System

Abstract

A system is provided.SOLUTION: A system comprising: means for acquiring a current position of a user; means for referring to data of past incident, accident, and disaster risks based on the acquired current position; means for analyzing the referred data and calculating a risk degree in a score form; and means for displaying the calculated risk degree score to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] In modern society, there is a growing need for users to know the real-time risk level of an area when traveling through urban areas or areas with high disaster risk. However, conventional systems lacked the means to integrate data on individual incidents, accidents, and disaster risks and comprehensively evaluate risk levels based on specific locations. This made it difficult for users to quickly obtain accurate information to ensure their own safety. Furthermore, conventional systems lacked the ability to display risk levels in a score format, making them difficult to present in an easy-to-understand format. [Means for solving the problem]

[0005] In order to solve the above-mentioned problems, the present invention provides the following means. A system is provided that includes a means for acquiring a user's current location, a means for referencing data on past incidents, accidents, and disaster risks based on the acquired current location, a means for analyzing the referenced data and calculating a risk level in the form of a score, and a means for displaying the calculated risk level score to the user. This system enables a user to grasp the risk level in real time based on their current location and take appropriate action. Furthermore, by adding a means for analyzing data using natural language processing and a means for displaying a risk level score in a range from 0 to 10, more accurate information can be provided. Furthermore, by including a means for acquiring the current location using a GPS module, the reliability and accuracy of the system are improved.

[0006] "Current location" indicates the exact location of the user using a GPS module or other location information acquisition means.

[0007] A "GPS module" is a device that receives signals from satellites and measures the current latitude and longitude.

[0008] An "incident" is a socially significant, unexpected occurrence, accident, or criminal act.

[0009] An "accident" is an incident that occurs as a result of an unexpected event and results in injury to persons or damage to property.

[0010] "Disaster risk" refers to dangerous situations or events that may occur due to natural disasters or man-made factors.

[0011] A "database" is a system that stores large amounts of data in an organized manner and allows it to be searched and retrieved under specific conditions.

[0012] "Reference" refers to the act of retrieving and using necessary information from another location (such as a database).

[0013] "Analysis" is the process of examining the acquired data in detail and discovering its meaning and trends.

[0014] The "score format" is a format in which the analysis results are converted into numbers such as 0 to 10 and displayed in a visually easy-to-understand manner.

[0015] "Display" refers to the act of visually providing information to a user through a terminal screen or the like. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0017] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0020] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0021] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0036] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0037] The present invention is a system that analyzes the risk of past incidents, accidents, and disasters based on the user's current location and displays the risk level of the area in the form of a score. Specific embodiments of this system will be described below.

[0038] First, the device held by the user is equipped with a GPS module. Using this GPS module, the device obtains the user's current location. For example, if the user is in Shibuya Ward, Tokyo, the device will obtain location information such as latitude 35.6623 and longitude 139.7034.

[0039] Once the location information is acquired, the device sends it to a server, which then queries a database to retrieve data on past incidents, accidents, and disaster risks. The data retrieved includes a series of past events and risk information related to the area.

[0040] The server analyzes the data retrieved from the database. Specifically, it utilizes chat generation AI and natural language processing technology to analyze patterns of past incidents and disasters. This allows it to calculate the level of danger in the area in the form of a score (for example, a number from 0 to 10). The score calculated in this way is intended to provide users with an intuitive, easy-to-understand indication of the danger level in the area.

[0041] After the score is calculated, the server sends the result to the terminal. The terminal analyzes the received data and displays the risk score to the user through a GUI (graphical user interface). For example, it may display a message such as, "The risk score for this area is 7 / 10."

[0042] As a concrete example, consider the case where a user is walking around Shibuya Ward while shopping. At this time, the device uses a GPS module to obtain the user's current location and sends this information to the server. The server retrieves past incident and accident data for Shibuya Ward from a database and calculates a danger score using natural language processing with a chat generation AI. Based on this analysis, the danger score for Shibuya Ward is calculated to be "7 / 10," and the server sends this score to the device. The device receives this score and displays on the user's screen, "The danger score for this area is 7 / 10." The user can view this information to understand the safety of the area they are in.

[0043] As described above, this system allows users to determine the risk level of their current location in real time and obtain reference information for taking safe actions. This function is extremely useful, especially when traveling in urban areas or areas with high disaster risk.

