system

Abstract

We provide the system. [Solution] A means of receiving data from users who input disaster information using a communication terminal, A means for automatically acquiring geographic information contained in the data, A means for inputting received data into a generating artificial intelligence model and evaluating the reliability of that information, A means of determining whether information is false based on evaluation, Means for providing the information to the appropriate organization according to the reliability of the information, A disaster information analysis system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the event of a disaster, accurate and rapid information transmission is required. However, the information flowing through modern communication networks contains a lot of false and incorrect information. The spread of such information may cause confusion in rescue operations, resulting in waste of human resources and delays in rescue. To address this issue, a mechanism is required to enhance the reliability of disaster information and enable prompt and accurate responses.

Means for Solving the Problems

[0005] This invention provides a system for receiving disaster information entered by users using a communication terminal and for evaluating the information by combining it with geographic information contained therein. This system includes means for inputting the received information into a generating artificial intelligence model and evaluating its reliability. Furthermore, it automatically determines whether the information is false based on the evaluation results and provides only highly reliable information to the appropriate organizations, thereby improving the efficiency of rescue and response during disasters.

[0006] "Communication terminal" refers to a device used by users to input disaster information, and includes smartphones, tablets, and other similar devices.

[0007] "Users" refers to individuals or organizations that use communication terminals to input disaster information and transmit data to the system.

[0008] "Data" refers to a series of pieces of information, such as text information and location information, that are sent from a communication terminal to a server.

[0009] "Geographic information" refers to data that indicates the user's current physical location, and includes real-time location tracking and GPS data.

[0010] A "generative artificial intelligence model" refers to a computer program that utilizes machine learning and AI technologies to analyze received disaster information and evaluate its reliability.

[0011] "Reliability" refers to the accuracy and validity of information when determining whether received information is false or not.

[0012] "Responsible organizations" refer to organizations and groups responsible for taking concrete actions upon receiving disaster information, and include fire departments, police, and ambulance services. [Brief explanation of the drawing]

[0013] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] Shows an emotion map to which multiple emotions are mapped. [Figure 10] Shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Mode for Carrying Out the Invention

[0014] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0017] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0019] In the following embodiments, the numbered communication I / F (Interface) is an interface that includes a communication processor and 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), or Bluetooth (registered trademark), and the like.

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] As shown in Figure 1, the 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.

[0024] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0027] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0034] This invention provides a specific model for implementing a system that efficiently analyzes information received during a disaster and provides only reliable information to the response organization. First, the user inputs disaster information using a communication terminal. At this time, the terminal automatically acquires geographical information and sends it to the server along with the information entered by the user. The server verifies and formats this received data and prepares it for storage.

[0035] Next, the server inputs the formatted information into an artificial intelligence (AI) model to evaluate the reliability of the information. This AI model analyzes the linguistic patterns contained in the disaster information text and its degree of relevance to the situation. For location information, the credibility of the report can be verified by comparing it with existing geographic information systems (GIS) and disaster data.

[0036] For example, if a user reports that their home is flooded, the location information obtained from the device is compared with rainfall data for that area on the server. This allows the AI ​​to assist in determining if a flood report is suspicious even though there is no record of rainfall.

[0037] If the evaluation determines that the information is reliable, the server automatically transmits the information to the appropriate agency. This enables an accurate and prompt response. If the information is determined to be highly likely to be false, a warning is sent to the administrator, and further verification and auditing are conducted.

[0038] The usefulness of this system lies in selecting reliable information from a vast amount of data and optimally allocating limited resources. This method is expected to improve the effectiveness and speed of disaster response.

[0039] The following describes the processing flow.

[0040] Step 1:

[0041] The user uses a communication terminal to input and send disaster information in text format. Based on the user's permission, the terminal automatically acquires geographical information and prepares to send this information along with the text to the server.

[0042] Step 2:

[0043] The terminal sends the entered information and any added geographical information to the server. The server verifies the format of the incoming data and checks for syntax errors or incomplete data.

[0044] Step 3:

[0045] The server decodes the received information as needed and formats it into a meaningful form as disaster information. This process includes appropriately identifying location information and text data.

[0046] Step 4:

[0047] The server transfers the formatted information to an artificial intelligence model. The AI ​​model analyzes the text data and evaluates its reliability by comparing it to language patterns and common disaster report formats.

[0048] Step 5:

[0049] The server analyzes location data in conjunction with a Geographic Information System (GIS) to verify whether the reported location was actually affected by the disaster. This step is performed in conjunction with an external disaster database.

[0050] Step 6:

[0051] The server calculates a reliability score for the information based on the evaluation results of the AI ​​model. This score assesses the likelihood that the information is true.

[0052] Step 7:

[0053] The server determines how to process information based on its reliability score. Information with a high score is sent to the appropriate agency, while information with a low score will issue a warning to the administrator and request further verification.

[0054] Step 8:

[0055] Information transmitted from the server is quickly processed by the responding agency, and necessary rescue operations and information sharing are initiated.

[0056] (Example 1)

[0057] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0058] During a disaster, it is crucial to quickly and accurately select reliable information from a vast amount of data and provide it to the appropriate response agencies. Furthermore, identifying false information and taking appropriate countermeasures is also essential. Under these circumstances, the current system faces the challenge of slow response due to the time required for information verification and processing.

[0059] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0060] In this invention, the server includes means for receiving, formatting, and correcting data; means for inputting the formatted data into a generating artificial intelligence model to evaluate its reliability; and means for automatically providing information to the responding agency based on the evaluation results. This enables the rapid and accurate sorting and automatic provision of disaster information to the responding agency.

[0061] A "communication terminal" is a device used by users to input disaster information and is equipped with a function that enables the automatic acquisition of geographical information.

[0062] "Geographic information" refers to data used to identify the location from which the information was provided, and is usually expressed in the form of latitude and longitude.

[0063] A "generative artificial intelligence model" is an algorithm or program used to analyze text data of disaster information and evaluate its reliability.

[0064] "Means for evaluating reliability" refers to processing methods that analyze received data and determine whether the information is accurate and true.

[0065] A "response agency" refers to an organization or department that takes necessary action after receiving disaster information, and begins its activities based on the information provided.

[0066] This invention relates to a system for efficiently analyzing and evaluating the reliability of information during disasters. This system is constructed using a communication terminal, a server, and a generative artificial intelligence model.

[0067] Users input disaster information using a communication terminal. The terminal automatically obtains the user's location information using its built-in GPS function and sends that information to the server. Specifically, for example, a user might input information such as "There is a fire in the neighborhood" and send it to the server along with their location information.

[0068] The server formats the received information and corrects any errors. The formatted information is then input into a generating AI model. This AI model utilizes natural language processing technology to analyze language patterns in the input text and evaluate the reliability of the disaster information. Furthermore, location information is verified for report validity by comparing it with existing geographic and disaster data using a GIS (Geographic Information System).

[0069] For example, if a report states that "the river is overflowing," the AI ​​model evaluates its reliability based on keywords such as "river" and "flooding," and verifies it by referring to location information and the flood history of that area.

[0070] An example of a prompt message to ensure the operation of this system is as follows: "User report: A fire has broken out in the neighborhood. Location: Latitude 35.6895, Longitude 139.6917. Please evaluate the reliability of this information."

[0071] This allows the server to automatically provide information deemed highly reliable to the response agency, enabling a rapid disaster response based on that information. If the information is determined to be potentially false, the server will issue a warning to the administrator, allowing for further verification procedures. In this way, the present invention aims to improve the efficiency and accuracy of disaster response.

[0072] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0073] Step 1:

[0074] The user inputs disaster information using a communication terminal. This input consists of text information related to the disaster. The terminal automatically acquires location information using its built-in GPS function and sends this location information to the server along with the input text. At this stage, the input information consists of the disaster report content and location data. The output is the transmission of information to the server. For example, if the user inputs "There is a fire," the terminal checks its current location and sends the data to the server.

[0075] Step 2:

[0076] The server receives the data. The received information is formatted, and any errors are corrected. For example, the date and time format is standardized, and the accuracy of location information is verified. The input is disaster information and location information sent from the terminal, and the output is data formatted in a standardized format. Specifically, the server converts the date and time to the format "2023-05-15T10:00:00" and re-verifies the location information.

[0077] Step 3:

[0078] The server inputs formatted data into a generating AI model. This model analyzes the language patterns of the input disaster information text and evaluates the reliability of the information. Location information is cross-referenced with a geographic information system to verify its authenticity. The input is formatted disaster report data, and the output is a reliability evaluation score or judgment result. Specifically, the AI ​​detects the language patterns of "fire" and "occurrence," and cross-references the location information with past fire data.

[0079] Step 4:

[0080] The server determines the reliability of the information based on the evaluation results from the generated AI model. If the information is deemed highly reliable, the server automatically provides it to the appropriate agency. If the information is deemed unreliable, it issues a warning to the administrator and initiates further verification procedures. The input is the result of the AI ​​model's reliability evaluation, and the output is the provision of information to the appropriate agency or a warning to the administrator. Specifically, highly reliable information is reported as "Reliability: High" and sent to the appropriate agency, or the administrator is notified as "Warning: Low Reliability."

[0081] (Application Example 1)

[0082] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0083] During a disaster, a large amount of information flows in, but it is difficult to quickly select reliable information from among it. This makes it difficult for response agencies to take immediate and appropriate action, potentially leading to an escalation of damage. To solve this problem, a system is needed that automatically evaluates the reliability of information and promptly notifies only those that are certain.

[0084] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0085] In this invention, the server includes means for receiving data from users who input disaster information using a communication device, means for automatically acquiring location information contained in the data, means for inputting the received data into an artificial intelligence model that generates data and evaluating the reliability of the information, means for determining whether the information is false based on the evaluation, means for providing the information to a response agency according to the reliability of the information, and means for automatically notifying a safety agency based on the reliability of the evaluated information. This makes it possible to appropriately and quickly notify response agencies of reliable disaster information from a vast amount of data.

[0086] A "communication device" is an electronic device used by users to input disaster information and enables the transmission and reception of data.

[0087] "Location information" refers to information used to identify the geographical location included in the data entered by the user, and is automatically acquired using technologies such as GPS.

[0088] An "artificial intelligence model" is a machine learning algorithm or data analysis tool used to analyze received data and evaluate the reliability of that information.

[0089] "Evaluation" is a process for determining the accuracy and reliability of received disaster information, thereby determining whether the information is true or false.

[0090] A "response organization" is an organization or agency that receives information in order to take appropriate action based on disaster information, and is primarily responsible for ensuring safety and mitigating damage.

[0091] A "safety agency" is an organization responsible for taking swift action to protect human lives and property during a disaster.

[0092] The system for realizing this invention consists of multiple communication devices, a server, and an artificial intelligence model to be generated. First, the user inputs disaster information into the communication device. This device is equipped with a location information acquisition function and can automatically acquire accurate geographic information using technologies such as GPS. The acquired disaster information and location information are transmitted to the server via the network.

[0093] The server stores the received data and uses pre-trained generative AI models, such as natural language processing toolkits and machine learning algorithms, to evaluate the reliability of the information. In this evaluation process, the content and location of the information are compared with historical disaster data. Specifically, the server uses GIS to match location data with existing disaster data and verify the degree of consistency of the reported information. Information deemed to have a low probability of being false is promptly provided to the response agency. On the other hand, information that is highly likely to be false undergoes further verification.

[0094] For example, if a user reports that "flooding is occurring at my current location," the system checks for recent weather data to see if there are any records of precipitation. If the weather records do not indicate a possibility of flooding, the AI ​​will deem the report questionable. At the same time, if the information is deemed reliable, safety notices are sent to relevant agencies to quickly take measures to minimize damage.

[0095] An example of a prompt message to input into the generating AI model is: "Evaluate the flood occurrence reported by the user, determine its reliability, and notify the result." This allows the system to receive specific instructions to make appropriate decisions.

[0096] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0097] Step 1:

[0098] On the terminal, the user inputs disaster information. The user reports specific disaster conditions (e.g., flood, earthquake) in text format, and the terminal automatically obtains the current location information using its GPS function. Both the input information and the location information are sent to the server. The input consists of text and location data, and the output is the data sent to the server.

[0099] Step 2:

[0100] The server first performs an initial filter on the received information. Specifically, it checks for abnormal strings and missing location information. An automated script is used for this, removing unformatted data and passing the formatted data to the generating AI model. The input is raw data from the user, and the output is formatted data that fits the AI ​​model.

