System

Abstract

A system is provided.SOLUTION: A system for grasping a situation of a human flow and a physical distribution in a disaster in real time, the system comprising: means for photographing and digitizing a situation of a human flow and a physical distribution by using a multimodal mounted camera; means for aggregating and analyzing a datum received by a server on a cloud and visualizing the datum on a map; means for receiving a request from a user and proposing an optimal action by using a AI; and means for transmitting the proposal to the 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 a disaster, it is necessary to quickly and accurately grasp the situation of people and goods in the affected area, but this is extremely difficult for humans to do in real time. It is also difficult to determine the optimal course of action in a situation that changes from moment to moment. The purpose of this invention is to solve these problems and enable users to take the optimal action in the event of a disaster. [Means for solving the problem]

[0005] The present invention is a system for understanding the flow of people and goods in real time during a disaster, and includes: a means for capturing and digitizing the flow of people and goods using a multimodal camera; a means for transmitting the data to a cloud-based server; a means for aggregating and analyzing the received data at the cloud-based server and visualizing it on a map; a means for receiving requests from users and proposing optimal actions using AI; and a means for transmitting the suggestions to the users. Furthermore, the system includes a means for transmitting user feedback to a cloud-based server and optimizing the delivery destination of relief supplies based on the feedback received by the cloud-based server, thereby enabling the system to propose optimal actions in real time in response to the situation. The cloud-based server includes a means for transmitting instructions for transporting relief supplies to related terminals based on the aggregated user requests, enabling the efficient delivery of supplies.

[0006] A "multimodal camera" is a camera device that can acquire data by combining different types of sensors.

[0007] "People flow" refers to the number of people passing through a certain area per unit time and the flow of their movement.

[0008] "Logistics" refers to the process and flow of movement of products and materials from the place of production to the place of consumption or use.

[0009] A "server" refers to a computer system that provides services to other computers (clients) on a network.

[0010] "Cloud" refers to a collection of computing resources, storage, and application services provided over the Internet.

[0011] "Real-time" refers to immediate processing or response without delay.

[0012] "Data aggregation" refers to the process of combining multiple pieces of data into a single data set.

[0013] "Data analysis" refers to the process of analyzing acquired data and extracting useful information from it.

[0014] "Visualization on a map" refers to visually displaying data as geographic information to make it easier to understand.

[0015] A "request" refers to the act of a user sending a request or demand to the system.

[0016] "Feedback" refers to a user reporting the results of their actions or new requests to the system.

[0017] "Relief supplies" refers to items such as water, food, and medicine that are needed by disaster victims during a disaster.

[0018] "Destination" refers to the target areas and facilities to which relief supplies will be supplied.

[0019] "Transportation instructions" refers to orders directing the movement and distribution of supplies.

[0020] "User" refers to a person or institution that uses the system. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0029] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0042] This invention is a system that grasps the situation of people and goods flow in real time during a disaster and suggests optimal actions to users. This system collects data using a multimodal camera, analyzes and visualizes the data on a cloud server, and suggests optimal actions to users.

[0043] Specific explanation of the program's operation

[0044] Device behavior

[0045] 1. Data Acquisition:

[0046] The device (a multimodal camera) captures real-time images of people and goods flow, such as images of supplies stored in local warehouses and people flowing through evacuation centers.

[0047] 2. Data conversion:

[0048] The captured image is analyzed within the device and converted into specific digital data. For example, the device may detect that there are 200 500ml bottles of water and generate that information as digital data.

[0049] 3. Data transmission:

[0050] The generated digital data is sent to a server on the cloud.

[0051] Server Operation

[0052] 4. Data reception:

[0053] The server receives people flow and logistics data transmitted from a plurality of terminals.

[0054] 5. Data Integration:

[0055] The received data is integrated to understand the overall situation. For example, data on water, food, medicine, etc. sent from multiple devices can be combined into one.

[0056] 6. Data Visualization:

[0057] The integrated data is visualized on a map and displayed in real time, allowing users and managers to grasp the overall situation at a glance.

[0058] 7. Receiving and parsing the request:

[0059] The server receives requests from users and uses AI to analyze the optimal action. For example, if a user requests "I want water," the server analyzes the data and identifies the optimal location.

[0060] 8. Submit a proposal:

[0061] The analysis results are sent to the user and the optimal course of action is suggested. For example, the system may notify the user that "If you go to location A, there are 200 500ml bottles of water."

[0062] User Actions

[0063] 9. Start action:

[0064] The user receives the suggestion from the server and initiates the optimal action, for example, moving to the suggested location to pick up the supplies.

[0065] 10. Send Feedback:

[0066] The user reports the results of the actions taken and new requests to the server as feedback, for example, "I arrived at location A and received water."

[0067] Server supply optimization

[0068] 11. Request Collection:

[0069] The server aggregates feedback requests from multiple users, thereby understanding overall demand.

[0070] 12. Supply decisions:

[0071] The server uses the aggregated data to optimize the delivery of relief supplies, for example by identifying areas with high demand for water and creating an optimal supply plan.

[0072] 13. Transfer instructions:

[0073] The server instructs the relevant terminals on supply destinations and transport plans. For example, it sends a command to the terminal to "transport 200 bottles of water from warehouse X to location Y."

[0074] Specific examples

[0075] For example, when a natural disaster occurs, this system can be used to grasp the status of supplies stored in warehouses in the affected area. When a user requests water, the server checks the warehouse status in real time and suggests the optimal warehouse and pick-up location to the user. The user can accept the suggestion, take action, and receive the water. Furthermore, if the user sends feedback after taking action, the server can reflect this in its next action proposals and supply plans.

[0076] In this way, the system of the present invention realizes effective management of people and goods flow during disasters and supports users in taking optimal actions.

[0077] The processing flow will be explained below.

[0078] Step 1:

[0079] The device uses a multimodal camera installed in the disaster area to capture real-time images of the surrounding human and physical flow. For example, the device captures and acquires images of people's movements around evacuation shelters.

[0080] Step 2:

[0081] The device analyzes the captured video and converts it into specific digital data using image recognition technology. For example, the device may identify from the video that there are 200 500ml water bottles and convert that information into data such as "500ml water: 200 bottles."

[0082] Step 3:

[0083] The device then sends the converted data to a cloud server via the internet, allowing data from devices in various locations to be centrally managed.

[0084] Step 4:

[0085] The server receives data sent from multiple devices and aggregates it on the cloud. For example, the server can consolidate data on the flow of supplies and people sent from each evacuation center.

[0086] Step 5:

[0087] The server analyzes and visualizes the aggregated data in real time, displaying the overall situation of people and goods flow on a geographical map, allowing users to see at a glance, for example, how much supplies are in which area and in which direction evacuees are moving.

[0088] Step 6:

[0089] Users access the cloud system from devices such as smartphones or tablets and send requests. For example, a user might input a request such as "I want water" and send it to the server.

[0090] Step 7:

[0091] The server receives a request from the user and begins analysis using AI. The server analyzes real-time data on the cloud to suggest optimal actions. For example, the server may determine that "Location A has 200 500ml water bottles."

[0092] Step 8:

[0093] The server creates a suggestion for the user based on the analysis results and sends that information to the user. For example, the server might send a suggestion to the user saying, "You can get water if you go to location A."

[0094] Step 9:

[0095] The user receives a suggestion from the server and begins to act based on it. The user travels to the specified location and collects the necessary supplies.

[0096] Step 10:

[0097] After taking an action, the user sends feedback from the device to the server. For example, the user reports, "I arrived at location A and received water."

[0098] Step 11:

[0099] The server receives feedback from users and reflects it in the next analysis. Based on the aggregated feedback, the server optimizes future plans for the delivery and transportation of relief supplies.

[0100] Step 12:

[0101] Based on the collected data, the server sends instructions for the supply of relief supplies to related devices as needed. For example, the server may issue an instruction such as "Transport 500 bottles of water from Warehouse X to Location Y."

[0102] The above is a detailed processing flow of the system for optimizing the flow of people and goods during disasters.

[0103] Example 1

[0104] 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."

[0105] During disasters, it is necessary to quickly grasp the status of people's movements and logistics and provide appropriate support. However, with conventional systems, it takes time to collect and analyze this information, and the proposal of appropriate actions is often delayed. As a result, it becomes difficult to effectively distribute relief supplies and quickly guide evacuees, resulting in a decrease in the efficiency of disaster response.

[0106] 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.

[0107] In this invention, the server includes means for capturing images and converting the situation of people and goods flowing in real time using a multimodal camera into data, means for transmitting the data to a cloud server, means for aggregating the received data in the cloud server to grasp the overall situation, means for visualizing the received data on a map, means for receiving requests from users and analyzing optimal actions using AI, and means for transmitting the analysis results to the users. This makes it possible to quickly and accurately grasp the situation of people and goods flowing in the event of a disaster and propose optimal actions to the users.

[0108] A "multimodal mounted camera" is a camera device that combines multiple different sensors (e.g., optical camera, infrared sensor, LIDAR, etc.) to capture people and logistics situations.

[0109] "Cloud servers" refer to remote computing servers accessible via the Internet that store, analyze, and visualize data.

[0110] "Digitization" is the process of converting captured images and information into digital format so that they can be handled electronically.

[0111] "Aggregation" is the act of centralizing information collected from multiple data sources and organizing and integrating it to grasp the overall situation.

[0112] "Visualization" refers to displaying numerical data or text data using visual representations such as maps or graphs to make the information easier to understand intuitively.

[0113] A "request" is a request or demand made by a user to the system, and may include the provision of a specific item or a search for information.

[0114] "AI" is an abbreviation for artificial intelligence, and is a technology that uses techniques such as machine learning and deep learning to analyze and propose optimal actions from large amounts of data.

[0115] "Means of analyzing optimal actions" refers to the process of using AI technology to determine the most effective actions for a user based on collected data and user requests.

[0116] "Feedback" refers to the actual results of actions or new requests that users provide to the system, and is used to further optimize the system.

[0117] "Distribution optimization" is the process of creating a plan based on aggregated data to distribute relief supplies most effectively.

[0118] A "transport instruction" is the act of sending an instruction to an associated terminal to transport relief supplies to a specific location.

[0119] The present invention provides a system for understanding the flow of people and goods in a disaster in real time and proposing optimal actions to users. Specific embodiments of the system will be described below.

[0120] First, the device uses a multimodal camera to capture real-time images of people and goods flow. This camera combines multiple different sensors, such as optical cameras, infrared sensors, and LIDAR. For example, it can measure the density of people in evacuation shelters or the amount of supplies stored in warehouses.

[0121] The device then analyzes the captured video and converts it into digital data using image processing libraries such as OpenCV and AI models. For example, it can detect the number of 500ml bottles of water and generate that information as JSON data.

[0122] The generated digital data is sent to a cloud server using a secure communication protocol (e.g., HTTPS), which receives the data in real time and aggregates it in a centralized database (e.g., MongoDB).

[0123] The server uses the aggregated data to grasp the overall situation of logistics and people flow. This data is visualized on a map and displayed visually using GIS (geographic information system) and Google Maps API, allowing managers and users to understand the situation at a glance.

[0124] When a user makes a request, a specific request such as "I want water" is sent to the server. The server uses an AI model (e.g., GPT-4) to analyze the request and propose the optimal action. The proposed action is notified to the user via a smartphone app. For example, "If you go to location A, there are 200 500ml bottles of water."

[0125] Users can carry out the suggested actions and receive the supplies. After that, they send the results of their actions and any new requests to the server as feedback. This feedback data is also aggregated on the cloud and used to optimize the delivery of relief supplies.

[0126] The server then uses the collected feedback and current data to create a plan to optimize the distribution of relief supplies, ensuring that supplies are distributed efficiently to where they are needed, and sends specific transport instructions to relevant devices to carry out the transport of supplies.

[0127] Specific examples

[0128] For example, when a natural disaster occurs, this system can be used to grasp the status of supplies stored in warehouses in the affected area. When a user uses a smartphone to request "water," the server checks the warehouse status in real time and suggests the optimal warehouse and pickup location to the user. The user can accept the suggestion, take action, and receive the water. Furthermore, if the user sends feedback after taking action, the server can reflect this in its next action proposal and supply plan. In this way, the system of the present invention realizes effective management of people and goods flow during disasters and supports users in taking optimal action.

[0129] Example prompts to input to the generative AI model

[0130] "Please explain a system that, when a natural disaster occurs, proposes the optimal course of action to efficiently supply necessary supplies to affected areas. Please explain the specific process for what data the system collects, how it analyzes it, and how it provides information to users."

[0131] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0132] Step 1:

[0133] Data Acquisition

[0134] The device uses a multimodal camera to capture people and goods flow in real time. The input data is the image captured by the camera, and the output is raw image data. Specifically, the camera captures a 360-degree range and collects data from multiple points.

[0135] Step 2:

[0136] Data Conversion

[0137] The device analyzes the captured video and converts it into digital data. The input is the raw video footage, and the output is the analyzed digital data (e.g., JSON format). Specifically, it uses OpenCV and AI models to count the number of objects and people in the video and generate digital data such as the number of 500ml bottles of water.

[0138] Step 3:

[0139] Data transmission

[0140] The terminal sends the generated digital data to a server on the cloud. The input is digital data, and the output is the completion of data transmission to the cloud server. Specifically, the HTTPS protocol is used to send the data securely while ensuring data integrity.

[0141] Step 4:

[0142] Data reception

[0143] The server receives digital data sent from the device. The input is digital data sent via the cloud, and the output is the storage of the received data. Specifically, it uses cloud platforms such as AWS and Google Cloud to quickly process large amounts of data and store it in a database.

[0144] Step 5:

[0145] Data Integration

[0146] The server integrates the data it receives to understand the overall situation. The input is data received from multiple devices, and the output is an integrated data set. Specifically, it uses a database such as MongoDB to consolidate information on water, food, medicine, etc.

[0147] Step 6:

[0148] Data Visualization

[0149] The server visualizes the integrated data on a map and displays it in real time. The input is the integrated data, and the output is the visualized information. Specifically, it uses GIS and Google Maps API to display the distribution status of supplies on a map.

[0150] Step 7:

[0151] Receiving and parsing requests

[0152] The server receives requests from users and uses AI to analyze the optimal course of action. The input is the user request (e.g., "I want water"), and the output is the analysis result (e.g., "There are 200 bottles of water at location A"). Specifically, it uses an AI model (e.g., GPT-4) to identify the optimal supply location and route.

[0153] Step 8:

[0154] Submit a proposal

[0155] The server sends the analysis results to the user. The input is the analysis results, and the output is a notification of the proposal to the user. Specifically, the server sends a notification to the user via a smartphone app.

[0156] Step 9:

[0157] Start of action

[0158] The user receives a proposal from the server and begins to act. The input is a proposal notification, and the output is the start of the action. Specifically, the user uses a map app on their smartphone to travel to the proposed warehouse.

[0159] Step 10:

[0160] Send Feedback

[0161] The user feeds back the results of their actions to the server. The input is feedback information, and the output is the completion of data transmission to the server. Specific operations include sending feedback from the smartphone to report the quantity and status of received supplies, as well as any new requests.

[0162] Step 11:

[0163] Request collection

[0164] The server manages the aggregated feedback data from multiple users. The input is the feedback from each user, and the output is the aggregated request data. Specifically, it uses an SQL database to manage the overall request and supply status.

[0165] Step 12:

[0166] supply decision

[0167] The server optimizes the destinations of relief supplies based on the aggregated data. The input is the aggregated data, and the output is a supply plan. Specifically, it creates a plan to prioritize the supply of supplies to areas with high demand.

[0168] Step 13:

[0169] Transfer instructions

[0170] The server sends transport instructions to the relevant terminals. The input is the supply plan, and the output is the command sent to the terminal. A specific operation is to send a specific command such as "Transport 200 bottles of water from warehouse X to location Y."

[0171] (Application example 1)

[0172] 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."

[0173] During disasters, there is a need to grasp the flow of people and goods in real time and propose optimal actions to users, but there is currently no satisfactory solution. In particular, there is an urgent need to provide a system that can efficiently manage the supply status of food and beverages and enable disaster victims to quickly obtain the supplies they need. It is also important to incorporate user feedback and flexibly optimize supply plans.

[0174] 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.

[0175] In this invention, the server includes: means for capturing images of people and goods flow using a multimodal camera and converting them into data; means for transmitting the data to a cloud server; means for aggregating and analyzing the received data at the cloud server and visualizing it on a map; means for receiving requests from users and proposing optimal actions using AI; means for transmitting the proposals to the users; means for grasping the surrounding supply situation in real time using a smartphone, analyzing the acquired data, and transmitting it to the cloud server; and means for the cloud server to integrate data transmitted from multiple smartphones and notify the user of optimal supply locations. This enables effective management of people and goods flow during disasters and propose optimal actions to users.

[0176] A "multimodal camera" is a camera that can simultaneously acquire multiple types of data (e.g., image data, audio data, etc.).

[0177] A "server on the cloud" is a remote server that provides data and services over the Internet.

[0178] "Digitization" is the conversion of physical information into digital data.

[0179] "Means of using AI to suggest optimal actions" refers to means of using artificial intelligence technology to calculate and suggest optimal actions based on the user's situation and requests.

[0180] A "smartphone" is a mobile phone with computing capabilities that can install applications and connect to the Internet.

[0181] "Supply status" refers to information that indicates the inventory and availability of goods and services in a specific region or location.

[0182] "Understanding the surrounding supply situation in real time" means instantly checking the current inventory and availability of goods and services on-site.

[0183] "Analyzing data" means converting acquired data into a form that is easy to interpret as information through calculations and logical operations.

[0184] "Integration" means bringing together multiple pieces of data and information into one system or format.

[0185] "Point of supply" means the location where goods or services are stocked or provided.

[0186] This invention relates to a system that grasps the situation of people and goods flow in real time during a disaster and suggests optimal actions to users. In particular, this invention realizes efficient supply management in the event of a disaster by grasping the supply situation in real time using a smartphone and notifying users of the optimal supply location.

[0187] Explaining system program generation and processing

[0188] Device operation (smartphone):

[0189] 1. Using the smartphone's camera and GPS module, information on the supply status and location is acquired and converted into data.

[0190] 2. The digitized supply information is sent via the Internet to a server on the cloud.

[0191] Server behavior:

[0192] 3. The server receives, integrates, and analyzes data sent from multiple smartphones on the cloud.

[0193] 4. Based on the analyzed data, the supply situation is visualized on a map, and the AI ​​suggests optimal actions in response to user requests.

[0194] 5. The proposed action is notified to the user, and user feedback is collected and reflected in optimizing the supply destination and suggesting the next action.

[0195] Hardware and software used

[0196] Hardware:

[0197] Smartphone: A mobile phone with computing capabilities and internet connectivity (e.g., a typical smartphone).

[0198] Camera: Smartphone built-in camera (e.g. Sony IMX586)

[0199] GPS: Built-in smartphone GPS module

[0200] software:

[0201] Python: Programming Language

[0202] The Requests library: a Python library for HTTP requests

[0203] OpenCV: A library for image recognition

[0204] Cloud services: Cloud platforms for data collection and analysis (e.g., AWS, Google Cloud)

[0205] Specific Description of the Embodiments

[0206] For example, in the event of a natural disaster, this system can be used to instantly grasp the food and beverage supply situation in the affected area. Users take photos of nearby food and beverage inventory with their smartphone cameras, and obtain location information using GPS. This information is sent to a cloud server, which then integrates and analyzes the supply information obtained from multiple smartphones. As a result, users are notified of the optimal supply location. Furthermore, feedback from users can be collected and reflected in optimizing the next supply plan.

[0207] Example prompts to input to the generative AI model

[0208] Example of input prompt:

[0209] A natural disaster has occurred, and there is a shortage of bottled water in the affected areas. Design an application that uses a smartphone to monitor the surrounding supply situation in real time and suggest the best course of action to the user. The application uses a camera to check the water bottle stock, obtains location information using GPS, and sends it to a cloud server. The server analyzes the data and notifies the user of the best location for a supply.

[0210] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0211] Step 1:

[0212] The device (smartphone) uses a camera to capture images of the surrounding supply situation (e.g., water or food inventory). The captured image data is analyzed using image recognition software (e.g., OpenCV) pre-installed on the device and converted into data such as inventory type and quantity. The device also obtains its current location information from its built-in GPS and compiles this data into a single data packet.

[0213] Input: Smartphone camera image, GPS location information

[0214] Output: Item inventory data, location information data

[0215] Step 2:

[0216] The device sends the collected and analyzed data packets over the Internet to a cloud server, using an HTTP request to send the data and confirm that the communication was successful.

[0217] Input: inventory data, location data

[0218] Output: HTTP request sent to the cloud server

[0219] Step 3:

[0220] The server receives data packets sent from multiple smartphones in the cloud, and the received data is stored in a database system for immediate analysis.

[0221] Input: Data packets from multiple smartphones

[0222] Output: Analyzable dataset

[0223] Step 4:

[0224] The server analyzes the received data and processes it into a format suitable for supply status statistics and map displays, including data integration and aggregation, and prepares it for immediate response when a user requests it.

[0225] Input: Analyzable dataset

[0226] Output: Statistics and map display data

[0227] Step 5:

[0228] When a request is received from a user, the server uses AI to suggest the optimal action. For example, if a user requests "I want water," the server will check the current supply situation based on the analyzed data and identify the optimal supply location for the user.

[0229] Input: User requests, statistics and data for map display

[0230] Output: Optimal action suggestion data

[0231] Step 6:

[0232] The server then sends the optimal action suggestions to the user's smartphone as push notifications or in-app messages, ensuring that the user receives them immediately.

[0233] Input: Optimal action suggestion data

[0234] Output: User notification

[0235] Step 7:

[0236] The user receives the proposal from the server and initiates the actual action. After taking the action, the user sends the results of the action as feedback from the terminal to the server. This feedback is used for the next proposal and for optimizing the supply plan.

[0237] Input: Suggestions from the server, user behavior results

[0238] Output: feedback of the results of the action

[0239] Step 8:

[0240] The server aggregates feedback data from multiple users and uses it to optimize supply destinations and transportation plans. The optimized supply destinations and transportation plans are then sent to related terminals, resulting in more efficient supply of goods.

[0241] Input: User feedback

[0242] Output: Optimized destination and transport planning data

[0243] 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.

