device to a local response team based on the provided information. This enables accurate understanding of the on-site situation in real time and prompt and appropriate determination of restoration priorities and delivery destinations. Furthermore, by quickly communicating this information to relevant parties, the efficiency and accuracy of response can be improved.

[1071] A "surveillance camera" is a device that captures video data of a specific area in real time.

[1072] "Video data" refers to image information captured by a surveillance camera and is typically stored in digital form.

[1073] "Preprocessing" refers to data processing to make subsequent analysis easier, such as removing noise from collected video data or adjusting resolution.

[1074] "Generative AI" is a model that uses artificial intelligence technology to analyze video data and recognize specific patterns.

[1075] "Analysis" refers to data processing to extract specific information (e.g., number of people, behavioral patterns, flow of goods, etc.) based on preprocessed video data.

[1076] "Recovery priority" is an evaluation criterion for determining the order in which recovery work should be carried out in the event of a disaster.

[1077] "Delivery destination of goods" is an indicator for determining to which region or location the required goods should be delivered.

[1078] "End-user devices" refers to devices such as smartphones, tablets, and computers used by local response teams and administrators.

[1079] "Instructions" are messages sent from end-user devices to local response teams with specific action plans and priorities.

[1080] The present invention relates to a system that collects video data from surveillance cameras in real time, analyzes it using a generative AI, determines restoration priorities and delivery destinations for goods, and provides the results to users. The system of the present invention is specifically implemented as follows.

[1081] surveillance cameras

[1082] The device consists of multiple surveillance cameras installed in the disaster area. These cameras capture video data in real time and transmit the data to a server. Specifically, cameras installed at major intersections and public facilities in the city capture real-time video at 30 frames per second and transmit the data securely to the server using AES encryption.

[1083] server

[1084] The server has the function of receiving video data transmitted in real time from multiple surveillance cameras, and then stores the received video data in a database. The stored data also includes metadata such as timestamps and camera IDs.

[1085] The server preprocesses the collected data, including noise reduction using a Gaussian filter and image resolution adjustment, improving image quality and enhancing the accuracy of analysis.

[1086] The server then inputs the preprocessed data into the generative AI, which uses a pre-trained model to send a specific prompt to the model: "Analyze people's movements during a disaster and identify areas that should be prioritized."

[1087] The generative AI model analyzes the number of people, behavioral patterns, and flow of goods in the video. This includes person detection, location tracking, and behavior classification. For example, the generative AI model detects people and vehicles appearing in the video and analyzes their location and movement.

[1088] The server runs an algorithm that determines restoration priorities and delivery destinations based on the analysis results obtained from the generative AI model. For example, it detects highly congested roads and sets them as the highest priority for restoration. It also identifies areas where supplies are in short supply and determines priority delivery destinations for those areas.

[1089] User

[1090] Users are on-site managers and response teams. The server provides the determined priority and delivery destination information to the user's smartphone or tablet via a RESTful API. The user then issues specific instructions to the local response team based on that information. For example, if a group of people is confirmed in a certain area, the user determines that area as a priority destination for the delivery of food and water, and issues specific instructions such as "restore the main roads in area A as the top priority" or "deliver food to area B as a priority."

[1091] This system will enable efficient and rapid disaster response, preventing damage from spreading and contributing to early recovery.

[1092] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1093] Step 1:

[1094] The terminal captures real-time video data of the target area through installed surveillance cameras. Specifically, surveillance cameras installed at major intersections and public facilities in the city generate video at 30 frames per second and send it to a server using AES encryption. The input is the captured raw video data, and the output is the encrypted video data.

[1095] Step 2:

[1096] The server stores the encrypted video data received from the device in a database. The input is encrypted video data, and the output is video data stored in the database. Specifically, the server immediately stores the received data in the database and adds a timestamp and camera ID as metadata.

[1097] Step 3:

[1098] The server performs preprocessing on the stored video data. Specifically, it applies a Gaussian filter to remove noise from the collected video data and adjusts the resolution. The input is the raw video data stored in the database, and the output is preprocessed video data with noise removed. The server stores the data after this preprocessing in another database or cache.

[1099] Step 4:

[1100] The server inputs the preprocessed video data into the generative AI model. It then sends the model a prompt, saying, "Analyze people's movements during a disaster and identify areas that should be prioritized," and begins analysis. The input is the preprocessed video data and the prompt, and the output is the analysis results. The generative AI model performs a detailed analysis of the number of people in the video, their behavioral patterns, and the flow of goods, and returns the results to the server.