[0101] Step 3:

[0102] A generative AI model is launched on the server and analyzes the formatted data. The AI ​​compares it with past disaster report data and evaluates the language patterns and degree of similarity of the report content. Furthermore, it guides the evaluation process using prompt sentences. The input is the formatted data, and the output is the reliability assessment result.

[0103] Step 4:

[0104] The server uses GIS to verify location information. It examines the credibility of reported conditions by comparing them with local weather data and disaster history. For example, reported floods are evaluated by directly comparing them with precipitation records. Input is location data, and output is the location verification result.

[0105] Step 5:

[0106] The server integrates information obtained from AI models and GIS to determine the final reliability of the information. If the reliability is high, it prepares to notify the relevant authorities. The notification includes the generated reliability assessment along with instructions on necessary actions. The input is the evaluation results from AI and GIS, and the output is the notification data.

[0107] Step 6:

[0108] The server notifies the response agency of reliable information. The notification system is automated and delivers information via multiple channels (e.g., SMS, email). This enables a rapid response. The input is the notification data, and the output is the delivered notification.

[0109] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0110] This invention describes an embodiment of a disaster information analysis system that incorporates an emotion engine to recognize user emotions when analyzing disaster information entered using a communication terminal. This system begins by automatically acquiring disaster information and related geographical information entered by the user into the terminal and transmitting that data to a server.

[0111] The server uses a generative artificial intelligence (AI) model to evaluate the reliability of the received data. This AI model analyzes text data, examining its linguistic patterns and format to determine its reliability. In addition, an emotion engine detects emotions from the text data entered by the user. This emotion data is used to evaluate the reliability of the information. For example, content entered in a panicked state may be weighted differently from content entered calmly.

[0112] For example, if a user types "Help! My house is flooding," the device sends the message to the server along with its current geographical location. The server's AI evaluates this text from a credibility standpoint, while simultaneously, an emotion engine measures the user's level of urgency. Information deemed highly urgent based on the user's emotion recognition is then evaluated considering this tendency and reflected in the prioritization of response agencies.

[0113] Based on the reliability of the information and the results of sentiment analysis, the server notifies the appropriate agency of the most reliable information. Considering sentiment data also enables the rapid transmission of highly urgent cases to the appropriate agency. This system configuration allows for multifaceted information evaluation, including sentiment analysis, and supports appropriate responses during disasters.

[0114] The following describes the processing flow.

[0115] Step 1:

[0116] The user uses a communication terminal to input and transmit disaster information in text format. The terminal automatically retrieves geographical information about the user's current location and prepares to package it together with the text information.

[0117] Step 2:

[0118] The terminal sends a prepared information package to the server. The server receives the incoming data, verifies its format, and determines whether it can be processed appropriately.

[0119] Step 3:

[0120] The server separates the received data into text information and geographic information. This data is then formatted for analysis by generative artificial intelligence models and sentiment engines.

[0121] Step 4:

[0122] The server inputs text information into an artificial intelligence model that generates text data, analyzes the language patterns of the disaster information, and evaluates its reliability. The AI ​​model measures the accuracy of the information based on the content, wording, and format of the report.

[0123] Step 5:

[0124] In parallel, the server sends text information to the sentiment engine to recognize the user's emotional state. This analysis is based on the tone of the text and words indicating urgency.

[0125] Step 6:

[0126] The server combines reliability assessments obtained from AI models with sentiment data from an emotion engine to calculate an overall information reliability score. The score reflects the truthfulness and urgency of the information.

[0127] Step 7:

[0128] The server decides how to process information based on the calculated reliability score. Information with a high score is quickly provided to the appropriate agency, while information with a low score sends a warning to the administrator for further verification.

[0129] Step 8:

[0130] Responding agencies will take swift action based on reliable information transmitted from the server and prepare to deploy relief operations if necessary. Urgency based on emotional data will also be considered, enabling effective decision-making.

[0131] (Example 2)

[0132] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0133] In collecting and analyzing disaster information, verifying the accuracy of the information and assessing its urgency based on users' emotions are crucial. However, conventional technologies lack mechanisms to integrate and utilize information reliability assessment and user sentiment analysis, which can make rapid and accurate responses difficult. To address this challenge, there is a need to provide an analysis method that simultaneously considers information reliability and users' emotional states.

[0134] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0135] In this invention, the server includes means for receiving data from users who input information using a communication device, means for automatically acquiring location information contained in the data, means for inputting the received data into a machine learning model to evaluate the reliability of the information, means for applying emotion recognition technology to the information to determine the user's emotional state, and means for classifying and providing information based on reliability and emotion analysis. This makes it possible to integrate and utilize information reliability evaluation and emotion analysis, enabling quick and appropriate responses.

[0136] A "communication device" is an electronic device used to send and receive information, and in particular refers to a terminal that allows users to input information and enables data communication.

[0137] "Location information" refers to data that indicates a geographical location, and usually includes coordinate information such as latitude and longitude.

[0138] A "machine learning model" refers to an algorithm or system that allows a computer to learn patterns from large amounts of data and then make predictions or classifications on new data.

[0139] "Information reliability" refers to the criteria used to evaluate whether the information provided is accurate and true.

[0140] "Emotion recognition technology" refers to technology that identifies a person's emotions from data such as text, audio, and images, and clarifies their emotional state.

[0141] "User's emotional state" refers to the mental state a user exhibits when entering information, such as whether they are feeling a sense of urgency or remaining calm.

[0142] "Means of classification and provision" refers to the function or method of classifying evaluated information based on specific criteria and providing it appropriately to the necessary institutions and systems.

[0143] The system in this invention consists of three components: a user, a terminal, and a server. First, the user inputs information related to the disaster using a communication device, such as a smartphone or tablet device. The input information is primarily text-based, but may also include images and audio data in some cases.

[0144] The device automatically acquires location information using its built-in GPS function, along with the entered information. This location information is transmitted to the server via a communication protocol. Specifically, location information is acquired using the Google® Maps API, and the data is sent to the server via HTTPS communication.

[0145] The server analyzes the received data using a generating artificial intelligence model. This model utilizes natural language processing technologies, such as OpenAI® models, to scrutinize the input text information and evaluate its reliability. Furthermore, sentiment recognition technology is applied to the received text data, and tools like IBM Watson® are used to determine the user's emotional state. This sentiment analysis helps understand the user's sense of urgency and reflects this in the weighting of the information.

[0146] For example, if a user types "Help! My house is flooded," this information and its location data are sent to the server. The server uses an AI model to evaluate the reliability of the text content and an emotion engine to analyze its urgency. As a result, the information is classified as urgent and notified to the appropriate authorities.

[0147] In this system embodiment, an example of a prompt message is used: "My home has been flooded due to heavy rain last night. Please take immediate action." By inputting such a prompt message into the AI ​​model and analyzing the reliability of the information and the emotional state, a rapid response becomes possible.

[0148] This method aims to enable accurate and rapid processing of disaster information, thereby improving the efficiency of responses in emergencies.

[0149] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0150] Step 1:

[0151] Users input disaster information using communication devices. Specifically, they write text messages via smartphone apps or web interfaces, attaching media such as images and audio as needed. The information entered at this stage consists of details of the disaster situation as observed by the user.

[0152] Step 2:

[0153] The device acquires location information along with the information entered by the user. Location information is obtained using the device's built-in GPS function or location services, and the current location is determined using tools such as the Google Maps API. The acquired geographic information and user input information are combined to create a dataset. This dataset becomes the data sent to the server.

[0154] Step 3:

[0155] The device sends the generated dataset to the server. The HTTPS protocol is used for transmission, ensuring secure and rapid data transfer. The transmitted data consists of user text information, location information, and metadata.

[0156] Step 4:

[0157] The server analyzes the received dataset. First, it uses a generative AI model to analyze the text information and evaluate its reliability. The AI ​​model uses natural language processing techniques to analyze text patterns and distinguish meaningful information from noise. The reliability evaluation results are then output.

[0158] Step 5:

[0159] The server applies sentiment recognition technology to the received text information. The sentiment engine analyzes the text content and identifies the user's emotional state—for example, urgency or fear. The output of the sentiment analysis serves as supplementary data that influences the reliability evaluation.

[0160] Step 6:

[0161] The server classifies information based on the output of reliability assessments and sentiment analysis. Based on the analysis results, it prioritizes the information and generates notification data for the appropriate response agency. This classification process ensures that important information is processed more quickly and appropriately.

[0162] Step 7:

[0163] The generated notification data is sent from the server to the appropriate agency. High-priority information is automatically notified to the emergency response department, enabling immediate action. The output data includes details and suggestions to identify necessary actions.

[0164] (Application Example 2)

[0165] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0166] Conventional disaster information systems had limitations in judging the accuracy of received information, particularly in their inability to consider the emotions of the information senders, and thus in their inability to accurately assess the urgency of the information. Furthermore, there were challenges in detecting false information and rapidly disseminating highly urgent information.

[0167] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0168] In this invention, the server includes means for receiving data from a user who inputs emergency information using a communication device, means for automatically acquiring location information contained in the data, means for inputting the received data into a generating artificial intelligence model to evaluate the accuracy of the information, means for detecting emotions from the user's input data using an emotion analysis engine, and means for providing the information to relevant organizations according to the accuracy of the information and the emotion data. By combining the accuracy of the information with the user's emotion information, it becomes possible to determine false information and provide information quickly based on priority.

[0169] "Communication equipment" is a general term for hardware and software that directly receives emergency information from users and processes the data.

[0170] "Location information" refers to geographical data about the location where the user entered emergency information, and is usually obtained through GPS or geographic information systems.

[0171] A "generative artificial intelligence model" refers to a collection of algorithms and software that use natural language processing and machine learning to evaluate data in order to determine the accuracy of received information.

[0172] An "emotion analysis engine" is an analytical technology that detects emotions from the user's input data and outputs the results as numerical values ​​or categories.

[0173] "Providing to relevant organizations" refers to the operation or process of transmitting the analyzed information to various relevant agencies and organizations at the appropriate time.

[0174] To implement this invention, a system is constructed that allows users to input emergency information using a communication terminal. This system includes a process for rapidly analyzing the received data and providing the information to relevant organizations as needed.

[0175] The server receives data entered by the user from their communication terminal and automatically acquires location information. This allows for understanding the geographical context of the location where the emergency occurred.

[0176] The received data is evaluated for accuracy using a generative artificial intelligence model. The AI ​​model uses natural language processing technology to analyze the content of the information and determine its reliability.

[0177] Furthermore, an emotion analysis engine detects emotions from the user's input data. This engine numerically or categorically evaluates the emotional nuances of the input text and voice data, and uses the results to assess urgency.

[0178] Considering the accuracy of the information and the detected sentiment data, the server provides the information to the relevant organizations. This allows for priority responses based on the urgency of the information.

[0179] For example, if a user voice-inputs "There is a fire. Please help," the server instantly converts this into text data, and an AI model evaluates its accuracy. Furthermore, an emotion analysis engine evaluates the user's emotions as a high level of urgency, enabling rapid notification to the fire department.

[0180] An example of a prompt for a generative AI model is: "Please describe in detail a method for analyzing urgent voice input from a user and evaluating its sentiment and trustworthiness."

[0181] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0182] Step 1:

[0183] The user enters emergency information using a communication terminal. This input can be in text or voice format. In the case of voice input, the terminal uses a speech recognition API (e.g., Google Cloud Speech-to-Text) to convert it to text. The output of this step is text data.

[0184] Step 2:

[0185] The device automatically obtains geographic information of its current location. Typically, it uses GPS functionality to obtain latitude and longitude from location services. The output of this step is a pair of location data (latitude and longitude).

[0186] Step 3:

[0187] A request containing text data and location data is sent from the terminal to the server. The server receives this request and stores the data. The output of this step is the user input data stored in the database on the server.

[0188] Step 4:

[0189] The server uses a generative artificial intelligence model to evaluate the reliability of the text data. The AI ​​model (e.g., a model using TENSORFLOW® or PyTorch) analyzes the context of the text using natural language processing techniques and generates a confidence score as output. The output of this step is the confidence score.

[0190] Step 5:

[0191] Simultaneously, the server uses an emotion analysis engine to detect emotions from the text data. The engine analyzes the emotional significance of the text and outputs the relevant emotion categories (e.g., urgency, fear, relief, etc.) as numerical data. The output of this step is the emotion score.

[0192] Step 6:

[0193] The server applies an algorithm to determine the priority of emergency information based on the obtained trust and sentiment scores. Based on the priority, it generates a result indicating whether or not to provide information to the relevant agencies. The output of this step is a notification request to the relevant agencies if notification is required.

