system

Abstract

We provide the system. [Solution] Message acquisition method, A means of classifying the acquired messages into categories, A means for evaluating the reliability of classified messages, A means of setting the priority of evaluated messages, A means of distributing information based on priority, A system that includes this.

Description

Technical Field

[0005]

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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 a disaster, in order to search for unknown people and pets quickly and surely, it is required to efficiently process a lot of information and identify highly reliable information. However, in the current method, the scrutiny and prioritization of information are entrusted to humans, and there are problems that inaccurate information and confusion are likely to occur. In addition, since there is a lack of a mechanism for preventing the spread of false information, it is difficult to contribute to improving the reliability of information.

Means for Solving the Problems

[0005] This invention solves these problems by providing a system equipped with message acquisition means, category classification means, reliability evaluation means, priority setting means, and information distribution means. By automatically classifying acquired messages and evaluating their reliability, misinformation can be effectively identified. Furthermore, by setting priorities for each piece of information, important information can be quickly distributed to relevant parties. Through such means, it is possible to provide rapid and accurate information during disasters and efficiently support the search for missing persons and pets.

[0006] "Message acquisition means" refers to a method or apparatus for collecting messages from messaging applications or other means of communication.

[0007] "Category classification means" refers to a method or apparatus for organizing acquired messages into categories based on pre-set criteria.

[0008] A "reliability evaluation means" is a method or apparatus for verifying the truthfulness of collected information and measuring its reliability.

[0009] "Priority setting means" refers to a method or apparatus for determining the order of processing or distribution of information based on its importance or urgency.

[0010] "Information distribution means" refers to a method or device for delivering information, organized according to priority, to the recipients or users who need it. [Brief explanation of the drawing]

[0011] [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] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4]This 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] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This 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] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This 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] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0012] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0013] First, let's explain the terminology used in the following explanation.

[0014] In the following embodiments, the labeled 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.

[0015] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0016] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. 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.

[0017] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. 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).

[0018] 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."

[0019] [First Embodiment]

[0020] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0021] 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.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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.

[0027] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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".

[0032] This invention is a system that enables rapid and accurate information distribution during disasters. This system revolves around three main roles: server, terminal, and user, which perform information acquisition, classification, evaluation, and distribution.

[0033] First, the server automatically retrieves messages from messaging applications and related communication methods using APIs. The collected messages are analyzed using natural language processing techniques and classified into categories based on predetermined criteria.

[0034] Next, the server uses a generated AI model to evaluate the reliability of the collected information. This allows it to identify misinformation and duplicate information and prioritize it based on its reliability.

[0035] The information processed through this mechanism is then distributed from the server to each terminal. Users receive the information on their terminals and can take quick and appropriate action based on the provided information. Because the distributed information is customized to the user's location and individual needs, optimal information is provided to each user.

[0036] As a concrete example, consider a scenario where a large-scale disaster occurs and many people and pets go missing. In this system, users post information about missing people and pets using their smartphones. A server collects this information, evaluates its reliability by comparing it with other related posts, and aggregates similar information.

[0037] Subsequently, the server prioritizes the most reliable information and quickly delivers the most useful information. Based on this information, users on terminals can grasp specific locations and situations, enabling them to conduct search and rescue operations more efficiently. In this way, the system of the present invention optimizes the flow of information during disasters, supporting accurate decision-making and rapid action.

[0038] The following describes the processing flow.

[0039] Step 1:

[0040] The server automatically retrieves newly posted messages in real time from messaging applications via API. These messages include author information, message body, and timestamp.

[0041] Step 2:

[0042] The server analyzes the messages it receives using natural language processing techniques to extract keywords. Based on these keywords, the messages are classified into categories such as "searching for a person" or "searching for a pet."

[0043] Step 3:

[0044] The server searches the database for other messages with similar content and evaluates the truthfulness of the information through cross-referencing. A generative AI model is used to calculate a confidence score.

[0045] Step 4:

[0046] The server prioritizes information based on its reliability score. Information that is urgent and highly reliable is given a higher priority.

[0047] Step 5:

[0048] The server prioritizes and delivers information to the appropriate user groups or individual devices. This may involve using push notifications or dedicated dashboards.

[0049] Step 6:

[0050] Users receive the distributed information and take the necessary actions. If users provide feedback, the server collects it and uses it as data to further improve the reliability of the information.

[0051] (Example 1)

[0052] 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."

[0053] During a disaster, it is extremely difficult to quickly, accurately, and reliably obtain reliable information from a vast amount of data and provide it to individual users according to their needs. The dissemination of incorrect or redundant information can hinder appropriate judgment and action. This invention aims to provide a system that efficiently solves these problems.

[0054] 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.

[0055] In this invention, the server includes means for acquiring messages, means for classifying acquired messages into categories using natural language processing technology, and means for evaluating the reliability of the classified messages using a generative artificial intelligence model. This enables the rapid acquisition of highly reliable information during disasters and the provision of information tailored to the needs of each user.

[0056] A "message acquisition method" is a system for automatically collecting disaster-related information from communication methods and information sources.

[0057] "Natural language processing technology" is a technology that allows computers to understand and analyze human language, and provides functions for classifying and summarizing text.

[0058] A "generative artificial intelligence model" is a technology that analyzes data based on machine learning and evaluates the reliability of the information.

[0059] "A means of setting priorities and customizing information based on user location and individual needs" refers to a system that ranks information according to its importance and provides information optimized for each individual user.

[0060] An "interactive display device" is a device that allows users to receive and interact with information, such as a smartphone or tablet.

[0061] A description of embodiments for carrying out the present invention will be provided.

[0062] The server acquires real-time data through messaging services and SNS APIs for information gathering during disasters. To maintain the volume of information and real-time capabilities, it is recommended that the server use load balancing technology and cloud computing services. Specifically, platforms such as AWS® Lambda and Google® Cloud Functions are available.

[0063] The collected data is analyzed on the server using natural language processing (NLP) techniques. Libraries such as Python's NLTK and SpaCy are used to classify the information into specific categories and determine its importance and urgency as needed. At this stage, machine learning models are pre-trained to improve classification accuracy.

[0064] Next, the server uses a generative AI model to evaluate the reliability of the acquired information. During this process, the generative AI model is prompted with the question, "Which other sources does this information match?" to check the consistency of the information. By analyzing the output of the generative AI model in response to this prompt, misinformation and duplicate information are identified, and highly reliable information is prioritized.

[0065] Reliable information is optimized based on the user's location and specific needs, and delivered to their device. This customized information is displayed on the user's interactive display device (such as a smartphone or tablet). Based on this information, the user can make quick and effective decisions.

[0066] As a concrete example, in the event of a major earthquake, users can post their situation via a messaging service. This information is collected and analyzed by a server, cross-referenced with other relevant information, and then provided to users according to its accuracy and urgency. This allows each user to quickly choose appropriate actions to ensure their own safety and the safety of their family.

[0067] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0068] Step 1:

[0069] The server retrieves data in real time through messaging service and SNS APIs. It receives raw message data from external sources as input and stores it in its internal system. Specifically, it interprets the retrieved data packets and stores each data item in a database along with a unique identifier. This data includes information about the type and location of the disaster.

[0070] Step 2:

[0071] The server analyzes the acquired messages using natural language processing techniques and classifies them into categories. Messages stored in a database are used as input. The output generates data where messages are classified into specific disaster categories (e.g., earthquake, flood). Specifically, it applies text analysis algorithms to automatically classify messages based on keywords and context.

[0072] Step 3:

[0073] The server evaluates the reliability of classified messages using a generative AI model. The input is messages classified by category. The output is a calculated reliability score for each message. Specifically, the generative AI model is prompted with the question, "Which other sources does this information match?", and the model's evaluation results are analyzed.

[0074] Step 4:

[0075] The server prioritizes messages based on their reliability scores and creates customized information tailored to the user's location and individual needs. The input consists of messages with reliability scores and user profile information. The output generates a prioritized information set for each user. Specifically, it uses an algorithm to compare scores and sorts the information based on its importance.

[0076] Step 5:

[0077] The terminal receives customized information and notifies the user. It receives a prioritized set of information sent from the server as input. As output, it generates specific action recommendations that are displayed on the user interface. As specific action, it dynamically displays information on an interactive display device, visually highlighting information important to the end user.

[0078] (Application Example 1)

[0079] 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."

[0080] In disasters and security-related emergencies, the speed and accuracy of information acquisition and distribution are crucial. However, the ease with which misinformation spreads and the risk of inappropriate decision-making based on unreliable information are significant challenges. Furthermore, the lack of effective information provision tailored to individual user needs makes it difficult to respond quickly to specific situations.

[0081] 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.

[0082] In this invention, the server includes means for acquiring messages, means for classifying acquired messages into categories, means for evaluating the reliability of the classified messages, means for setting priorities for the evaluated messages, means for distributing information based on the priorities, means for notifying the user of information based on location information, and means for customizing notifications based on the user's individual settings. This enables rapid and reliable information distribution, allowing users to take the most appropriate action based on their situation.

[0083] A "message acquisition method" is a function for automatically collecting information transmitted and received through a communication network.

[0084] "Means of categorization" refers to the process of classifying and organizing collected information based on pre-established criteria.

[0085] "Means of evaluating reliability" refers to processes that use generative AI models or other technologies to determine the accuracy and credibility of information.

[0086] A "means of setting priorities" is a function for ranking the importance and urgency of information based on evaluated information.

[0087] "Means of distributing information" refers to a system for sending prioritized information to a user's device.

[0088] "Location-based notification methods" refer to functions that select and deliver highly relevant information based on the user's current location.

[0089] "Means for customizing notifications" refers to a mechanism for adjusting and providing information delivered according to the user's individual settings and interests.

[0090] The system implementing this invention mainly consists of three elements: a server, a terminal, and a user. The server acquires messages via a communication network and analyzes and evaluates the collected information using natural language processing and generative AI models. Specifically, the server uses an API as a means of acquiring messages and automatically collects them. Next, the collected messages are classified into categories based on pre-set criteria and their reliability is evaluated. In this process, libraries such as spaCy can be used for natural language processing, and generative AI models such as GPT-3 (registered trademark) can be used for reliability evaluation.

[0091] The device receives information distributed from the server and notifies the user. Notifications are based on location information, and further customized information is provided. This allows the user to choose the optimal action based on their current location and individual needs. This supports quick and appropriate decision-making.

[0092] For example, if a security incident occurs in a region, this system can quickly deliver information to the user's smartphone, allowing the user to enhance their vigilance by checking the alert.

[0093] An example of a prompt message is: "Please provide the latest security-related information based on the user's location. Also, evaluate the reliability of each piece of information and notify the most important ones first." Based on this prompt, appropriate information tailored to the user's individual needs will be provided.

[0094] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0095] Step 1:

[0096] The server automatically collects disaster and security-related messages using a message retrieval API over the communication network. In this process, raw data is received from the API as input, and pre-processed raw message data is generated as output.

[0097] Step 2:

[0098] The server applies natural language processing to the collected messages and classifies them into categories based on pre-defined criteria. The input is the raw message data obtained in step 1, and the output is message data organized by category. Specifically, topic modeling using tools such as spaCy is performed.

[0099] Step 3:

[0100] The server evaluates the reliability of messages classified using a generative AI model. The input is categorized message data, and the output is data with a reliability score. In this process, generative AI such as GPT-3 is used to assess reliability using prompt messages.

[0101] Step 4:

[0102] The server sets the priority of each message based on the reliability evaluation results. The input is the message data whose reliability was evaluated in step 3, and the output is a list of messages with assigned priorities. Here, scoring is performed considering urgency and reliability.