[1101] Step 5:

[1102] The server runs an algorithm that determines restoration priorities and delivery destinations for supplies based on the analysis results obtained from the generative AI model. For example, it prioritizes restoration of highly congested roads and creates a priority delivery plan for areas where supplies are in short supply. The input is the analysis results of the generative AI model, and the output is restoration priorities and delivery destination information for supplies.

[1103] Step 6:

[1104] The server provides the determined priority and delivery destination information to the end-user device. Specifically, it uses a RESTful API to send the information to the user's smartphone or tablet. The input is the recovery priority and delivery destination information, and the output is the information sent to the user's end-user device.

[1105] Step 7:

[1106] Based on the information received from the server, the user sends specific instructions to the local response team, such as "Give top priority to restoring the main roads in area A" or "Give priority to delivering food to area B." The input is the information provided by the server, and the output is the specific instructions to the local response team.

[1107] (Application example 1)

[1108] 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."

[1109] In the event of a disaster, a rapid and appropriate response is required, but in many cases, it takes time to grasp the situation on-site, which leads to problems such as delays in recovery work and the delivery of supplies. Furthermore, appropriate resources may not be deployed to the necessary locations, making it difficult to respond efficiently. To resolve these situations, a system is needed that can accurately grasp the situation on-site in real time, clarify priorities, and respond quickly.

[1110] 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.

[1111] In this invention, the server includes means for collecting surveillance camera video data in real time, means for preprocessing the collected video data, means for analyzing the preprocessed data using a generation AI, means for determining restoration priorities and delivery destinations based on the analysis results, means for providing the determined priorities and delivery destination information to a user, means for notifying the user of the analysis results on a mobile information terminal, and means for visually displaying information on restoration work and delivery of goods, thereby enabling restoration work and delivery of goods to be carried out quickly and efficiently.

[1112] A "surveillance camera" is a device installed in a disaster area that collects video data in real time.

[1113] "Preprocessing" is a data processing method for removing noise from collected video data and improving the accuracy of analysis.

[1114] "Generative AI" is an artificial intelligence model that analyzes collected data to assess the number of people, trends in their behavior, and the flow of goods, and to determine recovery priorities and delivery destinations for goods.

[1115] "Recovery priority" is a criterion for evaluating the urgency of recovery work at a disaster site and determining which work should be given priority.

[1116] "Delivery destination of goods" is information that determines the location to which relief supplies and necessary goods should be delivered.

[1117] "Users" refers to the on-site managers and response teams who use this system.

[1118] A "mobile information terminal" is a portable information processing device such as a smartphone or tablet.

[1119] "Visual display of information on restoration work and goods delivery" is a function that displays the priority and delivery destination of restoration work and goods delivery in a form that is easy for the user to see.

[1120] This invention is a system for realizing a rapid and appropriate response in the event of a disaster. It collects video data from surveillance cameras in real time and analyzes it with a generative AI to determine recovery priorities and delivery destinations for goods, and provides the results to users. This system is specifically implemented as follows.

[1121] System configuration

[1122] 1. Surveillance cameras

[1123] The terminals consist of surveillance cameras installed in disaster areas. These cameras collect video data in real time and transmit it to a server.

[1124] 2. Server

[1125] The server receives video data sent from the surveillance camera, and first pre-processes the received data to remove noise.

[1126] The server then analyzes the pre-processed data using generative AI, which focuses on evaluating the number of people, their behavioral trends, and the flow of goods.

[1127] Based on the analysis results of the generating AI, the server runs an algorithm to determine the priority of recovery and the delivery destination of the goods.

[1128] The server notifies the user's mobile information terminal of the determined priority and delivery destination information.

[1129] 3. Users

[1130] The users are on-site managers and response teams, and receive information provided by the server using mobile information terminals.

[1131] Users can use a dashboard that visually displays recovery efforts and delivery information, and direct local response teams.

[1132] Program processing

[1133] Hardware and Software

[1134] Hardware: surveillance cameras, servers, mobile devices (smartphones and tablets).

[1135] Software: OpenCV library, some_ai_library, Flask server.

[1136] Program Flow

[1137] The server receives video data transmitted in real time from the surveillance cameras and stores it in a database.

[1138] Next, the video data is preprocessed using the OpenCV library, in particular by applying a Gaussian filter to remove noise.

[1139] The pre-processed data is sent to some_ai_library's generative AI model to analyze the number of people, behavioral trends, and flow of goods.

[1140] Based on the analysis results, an algorithm is run to determine restoration priorities and delivery destinations for goods.