[0194] Step 7:

[0195] The server sends a notification to the relevant agencies. The notification is sent automatically via the API, allowing the agencies to begin responding quickly. The output of this step is the sent notification and any possible responses from the agencies.

[0196] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0197] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0198] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0199] [Second Embodiment]

[0200] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0201] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0202] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0203] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0204] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0205] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0206] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0207] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0208] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0209] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0210] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0211] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0212] This invention provides a specific model for implementing a system that efficiently analyzes information received during a disaster and provides only reliable information to the response organization. First, the user inputs disaster information using a communication terminal. At this time, the terminal automatically acquires geographical information and sends it to the server along with the information entered by the user. The server verifies and formats this received data and prepares it for storage.

[0213] Next, the server inputs the formatted information into an artificial intelligence (AI) model to evaluate the reliability of the information. This AI model analyzes the linguistic patterns contained in the disaster information text and its degree of relevance to the situation. For location information, the credibility of the report can be verified by comparing it with existing geographic information systems (GIS) and disaster data.

[0214] For example, if a user reports that their home is flooded, the location information obtained from the device is compared with rainfall data for that area on the server. This allows the AI ​​to assist in determining if a flood report is suspicious even though there is no record of rainfall.

[0215] If the evaluation determines that the information is reliable, the server automatically transmits the information to the appropriate agency. This enables an accurate and prompt response. If the information is determined to be highly likely to be false, a warning is sent to the administrator, and further verification and auditing are conducted.

[0216] The usefulness of this system lies in selecting reliable information from a vast amount of data and optimally allocating limited resources. This method is expected to improve the effectiveness and speed of disaster response.

[0217] The following describes the processing flow.

[0218] Step 1:

[0219] The user uses a communication terminal to input and send disaster information in text format. Based on the user's permission, the terminal automatically acquires geographical information and prepares to send this information along with the text to the server.

[0220] Step 2:

[0221] The terminal sends the entered information and any added geographical information to the server. The server verifies the format of the incoming data and checks for syntax errors or incomplete data.

[0222] Step 3:

[0223] The server decodes the received information as needed and formats it into a meaningful form as disaster information. This process includes appropriately identifying location information and text data.

[0224] Step 4:

[0225] The server transfers the formatted information to an artificial intelligence model. The AI ​​model analyzes the text data and evaluates its reliability by comparing it to language patterns and common disaster report formats.

[0226] Step 5:

[0227] The server analyzes location data in conjunction with a Geographic Information System (GIS) to verify whether the reported location was actually affected by the disaster. This step is performed in conjunction with an external disaster database.

[0228] Step 6:

[0229] The server calculates a reliability score for the information based on the evaluation results of the AI ​​model. This score assesses the likelihood that the information is true.

[0230] Step 7:

[0231] The server determines how to process information based on its reliability score. Information with a high score is sent to the appropriate agency, while information with a low score will issue a warning to the administrator and request further verification.

[0232] Step 8:

[0233] Information transmitted from the server is quickly processed by the responding agency, and necessary rescue operations and information sharing are initiated.

[0234] (Example 1)

[0235] Next, we will describe Example 1. 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."

[0236] During a disaster, it is crucial to quickly and accurately select reliable information from a vast amount of data and provide it to the appropriate response agencies. Furthermore, identifying false information and taking appropriate countermeasures is also essential. Under these circumstances, the current system faces the challenge of slow response due to the time required for information verification and processing.

[0237] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0238] In this invention, the server includes means for receiving, formatting, and correcting data; means for inputting the formatted data into a generating artificial intelligence model to evaluate its reliability; and means for automatically providing information to the responding agency based on the evaluation results. This enables the rapid and accurate sorting and automatic provision of disaster information to the responding agency.

[0239] A "communication terminal" is a device used by users to input disaster information and is equipped with a function that enables the automatic acquisition of geographical information.

[0240] "Geographic information" refers to data used to identify the location from which the information was provided, and is usually expressed in the form of latitude and longitude.

[0241] A "generative artificial intelligence model" is an algorithm or program used to analyze text data of disaster information and evaluate its reliability.

[0242] "Means for evaluating reliability" refers to processing methods that analyze received data and determine whether the information is accurate and true.

[0243] A "response agency" refers to an organization or department that takes necessary action after receiving disaster information, and begins its activities based on the information provided.

[0244] This invention relates to a system for efficiently analyzing and evaluating the reliability of information during disasters. This system is constructed using a communication terminal, a server, and a generative artificial intelligence model.

[0245] Users input disaster information using a communication terminal. The terminal automatically obtains the user's location information using its built-in GPS function and sends that information to the server. Specifically, for example, a user might input information such as "There is a fire in the neighborhood" and send it to the server along with their location information.

[0246] The server formats the received information and corrects any errors. The formatted information is then input into a generating AI model. This AI model utilizes natural language processing technology to analyze language patterns in the input text and evaluate the reliability of the disaster information. Furthermore, location information is verified for report validity by comparing it with existing geographic and disaster data using a GIS (Geographic Information System).

[0247] For example, if a report states that "the river is overflowing," the AI ​​model evaluates its reliability based on keywords such as "river" and "flooding," and verifies it by referring to location information and the flood history of that area.

[0248] An example of a prompt message to ensure the operation of this system is as follows: "User report: A fire has broken out in the neighborhood. Location: Latitude 35.6895, Longitude 139.6917. Please evaluate the reliability of this information."

[0249] This allows the server to automatically provide information deemed highly reliable to the response agency, enabling a rapid disaster response based on that information. If the information is determined to be potentially false, the server will issue a warning to the administrator, allowing for further verification procedures. In this way, the present invention aims to improve the efficiency and accuracy of disaster response.

[0250] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0251] Step 1:

[0252] The user inputs disaster information using a communication terminal. This input consists of text information related to the disaster. The terminal automatically acquires location information using its built-in GPS function and sends this location information to the server along with the input text. At this stage, the input information consists of the disaster report content and location data. The output is the transmission of information to the server. For example, if the user inputs "There is a fire," the terminal checks its current location and sends the data to the server.

[0253] Step 2:

[0254] The server receives the data. The received information is formatted, and any errors are corrected. For example, the date and time format is standardized, and the accuracy of location information is verified. The input is disaster information and location information sent from the terminal, and the output is data formatted in a standardized format. Specifically, the server converts the date and time to the format "2023-05-15T10:00:00" and re-verifies the location information.

[0255] Step 3:

[0256] The server inputs formatted data into a generating AI model. This model analyzes the language patterns of the input disaster information text and evaluates the reliability of the information. Location information is cross-referenced with a geographic information system to verify its authenticity. The input is formatted disaster report data, and the output is a reliability evaluation score or judgment result. Specifically, the AI ​​detects the language patterns of "fire" and "occurrence," and cross-references the location information with past fire data.

[0257] Step 4:

[0258] The server determines the reliability of the information based on the evaluation results from the generated AI model. If the information is deemed highly reliable, the server automatically provides it to the appropriate agency. If the information is deemed unreliable, it issues a warning to the administrator and initiates further verification procedures. The input is the result of the AI ​​model's reliability evaluation, and the output is the provision of information to the appropriate agency or a warning to the administrator. Specifically, highly reliable information is reported as "Reliability: High" and sent to the appropriate agency, or the administrator is notified as "Warning: Low Reliability."

[0259] (Application Example 1)

[0260] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0261] During a disaster, a large amount of information flows in, but it is difficult to quickly select reliable information from among it. This makes it difficult for response agencies to take immediate and appropriate action, potentially leading to an escalation of damage. To solve this problem, a system is needed that automatically evaluates the reliability of information and promptly notifies only those that are certain.

[0262] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0263] In this invention, the server includes means for receiving data from users who input disaster information using a communication device, means for automatically acquiring location information contained in the data, means for inputting the received data into an artificial intelligence model that generates data and evaluating the reliability of the information, means for determining whether the information is false based on the evaluation, means for providing the information to a response agency according to the reliability of the information, and means for automatically notifying a safety agency based on the reliability of the evaluated information. This makes it possible to appropriately and quickly notify response agencies of reliable disaster information from a vast amount of data.

[0264] A "communication device" is an electronic device used by users to input disaster information and enables the transmission and reception of data.

[0265] "Location information" refers to information used to identify the geographical location included in the data entered by the user, and is automatically acquired using technologies such as GPS.

[0266] An "artificial intelligence model" is a machine learning algorithm or data analysis tool used to analyze received data and evaluate the reliability of that information.

[0267] "Evaluation" is a process for determining the accuracy and reliability of received disaster information, thereby determining whether the information is true or false.

[0268] A "response organization" is an organization or agency that receives information in order to take appropriate action based on disaster information, and is primarily responsible for ensuring safety and mitigating damage.

[0269] A "safety agency" is an organization responsible for taking swift action to protect human lives and property during a disaster.

[0270] The system for realizing this invention consists of multiple communication devices, a server, and an artificial intelligence model to be generated. First, the user inputs disaster information into the communication device. This device is equipped with a location information acquisition function and can automatically acquire accurate geographic information using technologies such as GPS. The acquired disaster information and location information are transmitted to the server via the network.

[0271] The server stores the received data and uses pre-trained generative AI models, such as natural language processing toolkits and machine learning algorithms, to evaluate the reliability of the information. In this evaluation process, the content and location of the information are compared with historical disaster data. Specifically, the server uses GIS to match location data with existing disaster data and verify the degree of consistency of the reported information. Information deemed to have a low probability of being false is promptly provided to the response agency. On the other hand, information that is highly likely to be false undergoes further verification.

[0272] For example, if a user reports that "flooding is occurring at my current location," the system checks for recent weather data to see if there are any records of precipitation. If the weather records do not indicate a possibility of flooding, the AI ​​will deem the report questionable. At the same time, if the information is deemed reliable, safety notices are sent to relevant agencies to quickly take measures to minimize damage.

[0273] An example of a prompt message to input into the generating AI model is: "Evaluate the flood occurrence reported by the user, determine its reliability, and notify the result." This allows the system to receive specific instructions to make appropriate decisions.

[0274] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0275] Step 1:

[0276] On the terminal, the user inputs disaster information. The user reports specific disaster conditions (e.g., flood, earthquake) in text format, and the terminal automatically obtains the current location information using its GPS function. Both the input information and the location information are sent to the server. The input consists of text and location data, and the output is the data sent to the server.

[0277] Step 2:

[0278] The server first performs an initial filter on the received information. Specifically, it checks for abnormal strings and missing location information. An automated script is used for this, removing unformatted data and passing the formatted data to the generating AI model. The input is raw data from the user, and the output is formatted data that fits the AI ​​model.

[0279] Step 3:

[0280] A generative AI model is launched on the server and analyzes the formatted data. The AI ​​compares it with past disaster report data and evaluates the language patterns and degree of similarity of the report content. Furthermore, it guides the evaluation process using prompt sentences. The input is the formatted data, and the output is the reliability assessment result.

[0281] Step 4:

[0282] The server uses GIS to verify location information. It examines the credibility of reported conditions by comparing them with local weather data and disaster history. For example, reported floods are evaluated by directly comparing them with precipitation records. Input is location data, and output is the location verification result.

[0283] Step 5:

[0284] The server integrates the information obtained from the AI model and GIS, and determines the final reliability of the information. If the reliability is high, it prepares to notify the corresponding agency. The notification includes instructions regarding the necessary measures together with the generated reliability evaluation. The input is the evaluation results from AI and GIS, and the output is the notification data.

[0285] Step 6:

[0286] The server notifies the response agency of highly reliable information. The notification system is automated and delivers the information through multiple channels (e.g., SMS, email). This enables a prompt response. The input is the notification data, and the output is the delivered notification.

[0287] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion recognition model 59 and perform specific processing using the user's emotion.

[0288] This invention describes an embodiment of a disaster information analysis system incorporating an emotion engine that recognizes the user's emotion when analyzing disaster information input using a communication terminal. This system starts from automatically acquiring geographical information related to the disaster information input by the user to the terminal and transmitting that data to the server.

[0289] For the received data, the server evaluates the reliability of the information using a generated artificial intelligence (AI) model. This AI model analyzes text data, examines its language patterns and formats, and determines the reliability of the information. In addition, the emotion engine detects emotions from the text data input by the user. This emotion data is used in the reliability evaluation of the information. For example, the content input in a panicked state and the content input calmly may be weighted differently. [[ID= twenty-two]]

[0290] For example, if a user types "Help! My house is flooding," the device sends the message to the server along with its current geographical location. The server's AI evaluates this text from a credibility standpoint, while simultaneously, an emotion engine measures the user's level of urgency. Information deemed highly urgent based on the user's emotion recognition is then evaluated considering this tendency and reflected in the prioritization of response agencies.