[0103] Step 5:

[0104] The server generates warning notifications based on priority and prepares them for delivery to terminals. The input is a prioritized list of messages, and the output is notification data ready for delivery. Here, the data is converted to a notification format suitable for the criteria.

[0105] Step 6:

[0106] The device receives warning notifications from the server and displays the most appropriate notification based on the user's location. The input is notification data from the server, and the output is a location-based warning presented to the user.

[0107] Step 7:

[0108] Users review notifications received on their devices and provide feedback as needed. Input is the notification information presented by the device, while output is the user's actions and feedback reflected in the system. This feedback is used for subsequent reliability evaluations and customization.

[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 relates to a system that performs information processing that takes into account not only the collection, classification, and distribution of information during disasters, but also the emotions of the user. In particular, by incorporating an emotion engine, this system realizes a new dimension of processing that analyzes the user's emotions.

[0111] First, the server retrieves messages related to the disaster area from messaging applications. This process is carried out by collecting messages in real time using existing APIs. The collected messages are analyzed using natural language processing technology. Based on the analysis results, the server classifies the messages into categories such as "searching for a person" or "searching for a pet."

[0112] Next, the server uses an emotion engine to analyze the emotions contained in the user's post. Emotion analysis is used to understand the nuances and emotional state of the user's statements, which allows for the assessment of stress and urgency during a disaster.

[0113] Furthermore, the server uses the emotions recognized by the emotion engine to evaluate the reliability of information and adjust its priority. For example, if the poster indicates a high level of tension or anxiety, the urgency of the message can be increased, allowing for a quicker response.

[0114] The organized information is then distributed from the server to the terminal. On the terminal, the user can receive and use the information in a format suitable for them. Since it also includes emotionally responsive feedback, it functions as part of user care and support.

[0115] As a concrete example, consider a scenario where a user posts a request to search for a missing pet in a disaster area. The message posted by the user may contain emotions such as "worry" or "sadness." The server's emotion engine detects these emotions and sets the urgency of the search to a higher level. This information is quickly delivered to the user on their device, allowing them to conduct efficient search operations based on that information.

[0116] Through this process, the system aims to improve the overall effectiveness of search and rescue operations by enabling the appropriate allocation of resources and psychological support during disasters.

[0117] The following describes the processing flow.

[0118] Step 1:

[0119] The server uses the messaging application's API to collect new messages related to the disaster. This allows data such as the poster's information, message body, and posting time to be collected.

[0120] Step 2:

[0121] The server analyzes the collected messages using natural language processing technology and classifies them into categories such as "searching for a person" or "searching for a pet" based on the extracted keywords.

[0122] Step 3:

[0123] The server uses an emotion engine to perform sentiment analysis on each message. It extracts emotions such as "tension," "anxiety," and "sadness" from the user's statements to understand their emotional tendencies.

[0124] Step 4:

[0125] The server reviews the urgency and importance of messages based on the analysis results from the emotion engine, and adjusts their priority. Messages that express strong emotions are given a particularly high priority.

[0126] Step 5:

[0127] The server delivers information, organized according to priority, to the relevant devices. It provides users with the information they need as needed through push notifications and dashboards.

[0128] Step 6:

[0129] The system receives information distributed to users and responds promptly. User feedback is sent to the server and used to improve the accuracy of information throughout the system.

[0130] Step 7:

[0131] The server analyzes user feedback and incorporates it into new information gathering, reliability evaluation, and sentiment analysis, thereby continuously improving the functionality of the disaster relief system.

[0132] (Example 2)

[0133] 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".

[0134] During a disaster, it is difficult to quickly and accurately extract important information from the vast amount of data generated, prioritize it appropriately, and distribute it effectively. Furthermore, there is a need to provide information that is sensitive to user emotions and to identify misinformation, but conventional systems do not adequately meet these requirements.

[0135] 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.

[0136] In this invention, the server includes means for acquiring messages, means for analyzing acquired messages using natural language processing technology and classifying them into categories, means for analyzing the emotions contained in posts and determining their urgency, means for evaluating the reliability of messages classified based on the analyzed emotions and setting priorities, and means for distributing information to terminals based on the priorities and providing feedback information that corresponds to the emotions. This enables the rapid extraction of important information during disasters and the provision of information that takes into account the user's emotions.

[0137] "Message acquisition means" refers to processes and devices for collecting relevant information in real time during a disaster, and primarily includes the function of acquiring data through communication means.

[0138] "Natural language processing technology" refers to the technology that enables computers to understand, interpret, and manipulate human language, and is primarily used for analyzing and classifying text data.

[0139] "Sentiment analysis" is a technology that extracts emotional nuances from text data to determine the user's emotional state, and it functions as a factor in evaluating the urgency and importance of a post.

[0140] "Means of evaluating reliability" refer to criteria and methods for judging the accuracy and reliability of information, and are primarily processes that take into account sentiment analysis and past data.

[0141] "Methods for setting priorities" refers to the process of organizing collected information based on its importance and urgency, and determining the order in which it will be distributed.

[0142] "Means of distributing information" refers to the mechanisms and methods for delivering organized information to a user's device, primarily through communication networks.

[0143] "Feedback information" refers to evaluation and support information provided to users, particularly information based on sentiment analysis to encourage appropriate responses.

[0144] This invention is a system that collects, classifies, and distributes information during disasters, and also processes information while considering the user's emotions. The server uses existing APIs to retrieve disaster-related messages from messaging applications via a communication network. Message collection includes platforms such as Twitter and LINE.

[0145] The server uses natural language processing libraries such as Python's NLTK and spaCy to analyze and categorize the received messages. This analysis classifies the messages into categories such as "searching for a person" or "searching for a pet."

[0146] The server also uses an emotion engine to extract emotions from text data. Sentiment analysis utilizes emotion analysis tools such as Microsoft® Azure® Text Analytics API and Google Cloud's Natural Language API. This classifies the emotions contained in posts into categories such as "joy," "sadness," and "anxiety," and reliability evaluations and prioritization are performed based on the results.

[0147] The organized information is delivered from the server to the terminal. On the terminal, the user can receive the information via a dedicated application or web browser, and feedback information tailored to the urgency of the situation is also provided. Based on this information, the user can take a quick and efficient response.

[0148] For example, if a request to search for a missing pet in a disaster area is posted, the server analyzes the message and detects emotions such as "worry" and "sadness." Based on this emotion analysis, the urgency level is set to high, and the information is quickly delivered to the user on their device. This process allows users to conduct search activities efficiently.

[0149] An example of a prompt might be: "Please explain the message sentiment analysis process for disaster information gathering systems."

[0150] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0151] Step 1:

[0152] The server retrieves messages related to disaster areas from messaging applications. The input is real-time message data, which is retrieved via a communication API. The output is raw message data stored in a database or memory. Specifically, the system periodically sends requests through an existing API (e.g., the Twitter API) to retrieve messages and write them to storage.

[0153] Step 2:

[0154] The server analyzes the messages it receives using natural language processing techniques and classifies them into categories. The input is collected message data located in a database or memory. This data is tokenized using Python's natural language processing libraries (NLTK or spaCy), and important keywords are extracted. The output is message data with categories added. Specifically, the server analyzes each message and automatically classifies them into categories such as "searching for a person" or "searching for a pet."

[0155] Step 3:

[0156] The server analyzes the emotions contained in the messages. The input is a message with categories attached, and an emotion analysis tool (e.g., Microsoft Azure's Text Analytics API) is applied to this data. The output is message data with emotion scores attached. Specifically, the server adds emotion categories such as "joy" and "anxiety" to the messages based on the emotion analysis results.

[0157] Step 4:

[0158] The server evaluates the reliability and prioritizes classified messages based on sentiment analysis. The input is message data with sentiment scores. Using this data, it executes logic to analyze the reliability of the information and determine its priority. The output is a list of messages with assigned priorities. Specifically, the server evaluates urgency and the reliability of the information, and if a message indicates high urgency, its priority is increased.

[0159] Step 5:

[0160] The system delivers information from the server to the terminal and provides emotionally responsive feedback. The input is a prioritized list of messages. The output is the information and feedback data delivered to the user's terminal. Specifically, the server sends organized information to the terminal as push notifications or emails, and the user receives the information in an appropriate format. This allows users to quickly take necessary actions during a disaster.

[0161] (Application Example 2)

[0162] 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 device 14 will be referred to as the "terminal."

[0163] During disasters, information becomes chaotic, making it difficult to immediately determine which information is urgent. Furthermore, there is a lack of information provision that considers users' emotions, resulting in inadequate care and support for users who are feeling anxious.

[0164] 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.

[0165] In this invention, the server includes means for acquiring messages, means for classifying acquired messages into categories, and means for analyzing the sentiment of the messages. This makes it possible to prioritize the delivery of information that is of high urgency, taking into account the user's emotions. It also enables the provision of emotionally supportive information tailored to the user.

[0166] "Means of acquiring messages" refers to the function of collecting disaster-related text data in real time via a communication network.

[0167] "Category classification" refers to a function that organizes acquired messages based on specific criteria, categorized by themes such as "searching for people" or "shortage of supplies."

[0168] "Methods for analyzing emotions" refer to technologies that analyze the text of a message to quantify or qualitatively determine the sender's emotions and sensibilities.

[0169] The "means of setting urgency" refer to a function that dynamically determines the importance and priority of a message based on information obtained through sentiment analysis.

[0170] "Means of distributing information" refers to a system that effectively and quickly transfers information to relevant users and devices according to the set level of urgency.

[0171] In implementing this invention, the server first collects disaster-related messages in real time via a communication network. Existing messaging APIs can be used for this purpose, and the data is aggregated on the server. Subsequently, the server uses natural language processing technology to analyze the messages as text data and classify each message into categories such as "search for people" or "shortage of supplies." In this process, the Google Cloud Natural Language API is utilized to achieve rapid and accurate analysis.

[0172] Subsequently, the server uses an emotion analysis engine to quantify or qualitatively determine the user's emotions from the retrieved messages. This emotion analysis uses emotion analysis software such as SentiStrength. Based on the analysis results, the server sets the urgency of the message. In doing so, it considers the intensity and type of emotion to identify information that should be addressed as a priority.

[0173] Ultimately, the server quickly delivers information to user terminals according to the configured urgency level. This allows users to receive information relevant to their situation and take appropriate action. For example, if a user in a flood-affected area posts a message based on "anxiety" and "fear," that information is quickly distributed to nearby residents, who are then guided to safe evacuation locations.

[0174] As a concrete example, a prompt message could read, "An evacuation order has been issued due to flooding. If you are feeling anxious, please find the following resources to help alleviate your worries." In this way, by adjusting the content of the messages based on the user's emotions, it is possible to provide appropriate care to the user.

[0175] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0176] Step 1:

[0177] The server acquires disaster-related messages via a communication network. It uses data received in real time from a messaging platform as input. The output is unanalyzed message data stored in the server's data storage. This operation aggregates information from the field during a disaster.

[0178] Step 2:

[0179] The server uses natural language processing technology to analyze the text data of the acquired messages. The input is the message data saved in the previous step. The output is the category information of the analyzed messages. By classifying them into categories such as "searching for people" or "shortage of supplies," the messages are organized based on their content.

[0180] Step 3:

[0181] The server uses an emotion analysis engine to analyze the user's emotions from the message. The input is the text data of the analyzed message, and the output is emotion data that has been quantified or qualitatively determined. In this step, software such as SentiStrength is used to determine the user's emotional state.

[0182] Step 4:

[0183] The server sets the urgency level of a message based on the sentiment analysis results. The input is the analyzed sentiment data, and the output is a numerical value or indicator of urgency. For example, if anxiety or fear is strong, a high urgency level will be set. This operation contributes to prioritizing information.