[1141] The results are sent to the mobile information terminal, and the user can receive the information via push notifications or a dashboard.

[1142] Specific examples

[1143] For example, if a major earthquake occurs and major roads are closed, the system will analyze video footage from surveillance cameras in various locations in real time. As a result, it will identify evacuation centers where people are gathering and set those locations as priority delivery destinations for supplies. It will also be possible to prioritize reopening roads with heavy traffic. This information will be sent to mobile devices, and users can visually check it on their dashboard.

[1144] Example prompts for generative AI models

[1145] "Analyze surveillance camera footage during a disaster to determine priority recovery efforts and delivery destinations. Pay attention to the number of people, their behavioral trends, and the flow of goods."

[1146] Overview of available systems

[1147] This system will enable a prompt and appropriate response in the event of a disaster, and will realize the efficient distribution of supplies and the streamlining of recovery work. It will also enable users to receive information in real time and give prompt instructions on on-site response.

[1148] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1149] Step 1:

[1150] The server receives video data in real time from surveillance cameras installed in the disaster area. Each surveillance camera transmits video of the scene to the server in streaming format. The input video data is transmitted from the surveillance cameras, and the output is stored in a database.

[1151] Step 2:

[1152] The server preprocesses the received video data. Specifically, it applies a Gaussian filter using the OpenCV library to remove noise. The input is the video data saved in step 1, and the output is preprocessed, clear video data.

[1153] Step 3:

[1154] The preprocessed data is input from the server into the generative AI model. Specifically, some_ai_library is used to perform video analysis and evaluate the number of people, behavioral trends, and flow of goods. The input is the preprocessed data, and the output is the analysis results. An example of a prompt sentence is input to the generative AI: "Analyze surveillance camera footage from the time of the disaster and determine the highest priority recovery work and delivery destinations for goods. Please place emphasis on the number of people, behavioral trends, and flow of goods."

[1155] Step 4:

[1156] The server runs an algorithm to determine restoration priorities and delivery destinations based on the analysis results of the generation AI. The input is the analysis results, and the output is a list of priorities and delivery destinations for the items.

[1157] Step 5:

[1158] The server notifies the user of the determined priority and delivery destination information. Specifically, it uses a RESTful API to send information to the user's mobile information device (smartphone or tablet). The input is a list of priorities and delivery destinations, and the output is a notification sent to the user's mobile information device.

[1159] Step 6:

[1160] Users receive notifications on their devices and use a dashboard that visually displays information on recovery efforts and supply delivery. The input is notifications sent from the server, and the output is a visual display. For example, users can check the priority of evacuation shelters and congested roads through the dashboard and issue instructions to on-site teams.

[1161] 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.

[1162] This invention combines a system that collects surveillance camera video data in real time, analyzes it with generative AI to determine restoration priorities and delivery destinations for supplies, and provides the system to users with an emotion engine that recognizes user emotions, further improving the efficiency and accuracy of disaster response.

[1163] overview

[1164] In order to realize a rapid and appropriate response in the event of a disaster, the system of the present invention collects video data from surveillance cameras and analyzes that data using a generative AI. Based on the results of this analysis, it determines recovery priorities and delivery destinations for goods, taking into account the user's emotional information to make optimal decisions.

[1165] System configuration

[1166] 1. Surveillance cameras

[1167] The terminals consist of surveillance cameras installed in disaster areas. These cameras collect video data in real time and transmit it to a server.

[1168] 2. Server

[1169] The server receives video data sent from the surveillance camera, and first performs preprocessing on the received data to remove noise.

[1170] The server then analyzes the pre-processed data using generative AI, which focuses on evaluating the number of people, their behavioral trends, and the flow of goods.

[1171] The server runs an algorithm that determines the priority of recovery and the delivery destination of goods based on the analysis results of the generating AI.

[1172] The server uses an emotion engine to recognize the user's emotions, reflects them in the analysis results, and makes optimal decisions.

[1173] 3. Users

[1174] Users of this system are on-site managers and response teams. They check the information provided by the server and issue instructions for on-site recovery work and delivery of goods.

[1175] Explanation of program processing

[1176] 1. Data Collection

[1177] The server receives video data from multiple surveillance cameras (terminals) in real time and stores it in a database.

[1178] Example: A server receives data every second from cameras installed at major intersections and public facilities in the city.

[1179] 2. Data Preprocessing

[1180] The server performs filtering to remove noise from the collected video data, thereby improving the accuracy of the analysis.

[1181] Example: The server uses a Gaussian filter to reduce unwanted image noise.