[0044] From this description, it will be understood that a specific embodiment of the present invention is shown, and that the present invention is a system that provides assistance to users in confirming safety anytime and anywhere.

[0045] The processing flow will be explained below.

[0046] Step 1: The device gets the user's current location

[0047] The device activates its built-in GPS module and acquires information about its current location. Specifically, the device receives signals from satellites and calculates its latitude and longitude. This location information is stored in the device's temporary memory.

[0048] Step 2: The device sends its location and request to the server

[0049] The device packages the user's request based on the location information it acquires. For example, if a user requests to know the current level of danger, the device combines the location information and the request into a single data package and sends it to the server over the network.

[0050] Step 3: The server retrieves the necessary data from the database

[0051] The server analyzes the data package received from the device and retrieves data on relevant past incidents, accidents, and disaster risks from a database based on the device's current location. Specifically, the server issues a database query using the location information as a key to retrieve the relevant data.

[0052] Step 4: The server parses the data

[0053] Based on the acquired data, the server uses chat generation AI to perform natural language processing. Specifically, it analyzes past data and identifies patterns of incidents, accidents, and disasters related to the current location. This then scores the area's risk level on a scale of 0 to 10.

[0054] Step 5: The server packages the analysis results and sends them to the device.

[0055] The server compiles the calculated risk score and related data into a package, which is then sent to the device via the network.

[0056] Step 6: The device receives the analysis results and displays them to the user

[0057] The device analyzes the data package received from the server and extracts a risk score. The device then launches a GUI and displays the result to the user, such as "The risk score for this area is 7 / 10."

[0058] Step 7: User confirms the results

[0059] Users can check their device screen and understand the risk score for their current location, which can provide them with information to help them decide on their course of action in that area.

[0060] Example 1

[0061] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0062] Currently, it is difficult for users to grasp their own safety in real time while traveling or out. In addition, there is a lack of means to instantly obtain information on past incidents, accidents, disaster risks, etc., and to intuitively understand the specific level of danger. As a result, the risk of encountering high-risk areas increases, potentially threatening the user's safety.

[0063] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0064] In this invention, the server includes a means for acquiring the user's current location, a means for referencing past risk data, and a means for analyzing the data and calculating a risk score, thereby enabling the user to grasp the risk level based on their current location in real time and take safe actions.

[0065] "User" refers to an individual or corporation that uses the system to obtain risk information about their current location.

[0066] "Current location" refers to the user's actual geographic location obtained through a GPS module or other location information acquisition means.

[0067] "Risk data" refers to data that comprehensively includes information on past incidents, accidents, and disaster risks.

[0068] "Database" refers to an information processing system for structuring and storing risk data.

[0069] "GPS module" refers to a hardware device for obtaining current location using the Global Positioning System.

[0070] The term "server" refers to an information processing device that analyzes risk data based on location information received from a user's terminal and returns the results to the terminal.

[0071] "Terminal" refers to a portable information processing device that is owned by a user and has a GPS module and communication functions.

[0072] "Chat generation AI" refers to artificial intelligence that uses natural language processing technology to analyze data and is designed to be able to have natural conversations with humans.

[0073] A "prompt sentence" refers to a sentence of instructions or questions that is entered into the chat generation AI to perform analysis.

[0074] An "HTTP request" refers to a form of communication protocol that a terminal sends to a server to request data.

[0075] "Danger score" refers to a numerical assessment of the danger level of a particular area based on data analysis.

[0076] "GUI" is an abbreviation for Graphical User Interface, and refers to an interface that provides information to users visually.

[0077] MODE FOR CARRYING OUT THE INVENTION

[0078] The present invention is a system that analyzes past incidents, accidents, and disaster risks based on the user's current location and displays the risk level of the area in the form of a score.

[0079] First, the user has a device equipped with a GPS module. This device uses the GPS module to obtain the user's current location. For example, if the user is in Shibuya Ward, Tokyo, the device will obtain location information such as latitude 35.6623 and longitude 139.7034.

[0080] The device then sends the location information to a server, typically via an HTTP request, which queries a database for past incidents, accidents, and disaster risk data.

[0081] The server uses a chat generation AI model to analyze past data. This AI model uses natural language processing technology to analyze risk data and calculate the risk level of the area in the form of a score. Specifically, the AI ​​is input with the prompt "Please give me an overview of incidents and accidents in Shibuya Ward over the past three years" to perform the analysis.