[0184] Step 5:

[0185] The server delivers information to terminals according to the configured urgency level. Input consists of messages and category information with set urgency levels, while output is push notifications and alerts delivered to the user's terminal. This allows users to quickly and accurately obtain information and take appropriate action.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] [Second Embodiment]

[0190] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0191] 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.

[0192] 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).

[0193] 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.

[0194] 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.

[0195] 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).

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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".

[0202] This invention is a system that enables rapid and accurate information distribution during disasters. This system revolves around three main roles: server, terminal, and user, which perform information acquisition, classification, evaluation, and distribution.

[0203] First, the server automatically retrieves messages from messaging applications and related communication methods using APIs. The collected messages are analyzed using natural language processing techniques and classified into categories based on predetermined criteria.

[0204] Next, the server uses a generated AI model to evaluate the reliability of the collected information. This allows it to identify misinformation and duplicate information and prioritize it based on its reliability.

[0205] The information processed through this mechanism is then distributed from the server to each terminal. Users receive the information on their terminals and can take quick and appropriate action based on the provided information. Because the distributed information is customized to the user's location and individual needs, optimal information is provided to each user.

[0206] As a concrete example, consider a scenario where a large-scale disaster occurs and many people and pets go missing. In this system, users post information about missing people and pets using their smartphones. A server collects this information, evaluates its reliability by comparing it with other related posts, and aggregates similar information.

[0207] Subsequently, the server prioritizes the most reliable information and quickly delivers the most useful information. Based on this information, users on terminals can grasp specific locations and situations, enabling them to conduct search and rescue operations more efficiently. In this way, the system of the present invention optimizes the flow of information during disasters, supporting accurate decision-making and rapid action.

[0208] The following describes the processing flow.

[0209] Step 1:

[0210] The server automatically retrieves newly posted messages in real time from messaging applications via API. These messages include author information, message body, and timestamp.

[0211] Step 2:

[0212] The server analyzes the messages it receives using natural language processing techniques to extract keywords. Based on these keywords, the messages are classified into categories such as "searching for a person" or "searching for a pet."

[0213] Step 3:

[0214] The server searches the database for other messages with similar content and evaluates the truthfulness of the information through cross-referencing. A generative AI model is used to calculate a confidence score.

[0215] Step 4:

[0216] The server prioritizes information based on its reliability score. Information that is urgent and highly reliable is given a higher priority.

[0217] Step 5:

[0218] The server prioritizes and delivers information to the appropriate user groups or individual devices. This may involve using push notifications or dedicated dashboards.

[0219] Step 6:

[0220] Users receive the distributed information and take the necessary actions. If users provide feedback, the server collects it and uses it as data to further improve the reliability of the information.

[0221] (Example 1)

[0222] 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."

[0223] During a disaster, it is extremely difficult to quickly, accurately, and reliably obtain reliable information from a vast amount of data and provide it to individual users according to their needs. The dissemination of incorrect or redundant information can hinder appropriate judgment and action. This invention aims to provide a system that efficiently solves these problems.

[0224] 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.

[0225] In this invention, the server includes means for acquiring messages, means for classifying acquired messages into categories using natural language processing technology, and means for evaluating the reliability of the classified messages using a generative artificial intelligence model. This enables the rapid acquisition of highly reliable information during disasters and the provision of information tailored to the needs of each user.

[0226] A "message acquisition method" is a system for automatically collecting disaster-related information from communication methods and information sources.

[0227] "Natural language processing technology" is a technology that allows computers to understand and analyze human language, and provides functions for classifying and summarizing text.

[0228] A "generative artificial intelligence model" is a technology that analyzes data based on machine learning and evaluates the reliability of the information.

[0229] "A means of setting priorities and customizing information based on user location and individual needs" refers to a system that ranks information according to its importance and provides information optimized for each individual user.

[0230] An "interactive display device" is a device that allows users to receive and interact with information, such as a smartphone or tablet.

[0231] A description of embodiments for carrying out the present invention will be provided.

[0232] The server acquires real-time data through messaging services and SNS APIs for information gathering during disasters. To maintain the volume of information and real-time capabilities, it is recommended that the server use load balancing technology and cloud computing services. Specifically, platforms such as AWS Lambda and Google Cloud Functions are available.

[0233] The collected data is analyzed on the server using natural language processing (NLP) techniques. Libraries such as Python's NLTK and SpaCy are used to classify the information into specific categories and determine its importance and urgency as needed. At this stage, machine learning models are pre-trained to improve classification accuracy.

[0234] Next, the server uses a generative AI model to evaluate the reliability of the acquired information. During this process, the generative AI model is prompted with the question, "Which other sources does this information match?" to check the consistency of the information. By analyzing the output of the generative AI model in response to this prompt, misinformation and duplicate information are identified, and highly reliable information is prioritized.

[0235] Reliable information is optimized based on the user's location and specific needs, and delivered to their device. This customized information is displayed on the user's interactive display device (such as a smartphone or tablet). Based on this information, the user can make quick and effective decisions.

[0236] As a concrete example, in the event of a major earthquake, users can post their situation via a messaging service. This information is collected and analyzed by a server, cross-referenced with other relevant information, and then provided to users according to its accuracy and urgency. This allows each user to quickly choose appropriate actions to ensure their own safety and the safety of their family.

[0237] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0238] Step 1:

[0239] The server retrieves data in real time through messaging service and SNS APIs. It receives raw message data from external sources as input and stores it in its internal system. Specifically, it interprets the retrieved data packets and stores each data item in a database along with a unique identifier. This data includes information about the type and location of the disaster.

[0240] Step 2:

[0241] The server analyzes the acquired messages using natural language processing techniques and classifies them into categories. Messages stored in a database are used as input. The output generates data where messages are classified into specific disaster categories (e.g., earthquake, flood). Specifically, it applies text analysis algorithms to automatically classify messages based on keywords and context.

[0242] Step 3:

[0243] The server evaluates the reliability of classified messages using a generative AI model. The input is messages classified by category. The output is a calculated reliability score for each message. Specifically, the generative AI model is prompted with the question, "Which other sources does this information match?", and the model's evaluation results are analyzed.

[0244] Step 4:

[0245] The server prioritizes messages based on their reliability scores and creates customized information tailored to the user's location and individual needs. The input consists of messages with reliability scores and user profile information. The output generates a prioritized information set for each user. Specifically, it uses an algorithm to compare scores and sorts the information based on its importance.

[0246] Step 5:

[0247] The terminal receives customized information and notifies the user. It receives a prioritized set of information sent from the server as input. As output, it generates specific action recommendations that are displayed on the user interface. As specific action, it dynamically displays information on an interactive display device, visually highlighting information important to the end user.

[0248] (Application Example 1)

[0249] 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."

[0250] In disasters and security-related emergencies, the speed and accuracy of information acquisition and distribution are crucial. However, the ease with which misinformation spreads and the risk of inappropriate decision-making based on unreliable information are significant challenges. Furthermore, the lack of effective information provision tailored to individual user needs makes it difficult to respond quickly to specific situations.

[0251] 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.

[0252] In this invention, the server includes means for acquiring messages, means for classifying acquired messages into categories, means for evaluating the reliability of the classified messages, means for setting priorities for the evaluated messages, means for distributing information based on the priorities, means for notifying the user of information based on location information, and means for customizing notifications based on the user's individual settings. This enables rapid and reliable information distribution, allowing users to take the most appropriate action based on their situation.

[0253] A "message acquisition method" is a function for automatically collecting information transmitted and received through a communication network.

[0254] "Means of categorization" refers to the process of classifying and organizing collected information based on pre-established criteria.

[0255] "Means of evaluating reliability" refers to processes that use generative AI models or other technologies to determine the accuracy and credibility of information.

[0256] A "means of setting priorities" is a function for ranking the importance and urgency of information based on evaluated information.

[0257] "Means of distributing information" refers to a system for sending prioritized information to a user's device.

[0258] "Location-based notification methods" refer to functions that select and deliver highly relevant information based on the user's current location.

[0259] "Means for customizing notifications" refers to a mechanism for adjusting and providing information delivered according to the user's individual settings and interests.

[0260] The system implementing this invention mainly consists of three elements: a server, a terminal, and a user. The server acquires messages via a communication network and analyzes and evaluates the collected information using natural language processing and generative AI models. Specifically, the server uses an API as a means of acquiring messages and automatically collects them. Next, the collected messages are classified into categories based on pre-set criteria and their reliability is evaluated. In this process, libraries such as spaCy can be used for natural language processing, and generative AI models such as GPT-3 can be used for reliability evaluation.

[0261] The device receives information distributed from the server and notifies the user. Notifications are based on location information, and further customized information is provided. This allows the user to choose the optimal action based on their current location and individual needs. This supports quick and appropriate decision-making.

[0262] For example, if a security incident occurs in a region, this system can quickly deliver information to users' smartphones, allowing them to enhance their vigilance by checking the alerts.

[0263] An example of a prompt message is: "Please provide the latest security-related information based on the user's location. Also, evaluate the reliability of each piece of information and notify the most important ones first." Based on this prompt, appropriate information tailored to the user's individual needs will be provided.

[0264] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0265] Step 1:

[0266] The server automatically collects disaster and security-related messages using a message retrieval API over the communication network. In this process, raw data is received from the API as input, and pre-processed raw message data is generated as output.

[0267] Step 2:

[0268] The server applies natural language processing to the collected messages and classifies them into categories based on pre-defined criteria. The input is the raw message data obtained in step 1, and the output is message data organized by category. Specifically, topic modeling using tools such as spaCy is performed.

[0269] Step 3:

[0270] The server evaluates the reliability of messages classified using a generative AI model. The input is categorized message data, and the output is data with a reliability score. In this process, generative AI such as GPT-3 is used to assess reliability using prompt messages.

[0271] Step 4:

[0272] The server sets the priority of each message based on the reliability evaluation results. The input is the message data whose reliability was evaluated in step 3, and the output is a list of messages with assigned priorities. Here, scoring is performed considering urgency and reliability.

[0273] Step 5:

[0274] The server generates warning notifications based on priority and prepares them for delivery to terminals. The input is a prioritized list of messages, and the output is notification data ready for delivery. Here, the data is converted to a notification format suitable for the criteria.

[0275] Step 6:

[0276] The device receives warning notifications from the server and displays the most appropriate notification based on the user's location. The input is notification data from the server, and the output is a location-based warning presented to the user.

[0277] Step 7:

[0278] Users review notifications received on their devices and provide feedback as needed. Input is the notification information presented by the device, while output is the user's actions and feedback reflected in the system. This feedback is used for subsequent reliability evaluations and customization.

[0279] 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.

[0280] This invention relates to a system that performs information processing that takes into account not only the collection, classification, and distribution of information during disasters, but also the emotions of the user. In particular, by incorporating an emotion engine, this system realizes a new dimension of processing that analyzes the user's emotions.

[0281] First, the server retrieves messages related to the disaster area from messaging applications. This process is carried out by collecting messages in real time using existing APIs. The collected messages are analyzed using natural language processing technology. Based on the analysis results, the server classifies the messages into categories such as "searching for a person" or "searching for a pet."

[0282] Next, the server uses an emotion engine to analyze the emotions contained in the user's post. Emotion analysis is used to understand the nuances and emotional state of the user's statements, which allows for the assessment of stress and urgency during a disaster.

[0283] Furthermore, the server uses the emotions recognized by the emotion engine to evaluate the reliability of information and adjust the priorities. For example, if the poster shows a high level of tension or anxiety, the urgency of the message can be increased and a prompt response can be made.