[1182] 3. Data Analysis

[1183] The server inputs the preprocessed data into a generative AI to analyze the number of people, behavioral trends, and flow of goods.

[1184] Example: AI detects people and vehicles appearing in video footage and analyzes their location and movement.

[1185] 4. Emotion recognition

[1186] The server uses an emotion engine that recognizes the user's emotions in real time through an interface with the user.

[1187] Example: Emotional information is collected through facial recognition and voice analysis while the user is viewing information on a tablet.

[1188] 5. Priority and delivery destination determination

[1189] The server runs an algorithm that determines recovery priorities and delivery destinations for items based on the analysis results obtained from the generative AI and the emotional information from the emotion engine.

[1190] For example, AI can detect highly congested roads and determine which roads should be prioritized for restoration, or identify areas where goods are in short supply and prioritize deliveries to those areas.

[1191] 6. Provision of Information

[1192] The server provides the determined restoration priority and delivery destination information to the site administrator (user).

[1193] Example: The server uses a RESTful API to send information to the administrator's smartphone or tablet.

[1194] Explanation with concrete examples

[1195] In disaster areas, surveillance cameras installed on major roads and public facilities collect video data and send it to a server. The server preprocesses the received data and analyzes it using generative AI. For example, if a group of people is confirmed in a certain area, the AI ​​will determine that area as a priority destination for delivering food and water. Also, if a particular road is extremely congested, it will be set as the top priority for restoration.

[1196] At the same time, the emotion engine recognizes the user's emotions and sends them to the server. For example, if the user is feeling stressed, it can respond by speeding up the delivery of supplies to the affected area.

[1197] This information is then sent from the server to the user's device, who then issues instructions to the local response team, ensuring quick and efficient recovery efforts and delivery of supplies.

[1198] The processing flow will be explained below.

[1199] Step 1:

[1200] The server acquires video data in real time from each device (surveillance camera) installed in the disaster area. For example, it collects video every second from surveillance cameras installed at intersections and public facilities and stores it in a database.

[1201] Step 2:

[1202] The server preprocesses the acquired video data, specifically applying a noise reduction filter to the video data to improve image quality, for example, by using a Gaussian filter to reduce unwanted noise.

[1203] Step 3:

[1204] The server then inputs the preprocessed video data into a generative AI, which analyzes the number of people, their behavioral trends, and the flow of goods. For example, the AI ​​can recognize people and vehicles in the video and track their location and movement.

[1205] Step 4:

[1206] The server runs an algorithm to determine restoration priorities based on the analysis results obtained from the AI ​​generation. For example, if a particular road is extremely congested, it will be given top priority for restoration.

[1207] Step 5:

[1208] The server determines the delivery destination of the goods based on the analysis results. For example, if the analysis results indicate that there is a shortage of food or water in a certain area, the server sets that area as a priority delivery destination.

[1209] Step 6:

[1210] The server's emotion engine recognizes the user's emotions in real time through the user interface. This emotion information is then reflected in prioritization and delivery destination decisions. For example, if the user expresses emotions indicating stress or urgency, that information is used to reevaluate the priority.

[1211] Step 7:

[1212] The server provides the determined recovery priority and delivery destination information to the on-site administrator (user). As a specific example, it sends the information to the administrator's tablet or smartphone using a RESTful API.

[1213] Step 8:

[1214] The user can review the provided information and issue instructions to the local response team for restoration work and material delivery. For example, the user can review the priority information on the tablet and inform the restoration team of the roads that need to be repaired with the highest priority.

[1215] Step 9:

[1216] The user monitors the progress of the recovery and delivery of goods and modifies instructions as needed. For example, if unexpected difficulties arise along the way, the user responds by issuing new instructions.

[1217] Step 10:

[1218] The server continuously collects new data from the surveillance cameras and repeatedly pre-processes and analyzes it, enabling optimal decisions to be made based on the latest information.

[1219] Example 2

[1220] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1221] It is not easy to respond quickly and appropriately in the event of a disaster and accurately determine restoration priorities and delivery destinations. Furthermore, there is a lack of methods for making optimal decisions that take into account users' emotional information. Conventional technologies do not provide effective solutions to these issues, which means that the efficiency and accuracy of disaster response are not sufficiently ensured.

[1222] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting video data from monitoring devices in real time, means for preprocessing the collected video data, means for analyzing the preprocessed data using a generative AI model, means for determining restoration priorities and delivery destinations of goods based on the analysis results, means for recognizing the user's emotions, means for making optimal decisions based on the analysis results including the emotion data, and means for providing the determined priorities and delivery destination information to the user. This enables a quick and appropriate response in the event of a disaster and allows optimal decisions to be made taking the user's emotions into account.