[0244] This invention is an advanced system that combines an emotion engine with a system that grasps the situation of people and goods flowing during a disaster in real time and suggests optimal actions to users. This system collects data using a multimodal camera, analyzes and visualizes the data on a cloud server, and further incorporates the user's emotional data to suggest optimal actions.

[0245] Specific explanation of the program's operation

[0246] Device behavior

[0247] 1. Data Acquisition:

[0248] The device (a multimodal camera) captures the flow of people and goods in real time. For example, the device captures the movements of people around an evacuation shelter and acquires the footage.

[0249] 2. Data conversion:

[0250] The captured video is analyzed within the device and converted into specific digital data. For example, the device may detect from the video that there are 200 500ml water bottles and digitize that information as "500ml water: 200 bottles."

[0251] 3. Emotion data acquisition:

[0252] The device's built-in emotion engine analyzes the user's facial expressions and tone of voice to collect emotional data. For example, the device analyzes the user's facial expressions to identify emotions such as "anxiety" or "impatience."

[0253] 4. Data transmission:

[0254] The converted data and emotion data are sent to a server on the cloud.

[0255] Server Operation

[0256] 5. Data Reception:

[0257] The server receives people flow and logistics data and user emotion data transmitted from multiple terminals.

[0258] 6. Data Integration:

[0259] The received data is integrated to grasp the overall situation. For example, the server combines data on supplies and people flow sent from each evacuation center with emotional data.

[0260] 7. Data Visualization:

[0261] The server visualizes the integrated data on a map and displays it in real time, allowing users to see the overall situation of people and goods flowing on a geographical map, and understand at a glance how much supplies are in which area and in which direction evacuees are moving.

[0262] 8. Receiving and parsing requests:

[0263] The server receives the user's request and begins analyzing it using AI. Emotional data is also incorporated into the analysis. For example, if a user requests "I want water" and the request is accompanied by emotional data such as "anxiety," that request will be given priority.

[0264] 9. Prioritization:

[0265] The AI ​​prioritizes requests based on the user's emotional data analyzed by the emotion engine. For example, it prioritizes requests from users who are highly "anxious" or "impatient."

[0266] 10. Submit a proposal:

[0267] Based on the analysis results, the server creates a suggestion for the user and sends that information to the user. For example, the server sends a suggestion to the user saying, "If you go to location A, there are 200 500ml bottles of water."

[0268] User Actions

[0269] 11. Start action:

[0270] The user receives a suggestion from the server and begins to act based on it. The user travels to the specified location and collects the necessary supplies.

[0271] 12. Send Feedback:

[0272] After taking an action, the user sends feedback from the device to the server. For example, the user reports, "I arrived at location A and received water."

[0273] Server supply optimization

[0274] 13. Request Collection:

[0275] The server aggregates feedback requests from multiple users, thereby understanding overall demand.

[0276] 14. Supply decisions:

[0277] The server uses the aggregated data to optimize the delivery of relief supplies, for example by identifying areas with high demand for water and creating an optimal supply plan.

[0278] 15. Transfer instructions:

[0279] The server instructs the relevant terminals on supply destinations and transport plans, for example, sending a command to the terminal to "transport 500 bottles of water from warehouse X to location Y."

[0280] Specific examples

[0281] For example, in the event of a natural disaster, this system can be used to grasp the status of supplies stored in warehouses in the affected area. If a user requests "water" and the emotion engine detects the user's "anxiety" or "impatience," the server will prioritize the request. The server will notify the user of the optimal warehouse and pickup location it suggests, allowing the user to accept the suggestion and receive the water.

[0282] In this way, the system of the present invention not only effectively manages the flow of people and goods during disasters, but also incorporates user emotion data to realize more accurate action suggestions and support.

[0283] The processing flow will be explained below.

[0284] Step 1:

[0285] The device uses a multimodal camera installed in the disaster area to capture the surrounding human and logistics flow in real time, for example, capturing the movements of people around evacuation shelters.

[0286] Step 2:

[0287] The device analyzes the captured video and converts it into specific digital data using image recognition technology. For example, the device may detect from the video that there are 200 500ml water bottles and digitize that information as "500ml water: 200 bottles."

[0288] Step 3:

[0289] The device's built-in emotion engine analyzes the user's facial expressions and tone of voice to collect emotional data. For example, the device analyzes the user's facial expressions to identify emotions such as "anxiety" or "impatience."

[0290] Step 4:

[0291] The devices then send the converted data and emotion data to a cloud server via the internet, allowing data from devices in various locations to be centrally managed.

[0292] Step 5:

[0293] The server receives data on people and goods flow and emotional data of users transmitted from multiple terminals, for example, data on supplies and emotional data transmitted from each evacuation shelter.

[0294] Step 6:

[0295] The server integrates the received data to grasp the overall situation, for example, by combining the supply data and emotion data for each evacuation shelter.

[0296] Step 7:

[0297] The server analyzes and visualizes the integrated data in real time, displaying the overall situation of people and goods flow on a geographical map, allowing users to see at a glance how much supplies are in which area and in which direction evacuees are moving.

[0298] Step 8:

[0299] Users access the cloud system from devices such as smartphones or tablets and send requests. For example, they can input a request such as "I want water" and send it to the server.

[0300] Step 9:

[0301] The server receives the user's request and begins analyzing it using AI. Emotional data is also incorporated into the analysis. For example, if a user requests "I want water" and the request is accompanied by emotional data such as "anxiety," that request will be processed with priority.

[0302] Step 10:

[0303] The server prioritizes requests based on emotional data, for example, prioritizing requests from users who are highly anxious or impatient.

[0304] Step 11:

[0305] The server creates a suggestion for the user based on the analysis results and sends that information to the user. For example, it might send a suggestion to the user saying, "If you go to location A, there are 200 500ml bottles of water."

[0306] Step 12:

[0307] The user receives a suggestion from the server and begins to act based on it, for example, by moving to a specified location and picking up the necessary supplies.

[0308] Step 13:

[0309] After taking an action, the user sends feedback from the device to the server, for example, reporting, "I arrived at location A and received water."

[0310] Step 14:

[0311] The server receives feedback from users and incorporates it into subsequent analysis, for example optimizing the delivery and transportation plans of relief supplies based on the aggregated feedback.

[0312] Step 15:

[0313] Based on the collected data, the server sends instructions to relevant terminals to supply relief supplies as needed, such as "Transport 500 bottles of water from Warehouse X to Location Y."

[0314] The above is a detailed description of the processing flow in the optimization system for people flow, logistics, and emotional data during disasters.

[0315] Example 2

[0316] 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."

[0317] In the event of a disaster, it is extremely important to grasp the situation of people and goods in real time and respond quickly and effectively. However, conventional systems do not adequately manage supplies or provide support to evacuees, and care is particularly lacking for users who are emotionally unstable. This leads to unclear priorities for support and makes it difficult to optimally allocate resources.

[0318] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for capturing and digitizing the flow of people and goods using a multimodal camera; means for analyzing a user's facial expression and tone of voice to acquire emotional data; means for transmitting the data and emotional data to a cloud server; means for aggregating and analyzing the received data and emotional data in the cloud server and visualizing them on a map; means for receiving requests from users, prioritizing the requests using AI, and proposing optimal actions; and means for transmitting the proposals to the users. This enables real-time management of supplies and evacuees during disasters, enabling prioritization taking into account the user's emotional state, and achieving optimal resource allocation and rapid response.

[0319] A "multimodal on-board camera" is a device equipped with multiple different sensors (e.g., visible light camera, infrared camera, depth sensor, etc.) to acquire complex environmental information.

[0320] "People flow" is a term that refers to the flow or movement of people moving through a specific area within a certain period of time.

[0321] "Logistics" is a term that refers to the overall flow and movement of goods and materials, including transportation, storage, and distribution.

[0322] "Emotion data" is data relating to the user's psychological state, obtained by analyzing information such as the user's facial expression and tone of voice.

[0323] "Cloud" is a term that refers to a system of computer resources and data storage that are remotely available over the Internet.

[0324] A "server" is a central computer system that provides data and services to other computers over a network.

[0325] "Digitization" is the act of converting physical or analog information into digital data so that it can be processed by a computer.

[0326] "Analysis" is the process of investigating and analyzing acquired data in detail to extract useful information.

[0327] "Visualization" is a method of displaying data visually in an easy-to-understand manner, and includes formats such as maps, graphs, and charts.

[0328] A "request" is a request from a user to the system for a specific operation or information provision.

[0329] "Priority" refers to the ordering used to determine which of multiple tasks or requests should be processed first.

[0330] "Action suggestions" are specific guidance or instructions that suggest optimal actions to the user based on the analysis results.

[0331] "Feedback" refers to response information provided by users to the system, and is used to improve services and as new information for decision-making.

[0332] This invention is an advanced system that grasps the situation of people and goods flow in real time during disasters and suggests optimal actions to users. This system is built by combining a multimodal camera, a cloud server, an AI model, and an emotion engine.

[0333] Device behavior

[0334] First, a multimodal camera is used to capture real-time images of people and goods flowing through the evacuation center. For example, it can capture footage of people's movements around an evacuation center. The captured footage is then analyzed within the device and converted into specific digital data. For example, AI image processing software can analyze the footage to detect that there are 200 500ml water bottles, digitizing this information as "500ml water: 200 bottles." Furthermore, the device's built-in emotion engine analyzes the user's facial expressions and tone of voice to collect emotional data. For example, it can analyze the user's facial expressions to identify emotions such as "anxiety" or "impatience." Finally, this data is sent to a cloud server.

[0335] Server Operation

[0336] The cloud-based server receives people and goods flow data sent from multiple devices, as well as user emotion data. This received data is integrated to grasp the overall situation. Specifically, it combines the emotion data with data on supplies and people flow sent from each evacuation shelter. The integrated data is then visualized on a map using a GIS (geographic information system). This allows the server to visually display the overall situation of people and goods flow on a geographical map, making it possible to see at a glance how many supplies are in which area and in which direction evacuees are moving.

[0337] The server then receives requests from users and begins analyzing them using an AI model. Emotional data is also incorporated into the analysis to determine the priority of user requests. For example, if a request for "water" is accompanied by emotional data such as "anxiety," that request will be processed with priority. Finally, based on the analysis results, a suggestion for the user's actions is created and sent to the user. For example, a suggestion such as "If you go to location A, there are 200 500ml bottles of water" is sent to the user.

[0338] User Actions

[0339] The user receives suggestions from the server and begins to act based on them. For example, they may move to a designated evacuation shelter or supply collection point and collect the necessary supplies. After taking action, they send feedback from their device to the server. For example, they may report, "I arrived at location A and received water."

[0340] Server supply optimization

[0341] The server aggregates requests fed back from multiple users and grasps overall demand. Based on the aggregated data, it optimizes the destination of relief supplies. For example, it identifies areas with high demand for water and creates a supply plan for those areas. It then instructs the relevant terminals on the supply destination and transportation plan. For example, it sends a command to the terminal saying, "Transport 500 bottles of water from warehouse X to location Y."

[0342] Specific examples

[0343] In the event of a natural disaster, this system can be used to grasp the status of supplies in the affected area. If a user sends a request saying "I want water," and the emotion engine detects the user's "anxiety" or "impatience," the server will prioritize the request. The server will notify the user of the optimal warehouse or pick-up location it suggests, and the user can accept the suggestion and receive the water.

[0344] In this way, the system of the present invention not only effectively manages the flow of people and goods during disasters, but also incorporates user emotion data to realize more accurate action suggestions and support.

[0345] Prompt Sentence Examples

[0346] Prompt to explain the system that suggests "optimal actions in the event of a disaster":

[0347] You are an evacuee in a disaster-hit area. You are currently in shelter C, but you are running low on water and food. Please tell us about your surroundings and how you are feeling. Based on that information, the AI ​​will suggest the best course of action for you.

[0348] As described above, in order to implement the present invention, by applying a multimodal camera, a cloud server, an AI model, and an emotion engine, it is possible to grasp the situation of people and goods flow during a disaster in real time and suggest optimal actions to the user.

[0349] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0350] Step 1: Data Acquisition

[0351] The device (a multimodal camera) captures real-time images of people and goods flowing through evacuation shelters and disaster sites, and acquires the video and audio data. The input is the video and audio captured by the camera, and the output is raw video and audio data. For example, it can capture the movement of people and the placement of supplies within an evacuation shelter.

[0352] Step 2: Data conversion

[0353] The device analyzes the captured video and audio data using AI image processing and audio analysis software. The input is raw video and audio data, and the output is specific digital data (e.g., "200 bottles of 500ml water" or "150 cans of food"). Specific operations include applying an image recognition algorithm to identify the type and quantity of supplies from the video.

[0354] Step 3: Acquire emotion data

[0355] The emotion engine installed in the device analyzes the user's facial expressions and tone of voice to collect emotional data. The input is data related to the user's face and tone of voice, and the output is emotional data (e.g., "anxiety," "impatience," etc.). Specific operations include analyzing the user's psychological state using facial expression recognition technology and voice analysis technology.

[0356] Step 4: Send data

[0357] The device transmits the converted material data and emotional data to a server on the cloud. The input is the digital data and emotional data analyzed and converted within the device, and the output is the data sent to the cloud server. The specific operation is to transmit the data via a wireless network.

[0358] Step 5: Receiving Data

[0359] The server receives people and logistics data, as well as emotion data, sent from multiple devices. The input is data from the devices, and the output is the received integrated data. Specifically, the server receives data using an API provided by the cloud platform.

[0360] Step 6: Data Integration

[0361] The server integrates the received data and grasps the overall situation. The input is the data received from each device, and the output is an integrated data set. Specific operations include the process of combining data from each evacuation shelter and the site into a single data set.

[0362] Step 7: Data visualization

[0363] The server visualizes the integrated data on a map in real time using a GIS (geographic information system). The input is the integrated data, and the output is a visualized geographic map. Specific operations include displaying the location of supplies and the movements of evacuees on the map.

[0364] Step 8: Receiving and Parsing the Request

[0365] The server receives requests from users and analyzes them using an AI model. It also incorporates emotional data into the analysis. The inputs are the user's request and emotional data, and the output is the analysis results. Specifically, it prioritizes requests based on the request content and the user's emotional state.

[0366] Step 9: Prioritize

[0367] The server determines the priority of requests based on the user's emotional data analyzed by the emotion engine. The input is the analysis result, and the output is a priority list. Specifically, requests from users who show high emotional levels, such as "anxiety" or "impatience," are prioritized.

[0368] Step 10: Submit your proposal

[0369] The server creates and sends a proposal to the user based on the analysis results. The input is the prioritized request and the analysis results, and the output is a proposal message. Specifically, it notifies the user that "If you go to location A, there are 200 500ml bottles of water."

[0370] Step 11: Take Action

[0371] The user receives a suggestion from the server and begins to act based on it. The input is a suggestion message from the server, and the output is the user's behavioral data. The specific action involves moving to a specified location and receiving the necessary supplies.

[0372] Step 12: Send feedback

[0373] After the user takes an action, they send feedback from their device to the server. The input is the user's reported data after the action, and the output is the feedback data sent to the server. A specific action is reported as "arrived at location A and received water."

[0374] Step 13: Request collection

[0375] The server aggregates feedback requests from multiple users. The input is feedback data from each user, and the output is aggregated request data. Specific operations include a process to understand how the overall demand is distributed.

[0376] Step 14: Supply Decision

[0377] The server optimizes the destinations of relief supplies based on the aggregated demand data. The input is the aggregated demand data, and the output is a supply plan. Specifically, it identifies the areas with the highest demand and formulates an appropriate supply plan.

[0378] Step 15: Transfer Instructions

[0379] The server instructs the relevant terminals on the supply destination and transfer plan. The input is the material supply plan, and the output is the transfer instruction. For example, an instruction to "transfer 500 bottles of water from warehouse X to location Y" is sent to the terminal. The specific operation is to send the transfer instruction to the relevant terminal and have it executed.

[0380] (Application example 2)

[0381] 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."

[0382] During disasters, it is difficult for victims and relief workers to receive supplies as quickly and efficiently as possible and ensure their safety. To improve convenience, it is necessary to determine priorities by taking into account not only people's movements and logistics situations, but also users' emotions. However, such an advanced system does not currently exist.

[0383] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for capturing and digitizing the situation of people and goods using a multimodal camera, means for transmitting the data to a cloud server, means for analyzing the user's facial expressions and tone of voice to collect emotional data, means for prioritizing requests using the collected emotional data and proposing optimal actions using AI, and means for transmitting the suggestions to the user. This makes it possible to grasp the situation of people and goods in real time even during a disaster and to propose optimal actions taking the user's emotions into consideration. It also makes it possible to provide relief supplies effectively and efficiently.

[0384] A "multimodal camera" is a camera that can simultaneously use multiple sensing methods, and is a device that can capture the flow of people and goods with high precision.

[0385] A "server on the cloud" is a remote server accessible via the Internet, and is a system that performs processes such as data storage, analysis, and integration.

[0386] "Analyzing the user's facial expressions and vocal tone" is a technology that quantifies the user's facial expressions and vocal tone to identify and evaluate their emotional state.

[0387] "Emotion data" is numerical or categorical data that indicates the emotional state of the user analyzed from facial expressions, tone of voice, and the like.

[0388] The "priority of a request" is the order of importance or urgency of a request to be executed among multiple user requests.

[0389] "Using AI to suggest optimal actions" refers to using artificial intelligence technology to analyze collected data and emotional data and recommend the most appropriate actions for the user.

[0390] "Understanding the situation of people and goods flow in real time" means instantly collecting and analyzing information on the movements and locations of people and goods at the current time.

[0391] "Providing relief supplies effectively and efficiently" means providing relief supplies to users who need them with the greatest effect and with the least amount of effort and time.

[0392] The present invention is a system that grasps the situation of people and goods flowing during a disaster in real time, incorporates user emotion data, and then suggests optimal actions. Below, we will explain in detail how to build and operate this system.

[0393] Hardware and software used

[0394] To realize the system of the present invention, the following main hardware and software are required.

[0395] Multimodal mounted camera: A device that captures people and logistics flows with high precision.

[0396] Cloud server: A remote server accessible via the Internet that stores, analyzes, integrates, and processes data.

[0397] Emotion engine: Software that recognizes the user's facial expressions and analyzes their voice to collect emotional data.

[0398] AI engine: An artificial intelligence technology that comprehensively analyzes collected data and emotional data to generate optimal action suggestions.

[0399] System operation details

[0400] 1. Data Acquisition:

[0401] The multimodal camera installed on the device captures real-time images of people and goods flowing through the evacuation center. For example, it can collect information on the movements of people and the location of supplies around evacuation centers. This data is then sent to a cloud server.

[0402] 2. Emotion data acquisition:

[0403] The emotion engine analyzes the user's facial expressions and tone of voice to collect emotional data, which can then be used to identify specific emotions such as "anxiety" or "impatience." This data is also sent to a cloud server.

[0404] 3. Data analysis and visualization:

[0405] The server analyzes the received data and grasps the overall situation, which is then visualized on a map, allowing users to see at a glance how many supplies are in which area and in which direction evacuees are moving.

[0406] 4. AI-powered recommendations for optimal actions:

[0407] The AI ​​engine generates optimal action suggestions based on collected people flow data, logistics data, and emotional data. If the emotional data indicates a high level of stress, such as anxiety or impatience, the request will be prioritized and immediate assistance will be provided to the user.

[0408] 5. Notification of Proposal:

[0409] The server generates suggestions and sends them to the user's smartphone or other device. For example, a specific suggestion such as "If you go to location A, there are 200 500ml bottles of water."

[0410] 6. Actions and Feedback:

[0411] The user then takes action based on the suggestions and later sends feedback from the device to the server, which then uses this feedback to optimize the delivery of relief supplies.

[0412] Specific examples

[0413] For example, if this system is used in an evacuation shelter where many evacuees gather after an earthquake, the following will happen: A multimodal camera captures the movements of people around the shelter, and an emotion engine detects the evacuees' anxiety. The cloud server integrates the data and suggests optimal actions (for example, moving supplies to a specific location). This allows relief supplies to be delivered quickly and efficiently.

[0414] Prompt Sentence Examples

[0415] "Create a program that identifies areas where food is scarce after an earthquake in real time and suggests optimal delivery routes. Prioritize based on user sentiment data. Use Python."

[0416] The above is the "mode for carrying out the invention" of the present invention. By constructing a system based on this mode, effective support in the event of a disaster can be achieved.

[0417] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0418] Step 1:

[0419] The device uses a multimodal camera to capture images of people and goods flowing through the device. The camera acquires video data in real time and captures it within the device. The input is the movement of people and objects, and the output is video data capturing these movements.

[0420] Step 2:

[0421] The device analyzes the acquired video data and converts it into specific digital data. For example, it identifies the type and quantity of supplies from the video data and organizes that information as digital data (e.g., 200 500ml bottles of water). The input is video data, and the output is analyzed digital data.

[0422] Step 3:

[0423] The device uses an emotion engine to analyze the user's facial expressions and tone of voice to collect emotional data. The emotional data includes specific emotional states such as "anxiety" and "impatience." The input is the user's facial expressions and voice, and the output is emotional data.

[0424] Step 4:

[0425] The device sends digital data and emotional data to a cloud server, which then centrally manages the collected data. The input is the analyzed digital data and emotional data, and the output is the data sent to the cloud server.

[0426] Step 5:

[0427] The server receives the data sent from the devices and integrates it to understand the overall situation. Based on this series of data, the server analyzes the overall picture of people and goods flow and visualizes the data on a single map. The input is the received data, and the output is the integrated and visualized data.

[0428] Step 6:

[0429] The server receives requests from users and analyzes them using AI. At the same time, it also incorporates user emotional data into the analysis and determines the priority of requests. The input is the user request and emotional data, and the output is a prioritized request.

[0430] Step 7:

[0431] The server then creates optimal action suggestions based on the results of the AI ​​analysis. These suggestions are derived by taking into account the user's request content and emotional data. The input is a prioritized request and the analysis results, and the output is a specific action suggestion.

[0432] Step 8:

[0433] The server sends the generated action suggestions to the user, allowing the user to receive information for deciding their next action. The input is the action suggestions, and the output is notification data for the user.

[0434] Step 9:

[0435] The user receives a suggestion from the server and starts to act based on it. For example, the user moves to a suggested location and picks up the necessary supplies. The input is notification data from the server, and the output is the user's action.