[0284] After that, the organized information is distributed from the server to the terminal. At the terminal, the user can receive and utilize the information in a suitable form. Since it also includes feedback information according to emotions, it functions as part of the care and support for the user.

[0285] As a specific example, assume that a search request for a missing pet in a disaster area is posted. The message posted by the user may contain emotions such as "worried" and "sad". The emotion engine of the server detects these emotions and sets a higher urgency for the search. The information is quickly distributed to the users of the terminal, and they can carry out efficient search activities based on that information.

[0286] Through such a process, the system aims to enable accurate resource allocation and mental care during disasters and improve the overall search effect.

[0287] The following explains the processing flow.

[0288] Step 1:

[0289] The server uses the API of the messaging application to collect new messages related to the disaster. As a result, data such as the information of the poster, the text of the message, and the posting time are collected.

[0290] Step 2:

[0291] The server analyzes the messages collected using natural language processing technology and classifies the messages into categories such as "search for people" and "search for pets" based on the extracted keywords.

[0292] Step 3:

[0293] The server uses an emotion engine to perform sentiment analysis on each message. It extracts emotions such as "tension," "anxiety," and "sadness" from the user's statements to understand their emotional tendencies.

[0294] Step 4:

[0295] The server reviews the urgency and importance of messages based on the analysis results from the emotion engine, and adjusts their priority. Messages that express strong emotions are given a particularly high priority.

[0296] Step 5:

[0297] The server delivers information, organized according to priority, to the relevant devices. It provides users with the information they need as needed through push notifications and dashboards.

[0298] Step 6:

[0299] The system receives information distributed to users and responds promptly. User feedback is sent to the server and used to improve the accuracy of information throughout the system.

[0300] Step 7:

[0301] The server analyzes user feedback and incorporates it into new information gathering, reliability evaluation, and sentiment analysis, thereby continuously improving the functionality of the disaster relief system.

[0302] (Example 2)

[0303] 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 glasses 214 will be referred to as the "terminal".

[0304] It is difficult to quickly and accurately extract important information from the large amount of information generated during a disaster, prioritize it appropriately, and distribute it. In addition, although there is a need for information provision that takes into account the emotions of users and the identification of misinformation, conventional systems do not fully meet these requirements.

[0305] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0306] In this invention, the server includes a message acquisition means, a means for analyzing the acquired message using natural language processing technology and classifying it into categories, a means for analyzing the emotion included in the post and judging the urgency, a means for evaluating the reliability of the classified message based on the analyzed emotion and setting the priority, a means for distributing information to the terminal based on the priority, and a means for providing feedback information according to the emotion. Thereby, it becomes possible to quickly extract important information during a disaster and provide information that takes into account the emotions of users.

[0307] The "message acquisition means" is a process or device for collecting information related to a disaster in real time, and mainly includes a function of acquiring data through communication means.

[0308] "Natural language processing technology" is a technology for a computer to understand, interpret, and manipulate human language, and is mainly used for the analysis and classification of text data.

[0309] "Emotion analysis" is a technology for extracting emotional nuances from text data and judging the emotional state of a user, and functions as an element for evaluating the urgency and importance of a post.

[0310] The "means for evaluating reliability" refers to the criteria and methods for judging the accuracy and reliability of information, and is mainly a process performed in consideration of emotion analysis and past data.

[0311] "Methods for setting priorities" refers to the process of organizing collected information based on its importance and urgency, and determining the order in which it will be distributed.

[0312] "Means of distributing information" refers to the mechanisms and methods for delivering organized information to a user's device, primarily through communication networks.

[0313] "Feedback information" refers to evaluation and support information provided to users, particularly information based on sentiment analysis to encourage appropriate responses.

[0314] This invention is a system that collects, classifies, and distributes information during disasters, and also processes information while considering the user's emotions. The server uses existing APIs to retrieve disaster-related messages from messaging applications via a communication network. Message collection includes platforms such as Twitter and LINE.

[0315] The server uses natural language processing libraries such as Python's NLTK and spaCy to analyze and categorize the received messages. This analysis classifies the messages into categories such as "searching for a person" or "searching for a pet."

[0316] The server also uses an emotion engine to extract emotions from text data. Sentiment analysis is performed using emotion analysis tools such as Microsoft Azure's Text Analytics API and Google Cloud's Natural Language API. This classifies the emotions contained in posts into categories such as "joy," "sadness," and "anxiety," and reliability evaluations and prioritization are performed based on the results.

[0317] The organized information is delivered from the server to the terminal. On the terminal, the user can receive the information via a dedicated application or web browser, and feedback information tailored to the urgency of the situation is also provided. Based on this information, the user can take a quick and efficient response.

[0318] For example, if a request to search for a missing pet in a disaster area is posted, the server analyzes the message and detects emotions such as "worry" and "sadness." Based on this emotion analysis, the urgency level is set to high, and the information is quickly delivered to the user on their device. This process allows users to conduct search activities efficiently.

[0319] An example of a prompt might be: "Please explain the message sentiment analysis process for disaster information gathering systems."

[0320] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0321] Step 1:

[0322] The server retrieves messages related to disaster areas from messaging applications. The input is real-time message data, which is retrieved via a communication API. The output is raw message data stored in a database or memory. Specifically, the system periodically sends requests through an existing API (e.g., the Twitter API) to retrieve messages and write them to storage.

[0323] Step 2:

[0324] The server analyzes the messages it receives using natural language processing techniques and classifies them into categories. The input is collected message data located in a database or memory. This data is tokenized using Python's natural language processing libraries (NLTK or spaCy), and important keywords are extracted. The output is message data with categories added. Specifically, the server analyzes each message and automatically classifies them into categories such as "searching for a person" or "searching for a pet."

[0325] Step 3:

[0326] The server analyzes the emotions contained in the messages. The input is a message with categories attached, and an emotion analysis tool (e.g., Microsoft Azure's Text Analytics API) is applied to this data. The output is message data with emotion scores attached. Specifically, the server adds emotion categories such as "joy" and "anxiety" to the messages based on the emotion analysis results.

[0327] Step 4:

[0328] The server evaluates the reliability and prioritizes classified messages based on sentiment analysis. The input is message data with sentiment scores. Using this data, it executes logic to analyze the reliability of the information and determine its priority. The output is a list of messages with assigned priorities. Specifically, the server evaluates urgency and the reliability of the information, and if a message indicates high urgency, its priority is increased.

[0329] Step 5:

[0330] The system delivers information from the server to the terminal and provides emotionally responsive feedback. The input is a prioritized list of messages. The output is the information and feedback data delivered to the user's terminal. Specifically, the server sends organized information to the terminal as push notifications or emails, and the user receives the information in an appropriate format. This allows users to quickly take necessary actions during a disaster.

[0331] (Application Example 2)

[0332] 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."

[0333] During disasters, information becomes chaotic, making it difficult to immediately determine which information is urgent. Furthermore, there is a lack of information provision that considers users' emotions, resulting in inadequate care and support for users who are feeling anxious.

[0334] 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.

[0335] In this invention, the server includes means for acquiring messages, means for classifying acquired messages into categories, and means for analyzing the sentiment of the messages. This makes it possible to prioritize the delivery of information that is of high urgency, taking into account the user's emotions. It also enables the provision of emotionally supportive information tailored to the user.

[0336] "Means of acquiring messages" refers to the function of collecting disaster-related text data in real time via a communication network.

[0337] "Means of categorization" refers to a function that organizes acquired messages based on specific conditions, categorized by themes such as "searching for people" or "shortage of supplies."

[0338] "Methods for analyzing emotions" refer to technologies that analyze the text of a message to quantify or qualitatively determine the sender's emotions and sensibilities.

[0339] The "means of setting urgency" refer to a function that dynamically determines the importance and priority of a message based on information obtained through sentiment analysis.

[0340] "Means of distributing information" refers to a system that effectively and quickly transfers information to relevant users and devices according to the set level of urgency.

[0341] In implementing this invention, the server first collects disaster-related messages in real time via a communication network. Existing messaging APIs can be used for this purpose, and the data is aggregated on the server. Subsequently, the server uses natural language processing technology to analyze the messages as text data and classify each message into categories such as "search for people" or "shortage of supplies." In this process, the Google Cloud Natural Language API is utilized to achieve rapid and accurate analysis.

[0342] Subsequently, the server uses an emotion analysis engine to quantify or qualitatively determine the user's emotions from the retrieved messages. This emotion analysis uses emotion analysis software such as SentiStrength. Based on the analysis results, the server sets the urgency of the message. In doing so, it considers the intensity and type of emotion to identify information that should be addressed as a priority.

[0343] Ultimately, the server quickly delivers information to user terminals according to the configured urgency level. This allows users to receive information relevant to their situation and take appropriate action. For example, if a user in a flood-affected area posts a message based on "anxiety" and "fear," that information is quickly distributed to nearby residents, who are then guided to safe evacuation locations.

[0344] As a concrete example, a prompt message could read, "An evacuation order has been issued due to flooding. If you are feeling anxious, please find the following resources to help alleviate your worries." In this way, by adjusting the content of the messages based on the user's emotions, it is possible to provide appropriate care to the user.

[0345] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0346] Step 1:

[0347] The server acquires disaster-related messages via a communication network. It uses data received in real time from a messaging platform as input. The output is unanalyzed message data stored in the server's data storage. This operation aggregates information from the field during a disaster.

[0348] Step 2:

[0349] The server uses natural language processing technology to analyze the text data of the acquired messages. The input is the message data saved in the previous step. The output is the category information of the analyzed messages. By classifying them into categories such as "searching for people" or "shortage of supplies," the messages are organized based on their content.

[0350] Step 3:

[0351] The server uses an emotion analysis engine to analyze the user's emotions from the message. The input is the text data of the analyzed message, and the output is emotion data that has been quantified or qualitatively determined. In this step, software such as SentiStrength is used to determine the user's emotional state.

[0352] Step 4:

[0353] The server sets the urgency of a message based on the sentiment analysis results. The input is the analyzed sentiment data, and the output is a numerical value or indicator of urgency. For example, if anxiety or fear is strong, a high urgency level will be set. This operation contributes to prioritizing information.

[0354] Step 5:

[0355] The server delivers information to terminals according to the configured urgency level. Input consists of messages and category information with set urgency levels, while output is push notifications and alerts delivered to the user's terminal. This allows users to quickly and accurately obtain information and take appropriate action.

[0356] 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.

[0357] 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.

[0358] 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.

[0359] [Third Embodiment]

[0360] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0361] 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.

[0362] 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).

[0363] 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.

[0364] 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.

[0365] 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).

[0366] 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.

[0367] 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.

[0368] 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.

[0369] 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.

[0370] 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.

[0371] 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".

[0372] This invention is a system that enables rapid and accurate information distribution during disasters. This system revolves around three main roles: server, terminal, and user, which perform information acquisition, classification, evaluation, and distribution.

[0373] First, the server automatically retrieves messages from messaging applications and related communication methods using APIs. The collected messages are analyzed using natural language processing techniques and classified into categories based on predetermined criteria.

[0374] Next, the server uses a generated AI model to evaluate the reliability of the collected information. This allows it to identify misinformation and duplicate information and prioritize it based on its reliability.

[0375] The information processed through this mechanism is then distributed from the server to each terminal. Users receive the information on their terminals and can take quick and appropriate action based on the provided information. Because the distributed information is customized to the user's location and individual needs, optimal information is provided to each user.

[0376] As a concrete example, consider a scenario where a large-scale disaster occurs and many people and pets go missing. In this system, users post information about missing people and pets using their smartphones. A server collects this information, evaluates its reliability by comparing it with other related posts, and aggregates similar information.