[1223] "Surveillance equipment" is a general term for cameras and other imaging devices installed in disaster areas that collect video data in real time.

[1224] "Video data" refers to real-time images and video information collected by surveillance equipment.

[1225] "Preprocessing" refers to the process of removing noise from collected video data and performing initial data processing to improve the accuracy of analysis.

[1226] A "generative AI model" is an artificial intelligence model used to analyze collected and pre-processed video data to detect and analyze the number of people, behavioral trends, and flow of goods.

[1227] "Analysis results" refers to data derived by the generative AI model, such as the number of people, behavioral trends, and flow of goods.

[1228] "Recovery priority" is a standard for evaluating the importance of areas and infrastructure that require restoration in the event of a disaster, and determining the order in which they should be prioritized.

[1229] "Delivery destination of goods" refers to the location or area where necessary supplies should be delivered in the event of a disaster.

[1230] "Means for recognizing emotions" refers to technology that analyzes emotions in real time from the user's facial expressions, voice, etc., and feeds the results back to the system.

[1231] "Optimal judgment" is a process that comprehensively considers analysis results and emotional data to make the most appropriate decisions regarding recovery operations and delivery of goods.

[1232] "User" refers to administrators and response teams who use this system to respond to disasters.

[1233] This invention is a system for realizing a rapid and appropriate response in the event of a disaster. It collects video data from surveillance equipment in real time, analyzes it using a generative AI model, determines recovery priorities and delivery destinations for supplies, and provides them to users. In addition, by combining it with a means to recognize user emotions, the efficiency and accuracy of disaster response can be further improved.

[1234] System configuration

[1235] monitoring equipment

[1236] The terminals consist of surveillance equipment installed in disaster areas. These surveillance equipment collect video data in real time and transmit it to a server. Specifically, surveillance cameras installed at major intersections and public facilities are used.

[1237] server

[1238] The server receives the video data sent from the surveillance equipment and stores it in a database, typically an RDBMS such as MySQL.

[1239] The server preprocesses the received video data to remove noise, using the Gaussian filtering function of the OpenCV library.

[1240] The server then analyzes the pre-processed data using a generative AI model powered by TensorFlow to analyze the number of people, their behavioral trends, and the flow of goods.

[1241] The server runs an algorithm that determines the priority of recovery and delivery destination based on the analysis results, by integrating the urgency score and emotion recognition results.

[1242] The server uses an emotion engine through the user interface to recognize the user's emotions in real time, using emotion recognition APIs such as Microsoft Azure's Emotion API.

[1243] The server sends the determined priority and delivery information via a RESTful API to provide the user with the information.

[1244] User

[1245] Users are on-site managers and response teams who handle disaster response. They check the information provided by the server using a dedicated application or dashboard, and issue instructions for on-site recovery work and the delivery of supplies.

[1246] Specific examples

[1247] In disaster areas, surveillance cameras installed on major roads and public facilities collect video data and send it to a server. For example, if a group of people is spotted in a certain area, the generative AI model will determine that area as a priority destination for delivering food and water. Also, if a particular road is extremely congested, it will be designated as a top priority for restoration.

[1248] At the same time, the emotion engine recognizes the user's emotions and sends them to the server. While the user is checking information on the tablet, emotional information is collected through facial recognition and voice analysis. For example, if the user is feeling high levels of stress, the system can take action such as speeding up the delivery of supplies to the affected area.

[1249] This information is sent from the server to the user's device, allowing the user to provide specific instructions to the local response team, ensuring that recovery efforts and delivery of supplies are carried out quickly and efficiently.

[1250] Prompt Sentence Examples

[1251] You can use prompts like the following for your generative AI model:

[1252] "Analyze video data from within the city to assess crowds and road congestion."

[1253] "If there is a shortage of goods in a particular area, determine where to prioritize delivery."

[1254] "Based on user sentiment data, please suggest prioritized support measures for high-stress areas."

[1255] This system will enable a rapid and accurate response in the event of a disaster.

[1256] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1257] Step 1: Data collection

[1258] Input: Real-time video data from surveillance equipment.

[1259] How it works: Surveillance devices are installed in disaster areas and capture video data at 30 frames per second, which are then encoded and streamed to a server in real time.

[1260] Output: Real-time video data sent to the server.

[1261] Step 2: Receiving and storing data

[1262] Input: Real-time video data streamed from surveillance equipment.