[0082] Once the analysis is complete, the server sends the calculated risk score to the device. Based on the received data, the device displays the risk score to the user via a GUI (graphical user interface). For example, the device might display "The risk score for this area is 7 / 10."

[0083] As a concrete example, consider the case where a user is walking around Shibuya Ward while shopping. At this time, the device uses a GPS module to obtain the user's current location and sends this information to the server. The server retrieves past incident and accident data for Shibuya Ward from a database and calculates a danger score using natural language processing with a chat generation AI. Based on this analysis, the danger score for Shibuya Ward is calculated to be "7 / 10," and the server sends this score to the device. The device receives this score and displays the message "The danger score for this area is 7 / 10" on the user's screen.

[0084] As described above, this system allows users to determine the risk level of their current location in real time and obtain reference information for safe behavior, which is particularly useful when traveling through urban areas or areas with high disaster risk.

[0085] The hardware used includes a GPS module and a terminal, and the software used includes a database management system, an HTTP communication library, a chat generation AI model, and a natural language processing library. By implementing this technology, users can obtain a real-time risk score and understand their safety.

[0086] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0087] Specific explanation of processing steps

[0088] Step 1: Get current location

[0089] A user carries a device with a GPS function.

[0090] Input: The user's current geographic location

[0091] The device periodically activates the GPS module and obtains its current location (latitude and longitude).

[0092] Output: Current location (e.g., latitude 35.6623, longitude 139.7034)

[0093] Specific behavior: The code is implemented so that the device obtains location information using the GPS API.

[0094] Step 2: Send location information

[0095] The device sends the current location data it has acquired to the server via an HTTP request.

[0096] Input: Current location (latitude and longitude)

[0097] Output: Location information sent to the server

[0098] Specific operation: The device generates an HTTP request and posts the location information to the server in JSON format or similar.

[0099] Step 3: Obtaining historical data

[0100] Based on the location information received by the server, an SQL query is issued to the database to retrieve data on past incidents, accidents, and disaster risks.

[0101] Input: Location information sent to the server

[0102] The server issues a query to the database such as "SELECT FROM risk_data WHERE latitude=35.6623 AND longitude=139.7034".

[0103] Output: Past incidents, accidents, and disaster risk data

[0104] Specific operation: The server retrieves data from the database using an ORM such as SQLAlchemy.

[0105] Step 4: Analyze the data

[0106] The server uses chat generation AI and natural language processing technology to analyze past data.

[0107] Input: Historical risk data

[0108] The server inputs the prompt text "Please give me an overview of the incidents and accidents in Shibuya Ward over the past three years" into the chat generation AI, and the AI ​​performs the analysis.

[0109] Output: Hazard score for the area (e.g. 7 / 10)

[0110] Specific operation: The server sends a prompt to the AI ​​model and receives the analysis results.

[0111] Data processing: Analyze regular text data and convert it into a numerical risk score.

[0112] Step 5: Submit your score

[0113] The server sends the calculated risk score to the terminal in JSON format as an HTTP response.

[0114] Input: Calculated risk score

[0115] Output: Risk score sent to the device

[0116] Specific operation: The server generates an HTTP response and sends the risk score in JSON format to the device.

[0117] Step 6: View your score

[0118] The risk score received by the terminal is displayed to the user via a GUI (graphical user interface).

[0119] Input: Risk score sent from the server

[0120] Output: Risk score displayed to the user

[0121] Specific operation: The device uses JavaScript or native application code to dynamically display the risk score on the screen.

[0122] Example: The device screen displays, "The danger score for this area is 7 / 10."

[0123] (Application example 1)

[0124] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0125] With conventional safety confirmation systems, it was difficult for users to immediately grasp the risk level of their current location. Furthermore, there was a lack of a well-established mechanism for displaying the risk level of a location in real time, which could lead to delayed safety measures. Furthermore, there was a lack of technology to analyze detailed data on past incidents and disaster risks when calculating risk scores.

[0126] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0127] In this invention, the server includes a means for referencing data on past incidents, accidents, and disaster risks based on location information, a means for analyzing the referenced data using natural language processing technology and calculating a risk score using a generation AI model, and a means for displaying the risk score in real time, thereby enabling the user to instantly grasp the risk level of the area where they are currently located and take safe actions based on the risk score displayed in real time.