[0436] Step 10:

[0437] After taking an action, the user sends feedback from their device to the server. This feedback information is also managed by the server and used as information for future decisions. The input is the result of the user's action, and the output is feedback data sent to the server.

[0438] The above is a series of processing steps for realizing the system of the present invention, which makes it possible to grasp the situation of people and goods flowing in real time even during a disaster and to propose optimal actions that take the user's emotions into consideration.

[0439] 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.

[0440] 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.

[0441] 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.

[0442] [Second embodiment]

[0443] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0444] 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.

[0445] 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).

[0446] 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.

[0447] 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.

[0448] 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).

[0449] 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.

[0450] 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.

[0451] 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.

[0452] 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.

[0453] 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.

[0454] 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."

[0455] This invention is a system that grasps the situation of people and goods flow in real time during a disaster and suggests optimal actions to users. This system collects data using a multimodal camera, analyzes and visualizes the data on a cloud server, and suggests optimal actions to users.

[0456] Specific explanation of the program's operation

[0457] Device behavior

[0458] 1. Data Acquisition:

[0459] The device (a multimodal camera) captures real-time images of people and goods flow, such as images of supplies stored in local warehouses and people flowing through evacuation centers.

[0460] 2. Data conversion:

[0461] The captured image is analyzed within the device and converted into specific digital data. For example, the device may detect that there are 200 500ml bottles of water and generate that information as digital data.

[0462] 3. Data transmission:

[0463] The generated digital data is sent to a server on the cloud.

[0464] Server Operation

[0465] 4. Data reception:

[0466] The server receives people flow and logistics data transmitted from a plurality of terminals.

[0467] 5. Data Integration:

[0468] The received data is integrated to understand the overall situation. For example, data on water, food, medicine, etc. sent from multiple devices can be combined into one.

[0469] 6. Data Visualization:

[0470] The integrated data is visualized on a map and displayed in real time, allowing users and managers to grasp the overall situation at a glance.

[0471] 7. Receiving and parsing the request:

[0472] The server receives requests from users and uses AI to analyze the optimal action. For example, if a user requests "I want water," the server analyzes the data and identifies the optimal location.

[0473] 8. Submit a proposal:

[0474] The analysis results are sent to the user and the optimal course of action is suggested. For example, the system may notify the user that "If you go to location A, there are 200 500ml bottles of water."

[0475] User Actions

[0476] 9. Start action:

[0477] The user receives the suggestion from the server and initiates the optimal action, for example, moving to the suggested location to pick up the supplies.

[0478] 10. Send Feedback:

[0479] The user reports the results of the actions taken and new requests to the server as feedback, for example, "I arrived at location A and received water."

[0480] Server supply optimization

[0481] 11. Request Collection:

[0482] The server aggregates feedback requests from multiple users, thereby understanding overall demand.

[0483] 12. Supply decisions:

[0484] The server uses the aggregated data to optimize the delivery of relief supplies, for example by identifying areas with high demand for water and creating an optimal supply plan.

[0485] 13. Transfer instructions:

[0486] The server instructs the relevant terminals on supply destinations and transport plans. For example, it sends a command to the terminal to "transport 200 bottles of water from warehouse X to location Y."

[0487] Specific examples

[0488] For example, when a natural disaster occurs, this system can be used to grasp the status of supplies stored in warehouses in the affected area. When a user requests water, the server checks the warehouse status in real time and suggests the optimal warehouse and pick-up location to the user. The user can accept the suggestion, take action, and receive the water. Furthermore, if the user sends feedback after taking action, the server can reflect this in its next action proposals and supply plans.

[0489] In this way, the system of the present invention realizes effective management of people and goods flow during disasters and supports users in taking optimal actions.

[0490] The processing flow will be explained below.

[0491] Step 1:

[0492] The device uses a multimodal camera installed in the disaster area to capture real-time images of the surrounding human and physical flow. For example, the device captures and acquires images of people's movements around evacuation shelters.

[0493] Step 2:

[0494] The device analyzes the captured video and converts it into specific digital data using image recognition technology. For example, the device may identify from the video that there are 200 500ml water bottles and convert that information into data such as "500ml water: 200 bottles."

[0495] Step 3:

[0496] The device then sends the converted data to a cloud server via the internet, allowing data from devices in various locations to be centrally managed.

[0497] Step 4:

[0498] The server receives data sent from multiple devices and aggregates it on the cloud. For example, the server can consolidate data on the flow of supplies and people sent from each evacuation center.

[0499] Step 5:

[0500] The server analyzes and visualizes the aggregated data in real time, displaying the overall situation of people and goods flow on a geographical map, allowing users to see at a glance, for example, how much supplies are in which area and in which direction evacuees are moving.

[0501] Step 6:

[0502] Users access the cloud system from devices such as smartphones or tablets and send requests. For example, a user might input a request such as "I want water" and send it to the server.

[0503] Step 7:

[0504] The server receives a request from the user and begins analysis using AI. The server analyzes real-time data on the cloud to suggest optimal actions. For example, the server may determine that "Location A has 200 500ml water bottles."

[0505] Step 8:

[0506] The server creates a suggestion for the user based on the analysis results and sends that information to the user. For example, the server might send a suggestion to the user saying, "You can get water if you go to location A."

[0507] Step 9:

[0508] The user receives a suggestion from the server and begins to act based on it. The user travels to the specified location and collects the necessary supplies.

[0509] Step 10:

[0510] After taking an action, the user sends feedback from the device to the server. For example, the user reports, "I arrived at location A and received water."

[0511] Step 11:

[0512] The server receives feedback from users and reflects it in the next analysis. Based on the aggregated feedback, the server optimizes future plans for the delivery and transportation of relief supplies.

[0513] Step 12:

[0514] Based on the collected data, the server sends instructions for the supply of relief supplies to related devices as needed. For example, the server may issue an instruction such as "Transport 500 bottles of water from Warehouse X to Location Y."

[0515] The above is a detailed processing flow of the system for optimizing the flow of people and goods during disasters.

[0516] Example 1

[0517] 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."

[0518] During disasters, it is necessary to quickly grasp the status of people's movements and logistics and provide appropriate support. However, with conventional systems, it takes time to collect and analyze this information, and the proposal of appropriate actions is often delayed. As a result, it becomes difficult to effectively distribute relief supplies and quickly guide evacuees, resulting in a decrease in the efficiency of disaster response.

[0519] 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.

[0520] In this invention, the server includes means for capturing images and converting the situation of people and goods flowing in real time using a multimodal camera into data, means for transmitting the data to a cloud server, means for aggregating the received data in the cloud server to grasp the overall situation, means for visualizing the received data on a map, means for receiving requests from users and analyzing optimal actions using AI, and means for transmitting the analysis results to the users. This makes it possible to quickly and accurately grasp the situation of people and goods flowing in the event of a disaster and propose optimal actions to the users.

[0521] A "multimodal mounted camera" is a camera device that combines multiple different sensors (e.g., optical camera, infrared sensor, LIDAR, etc.) to capture people and logistics situations.

[0522] "Cloud servers" refer to remote computing servers accessible via the Internet that store, analyze, and visualize data.

[0523] "Digitization" is the process of converting captured images and information into digital format so that they can be handled electronically.

[0524] "Aggregation" is the act of centralizing information collected from multiple data sources and organizing and integrating it to grasp the overall situation.

[0525] "Visualization" refers to displaying numerical data or text data using visual representations such as maps or graphs to make the information easier to understand intuitively.

[0526] A "request" is a request or demand made by a user to the system, and may include the provision of a specific item or a search for information.

[0527] "AI" is an abbreviation for artificial intelligence, and is a technology that uses techniques such as machine learning and deep learning to analyze and propose optimal actions from large amounts of data.

[0528] "Means of analyzing optimal actions" refers to the process of using AI technology to determine the most effective actions for a user based on collected data and user requests.

[0529] "Feedback" refers to the actual results of actions or new requests that users provide to the system, and is used to further optimize the system.

[0530] "Distribution optimization" is the process of creating a plan based on aggregated data to distribute relief supplies most effectively.

[0531] A "transport instruction" is the act of sending an instruction to an associated terminal to transport relief supplies to a specific location.

[0532] The present invention provides a system for understanding the flow of people and goods in a disaster in real time and proposing optimal actions to users. Specific embodiments of the system will be described below.

[0533] First, the device uses a multimodal camera to capture real-time images of people and goods flow. This camera combines multiple different sensors, such as optical cameras, infrared sensors, and LIDAR. For example, it can measure the density of people in evacuation shelters or the amount of supplies stored in warehouses.

[0534] The device then analyzes the captured video and converts it into digital data using image processing libraries such as OpenCV and AI models. For example, it can detect the number of 500ml bottles of water and generate that information as JSON data.

[0535] The generated digital data is sent to a cloud server using a secure communication protocol (e.g., HTTPS), which receives the data in real time and aggregates it in a centralized database (e.g., MongoDB).

[0536] The server uses the aggregated data to grasp the overall situation of logistics and people flow. This data is visualized on a map and displayed visually using GIS (geographic information system) and Google Maps API, allowing managers and users to understand the situation at a glance.

[0537] When a user makes a request, a specific request such as "I want water" is sent to the server. The server uses an AI model (e.g., GPT-4) to analyze the request and propose the optimal action. The proposed action is notified to the user via a smartphone app. For example, "If you go to location A, there are 200 500ml bottles of water."

[0538] Users can carry out the suggested actions and receive the supplies. After that, they send the results of their actions and any new requests to the server as feedback. This feedback data is also aggregated on the cloud and used to optimize the delivery of relief supplies.

[0539] The server then uses the collected feedback and current data to create a plan to optimize the distribution of relief supplies, ensuring that supplies are distributed efficiently to where they are needed, and sends specific transport instructions to relevant devices to carry out the transport of supplies.

[0540] Specific examples

[0541] For example, when a natural disaster occurs, this system can be used to grasp the status of supplies stored in warehouses in the affected area. When a user uses a smartphone to request "water," the server checks the warehouse status in real time and suggests the optimal warehouse and pickup location to the user. The user can accept the suggestion, take action, and receive the water. Furthermore, if the user sends feedback after taking action, the server can reflect this in its next action proposal and supply plan. In this way, the system of the present invention realizes effective management of people and goods flow during disasters and supports users in taking optimal action.

[0542] Example prompts to input to the generative AI model

[0543] "Please explain a system that, when a natural disaster occurs, proposes the optimal course of action to efficiently supply necessary supplies to affected areas. Please explain the specific process for what data the system collects, how it analyzes it, and how it provides information to users."

[0544] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0545] Step 1:

[0546] Data Acquisition

[0547] The device uses a multimodal camera to capture people and goods flow in real time. The input data is the image captured by the camera, and the output is raw image data. Specifically, the camera captures a 360-degree range and collects data from multiple points.

[0548] Step 2:

[0549] Data Conversion

[0550] The device analyzes the captured video and converts it into digital data. The input is the raw video footage, and the output is the analyzed digital data (e.g., JSON format). Specifically, it uses OpenCV and AI models to count the number of objects and people in the video and generate digital data such as the number of 500ml bottles of water.

[0551] Step 3:

[0552] Data transmission

[0553] The terminal sends the generated digital data to a server on the cloud. The input is digital data, and the output is the completion of data transmission to the cloud server. Specifically, the HTTPS protocol is used to send the data securely while ensuring data integrity.

[0554] Step 4:

[0555] Data reception

[0556] The server receives digital data sent from the device. The input is digital data sent via the cloud, and the output is the storage of the received data. Specifically, it uses cloud platforms such as AWS and Google Cloud to quickly process large amounts of data and store it in a database.

[0557] Step 5:

[0558] Data Integration

[0559] The server integrates the data it receives to understand the overall situation. The input is data received from multiple devices, and the output is an integrated data set. Specifically, it uses a database such as MongoDB to consolidate information on water, food, medicine, etc.

[0560] Step 6:

[0561] Data Visualization

[0562] The server visualizes the integrated data on a map and displays it in real time. The input is the integrated data, and the output is the visualized information. Specifically, it uses GIS and Google Maps API to display the distribution status of supplies on a map.

[0563] Step 7:

[0564] Receiving and parsing requests

[0565] The server receives requests from users and uses AI to analyze the optimal course of action. The input is the user request (e.g., "I want water"), and the output is the analysis result (e.g., "There are 200 bottles of water at location A"). Specifically, it uses an AI model (e.g., GPT-4) to identify the optimal supply location and route.

[0566] Step 8:

[0567] Submit a proposal

[0568] The server sends the analysis results to the user. The input is the analysis results, and the output is a notification of the proposal to the user. Specifically, the server sends a notification to the user via a smartphone app.

[0569] Step 9:

[0570] Start of action

[0571] The user receives a proposal from the server and begins to act. The input is a proposal notification, and the output is the start of the action. Specifically, the user uses a map app on their smartphone to travel to the proposed warehouse.

[0572] Step 10:

[0573] Send Feedback

[0574] The user feeds back the results of their actions to the server. The input is feedback information, and the output is the completion of data transmission to the server. Specific operations include sending feedback from the smartphone to report the quantity and status of received supplies, as well as any new requests.

[0575] Step 11:

[0576] Request collection

[0577] The server manages the aggregated feedback data from multiple users. The input is the feedback from each user, and the output is the aggregated request data. Specifically, it uses an SQL database to manage the overall request and supply status.

[0578] Step 12:

[0579] supply decision

[0580] The server optimizes the destinations of relief supplies based on the aggregated data. The input is the aggregated data, and the output is a supply plan. Specifically, it creates a plan to prioritize the supply of supplies to areas with high demand.

[0581] Step 13:

[0582] Transfer instructions

[0583] The server sends transport instructions to the relevant terminals. The input is the supply plan, and the output is the command sent to the terminal. A specific operation is to send a specific command such as "Transport 200 bottles of water from warehouse X to location Y."

[0584] (Application example 1)

[0585] 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."

[0586] During disasters, there is a need to grasp the flow of people and goods in real time and propose optimal actions to users, but there is currently no satisfactory solution. In particular, there is an urgent need to provide a system that can efficiently manage the supply status of food and beverages and enable disaster victims to quickly obtain the supplies they need. It is also important to incorporate user feedback and flexibly optimize supply plans.

[0587] 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.

[0588] In this invention, the server includes: means for capturing images of people and goods flow using a multimodal camera and converting them into data; means for transmitting the data to a cloud server; means for aggregating and analyzing the received data at the cloud server and visualizing it on a map; means for receiving requests from users and proposing optimal actions using AI; means for transmitting the proposals to the users; means for grasping the surrounding supply situation in real time using a smartphone, analyzing the acquired data, and transmitting it to the cloud server; and means for the cloud server to integrate data transmitted from multiple smartphones and notify the user of optimal supply locations. This enables effective management of people and goods flow during disasters and propose optimal actions to users.

[0589] A "multimodal camera" is a camera that can simultaneously acquire multiple types of data (e.g., image data, audio data, etc.).

[0590] A "server on the cloud" is a remote server that provides data and services over the Internet.

[0591] "Digitization" is the conversion of physical information into digital data.

[0592] "Means of using AI to suggest optimal actions" refers to means of using artificial intelligence technology to calculate and suggest optimal actions based on the user's situation and requests.

[0593] A "smartphone" is a mobile phone with computing capabilities that can install applications and connect to the Internet.

[0594] "Supply status" refers to information that indicates the inventory and availability of goods and services in a specific region or location.

[0595] "Understanding the surrounding supply situation in real time" means instantly checking the current inventory and availability of goods and services on-site.

[0596] "Analyzing data" means converting acquired data into a form that is easy to interpret as information through calculations and logical operations.

[0597] "Integration" means bringing together multiple pieces of data and information into one system or format.

[0598] "Point of supply" means the location where goods or services are stocked or provided.

[0599] This invention relates to a system that grasps the situation of people and goods flow in real time during a disaster and suggests optimal actions to users. In particular, this invention realizes efficient supply management in the event of a disaster by grasping the supply situation in real time using a smartphone and notifying users of the optimal supply location.

[0600] Explaining system program generation and processing

[0601] Device operation (smartphone):

[0602] 1. Using the smartphone's camera and GPS module, information on the supply status and location is acquired and converted into data.

[0603] 2. The digitized supply information is sent via the Internet to a server on the cloud.

[0604] Server behavior:

[0605] 3. The server receives, integrates, and analyzes data sent from multiple smartphones on the cloud.

[0606] 4. Based on the analyzed data, the supply situation is visualized on a map, and the AI ​​suggests optimal actions in response to user requests.

[0607] 5. The proposed action is notified to the user, and user feedback is collected and reflected in optimizing the supply destination and suggesting the next action.

[0608] Hardware and software used

[0609] Hardware:

[0610] Smartphone: A mobile phone with computing capabilities and internet connectivity (e.g., a typical smartphone).

[0611] Camera: Smartphone built-in camera (e.g. Sony IMX586)

[0612] GPS: Built-in smartphone GPS module

[0613] software:

[0614] Python: Programming Language

[0615] The Requests library: a Python library for HTTP requests

[0616] OpenCV: A library for image recognition

[0617] Cloud services: Cloud platforms for data collection and analysis (e.g., AWS, Google Cloud)

[0618] Specific Description of the Embodiments

[0619] For example, in the event of a natural disaster, this system can be used to instantly grasp the food and beverage supply situation in the affected area. Users take photos of nearby food and beverage inventory with their smartphone cameras, and obtain location information using GPS. This information is sent to a cloud server, which then integrates and analyzes the supply information obtained from multiple smartphones. As a result, users are notified of the optimal supply location. Furthermore, feedback from users can be collected and reflected in optimizing the next supply plan.

[0620] Example prompts to input to the generative AI model

[0621] Example of input prompt:

[0622] A natural disaster has occurred, and there is a shortage of bottled water in the affected areas. Design an application that uses a smartphone to monitor the surrounding supply situation in real time and suggest the best course of action to the user. The application uses a camera to check the water bottle stock, obtains location information using GPS, and sends it to a cloud server. The server analyzes the data and notifies the user of the best location for a supply.

[0623] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0624] Step 1:

[0625] The device (smartphone) uses a camera to capture images of the surrounding supply situation (e.g., water or food inventory). The captured image data is analyzed using image recognition software (e.g., OpenCV) pre-installed on the device and converted into data such as inventory type and quantity. The device also obtains its current location information from its built-in GPS and compiles this data into a single data packet.

[0626] Input: Smartphone camera image, GPS location information

[0627] Output: Item inventory data, location information data

[0628] Step 2:

[0629] The device sends the collected and analyzed data packets over the Internet to a cloud server, using an HTTP request to send the data and confirm that the communication was successful.

[0630] Input: inventory data, location data

[0631] Output: HTTP request sent to the cloud server

[0632] Step 3:

[0633] The server receives data packets sent from multiple smartphones in the cloud, and the received data is stored in a database system for immediate analysis.

[0634] Input: Data packets from multiple smartphones

[0635] Output: Analyzable dataset

[0636] Step 4:

[0637] The server analyzes the received data and processes it into a format suitable for supply status statistics and map displays, including data integration and aggregation, and prepares it for immediate response when a user requests it.

[0638] Input: Analyzable dataset

[0639] Output: Statistics and map display data

[0640] Step 5:

[0641] When a request is received from a user, the server uses AI to suggest the optimal action. For example, if a user requests "I want water," the server will check the current supply situation based on the analyzed data and identify the optimal supply location for the user.

[0642] Input: User requests, statistics and data for map display

[0643] Output: Optimal action suggestion data

[0644] Step 6:

[0645] The server then sends the optimal action suggestions to the user's smartphone as push notifications or in-app messages, ensuring that the user receives them immediately.

[0646] Input: Optimal action suggestion data

[0647] Output: User notification

[0648] Step 7:

[0649] The user receives the proposal from the server and initiates the actual action. After taking the action, the user sends the results of the action as feedback from the terminal to the server. This feedback is used for the next proposal and for optimizing the supply plan.

[0650] Input: Suggestions from the server, user behavior results

[0651] Output: feedback of the results of the action

[0652] Step 8:

[0653] The server aggregates feedback data from multiple users and uses it to optimize supply destinations and transportation plans. The optimized supply destinations and transportation plans are then sent to related terminals, resulting in more efficient supply of goods.

[0654] Input: User feedback

[0655] Output: Optimized destination and transport planning data

[0656] 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.

[0657] This invention is an advanced system that combines an emotion engine with a system that grasps the situation of people and goods flowing during a disaster in real time and suggests optimal actions to users. This system collects data using a multimodal camera, analyzes and visualizes the data on a cloud server, and further incorporates the user's emotional data to suggest optimal actions.

[0658] Specific explanation of the program's operation

[0659] Device behavior

[0660] 1. Data Acquisition:

[0661] The device (a multimodal camera) captures the flow of people and goods in real time. For example, the device captures the movements of people around an evacuation shelter and acquires the footage.

[0662] 2. Data conversion:

[0663] The captured video is analyzed within the device and converted into specific digital data. For example, the device may detect from the video that there are 200 500ml water bottles and digitize that information as "500ml water: 200 bottles."

[0664] 3. Emotion data acquisition:

[0665] The device's built-in emotion engine analyzes the user's facial expressions and tone of voice to collect emotional data. For example, the device analyzes the user's facial expressions to identify emotions such as "anxiety" or "impatience."

[0666] 4. Data transmission:

[0667] The converted data and emotion data are sent to a server on the cloud.

[0668] Server Operation

[0669] 5. Data Reception:

[0670] The server receives people flow and logistics data and user emotion data transmitted from multiple terminals.

[0671] 6. Data Integration:

[0672] The received data is integrated to grasp the overall situation. For example, the server combines data on supplies and people flow sent from each evacuation center with emotional data.

[0673] 7. Data Visualization:

[0674] The server visualizes the integrated data on a map and displays it in real time, allowing users to see the overall situation of people and goods flowing on a geographical map, and understand at a glance how much supplies are in which area and in which direction evacuees are moving.

[0675] 8. Receiving and parsing requests:

[0676] The server receives the user's request and begins analyzing it using AI. Emotional data is also incorporated into the analysis. For example, if a user requests "I want water" and the request is accompanied by emotional data such as "anxiety," that request will be given priority.

[0677] 9. Prioritization:

[0678] The AI ​​prioritizes requests based on the user's emotional data analyzed by the emotion engine. For example, it prioritizes requests from users who are highly "anxious" or "impatient."

[0679] 10. Submit a proposal:

[0680] Based on the analysis results, the server creates a suggestion for the user and sends that information to the user. For example, the server sends a suggestion to the user saying, "If you go to location A, there are 200 500ml bottles of water."