[0291] Based on the reliability of the information and the results of sentiment analysis, the server notifies the appropriate agency of the most reliable information. Considering sentiment data also enables the rapid transmission of highly urgent cases to the appropriate agency. This system configuration allows for multifaceted information evaluation, including sentiment analysis, and supports appropriate responses during disasters.

[0292] The following describes the processing flow.

[0293] Step 1:

[0294] The user uses a communication terminal to input and transmit disaster information in text format. The terminal automatically retrieves geographical information about the user's current location and prepares to package it together with the text information.

[0295] Step 2:

[0296] The terminal sends a prepared information package to the server. The server receives the incoming data, verifies its format, and determines whether it can be processed appropriately.

[0297] Step 3:

[0298] The server separates the received data into text information and geographic information. This data is then formatted for analysis by generative artificial intelligence models and sentiment engines.

[0299] Step 4:

[0300] The server inputs the text information into the generative artificial intelligence model to analyze the language pattern of the disaster information and evaluate its reliability. The AI model measures the accuracy of the information based on the content, diction, and format of the report.

[0301] Step 5:

[0302] In parallel, the server sends the text information to the sentiment engine to recognize the user's emotional state. This analysis is based on words indicating the tone and urgency of the text.

[0303] Step 6:

[0304] The server combines the reliability evaluation obtained from the AI model and the sentiment data from the sentiment engine to calculate a comprehensive information reliability score. The score reflects the authenticity and urgency of the information.

[0305] Step 7:

[0306] The server determines the processing of the information based on the calculated reliability score. Information with a high score is provided to the response agency promptly, while information with a low score is sent as a warning to the administrator for further verification.

[0307] Step 8:

[0308] The response agency takes prompt action based on the highly reliable information sent by the server and prepares to launch rescue operations if necessary. Considering the urgency based on the sentiment data, effective decisions can be made.

[0309] (Example 2)

[0310] Next, Example 2 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0311] In collecting and analyzing disaster information, verifying the accuracy of the information and assessing its urgency based on users' emotions are crucial. However, conventional technologies lack mechanisms to integrate and utilize information reliability assessment and user sentiment analysis, which can make rapid and accurate responses difficult. To address this challenge, there is a need to provide an analysis method that simultaneously considers information reliability and users' emotional states.

[0312] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0313] In this invention, the server includes means for receiving data from users who input information using a communication device, means for automatically acquiring location information contained in the data, means for inputting the received data into a machine learning model to evaluate the reliability of the information, means for applying emotion recognition technology to the information to determine the user's emotional state, and means for classifying and providing information based on reliability and emotion analysis. This makes it possible to integrate and utilize information reliability evaluation and emotion analysis, enabling quick and appropriate responses.

[0314] A "communication device" is an electronic device used to send and receive information, and in particular refers to a terminal that allows users to input information and enables data communication.

[0315] "Location information" refers to data that indicates a geographical location, and usually includes coordinate information such as latitude and longitude.

[0316] A "machine learning model" refers to an algorithm or system that allows a computer to learn patterns from large amounts of data and then make predictions or classifications on new data.

[0317] "Information reliability" refers to the criteria used to evaluate whether the information provided is accurate and true.

[0318] "Emotion recognition technology" refers to technology that identifies a person's emotions from data such as text, audio, and images, and clarifies their emotional state.

[0319] "User's emotional state" refers to the mental state a user exhibits when entering information, such as whether they are feeling a sense of urgency or remaining calm.

[0320] "Means of classification and provision" refers to the function or method of classifying evaluated information based on specific criteria and providing it appropriately to the necessary institutions and systems.

[0321] The system in this invention consists of three components: a user, a terminal, and a server. First, the user inputs information related to the disaster using a communication device, such as a smartphone or tablet device. The input information is primarily text-based, but may also include images and audio data in some cases.

[0322] The device automatically acquires location information using its built-in GPS function, along with the entered information. This location information is transmitted to the server via a communication protocol. Specifically, location information is acquired using the Google Maps API, and the data is sent to the server via HTTPS communication.

[0323] The server analyzes the received data using a generative artificial intelligence model. This model utilizes natural language processing technologies, such as OpenAI models, to scrutinize the input text information and evaluate its reliability. Furthermore, sentiment recognition technology is applied to the received text data, using tools like IBM Watson to determine the user's emotional state. This sentiment analysis helps understand the user's sense of urgency and reflects this in the weighting of the information.

[0324] For example, if a user types "Help! My house is flooded," this information and its location data are sent to the server. The server uses an AI model to evaluate the reliability of the text content and an emotion engine to analyze its urgency. As a result, the information is classified as urgent and notified to the appropriate authorities.

[0325] In this system embodiment, an example of a prompt message is used: "My home has been flooded due to heavy rain last night. Please take immediate action." By inputting such a prompt message into the AI ​​model and analyzing the reliability of the information and the emotional state, a rapid response becomes possible.

[0326] This method aims to enable accurate and rapid processing of disaster information, thereby improving the efficiency of responses in emergencies.

[0327] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0328] Step 1:

[0329] Users input disaster information using communication devices. Specifically, they write text messages via smartphone apps or web interfaces, attaching media such as images and audio as needed. The information entered at this stage consists of details of the disaster situation as observed by the user.

[0330] Step 2:

[0331] The device acquires location information along with the information entered by the user. Location information is obtained using the device's built-in GPS function or location services, and the current location is determined using tools such as the Google Maps API. The acquired geographic information and user input information are combined to create a dataset. This dataset becomes the data sent to the server.

[0332] Step 3:

[0333] The device sends the generated dataset to the server. The HTTPS protocol is used for transmission, ensuring secure and rapid data transfer. The transmitted data consists of user text information, location information, and metadata.

[0334] Step 4:

[0335] The server analyzes the received dataset. First, it uses a generative AI model to analyze the text information and evaluate its reliability. The AI ​​model uses natural language processing techniques to analyze text patterns and distinguish meaningful information from noise. The reliability evaluation results are then output.

[0336] Step 5:

[0337] The server applies sentiment recognition technology to the received text information. The sentiment engine analyzes the text content and identifies the user's emotional state—for example, urgency or fear. The output of the sentiment analysis serves as supplementary data that influences the reliability evaluation.

[0338] Step 6:

[0339] The server classifies information based on the output of reliability assessments and sentiment analysis. Based on the analysis results, it prioritizes the information and generates notification data for the appropriate response agency. This classification process ensures that important information is processed more quickly and appropriately.

[0340] Step 7:

[0341] The generated notification data is sent from the server to the appropriate agency. High-priority information is automatically notified to the emergency response department, enabling immediate action. The output data includes details and suggestions to identify necessary actions.

[0342] (Application Example 2)

[0343] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0344] Conventional disaster information systems had limitations in judging the accuracy of received information, particularly in their inability to consider the emotions of the information senders, and thus in their inability to accurately assess the urgency of the information. Furthermore, there were challenges in detecting false information and rapidly disseminating highly urgent information.

[0345] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0346] In this invention, the server includes means for receiving data from a user who inputs emergency information using a communication device, means for automatically acquiring location information contained in the data, means for inputting the received data into a generating artificial intelligence model to evaluate the accuracy of the information, means for detecting emotions from the user's input data using an emotion analysis engine, and means for providing the information to relevant organizations according to the accuracy of the information and the emotion data. By combining the accuracy of the information with the user's emotion information, it becomes possible to determine false information and provide information quickly based on priority.

[0347] "Communication equipment" is a general term for hardware and software that directly receives emergency information from users and processes the data.

[0348] "Location information" refers to geographical data about the location where the user entered emergency information, and is usually obtained through GPS or geographic information systems.

[0349] A "generative artificial intelligence model" refers to a collection of algorithms and software that use natural language processing and machine learning to evaluate data in order to determine the accuracy of received information.

[0350] An "emotion analysis engine" is an analytical technology that detects emotions from the user's input data and outputs the results as numerical values ​​or categories.

[0351] "Providing to relevant organizations" refers to the operation or process of transmitting the analyzed information to various relevant agencies and organizations at the appropriate time.

[0352] To implement this invention, a system is constructed that allows users to input emergency information using a communication terminal. This system includes a process for rapidly analyzing the received data and providing the information to relevant organizations as needed.

[0353] The server receives data entered by the user from their communication terminal and automatically acquires location information. This allows for understanding the geographical context of the location where the emergency occurred.

[0354] The received data is evaluated for accuracy using a generative artificial intelligence model. The AI ​​model uses natural language processing technology to analyze the content of the information and determine its reliability.

[0355] Furthermore, an emotion analysis engine detects emotions from the user's input data. This engine numerically or categorically evaluates the emotional nuances of the input text and voice data, and uses the results to assess urgency.

[0356] Considering the accuracy of the information and the detected sentiment data, the server provides the information to the relevant organizations. This allows for priority responses based on the urgency of the information.

[0357] For example, if a user voice-inputs "There is a fire. Please help," the server instantly converts this into text data, and an AI model evaluates its accuracy. Furthermore, an emotion analysis engine evaluates the user's emotions as a high level of urgency, enabling rapid notification to the fire department.

[0358] An example of a prompt for a generative AI model is: "Please describe in detail a method for analyzing urgent voice input from a user and evaluating its sentiment and trustworthiness."

[0359] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0360] Step 1:

[0361] The user enters emergency information using a communication terminal. This input can be in text or voice format. In the case of voice input, the terminal uses a speech recognition API (e.g., Google Cloud Speech-to-Text) to convert it to text. The output of this step is text data.

[0362] Step 2:

[0363] The device automatically obtains geographic information of its current location. Typically, it uses GPS functionality to obtain latitude and longitude from location services. The output of this step is a pair of location data (latitude and longitude).

[0364] Step 3:

[0365] A request containing text data and location data is sent from the terminal to the server. The server receives this request and stores the data. The output of this step is the user input data stored in the database on the server.

[0366] Step 4:

[0367] The server uses a generative artificial intelligence model to evaluate the reliability of the text data. The AI ​​model (e.g., a model using TensorFlow or PyTorch) analyzes the context of the text using natural language processing techniques and generates a confidence score as output. The output of this step is the confidence score.

[0368] Step 5:

[0369] Simultaneously, the server uses an emotion analysis engine to detect emotions from the text data. The engine analyzes the emotional significance of the text and outputs the relevant emotion categories (e.g., urgency, fear, relief, etc.) as numerical data. The output of this step is the emotion score.

[0370] Step 6:

[0371] The server applies an algorithm to determine the priority of emergency information based on the obtained trust and sentiment scores. Based on the priority, it generates a result indicating whether or not to provide information to the relevant agencies. The output of this step is a notification request to the relevant agencies if notification is required.

[0372] Step 7:

[0373] The server sends a notification to the relevant agencies. The notification is sent automatically via the API, allowing the agencies to begin responding quickly. The output of this step is the sent notification and any possible responses from the agencies.

[0374] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0375] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0376] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0377] [Third Embodiment]

[0378] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0379] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0380] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0381] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0382] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0383] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0384] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0385] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0386] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0387] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0388] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0389] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0390] This invention provides a specific model for implementing a system that efficiently analyzes information received during a disaster and provides only reliable information to the response organization. First, the user inputs disaster information using a communication terminal. At this time, the terminal automatically acquires geographical information and sends it to the server along with the information entered by the user. The server verifies and formats this received data and prepares it for storage.

[0391] Next, the server inputs the formatted information into an artificial intelligence (AI) model to evaluate the reliability of the information. This AI model analyzes the linguistic patterns contained in the disaster information text and its degree of relevance to the situation. For location information, the credibility of the report can be verified by comparing it with existing geographic information systems (GIS) and disaster data.

[0392] For example, if a user reports that their home is flooded, the location information obtained from the device is compared with rainfall data for that area on the server. This allows the AI ​​to assist in determining if a flood report is suspicious even though there is no record of rainfall.

[0393] If the evaluation determines that the information is reliable, the server automatically transmits the information to the appropriate agency. This enables an accurate and prompt response. If the information is determined to be highly likely to be false, a warning is sent to the administrator, and further verification and auditing are conducted.

[0394] The usefulness of this system lies in selecting reliable information from a vast amount of data and optimally allocating limited resources. This method is expected to improve the effectiveness and speed of disaster response.