[0128] The "current location" is location information that indicates the latitude and longitude of the user when he or she is at a specific point.

[0129] The "reference means" is a means for obtaining data on incidents, accidents, and disaster risks that have occurred in the past from a database based on the user's current location.

[0130] The "means of analysis" refers to a method for calculating the risk level of an area in the form of a score based on the acquired data on past incidents, accidents, and disaster risks.

[0131] The "display means" is a means for visually presenting the calculated risk score to the user.

[0132] A "database" is an information system that accumulates information on past incidents, accidents, and disaster risks and stores it in a searchable format.

[0133] "Natural language processing" is a technology that allows computers to understand and analyze human language.

[0134] A "generative AI model" is an artificial intelligence model that learns patterns from past data to generate or analyze new data.

[0135] A "Global Positioning System (GPS) module" is a device that receives signals from satellites and uses them to determine one's current location on Earth.

[0136] A "prompt sentence" is an input sentence that gives specific analysis and generation instructions to a generative AI model.

[0137] The present invention is a system that analyzes the risk of past incidents, accidents, and disasters based on the user's current location and displays the risk level of the area in the form of a score. Specific embodiments of this system will be described below.

[0138] First, the device is equipped with a Global Positioning System (GPS) module, which allows the device to obtain the user's current location. For example, if the user is traveling within a metropolitan area, the device will obtain latitude and longitude location information.

[0139] Once the location information is acquired, the device sends it to a server. The server then uses the received location information to reference a database of data on past incidents, accidents, and disaster risks. The database contains detailed information on past incidents, accidents, and disaster risks.

[0140] The server analyzes the data retrieved from the database. This analysis uses natural language processing technology and a generative AI model to analyze patterns of past incidents and disasters. This pattern analysis calculates the risk level in the area in the form of a score (for example, a number from 0 to 10). Using a generative AI model makes it possible to calculate a risk score with greater accuracy.

[0141] After calculating the risk score, the server sends the results to the terminal. The terminal analyzes the received data and displays the risk score to the user in real time through a graphical user interface (GUI). For example, it may display "The risk score for this area is 7 / 10." This allows the user to instantly understand the safety of the area and obtain reference information for taking safe actions.

[0142] As a concrete example, consider a user walking through an unfamiliar city at night. The device uses a GPS module to obtain the user's current location and sends that information to a server. The server then retrieves past incident and accident data for that city from a database and analyzes it using natural language processing technology. A highly accurate risk score is calculated using a generative AI model. For example, if the analysis determines that "the risk score for this area is 8 / 10," the server sends this score to the device. The device receives this score and displays "The risk score for this area is 8 / 10" on the user's screen. By viewing this information, the user can immediately understand the safety of the area and take safety-first actions.

[0143] An example prompt is:

[0144] The user is currently in Shinjuku Ward. Please calculate the risk score for this area based on incident, accident, and disaster risk data for Shinjuku Ward over the past five years. The score should be a number between 0 and 10, and should be output as, for example, "The risk score for this area is 7 / 10."

[0145] In this way, the present invention is a system that allows a user to immediately grasp the degree of danger in the area where he or she is currently located and provides useful information for quickly taking safety measures.

[0146] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0147] Step 1:

[0148] The device uses the GPS module to obtain the user's current location (latitude and longitude), which is used as input data.

[0149] Step 2:

[0150] The device sends the current location information (latitude and longitude) to the server.

[0151] Step 3:

[0152] Based on the location information received by the server, a query is issued to the database to retrieve data on past incidents, accidents, and disaster risks. This query outputs past data related to the specified location information from the database.

[0153] Step 4:

[0154] The server analyzes data on past incidents, accidents, and disaster risks using generative AI models and natural language processing technology. This analysis calculates a risk score for the area. The input data is data on past incidents, accidents, and disaster risks, and the output data is the risk score.

[0155] Step 5:

[0156] The server sends the calculated risk score to the terminal. The data sent is the risk score.

[0157] Step 6:

[0158] The terminal analyzes the received risk score and displays it to the user in real time through a graphical user interface (GUI). The operation is to visually present the risk score to the user.

[0159] Step 7:

[0160] The user checks the screen of the device and takes safe actions based on the risk score displayed in real time. In this step, the risk score plays a role in supporting the user's decision-making.