[0681] User Actions

[0682] 11. Start action:

[0683] The user receives a suggestion from the server and begins to act based on it. The user travels to the specified location and collects the necessary supplies.

[0684] 12. Send Feedback:

[0685] After taking an action, the user sends feedback from the device to the server. For example, the user reports, "I arrived at location A and received water."

[0686] Server supply optimization

[0687] 13. Request Collection:

[0688] The server aggregates feedback requests from multiple users, thereby understanding overall demand.

[0689] 14. Supply decisions:

[0690] The server uses the aggregated data to optimize the delivery of relief supplies, for example by identifying areas with high demand for water and creating an optimal supply plan.

[0691] 15. Transfer instructions:

[0692] The server instructs the relevant terminals on supply destinations and transport plans, for example, sending a command to the terminal to "transport 500 bottles of water from warehouse X to location Y."

[0693] Specific examples

[0694] For example, in the event of a natural disaster, this system can be used to grasp the status of supplies stored in warehouses in the affected area. If a user requests "water" and the emotion engine detects the user's "anxiety" or "impatience," the server will prioritize the request. The server will notify the user of the optimal warehouse and pickup location it suggests, allowing the user to accept the suggestion and receive the water.

[0695] In this way, the system of the present invention not only effectively manages the flow of people and goods during disasters, but also incorporates user emotion data to realize more accurate action suggestions and support.

[0696] The processing flow will be explained below.

[0697] Step 1:

[0698] The device uses a multimodal camera installed in the disaster area to capture the surrounding human and logistics flow in real time, for example, capturing the movements of people around evacuation shelters.

[0699] Step 2:

[0700] The device analyzes the captured video and converts it into specific digital data using image recognition technology. For example, the device may detect from the video that there are 200 500ml water bottles and digitize that information as "500ml water: 200 bottles."

[0701] Step 3:

[0702] The device's built-in emotion engine analyzes the user's facial expressions and tone of voice to collect emotional data. For example, the device analyzes the user's facial expressions to identify emotions such as "anxiety" or "impatience."

[0703] Step 4:

[0704] The devices then send the converted data and emotion data to a cloud server via the internet, allowing data from devices in various locations to be centrally managed.

[0705] Step 5:

[0706] The server receives data on people and goods flow and emotional data of users transmitted from multiple terminals, for example, data on supplies and emotional data transmitted from each evacuation shelter.

[0707] Step 6:

[0708] The server integrates the received data to grasp the overall situation, for example, by combining the supply data and emotion data for each evacuation shelter.

[0709] Step 7:

[0710] The server analyzes and visualizes the integrated data in real time, displaying the overall situation of people and goods flow on a geographical map, allowing users to see at a glance how much supplies are in which area and in which direction evacuees are moving.

[0711] Step 8:

[0712] Users access the cloud system from devices such as smartphones or tablets and send requests. For example, they can input a request such as "I want water" and send it to the server.

[0713] Step 9:

[0714] The server receives the user's request and begins analyzing it using AI. Emotional data is also incorporated into the analysis. For example, if a user requests "I want water" and the request is accompanied by emotional data such as "anxiety," that request will be processed with priority.

[0715] Step 10:

[0716] The server prioritizes requests based on emotional data, for example, prioritizing requests from users who are highly anxious or impatient.

[0717] Step 11:

[0718] The server creates a suggestion for the user based on the analysis results and sends that information to the user. For example, it might send a suggestion to the user saying, "If you go to location A, there are 200 500ml bottles of water."

[0719] Step 12:

[0720] The user receives a suggestion from the server and begins to act based on it, for example, by moving to a specified location and picking up the necessary supplies.

[0721] Step 13:

[0722] After taking an action, the user sends feedback from the device to the server, for example, reporting, "I arrived at location A and received water."

[0723] Step 14:

[0724] The server receives feedback from users and incorporates it into subsequent analysis, for example optimizing the delivery and transportation plans of relief supplies based on the aggregated feedback.

[0725] Step 15:

[0726] Based on the collected data, the server sends instructions to relevant terminals to supply relief supplies as needed, such as "Transport 500 bottles of water from Warehouse X to Location Y."

[0727] The above is a detailed description of the processing flow in the optimization system for people flow, logistics, and emotional data during disasters.

[0728] Example 2

[0729] 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."

[0730] In the event of a disaster, it is extremely important to grasp the situation of people and goods in real time and respond quickly and effectively. However, conventional systems do not adequately manage supplies or provide support to evacuees, and care is particularly lacking for users who are emotionally unstable. This leads to unclear priorities for support and makes it difficult to optimally allocate resources.

[0731] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for capturing and digitizing the flow of people and goods using a multimodal camera; means for analyzing a user's facial expression and tone of voice to acquire emotional data; means for transmitting the data and emotional data to a cloud server; means for aggregating and analyzing the received data and emotional data in the cloud server and visualizing them on a map; means for receiving requests from users, prioritizing the requests using AI, and proposing optimal actions; and means for transmitting the proposals to the users. This enables real-time management of supplies and evacuees during disasters, enabling prioritization taking into account the user's emotional state, and achieving optimal resource allocation and rapid response.

[0732] A "multimodal on-board camera" is a device equipped with multiple different sensors (e.g., visible light camera, infrared camera, depth sensor, etc.) to acquire complex environmental information.

[0733] "People flow" is a term that refers to the flow or movement of people moving through a specific area within a certain period of time.

[0734] "Logistics" is a term that refers to the overall flow and movement of goods and materials, including transportation, storage, and distribution.

[0735] "Emotion data" is data relating to the user's psychological state, obtained by analyzing information such as the user's facial expression and tone of voice.

[0736] "Cloud" is a term that refers to a system of computer resources and data storage that are remotely available over the Internet.

[0737] A "server" is a central computer system that provides data and services to other computers over a network.

[0738] "Digitization" is the act of converting physical or analog information into digital data so that it can be processed by a computer.

[0739] "Analysis" is the process of investigating and analyzing acquired data in detail to extract useful information.

[0740] "Visualization" is a method of displaying data visually in an easy-to-understand manner, and includes formats such as maps, graphs, and charts.

[0741] A "request" is a request from a user to the system for a specific operation or information provision.

[0742] "Priority" refers to the ordering used to determine which of multiple tasks or requests should be processed first.

[0743] "Action suggestions" are specific guidance or instructions that suggest optimal actions to the user based on the analysis results.

[0744] "Feedback" refers to response information provided by users to the system, and is used to improve services and as new information for decision-making.

[0745] This invention is an advanced system that grasps the situation of people and goods flow in real time during disasters and suggests optimal actions to users. This system is built by combining a multimodal camera, a cloud server, an AI model, and an emotion engine.

[0746] Device behavior

[0747] First, a multimodal camera is used to capture real-time images of people and goods flowing through the evacuation center. For example, it can capture footage of people's movements around an evacuation center. The captured footage is then analyzed within the device and converted into specific digital data. For example, AI image processing software can analyze the footage to detect that there are 200 500ml water bottles, digitizing this information as "500ml water: 200 bottles." Furthermore, the device's built-in emotion engine analyzes the user's facial expressions and tone of voice to collect emotional data. For example, it can analyze the user's facial expressions to identify emotions such as "anxiety" or "impatience." Finally, this data is sent to a cloud server.

[0748] Server Operation

[0749] The cloud-based server receives people and goods flow data sent from multiple devices, as well as user emotion data. This received data is integrated to grasp the overall situation. Specifically, it combines the emotion data with data on supplies and people flow sent from each evacuation shelter. The integrated data is then visualized on a map using a GIS (geographic information system). This allows the server to visually display the overall situation of people and goods flow on a geographical map, making it possible to see at a glance how many supplies are in which area and in which direction evacuees are moving.

[0750] The server then receives requests from users and begins analyzing them using an AI model. Emotional data is also incorporated into the analysis to determine the priority of user requests. For example, if a request for "water" is accompanied by emotional data such as "anxiety," that request will be processed with priority. Finally, based on the analysis results, a suggestion for the user's actions is created and sent to the user. For example, a suggestion such as "If you go to location A, there are 200 500ml bottles of water" is sent to the user.

[0751] User Actions

[0752] The user receives suggestions from the server and begins to act based on them. For example, they may move to a designated evacuation shelter or supply collection point and collect the necessary supplies. After taking action, they send feedback from their device to the server. For example, they may report, "I arrived at location A and received water."

[0753] Server supply optimization

[0754] The server aggregates requests fed back from multiple users and grasps overall demand. Based on the aggregated data, it optimizes the destination of relief supplies. For example, it identifies areas with high demand for water and creates a supply plan for those areas. It then instructs the relevant terminals on the supply destination and transportation plan. For example, it sends a command to the terminal saying, "Transport 500 bottles of water from warehouse X to location Y."

[0755] Specific examples

[0756] In the event of a natural disaster, this system can be used to grasp the status of supplies in the affected area. If a user sends a request saying "I want water," and the emotion engine detects the user's "anxiety" or "impatience," the server will prioritize the request. The server will notify the user of the optimal warehouse or pick-up location it suggests, and the user can accept the suggestion and receive the water.

[0757] In this way, the system of the present invention not only effectively manages the flow of people and goods during disasters, but also incorporates user emotion data to realize more accurate action suggestions and support.

[0758] Prompt Sentence Examples

[0759] Prompt to explain the system that suggests "optimal actions in the event of a disaster":

[0760] You are an evacuee in a disaster-hit area. You are currently in shelter C, but you are running low on water and food. Please tell us about your surroundings and how you are feeling. Based on that information, the AI ​​will suggest the best course of action for you.

[0761] As described above, in order to implement the present invention, by applying a multimodal camera, a cloud server, an AI model, and an emotion engine, it is possible to grasp the situation of people and goods flow during a disaster in real time and suggest optimal actions to the user.

[0762] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0763] Step 1: Data Acquisition

[0764] The device (a multimodal camera) captures real-time images of people and goods flowing through evacuation shelters and disaster sites, and acquires the video and audio data. The input is the video and audio captured by the camera, and the output is raw video and audio data. For example, it can capture the movement of people and the placement of supplies within an evacuation shelter.

[0765] Step 2: Data conversion

[0766] The device analyzes the captured video and audio data using AI image processing and audio analysis software. The input is raw video and audio data, and the output is specific digital data (e.g., "200 bottles of 500ml water" or "150 cans of food"). Specific operations include applying an image recognition algorithm to identify the type and quantity of supplies from the video.

[0767] Step 3: Acquire emotion data

[0768] The emotion engine installed in the device analyzes the user's facial expressions and tone of voice to collect emotional data. The input is data related to the user's face and tone of voice, and the output is emotional data (e.g., "anxiety," "impatience," etc.). Specific operations include analyzing the user's psychological state using facial expression recognition technology and voice analysis technology.

[0769] Step 4: Send data

[0770] The device transmits the converted material data and emotional data to a server on the cloud. The input is the digital data and emotional data analyzed and converted within the device, and the output is the data sent to the cloud server. The specific operation is to transmit the data via a wireless network.

[0771] Step 5: Receiving Data

[0772] The server receives people and logistics data, as well as emotion data, sent from multiple devices. The input is data from the devices, and the output is the received integrated data. Specifically, the server receives data using an API provided by the cloud platform.

[0773] Step 6: Data Integration

[0774] The server integrates the received data and grasps the overall situation. The input is the data received from each device, and the output is an integrated data set. Specific operations include the process of combining data from each evacuation shelter and the site into a single data set.

[0775] Step 7: Data visualization

[0776] The server visualizes the integrated data on a map in real time using a GIS (geographic information system). The input is the integrated data, and the output is a visualized geographic map. Specific operations include displaying the location of supplies and the movements of evacuees on the map.

[0777] Step 8: Receiving and Parsing the Request

[0778] The server receives requests from users and analyzes them using an AI model. It also incorporates emotional data into the analysis. The inputs are the user's request and emotional data, and the output is the analysis results. Specifically, it prioritizes requests based on the request content and the user's emotional state.

[0779] Step 9: Prioritize

[0780] The server determines the priority of requests based on the user's emotional data analyzed by the emotion engine. The input is the analysis result, and the output is a priority list. Specifically, requests from users who show high emotional levels, such as "anxiety" or "impatience," are prioritized.

[0781] Step 10: Submit your proposal

[0782] The server creates and sends a proposal to the user based on the analysis results. The input is the prioritized request and the analysis results, and the output is a proposal message. Specifically, it notifies the user that "If you go to location A, there are 200 500ml bottles of water."

[0783] Step 11: Take Action

[0784] The user receives a suggestion from the server and begins to act based on it. The input is a suggestion message from the server, and the output is the user's behavioral data. The specific action involves moving to a specified location and receiving the necessary supplies.

[0785] Step 12: Send feedback

[0786] After the user takes an action, they send feedback from their device to the server. The input is the user's reported data after the action, and the output is the feedback data sent to the server. A specific action is reported as "arrived at location A and received water."

[0787] Step 13: Request collection

[0788] The server aggregates feedback requests from multiple users. The input is feedback data from each user, and the output is aggregated request data. Specific operations include a process to understand how the overall demand is distributed.

[0789] Step 14: Supply Decision

[0790] The server optimizes the destinations of relief supplies based on the aggregated demand data. The input is the aggregated demand data, and the output is a supply plan. Specifically, it identifies the areas with the highest demand and formulates an appropriate supply plan.

[0791] Step 15: Transfer Instructions

[0792] The server instructs the relevant terminals on the supply destination and transfer plan. The input is the material supply plan, and the output is the transfer instruction. For example, an instruction to "transfer 500 bottles of water from warehouse X to location Y" is sent to the terminal. The specific operation is to send the transfer instruction to the relevant terminal and have it executed.

[0793] (Application example 2)

[0794] 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."

[0795] During disasters, it is difficult for victims and relief workers to receive supplies as quickly and efficiently as possible and ensure their safety. To improve convenience, it is necessary to determine priorities by taking into account not only people's movements and logistics situations, but also users' emotions. However, such an advanced system does not currently exist.

[0796] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for capturing and digitizing the situation of people and goods using a multimodal camera, means for transmitting the data to a cloud server, means for analyzing the user's facial expressions and tone of voice to collect emotional data, means for prioritizing requests using the collected emotional data and proposing optimal actions using AI, and means for transmitting the suggestions to the user. This makes it possible to grasp the situation of people and goods in real time even during a disaster and to propose optimal actions taking the user's emotions into consideration. It also makes it possible to provide relief supplies effectively and efficiently.

[0797] A "multimodal camera" is a camera that can simultaneously use multiple sensing methods, and is a device that can capture the flow of people and goods with high precision.

[0798] A "server on the cloud" is a remote server accessible via the Internet, and is a system that performs processes such as data storage, analysis, and integration.

[0799] "Analyzing the user's facial expressions and vocal tone" is a technology that quantifies the user's facial expressions and vocal tone to identify and evaluate their emotional state.

[0800] "Emotion data" is numerical or categorical data that indicates the emotional state of the user analyzed from facial expressions, tone of voice, and the like.

[0801] The "priority of a request" is the order of importance or urgency of a request to be executed among multiple user requests.

[0802] "Using AI to suggest optimal actions" refers to using artificial intelligence technology to analyze collected data and emotional data and recommend the most appropriate actions for the user.

[0803] "Understanding the situation of people and goods flow in real time" means instantly collecting and analyzing information on the movements and locations of people and goods at the current time.

[0804] "Providing relief supplies effectively and efficiently" means providing relief supplies to users who need them with the greatest effect and with the least amount of effort and time.

[0805] The present invention is a system that grasps the situation of people and goods flowing during a disaster in real time, incorporates user emotion data, and then suggests optimal actions. Below, we will explain in detail how to build and operate this system.

[0806] Hardware and software used

[0807] To realize the system of the present invention, the following main hardware and software are required.

[0808] Multimodal mounted camera: A device that captures people and logistics flows with high precision.

[0809] Cloud server: A remote server accessible via the Internet that stores, analyzes, integrates, and processes data.

[0810] Emotion engine: Software that recognizes the user's facial expressions and analyzes their voice to collect emotional data.

[0811] AI engine: An artificial intelligence technology that comprehensively analyzes collected data and emotional data to generate optimal action suggestions.

[0812] System operation details

[0813] 1. Data Acquisition:

[0814] The multimodal camera installed on the device captures real-time images of people and goods flowing through the evacuation center. For example, it can collect information on the movements of people and the location of supplies around evacuation centers. This data is then sent to a cloud server.

[0815] 2. Emotion data acquisition:

[0816] The emotion engine analyzes the user's facial expressions and tone of voice to collect emotional data, which can then be used to identify specific emotions such as "anxiety" or "impatience." This data is also sent to a cloud server.

[0817] 3. Data analysis and visualization:

[0818] The server analyzes the received data and grasps the overall situation, which is then visualized on a map, allowing users to see at a glance how many supplies are in which area and in which direction evacuees are moving.

[0819] 4. AI-powered recommendations for optimal actions:

[0820] The AI ​​engine generates optimal action suggestions based on collected people flow data, logistics data, and emotional data. If the emotional data indicates a high level of stress, such as anxiety or impatience, the request will be prioritized and immediate assistance will be provided to the user.

[0821] 5. Notification of Proposal:

[0822] The server generates suggestions and sends them to the user's smartphone or other device. For example, a specific suggestion such as "If you go to location A, there are 200 500ml bottles of water."

[0823] 6. Actions and Feedback:

[0824] The user then takes action based on the suggestions and later sends feedback from the device to the server, which then uses this feedback to optimize the delivery of relief supplies.

[0825] Specific examples

[0826] For example, if this system is used in an evacuation shelter where many evacuees gather after an earthquake, the following will happen: A multimodal camera captures the movements of people around the shelter, and an emotion engine detects the evacuees' anxiety. The cloud server integrates the data and suggests optimal actions (for example, moving supplies to a specific location). This allows relief supplies to be delivered quickly and efficiently.

[0827] Prompt Sentence Examples

[0828] "Create a program that identifies areas where food is scarce after an earthquake in real time and suggests optimal delivery routes. Prioritize based on user sentiment data. Use Python."

[0829] The above is the "mode for carrying out the invention" of the present invention. By constructing a system based on this mode, effective support in the event of a disaster can be achieved.

[0830] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0831] Step 1:

[0832] The device uses a multimodal camera to capture images of people and goods flowing through the device. The camera acquires video data in real time and captures it within the device. The input is the movement of people and objects, and the output is video data capturing these movements.

[0833] Step 2:

[0834] The device analyzes the acquired video data and converts it into specific digital data. For example, it identifies the type and quantity of supplies from the video data and organizes that information as digital data (e.g., 200 500ml bottles of water). The input is video data, and the output is analyzed digital data.

[0835] Step 3:

[0836] The device uses an emotion engine to analyze the user's facial expressions and tone of voice to collect emotional data. The emotional data includes specific emotional states such as "anxiety" and "impatience." The input is the user's facial expressions and voice, and the output is emotional data.

[0837] Step 4:

[0838] The device sends digital data and emotional data to a cloud server, which then centrally manages the collected data. The input is the analyzed digital data and emotional data, and the output is the data sent to the cloud server.

[0839] Step 5:

[0840] The server receives the data sent from the devices and integrates it to understand the overall situation. Based on this series of data, the server analyzes the overall picture of people and goods flow and visualizes the data on a single map. The input is the received data, and the output is the integrated and visualized data.

[0841] Step 6:

[0842] The server receives requests from users and analyzes them using AI. At the same time, it also incorporates user emotional data into the analysis and determines the priority of requests. The input is the user request and emotional data, and the output is a prioritized request.

[0843] Step 7:

[0844] The server then creates optimal action suggestions based on the results of the AI ​​analysis. These suggestions are derived by taking into account the user's request content and emotional data. The input is a prioritized request and the analysis results, and the output is a specific action suggestion.

[0845] Step 8:

[0846] The server sends the generated action suggestions to the user, allowing the user to receive information for deciding their next action. The input is the action suggestions, and the output is notification data for the user.

[0847] Step 9:

[0848] The user receives a suggestion from the server and starts to act based on it. For example, the user moves to a suggested location and picks up the necessary supplies. The input is notification data from the server, and the output is the user's action.

[0849] Step 10:

[0850] After taking an action, the user sends feedback from their device to the server. This feedback information is also managed by the server and used as information for future decisions. The input is the result of the user's action, and the output is feedback data sent to the server.

[0851] The above is a series of processing steps for realizing the system of the present invention, which makes it possible to grasp the situation of people and goods flowing in real time even during a disaster and to propose optimal actions that take the user's emotions into consideration.

[0852] 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.

[0853] 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.

[0854] 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.

[0855] [Third embodiment]

[0856] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0857] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0858] 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).

[0859] 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.

[0860] 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.

[0861] 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).

[0862] 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.

[0863] 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.

[0864] 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.

[0865] 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.

[0866] 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.

[0867] 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."

[0868] This invention is a system that grasps the situation of people and goods flow in real time during a disaster and suggests optimal actions to users. This system collects data using a multimodal camera, analyzes and visualizes the data on a cloud server, and suggests optimal actions to users.

[0869] Specific explanation of the program's operation

[0870] Device behavior

[0871] 1. Data Acquisition:

[0872] The device (a multimodal camera) captures real-time images of people and goods flow, such as images of supplies stored in local warehouses and people flowing through evacuation centers.

[0873] 2. Data conversion:

[0874] The captured image is analyzed within the device and converted into specific digital data. For example, the device may detect that there are 200 500ml bottles of water and generate that information as digital data.

[0875] 3. Data transmission:

[0876] The generated digital data is sent to a server on the cloud.

[0877] Server Operation

[0878] 4. Data reception:

[0879] The server receives people flow and logistics data transmitted from a plurality of terminals.

[0880] 5. Data Integration:

[0881] The received data is integrated to understand the overall situation. For example, data on water, food, medicine, etc. sent from multiple devices can be combined into one.

[0882] 6. Data Visualization:

[0883] The integrated data is visualized on a map and displayed in real time, allowing users and managers to grasp the overall situation at a glance.

[0884] 7. Receiving and parsing the request:

[0885] The server receives requests from users and uses AI to analyze the optimal action. For example, if a user requests "I want water," the server analyzes the data and identifies the optimal location.

[0886] 8. Submit a proposal:

[0887] The analysis results are sent to the user and the optimal course of action is suggested. For example, the system may notify the user that "If you go to location A, there are 200 500ml bottles of water."