[0395] The following describes the processing flow.

[0396] Step 1:

[0397] The user uses a communication terminal to input and send disaster information in text format. Based on the user's permission, the terminal automatically acquires geographical information and prepares to send this information along with the text to the server.

[0398] Step 2:

[0399] The terminal sends the entered information and any added geographical information to the server. The server verifies the format of the incoming data and checks for syntax errors or incomplete data.

[0400] Step 3:

[0401] The server decodes the received information as needed and formats it into a meaningful form as disaster information. This process includes appropriately identifying location information and text data.

[0402] Step 4:

[0403] The server transfers the formatted information to an artificial intelligence model. The AI ​​model analyzes the text data and evaluates its reliability by comparing it to language patterns and common disaster report formats.

[0404] Step 5:

[0405] The server analyzes location data in conjunction with a Geographic Information System (GIS) to verify whether the reported location was actually affected by the disaster. This step is performed in conjunction with an external disaster database.

[0406] Step 6:

[0407] The server calculates a reliability score for the information based on the evaluation results of the AI ​​model. This score assesses the likelihood that the information is true.

[0408] Step 7:

[0409] The server determines how to process information based on its reliability score. Information with a high score is sent to the appropriate agency, while information with a low score will issue a warning to the administrator and request further verification.

[0410] Step 8:

[0411] Information transmitted from the server is quickly processed by the responding agency, and necessary rescue operations and information sharing are initiated.

[0412] (Example 1)

[0413] Next, we will describe Example 1. 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."

[0414] During a disaster, it is crucial to quickly and accurately select reliable information from a vast amount of data and provide it to the appropriate response agencies. Furthermore, identifying false information and taking appropriate countermeasures is also essential. Under these circumstances, the current system faces the challenge of slow response due to the time required for information verification and processing.

[0415] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0416] In this invention, the server includes means for receiving, formatting, and correcting data; means for inputting the formatted data into a generating artificial intelligence model to evaluate its reliability; and means for automatically providing information to the responding agency based on the evaluation results. This enables the rapid and accurate sorting and automatic provision of disaster information to the responding agency.

[0417] A "communication terminal" is a device used by users to input disaster information and is equipped with a function that enables the automatic acquisition of geographical information.

[0418] "Geographic information" refers to data used to identify the location from which the information was provided, and is usually expressed in the form of latitude and longitude.

[0419] A "generative artificial intelligence model" is an algorithm or program used to analyze text data of disaster information and evaluate its reliability.

[0420] "Means for evaluating reliability" refers to processing methods that analyze received data and determine whether the information is accurate and true.

[0421] A "response agency" refers to an organization or department that takes necessary action after receiving disaster information, and begins its activities based on the information provided.

[0422] This invention relates to a system for efficiently analyzing and evaluating the reliability of information during disasters. This system is constructed using a communication terminal, a server, and a generative artificial intelligence model.

[0423] Users input disaster information using a communication terminal. The terminal automatically obtains the user's location information using its built-in GPS function and sends that information to the server. Specifically, for example, a user might input information such as "There is a fire in the neighborhood" and send it to the server along with their location information.

[0424] The server formats the received information and corrects any errors. The formatted information is then input into a generating AI model. This AI model utilizes natural language processing technology to analyze language patterns in the input text and evaluate the reliability of the disaster information. Furthermore, location information is verified for report validity by comparing it with existing geographic and disaster data using a GIS (Geographic Information System).

[0425] For example, if a report states that "the river is overflowing," the AI ​​model evaluates its reliability based on keywords such as "river" and "flooding," and verifies it by referring to location information and the flood history of that area.

[0426] An example of a prompt message to ensure the operation of this system is as follows: "User Report: A fire has broken out in the neighborhood. Location: Latitude 35.6895, Longitude 139.6917. Please evaluate the reliability of this information."

[0427] This allows the server to automatically provide information deemed highly reliable to the response agency, enabling a rapid disaster response based on that information. If the information is determined to be potentially false, the server will issue a warning to the administrator, allowing for further verification procedures. In this way, the present invention aims to improve the efficiency and accuracy of disaster response.

[0428] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0429] Step 1:

[0430] The user inputs disaster information using a communication terminal. This input consists of text information related to the disaster. The terminal automatically acquires location information using its built-in GPS function and sends this location information to the server along with the input text. At this stage, the input information consists of the disaster report content and location data. The output is the transmission of information to the server. For example, if the user inputs "There is a fire," the terminal checks its current location and sends the data to the server.

[0431] Step 2:

[0432] The server receives the data. The received information is formatted, and any errors are corrected. For example, the date and time format is standardized, and the accuracy of location information is verified. The input is disaster information and location information sent from the terminal, and the output is data formatted in a standardized format. Specifically, the server converts the date and time to the format "2023-05-15T10:00:00" and re-verifies the location information.

[0433] Step 3:

[0434] The server inputs formatted data into a generating AI model. This model analyzes the language patterns of the input disaster information text and evaluates the reliability of the information. Location information is cross-referenced with a geographic information system to verify its authenticity. The input is formatted disaster report data, and the output is a reliability evaluation score or judgment result. Specifically, the AI ​​detects the language patterns of "fire" and "occurrence," and cross-references the location information with past fire data.

[0435] Step 4:

[0436] The server determines the reliability of the information based on the evaluation results from the generated AI model. If the information is deemed highly reliable, the server automatically provides it to the appropriate agency. If the information is deemed unreliable, it issues a warning to the administrator and initiates further verification procedures. The input is the result of the AI ​​model's reliability evaluation, and the output is the provision of information to the appropriate agency or a warning to the administrator. Specifically, highly reliable information is reported as "Reliability: High" and sent to the appropriate agency, or the administrator is notified as "Warning: Low Reliability."

[0437] (Application Example 1)

[0438] Next, we will explain Application Example 1. In the following explanation, 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."

[0439] During a disaster, a large amount of information flows in, but it is difficult to quickly select reliable information from among it. This makes it difficult for response agencies to take immediate and appropriate action, potentially leading to an escalation of damage. To solve this problem, a system is needed that automatically evaluates the reliability of information and promptly notifies only those that are certain.

[0440] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0441] In this invention, the server includes means for receiving data from users who input disaster information using a communication device, means for automatically acquiring location information contained in the data, means for inputting the received data into an artificial intelligence model that generates data and evaluating the reliability of the information, means for determining whether the information is false based on the evaluation, means for providing the information to a response agency according to the reliability of the information, and means for automatically notifying a safety agency based on the reliability of the evaluated information. This makes it possible to appropriately and quickly notify response agencies of reliable disaster information from a vast amount of data.

[0442] A "communication device" is an electronic device used by users to input disaster information and enables the transmission and reception of data.

[0443] "Location information" refers to information used to identify the geographical location included in the data entered by the user, and is automatically acquired using technologies such as GPS.

[0444] An "artificial intelligence model" is a machine learning algorithm or data analysis tool used to analyze received data and evaluate the reliability of that information.

[0445] "Evaluation" is a process for determining the accuracy and reliability of received disaster information, thereby determining whether the information is true or false.

[0446] A "response organization" is an organization or agency that receives information in order to take appropriate action based on disaster information, and is primarily responsible for ensuring safety and mitigating damage.

[0447] A "safety agency" is an organization responsible for taking swift action to protect human lives and property during a disaster.

[0448] The system for realizing this invention consists of multiple communication devices, a server, and an artificial intelligence model to be generated. First, the user inputs disaster information into the communication device. This device is equipped with a location information acquisition function and can automatically acquire accurate geographic information using technologies such as GPS. The acquired disaster information and location information are transmitted to the server via the network.

[0449] The server stores the received data and uses pre-trained generative AI models, such as natural language processing toolkits and machine learning algorithms, to evaluate the reliability of the information. In this evaluation process, the content and location of the information are compared with historical disaster data. Specifically, the server uses GIS to match location data with existing disaster data and verify the degree of consistency of the reported information. Information deemed to have a low probability of being false is promptly provided to the response agency. On the other hand, information that is highly likely to be false undergoes further verification.

[0450] For example, if a user reports that "flooding is occurring at my current location," the system checks for recent weather data to see if there are any records of precipitation. If the weather records do not indicate a possibility of flooding, the AI ​​will deem the report questionable. At the same time, if the information is deemed reliable, safety notices are sent to relevant agencies to quickly take measures to minimize damage.

[0451] An example of a prompt message to input into the generating AI model is: "Evaluate the flood occurrence reported by the user, determine its reliability, and notify the result." This allows the system to receive specific instructions to make appropriate decisions.

[0452] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0453] Step 1:

[0454] On the terminal, the user inputs disaster information. The user reports specific disaster conditions (e.g., flood, earthquake) in text format, and the terminal automatically obtains the current location information using its GPS function. Both the input information and the location information are sent to the server. The input consists of text and location data, and the output is the data sent to the server.

[0455] Step 2:

[0456] The server first performs an initial filter on the received information. Specifically, it checks for abnormal strings and missing location information. An automated script is used for this, removing unformatted data and passing the formatted data to the generating AI model. The input is raw data from the user, and the output is formatted data that fits the AI ​​model.

[0457] Step 3:

[0458] A generative AI model is launched on the server and analyzes the formatted data. The AI ​​compares it with past disaster report data and evaluates the language patterns and degree of similarity of the report content. Furthermore, it guides the evaluation process using prompt sentences. The input is the formatted data, and the output is the reliability assessment result.

[0459] Step 4:

[0460] The server uses GIS to verify location information. It examines the credibility of reported conditions by comparing them with local weather data and disaster history. For example, reported floods are evaluated by directly comparing them with precipitation records. Input is location data, and output is the location verification result.

[0461] Step 5:

[0462] The server integrates information obtained from AI models and GIS to determine the final reliability of the information. If the reliability is high, it prepares to notify the relevant authorities. The notification includes the generated reliability assessment along with instructions on necessary actions. The input is the evaluation results from AI and GIS, and the output is the notification data.

[0463] Step 6:

[0464] The server notifies the response agency of reliable information. The notification system is automated and delivers information via multiple channels (e.g., SMS, email). This enables a rapid response. The input is the notification data, and the output is the delivered notification.

[0465] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0466] This invention describes an embodiment of a disaster information analysis system that incorporates an emotion engine to recognize user emotions when analyzing disaster information entered using a communication terminal. This system begins by automatically acquiring disaster information and related geographical information entered by the user into the terminal and transmitting that data to a server.

[0467] The server uses a generative artificial intelligence (AI) model to evaluate the reliability of the received data. This AI model analyzes text data, examining its linguistic patterns and format to determine its reliability. In addition, an emotion engine detects emotions from the text data entered by the user. This emotion data is used to evaluate the reliability of the information. For example, content entered in a panicked state may be weighted differently from content entered calmly.

[0468] For example, if a user types "Help! My house is flooding," the device sends the message to the server along with its current geographical location. The server's AI evaluates this text from a credibility standpoint, while simultaneously, an emotion engine measures the user's level of urgency. Information deemed highly urgent based on the user's emotion recognition is then evaluated considering this tendency and reflected in the prioritization of response agencies.

[0469] Based on the reliability of the information and the results of sentiment analysis, the server notifies the appropriate agency of the most reliable information. Considering sentiment data also enables the rapid transmission of highly urgent cases to the appropriate agency. This system configuration allows for multifaceted information evaluation, including sentiment analysis, and supports appropriate responses during disasters.

[0470] The following describes the processing flow.

[0471] Step 1:

[0472] The user uses a communication terminal to input and transmit disaster information in text format. The terminal automatically retrieves geographical information about the user's current location and prepares to package it together with the text information.

[0473] Step 2:

[0474] The terminal sends a prepared information package to the server. The server receives the incoming data, verifies its format, and determines whether it can be processed appropriately.

[0475] Step 3:

[0476] The server separates the received data into text information and geographic information. This data is then formatted for analysis by generative artificial intelligence models and sentiment engines.

[0477] Step 4:

[0478] The server inputs text information into an artificial intelligence model that generates text data, analyzes the language patterns of the disaster information, and evaluates its reliability. The AI ​​model measures the accuracy of the information based on the content, wording, and format of the report.

[0479] Step 5:

[0480] In parallel, the server sends text information to the sentiment engine to recognize the user's emotional state. This analysis is based on the tone of the text and words indicating urgency.

[0481] Step 6:

[0482] The server combines reliability assessments obtained from AI models with sentiment data from an emotion engine to calculate an overall information reliability score. The score reflects the truthfulness and urgency of the information.