[0161] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0162] The present invention combines a system that analyzes past incidents, accidents, and disaster risks based on the user's current location and displays the risk level of the area in the form of a score with an emotion engine that recognizes the user's emotions. A specific embodiment of this system will be described below.

[0163] First, the user's device is equipped with a GPS module and an emotion recognition engine. Using the GPS module, the device obtains the user's current location. For example, if the user is in Shibuya Ward, Tokyo, the device obtains location information such as latitude 35.6623 and longitude 139.7034.

[0164] Once the location information is acquired, the device sends this location information and the user's emotional data acquired by the emotion recognition engine to the server. The emotion recognition engine analyzes the user's emotions using voice input or a facial recognition camera. Specifically, if the user indicates an emotion such as "I'm nervous right now," that information is also sent to the server.

[0165] Based on the received location information and emotion data, the server issues a query to the database to reference data on past incidents, accidents, and disaster risks. This query retrieves past data for the relevant area.

[0166] The server then analyzes the data retrieved from the database. Utilizing chat generation AI and natural language processing technology, the server analyzes patterns of past incidents and disasters. The results of this analysis are combined with the user's emotional data to calculate the danger level of the area in the form of a score. For example, if the user is nervous, the danger score may be set higher.

[0167] After the score is calculated, the server sends the results to the device, which analyzes the data and displays the risk score to the user through a GUI. For example, it might say, "The risk score for this area is 7 / 10. Caution is advised."

[0168] As a concrete example, consider a user walking through Shibuya Ward while shopping. At this time, the device uses a GPS module to obtain the user's current location and sends that information to the server. At the same time, emotional data, which the user recognizes as "anxiety," is also sent. The server retrieves past incident and accident data for Shibuya Ward from a database and uses natural language processing with chat generation AI to calculate a danger score. Based on this analysis, the danger score for Shibuya Ward is calculated as "7 / 10." The emotional data is then taken into account and the score is finally adjusted to "7.5 / 10." The server then sends this score to the device. The device receives the score and displays a message on the user's screen saying, "The danger score for this area is 7.5 / 10. Caution is advised." Using this information, the user can understand the safety of their area.

[0169] As described above, this system, which combines an emotion recognition engine, allows users to determine the risk level of their current location in real time with greater accuracy, and provides reference information for taking safe actions. This type of function is extremely useful, especially when traveling in urban areas or areas with a high risk of disasters.

[0170] From this description, it will be understood that a specific embodiment of the present invention is shown, and that the system provides assistance to users in checking information that takes into consideration their safety and their emotional state, anytime and anywhere.

[0171] The processing flow will be explained below.

[0172] Step 1: The device gets the user's current location

[0173] The device activates its built-in GPS module and acquires information about its current location. Specifically, the device receives signals from satellites and calculates its latitude and longitude. This location information is stored in the device's temporary memory.

[0174] Step 2: The device recognizes the user's emotions

[0175] The device's built-in emotion recognition engine detects the user's emotions. It uses voice input and a facial recognition camera to determine the user's emotions and generates emotion data such as "tension," "anxiety," or "relaxation." This emotion data is also temporarily stored on the device.

[0176] Step 3: The device sends location and emotion data to the server.

[0177] The device packages the location information and emotion data it acquires and sends them to a server via the network. Specifically, location information (e.g., latitude 35.6623, longitude 139.7034) and emotion data (e.g., "anxiety") are combined into a single data package.

[0178] Step 4: The server retrieves the necessary data from the database

[0179] The server analyzes the location and emotion data received from the device and issues a database query based on the location information. The database returns data on past incidents, accidents, and disaster risks related to the area to the server.

[0180] Step 5: The server parses the data

[0181] Using the acquired data, the server operates a chat generation AI. Specifically, it analyzes data on past incidents, accidents, and disaster risks using natural language processing technology, and calculates the risk level in the form of a score (e.g., 0 to 10) taking into account location information and emotional data. If the emotional data indicates "anxiety," the risk score is adjusted higher.

[0182] Step 6: The server packages the analysis results and sends them to the device.

[0183] The server combines the calculated risk score and analysis data into a single package and sends it to the terminal.

[0184] Step 7: The device receives the analysis results and displays them to the user

[0185] The device analyzes the data package received from the server and extracts a risk score.The device then launches a GUI and displays the results to the user in the form of, for example, "The risk score for this area is 7.5 / 10. Caution is advised."