[0888] User Actions

[0889] 9. Start action:

[0890] The user receives the suggestion from the server and initiates the optimal action, for example, moving to the suggested location to pick up the supplies.

[0891] 10. Send Feedback:

[0892] The user reports the results of the actions taken and new requests to the server as feedback, for example, "I arrived at location A and received water."

[0893] Server supply optimization

[0894] 11. Request Collection:

[0895] The server aggregates feedback requests from multiple users, thereby understanding overall demand.

[0896] 12. Supply decisions:

[0897] The server uses the aggregated data to optimize the delivery of relief supplies, for example by identifying areas with high demand for water and creating an optimal supply plan.

[0898] 13. Transfer instructions:

[0899] The server instructs the relevant terminals on supply destinations and transport plans. For example, it sends a command to the terminal to "transport 200 bottles of water from warehouse X to location Y."

[0900] Specific examples

[0901] For example, when a natural disaster occurs, this system can be used to grasp the status of supplies stored in warehouses in the affected area. When a user requests water, the server checks the warehouse status in real time and suggests the optimal warehouse and pick-up location to the user. The user can accept the suggestion, take action, and receive the water. Furthermore, if the user sends feedback after taking action, the server can reflect this in its next action proposals and supply plans.

[0902] In this way, the system of the present invention realizes effective management of people and goods flow during disasters and supports users in taking optimal actions.

[0903] The processing flow will be explained below.

[0904] Step 1:

[0905] The device uses a multimodal camera installed in the disaster area to capture real-time images of the surrounding human and physical flow. For example, the device captures and acquires images of people's movements around evacuation shelters.

[0906] Step 2:

[0907] The device analyzes the captured video and converts it into specific digital data using image recognition technology. For example, the device may identify from the video that there are 200 500ml water bottles and convert that information into data such as "500ml water: 200 bottles."

[0908] Step 3:

[0909] The device then sends the converted data to a cloud server via the internet, allowing data from devices in various locations to be centrally managed.

[0910] Step 4:

[0911] The server receives data sent from multiple devices and aggregates it on the cloud. For example, the server can consolidate data on the flow of supplies and people sent from each evacuation center.

[0912] Step 5:

[0913] The server analyzes and visualizes the aggregated data in real time, displaying the overall situation of people and goods flow on a geographical map, allowing users to see at a glance, for example, how much supplies are in which area and in which direction evacuees are moving.

[0914] Step 6:

[0915] Users access the cloud system from devices such as smartphones or tablets and send requests. For example, a user might input a request such as "I want water" and send it to the server.

[0916] Step 7:

[0917] The server receives a request from the user and begins analysis using AI. The server analyzes real-time data on the cloud to suggest optimal actions. For example, the server may determine that "Location A has 200 500ml water bottles."

[0918] Step 8:

[0919] The server creates a suggestion for the user based on the analysis results and sends that information to the user. For example, the server might send a suggestion to the user saying, "You can get water if you go to location A."

[0920] Step 9:

[0921] The user receives a suggestion from the server and begins to act based on it. The user travels to the specified location and collects the necessary supplies.

[0922] Step 10:

[0923] After taking an action, the user sends feedback from the device to the server. For example, the user reports, "I arrived at location A and received water."

[0924] Step 11:

[0925] The server receives feedback from users and reflects it in the next analysis. Based on the aggregated feedback, the server optimizes future plans for the delivery and transportation of relief supplies.

[0926] Step 12:

[0927] Based on the collected data, the server sends instructions for the supply of relief supplies to related devices as needed. For example, the server may issue an instruction such as "Transport 500 bottles of water from Warehouse X to Location Y."

[0928] The above is a detailed processing flow of the system for optimizing the flow of people and goods during disasters.

[0929] Example 1

[0930] 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."

[0931] During disasters, it is necessary to quickly grasp the status of people's movements and logistics and provide appropriate support. However, with conventional systems, it takes time to collect and analyze this information, and the proposal of appropriate actions is often delayed. As a result, it becomes difficult to effectively distribute relief supplies and quickly guide evacuees, resulting in a decrease in the efficiency of disaster response.

[0932] 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.

[0933] In this invention, the server includes means for capturing images and converting the situation of people and goods flowing in real time using a multimodal camera into data, means for transmitting the data to a cloud server, means for aggregating the received data in the cloud server to grasp the overall situation, means for visualizing the received data on a map, means for receiving requests from users and analyzing optimal actions using AI, and means for transmitting the analysis results to the users. This makes it possible to quickly and accurately grasp the situation of people and goods flowing in the event of a disaster and propose optimal actions to the users.

[0934] A "multimodal mounted camera" is a camera device that combines multiple different sensors (e.g., optical camera, infrared sensor, LIDAR, etc.) to capture people and logistics situations.

[0935] "Cloud servers" refer to remote computing servers accessible via the Internet that store, analyze, and visualize data.

[0936] "Digitization" is the process of converting captured images and information into digital format so that they can be handled electronically.

[0937] "Aggregation" is the act of centralizing information collected from multiple data sources and organizing and integrating it to grasp the overall situation.

[0938] "Visualization" refers to displaying numerical data or text data using visual representations such as maps or graphs to make the information easier to understand intuitively.

[0939] A "request" is a request or demand made by a user to the system, and may include the provision of a specific item or a search for information.

[0940] "AI" is an abbreviation for artificial intelligence, and is a technology that uses techniques such as machine learning and deep learning to analyze and propose optimal actions from large amounts of data.

[0941] "Means of analyzing optimal actions" refers to the process of using AI technology to determine the most effective actions for a user based on collected data and user requests.

[0942] "Feedback" refers to the actual results of actions or new requests that users provide to the system, and is used to further optimize the system.

[0943] "Distribution optimization" is the process of creating a plan based on aggregated data to distribute relief supplies most effectively.

[0944] A "transport instruction" is the act of sending an instruction to an associated terminal to transport relief supplies to a specific location.

[0945] The present invention provides a system for understanding the flow of people and goods in a disaster in real time and proposing optimal actions to users. Specific embodiments of the system will be described below.

[0946] First, the device uses a multimodal camera to capture real-time images of people and goods flow. This camera combines multiple different sensors, such as optical cameras, infrared sensors, and LIDAR. For example, it can measure the density of people in evacuation shelters or the amount of supplies stored in warehouses.

[0947] The device then analyzes the captured video and converts it into digital data using image processing libraries such as OpenCV and AI models. For example, it can detect the number of 500ml bottles of water and generate that information as JSON data.

[0948] The generated digital data is sent to a cloud server using a secure communication protocol (e.g., HTTPS), which receives the data in real time and aggregates it in a centralized database (e.g., MongoDB).

[0949] The server uses the aggregated data to grasp the overall situation of logistics and people flow. This data is visualized on a map and displayed visually using GIS (geographic information system) and Google Maps API, allowing managers and users to understand the situation at a glance.

[0950] When a user makes a request, a specific request such as "I want water" is sent to the server. The server uses an AI model (e.g., GPT-4) to analyze the request and propose the optimal action. The proposed action is notified to the user via a smartphone app. For example, "If you go to location A, there are 200 500ml bottles of water."

[0951] Users can carry out the suggested actions and receive the supplies. After that, they send the results of their actions and any new requests to the server as feedback. This feedback data is also aggregated on the cloud and used to optimize the delivery of relief supplies.

[0952] The server then uses the collected feedback and current data to create a plan to optimize the distribution of relief supplies, ensuring that supplies are distributed efficiently to where they are needed, and sends specific transport instructions to relevant devices to carry out the transport of supplies.

[0953] Specific examples

[0954] For example, when a natural disaster occurs, this system can be used to grasp the status of supplies stored in warehouses in the affected area. When a user uses a smartphone to request "water," the server checks the warehouse status in real time and suggests the optimal warehouse and pickup location to the user. The user can accept the suggestion, take action, and receive the water. Furthermore, if the user sends feedback after taking action, the server can reflect this in its next action proposal and supply plan. In this way, the system of the present invention realizes effective management of people and goods flow during disasters and supports users in taking optimal action.

[0955] Example prompts to input to the generative AI model

[0956] "Please explain a system that, when a natural disaster occurs, proposes the optimal course of action to efficiently supply necessary supplies to affected areas. Please explain the specific process for what data the system collects, how it analyzes it, and how it provides information to users."

[0957] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0958] Step 1:

[0959] Data Acquisition

[0960] The device uses a multimodal camera to capture people and goods flow in real time. The input data is the image captured by the camera, and the output is raw image data. Specifically, the camera captures a 360-degree range and collects data from multiple points.

[0961] Step 2:

[0962] Data Conversion

[0963] The device analyzes the captured video and converts it into digital data. The input is the raw video footage, and the output is the analyzed digital data (e.g., JSON format). Specifically, it uses OpenCV and AI models to count the number of objects and people in the video and generate digital data such as the number of 500ml bottles of water.

[0964] Step 3:

[0965] Data transmission

[0966] The terminal sends the generated digital data to a server on the cloud. The input is digital data, and the output is the completion of data transmission to the cloud server. Specifically, the HTTPS protocol is used to send the data securely while ensuring data integrity.

[0967] Step 4:

[0968] Data reception

[0969] The server receives digital data sent from the device. The input is digital data sent via the cloud, and the output is the storage of the received data. Specifically, it uses cloud platforms such as AWS and Google Cloud to quickly process large amounts of data and store it in a database.

[0970] Step 5:

[0971] Data Integration

[0972] The server integrates the data it receives to understand the overall situation. The input is data received from multiple devices, and the output is an integrated data set. Specifically, it uses a database such as MongoDB to consolidate information on water, food, medicine, etc.

[0973] Step 6:

[0974] Data Visualization

[0975] The server visualizes the integrated data on a map and displays it in real time. The input is the integrated data, and the output is the visualized information. Specifically, it uses GIS and Google Maps API to display the distribution status of supplies on a map.

[0976] Step 7:

[0977] Receiving and parsing requests

[0978] The server receives requests from users and uses AI to analyze the optimal course of action. The input is the user request (e.g., "I want water"), and the output is the analysis result (e.g., "There are 200 bottles of water at location A"). Specifically, it uses an AI model (e.g., GPT-4) to identify the optimal supply location and route.

[0979] Step 8:

[0980] Submit a proposal

[0981] The server sends the analysis results to the user. The input is the analysis results, and the output is a notification of the proposal to the user. Specifically, the server sends a notification to the user via a smartphone app.

[0982] Step 9:

[0983] Start of action

[0984] The user receives a proposal from the server and begins to act. The input is a proposal notification, and the output is the start of the action. Specifically, the user uses a map app on their smartphone to travel to the proposed warehouse.

[0985] Step 10:

[0986] Send Feedback

[0987] The user feeds back the results of their actions to the server. The input is feedback information, and the output is the completion of data transmission to the server. Specific operations include sending feedback from the smartphone to report the quantity and status of received supplies, as well as any new requests.

[0988] Step 11:

[0989] Request collection

[0990] The server manages the aggregated feedback data from multiple users. The input is the feedback from each user, and the output is the aggregated request data. Specifically, it uses an SQL database to manage the overall request and supply status.

[0991] Step 12:

[0992] supply decision

[0993] The server optimizes the destinations of relief supplies based on the aggregated data. The input is the aggregated data, and the output is a supply plan. Specifically, it creates a plan to prioritize the supply of supplies to areas with high demand.

[0994] Step 13:

[0995] Transfer instructions

[0996] The server sends transport instructions to the relevant terminals. The input is the supply plan, and the output is the command sent to the terminal. A specific operation is to send a specific command such as "Transport 200 bottles of water from warehouse X to location Y."

[0997] (Application example 1)

[0998] 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."

[0999] During disasters, there is a need to grasp the flow of people and goods in real time and propose optimal actions to users, but there is currently no satisfactory solution. In particular, there is an urgent need to provide a system that can efficiently manage the supply status of food and beverages and enable disaster victims to quickly obtain the supplies they need. It is also important to incorporate user feedback and flexibly optimize supply plans.

[1000] 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.

[1001] In this invention, the server includes: means for capturing images of people and goods flow using a multimodal camera and converting them into data; means for transmitting the data to a cloud server; means for aggregating and analyzing the received data at the cloud server and visualizing it on a map; means for receiving requests from users and proposing optimal actions using AI; means for transmitting the proposals to the users; means for grasping the surrounding supply situation in real time using a smartphone, analyzing the acquired data, and transmitting it to the cloud server; and means for the cloud server to integrate data transmitted from multiple smartphones and notify the user of optimal supply locations. This enables effective management of people and goods flow during disasters and propose optimal actions to users.

[1002] A "multimodal camera" is a camera that can simultaneously acquire multiple types of data (e.g., image data, audio data, etc.).

[1003] A "server on the cloud" is a remote server that provides data and services over the Internet.

[1004] "Digitization" is the conversion of physical information into digital data.

[1005] "Means of using AI to suggest optimal actions" refers to means of using artificial intelligence technology to calculate and suggest optimal actions based on the user's situation and requests.

[1006] A "smartphone" is a mobile phone with computing capabilities that can install applications and connect to the Internet.

[1007] "Supply status" refers to information that indicates the inventory and availability of goods and services in a specific region or location.

[1008] "Understanding the surrounding supply situation in real time" means instantly checking the current inventory and availability of goods and services on-site.

[1009] "Analyzing data" means converting acquired data into a form that is easy to interpret as information through calculations and logical operations.

[1010] "Integration" means bringing together multiple pieces of data and information into one system or format.

[1011] "Point of supply" means the location where goods or services are stocked or provided.

[1012] This invention relates to a system that grasps the situation of people and goods flow in real time during a disaster and suggests optimal actions to users. In particular, this invention realizes efficient supply management in the event of a disaster by grasping the supply situation in real time using a smartphone and notifying users of the optimal supply location.

[1013] Explaining system program generation and processing

[1014] Device operation (smartphone):

[1015] 1. Using the smartphone's camera and GPS module, information on the supply status and location is acquired and converted into data.

[1016] 2. The digitized supply information is sent via the Internet to a server on the cloud.

[1017] Server behavior:

[1018] 3. The server receives, integrates, and analyzes data sent from multiple smartphones on the cloud.

[1019] 4. Based on the analyzed data, the supply situation is visualized on a map, and the AI ​​suggests optimal actions in response to user requests.

[1020] 5. The proposed action is notified to the user, and user feedback is collected and reflected in optimizing the supply destination and suggesting the next action.

[1021] Hardware and software used

[1022] Hardware:

[1023] Smartphone: A mobile phone with computing capabilities and internet connectivity (e.g., a typical smartphone).

[1024] Camera: Smartphone built-in camera (e.g. Sony IMX586)

[1025] GPS: Built-in smartphone GPS module

[1026] software:

[1027] Python: Programming Language

[1028] The Requests library: a Python library for HTTP requests

[1029] OpenCV: A library for image recognition

[1030] Cloud services: Cloud platforms for data collection and analysis (e.g., AWS, Google Cloud)

[1031] Specific Description of the Embodiments

[1032] For example, in the event of a natural disaster, this system can be used to instantly grasp the food and beverage supply situation in the affected area. Users take photos of nearby food and beverage inventory with their smartphone cameras, and obtain location information using GPS. This information is sent to a cloud server, which then integrates and analyzes the supply information obtained from multiple smartphones. As a result, users are notified of the optimal supply location. Furthermore, feedback from users can be collected and reflected in optimizing the next supply plan.

[1033] Example prompts to input to the generative AI model

[1034] Example of input prompt:

[1035] A natural disaster has occurred, and there is a shortage of bottled water in the affected areas. Design an application that uses a smartphone to monitor the surrounding supply situation in real time and suggest the best course of action to the user. The application uses a camera to check the water bottle stock, obtains location information using GPS, and sends it to a cloud server. The server analyzes the data and notifies the user of the best location for a supply.

[1036] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1037] Step 1:

[1038] The device (smartphone) uses a camera to capture images of the surrounding supply situation (e.g., water or food inventory). The captured image data is analyzed using image recognition software (e.g., OpenCV) pre-installed on the device and converted into data such as inventory type and quantity. The device also obtains its current location information from its built-in GPS and compiles this data into a single data packet.

[1039] Input: Smartphone camera image, GPS location information

[1040] Output: Item inventory data, location information data

[1041] Step 2:

[1042] The device sends the collected and analyzed data packets over the Internet to a cloud server, using an HTTP request to send the data and confirm that the communication was successful.

[1043] Input: inventory data, location data

[1044] Output: HTTP request sent to the cloud server

[1045] Step 3:

[1046] The server receives data packets sent from multiple smartphones in the cloud, and the received data is stored in a database system for immediate analysis.

[1047] Input: Data packets from multiple smartphones

[1048] Output: Analyzable dataset

[1049] Step 4:

[1050] The server analyzes the received data and processes it into a format suitable for supply status statistics and map displays, including data integration and aggregation, and prepares it for immediate response when a user requests it.

[1051] Input: Analyzable dataset

[1052] Output: Statistics and map display data

[1053] Step 5:

[1054] When a request is received from a user, the server uses AI to suggest the optimal action. For example, if a user requests "I want water," the server will check the current supply situation based on the analyzed data and identify the optimal supply location for the user.

[1055] Input: User requests, statistics and data for map display

[1056] Output: Optimal action suggestion data

[1057] Step 6:

[1058] The server then sends the optimal action suggestions to the user's smartphone as push notifications or in-app messages, ensuring that the user receives them immediately.

[1059] Input: Optimal action suggestion data

[1060] Output: User notification

[1061] Step 7:

[1062] The user receives the proposal from the server and initiates the actual action. After taking the action, the user sends the results of the action as feedback from the terminal to the server. This feedback is used for the next proposal and for optimizing the supply plan.

[1063] Input: Suggestions from the server, user behavior results

[1064] Output: feedback of the results of the action

[1065] Step 8:

[1066] The server aggregates feedback data from multiple users and uses it to optimize supply destinations and transportation plans. The optimized supply destinations and transportation plans are then sent to related terminals, resulting in more efficient supply of goods.

[1067] Input: User feedback

[1068] Output: Optimized destination and transport planning data

[1069] 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.

[1070] This invention is an advanced system that combines an emotion engine with a system that grasps the situation of people and goods flowing during a disaster in real time and suggests optimal actions to users. This system collects data using a multimodal camera, analyzes and visualizes the data on a cloud server, and further incorporates the user's emotional data to suggest optimal actions.

[1071] Specific explanation of the program's operation

[1072] Device behavior

[1073] 1. Data Acquisition:

[1074] The device (a multimodal camera) captures the flow of people and goods in real time. For example, the device captures the movements of people around an evacuation shelter and acquires the footage.

[1075] 2. Data conversion:

[1076] The captured video is analyzed within the device and converted into specific digital data. For example, the device may detect from the video that there are 200 500ml water bottles and digitize that information as "500ml water: 200 bottles."

[1077] 3. Emotion data acquisition:

[1078] The device's built-in emotion engine analyzes the user's facial expressions and tone of voice to collect emotional data. For example, the device analyzes the user's facial expressions to identify emotions such as "anxiety" or "impatience."

[1079] 4. Data transmission:

[1080] The converted data and emotion data are sent to a server on the cloud.

[1081] Server Operation

[1082] 5. Data Reception:

[1083] The server receives people flow and logistics data and user emotion data transmitted from multiple terminals.

[1084] 6. Data Integration:

[1085] The received data is integrated to grasp the overall situation. For example, the server combines data on supplies and people flow sent from each evacuation center with emotional data.

[1086] 7. Data Visualization:

[1087] The server visualizes the integrated data on a map and displays it in real time, allowing users to see the overall situation of people and goods flowing on a geographical map, and understand at a glance how much supplies are in which area and in which direction evacuees are moving.

[1088] 8. Receiving and parsing requests:

[1089] The server receives the user's request and begins analyzing it using AI. Emotional data is also incorporated into the analysis. For example, if a user requests "I want water" and the request is accompanied by emotional data such as "anxiety," that request will be given priority.

[1090] 9. Prioritization:

[1091] The AI ​​prioritizes requests based on the user's emotional data analyzed by the emotion engine. For example, it prioritizes requests from users who are highly "anxious" or "impatient."

[1092] 10. Submit a proposal:

[1093] Based on the analysis results, the server creates a suggestion for the user and sends that information to the user. For example, the server sends a suggestion to the user saying, "If you go to location A, there are 200 500ml bottles of water."

[1094] User Actions

[1095] 11. Start action:

[1096] The user receives a suggestion from the server and begins to act based on it. The user travels to the specified location and collects the necessary supplies.

[1097] 12. Send Feedback:

[1098] After taking an action, the user sends feedback from the device to the server. For example, the user reports, "I arrived at location A and received water."

[1099] Server supply optimization

[1100] 13. Request Collection:

[1101] The server aggregates feedback requests from multiple users, thereby understanding overall demand.

[1102] 14. Supply decisions:

[1103] The server uses the aggregated data to optimize the delivery of relief supplies, for example by identifying areas with high demand for water and creating an optimal supply plan.

[1104] 15. Transfer instructions:

[1105] The server instructs the relevant terminals on supply destinations and transport plans, for example, sending a command to the terminal to "transport 500 bottles of water from warehouse X to location Y."

[1106] Specific examples

[1107] For example, in the event of a natural disaster, this system can be used to grasp the status of supplies stored in warehouses in the affected area. If a user requests "water" and the emotion engine detects the user's "anxiety" or "impatience," the server will prioritize the request. The server will notify the user of the optimal warehouse and pickup location it suggests, allowing the user to accept the suggestion and receive the water.

[1108] In this way, the system of the present invention not only effectively manages the flow of people and goods during disasters, but also incorporates user emotion data to realize more accurate action suggestions and support.

[1109] The processing flow will be explained below.

[1110] Step 1:

[1111] The device uses a multimodal camera installed in the disaster area to capture the surrounding human and logistics flow in real time, for example, capturing the movements of people around evacuation shelters.

[1112] Step 2:

[1113] The device analyzes the captured video and converts it into specific digital data using image recognition technology. For example, the device may detect from the video that there are 200 500ml water bottles and digitize that information as "500ml water: 200 bottles."

[1114] Step 3:

[1115] The device's built-in emotion engine analyzes the user's facial expressions and tone of voice to collect emotional data. For example, the device analyzes the user's facial expressions to identify emotions such as "anxiety" or "impatience."