[1263] Specific operation: The server receives video data sent from multiple surveillance devices and stores it in a database (e.g., MySQL) in H.264 format.

[1264] Output: Raw video data stored in a database.

[1265] Step 3: Preprocessing for noise reduction

[1266] Input: Raw video data stored in a database.

[1267] Specific operation: The server uses the Gaussian filtering function of the OpenCV library to remove noise from the received video data.

[1268] Output: Denoised video data.

[1269] Step 4: Analyzing the video data

[1270] Input: Denoised video data.

[1271] How it works: The server inputs video data into a generative AI model using TensorFlow to analyze the number of people, behavioral trends, and flow of goods. Specifically, it detects people and vehicles in the video and identifies their location information and movement patterns.

[1272] Output: Data on the number of people, behavioral trends, and flow of goods analyzed by the generative AI model.

[1273] Step 5: Performing Emotion Recognition

[1274] Input: Facial expressions and voice data as users interact with tablets and smartphones through the interface.

[1275] Specific operation: The server analyzes the voice and facial expression data collected from tablets and smartphones using emotion recognition APIs such as Microsoft Azure's Emotion API.

[1276] Output: Parsed user emotion data.

[1277] Step 6: Prioritize and route your delivery

[1278] Input: Analysis results from the generative AI model and emotion data obtained from emotion recognition.

[1279] How it works: The server aggregates this data and uses a priority algorithm to determine the priority of recovery and delivery destinations. For example, areas with high urgency scores and high user stress levels are given top priority.

[1280] Output: Priority and item delivery destination decision data.

[1281] Step 7: Provide information

[1282] Input: Priority and item destination determination data.

[1283] Specific operation: The server uses a RESTful API to send notifications to smartphones and tablets, and displays information in real time on a dedicated application or dashboard.

[1284] Output: Priority and delivery information displayed on a smartphone or tablet.

[1285] At each step, the server, terminal, and user work together to enable a rapid and optimal response in the event of a disaster.

[1286] (Application example 2)

[1287] 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."

[1288] Rapid and appropriate recovery efforts and delivery of supplies are extremely important in the event of a disaster. However, current systems have difficulty in determining priorities and delivery locations, fully reflecting user emotions and real-time situations. Furthermore, once priorities and delivery destinations have been determined, there is a lack of a means to quickly and effectively notify local managers and response teams. Therefore, a new system is needed to improve the efficiency and accuracy of disaster response.

[1289] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1290] In this invention, the server includes means for collecting surveillance camera video data in real time, means for preprocessing the collected video data, means for analyzing the preprocessed data using a generative AI, means for determining restoration priorities and delivery destinations, means for providing the restoration priorities and delivery destination information to a user and reflecting the information in the analysis results using an emotion engine that recognizes the user's emotions, and means for notifying a device such as a smartphone or smart glasses of the determined priorities and delivery destination information. This makes it possible to determine optimal restoration work and delivery destinations in real time while reflecting the user's emotions, and to quickly provide related information to a local manager.

[1291] A "surveillance camera" is a device for continuously monitoring a specific location or area and recording and transmitting video data in real time.

[1292] "Video data" refers to data including real-time video images collected by surveillance cameras and related information.

[1293] "Preprocessing" refers to the process of filtering and data cleaning to remove noise from collected video data and improve the accuracy of analysis.

[1294] "Generative AI" is an artificial intelligence technology that learns from large amounts of data and analyzes video data.

[1295] The "emotion engine" is a system that recognizes the user's emotions and reflects that information in the analysis results.

[1296] "Recovery priority" is a criterion for determining which areas and tasks should be given priority when carrying out recovery work after a disaster.

[1297] "Delivery destination of goods" is an address that indicates the location where necessary supplies should be delivered first in the event of a disaster.

[1298] "Users" are the on-site managers and response teams who operate the system and instruct recovery work and delivery of goods.

[1299] "Notification" is the means by which the system communicates analysis results and decisions to the user in real time.

[1300] A "smartphone" is a portable information terminal that has the functionality of a mobile phone and can run a variety of applications.

[1301] "Smart glasses" are a type of wearable device, an electronic device in the shape of glasses that provides visual information to the user.

[1302] This invention is a system for realizing rapid and appropriate recovery efforts and delivery of supplies in the event of a disaster. This system collects video data from surveillance cameras in real time and analyzes it using generative AI and an emotion engine to determine recovery priorities and delivery destinations. It also reflects the user's emotions and quickly provides the analysis results to on-site managers and response teams.