[0186] Step 8: User confirms the results

[0187] Users can check their device screen and understand the risk score for their current location, which can help them decide how to proceed in that area.

[0188] Example 2

[0189] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0190] Conventional risk assessment systems display the risk level of a user's current area in the form of a score based on past incident, accident, and disaster risk data, but do not take the user's emotional state into consideration. As a result, risk assessments cannot reflect the user's subjective feelings, such as anxiety or a sense of security, and risk scores may not be appropriate for the user. Therefore, there is a need for a method of more accurate and practical risk assessment for users that takes the user's emotional state into consideration.

[0191] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0192] In this invention, the server includes a means for acquiring the user's current location, a means for acquiring data on past incidents, accidents, and disaster risks from a database, and a means for analyzing the data using natural language processing, thereby enabling risk assessment that reflects the user's emotional state.

[0193] "User's current location" is data that indicates the geographic location of a user at a particular time, typically expressed as latitude and longitude coordinate information.

[0194] An "incident" is data that indicates a criminal act that occurred at a specific place and time.

[0195] An "incident" is data that indicates an unexpected adverse occurrence caused by human or natural factors.

[0196] "Disaster risk" is data that indicates the danger that may occur due to natural or man-made disasters.

[0197] A "database" is a system that systematically stores information on past incidents, accidents, and disaster risks.

[0198] "Emotion recognition" is a technology that analyzes and determines a user's emotional state from their voice, facial expressions, etc.

[0199] "Natural language processing" is a technology that enables computers to understand and analyze human language.

[0200] The "risk score" is a numerical representation of the risk in a particular location, and is an index that indicates the risk level for the user.

[0201] A "server" is a computer system for processing and storing data.

[0202] A "terminal" is a computing device that is directly operated by a user.

[0203] MODE FOR CARRYING OUT THE INVENTION

[0204] The present invention combines a system that analyzes past incidents, accidents, and disaster risks based on the user's current location and displays the risk level of the area in the form of a score with an emotion engine that recognizes the user's emotions. A specific embodiment of this system will be described below.

[0205] First, the device held by the user is equipped with a GPS module and an emotion recognition engine. Using the GPS module, the device obtains the user's current location. For example, if the user is in Shibuya Ward, Tokyo, the device obtains location information such as latitude 35.6623 and longitude 139.7034.

[0206] Once the location information is acquired, the device sends this location information and the user's emotional data acquired by the emotion recognition engine to the server. The emotion recognition engine analyzes the user's emotions using voice input or a facial recognition camera. Specifically, if the user expresses emotions such as "I'm nervous" or "anxious," that information is also sent to the server.

[0207] Based on the received location information and emotion data, the server issues a query to the database to reference data on past incidents, accidents, and disaster risks. This query retrieves past data for the relevant area.

[0208] The server then analyzes the data retrieved from the database. It uses natural language processing technology to analyze patterns of past incidents and disasters. The results of this analysis are combined with the user's emotional data to calculate the danger level of the area in the form of a score. For example, if the user is nervous, the danger score may be set higher.

[0209] After the score is calculated, the server sends the results to the device, which analyzes the data and displays the risk score to the user through a GUI. For example, it might say, "The risk score for this area is 7 / 10. Caution is advised."

[0210] As a concrete example, consider the case where a user is walking around Shibuya Ward while shopping. At this time, the device uses a GPS module to obtain the user's current location and sends that information to the server. At the same time, emotional data, which the user recognizes as "anxiety," is also sent. The server retrieves past incident and accident data for Shibuya Ward from a database and calculates a danger score using natural language processing technology. Based on this analysis, the danger score for Shibuya Ward is calculated to be "7 / 10." The emotional data is then taken into account and the score is finally adjusted to "7.5 / 10." The server then sends this score to the device. The device receives this score and displays a message on the user's screen saying, "The danger score for this area is 7.5 / 10. Caution is advised." Using this information, the user can understand the safety of their area.

[0211] An example prompt for querying the generative AI model about this system is as follows:

[0212] plaintext

[0213] We have a system that analyzes past incidents, accidents, and disaster risks based on the user's current location and emotional data, and displays the risk level in the form of a score. For example, if a user feels "anxious" in Shibuya Ward, the system will display the risk level score for that area as "7.5 / 10." Please tell me the specific processing steps of this system.