[1116] Step 4:

[1117] The devices then send the converted data and emotion data to a cloud server via the internet, allowing data from devices in various locations to be centrally managed.

[1118] Step 5:

[1119] The server receives data on people and goods flow and emotional data of users transmitted from multiple terminals, for example, data on supplies and emotional data transmitted from each evacuation shelter.

[1120] Step 6:

[1121] The server integrates the received data to grasp the overall situation, for example, by combining the supply data and emotion data for each evacuation shelter.

[1122] Step 7:

[1123] The server analyzes and visualizes the integrated data in real time, displaying the overall situation of people and goods flow on a geographical map, allowing users to see at a glance how much supplies are in which area and in which direction evacuees are moving.

[1124] Step 8:

[1125] Users access the cloud system from devices such as smartphones or tablets and send requests. For example, they can input a request such as "I want water" and send it to the server.

[1126] Step 9:

[1127] The server receives the user's request and begins analyzing it using AI. Emotional data is also incorporated into the analysis. For example, if a user requests "I want water" and the request is accompanied by emotional data such as "anxiety," that request will be processed with priority.

[1128] Step 10:

[1129] The server prioritizes requests based on emotional data, for example, prioritizing requests from users who are highly anxious or impatient.

[1130] Step 11:

[1131] The server creates a suggestion for the user based on the analysis results and sends that information to the user. For example, it might send a suggestion to the user saying, "If you go to location A, there are 200 500ml bottles of water."

[1132] Step 12:

[1133] The user receives a suggestion from the server and begins to act based on it, for example, by moving to a specified location and picking up the necessary supplies.

[1134] Step 13:

[1135] After taking an action, the user sends feedback from the device to the server, for example, reporting, "I arrived at location A and received water."

[1136] Step 14:

[1137] The server receives feedback from users and incorporates it into subsequent analysis, for example optimizing the delivery and transportation plans of relief supplies based on the aggregated feedback.

[1138] Step 15:

[1139] Based on the collected data, the server sends instructions to relevant terminals to supply relief supplies as needed, such as "Transport 500 bottles of water from Warehouse X to Location Y."

[1140] The above is a detailed description of the processing flow in the optimization system for people flow, logistics, and emotional data during disasters.

[1141] Example 2

[1142] 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."

[1143] In the event of a disaster, it is extremely important to grasp the situation of people and goods in real time and respond quickly and effectively. However, conventional systems do not adequately manage supplies or provide support to evacuees, and care is particularly lacking for users who are emotionally unstable. This leads to unclear priorities for support and makes it difficult to optimally allocate resources.

[1144] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for capturing and digitizing the flow of people and goods using a multimodal camera; means for analyzing a user's facial expression and tone of voice to acquire emotional data; means for transmitting the data and emotional data to a cloud server; means for aggregating and analyzing the received data and emotional data in the cloud server and visualizing them on a map; means for receiving requests from users, prioritizing the requests using AI, and proposing optimal actions; and means for transmitting the proposals to the users. This enables real-time management of supplies and evacuees during disasters, enabling prioritization taking into account the user's emotional state, and achieving optimal resource allocation and rapid response.

[1145] A "multimodal on-board camera" is a device equipped with multiple different sensors (e.g., visible light camera, infrared camera, depth sensor, etc.) to acquire complex environmental information.

[1146] "People flow" is a term that refers to the flow or movement of people moving through a specific area within a certain period of time.

[1147] "Logistics" is a term that refers to the overall flow and movement of goods and materials, including transportation, storage, and distribution.

[1148] "Emotion data" is data relating to the user's psychological state, obtained by analyzing information such as the user's facial expression and tone of voice.

[1149] "Cloud" is a term that refers to a system of computer resources and data storage that are remotely available over the Internet.

[1150] A "server" is a central computer system that provides data and services to other computers over a network.

[1151] "Digitization" is the act of converting physical or analog information into digital data so that it can be processed by a computer.

[1152] "Analysis" is the process of investigating and analyzing acquired data in detail to extract useful information.

[1153] "Visualization" is a method of displaying data visually in an easy-to-understand manner, and includes formats such as maps, graphs, and charts.

[1154] A "request" is a request from a user to the system for a specific operation or information provision.

[1155] "Priority" refers to the ordering used to determine which of multiple tasks or requests should be processed first.

[1156] "Action suggestions" are specific guidance or instructions that suggest optimal actions to the user based on the analysis results.

[1157] "Feedback" refers to response information provided by users to the system, and is used to improve services and as new information for decision-making.

[1158] This invention is an advanced system that grasps the situation of people and goods flow in real time during disasters and suggests optimal actions to users. This system is built by combining a multimodal camera, a cloud server, an AI model, and an emotion engine.

[1159] Device behavior

[1160] First, a multimodal camera is used to capture real-time images of people and goods flowing through the evacuation center. For example, it can capture footage of people's movements around an evacuation center. The captured footage is then analyzed within the device and converted into specific digital data. For example, AI image processing software can analyze the footage to detect that there are 200 500ml water bottles, digitizing this information as "500ml water: 200 bottles." Furthermore, the device's built-in emotion engine analyzes the user's facial expressions and tone of voice to collect emotional data. For example, it can analyze the user's facial expressions to identify emotions such as "anxiety" or "impatience." Finally, this data is sent to a cloud server.

[1161] Server Operation

[1162] The cloud-based server receives people and goods flow data sent from multiple devices, as well as user emotion data. This received data is integrated to grasp the overall situation. Specifically, it combines the emotion data with data on supplies and people flow sent from each evacuation shelter. The integrated data is then visualized on a map using a GIS (geographic information system). This allows the server to visually display the overall situation of people and goods flow on a geographical map, making it possible to see at a glance how many supplies are in which area and in which direction evacuees are moving.

[1163] The server then receives requests from users and begins analyzing them using an AI model. Emotional data is also incorporated into the analysis to determine the priority of user requests. For example, if a request for "water" is accompanied by emotional data such as "anxiety," that request will be processed with priority. Finally, based on the analysis results, a suggestion for the user's actions is created and sent to the user. For example, a suggestion such as "If you go to location A, there are 200 500ml bottles of water" is sent to the user.

[1164] User Actions

[1165] The user receives suggestions from the server and begins to act based on them. For example, they may move to a designated evacuation shelter or supply collection point and collect the necessary supplies. After taking action, they send feedback from their device to the server. For example, they may report, "I arrived at location A and received water."

[1166] Server supply optimization

[1167] The server aggregates requests fed back from multiple users and grasps overall demand. Based on the aggregated data, it optimizes the destination of relief supplies. For example, it identifies areas with high demand for water and creates a supply plan for those areas. It then instructs the relevant terminals on the supply destination and transportation plan. For example, it sends a command to the terminal saying, "Transport 500 bottles of water from warehouse X to location Y."

[1168] Specific examples

[1169] In the event of a natural disaster, this system can be used to grasp the status of supplies in the affected area. If a user sends a request saying "I want water," and the emotion engine detects the user's "anxiety" or "impatience," the server will prioritize the request. The server will notify the user of the optimal warehouse or pick-up location it suggests, and the user can accept the suggestion and receive the water.

[1170] In this way, the system of the present invention not only effectively manages the flow of people and goods during disasters, but also incorporates user emotion data to realize more accurate action suggestions and support.

[1171] Prompt Sentence Examples

[1172] Prompt to explain the system that suggests "optimal actions in the event of a disaster":

[1173] You are an evacuee in a disaster-hit area. You are currently in shelter C, but you are running low on water and food. Please tell us about your surroundings and how you are feeling. Based on that information, the AI ​​will suggest the best course of action for you.

[1174] As described above, in order to implement the present invention, by applying a multimodal camera, a cloud server, an AI model, and an emotion engine, it is possible to grasp the situation of people and goods flow during a disaster in real time and suggest optimal actions to the user.

[1175] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1176] Step 1: Data Acquisition

[1177] The device (a multimodal camera) captures real-time images of people and goods flowing through evacuation shelters and disaster sites, and acquires the video and audio data. The input is the video and audio captured by the camera, and the output is raw video and audio data. For example, it can capture the movement of people and the placement of supplies within an evacuation shelter.

[1178] Step 2: Data conversion

[1179] The device analyzes the captured video and audio data using AI image processing and audio analysis software. The input is raw video and audio data, and the output is specific digital data (e.g., "200 bottles of 500ml water" or "150 cans of food"). Specific operations include applying an image recognition algorithm to identify the type and quantity of supplies from the video.

[1180] Step 3: Acquire emotion data

[1181] The emotion engine installed in the device analyzes the user's facial expressions and tone of voice to collect emotional data. The input is data related to the user's face and tone of voice, and the output is emotional data (e.g., "anxiety," "impatience," etc.). Specific operations include analyzing the user's psychological state using facial expression recognition technology and voice analysis technology.

[1182] Step 4: Send data

[1183] The device transmits the converted material data and emotional data to a server on the cloud. The input is the digital data and emotional data analyzed and converted within the device, and the output is the data sent to the cloud server. The specific operation is to transmit the data via a wireless network.

[1184] Step 5: Receiving Data

[1185] The server receives people and logistics data, as well as emotion data, sent from multiple devices. The input is data from the devices, and the output is the received integrated data. Specifically, the server receives data using an API provided by the cloud platform.

[1186] Step 6: Data Integration

[1187] The server integrates the received data and grasps the overall situation. The input is the data received from each device, and the output is an integrated data set. Specific operations include the process of combining data from each evacuation shelter and the site into a single data set.

[1188] Step 7: Data visualization

[1189] The server visualizes the integrated data on a map in real time using a GIS (geographic information system). The input is the integrated data, and the output is a visualized geographic map. Specific operations include displaying the location of supplies and the movements of evacuees on the map.

[1190] Step 8: Receiving and Parsing the Request

[1191] The server receives requests from users and analyzes them using an AI model. It also incorporates emotional data into the analysis. The inputs are the user's request and emotional data, and the output is the analysis results. Specifically, it prioritizes requests based on the request content and the user's emotional state.

[1192] Step 9: Prioritize

[1193] The server determines the priority of requests based on the user's emotional data analyzed by the emotion engine. The input is the analysis result, and the output is a priority list. Specifically, requests from users who show high emotional levels, such as "anxiety" or "impatience," are prioritized.

[1194] Step 10: Submit your proposal

[1195] The server creates and sends a proposal to the user based on the analysis results. The input is the prioritized request and the analysis results, and the output is a proposal message. Specifically, it notifies the user that "If you go to location A, there are 200 500ml bottles of water."

[1196] Step 11: Take Action

[1197] The user receives a suggestion from the server and begins to act based on it. The input is a suggestion message from the server, and the output is the user's behavioral data. The specific action involves moving to a specified location and receiving the necessary supplies.

[1198] Step 12: Send feedback

[1199] After the user takes an action, they send feedback from their device to the server. The input is the user's reported data after the action, and the output is the feedback data sent to the server. A specific action is reported as "arrived at location A and received water."

[1200] Step 13: Request collection

[1201] The server aggregates feedback requests from multiple users. The input is feedback data from each user, and the output is aggregated request data. Specific operations include a process to understand how the overall demand is distributed.

[1202] Step 14: Supply Decision

[1203] The server optimizes the destinations of relief supplies based on the aggregated demand data. The input is the aggregated demand data, and the output is a supply plan. Specifically, it identifies the areas with the highest demand and formulates an appropriate supply plan.

[1204] Step 15: Transfer Instructions

[1205] The server instructs the relevant terminals on the supply destination and transfer plan. The input is the material supply plan, and the output is the transfer instruction. For example, an instruction to "transfer 500 bottles of water from warehouse X to location Y" is sent to the terminal. The specific operation is to send the transfer instruction to the relevant terminal and have it executed.

[1206] (Application example 2)

[1207] 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."

[1208] During disasters, it is difficult for victims and relief workers to receive supplies as quickly and efficiently as possible and ensure their safety. To improve convenience, it is necessary to determine priorities by taking into account not only people's movements and logistics situations, but also users' emotions. However, such an advanced system does not currently exist.

[1209] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for capturing and digitizing the situation of people and goods using a multimodal camera, means for transmitting the data to a cloud server, means for analyzing the user's facial expressions and tone of voice to collect emotional data, means for prioritizing requests using the collected emotional data and proposing optimal actions using AI, and means for transmitting the suggestions to the user. This makes it possible to grasp the situation of people and goods in real time even during a disaster and to propose optimal actions taking the user's emotions into consideration. It also makes it possible to provide relief supplies effectively and efficiently.

[1210] A "multimodal camera" is a camera that can simultaneously use multiple sensing methods, and is a device that can capture the flow of people and goods with high precision.

[1211] A "server on the cloud" is a remote server accessible via the Internet, and is a system that performs processes such as data storage, analysis, and integration.

[1212] "Analyzing the user's facial expressions and vocal tone" is a technology that quantifies the user's facial expressions and vocal tone to identify and evaluate their emotional state.

[1213] "Emotion data" is numerical or categorical data that indicates the emotional state of the user analyzed from facial expressions, tone of voice, and the like.

[1214] The "priority of a request" is the order of importance or urgency of a request to be executed among multiple user requests.

[1215] "Using AI to suggest optimal actions" refers to using artificial intelligence technology to analyze collected data and emotional data and recommend the most appropriate actions for the user.

[1216] "Understanding the situation of people and goods flow in real time" means instantly collecting and analyzing information on the movements and locations of people and goods at the current time.

[1217] "Providing relief supplies effectively and efficiently" means providing relief supplies to users who need them with the greatest effect and with the least amount of effort and time.

[1218] The present invention is a system that grasps the situation of people and goods flowing during a disaster in real time, incorporates user emotion data, and then suggests optimal actions. Below, we will explain in detail how to build and operate this system.

[1219] Hardware and software used

[1220] To realize the system of the present invention, the following main hardware and software are required.

[1221] Multimodal mounted camera: A device that captures people and logistics flows with high precision.

[1222] Cloud server: A remote server accessible via the Internet that stores, analyzes, integrates, and processes data.

[1223] Emotion engine: Software that recognizes the user's facial expressions and analyzes their voice to collect emotional data.

[1224] AI engine: An artificial intelligence technology that comprehensively analyzes collected data and emotional data to generate optimal action suggestions.

[1225] System operation details

[1226] 1. Data Acquisition:

[1227] The multimodal camera installed on the device captures real-time images of people and goods flowing through the evacuation center. For example, it can collect information on the movements of people and the location of supplies around evacuation centers. This data is then sent to a cloud server.

[1228] 2. Emotion data acquisition:

[1229] The emotion engine analyzes the user's facial expressions and tone of voice to collect emotional data, which can then be used to identify specific emotions such as "anxiety" or "impatience." This data is also sent to a cloud server.

[1230] 3. Data analysis and visualization:

[1231] The server analyzes the received data and grasps the overall situation, which is then visualized on a map, allowing users to see at a glance how many supplies are in which area and in which direction evacuees are moving.

[1232] 4. AI-powered recommendations for optimal actions:

[1233] The AI ​​engine generates optimal action suggestions based on collected people flow data, logistics data, and emotional data. If the emotional data indicates a high level of stress, such as anxiety or impatience, the request will be prioritized and immediate assistance will be provided to the user.

[1234] 5. Notification of Proposal:

[1235] The server generates suggestions and sends them to the user's smartphone or other device. For example, a specific suggestion such as "If you go to location A, there are 200 500ml bottles of water."

[1236] 6. Actions and Feedback:

[1237] The user then takes action based on the suggestions and later sends feedback from the device to the server, which then uses this feedback to optimize the delivery of relief supplies.

[1238] Specific examples

[1239] For example, if this system is used in an evacuation shelter where many evacuees gather after an earthquake, the following will happen: A multimodal camera captures the movements of people around the shelter, and an emotion engine detects the evacuees' anxiety. The cloud server integrates the data and suggests optimal actions (for example, moving supplies to a specific location). This allows relief supplies to be delivered quickly and efficiently.

[1240] Prompt Sentence Examples

[1241] "Create a program that identifies areas where food is scarce after an earthquake in real time and suggests optimal delivery routes. Prioritize based on user sentiment data. Use Python."

[1242] The above is the "mode for carrying out the invention" of the present invention. By constructing a system based on this mode, effective support in the event of a disaster can be achieved.

[1243] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1244] Step 1:

[1245] The device uses a multimodal camera to capture images of people and goods flowing through the device. The camera acquires video data in real time and captures it within the device. The input is the movement of people and objects, and the output is video data capturing these movements.

[1246] Step 2:

[1247] The device analyzes the acquired video data and converts it into specific digital data. For example, it identifies the type and quantity of supplies from the video data and organizes that information as digital data (e.g., 200 500ml bottles of water). The input is video data, and the output is analyzed digital data.

[1248] Step 3:

[1249] The device uses an emotion engine to analyze the user's facial expressions and tone of voice to collect emotional data. The emotional data includes specific emotional states such as "anxiety" and "impatience." The input is the user's facial expressions and voice, and the output is emotional data.

[1250] Step 4:

[1251] The device sends digital data and emotional data to a cloud server, which then centrally manages the collected data. The input is the analyzed digital data and emotional data, and the output is the data sent to the cloud server.

[1252] Step 5:

[1253] The server receives the data sent from the devices and integrates it to understand the overall situation. Based on this series of data, the server analyzes the overall picture of people and goods flow and visualizes the data on a single map. The input is the received data, and the output is the integrated and visualized data.

[1254] Step 6:

[1255] The server receives requests from users and analyzes them using AI. At the same time, it also incorporates user emotional data into the analysis and determines the priority of requests. The input is the user request and emotional data, and the output is a prioritized request.

[1256] Step 7:

[1257] The server then creates optimal action suggestions based on the results of the AI ​​analysis. These suggestions are derived by taking into account the user's request content and emotional data. The input is a prioritized request and the analysis results, and the output is a specific action suggestion.

[1258] Step 8:

[1259] The server sends the generated action suggestions to the user, allowing the user to receive information for deciding their next action. The input is the action suggestions, and the output is notification data for the user.

[1260] Step 9:

[1261] The user receives a suggestion from the server and starts to act based on it. For example, the user moves to a suggested location and picks up the necessary supplies. The input is notification data from the server, and the output is the user's action.

[1262] Step 10:

[1263] After taking an action, the user sends feedback from their device to the server. This feedback information is also managed by the server and used as information for future decisions. The input is the result of the user's action, and the output is feedback data sent to the server.

[1264] The above is a series of processing steps for realizing the system of the present invention, which makes it possible to grasp the situation of people and goods flowing in real time even during a disaster and to propose optimal actions that take the user's emotions into consideration.

[1265] 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.

[1266] 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.

[1267] 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.

[1268] [Fourth embodiment]

[1269] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1270] 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.

[1271] 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).

[1272] 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.

[1273] 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.

[1274] 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).

[1275] 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.

[1276] 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.

[1277] 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.

[1278] 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.

[1279] 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.

[1280] 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.

[1281] 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."

[1282] This invention is a system that grasps the situation of people and goods flow in real time during a disaster and suggests optimal actions to users. This system collects data using a multimodal camera, analyzes and visualizes the data on a cloud server, and suggests optimal actions to users.

[1283] Specific explanation of the program's operation

[1284] Device behavior

[1285] 1. Data Acquisition:

[1286] The device (a multimodal camera) captures real-time images of people and goods flow, such as images of supplies stored in local warehouses and people flowing through evacuation centers.

[1287] 2. Data conversion:

[1288] The captured image is analyzed within the device and converted into specific digital data. For example, the device may detect that there are 200 500ml bottles of water and generate that information as digital data.

[1289] 3. Data transmission:

[1290] The generated digital data is sent to a server on the cloud.

[1291] Server Operation

[1292] 4. Data reception:

[1293] The server receives people flow and logistics data transmitted from a plurality of terminals.

[1294] 5. Data Integration:

[1295] The received data is integrated to understand the overall situation. For example, data on water, food, medicine, etc. sent from multiple devices can be combined into one.

[1296] 6. Data Visualization:

[1297] The integrated data is visualized on a map and displayed in real time, allowing users and managers to grasp the overall situation at a glance.

[1298] 7. Receiving and parsing the request:

[1299] The server receives requests from users and uses AI to analyze the optimal action. For example, if a user requests "I want water," the server analyzes the data and identifies the optimal location.

[1300] 8. Submit a proposal:

[1301] The analysis results are sent to the user and the optimal course of action is suggested. For example, the system may notify the user that "If you go to location A, there are 200 500ml bottles of water."

[1302] User Actions

[1303] 9. Start action:

[1304] The user receives the suggestion from the server and initiates the optimal action, for example, moving to the suggested location to pick up the supplies.

[1305] 10. Send Feedback:

[1306] The user reports the results of the actions taken and new requests to the server as feedback, for example, "I arrived at location A and received water."

[1307] Server supply optimization

[1308] 11. Request Collection:

[1309] The server aggregates feedback requests from multiple users, thereby understanding overall demand.

[1310] 12. Supply decisions:

[1311] The server uses the aggregated data to optimize the delivery of relief supplies, for example by identifying areas with high demand for water and creating an optimal supply plan.

[1312] 13. Transfer instructions:

[1313] The server instructs the relevant terminals on supply destinations and transport plans. For example, it sends a command to the terminal to "transport 200 bottles of water from warehouse X to location Y."

[1314] Specific examples

[1315] For example, when a natural disaster occurs, this system can be used to grasp the status of supplies stored in warehouses in the affected area. When a user requests water, the server checks the warehouse status in real time and suggests the optimal warehouse and pick-up location to the user. The user can accept the suggestion, take action, and receive the water. Furthermore, if the user sends feedback after taking action, the server can reflect this in its next action proposals and supply plans.

[1316] In this way, the system of the present invention realizes effective management of people and goods flow during disasters and supports users in taking optimal actions.

[1317] The processing flow will be explained below.

[1318] Step 1:

[1319] The device uses a multimodal camera installed in the disaster area to capture real-time images of the surrounding human and physical flow. For example, the device captures and acquires images of people's movements around evacuation shelters.

[1320] Step 2:

[1321] The device analyzes the captured video and converts it into specific digital data using image recognition technology. For example, the device may identify from the video that there are 200 500ml water bottles and convert that information into data such as "500ml water: 200 bottles."

[1322] Step 3:

[1323] The device then sends the converted data to a cloud server via the internet, allowing data from devices in various locations to be centrally managed.

[1324] Step 4:

[1325] The server receives data sent from multiple devices and aggregates it on the cloud. For example, the server can consolidate data on the flow of supplies and people sent from each evacuation center.