[0483] Step 7:

[0484] The server decides how to process information based on the calculated reliability score. Information with a high score is quickly provided to the appropriate agency, while information with a low score sends a warning to the administrator for further verification.

[0485] Step 8:

[0486] Responding agencies will take swift action based on reliable information transmitted from the server and prepare to deploy relief operations if necessary. Urgency based on emotional data will also be considered, enabling effective decision-making.

[0487] (Example 2)

[0488] Next, we will describe Example 2. 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."

[0489] In collecting and analyzing disaster information, verifying the accuracy of the information and assessing its urgency based on users' emotions are crucial. However, conventional technologies lack mechanisms to integrate and utilize information reliability assessment and user sentiment analysis, which can make rapid and accurate responses difficult. To address this challenge, there is a need to provide an analysis method that simultaneously considers information reliability and users' emotional states.

[0490] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0491] In this invention, the server includes means for receiving data from users who input information using a communication device, means for automatically acquiring location information contained in the data, means for inputting the received data into a machine learning model to evaluate the reliability of the information, means for applying emotion recognition technology to the information to determine the user's emotional state, and means for classifying and providing information based on reliability and emotion analysis. This makes it possible to integrate and utilize information reliability evaluation and emotion analysis, enabling quick and appropriate responses.

[0492] A "communication device" is an electronic device used to send and receive information, and in particular refers to a terminal that allows users to input information and enables data communication.

[0493] "Location information" refers to data that indicates a geographical location, and usually includes coordinate information such as latitude and longitude.

[0494] A "machine learning model" refers to an algorithm or system that allows a computer to learn patterns from large amounts of data and then make predictions or classifications on new data.

[0495] "Information reliability" refers to the criteria used to evaluate whether the information provided is accurate and true.

[0496] "Emotion recognition technology" refers to technology that identifies a person's emotions from data such as text, audio, and images, and clarifies their emotional state.

[0497] "User's emotional state" refers to the mental state a user exhibits when entering information, such as whether they are feeling a sense of urgency or remaining calm.

[0498] "Means of classification and provision" refers to the function or method of classifying evaluated information based on specific criteria and providing it appropriately to the necessary institutions and systems.

[0499] The system in this invention consists of three components: a user, a terminal, and a server. First, the user inputs information related to the disaster using a communication device, such as a smartphone or tablet device. The input information is primarily text-based, but may also include images and audio data in some cases.

[0500] The device automatically acquires location information using its built-in GPS function, along with the entered information. This location information is transmitted to the server via a communication protocol. Specifically, location information is acquired using the Google Maps API, and the data is sent to the server via HTTPS communication.

[0501] The server analyzes the received data using a generative artificial intelligence model. This model utilizes natural language processing technologies, such as OpenAI models, to scrutinize the input text information and evaluate its reliability. Furthermore, sentiment recognition technology is applied to the received text data, using tools like IBM Watson to determine the user's emotional state. This sentiment analysis helps understand the user's sense of urgency and reflects this in the weighting of the information.

[0502] For example, if a user types "Help! My house is flooded," this information and its location data are sent to the server. The server uses an AI model to evaluate the reliability of the text content and an emotion engine to analyze its urgency. As a result, the information is classified as urgent and notified to the appropriate authorities.

[0503] In this system embodiment, an example of a prompt message is used: "My home has been flooded due to heavy rain last night. Please take immediate action." By inputting such a prompt message into the AI ​​model and analyzing the reliability of the information and the emotional state, a rapid response becomes possible.

[0504] This method aims to enable accurate and rapid processing of disaster information, thereby improving the efficiency of responses in emergencies.

[0505] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0506] Step 1:

[0507] Users input disaster information using communication devices. Specifically, they write text messages via smartphone apps or web interfaces, attaching media such as images and audio as needed. The information entered at this stage consists of details of the disaster situation as observed by the user.

[0508] Step 2:

[0509] The device acquires location information along with the information entered by the user. Location information is obtained using the device's built-in GPS function or location services, and the current location is determined using tools such as the Google Maps API. The acquired geographic information and user input information are combined to create a dataset. This dataset becomes the data sent to the server.

[0510] Step 3:

[0511] The device sends the generated dataset to the server. The HTTPS protocol is used for transmission, ensuring secure and rapid data transfer. The transmitted data consists of user text information, location information, and metadata.

[0512] Step 4:

[0513] The server analyzes the received dataset. First, it uses a generative AI model to analyze the text information and evaluate its reliability. The AI ​​model uses natural language processing techniques to analyze text patterns and distinguish meaningful information from noise. The reliability evaluation results are then output.

[0514] Step 5:

[0515] The server applies sentiment recognition technology to the received text information. The sentiment engine analyzes the text content and identifies the user's emotional state—for example, urgency or fear. The output of the sentiment analysis serves as supplementary data that influences the reliability assessment.

[0516] Step 6:

[0517] The server categorizes information based on the output of reliability assessments and sentiment analysis. Based on the analysis results, it prioritizes the information and generates notification data for the appropriate response agency. This classification process ensures that important information is processed more quickly and appropriately.

[0518] Step 7:

[0519] The generated notification data is sent from the server to the appropriate agency. High-priority information is automatically notified to the emergency response department, enabling immediate action. The output data includes details and suggestions to identify necessary actions.

[0520] (Application Example 2)

[0521] Next, we will explain application example 2. In the following explanation, 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."

[0522] Conventional disaster information systems had limitations in judging the accuracy of received information, particularly in their inability to consider the emotions of the information senders, and thus in their inability to accurately assess the urgency of the information. Furthermore, there were challenges in detecting false information and rapidly disseminating highly urgent information.

[0523] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0524] In this invention, the server includes means for receiving data from a user who inputs emergency information using a communication device, means for automatically acquiring location information contained in the data, means for inputting the received data into a generating artificial intelligence model to evaluate the accuracy of the information, means for detecting emotions from the user's input data using an emotion analysis engine, and means for providing the information to relevant organizations according to the accuracy of the information and the emotion data. By combining the accuracy of the information with the user's emotion information, it becomes possible to determine false information and provide information quickly based on priority.

[0525] "Communication equipment" is a general term for hardware and software that directly receives emergency information from users and processes the data.

[0526] "Location information" refers to geographical data about the location where the user entered emergency information, and is usually obtained through GPS or geographic information systems.

[0527] A "generative artificial intelligence model" refers to a collection of algorithms and software that use natural language processing and machine learning to evaluate data in order to determine the accuracy of received information.

[0528] An "emotion analysis engine" is an analytical technology that detects emotions from the user's input data and outputs the results as numerical values ​​or categories.

[0529] "Providing to relevant organizations" refers to the operation or process of transmitting the analyzed information to various relevant agencies and organizations at the appropriate time.

[0530] To implement this invention, a system is constructed that allows users to input emergency information using a communication terminal. This system includes a process for rapidly analyzing the received data and providing the information to relevant organizations as needed.

[0531] The server receives data entered by the user from their communication terminal and automatically acquires location information. This allows for understanding the geographical context of the location where the emergency occurred.

[0532] The received data is evaluated for accuracy using a generative artificial intelligence model. The AI ​​model uses natural language processing technology to analyze the content of the information and determine its reliability.

[0533] Furthermore, an emotion analysis engine detects emotions from the user's input data. This engine numerically or categorically evaluates the emotional nuances of the input text and voice data, and uses the results to assess urgency.

[0534] Considering the accuracy of the information and the detected sentiment data, the server provides the information to the relevant organizations. This allows for priority responses based on the urgency of the information.

[0535] For example, if a user voice-inputs "There is a fire. Please help," the server instantly converts this into text data, and an AI model evaluates its accuracy. Furthermore, an emotion analysis engine evaluates the user's emotions as a high level of urgency, enabling rapid notification to the fire department.

[0536] An example of a prompt for a generative AI model is: "Please describe in detail a method for analyzing urgent voice input from a user and evaluating its sentiment and trustworthiness."

[0537] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0538] Step 1:

[0539] The user enters emergency information using a communication terminal. This input can be in text or voice format. In the case of voice input, the terminal uses a speech recognition API (e.g., Google Cloud Speech-to-Text) to convert it to text. The output of this step is text data.

[0540] Step 2:

[0541] The device automatically obtains geographic information of its current location. Typically, it uses GPS functionality to obtain latitude and longitude from location services. The output of this step is a pair of location data (latitude and longitude).

[0542] Step 3:

[0543] A request containing text data and location data is sent from the terminal to the server. The server receives this request and stores the data. The output of this step is the user input data stored in the database on the server.

[0544] Step 4:

[0545] The server uses a generative artificial intelligence model to evaluate the reliability of the text data. The AI ​​model (e.g., a model using TensorFlow or PyTorch) analyzes the context of the text using natural language processing techniques and generates a confidence score as output. The output of this step is the confidence score.

[0546] Step 5:

[0547] Simultaneously, the server uses an emotion analysis engine to detect emotions from the text data. The engine analyzes the emotional significance of the text and outputs the relevant emotion categories (e.g., urgency, fear, relief, etc.) as numerical data. The output of this step is the emotion score.

[0548] Step 6:

[0549] The server applies an algorithm to determine the priority of emergency information based on the obtained trust and sentiment scores. Based on the priority, it generates a result indicating whether or not to provide information to the relevant agencies. The output of this step is a notification request to the relevant agencies if notification is required.

[0550] Step 7:

[0551] The server sends a notification to the relevant agencies. The notification is sent automatically via the API, allowing the agencies to begin responding quickly. The output of this step is the sent notification and any possible responses from the agencies.

[0552] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0553] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0554] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0555] [Fourth Embodiment]

[0556] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0557] As shown in Figure 7, the 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.

[0558] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0559] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0560] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0561] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0562] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0563] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0564] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0565] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0566] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0567] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0568] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0569] This invention provides a specific model for implementing a system that efficiently analyzes information received during a disaster and provides only reliable information to the response organization. First, the user inputs disaster information using a communication terminal. At this time, the terminal automatically acquires geographical information and sends it to the server along with the information entered by the user. The server verifies and formats this received data and prepares it for storage.

[0570] Next, the server inputs the formatted information into an artificial intelligence (AI) model to evaluate the reliability of the information. This AI model analyzes the linguistic patterns contained in the disaster information text and its degree of relevance to the situation. For location information, the credibility of the report can be verified by comparing it with existing geographic information systems (GIS) and disaster data.

[0571] For example, if a user reports that their home is flooded, the location information obtained from the device is compared with rainfall data for that area on the server. This allows the AI ​​to assist in determining if a flood report is suspicious even though there is no record of rainfall.

[0572] If the evaluation determines that the information is reliable, the server automatically transmits the information to the appropriate agency. This enables an accurate and prompt response. If the information is determined to be highly likely to be false, a warning is sent to the administrator, and further verification and auditing are conducted.

[0573] The usefulness of this system lies in selecting reliable information from a vast amount of data and optimally allocating limited resources. This method is expected to improve the effectiveness and speed of disaster response.

[0574] The following describes the processing flow.

[0575] Step 1:

[0576] The user uses a communication terminal to input and send disaster information in text format. Based on the user's permission, the terminal automatically acquires geographical information and prepares to send this information along with the text to the server.

[0577] Step 2:

[0578] The terminal sends the entered information and any added geographical information to the server. The server verifies the format of the incoming data and checks for syntax errors or incomplete data.

[0579] Step 3:

[0580] The server decodes the received information as needed and formats it into a meaningful form as disaster information. This process includes appropriately identifying location information and text data.

[0581] Step 4:

[0582] The server transfers the formatted information to an artificial intelligence model. The AI ​​model analyzes the text data and evaluates its reliability by comparing it to language patterns and common disaster report formats.

[0583] Step 5:

[0584] The server analyzes location data in conjunction with a Geographic Information System (GIS) to verify whether the reported location was actually affected by the disaster. This step is performed in conjunction with an external disaster database.

[0585] Step 6:

[0586] The server calculates a reliability score for the information based on the evaluation results of the AI ​​model. This score assesses the likelihood that the information is true.

[0587] Step 7:

[0588] The server determines how to process information based on its reliability score. Information with a high score is sent to the appropriate agency, while information with a low score will issue a warning to the administrator and request further verification.

[0589] Step 8:

[0590] Information transmitted from the server is quickly processed by the responding agency, and necessary rescue operations and information sharing are initiated.