[0377] Subsequently, the server prioritizes the most reliable information and quickly delivers the most useful information. Based on this information, users on terminals can grasp specific locations and situations, enabling them to conduct search and rescue operations more efficiently. In this way, the system of the present invention optimizes the flow of information during disasters, supporting accurate decision-making and rapid action.

[0378] The following describes the processing flow.

[0379] Step 1:

[0380] The server automatically retrieves newly posted messages in real time from messaging applications via API. These messages include author information, message body, and timestamp.

[0381] Step 2:

[0382] The server analyzes the messages it receives using natural language processing techniques to extract keywords. Based on these keywords, the messages are classified into categories such as "searching for a person" or "searching for a pet."

[0383] Step 3:

[0384] The server searches the database for other messages with similar content and evaluates the truthfulness of the information through cross-referencing. A generative AI model is used to calculate a confidence score.

[0385] Step 4:

[0386] The server prioritizes information based on its reliability score. Information that is urgent and highly reliable is given a higher priority.

[0387] Step 5:

[0388] The server prioritizes and delivers information to the appropriate user groups or individual devices. This may involve using push notifications or dedicated dashboards.

[0389] Step 6:

[0390] Users receive the distributed information and take the necessary actions. If users provide feedback, the server collects it and uses it as data to further improve the reliability of the information.

[0391] (Example 1)

[0392] 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."

[0393] During a disaster, it is extremely difficult to quickly, accurately, and reliably obtain reliable information from a vast amount of data and provide it to individual users according to their needs. The dissemination of incorrect or redundant information can hinder appropriate judgment and action. This invention aims to provide a system that efficiently solves these problems.

[0394] 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.

[0395] In this invention, the server includes means for acquiring messages, means for classifying acquired messages into categories using natural language processing technology, and means for evaluating the reliability of the classified messages using a generative artificial intelligence model. This enables the rapid acquisition of highly reliable information during disasters and the provision of information tailored to the needs of each user.

[0396] A "message acquisition method" is a system for automatically collecting disaster-related information from communication methods and information sources.

[0397] "Natural language processing technology" is a technology that allows computers to understand and analyze human language, and provides functions for classifying and summarizing text.

[0398] A "generative artificial intelligence model" is a technology that analyzes data based on machine learning and evaluates the reliability of the information.

[0399] "A means of setting priorities and customizing information based on user location and individual needs" refers to a system that ranks information according to its importance and provides information optimized for each individual user.

[0400] An "interactive display device" is a device that allows users to receive and interact with information, such as a smartphone or tablet.

[0401] A description of embodiments for carrying out the present invention will be provided.

[0402] The server acquires real-time data through messaging services and SNS APIs for information gathering during disasters. To maintain the volume of information and real-time capabilities, it is recommended that the server use load balancing technology and cloud computing services. Specifically, platforms such as AWS Lambda and Google Cloud Functions are available.

[0403] The collected data is analyzed on the server using natural language processing (NLP) techniques. Libraries such as Python's NLTK and SpaCy are used to classify the information into specific categories and determine its importance and urgency as needed. At this stage, machine learning models are pre-trained to improve classification accuracy.

[0404] Next, the server uses a generative AI model to evaluate the reliability of the acquired information. During this process, the generative AI model is prompted with the question, "Which other sources does this information match?" to check the consistency of the information. By analyzing the output of the generative AI model in response to this prompt, misinformation and duplicate information are identified, and highly reliable information is prioritized.

[0405] Reliable information is optimized based on the user's location and specific needs, and delivered to their device. This customized information is displayed on the user's interactive display device (such as a smartphone or tablet). Based on this information, the user can make quick and effective decisions.

[0406] As a concrete example, in the event of a major earthquake, users can post their situation via a messaging service. This information is collected and analyzed by a server, cross-referenced with other relevant information, and then provided to users according to its accuracy and urgency. This allows each user to quickly choose appropriate actions to ensure their own safety and the safety of their family.

[0407] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0408] Step 1:

[0409] The server retrieves data in real time through messaging service and SNS APIs. It receives raw message data from external sources as input and stores it in its internal system. Specifically, it interprets the retrieved data packets and stores each data item in a database along with a unique identifier. This data includes information about the type and location of the disaster.

[0410] Step 2:

[0411] The server analyzes the acquired messages using natural language processing techniques and classifies them into categories. Messages stored in a database are used as input. The output generates data where messages are classified into specific disaster categories (e.g., earthquake, flood). Specifically, it applies text analysis algorithms to automatically classify messages based on keywords and context.

[0412] Step 3:

[0413] The server evaluates the reliability of classified messages using a generative AI model. The input is messages classified by category. The output is a calculated reliability score for each message. Specifically, the generative AI model is prompted with the question, "Which other sources does this information match?", and the model's evaluation results are analyzed.

[0414] Step 4:

[0415] The server prioritizes messages based on their reliability scores and creates customized information tailored to the user's location and individual needs. The input consists of messages with reliability scores and user profile information. The output generates a prioritized information set for each user. Specifically, it uses an algorithm to compare scores and sorts the information based on its importance.

[0416] Step 5:

[0417] The terminal receives customized information and notifies the user. It receives a prioritized set of information sent from the server as input. As output, it generates specific action recommendations that are displayed on the user interface. As specific action, it dynamically displays information on an interactive display device, visually highlighting information important to the end user.

[0418] (Application Example 1)

[0419] 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."

[0420] In disasters and security-related emergencies, the speed and accuracy of information acquisition and distribution are crucial. However, the ease with which misinformation spreads and the risk of inappropriate decision-making based on unreliable information are significant challenges. Furthermore, the lack of effective information provision tailored to individual user needs makes it difficult to respond quickly to specific situations.

[0421] 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.

[0422] In this invention, the server includes means for acquiring messages, means for classifying acquired messages into categories, means for evaluating the reliability of the classified messages, means for setting priorities for the evaluated messages, means for distributing information based on the priorities, means for notifying the user of information based on location information, and means for customizing notifications based on the user's individual settings. This enables rapid and reliable information distribution, allowing users to take the most appropriate action based on their situation.

[0423] A "message acquisition method" is a function for automatically collecting information transmitted and received through a communication network.

[0424] "Means of categorization" refers to the process of classifying and organizing collected information based on pre-established criteria.

[0425] "Means of evaluating reliability" refers to processes that use generative AI models or other technologies to determine the accuracy and credibility of information.

[0426] A "means of setting priorities" is a function for ranking the importance and urgency of information based on evaluated information.

[0427] "Means of distributing information" refers to a system for sending prioritized information to a user's device.

[0428] "Location-based notification methods" refer to functions that select and deliver highly relevant information based on the user's current location.

[0429] "Means for customizing notifications" refers to a mechanism for adjusting and providing information delivered according to the user's individual settings and interests.

[0430] The system implementing this invention mainly consists of three elements: a server, a terminal, and a user. The server acquires messages via a communication network and analyzes and evaluates the collected information using natural language processing and generative AI models. Specifically, the server uses an API as a means of acquiring messages and automatically collects them. Next, the collected messages are classified into categories based on pre-set criteria and their reliability is evaluated. In this process, libraries such as spaCy can be used for natural language processing, and generative AI models such as GPT-3 can be used for reliability evaluation.

[0431] The device receives information distributed from the server and notifies the user. Notifications are based on location information, and further customized information is provided. This allows the user to choose the optimal action based on their current location and individual needs. This supports quick and appropriate decision-making.

[0432] For example, if a security incident occurs in a region, this system can quickly deliver information to users' smartphones, allowing them to enhance their vigilance by checking the alerts.

[0433] An example of a prompt message is: "Please provide the latest security-related information based on the user's location. Also, evaluate the reliability of each piece of information and notify the most important ones first." Based on this prompt, appropriate information tailored to the user's individual needs will be provided.

[0434] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0435] Step 1:

[0436] The server automatically collects disaster and security-related messages using a message retrieval API over the communication network. In this process, raw data is received from the API as input, and pre-processed raw message data is generated as output.

[0437] Step 2:

[0438] The server applies natural language processing to the collected messages and classifies them into categories based on pre-defined criteria. The input is the raw message data obtained in step 1, and the output is message data organized by category. Specifically, topic modeling using tools such as spaCy is performed.

[0439] Step 3:

[0440] The server evaluates the reliability of messages classified using a generative AI model. The input is categorized message data, and the output is data with a reliability score. In this process, generative AI such as GPT-3 is used to assess reliability using prompt messages.

[0441] Step 4:

[0442] The server sets the priority of each message based on the reliability evaluation results. The input is the message data whose reliability was evaluated in step 3, and the output is a list of messages with assigned priorities. Here, scoring is performed considering urgency and reliability.

[0443] Step 5:

[0444] The server generates warning notifications based on priority and prepares them for delivery to terminals. The input is a prioritized list of messages, and the output is notification data ready for delivery. Here, the data is converted to a notification format suitable for the criteria.

[0445] Step 6:

[0446] The device receives warning notifications from the server and displays the most appropriate notification based on the user's location. The input is notification data from the server, and the output is a location-based warning presented to the user.

[0447] Step 7:

[0448] Users review notifications received on their devices and provide feedback as needed. Input is the notification information presented by the device, while output is the user's actions and feedback reflected in the system. This feedback is used for subsequent reliability evaluations and customization.

[0449] 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.

[0450] This invention relates to a system that performs information processing that takes into account not only the collection, classification, and distribution of information during disasters, but also the emotions of the user. In particular, by incorporating an emotion engine, this system realizes a new dimension of processing that analyzes the user's emotions.

[0451] First, the server retrieves messages related to the disaster area from messaging applications. This process is carried out by collecting messages in real time using existing APIs. The collected messages are analyzed using natural language processing technology. Based on the analysis results, the server classifies the messages into categories such as "searching for a person" or "searching for a pet."

[0452] Next, the server uses an emotion engine to analyze the emotions contained in the user's post. Emotion analysis is used to understand the nuances and emotional state of the user's statements, which allows for the assessment of stress and urgency during a disaster.

[0453] Furthermore, the server uses the emotions recognized by the emotion engine to evaluate the reliability of information and adjust its priority. For example, if the poster indicates a high level of tension or anxiety, the urgency of the message can be increased, allowing for a quicker response.

[0454] The organized information is then distributed from the server to the terminal. On the terminal, the user can receive and use the information in a format suitable for them. Since it also includes emotionally responsive feedback, it functions as part of user care and support.

[0455] As a concrete example, consider a scenario where a user posts a request to search for a missing pet in a disaster area. The message posted by the user may contain emotions such as "worry" or "sadness." The server's emotion engine detects these emotions and sets the urgency of the search to a higher level. This information is quickly delivered to the user on their device, allowing them to conduct efficient search operations based on that information.

[0456] Through this process, the system aims to improve the overall effectiveness of search and rescue operations by enabling the appropriate allocation of resources and psychological support during disasters.

[0457] The following describes the processing flow.

[0458] Step 1:

[0459] The server uses the messaging application's API to collect new messages related to the disaster. This allows data such as the poster's information, message body, and posting time to be collected.

[0460] Step 2:

[0461] The server analyzes the collected messages using natural language processing technology and classifies them into categories such as "searching for a person" or "searching for a pet" based on the extracted keywords.

[0462] Step 3:

[0463] The server uses an emotion engine to perform sentiment analysis on each message. It extracts emotions such as "tension," "anxiety," and "sadness" from the user's statements to understand their emotional tendencies.

[0464] Step 4:

[0465] The server reviews the urgency and importance of messages based on the analysis results from the emotion engine, and adjusts their priority. Messages that express strong emotions are given a particularly high priority.