[1326] Step 5:

[1327] The server analyzes and visualizes the aggregated data in real time, displaying the overall situation of people and goods flow on a geographical map, allowing users to see at a glance, for example, how much supplies are in which area and in which direction evacuees are moving.

[1328] Step 6:

[1329] Users access the cloud system from devices such as smartphones or tablets and send requests. For example, a user might input a request such as "I want water" and send it to the server.

[1330] Step 7:

[1331] The server receives a request from the user and begins analysis using AI. The server analyzes real-time data on the cloud to suggest optimal actions. For example, the server may determine that "Location A has 200 500ml water bottles."

[1332] Step 8:

[1333] The server creates a suggestion for the user based on the analysis results and sends that information to the user. For example, the server might send a suggestion to the user saying, "You can get water if you go to location A."

[1334] Step 9:

[1335] The user receives a suggestion from the server and begins to act based on it. The user travels to the specified location and collects the necessary supplies.

[1336] Step 10:

[1337] After taking an action, the user sends feedback from the device to the server. For example, the user reports, "I arrived at location A and received water."

[1338] Step 11:

[1339] The server receives feedback from users and reflects it in the next analysis. Based on the aggregated feedback, the server optimizes future plans for the delivery and transportation of relief supplies.

[1340] Step 12:

[1341] Based on the collected data, the server sends instructions for the supply of relief supplies to related devices as needed. For example, the server may issue an instruction such as "Transport 500 bottles of water from Warehouse X to Location Y."

[1342] The above is a detailed processing flow of the system for optimizing the flow of people and goods during disasters.

[1343] Example 1

[1344] 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."

[1345] During disasters, it is necessary to quickly grasp the status of people's movements and logistics and provide appropriate support. However, with conventional systems, it takes time to collect and analyze this information, and the proposal of appropriate actions is often delayed. As a result, it becomes difficult to effectively distribute relief supplies and quickly guide evacuees, resulting in a decrease in the efficiency of disaster response.

[1346] 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.

[1347] In this invention, the server includes means for capturing images and converting the situation of people and goods flowing in real time using a multimodal camera into data, means for transmitting the data to a cloud server, means for aggregating the received data in the cloud server to grasp the overall situation, means for visualizing the received data on a map, means for receiving requests from users and analyzing optimal actions using AI, and means for transmitting the analysis results to the users. This makes it possible to quickly and accurately grasp the situation of people and goods flowing in the event of a disaster and propose optimal actions to the users.

[1348] A "multimodal mounted camera" is a camera device that combines multiple different sensors (e.g., optical camera, infrared sensor, LIDAR, etc.) to capture people and logistics situations.

[1349] "Cloud servers" refer to remote computing servers accessible via the Internet that store, analyze, and visualize data.

[1350] "Digitization" is the process of converting captured images and information into digital format so that they can be handled electronically.

[1351] "Aggregation" is the act of centralizing information collected from multiple data sources and organizing and integrating it to grasp the overall situation.

[1352] "Visualization" refers to displaying numerical data or text data using visual representations such as maps or graphs to make the information easier to understand intuitively.

[1353] A "request" is a request or demand made by a user to the system, and may include the provision of a specific item or a search for information.

[1354] "AI" is an abbreviation for artificial intelligence, and is a technology that uses techniques such as machine learning and deep learning to analyze and propose optimal actions from large amounts of data.

[1355] "Means of analyzing optimal actions" refers to the process of using AI technology to determine the most effective actions for a user based on collected data and user requests.

[1356] "Feedback" refers to the actual results of actions or new requests that users provide to the system, and is used to further optimize the system.

[1357] "Distribution optimization" is the process of creating a plan based on aggregated data to distribute relief supplies most effectively.

[1358] A "transport instruction" is the act of sending an instruction to an associated terminal to transport relief supplies to a specific location.

[1359] The present invention provides a system for understanding the flow of people and goods in a disaster in real time and proposing optimal actions to users. Specific embodiments of the system will be described below.

[1360] First, the device uses a multimodal camera to capture real-time images of people and goods flow. This camera combines multiple different sensors, such as optical cameras, infrared sensors, and LIDAR. For example, it can measure the density of people in evacuation shelters or the amount of supplies stored in warehouses.

[1361] The device then analyzes the captured video and converts it into digital data using image processing libraries such as OpenCV and AI models. For example, it can detect the number of 500ml bottles of water and generate that information as JSON data.

[1362] The generated digital data is sent to a cloud server using a secure communication protocol (e.g., HTTPS), which receives the data in real time and aggregates it in a centralized database (e.g., MongoDB).

[1363] The server uses the aggregated data to grasp the overall situation of logistics and people flow. This data is visualized on a map and displayed visually using GIS (geographic information system) and Google Maps API, allowing managers and users to understand the situation at a glance.

[1364] When a user makes a request, a specific request such as "I want water" is sent to the server. The server uses an AI model (e.g., GPT-4) to analyze the request and propose the optimal action. The proposed action is notified to the user via a smartphone app. For example, "If you go to location A, there are 200 500ml bottles of water."

[1365] Users can carry out the suggested actions and receive the supplies. After that, they send the results of their actions and any new requests to the server as feedback. This feedback data is also aggregated on the cloud and used to optimize the delivery of relief supplies.

[1366] The server then uses the collected feedback and current data to create a plan to optimize the distribution of relief supplies, ensuring that supplies are distributed efficiently to where they are needed, and sends specific transport instructions to relevant devices to carry out the transport of supplies.

[1367] Specific examples

[1368] For example, when a natural disaster occurs, this system can be used to grasp the status of supplies stored in warehouses in the affected area. When a user uses a smartphone to request "water," the server checks the warehouse status in real time and suggests the optimal warehouse and pickup location to the user. The user can accept the suggestion, take action, and receive the water. Furthermore, if the user sends feedback after taking action, the server can reflect this in its next action proposal and supply plan. In this way, the system of the present invention realizes effective management of people and goods flow during disasters and supports users in taking optimal action.

[1369] Example prompts to input to the generative AI model

[1370] "Please explain a system that, when a natural disaster occurs, proposes the optimal course of action to efficiently supply necessary supplies to affected areas. Please explain the specific process for what data the system collects, how it analyzes it, and how it provides information to users."

[1371] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1372] Step 1:

[1373] Data Acquisition

[1374] The device uses a multimodal camera to capture people and goods flow in real time. The input data is the image captured by the camera, and the output is raw image data. Specifically, the camera captures a 360-degree range and collects data from multiple points.

[1375] Step 2:

[1376] Data Conversion

[1377] The device analyzes the captured video and converts it into digital data. The input is the raw video footage, and the output is the analyzed digital data (e.g., JSON format). Specifically, it uses OpenCV and AI models to count the number of objects and people in the video and generate digital data such as the number of 500ml bottles of water.

[1378] Step 3:

[1379] Data transmission

[1380] The terminal sends the generated digital data to a server on the cloud. The input is digital data, and the output is the completion of data transmission to the cloud server. Specifically, the HTTPS protocol is used to send the data securely while ensuring data integrity.

[1381] Step 4:

[1382] Data reception

[1383] The server receives digital data sent from the device. The input is digital data sent via the cloud, and the output is the storage of the received data. Specifically, it uses cloud platforms such as AWS and Google Cloud to quickly process large amounts of data and store it in a database.

[1384] Step 5:

[1385] Data Integration

[1386] The server integrates the data it receives to understand the overall situation. The input is data received from multiple devices, and the output is an integrated data set. Specifically, it uses a database such as MongoDB to consolidate information on water, food, medicine, etc.

[1387] Step 6:

[1388] Data Visualization

[1389] The server visualizes the integrated data on a map and displays it in real time. The input is the integrated data, and the output is the visualized information. Specifically, it uses GIS and Google Maps API to display the distribution status of supplies on a map.

[1390] Step 7:

[1391] Receiving and parsing requests

[1392] The server receives requests from users and uses AI to analyze the optimal course of action. The input is the user request (e.g., "I want water"), and the output is the analysis result (e.g., "There are 200 bottles of water at location A"). Specifically, it uses an AI model (e.g., GPT-4) to identify the optimal supply location and route.

[1393] Step 8:

[1394] Submit a proposal

[1395] The server sends the analysis results to the user. The input is the analysis results, and the output is a notification of the proposal to the user. Specifically, the server sends a notification to the user via a smartphone app.

[1396] Step 9:

[1397] Start of action

[1398] The user receives a proposal from the server and begins to act. The input is a proposal notification, and the output is the start of the action. Specifically, the user uses a map app on their smartphone to travel to the proposed warehouse.

[1399] Step 10:

[1400] Send Feedback

[1401] The user feeds back the results of their actions to the server. The input is feedback information, and the output is the completion of data transmission to the server. Specific operations include sending feedback from the smartphone to report the quantity and status of received supplies, as well as any new requests.

[1402] Step 11:

[1403] Request collection

[1404] The server manages the aggregated feedback data from multiple users. The input is the feedback from each user, and the output is the aggregated request data. Specifically, it uses an SQL database to manage the overall request and supply status.

[1405] Step 12:

[1406] supply decision

[1407] The server optimizes the destinations of relief supplies based on the aggregated data. The input is the aggregated data, and the output is a supply plan. Specifically, it creates a plan to prioritize the supply of supplies to areas with high demand.

[1408] Step 13:

[1409] Transfer instructions

[1410] The server sends transport instructions to the relevant terminals. The input is the supply plan, and the output is the command sent to the terminal. A specific operation is to send a specific command such as "Transport 200 bottles of water from warehouse X to location Y."

[1411] (Application example 1)

[1412] 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."

[1413] During disasters, there is a need to grasp the flow of people and goods in real time and propose optimal actions to users, but there is currently no satisfactory solution. In particular, there is an urgent need to provide a system that can efficiently manage the supply status of food and beverages and enable disaster victims to quickly obtain the supplies they need. It is also important to incorporate user feedback and flexibly optimize supply plans.

[1414] 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.

[1415] In this invention, the server includes: means for capturing images of people and goods flow using a multimodal camera and converting them into data; means for transmitting the data to a cloud server; means for aggregating and analyzing the received data at the cloud server and visualizing it on a map; means for receiving requests from users and proposing optimal actions using AI; means for transmitting the proposals to the users; means for grasping the surrounding supply situation in real time using a smartphone, analyzing the acquired data, and transmitting it to the cloud server; and means for the cloud server to integrate data transmitted from multiple smartphones and notify the user of optimal supply locations. This enables effective management of people and goods flow during disasters and propose optimal actions to users.

[1416] A "multimodal camera" is a camera that can simultaneously acquire multiple types of data (e.g., image data, audio data, etc.).

[1417] A "server on the cloud" is a remote server that provides data and services over the Internet.

[1418] "Digitization" is the conversion of physical information into digital data.

[1419] "Means of using AI to suggest optimal actions" refers to means of using artificial intelligence technology to calculate and suggest optimal actions based on the user's situation and requests.

[1420] A "smartphone" is a mobile phone with computing capabilities that can install applications and connect to the Internet.

[1421] "Supply status" refers to information that indicates the inventory and availability of goods and services in a specific region or location.

[1422] "Understanding the surrounding supply situation in real time" means instantly checking the current inventory and availability of goods and services on-site.

[1423] "Analyzing data" means converting acquired data into a form that is easy to interpret as information through calculations and logical operations.

[1424] "Integration" means bringing together multiple pieces of data and information into one system or format.

[1425] "Point of supply" means the location where goods or services are stocked or provided.

[1426] This invention relates to a system that grasps the situation of people and goods flow in real time during a disaster and suggests optimal actions to users. In particular, this invention realizes efficient supply management in the event of a disaster by grasping the supply situation in real time using a smartphone and notifying users of the optimal supply location.

[1427] Explaining system program generation and processing

[1428] Device operation (smartphone):

[1429] 1. Using the smartphone's camera and GPS module, information on the supply status and location is acquired and converted into data.

[1430] 2. The digitized supply information is sent via the Internet to a server on the cloud.

[1431] Server behavior:

[1432] 3. The server receives, integrates, and analyzes data sent from multiple smartphones on the cloud.

[1433] 4. Based on the analyzed data, the supply situation is visualized on a map, and the AI ​​suggests optimal actions in response to user requests.

[1434] 5. The proposed action is notified to the user, and user feedback is collected and reflected in optimizing the supply destination and suggesting the next action.

[1435] Hardware and software used

[1436] Hardware:

[1437] Smartphone: A mobile phone with computing capabilities and internet connectivity (e.g., a typical smartphone).

[1438] Camera: Smartphone built-in camera (e.g. Sony IMX586)

[1439] GPS: Built-in smartphone GPS module

[1440] software:

[1441] Python: Programming Language

[1442] The Requests library: a Python library for HTTP requests

[1443] OpenCV: A library for image recognition

[1444] Cloud services: Cloud platforms for data collection and analysis (e.g., AWS, Google Cloud)

[1445] Specific Description of the Embodiments

[1446] For example, in the event of a natural disaster, this system can be used to instantly grasp the food and beverage supply situation in the affected area. Users take photos of nearby food and beverage inventory with their smartphone cameras, and obtain location information using GPS. This information is sent to a cloud server, which then integrates and analyzes the supply information obtained from multiple smartphones. As a result, users are notified of the optimal supply location. Furthermore, feedback from users can be collected and reflected in optimizing the next supply plan.

[1447] Example prompts to input to the generative AI model

[1448] Example of input prompt:

[1449] A natural disaster has occurred, and there is a shortage of bottled water in the affected areas. Design an application that uses a smartphone to monitor the surrounding supply situation in real time and suggest the best course of action to the user. The application uses a camera to check the water bottle stock, obtains location information using GPS, and sends it to a cloud server. The server analyzes the data and notifies the user of the best location for a supply.

[1450] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1451] Step 1:

[1452] The device (smartphone) uses a camera to capture images of the surrounding supply situation (e.g., water or food inventory). The captured image data is analyzed using image recognition software (e.g., OpenCV) pre-installed on the device and converted into data such as inventory type and quantity. The device also obtains its current location information from its built-in GPS and compiles this data into a single data packet.

[1453] Input: Smartphone camera image, GPS location information

[1454] Output: Item inventory data, location information data

[1455] Step 2:

[1456] The device sends the collected and analyzed data packets over the Internet to a cloud server, using an HTTP request to send the data and confirm that the communication was successful.

[1457] Input: inventory data, location data

[1458] Output: HTTP request sent to the cloud server

[1459] Step 3:

[1460] The server receives data packets sent from multiple smartphones in the cloud, and the received data is stored in a database system for immediate analysis.

[1461] Input: Data packets from multiple smartphones

[1462] Output: Analyzable dataset

[1463] Step 4:

[1464] The server analyzes the received data and processes it into a format suitable for supply status statistics and map displays, including data integration and aggregation, and prepares it for immediate response when a user requests it.

[1465] Input: Analyzable dataset

[1466] Output: Statistics and map display data

[1467] Step 5:

[1468] When a request is received from a user, the server uses AI to suggest the optimal action. For example, if a user requests "I want water," the server will check the current supply situation based on the analyzed data and identify the optimal supply location for the user.

[1469] Input: User requests, statistics and data for map display

[1470] Output: Optimal action suggestion data

[1471] Step 6:

[1472] The server then sends the optimal action suggestions to the user's smartphone as push notifications or in-app messages, ensuring that the user receives them immediately.

[1473] Input: Optimal action suggestion data

[1474] Output: User notification

[1475] Step 7:

[1476] The user receives the proposal from the server and initiates the actual action. After taking the action, the user sends the results of the action as feedback from the terminal to the server. This feedback is used for the next proposal and for optimizing the supply plan.

[1477] Input: Suggestions from the server, user behavior results

[1478] Output: feedback of the results of the action

[1479] Step 8:

[1480] The server aggregates feedback data from multiple users and uses it to optimize supply destinations and transportation plans. The optimized supply destinations and transportation plans are then sent to related terminals, resulting in more efficient supply of goods.

[1481] Input: User feedback

[1482] Output: Optimized destination and transport planning data

[1483] 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.

[1484] This invention is an advanced system that combines an emotion engine with a system that grasps the situation of people and goods flowing during a disaster in real time and suggests optimal actions to users. This system collects data using a multimodal camera, analyzes and visualizes the data on a cloud server, and further incorporates the user's emotional data to suggest optimal actions.

[1485] Specific explanation of the program's operation

[1486] Device behavior

[1487] 1. Data Acquisition:

[1488] The device (a multimodal camera) captures the flow of people and goods in real time. For example, the device captures the movements of people around an evacuation shelter and acquires the footage.

[1489] 2. Data conversion:

[1490] The captured video is analyzed within the device and converted into specific digital data. For example, the device may detect from the video that there are 200 500ml water bottles and digitize that information as "500ml water: 200 bottles."

[1491] 3. Emotion data acquisition:

[1492] The device's built-in emotion engine analyzes the user's facial expressions and tone of voice to collect emotional data. For example, the device analyzes the user's facial expressions to identify emotions such as "anxiety" or "impatience."

[1493] 4. Data transmission:

[1494] The converted data and emotion data are sent to a server on the cloud.

[1495] Server Operation

[1496] 5. Data Reception:

[1497] The server receives people flow and logistics data and user emotion data transmitted from multiple terminals.

[1498] 6. Data Integration:

[1499] The received data is integrated to grasp the overall situation. For example, the server combines data on supplies and people flow sent from each evacuation center with emotional data.

[1500] 7. Data Visualization:

[1501] The server visualizes the integrated data on a map and displays it in real time, allowing users to see the overall situation of people and goods flowing on a geographical map, and understand at a glance how much supplies are in which area and in which direction evacuees are moving.

[1502] 8. Receiving and parsing requests:

[1503] The server receives the user's request and begins analyzing it using AI. Emotional data is also incorporated into the analysis. For example, if a user requests "I want water" and the request is accompanied by emotional data such as "anxiety," that request will be given priority.

[1504] 9. Prioritization:

[1505] The AI ​​prioritizes requests based on the user's emotional data analyzed by the emotion engine. For example, it prioritizes requests from users who are highly "anxious" or "impatient."

[1506] 10. Submit a proposal:

[1507] Based on the analysis results, the server creates a suggestion for the user and sends that information to the user. For example, the server sends a suggestion to the user saying, "If you go to location A, there are 200 500ml bottles of water."

[1508] User Actions

[1509] 11. Start action:

[1510] The user receives a suggestion from the server and begins to act based on it. The user travels to the specified location and collects the necessary supplies.

[1511] 12. Send Feedback:

[1512] After taking an action, the user sends feedback from the device to the server. For example, the user reports, "I arrived at location A and received water."

[1513] Server supply optimization

[1514] 13. Request Collection:

[1515] The server aggregates feedback requests from multiple users, thereby understanding overall demand.

[1516] 14. Supply decisions:

[1517] The server uses the aggregated data to optimize the delivery of relief supplies, for example by identifying areas with high demand for water and creating an optimal supply plan.

[1518] 15. Transfer instructions:

[1519] The server instructs the relevant terminals on supply destinations and transport plans, for example, sending a command to the terminal to "transport 500 bottles of water from warehouse X to location Y."

[1520] Specific examples

[1521] For example, in the event of a natural disaster, this system can be used to grasp the status of supplies stored in warehouses in the affected area. If a user requests "water" and the emotion engine detects the user's "anxiety" or "impatience," the server will prioritize the request. The server will notify the user of the optimal warehouse and pickup location it suggests, allowing the user to accept the suggestion and receive the water.

[1522] In this way, the system of the present invention not only effectively manages the flow of people and goods during disasters, but also incorporates user emotion data to realize more accurate action suggestions and support.

[1523] The processing flow will be explained below.

[1524] Step 1:

[1525] The device uses a multimodal camera installed in the disaster area to capture the surrounding human and logistics flow in real time, for example, capturing the movements of people around evacuation shelters.

[1526] Step 2:

[1527] The device analyzes the captured video and converts it into specific digital data using image recognition technology. For example, the device may detect from the video that there are 200 500ml water bottles and digitize that information as "500ml water: 200 bottles."

[1528] Step 3:

[1529] The device's built-in emotion engine analyzes the user's facial expressions and tone of voice to collect emotional data. For example, the device analyzes the user's facial expressions to identify emotions such as "anxiety" or "impatience."

[1530] Step 4:

[1531] The devices then send the converted data and emotion data to a cloud server via the internet, allowing data from devices in various locations to be centrally managed.

[1532] Step 5:

[1533] The server receives data on people and goods flow and emotional data of users transmitted from multiple terminals, for example, data on supplies and emotional data transmitted from each evacuation shelter.

[1534] Step 6:

[1535] The server integrates the received data to grasp the overall situation, for example, by combining the supply data and emotion data for each evacuation shelter.

[1536] Step 7:

[1537] The server analyzes and visualizes the integrated data in real time, displaying the overall situation of people and goods flow on a geographical map, allowing users to see at a glance how much supplies are in which area and in which direction evacuees are moving.

[1538] Step 8:

[1539] Users access the cloud system from devices such as smartphones or tablets and send requests. For example, they can input a request such as "I want water" and send it to the server.

[1540] Step 9:

[1541] The server receives the user's request and begins analyzing it using AI. Emotional data is also incorporated into the analysis. For example, if a user requests "I want water" and the request is accompanied by emotional data such as "anxiety," that request will be processed with priority.

[1542] Step 10:

[1543] The server prioritizes requests based on emotional data, for example, prioritizing requests from users who are highly anxious or impatient.

[1544] Step 11:

[1545] The server creates a suggestion for the user based on the analysis results and sends that information to the user. For example, it might send a suggestion to the user saying, "If you go to location A, there are 200 500ml bottles of water."

[1546] Step 12:

[1547] The user receives a suggestion from the server and begins to act based on it, for example, by moving to a specified location and picking up the necessary supplies.

[1548] Step 13:

[1549] After taking an action, the user sends feedback from the device to the server, for example, reporting, "I arrived at location A and received water."

[1550] Step 14:

[1551] The server receives feedback from users and incorporates it into subsequent analysis, for example optimizing the delivery and transportation plans of relief supplies based on the aggregated feedback.

[1552] Step 15:

[1553] Based on the collected data, the server sends instructions to relevant terminals to supply relief supplies as needed, such as "Transport 500 bottles of water from Warehouse X to Location Y."

[1554] The above is a detailed description of the processing flow in the optimization system for people flow, logistics, and emotional data during disasters.