[1303] The server first receives video data from multiple surveillance cameras in real time and stores it in a database. The video data is then filtered in the pre-processing stage to remove noise. A Gaussian filter is applied using a framework such as OpenCV. The pre-processed data is then input into a generative AI model (e.g., TensorFlow or PyTorch) to detect people and objects.

[1304] Based on the analysis results of the Generative AI, the server runs an algorithm to determine restoration priorities and delivery destinations. This algorithm primarily analyzes the number of people, their behavioral trends, and the flow of goods. Furthermore, it collects and analyzes user emotional information through an emotion engine (e.g., Microsoft Azure Face API or Affectiva), which is reflected in the Generative AI's analysis results. This allows for prioritization of restoration efforts and delivery of goods in areas where users are experiencing high levels of stress or anxiety.

[1305] The determined restoration priority and delivery destination information are sent to devices such as smartphones or smart glasses. Based on this notification information, users can instruct on-site restoration work and item delivery. Specifically, information is displayed in real time on the user's smartphone or smart glasses, and notifications can be received by voice or vibration if necessary.

[1306] For example, in disaster areas, surveillance cameras installed on major roads and public facilities collect video data, which is then sent to a server. The server preprocesses the video data and analyzes it using generative AI. If a large number of people are gathered in a certain area, the server will determine that area as a priority destination for the delivery of food and water. Also, if a particular road is extremely congested, the server will set that road as the top priority for restoration. At the same time, the emotion engine will recognize the user's emotions, and if the user is feeling stressed, it can take action such as speeding up the delivery of supplies to that area.

[1307] An example prompt is:

[1308] "I want to build a system that collects surveillance camera footage from disaster areas in real time and analyzes it using generative AI. Based on the results of this analysis, I want to determine recovery priorities and delivery destinations for supplies. I also want to take user sentiment into account when making these decisions. What frameworks and APIs should I use?"

[1309] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1310] Step 1:

[1311] The server receives video data from the surveillance cameras in real time. Each surveillance camera transmits its video data via the Internet, and the server stores it in a database. The input is the video data from the surveillance cameras, and the output is the stored video data that is subjected to pre-processing.

[1312] Step 2:

[1313] The server preprocesses the collected video data. Specifically, it applies a Gaussian filter using OpenCV to remove noise. The input of this process is the stored video data, and the output is the denoised video data.

[1314] Step 3:

[1315] The server inputs the preprocessed data into a generative AI model for analysis. This model is built using TensorFlow and PyTorch and detects the number of people, behavioral trends, and flow of goods. The input for this process is the preprocessed video data, and the output is the data obtained as the analysis results (e.g., number of people, behavioral patterns, and location information of goods).

[1316] Step 4:

[1317] The server runs an algorithm that determines restoration priorities and delivery destinations based on the analysis results. The algorithm evaluates people's density and behavioral patterns to identify high-priority areas and necessary supplies. The input to this process is the analysis results, and the output is a list of restoration priorities and a list of delivery destinations for supplies.

[1318] Step 5:

[1319] The device receives emotional information from the user as input and analyzes it using an emotion engine. The emotion engine (e.g., Microsoft Azure Face API) analyzes the user's level of stress or anxiety from their facial expressions and voice. The input to this process is the user's emotional information, and the output is analyzed emotional data.

[1320] Step 6:

[1321] The server integrates the analysis results from the emotion engine with those from the generation AI and reflects them in the priority determination process. This allows areas where users are feeling high stress to be given a higher priority. The inputs to this process are emotion data and the analysis results from the generation AI, and the output is a recovery priority list that takes emotion into account and a list of delivery destinations for goods.

[1322] Step 7:

[1323] The server notifies the determined recovery priority and delivery destination information to devices such as smartphones and smart glasses. Information is sent in real time using a RESTful API, and various data is displayed on the user's device. The input to this process is a recovery priority list that takes emotions into account and a list of delivery destinations for items, and the output is notification information displayed on the user's device.

[1324] 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.

[1325] 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.

[1326] 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.

[1327] 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.

[1328] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1329] 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.

[1330] 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).

[1331] 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.

[1332] 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."

[1333] 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.

[1334] 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).

[1335] 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.

[1336] 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.

[1337] 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.

[1338] 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.

[1339] 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.

[1340] 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.

[1341] 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.

[1342] 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.

[1343] 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.

[1344] 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.

[1345] The following is further disclosed regarding the above embodiment.