[0466] Step 5:

[0467] The server delivers information, organized according to priority, to the relevant devices. It provides users with the information they need as needed through push notifications and dashboards.

[0468] Step 6:

[0469] The system receives information distributed to users and responds promptly. User feedback is sent to the server and used to improve the accuracy of information throughout the system.

[0470] Step 7:

[0471] The server analyzes user feedback and incorporates it into new information gathering, reliability evaluation, and sentiment analysis, thereby continuously improving the functionality of the disaster relief system.

[0472] (Example 2)

[0473] 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."

[0474] During a disaster, it is difficult to quickly and accurately extract important information from the vast amount of data generated, prioritize it appropriately, and distribute it effectively. Furthermore, there is a need to provide information that is sensitive to user emotions and to identify misinformation, but conventional systems do not adequately meet these requirements.

[0475] 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.

[0476] In this invention, the server includes means for acquiring messages, means for analyzing acquired messages using natural language processing technology and classifying them into categories, means for analyzing the emotions contained in posts and determining their urgency, means for evaluating the reliability of messages classified based on the analyzed emotions and setting priorities, and means for distributing information to terminals based on the priorities and providing feedback information that corresponds to the emotions. This enables the rapid extraction of important information during disasters and the provision of information that takes into account the user's emotions.

[0477] "Message acquisition means" refers to processes and devices for collecting relevant information in real time during a disaster, and primarily includes the function of acquiring data through communication means.

[0478] "Natural language processing technology" refers to the technology that enables computers to understand, interpret, and manipulate human language, and is primarily used for analyzing and classifying text data.

[0479] "Sentiment analysis" is a technology that extracts emotional nuances from text data to determine the user's emotional state, and it functions as a factor in evaluating the urgency and importance of a post.

[0480] "Means of evaluating reliability" refer to criteria and methods for judging the accuracy and reliability of information, and are primarily processes that take into account sentiment analysis and past data.

[0481] "Methods for setting priorities" refers to the process of organizing collected information based on its importance and urgency, and determining the order in which it will be distributed.

[0482] "Means of distributing information" refers to the mechanisms and methods for delivering organized information to a user's device, primarily through communication networks.

[0483] "Feedback information" refers to evaluation and support information provided to users, particularly information based on sentiment analysis to encourage appropriate responses.

[0484] This invention is a system that collects, classifies, and distributes information during disasters, and also processes information while considering the user's emotions. The server uses existing APIs to retrieve disaster-related messages from messaging applications via a communication network. Message collection includes platforms such as Twitter and LINE.

[0485] The server uses natural language processing libraries such as Python's NLTK and spaCy to analyze and categorize the received messages. This analysis classifies the messages into categories such as "searching for a person" or "searching for a pet."

[0486] The server also uses an emotion engine to extract emotions from text data. Sentiment analysis is performed using emotion analysis tools such as Microsoft Azure's Text Analytics API and Google Cloud's Natural Language API. This classifies the emotions contained in posts into categories such as "joy," "sadness," and "anxiety," and reliability evaluations and prioritization are performed based on the results.

[0487] The organized information is delivered from the server to the terminal. On the terminal, the user can receive the information via a dedicated application or web browser, and feedback information tailored to the urgency of the situation is also provided. Based on this information, the user can take a quick and efficient response.

[0488] For example, if a request to search for a missing pet in a disaster area is posted, the server analyzes the message and detects emotions such as "worry" and "sadness." Based on this emotion analysis, the urgency level is set to high, and the information is quickly delivered to the user on their device. This process allows users to conduct search activities efficiently.

[0489] An example of a prompt might be: "Please explain the message sentiment analysis process for disaster information gathering systems."

[0490] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0491] Step 1:

[0492] The server retrieves messages related to disaster areas from messaging applications. The input is real-time message data, which is retrieved via a communication API. The output is raw message data stored in a database or memory. Specifically, the system periodically sends requests through an existing API (e.g., the Twitter API) to retrieve messages and write them to storage.

[0493] Step 2:

[0494] The server analyzes the messages it receives using natural language processing techniques and classifies them into categories. The input is collected message data located in a database or memory. This data is tokenized using Python's natural language processing libraries (NLTK or spaCy), and important keywords are extracted. The output is message data with categories added. Specifically, the server analyzes each message and automatically classifies them into categories such as "searching for a person" or "searching for a pet."

[0495] Step 3:

[0496] The server analyzes the emotions contained in the messages. The input is a message with categories attached, and an emotion analysis tool (e.g., Microsoft Azure's Text Analytics API) is applied to this data. The output is message data with emotion scores attached. Specifically, the server adds emotion categories such as "joy" and "anxiety" to the messages based on the emotion analysis results.

[0497] Step 4:

[0498] The server evaluates the reliability and prioritizes classified messages based on sentiment analysis. The input is message data with sentiment scores. Using this data, it executes logic to analyze the reliability of the information and determine its priority. The output is a list of messages with assigned priorities. Specifically, the server evaluates urgency and the reliability of the information, and if a message indicates high urgency, its priority is increased.

[0499] Step 5:

[0500] The system delivers information from the server to the terminal and provides emotionally responsive feedback. The input is a prioritized list of messages. The output is the information and feedback data delivered to the user's terminal. Specifically, the server sends organized information to the terminal as push notifications or emails, and the user receives the information in an appropriate format. This allows users to quickly take necessary actions during a disaster.

[0501] (Application Example 2)

[0502] 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."

[0503] During disasters, information becomes chaotic, making it difficult to immediately determine which information is urgent. Furthermore, there is a lack of information provision that considers users' emotions, resulting in inadequate care and support for users who are feeling anxious.

[0504] 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.

[0505] In this invention, the server includes means for acquiring messages, means for classifying acquired messages into categories, and means for analyzing the sentiment of the messages. This makes it possible to prioritize the delivery of information that is of high urgency, taking into account the user's emotions. It also enables the provision of emotionally supportive information tailored to the user.

[0506] "Means of acquiring messages" refers to the function of collecting disaster-related text data in real time via a communication network.

[0507] "Means of categorization" refers to a function that organizes acquired messages based on specific conditions, categorized by themes such as "searching for people" or "shortage of supplies."

[0508] "Methods for analyzing emotions" refer to technologies that analyze the text of a message to quantify or qualitatively determine the sender's emotions and sensibilities.

[0509] The "means of setting urgency" refer to a function that dynamically determines the importance and priority of a message based on information obtained through sentiment analysis.

[0510] "Means of distributing information" refers to a system that effectively and quickly transfers information to relevant users and devices according to the set level of urgency.

[0511] In implementing this invention, the server first collects disaster-related messages in real time via a communication network. Existing messaging APIs can be used for this purpose, and the data is aggregated on the server. Subsequently, the server uses natural language processing technology to analyze the messages as text data and classify each message into categories such as "search for people" or "shortage of supplies." In this process, the Google Cloud Natural Language API is utilized to achieve rapid and accurate analysis.

[0512] Subsequently, the server uses an emotion analysis engine to quantify or qualitatively determine the user's emotions from the retrieved messages. This emotion analysis uses emotion analysis software such as SentiStrength. Based on the analysis results, the server sets the urgency of the message. In doing so, it considers the intensity and type of emotion to identify information that should be addressed as a priority.

[0513] Ultimately, the server quickly delivers information to user terminals according to the configured urgency level. This allows users to receive information relevant to their situation and take appropriate action. For example, if a user in a flood-affected area posts a message based on "anxiety" and "fear," that information is quickly distributed to nearby residents, who are then guided to safe evacuation locations.

[0514] As a concrete example, a prompt message could read, "An evacuation order has been issued due to flooding. If you are feeling anxious, please find the following resources to help alleviate your worries." In this way, by adjusting the content of the messages based on the user's emotions, it is possible to provide appropriate care to the user.

[0515] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0516] Step 1:

[0517] The server acquires disaster-related messages via a communication network. It uses data received in real time from a messaging platform as input. The output is unanalyzed message data stored in the server's data storage. This operation aggregates information from the field during a disaster.

[0518] Step 2:

[0519] The server uses natural language processing technology to analyze the text data of the acquired messages. The input is the message data saved in the previous step. The output is the category information of the analyzed messages. By classifying them into categories such as "searching for people" or "shortage of supplies," the messages are organized based on their content.

[0520] Step 3:

[0521] The server uses an emotion analysis engine to analyze the user's emotions from the message. The input is the text data of the analyzed message, and the output is emotion data that has been quantified or qualitatively determined. In this step, software such as SentiStrength is used to determine the user's emotional state.

[0522] Step 4:

[0523] The server sets the urgency of a message based on the sentiment analysis results. The input is the analyzed sentiment data, and the output is a numerical value or indicator of urgency. For example, if anxiety or fear is strong, a high urgency level will be set. This operation contributes to prioritizing information.

[0524] Step 5:

[0525] The server delivers information to terminals according to the configured urgency level. Input consists of messages and category information with set urgency levels, while output is push notifications and alerts delivered to the user's terminal. This allows users to quickly and accurately obtain information and take appropriate action.

[0526] 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.

[0527] 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.

[0528] 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.

[0529] [Fourth Embodiment]

[0530] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0531] 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.

[0532] 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).

[0533] 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.

[0534] 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.

[0535] 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).

[0536] 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.

[0537] 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.

[0538] 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.

[0539] 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.

[0540] 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.

[0541] 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.

[0542] 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".

[0543] This invention is a system that enables rapid and accurate information distribution during disasters. This system revolves around three main roles: server, terminal, and user, which perform information acquisition, classification, evaluation, and distribution.

[0544] First, the server automatically retrieves messages from messaging applications and related communication methods using APIs. The collected messages are analyzed using natural language processing techniques and classified into categories based on predetermined criteria.

[0545] Next, the server uses a generated AI model to evaluate the reliability of the collected information. This allows it to identify misinformation and duplicate information and prioritize it based on its reliability.

[0546] The information processed through this mechanism is then distributed from the server to each terminal. Users receive the information on their terminals and can take quick and appropriate action based on the provided information. Because the distributed information is customized to the user's location and individual needs, optimal information is provided to each user.

[0547] As a concrete example, consider a scenario where a large-scale disaster occurs and many people and pets go missing. In this system, users post information about missing people and pets using their smartphones. A server collects this information, evaluates its reliability by comparing it with other related posts, and aggregates similar information.

[0548] Subsequently, the server prioritizes the most reliable information and quickly delivers the most useful information. Based on this information, users on terminals can grasp specific locations and situations, enabling them to conduct search and rescue operations more efficiently. In this way, the system of the present invention optimizes the flow of information during disasters, supporting accurate decision-making and rapid action.

[0549] The following describes the processing flow.

[0550] Step 1:

[0551] The server automatically retrieves newly posted messages in real time from messaging applications via API. These messages include author information, message body, and timestamp.

[0552] Step 2:

[0553] The server analyzes the messages it receives using natural language processing techniques to extract keywords. Based on these keywords, the messages are classified into categories such as "searching for a person" or "searching for a pet."

[0554] Step 3:

[0555] The server searches the database for other messages with similar content and evaluates the truthfulness of the information through cross-referencing. A generative AI model is used to calculate a confidence score.

[0556] Step 4:

[0557] The server prioritizes information based on its reliability score. Information that is urgent and highly reliable is given a higher priority.

[0558] Step 5:

[0559] The server prioritizes and delivers information to the appropriate user groups or individual devices. This may involve using push notifications or dedicated dashboards.

[0560] Step 6:

[0561] Users receive the distributed information and take the necessary actions. If users provide feedback, the server collects it and uses it as data to further improve the reliability of the information.

[0562] (Example 1)

[0563] 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".