[0591] (Example 1)

[0592] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0593] During a disaster, it is crucial to quickly and accurately select reliable information from a vast amount of data and provide it to the appropriate response agencies. Furthermore, identifying false information and taking appropriate countermeasures is also essential. Under these circumstances, the current system faces the challenge of slow response due to the time required for information verification and processing.

[0594] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0595] In this invention, the server includes means for receiving, formatting, and correcting data; means for inputting the formatted data into a generating artificial intelligence model to evaluate its reliability; and means for automatically providing information to the responding agency based on the evaluation results. This enables the rapid and accurate sorting and automatic provision of disaster information to the responding agency.

[0596] A "communication terminal" is a device used by users to input disaster information and is equipped with a function that enables the automatic acquisition of geographical information.

[0597] "Geographic information" refers to data used to identify the location from which the information was provided, and is usually expressed in the form of latitude and longitude.

[0598] A "generative artificial intelligence model" is an algorithm or program used to analyze text data of disaster information and evaluate its reliability.

[0599] "Means for evaluating reliability" refers to processing methods that analyze received data and determine whether the information is accurate and true.

[0600] A "response agency" refers to an organization or department that takes necessary action after receiving disaster information, and begins its activities based on the information provided.

[0601] This invention relates to a system for efficiently analyzing and evaluating the reliability of information during disasters. This system is constructed using a communication terminal, a server, and a generative artificial intelligence model.

[0602] Users input disaster information using a communication terminal. The terminal automatically obtains the user's location information using its built-in GPS function and sends that information to the server. Specifically, for example, a user might input information such as "There is a fire in the neighborhood" and send it to the server along with their location information.

[0603] The server formats the received information and corrects any errors. The formatted information is then input into a generating AI model. This AI model utilizes natural language processing technology to analyze language patterns in the input text and evaluate the reliability of the disaster information. Furthermore, location information is verified for report validity by comparing it with existing geographic and disaster data using a GIS (Geographic Information System).

[0604] For example, if a report states that "the river is overflowing," the AI ​​model evaluates its reliability based on keywords such as "river" and "flooding," and verifies it by referring to location information and the flood history of that area.

[0605] An example of a prompt message to ensure the operation of this system is as follows: "User report: A fire has broken out in the neighborhood. Location: Latitude 35.6895, Longitude 139.6917. Please evaluate the reliability of this information."

[0606] This allows the server to automatically provide information deemed highly reliable to the response agency, enabling a rapid disaster response based on that information. If the information is determined to be potentially false, the server will issue a warning to the administrator, allowing for further verification procedures. In this way, the present invention aims to improve the efficiency and accuracy of disaster response.

[0607] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0608] Step 1:

[0609] The user inputs disaster information using a communication terminal. This input consists of text information related to the disaster. The terminal automatically acquires location information using its built-in GPS function and sends this location information to the server along with the input text. At this stage, the input information consists of the disaster report content and location data. The output is the transmission of information to the server. For example, if the user inputs "There is a fire," the terminal checks its current location and sends the data to the server.

[0610] Step 2:

[0611] The server receives the data. The received information is formatted, and any errors are corrected. For example, the date and time format is standardized, and the accuracy of location information is verified. The input is disaster information and location information sent from the terminal, and the output is data formatted in a standardized format. Specifically, the server converts the date and time to the format "2023-05-15T10:00:00" and re-verifies the location information.

[0612] Step 3:

[0613] The server inputs formatted data into a generating AI model. This model analyzes the language patterns of the input disaster information text and evaluates the reliability of the information. Location information is cross-referenced with a geographic information system to verify its authenticity. The input is formatted disaster report data, and the output is a reliability evaluation score or judgment result. Specifically, the AI ​​detects the language patterns of "fire" and "occurrence," and cross-references the location information with past fire data.

[0614] Step 4:

[0615] The server determines the reliability of the information based on the evaluation results from the generated AI model. If the information is deemed highly reliable, the server automatically provides it to the appropriate agency. If the information is deemed unreliable, it issues a warning to the administrator and initiates further verification procedures. The input is the result of the AI ​​model's reliability evaluation, and the output is the provision of information to the appropriate agency or a warning to the administrator. Specifically, highly reliable information is reported as "Reliability: High" and sent to the appropriate agency, or the administrator is notified as "Warning: Low Reliability."

[0616] (Application Example 1)

[0617] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0618] During a disaster, a large amount of information flows in, but it is difficult to quickly select reliable information from among it. This makes it difficult for response agencies to take immediate and appropriate action, potentially leading to an escalation of damage. To solve this problem, a system is needed that automatically evaluates the reliability of information and promptly notifies only those that are certain.

[0619] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0620] In this invention, the server includes means for receiving data from users who input disaster information using a communication device, means for automatically acquiring location information contained in the data, means for inputting the received data into an artificial intelligence model that generates data and evaluating the reliability of the information, means for determining whether the information is false based on the evaluation, means for providing the information to a response agency according to the reliability of the information, and means for automatically notifying a safety agency based on the reliability of the evaluated information. This makes it possible to appropriately and quickly notify response agencies of reliable disaster information from a vast amount of data.

[0621] A "communication device" is an electronic device used by users to input disaster information and enables the transmission and reception of data.

[0622] "Location information" refers to information used to identify the geographical location included in the data entered by the user, and is automatically acquired using technologies such as GPS.

[0623] An "artificial intelligence model" is a machine learning algorithm or data analysis tool used to analyze received data and evaluate the reliability of that information.

[0624] "Evaluation" is a process for determining the accuracy and reliability of received disaster information, thereby determining whether the information is true or false.

[0625] A "response organization" is an organization or agency that receives information in order to take appropriate action based on disaster information, and is primarily responsible for ensuring safety and mitigating damage.

[0626] A "safety agency" is an organization responsible for taking swift action to protect human lives and property during a disaster.

[0627] The system for realizing this invention consists of multiple communication devices, a server, and an artificial intelligence model to be generated. First, the user inputs disaster information into the communication device. This device is equipped with a location information acquisition function and can automatically acquire accurate geographic information using technologies such as GPS. The acquired disaster information and location information are transmitted to the server via the network.

[0628] The server stores the received data and uses pre-trained generative AI models, such as natural language processing toolkits and machine learning algorithms, to evaluate the reliability of the information. In this evaluation process, the content and location of the information are compared with historical disaster data. Specifically, the server uses GIS to match location data with existing disaster data and verify the degree of consistency of the reported information. Information deemed to have a low probability of being false is promptly provided to the response agency. On the other hand, information that is highly likely to be false undergoes further verification.

[0629] For example, if a user reports that "flooding is occurring at my current location," the system checks for recent weather data to see if there are any records of precipitation. If the weather records do not indicate a possibility of flooding, the AI ​​will deem the report questionable. At the same time, if the information is deemed reliable, safety notices are sent to relevant agencies to quickly take measures to minimize damage.

[0630] An example of a prompt message to input into the generating AI model is: "Evaluate the flood occurrence reported by the user, determine its reliability, and notify the result." This allows the system to receive specific instructions to make appropriate decisions.

[0631] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0632] Step 1:

[0633] On the terminal, the user inputs disaster information. The user reports specific disaster conditions (e.g., flood, earthquake) in text format, and the terminal automatically obtains the current location information using its GPS function. Both the input information and the location information are sent to the server. The input consists of text and location data, and the output is the data sent to the server.

[0634] Step 2:

[0635] The server first performs an initial filter on the received information. Specifically, it checks for abnormal strings and missing location information. An automated script is used for this, removing unformatted data and passing the formatted data to the generating AI model. The input is raw data from the user, and the output is formatted data that fits the AI ​​model.

[0636] Step 3:

[0637] A generative AI model is launched on the server and analyzes the formatted data. The AI ​​compares it with past disaster report data and evaluates the language patterns and degree of similarity of the report content. Furthermore, it guides the evaluation process using prompt sentences. The input is the formatted data, and the output is the reliability assessment result.

[0638] Step 4:

[0639] The server uses GIS to verify location information. It examines the credibility of reported conditions by comparing them with local weather data and disaster history. For example, reported floods are evaluated by directly comparing them with precipitation records. Input is location data, and output is the location verification result.

[0640] Step 5:

[0641] The server integrates information obtained from AI models and GIS to determine the final reliability of the information. If the reliability is high, it prepares to notify the relevant authorities. The notification includes the generated reliability assessment along with instructions on necessary actions. The input is the evaluation results from AI and GIS, and the output is the notification data.

[0642] Step 6:

[0643] The server notifies the response agency of reliable information. The notification system is automated and delivers information via multiple channels (e.g., SMS, email). This enables a rapid response. The input is the notification data, and the output is the delivered notification.

[0644] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0645] This invention describes an embodiment of a disaster information analysis system that incorporates an emotion engine to recognize user emotions when analyzing disaster information entered using a communication terminal. This system begins by automatically acquiring disaster information and related geographical information entered by the user into the terminal and transmitting that data to a server.

[0646] The server uses a generative artificial intelligence (AI) model to evaluate the reliability of the received data. This AI model analyzes text data, examining its linguistic patterns and format to determine its reliability. In addition, an emotion engine detects emotions from the text data entered by the user. This emotion data is used to evaluate the reliability of the information. For example, content entered in a panicked state may be weighted differently from content entered calmly.

[0647] For example, if a user types "Help! My house is flooding," the device sends the message to the server along with its current geographical location. The server's AI evaluates this text from a credibility standpoint, while simultaneously, an emotion engine measures the user's level of urgency. Information deemed highly urgent based on the user's emotion recognition is then evaluated considering this tendency and reflected in the prioritization of response agencies.

[0648] Based on the reliability of the information and the results of sentiment analysis, the server notifies the appropriate agency of the most reliable information. Considering sentiment data also enables the rapid transmission of highly urgent cases to the appropriate agency. This system configuration allows for multifaceted information evaluation, including sentiment analysis, and supports appropriate responses during disasters.

[0649] The following describes the processing flow.

[0650] Step 1:

[0651] The user uses a communication terminal to input and transmit disaster information in text format. The terminal automatically retrieves geographical information about the user's current location and prepares to package it together with the text information.

[0652] Step 2:

[0653] The terminal sends a prepared information package to the server. The server receives the incoming data, verifies its format, and determines whether it can be processed appropriately.

[0654] Step 3:

[0655] The server separates the received data into text information and geographic information. This data is then formatted for analysis by generative artificial intelligence models and sentiment engines.

[0656] Step 4:

[0657] The server inputs text information into an artificial intelligence model that generates text data, analyzes the language patterns of the disaster information, and evaluates its reliability. The AI ​​model measures the accuracy of the information based on the content, wording, and format of the report.

[0658] Step 5:

[0659] In parallel, the server sends text information to the sentiment engine to recognize the user's emotional state. This analysis is based on the tone of the text and words indicating urgency.

[0660] Step 6:

[0661] The server combines reliability assessments obtained from AI models with sentiment data from an emotion engine to calculate an overall information reliability score. The score reflects the truthfulness and urgency of the information.

[0662] Step 7:

[0663] The server decides how to process information based on the calculated reliability score. Information with a high score is quickly provided to the appropriate agency, while information with a low score sends a warning to the administrator for further verification.

[0664] Step 8:

[0665] Responding agencies will take swift action based on reliable information transmitted from the server and prepare to deploy relief operations if necessary. Urgency based on emotional data will also be considered, enabling effective decision-making.

[0666] (Example 2)

[0667] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0668] In collecting and analyzing disaster information, verifying the accuracy of the information and assessing its urgency based on users' emotions are crucial. However, conventional technologies lack mechanisms to integrate and utilize information reliability assessment and user sentiment analysis, which can make rapid and accurate responses difficult. To address this challenge, there is a need to provide an analysis method that simultaneously considers information reliability and users' emotional states.

[0669] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0670] In this invention, the server includes means for receiving data from users who input information using a communication device, means for automatically acquiring location information contained in the data, means for inputting the received data into a machine learning model to evaluate the reliability of the information, means for applying emotion recognition technology to the information to determine the user's emotional state, and means for classifying and providing information based on reliability and emotion analysis. This makes it possible to integrate and utilize information reliability evaluation and emotion analysis, enabling quick and appropriate responses.

[0671] A "communication device" is an electronic device used to send and receive information, and in particular refers to a terminal that allows users to input information and enables data communication.

[0672] "Location information" refers to data that indicates a geographical location, and usually includes coordinate information such as latitude and longitude.

[0673] A "machine learning model" refers to an algorithm or system that allows a computer to learn patterns from large amounts of data and then make predictions or classifications on new data.

[0674] "Information reliability" refers to the criteria used to evaluate whether the information provided is accurate and true.