[1555] Example 2

[1556] 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."

[1557] In the event of a disaster, it is extremely important to grasp the situation of people and goods in real time and respond quickly and effectively. However, conventional systems do not adequately manage supplies or provide support to evacuees, and care is particularly lacking for users who are emotionally unstable. This leads to unclear priorities for support and makes it difficult to optimally allocate resources.

[1558] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for capturing and digitizing the flow of people and goods using a multimodal camera; means for analyzing a user's facial expression and tone of voice to acquire emotional data; means for transmitting the data and emotional data to a cloud server; means for aggregating and analyzing the received data and emotional data in the cloud server and visualizing them on a map; means for receiving requests from users, prioritizing the requests using AI, and proposing optimal actions; and means for transmitting the proposals to the users. This enables real-time management of supplies and evacuees during disasters, enabling prioritization taking into account the user's emotional state, and achieving optimal resource allocation and rapid response.

[1559] A "multimodal on-board camera" is a device equipped with multiple different sensors (e.g., visible light camera, infrared camera, depth sensor, etc.) to acquire complex environmental information.

[1560] "People flow" is a term that refers to the flow or movement of people moving through a specific area within a certain period of time.

[1561] "Logistics" is a term that refers to the overall flow and movement of goods and materials, including transportation, storage, and distribution.

[1562] "Emotion data" is data relating to the user's psychological state, obtained by analyzing information such as the user's facial expression and tone of voice.

[1563] "Cloud" is a term that refers to a system of computer resources and data storage that are remotely available over the Internet.

[1564] A "server" is a central computer system that provides data and services to other computers over a network.

[1565] "Digitization" is the act of converting physical or analog information into digital data so that it can be processed by a computer.

[1566] "Analysis" is the process of investigating and analyzing acquired data in detail to extract useful information.

[1567] "Visualization" is a method of displaying data visually in an easy-to-understand manner, and includes formats such as maps, graphs, and charts.

[1568] A "request" is a request from a user to the system for a specific operation or information provision.

[1569] "Priority" refers to the ordering used to determine which of multiple tasks or requests should be processed first.

[1570] "Action suggestions" are specific guidance or instructions that suggest optimal actions to the user based on the analysis results.

[1571] "Feedback" refers to response information provided by users to the system, and is used to improve services and as new information for decision-making.

[1572] This invention is an advanced system that grasps the situation of people and goods flow in real time during disasters and suggests optimal actions to users. This system is built by combining a multimodal camera, a cloud server, an AI model, and an emotion engine.

[1573] Device behavior

[1574] First, a multimodal camera is used to capture real-time images of people and goods flowing through the evacuation center. For example, it can capture footage of people's movements around an evacuation center. The captured footage is then analyzed within the device and converted into specific digital data. For example, AI image processing software can analyze the footage to detect that there are 200 500ml water bottles, digitizing this information as "500ml water: 200 bottles." Furthermore, the device's built-in emotion engine analyzes the user's facial expressions and tone of voice to collect emotional data. For example, it can analyze the user's facial expressions to identify emotions such as "anxiety" or "impatience." Finally, this data is sent to a cloud server.

[1575] Server Operation

[1576] The cloud-based server receives people and goods flow data sent from multiple devices, as well as user emotion data. This received data is integrated to grasp the overall situation. Specifically, it combines the emotion data with data on supplies and people flow sent from each evacuation shelter. The integrated data is then visualized on a map using a GIS (geographic information system). This allows the server to visually display the overall situation of people and goods flow on a geographical map, making it possible to see at a glance how many supplies are in which area and in which direction evacuees are moving.

[1577] The server then receives requests from users and begins analyzing them using an AI model. Emotional data is also incorporated into the analysis to determine the priority of user requests. For example, if a request for "water" is accompanied by emotional data such as "anxiety," that request will be processed with priority. Finally, based on the analysis results, a suggestion for the user's actions is created and sent to the user. For example, a suggestion such as "If you go to location A, there are 200 500ml bottles of water" is sent to the user.

[1578] User Actions

[1579] The user receives suggestions from the server and begins to act based on them. For example, they may move to a designated evacuation shelter or supply collection point and collect the necessary supplies. After taking action, they send feedback from their device to the server. For example, they may report, "I arrived at location A and received water."

[1580] Server supply optimization

[1581] The server aggregates requests fed back from multiple users and grasps overall demand. Based on the aggregated data, it optimizes the destination of relief supplies. For example, it identifies areas with high demand for water and creates a supply plan for those areas. It then instructs the relevant terminals on the supply destination and transportation plan. For example, it sends a command to the terminal saying, "Transport 500 bottles of water from warehouse X to location Y."

[1582] Specific examples

[1583] In the event of a natural disaster, this system can be used to grasp the status of supplies in the affected area. If a user sends a request saying "I want water," and the emotion engine detects the user's "anxiety" or "impatience," the server will prioritize the request. The server will notify the user of the optimal warehouse or pick-up location it suggests, and the user can accept the suggestion and receive the water.

[1584] In this way, the system of the present invention not only effectively manages the flow of people and goods during disasters, but also incorporates user emotion data to realize more accurate action suggestions and support.

[1585] Prompt Sentence Examples

[1586] Prompt to explain the system that suggests "optimal actions in the event of a disaster":

[1587] You are an evacuee in a disaster-hit area. You are currently in shelter C, but you are running low on water and food. Please tell us about your surroundings and how you are feeling. Based on that information, the AI ​​will suggest the best course of action for you.

[1588] As described above, in order to implement the present invention, by applying a multimodal camera, a cloud server, an AI model, and an emotion engine, it is possible to grasp the situation of people and goods flow during a disaster in real time and suggest optimal actions to the user.

[1589] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1590] Step 1: Data Acquisition

[1591] The device (a multimodal camera) captures real-time images of people and goods flowing through evacuation shelters and disaster sites, and acquires the video and audio data. The input is the video and audio captured by the camera, and the output is raw video and audio data. For example, it can capture the movement of people and the placement of supplies within an evacuation shelter.

[1592] Step 2: Data conversion

[1593] The device analyzes the captured video and audio data using AI image processing and audio analysis software. The input is raw video and audio data, and the output is specific digital data (e.g., "200 bottles of 500ml water" or "150 cans of food"). Specific operations include applying an image recognition algorithm to identify the type and quantity of supplies from the video.

[1594] Step 3: Acquire emotion data

[1595] The emotion engine installed in the device analyzes the user's facial expressions and tone of voice to collect emotional data. The input is data related to the user's face and tone of voice, and the output is emotional data (e.g., "anxiety," "impatience," etc.). Specific operations include analyzing the user's psychological state using facial expression recognition technology and voice analysis technology.

[1596] Step 4: Send data

[1597] The device transmits the converted material data and emotional data to a server on the cloud. The input is the digital data and emotional data analyzed and converted within the device, and the output is the data sent to the cloud server. The specific operation is to transmit the data via a wireless network.

[1598] Step 5: Receiving Data

[1599] The server receives people and logistics data, as well as emotion data, sent from multiple devices. The input is data from the devices, and the output is the received integrated data. Specifically, the server receives data using an API provided by the cloud platform.

[1600] Step 6: Data Integration

[1601] The server integrates the received data and grasps the overall situation. The input is the data received from each device, and the output is an integrated data set. Specific operations include the process of combining data from each evacuation shelter and the site into a single data set.

[1602] Step 7: Data visualization

[1603] The server visualizes the integrated data on a map in real time using a GIS (geographic information system). The input is the integrated data, and the output is a visualized geographic map. Specific operations include displaying the location of supplies and the movements of evacuees on the map.

[1604] Step 8: Receiving and Parsing the Request

[1605] The server receives requests from users and analyzes them using an AI model. It also incorporates emotional data into the analysis. The inputs are the user's request and emotional data, and the output is the analysis results. Specifically, it prioritizes requests based on the request content and the user's emotional state.

[1606] Step 9: Prioritize

[1607] The server determines the priority of requests based on the user's emotional data analyzed by the emotion engine. The input is the analysis result, and the output is a priority list. Specifically, requests from users who show high emotional levels, such as "anxiety" or "impatience," are prioritized.

[1608] Step 10: Submit your proposal

[1609] The server creates and sends a proposal to the user based on the analysis results. The input is the prioritized request and the analysis results, and the output is a proposal message. Specifically, it notifies the user that "If you go to location A, there are 200 500ml bottles of water."

[1610] Step 11: Take Action

[1611] The user receives a suggestion from the server and begins to act based on it. The input is a suggestion message from the server, and the output is the user's behavioral data. The specific action involves moving to a specified location and receiving the necessary supplies.

[1612] Step 12: Send feedback

[1613] After the user takes an action, they send feedback from their device to the server. The input is the user's reported data after the action, and the output is the feedback data sent to the server. A specific action is reported as "arrived at location A and received water."

[1614] Step 13: Request collection

[1615] The server aggregates feedback requests from multiple users. The input is feedback data from each user, and the output is aggregated request data. Specific operations include a process to understand how the overall demand is distributed.

[1616] Step 14: Supply Decision

[1617] The server optimizes the destinations of relief supplies based on the aggregated demand data. The input is the aggregated demand data, and the output is a supply plan. Specifically, it identifies the areas with the highest demand and formulates an appropriate supply plan.

[1618] Step 15: Transfer Instructions

[1619] The server instructs the relevant terminals on the supply destination and transfer plan. The input is the material supply plan, and the output is the transfer instruction. For example, an instruction to "transfer 500 bottles of water from warehouse X to location Y" is sent to the terminal. The specific operation is to send the transfer instruction to the relevant terminal and have it executed.

[1620] (Application example 2)

[1621] 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."

[1622] During disasters, it is difficult for victims and relief workers to receive supplies as quickly and efficiently as possible and ensure their safety. To improve convenience, it is necessary to determine priorities by taking into account not only people's movements and logistics situations, but also users' emotions. However, such an advanced system does not currently exist.

[1623] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for capturing and digitizing the situation of people and goods using a multimodal camera, means for transmitting the data to a cloud server, means for analyzing the user's facial expressions and tone of voice to collect emotional data, means for prioritizing requests using the collected emotional data and proposing optimal actions using AI, and means for transmitting the suggestions to the user. This makes it possible to grasp the situation of people and goods in real time even during a disaster and to propose optimal actions taking the user's emotions into consideration. It also makes it possible to provide relief supplies effectively and efficiently.

[1624] A "multimodal camera" is a camera that can simultaneously use multiple sensing methods, and is a device that can capture the flow of people and goods with high precision.

[1625] A "server on the cloud" is a remote server accessible via the Internet, and is a system that performs processes such as data storage, analysis, and integration.

[1626] "Analyzing the user's facial expressions and vocal tone" is a technology that quantifies the user's facial expressions and vocal tone to identify and evaluate their emotional state.

[1627] "Emotion data" is numerical or categorical data that indicates the emotional state of the user analyzed from facial expressions, tone of voice, and the like.

[1628] The "priority of a request" is the order of importance or urgency of a request to be executed among multiple user requests.

[1629] "Using AI to suggest optimal actions" refers to using artificial intelligence technology to analyze collected data and emotional data and recommend the most appropriate actions for the user.

[1630] "Understanding the situation of people and goods flow in real time" means instantly collecting and analyzing information on the movements and locations of people and goods at the current time.

[1631] "Providing relief supplies effectively and efficiently" means providing relief supplies to users who need them with the greatest effect and with the least amount of effort and time.

[1632] The present invention is a system that grasps the situation of people and goods flowing during a disaster in real time, incorporates user emotion data, and then suggests optimal actions. Below, we will explain in detail how to build and operate this system.

[1633] Hardware and software used

[1634] To realize the system of the present invention, the following main hardware and software are required.

[1635] Multimodal mounted camera: A device that captures people and logistics flows with high precision.

[1636] Cloud server: A remote server accessible via the Internet that stores, analyzes, integrates, and processes data.

[1637] Emotion engine: Software that recognizes the user's facial expressions and analyzes their voice to collect emotional data.

[1638] AI engine: An artificial intelligence technology that comprehensively analyzes collected data and emotional data to generate optimal action suggestions.

[1639] System operation details

[1640] 1. Data Acquisition:

[1641] The multimodal camera installed on the device captures real-time images of people and goods flowing through the evacuation center. For example, it can collect information on the movements of people and the location of supplies around evacuation centers. This data is then sent to a cloud server.

[1642] 2. Emotion data acquisition:

[1643] The emotion engine analyzes the user's facial expressions and tone of voice to collect emotional data, which can then be used to identify specific emotions such as "anxiety" or "impatience." This data is also sent to a cloud server.

[1644] 3. Data analysis and visualization:

[1645] The server analyzes the received data and grasps the overall situation, which is then visualized on a map, allowing users to see at a glance how many supplies are in which area and in which direction evacuees are moving.

[1646] 4. AI-powered recommendations for optimal actions:

[1647] The AI ​​engine generates optimal action suggestions based on collected people flow data, logistics data, and emotional data. If the emotional data indicates a high level of stress, such as anxiety or impatience, the request will be prioritized and immediate assistance will be provided to the user.

[1648] 5. Notification of Proposal:

[1649] The server generates suggestions and sends them to the user's smartphone or other device. For example, a specific suggestion such as "If you go to location A, there are 200 500ml bottles of water."

[1650] 6. Actions and Feedback:

[1651] The user then takes action based on the suggestions and later sends feedback from the device to the server, which then uses this feedback to optimize the delivery of relief supplies.

[1652] Specific examples

[1653] For example, if this system is used in an evacuation shelter where many evacuees gather after an earthquake, the following will happen: A multimodal camera captures the movements of people around the shelter, and an emotion engine detects the evacuees' anxiety. The cloud server integrates the data and suggests optimal actions (for example, moving supplies to a specific location). This allows relief supplies to be delivered quickly and efficiently.

[1654] Prompt Sentence Examples

[1655] "Create a program that identifies areas where food is scarce after an earthquake in real time and suggests optimal delivery routes. Prioritize based on user sentiment data. Use Python."

[1656] The above is the "mode for carrying out the invention" of the present invention. By constructing a system based on this mode, effective support in the event of a disaster can be achieved.

[1657] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1658] Step 1:

[1659] The device uses a multimodal camera to capture images of people and goods flowing through the device. The camera acquires video data in real time and captures it within the device. The input is the movement of people and objects, and the output is video data capturing these movements.

[1660] Step 2:

[1661] The device analyzes the acquired video data and converts it into specific digital data. For example, it identifies the type and quantity of supplies from the video data and organizes that information as digital data (e.g., 200 500ml bottles of water). The input is video data, and the output is analyzed digital data.

[1662] Step 3:

[1663] The device uses an emotion engine to analyze the user's facial expressions and tone of voice to collect emotional data. The emotional data includes specific emotional states such as "anxiety" and "impatience." The input is the user's facial expressions and voice, and the output is emotional data.

[1664] Step 4:

[1665] The device sends digital data and emotional data to a cloud server, which then centrally manages the collected data. The input is the analyzed digital data and emotional data, and the output is the data sent to the cloud server.

[1666] Step 5:

[1667] The server receives the data sent from the devices and integrates it to understand the overall situation. Based on this series of data, the server analyzes the overall picture of people and goods flow and visualizes the data on a single map. The input is the received data, and the output is the integrated and visualized data.

[1668] Step 6:

[1669] The server receives requests from users and analyzes them using AI. At the same time, it also incorporates user emotional data into the analysis and determines the priority of requests. The input is the user request and emotional data, and the output is a prioritized request.

[1670] Step 7:

[1671] The server then creates optimal action suggestions based on the results of the AI ​​analysis. These suggestions are derived by taking into account the user's request content and emotional data. The input is a prioritized request and the analysis results, and the output is a specific action suggestion.

[1672] Step 8:

[1673] The server sends the generated action suggestions to the user, allowing the user to receive information for deciding their next action. The input is the action suggestions, and the output is notification data for the user.

[1674] Step 9:

[1675] The user receives a suggestion from the server and starts to act based on it. For example, the user moves to a suggested location and picks up the necessary supplies. The input is notification data from the server, and the output is the user's action.

[1676] Step 10:

[1677] After taking an action, the user sends feedback from their device to the server. This feedback information is also managed by the server and used as information for future decisions. The input is the result of the user's action, and the output is feedback data sent to the server.

[1678] The above is a series of processing steps for realizing the system of the present invention, which makes it possible to grasp the situation of people and goods flowing in real time even during a disaster and to propose optimal actions that take the user's emotions into consideration.

[1679] 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.

[1680] 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.

[1681] 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.

[1682] 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.

[1683] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1684] 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.

[1685] 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).

[1686] 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.

[1687] 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."

[1688] 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.

[1689] 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).

[1690] 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.

[1691] 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.

[1692] 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.

[1693] 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.

[1694] 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.

[1695] 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.

[1696] 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.

[1697] 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.

[1698] 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.

[1699] 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.

[1700] The following is further disclosed regarding the above embodiment.

[1701] (Claim 1)

[1702] A system for understanding the situation of people and goods flow in real time during a disaster,

[1703] A means of capturing and digitizing the flow of people and goods using a multimodal camera;

[1704] means for transmitting the data to a server on the cloud;

[1705] A means to aggregate and analyze the received data on a cloud server and visualize it on a map.

[1706] A means of receiving requests from users and using AI to suggest optimal actions,

[1707] means for transmitting the suggestions to a user;

[1708] A system including:

[1709] (Claim 2)

[1710] 2. The system according to claim 1, further comprising means for transmitting feedback from users to a server on the cloud, and optimizing destinations for supplying relief supplies based on the feedback received by the server on the cloud.

[1711] (Claim 3)

[1712] 2. The system according to claim 1, wherein the server on the cloud further comprises means for transmitting instructions for transporting relief supplies to related terminals based on the aggregated requests of users.

[1713] "Example 1"

[1714] (Claim 1)

[1715] A means of capturing and digitizing the flow of people and goods using a multimodal camera;

[1716] means for transmitting the data to a server on the cloud;

[1717] A means of aggregating the data received on a cloud server and understanding the overall situation,

[1718] a means for visualizing the received data on a map;

[1719] A means of receiving requests from users and analyzing the optimal course of action using AI;

[1720] means for transmitting the analysis results to a user;

[1721] A system including:

[1722] (Claim 2)

[1723] 2. The system according to claim 1, further comprising means for transmitting feedback from users to a server on the cloud, and optimizing destinations for supplying relief supplies based on the feedback received by the server on the cloud.

[1724] (Claim 3)

[1725] 2. The system according to claim 1, wherein the server on the cloud further comprises means for transmitting instructions for transporting relief supplies to related terminals based on the aggregated requests of users.

[1726] "Application Example 1"

[1727] (Claim 1)

[1728] A system for understanding the situation of people and goods flow in real time during a disaster,

[1729] A means of capturing and digitizing the flow of people and goods using a multimodal camera;

[1730] means for transmitting the data to a server on the cloud;

[1731] A means to aggregate and analyze the received data on a cloud server and visualize it on a map.

[1732] A means of receiving requests from users and using AI to suggest optimal actions,

[1733] means for transmitting the suggestions to a user;

[1734] A method for grasping the surrounding supply situation in real time using a smartphone, analyzing the acquired data, and sending it to a server on the cloud.

[1735] A cloud server integrates data sent from multiple smartphones and notifies users of the optimal supply location;

[1736] A system including:

[1737] (Claim 2)

[1738] 2. The system according to claim 1, further comprising means for transmitting feedback from users to a server on the cloud, and optimizing destinations for supplying relief supplies based on the feedback received by the server on the cloud.

[1739] (Claim 3)

[1740] 2. The system according to claim 1, wherein the server on the cloud further comprises means for transmitting instructions for transporting relief supplies to related terminals based on the aggregated requests of users.

[1741] "Example 2: Combining Emotion Engines"

[1742] (Claim 1)

[1743] A means of capturing and digitizing the flow of people and goods using a multimodal camera;

[1744] A means for analyzing a user's facial expression and tone of voice to acquire emotional data;

[1745] means for transmitting the data and emotion data to a server on the cloud;

[1746] A cloud server aggregates and analyzes the received data and emotion data, and visualizes them on a map.

[1747] A means to receive requests from users, prioritize them using AI, and suggest the best course of action;

[1748] means for transmitting the suggestions to a user;

[1749] A system including:

[1750] (Claim 2)

[1751] 2. The system according to claim 1, further comprising means for transmitting feedback from users to a server on the cloud and optimizing destinations for supplying relief supplies based on the feedback received by the server on the cloud.

[1752] (Claim 3)

[1753] 2. The system according to claim 1, wherein the server on the cloud further comprises means for transmitting instructions for transporting relief supplies to associated terminals based on the aggregated user requests and emotion data.

[1754] "Application example 2 when combining emotion engines"

[1755] (Claim 1)

[1756] A system for understanding the situation of people and goods flow in real time during a disaster,

[1757] A means of capturing and digitizing the flow of people and goods using a multimodal camera;

[1758] means for transmitting the data to a server on the cloud;

[1759] A means to aggregate and analyze the received data on a cloud server and visualize it on a map.

[1760] A means for collecting emotional data by analyzing the user's facial expressions and tone of voice;

[1761] A method to prioritize requests using collected emotional data and suggest optimal actions using AI.

[1762] means for transmitting the suggestions to a user;

[1763] A system including:

[1764] (Claim 2)

[1765] 2. The system according to claim 1, further comprising means for transmitting feedback from users to a server on the cloud, and optimizing destinations for supplying relief supplies based on the feedback received by the server on the cloud.

[1766] (Claim 3)

[1767] 2. The system according to claim 1, wherein the server on the cloud further comprises means for transmitting instructions for transporting relief supplies to related terminals based on the aggregated requests of users. [Explanation of symbols]

[1768] 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 system for understanding the situation of people and goods flow in real time during a disaster, A means for capturing and digitizing the situation of people and goods flow using a multimodal mounted camera; means for transmitting the data to a server on the cloud; A means to aggregate and analyze the received data on a cloud server and visualize it on a map. A means of receiving requests from users and using AI to suggest optimal actions, means for transmitting the suggestions to a user; A system including:

2. The system according to claim 1 , further comprising means for transmitting feedback from users to a server on the cloud and optimizing destinations for supplying relief supplies based on the feedback received by the server on the cloud.

3. The system according to claim 1 , further comprising means for transmitting instructions for transporting relief supplies to related terminals based on the aggregated requests of users, in the server on the cloud.

Images