[0564] During a disaster, it is extremely difficult to quickly, accurately, and reliably obtain reliable information from a vast amount of data and provide it to individual users according to their needs. The dissemination of incorrect or redundant information can hinder appropriate judgment and action. This invention aims to provide a system that efficiently solves these problems.

[0565] 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.

[0566] In this invention, the server includes means for acquiring messages, means for classifying acquired messages into categories using natural language processing technology, and means for evaluating the reliability of the classified messages using a generative artificial intelligence model. This enables the rapid acquisition of highly reliable information during disasters and the provision of information tailored to the needs of each user.

[0567] A "message acquisition method" is a system for automatically collecting disaster-related information from communication methods and information sources.

[0568] "Natural language processing technology" is a technology that allows computers to understand and analyze human language, and provides functions for classifying and summarizing text.

[0569] A "generative artificial intelligence model" is a technology that analyzes data based on machine learning and evaluates the reliability of the information.

[0570] "A means of setting priorities and customizing information based on user location and individual needs" refers to a system that ranks information according to its importance and provides information optimized for each individual user.

[0571] An "interactive display device" is a device that allows users to receive and interact with information, such as a smartphone or tablet.

[0572] A description of embodiments for carrying out the present invention will be provided.

[0573] The server acquires real-time data through messaging services and SNS APIs for information gathering during disasters. To maintain the volume of information and real-time capabilities, it is recommended that the server use load balancing technology and cloud computing services. Specifically, platforms such as AWS Lambda and Google Cloud Functions are available.

[0574] The collected data is analyzed on the server using natural language processing (NLP) techniques. Libraries such as Python's NLTK and SpaCy are used to classify the information into specific categories and determine its importance and urgency as needed. At this stage, machine learning models are pre-trained to improve classification accuracy.

[0575] Next, the server uses a generative AI model to evaluate the reliability of the acquired information. During this process, the generative AI model is prompted with the question, "Which other sources does this information match?" to check the consistency of the information. By analyzing the output of the generative AI model in response to this prompt, misinformation and duplicate information are identified, and highly reliable information is prioritized.

[0576] Reliable information is optimized based on the user's location and specific needs, and delivered to their device. This customized information is displayed on the user's interactive display device (such as a smartphone or tablet). Based on this information, the user can make quick and effective decisions.

[0577] As a concrete example, in the event of a major earthquake, users can post their situation via a messaging service. This information is collected and analyzed by a server, cross-referenced with other relevant information, and then provided to users according to its accuracy and urgency. This allows each user to quickly choose appropriate actions to ensure their own safety and the safety of their family.

[0578] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0579] Step 1:

[0580] The server retrieves data in real time through messaging service and SNS APIs. It receives raw message data from external sources as input and stores it in its internal system. Specifically, it interprets the retrieved data packets and stores each data item in a database along with a unique identifier. This data includes information about the type and location of the disaster.

[0581] Step 2:

[0582] The server analyzes the acquired messages using natural language processing techniques and classifies them into categories. Messages stored in a database are used as input. The output generates data where messages are classified into specific disaster categories (e.g., earthquake, flood). Specifically, it applies text analysis algorithms to automatically classify messages based on keywords and context.

[0583] Step 3:

[0584] The server evaluates the reliability of classified messages using a generative AI model. The input is messages classified by category. The output is a calculated reliability score for each message. Specifically, the generative AI model is prompted with the question, "Which other sources does this information match?", and the model's evaluation results are analyzed.

[0585] Step 4:

[0586] The server prioritizes messages based on their reliability scores and creates customized information tailored to the user's location and individual needs. The input consists of messages with reliability scores and user profile information. The output generates a prioritized information set for each user. Specifically, it uses an algorithm to compare scores and sorts the information based on its importance.

[0587] Step 5:

[0588] The terminal receives customized information and notifies the user. It receives a prioritized set of information sent from the server as input. As output, it generates specific action recommendations that are displayed on the user interface. As specific action, it dynamically displays information on an interactive display device, visually highlighting information important to the end user.

[0589] (Application Example 1)

[0590] 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".

[0591] In disasters and security-related emergencies, the speed and accuracy of information acquisition and distribution are crucial. However, the ease with which misinformation spreads and the risk of inappropriate decision-making based on unreliable information are significant challenges. Furthermore, the lack of effective information provision tailored to individual user needs makes it difficult to respond quickly to specific situations.

[0592] 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.

[0593] In this invention, the server includes means for acquiring messages, means for classifying acquired messages into categories, means for evaluating the reliability of the classified messages, means for setting priorities for the evaluated messages, means for distributing information based on the priorities, means for notifying the user of information based on location information, and means for customizing notifications based on the user's individual settings. This enables rapid and reliable information distribution, allowing users to take the most appropriate action based on their situation.

[0594] A "message acquisition method" is a function for automatically collecting information transmitted and received through a communication network.

[0595] "Means of categorization" refers to the process of classifying and organizing collected information based on pre-established criteria.

[0596] "Means of evaluating reliability" refers to processes that use generative AI models or other technologies to determine the accuracy and credibility of information.

[0597] A "means of setting priorities" is a function for ranking the importance and urgency of information based on evaluated information.

[0598] "Means of distributing information" refers to a system for sending prioritized information to a user's device.

[0599] "Location-based notification methods" refer to functions that select and deliver highly relevant information based on the user's current location.

[0600] "Means for customizing notifications" refers to a mechanism for adjusting and providing information delivered according to the user's individual settings and interests.

[0601] The system implementing this invention mainly consists of three elements: a server, a terminal, and a user. The server acquires messages via a communication network and analyzes and evaluates the collected information using natural language processing and generative AI models. Specifically, the server uses an API as a means of acquiring messages and automatically collects them. Next, the collected messages are classified into categories based on pre-set criteria and their reliability is evaluated. In this process, libraries such as spaCy can be used for natural language processing, and generative AI models such as GPT-3 can be used for reliability evaluation.

[0602] The device receives information distributed from the server and notifies the user. Notifications are based on location information, and further customized information is provided. This allows the user to choose the optimal action based on their current location and individual needs. This supports quick and appropriate decision-making.

[0603] For example, if a security incident occurs in a region, this system can quickly deliver information to users' smartphones, allowing them to enhance their vigilance by checking the alerts.

[0604] An example of a prompt message is: "Please provide the latest security-related information based on the user's location. Also, evaluate the reliability of each piece of information and notify the most important ones first." Based on this prompt, appropriate information tailored to the user's individual needs will be provided.

[0605] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0606] Step 1:

[0607] The server automatically collects disaster and security-related messages using a message retrieval API over the communication network. In this process, raw data is received from the API as input, and pre-processed raw message data is generated as output.

[0608] Step 2:

[0609] The server applies natural language processing to the collected messages and classifies them into categories based on pre-defined criteria. The input is the raw message data obtained in step 1, and the output is message data organized by category. Specifically, topic modeling using tools such as spaCy is performed.

[0610] Step 3:

[0611] The server evaluates the reliability of messages classified using a generative AI model. The input is categorized message data, and the output is data with a reliability score. In this process, generative AI such as GPT-3 is used to assess reliability using prompt messages.

[0612] Step 4:

[0613] The server sets the priority of each message based on the reliability evaluation results. The input is the message data whose reliability was evaluated in step 3, and the output is a list of messages with assigned priorities. Here, scoring is performed considering urgency and reliability.

[0614] Step 5:

[0615] The server generates warning notifications based on priority and prepares them for delivery to terminals. The input is a prioritized list of messages, and the output is notification data ready for delivery. Here, the data is converted to a notification format suitable for the criteria.

[0616] Step 6:

[0617] The device receives warning notifications from the server and displays the most appropriate notification based on the user's location. The input is notification data from the server, and the output is a location-based warning presented to the user.

[0618] Step 7:

[0619] Users review notifications received on their devices and provide feedback as needed. Input is the notification information presented by the device, while output is the user's actions and feedback reflected in the system. This feedback is used for subsequent reliability evaluations and customization.

[0620] 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.

[0621] This invention relates to a system that performs information processing that takes into account not only the collection, classification, and distribution of information during disasters, but also the emotions of the user. In particular, by incorporating an emotion engine, this system realizes a new dimension of processing that analyzes the user's emotions.

[0622] First, the server retrieves messages related to the disaster area from messaging applications. This process is carried out by collecting messages in real time using existing APIs. The collected messages are analyzed using natural language processing technology. Based on the analysis results, the server classifies the messages into categories such as "searching for a person" or "searching for a pet."

[0623] Next, the server uses an emotion engine to analyze the emotions contained in the user's post. Emotion analysis is used to understand the nuances and emotional state of the user's statements, which allows for the assessment of stress and urgency during a disaster.

[0624] Furthermore, the server uses the emotions recognized by the emotion engine to evaluate the reliability of information and adjust its priority. For example, if the poster indicates a high level of tension or anxiety, the urgency of the message can be increased, allowing for a quicker response.

[0625] The organized information is then distributed from the server to the terminal. On the terminal, the user can receive and use the information in a format suitable for them. Since it also includes emotionally responsive feedback, it functions as part of user care and support.

[0626] As a concrete example, consider a scenario where a user posts a request to search for a missing pet in a disaster area. The message posted by the user may contain emotions such as "worry" or "sadness." The server's emotion engine detects these emotions and sets the urgency of the search to a higher level. This information is quickly delivered to the user on their device, allowing them to conduct efficient search operations based on that information.

[0627] Through this process, the system aims to improve the overall effectiveness of search and rescue operations by enabling the appropriate allocation of resources and psychological support during disasters.

[0628] The following describes the processing flow.

[0629] Step 1:

[0630] The server uses the messaging application's API to collect new messages related to the disaster. This allows data such as the poster's information, message body, and posting time to be collected.

[0631] Step 2:

[0632] The server analyzes the collected messages using natural language processing technology and classifies them into categories such as "searching for a person" or "searching for a pet" based on the extracted keywords.

[0633] Step 3:

[0634] The server uses an emotion engine to perform sentiment analysis on each message. It extracts emotions such as "tension," "anxiety," and "sadness" from the user's statements to understand their emotional tendencies.

[0635] Step 4:

[0636] The server reviews the urgency and importance of messages based on the analysis results from the emotion engine, and adjusts their priority. Messages that express strong emotions are given a particularly high priority.

[0637] Step 5:

[0638] The server delivers information, organized according to priority, to the relevant devices. It provides users with the information they need as needed through push notifications and dashboards.

[0639] Step 6:

[0640] The system receives information distributed to users and responds promptly. User feedback is sent to the server and used to improve the accuracy of information throughout the system.

[0641] Step 7:

[0642] The server analyzes user feedback and incorporates it into new information gathering, reliability evaluation, and sentiment analysis, thereby continuously improving the functionality of the disaster relief system.

[0643] (Example 2)

[0644] 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".

[0645] During a disaster, it is difficult to quickly and accurately extract important information from the vast amount of data generated, prioritize it appropriately, and distribute it effectively. Furthermore, there is a need to provide information that is sensitive to user emotions and to identify misinformation, but conventional systems do not adequately meet these requirements.

[0646] 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.

[0647] In this invention, the server includes means for acquiring messages, means for analyzing acquired messages using natural language processing technology and classifying them into categories, means for analyzing the emotions contained in posts and determining their urgency, means for evaluating the reliability of messages classified based on the analyzed emotions and setting priorities, and means for distributing information to terminals based on the priorities and providing feedback information that corresponds to the emotions. This enables the rapid extraction of important information during disasters and the provision of information that takes into account the user's emotions.

[0648] "Message acquisition means" refers to processes and devices for collecting relevant information in real time during a disaster, and primarily includes the function of acquiring data through communication means.