[0675] "Emotion recognition technology" refers to technology that identifies a person's emotions from data such as text, audio, and images, and clarifies their emotional state.

[0676] "User's emotional state" refers to the mental state a user exhibits when entering information, such as whether they are feeling a sense of urgency or remaining calm.

[0677] "Means of classification and provision" refers to the function or method of classifying evaluated information based on specific criteria and providing it appropriately to the necessary institutions and systems.

[0678] The system in this invention consists of three components: a user, a terminal, and a server. First, the user inputs information related to the disaster using a communication device, such as a smartphone or tablet device. The input information is primarily text-based, but may also include images and audio data in some cases.

[0679] The device automatically acquires location information using its built-in GPS function, along with the entered information. This location information is transmitted to the server via a communication protocol. Specifically, location information is acquired using the Google Maps API, and the data is sent to the server via HTTPS communication.

[0680] The server analyzes the received data using a generative artificial intelligence model. This model utilizes natural language processing technologies, such as OpenAI models, to scrutinize the input text information and evaluate its reliability. Furthermore, sentiment recognition technology is applied to the received text data, using tools like IBM Watson to determine the user's emotional state. This sentiment analysis helps understand the user's sense of urgency and reflects this in the weighting of the information.

[0681] For example, if a user types "Help! My house is flooded," this information and its location data are sent to the server. The server uses an AI model to evaluate the reliability of the text content and an emotion engine to analyze its urgency. As a result, the information is classified as urgent and notified to the appropriate authorities.

[0682] In this system embodiment, an example of a prompt message is used: "My home has been flooded due to heavy rain last night. Please take immediate action." By inputting such a prompt message into the AI ​​model and analyzing the reliability of the information and the emotional state, a rapid response becomes possible.

[0683] This method aims to enable accurate and rapid processing of disaster information, thereby improving the efficiency of responses in emergencies.

[0684] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0685] Step 1:

[0686] Users input disaster information using communication devices. Specifically, they write text messages via smartphone apps or web interfaces, attaching media such as images and audio as needed. The information entered at this stage consists of details of the disaster situation as observed by the user.

[0687] Step 2:

[0688] The device acquires location information along with the information entered by the user. Location information is obtained using the device's built-in GPS function or location services, and the current location is determined using tools such as the Google Maps API. The acquired geographic information and user input information are combined to create a dataset. This dataset becomes the data sent to the server.

[0689] Step 3:

[0690] The device sends the generated dataset to the server. The HTTPS protocol is used for transmission, ensuring secure and rapid data transfer. The transmitted data consists of user text information, location information, and metadata.

[0691] Step 4:

[0692] The server analyzes the received dataset. First, it uses a generative AI model to analyze the text information and evaluate its reliability. The AI ​​model uses natural language processing techniques to analyze text patterns and distinguish meaningful information from noise. The reliability evaluation results are then output.

[0693] Step 5:

[0694] The server applies sentiment recognition technology to the received text information. The sentiment engine analyzes the text content and identifies the user's emotional state—for example, urgency or fear. The output of the sentiment analysis serves as supplementary data that influences the reliability evaluation.

[0695] Step 6:

[0696] The server classifies information based on the output of reliability assessments and sentiment analysis. Based on the analysis results, it prioritizes the information and generates notification data for the appropriate response agency. This classification process ensures that important information is processed more quickly and appropriately.

[0697] Step 7:

[0698] The generated notification data is sent from the server to the appropriate agency. High-priority information is automatically notified to the emergency response department, enabling immediate action. The output data includes details and suggestions to identify necessary actions.

[0699] (Application Example 2)

[0700] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0701] Conventional disaster information systems had limitations in judging the accuracy of received information, particularly in their inability to consider the emotions of the information senders, and thus in their inability to accurately assess the urgency of the information. Furthermore, there were challenges in detecting false information and rapidly disseminating highly urgent information.

[0702] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0703] In this invention, the server includes means for receiving data from a user who inputs emergency information using a communication device, means for automatically acquiring location information contained in the data, means for inputting the received data into a generating artificial intelligence model to evaluate the accuracy of the information, means for detecting emotions from the user's input data using an emotion analysis engine, and means for providing the information to relevant organizations according to the accuracy of the information and the emotion data. By combining the accuracy of the information with the user's emotion information, it becomes possible to determine false information and provide information quickly based on priority.

[0704] "Communication equipment" is a general term for hardware and software that directly receives emergency information from users and processes the data.

[0705] "Location information" refers to geographical data about the location where the user entered emergency information, and is usually obtained through GPS or geographic information systems.

[0706] A "generative artificial intelligence model" refers to a collection of algorithms and software that use natural language processing and machine learning to evaluate data in order to determine the accuracy of received information.

[0707] An "emotion analysis engine" is an analytical technology that detects emotions from the user's input data and outputs the results as numerical values ​​or categories.

[0708] "Providing to relevant organizations" refers to the operation or process of transmitting the analyzed information to various relevant agencies and organizations at the appropriate time.

[0709] To implement this invention, a system is constructed that allows users to input emergency information using a communication terminal. This system includes a process for rapidly analyzing the received data and providing the information to relevant organizations as needed.

[0710] The server receives data entered by the user from their communication terminal and automatically acquires location information. This allows for understanding the geographical context of the location where the emergency occurred.

[0711] The received data is evaluated for accuracy using a generative artificial intelligence model. The AI ​​model uses natural language processing technology to analyze the content of the information and determine its reliability.

[0712] Furthermore, an emotion analysis engine detects emotions from the user's input data. This engine numerically or categorically evaluates the emotional nuances of the input text and voice data, and uses the results to assess urgency.

[0713] Considering the accuracy of the information and the detected sentiment data, the server provides the information to the relevant organizations. This allows for priority responses based on the urgency of the information.

[0714] For example, if a user voice-inputs "There is a fire. Please help," the server instantly converts this into text data, and an AI model evaluates its accuracy. Furthermore, an emotion analysis engine evaluates the user's emotions as a high level of urgency, enabling rapid notification to the fire department.

[0715] An example of a prompt for a generative AI model is: "Please describe in detail a method for analyzing urgent voice input from a user and evaluating its sentiment and trustworthiness."

[0716] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0717] Step 1:

[0718] The user enters emergency information using a communication terminal. This input can be in text or voice format. In the case of voice input, the terminal uses a speech recognition API (e.g., Google Cloud Speech-to-Text) to convert it to text. The output of this step is text data.

[0719] Step 2:

[0720] The device automatically obtains geographic information of its current location. Typically, it uses GPS functionality to obtain latitude and longitude from location services. The output of this step is a pair of location data (latitude and longitude).

[0721] Step 3:

[0722] A request containing text data and location data is sent from the terminal to the server. The server receives this request and stores the data. The output of this step is the user input data stored in the database on the server.

[0723] Step 4:

[0724] The server uses a generative artificial intelligence model to evaluate the reliability of the text data. The AI ​​model (e.g., a model using TensorFlow or PyTorch) analyzes the context of the text using natural language processing techniques and generates a confidence score as output. The output of this step is the confidence score.

[0725] Step 5:

[0726] Simultaneously, the server uses an emotion analysis engine to detect emotions from the text data. The engine analyzes the emotional significance of the text and outputs the relevant emotion categories (e.g., urgency, fear, relief, etc.) as numerical data. The output of this step is the emotion score.

[0727] Step 6:

[0728] The server applies an algorithm to determine the priority of emergency information based on the obtained trust and sentiment scores. Based on the priority, it generates a result indicating whether or not to provide information to the relevant agencies. The output of this step is a notification request to the relevant agencies if notification is required.

[0729] Step 7:

[0730] The server sends a notification to the relevant agencies. The notification is sent automatically via the API, allowing the agencies to begin responding quickly. The output of this step is the sent notification and any possible responses from the agencies.

[0731] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0732] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0733] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0734] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0735] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0736] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0737] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0738] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0739] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0740] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0741] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0742] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0743] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0744] 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.

[0745] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0746] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0747] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0748] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0749] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0750] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0751] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0752] The following is further disclosed regarding the embodiments described above.

[0753] (Claim 1)

[0754] A means of receiving data from users who input disaster information using a communication terminal,

[0755] A means for automatically acquiring geographic information contained in the data,

[0756] A means for inputting received data into a generating artificial intelligence model and evaluating the reliability of that information,

[0757] A means of determining whether information is false based on evaluation,

[0758] Means for providing the information to the appropriate organization according to the reliability of the information,

[0759] A disaster information analysis system that includes this.

[0760] (Claim 2)

[0761] A disaster information analysis system according to claim 1, which analyzes disaster information received from users in conjunction with existing disaster data.

[0762] (Claim 3)

[0763] The disaster information analysis system according to claim 1, which automatically notifies the emergency response department based on the reliability of the evaluated information.

[0764] "Example 1"

[0765] (Claim 1)

[0766] A means of receiving data from users who input disaster information using a communication terminal,

[0767] A means for automatically acquiring geographic information contained in the data,

[0768] A means to format the received data and correct any defects,

[0769] A means for inputting formatted data into an artificial intelligence model and evaluating the reliability of that information,

[0770] A means of determining whether information is reliable based on evaluation,

[0771] A means of automatically providing the information to the appropriate agency according to the reliability of the information,

[0772] A means of issuing a warning to the administrator when there is a high probability that the information is false,

[0773] A system that includes this.

[0774] (Claim 2)

[0775] The system according to claim 1, which analyzes disaster information received from users in conjunction with geographic information and existing disaster data.

[0776] (Claim 3)

[0777] The system according to claim 1, which automatically notifies the appropriate agency based on the reliability of the evaluated information.

[0778] "Application Example 1"

[0779] (Claim 1)

[0780] A means for receiving data from users who input disaster information using a communication device,

[0781] A means for automatically acquiring location information contained in the data,

[0782] A means of inputting received data into an artificial intelligence model that generates data, and evaluating the reliability of that information,

[0783] A means of determining whether information is false based on evaluation,

[0784] Means for providing the information to the responding organization according to the reliability of the information,

[0785] A means of automatically notifying safety authorities based on the reliability of the evaluated information,

[0786] An information analysis system that includes this.

[0787] (Claim 2)

[0788] The system according to claim 1, which analyzes disaster information received from users in conjunction with an existing disaster database.

[0789] (Claim 3)

[0790] The system according to claim 1, which promptly notifies a response agency of highly reliable information.

[0791] "Example 2 of combining an emotion engine"

[0792] (Claim 1)

[0793] A means for receiving data from users who input information using a communication device,

[0794] A means for automatically acquiring location information contained in the data,

[0795] A means of inputting received data into a machine learning model and evaluating the reliability of that information,

[0796] A means for determining the user's emotional state by applying emotion recognition technology to the information,

[0797] A means of classifying and providing information based on reliability and sentiment analysis,

[0798] A system that includes this.

[0799] (Claim 2)

[0800] The system according to claim 1, which analyzes information received from users in conjunction with existing data.

[0801] (Claim 3)

[0802] The system according to claim 1, which automatically notifies the relevant department based on the results of reliability and sentiment analysis.

[0803] "Application example 2 when combining with an emotional engine"

[0804] (Claim 1)

[0805] A means for receiving data from users who input emergency information using a communication device,

[0806] A means for automatically acquiring location information contained in the data,

[0807] A means of inputting received data into a generating artificial intelligence model and evaluating the accuracy of that information,

[0808] A means of determining whether information is false based on evaluation,

[0809] A means of detecting emotions from user input data using an emotion analysis engine,

[0810] Means for providing such information to relevant organizations in accordance with the accuracy and sentiment data of the information,

[0811] A system that includes this.

[0812] (Claim 2)

[0813] The system according to claim 1, which analyzes emergency information received from users in conjunction with existing disaster data and evaluates it, including emotional data.

[0814] (Claim 3)

[0815] The system according to claim 1, which automatically provides priority notification to the emergency response department based on the accuracy and sentiment data of the evaluated information. [Explanation of Symbols]

[0816] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of receiving data from users who input disaster information using a communication terminal, A means for automatically acquiring geographic information contained in the data, A means for inputting received data into a generating artificial intelligence model and evaluating the reliability of that information, A means of determining whether information is false based on evaluation, Means for providing the information to the appropriate organization according to the reliability of the information, A disaster information analysis system that includes this.

2. A disaster information analysis system according to claim 1, which analyzes disaster information received from users in conjunction with existing disaster data.

3. The disaster information analysis system according to claim 1, which automatically notifies the emergency response department based on the reliability of the evaluated information.

Images