[1346] (Claim 1)

[1347] A means for collecting surveillance camera video data in real time;

[1348] means for pre-processing the collected video data;

[1349] A means for analyzing the preprocessed data by a generating AI;

[1350] A means for determining a priority order for restoration and a delivery destination of the goods based on the analysis results;

[1351] means for providing the determined priority and delivery destination information to a user;

[1352] A system including:

[1353] (Claim 2)

[1354] 10. The system of claim 1, further comprising filtering means for removing noise from the surveillance camera video data.

[1355] (Claim 3)

[1356] The system of claim 1, further comprising means for analyzing the number of people, behavioral trends, and flow of goods by the generative AI.

[1357] "Example 1"

[1358] (Claim 1)

[1359] A means for collecting surveillance camera video data in real time;

[1360] means for pre-processing the collected video data;

[1361] A means for analyzing the preprocessed data by a generating AI;

[1362] A means for determining a priority order for restoration and a delivery destination of the goods based on the analysis results;

[1363] means for providing said determined priority and delivery information to an end user device;

[1364] means for transmitting instructions from the end user device to a local response team based on said provided information;

[1365] A system including:

[1366] (Claim 2)

[1367] 10. The system of claim 1, further comprising filtering means for removing noise from the surveillance camera video data.

[1368] (Claim 3)

[1369] 10. The system of claim 1, further comprising means for analyzing the number of people, behavioral trends, and flow of goods by the generative AI.

[1370] "Application Example 1"

[1371] (Claim 1)

[1372] A means for collecting surveillance camera video data in real time;

[1373] means for pre-processing the collected video data;

[1374] A means for analyzing the preprocessed data by a generating AI;

[1375] A means for determining a priority order for restoration and a delivery destination of the goods based on the analysis results;

[1376] means for providing the determined priority and delivery destination information to a user;

[1377] a means for notifying the user of the analysis result on a mobile information terminal;

[1378] a means for visually displaying information on recovery efforts and goods delivery;

[1379] A system including:

[1380] (Claim 2)

[1381] 10. The system of claim 1, further comprising filtering means for removing noise from the surveillance camera video data.

[1382] (Claim 3)

[1383] The system of claim 1, further comprising means for analyzing the number of people, behavioral trends, and flow of goods by the generative AI.

[1384] "Example 2: Combining Emotion Engines"

[1385] (Claim 1)

[1386] A means for collecting video data from surveillance equipment in real time;

[1387] means for pre-processing the collected video data;

[1388] means for analyzing the preprocessed data with a generative AI model;

[1389] A means for determining a priority order for restoration and a delivery destination of the goods based on the analysis results;

[1390] means for recognizing the emotion of the user;

[1391] means for making an optimal decision based on the analysis results including the emotion data;

[1392] means for providing the determined priority and delivery destination information to a user;

[1393] A system including:

[1394] (Claim 2)

[1395] 10. The system of claim 1, further comprising filtering means for removing noise from the video data of the surveillance equipment.

[1396] (Claim 3)

[1397] 10. The system of claim 1, further comprising means for analyzing the number of people, behavioral trends, and flow of goods with a generative AI model.

[1398] "Application example 2 when combining emotion engines"

[1399] (Claim 1)

[1400] A means for collecting surveillance camera video data in real time;

[1401] means for pre-processing the collected video data;

[1402] A means for analyzing the preprocessed data by a generating AI;

[1403] A means for determining a priority order for restoration and a delivery destination of the goods based on the analysis results;

[1404] A means for providing the user with restoration priority and delivery destination information, and reflecting the information in the analysis results using an emotion engine that recognizes the user's emotions;

[1405] a means for notifying a terminal such as a smartphone or smart glasses of the determined priority and delivery destination information;

[1406] A system including:

[1407] (Claim 2)

[1408] 10. The system of claim 1, further comprising filtering means for removing noise from the surveillance camera video data.

[1409] (Claim 3)

[1410] The system of claim 1, further comprising means for analyzing the number of people, behavioral trends, and flow of goods using generative AI, and further optimizing multiple recovery priorities and delivery destinations. [Explanation of symbols]

[1411] 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 collecting surveillance camera video data in real time; means for pre-processing the collected video data; A means for analyzing the preprocessed data by a generating AI; A means for determining a priority order for restoration and a delivery destination of the goods based on the analysis results; means for providing the determined priority and delivery destination information to a user; A system including:

2. 10. The system of claim 1, further comprising filtering means for removing noise from the video data of the surveillance camera.

3. The system of claim 1 , further comprising means for analyzing the number of people, behavioral trends, and flow of goods by the generative AI.

Images