[0649] "Natural language processing technology" refers to the technology that enables computers to understand, interpret, and manipulate human language, and is primarily used for analyzing and classifying text data.

[0650] "Sentiment analysis" is a technology that extracts emotional nuances from text data to determine the user's emotional state, and it functions as a factor in evaluating the urgency and importance of a post.

[0651] "Means of evaluating reliability" refer to criteria and methods for judging the accuracy and reliability of information, and are primarily processes that take into account sentiment analysis and past data.

[0652] "Methods for setting priorities" refers to the process of organizing collected information based on its importance and urgency, and determining the order in which it will be distributed.

[0653] "Means of distributing information" refers to the mechanisms and methods for delivering organized information to a user's device, primarily through communication networks.

[0654] "Feedback information" refers to evaluation and support information provided to users, particularly information based on sentiment analysis to encourage appropriate responses.

[0655] This invention is a system that collects, classifies, and distributes information during disasters, and also processes information while considering the user's emotions. The server uses existing APIs to retrieve disaster-related messages from messaging applications via a communication network. Message collection includes platforms such as Twitter and LINE.

[0656] The server uses natural language processing libraries such as Python's NLTK and spaCy to analyze and categorize the received messages. This analysis classifies the messages into categories such as "searching for a person" or "searching for a pet."

[0657] The server also uses an emotion engine to extract emotions from text data. Sentiment analysis is performed using emotion analysis tools such as Microsoft Azure's Text Analytics API and Google Cloud's Natural Language API. This classifies the emotions contained in posts into categories such as "joy," "sadness," and "anxiety," and reliability evaluations and prioritization are performed based on the results.

[0658] The organized information is delivered from the server to the terminal. On the terminal, the user can receive the information via a dedicated application or web browser, and feedback information tailored to the urgency of the situation is also provided. Based on this information, the user can take a quick and efficient response.

[0659] For example, if a request to search for a missing pet in a disaster area is posted, the server analyzes the message and detects emotions such as "worry" and "sadness." Based on this emotion analysis, the urgency level is set to high, and the information is quickly delivered to the user on their device. This process allows users to conduct search activities efficiently.

[0660] An example of a prompt might be: "Please explain the message sentiment analysis process for disaster information gathering systems."

[0661] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0662] Step 1:

[0663] The server retrieves messages related to disaster areas from messaging applications. The input is real-time message data, which is retrieved via a communication API. The output is raw message data stored in a database or memory. Specifically, the system periodically sends requests through an existing API (e.g., the Twitter API) to retrieve messages and write them to storage.

[0664] Step 2:

[0665] The server analyzes the messages it receives using natural language processing techniques and classifies them into categories. The input is collected message data located in a database or memory. This data is tokenized using Python's natural language processing libraries (NLTK or spaCy), and important keywords are extracted. The output is message data with categories added. Specifically, the server analyzes each message and automatically classifies them into categories such as "searching for a person" or "searching for a pet."

[0666] Step 3:

[0667] The server analyzes the emotions contained in the messages. The input is a message with categories attached, and an emotion analysis tool (e.g., Microsoft Azure's Text Analytics API) is applied to this data. The output is message data with emotion scores attached. Specifically, the server adds emotion categories such as "joy" and "anxiety" to the messages based on the emotion analysis results.

[0668] Step 4:

[0669] The server evaluates the reliability and prioritizes classified messages based on sentiment analysis. The input is message data with sentiment scores. Using this data, it executes logic to analyze the reliability of the information and determine its priority. The output is a list of messages with assigned priorities. Specifically, the server evaluates urgency and the reliability of the information, and if a message indicates high urgency, its priority is increased.

[0670] Step 5:

[0671] The system delivers information from the server to the terminal and provides emotionally responsive feedback. The input is a prioritized list of messages. The output is the information and feedback data delivered to the user's terminal. Specifically, the server sends organized information to the terminal as push notifications or emails, and the user receives the information in an appropriate format. This allows users to quickly take necessary actions during a disaster.

[0672] (Application Example 2)

[0673] 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".

[0674] During disasters, information becomes chaotic, making it difficult to immediately determine which information is urgent. Furthermore, there is a lack of information provision that considers users' emotions, resulting in inadequate care and support for users who are feeling anxious.

[0675] 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.

[0676] In this invention, the server includes means for acquiring messages, means for classifying acquired messages into categories, and means for analyzing the sentiment of the messages. This makes it possible to prioritize the delivery of information that is of high urgency, taking into account the user's emotions. It also enables the provision of emotionally supportive information tailored to the user.

[0677] "Means of acquiring messages" refers to the function of collecting disaster-related text data in real time via a communication network.

[0678] "Means of categorization" refers to a function that organizes acquired messages based on specific conditions, categorized by themes such as "searching for people" or "shortage of supplies."

[0679] "Methods for analyzing emotions" refer to technologies that analyze the text of a message to quantify or qualitatively determine the sender's emotions and sensibilities.

[0680] The "means of setting urgency" refer to a function that dynamically determines the importance and priority of a message based on information obtained through sentiment analysis.

[0681] "Means of distributing information" refers to a system that effectively and quickly transfers information to relevant users and devices according to the set level of urgency.

[0682] In implementing this invention, the server first collects disaster-related messages in real time via a communication network. Existing messaging APIs can be used for this purpose, and the data is aggregated on the server. Subsequently, the server uses natural language processing technology to analyze the messages as text data and classify each message into categories such as "search for people" or "shortage of supplies." In this process, the Google Cloud Natural Language API is utilized to achieve rapid and accurate analysis.

[0683] Subsequently, the server uses an emotion analysis engine to quantify or qualitatively determine the user's emotions from the retrieved messages. This emotion analysis uses emotion analysis software such as SentiStrength. Based on the analysis results, the server sets the urgency of the message. In doing so, it considers the intensity and type of emotion to identify information that should be addressed as a priority.

[0684] Ultimately, the server quickly delivers information to user terminals according to the configured urgency level. This allows users to receive information relevant to their situation and take appropriate action. For example, if a user in a flood-affected area posts a message based on "anxiety" and "fear," that information is quickly distributed to nearby residents, who are then guided to safe evacuation locations.

[0685] As a concrete example, a prompt message could read, "An evacuation order has been issued due to flooding. If you are feeling anxious, please find the following resources to help alleviate your worries." In this way, by adjusting the content of the messages based on the user's emotions, it is possible to provide appropriate care to the user.

[0686] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0687] Step 1:

[0688] The server acquires disaster-related messages via a communication network. It uses data received in real time from a messaging platform as input. The output is unanalyzed message data stored in the server's data storage. This operation aggregates information from the field during a disaster.

[0689] Step 2:

[0690] The server uses natural language processing technology to analyze the text data of the acquired messages. The input is the message data saved in the previous step. The output is the category information of the analyzed messages. By classifying them into categories such as "searching for people" or "shortage of supplies," the messages are organized based on their content.

[0691] Step 3:

[0692] The server uses an emotion analysis engine to analyze the user's emotions from the message. The input is the text data of the analyzed message, and the output is emotion data that has been quantified or qualitatively determined. In this step, software such as SentiStrength is used to determine the user's emotional state.

[0693] Step 4:

[0694] The server sets the urgency of a message based on the sentiment analysis results. The input is the analyzed sentiment data, and the output is a numerical value or indicator of urgency. For example, if anxiety or fear is strong, a high urgency level will be set. This operation contributes to prioritizing information.

[0695] Step 5:

[0696] The server delivers information to terminals according to the configured urgency level. Input consists of messages and category information with set urgency levels, while output is push notifications and alerts delivered to the user's terminal. This allows users to quickly and accurately obtain information and take appropriate action.

[0697] 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.

[0698] 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.

[0699] 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.

[0700] 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.

[0701] 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.

[0702] 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.

[0703] 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.

[0704] 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.

[0705] 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."

[0706] 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.

[0707] 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.

[0708] 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.

[0709] 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.

[0710] 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.

[0711] 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.

[0712] 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.

[0713] 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.

[0714] 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.

[0715] 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.

[0716] 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.

[0717] 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 as being incorporated by reference.

[0718] The following is further disclosed regarding the embodiments described above.

[0719] (Claim 1)

[0720] Message acquisition method,

[0721] A means of classifying the acquired messages into categories,

[0722] A means for evaluating the reliability of classified messages,

[0723] A means of setting the priority of evaluated messages,

[0724] A means of distributing information based on priority,

[0725] A system that includes this.

[0726] (Claim 2)

[0727] The system according to claim 1, comprising means for identifying misinformation from evaluated messages.

[0728] (Claim 3)

[0729] The system according to claim 1, comprising means for receiving user feedback.

[0730] "Example 1"

[0731] (Claim 1)

[0732] Message acquisition method,

[0733] A means for classifying acquired messages into categories using natural language processing techniques,

[0734] A means for evaluating the reliability of classified messages using a generative artificial intelligence model,

[0735] A means to prioritize evaluated messages and customize information based on the user's location and individual needs,

[0736] A means for delivering customized information to an interactive display device,

[0737] A system that includes this.

[0738] (Claim 2)

[0739] The system according to claim 1, comprising means for identifying misinformation and duplicate information from evaluated messages.

[0740] (Claim 3)

[0741] The system according to claim 1, comprising means for receiving user feedback and reflecting that feedback in information customization.

[0742] "Application Example 1"

[0743] (Claim 1)

[0744] Message acquisition method,

[0745] A means of classifying the acquired messages into categories,

[0746] A means for evaluating the reliability of classified messages,

[0747] A means of setting the priority of evaluated messages,

[0748] A means of distributing information based on priority,

[0749] A means of notifying the user of information based on location information,

[0750] A means to customize notifications based on individual user settings,

[0751] A system that includes this.

[0752] (Claim 2)

[0753] The system according to claim 1, comprising means for identifying misinformation from evaluated messages.

[0754] (Claim 3)

[0755] The system according to claim 1, comprising means for receiving user feedback.

[0756] "Example 2 of combining an emotion engine"

[0757] (Claim 1)

[0758] Message acquisition method,

[0759] A means for analyzing the acquired messages using natural language processing techniques and classifying them into categories,

[0760] A means of analyzing the emotions contained in a post and determining its urgency,

[0761] A means of evaluating the reliability of messages classified based on analyzed emotions and setting priorities,

[0762] A means of delivering information to devices based on priority and providing emotionally responsive feedback,

[0763] A system that includes this.

[0764] (Claim 2)

[0765] The system according to claim 1, comprising means for identifying misinformation from messages evaluated based on sentiment analysis.

[0766] (Claim 3)

[0767] The system according to claim 1, comprising means for receiving emotionally responsive feedback from users.

[0768] "Application example 2 when combining with an emotional engine"

[0769] (Claim 1)

[0770] Means of obtaining messages,

[0771] A means of classifying the acquired messages into categories,

[0772] A means of analyzing the emotions in a message,

[0773] A means of setting the urgency of a message based on analyzed emotions,

[0774] A means of setting priorities based on urgency,

[0775] A means of distributing information based on priority,

[0776] A system that includes this.

[0777] (Claim 2)

[0778] The system according to claim 1, comprising means for identifying misinformation from evaluated messages.

[0779] (Claim 3)

[0780] The system according to claim 1, comprising means for receiving user feedback. [Explanation of symbols]

[0781] 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. Message acquisition method, A means of classifying the acquired messages into categories, A means for evaluating the reliability of classified messages, A means of setting the priority of evaluated messages, A means of distributing information based on priority, A system that includes this.

2. The system according to claim 1, comprising means for identifying misinformation from evaluated messages.

3. The system according to claim 1, further comprising means for receiving user feedback.

Images