[0214] As described above, this system integrates a risk assessment function based on the user's current location and emotional data, allowing users to check the safety of the area in real time, providing useful information for travel, especially in urban areas and areas with high disaster risk.

[0215] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0216] Processing flow

[0217] Step 1: Get the user's current location

[0218] explanation

[0219] The GPS module installed on the device is activated and the user's current location is obtained. The hardware used is a GPS module.

[0220] Input and Output

[0221] Input: None (the device itself obtains the current location)

[0222] Data processing and data calculation: The GPS module calculates the position information from the satellite signals

[0223] Output: Latitude and longitude (e.g. 35.6623, 139.7034)

[0224] Specific actions

[0225] When the user is in Shibuya Ward, the device activates the GPS module and obtains location information of latitude 35.6623 and longitude 139.7034.

[0226] Step 2: Obtain user emotion data

[0227] explanation

[0228] The emotion recognition engine installed in the device is activated, and emotion data is acquired using the user's voice input or facial expression recognition camera.

[0229] Input and Output

[0230] Input: Audio data or video data (user's facial expression)

[0231] Data processing and data calculation: Estimating emotional states through speech or image analysis

[0232] Output: Emotion data such as "anxiety"

[0233] Specific actions

[0234] If the user is feeling anxious, the device's emotion recognition engine analyzes their voice and facial expressions, and as a result, obtains the emotion data "anxiety."

[0235] Step 3: Send location and emotion data to the server

[0236] explanation

[0237] When the location information and emotion data acquired by the device is sent to the server, it is encrypted using SSL / TLS to ensure the security of the data.

[0238] Input and Output

[0239] Input: Location (35.6623, 139.7034) and emotion data ("anxiety")

[0240] Data processing and data calculation: Data is organized into packets, encrypted, and sent to the server

[0241] Output: Data sent to server completed

[0242] Specific actions

[0243] The device sends location information (35.6623, 139.7034) and emotion data ("anxiety") to the server using SSL / TLS encryption.

[0244] Step 4: Retrieve historical data from the database

[0245] explanation

[0246] Based on the location information and emotion data received by the server, a query is issued to the database to obtain data on past incidents, accidents, and disaster risks.

[0247] Input and Output

[0248] Input: Location information (35.6623, 139.7034)

[0249] Data manipulation and data calculations: Search past data using SQL queries

[0250] Output: Past incidents, accidents, and disaster data for a specific area (Shibuya Ward)

[0251] Specific actions

[0252] The server queries the database based on the location information and retrieves data on past incidents, accidents, and disasters in Shibuya Ward.

[0253] Step 5: Data analysis and risk score calculation

[0254] explanation

[0255] The server combines the data acquired with the user's emotional data and calculates a risk score using natural language processing technology.

[0256] Input and Output

[0257] Input: Past incident, accident, and disaster data and emotional data ("anxiety")

[0258] Data processing and data calculations: Analyze data using natural language processing techniques and generative AI models to calculate risk scores

[0259] Output: Risk score (e.g. 7.5 / 10)

[0260] Specific actions

[0261] The server uses past data and the user's emotional data of "anxiety" to perform an analysis using natural language processing and calculates a risk score of 7.5 / 10.

[0262] Step 6: Submit your risk score

[0263] explanation

[0264] The server sends the calculated risk score to the terminal.

[0265] Input and Output

[0266] Input: Risk Score (7.5 / 10)

[0267] Data processing and calculation: The scores are packed into packets and sent to the terminal.

[0268] Output: Data sent to the terminal completed

[0269] Specific actions

[0270] The server sends a risk score of 7.5 / 10 to the device.

[0271] Step 7: View your risk score

[0272] explanation

[0273] The device analyzes the received risk score and displays it to the user using a GUI.

[0274] Input and Output

[0275] Input: Risk Score (7.5 / 10)

[0276] Data processing and data calculation: converting scores into a format that can be displayed in the GUI

[0277] Output: Display of danger score (e.g. "This area has a danger score of 7.5 / 10. Caution required.")

[0278] Specific actions

[0279] The device receives a danger score of 7.5 / 10 and displays on the GUI, "The danger score for this area is 7.5 / 10. Caution is required."

[0280] (Application example 2)

[0281] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0282] In recent years, advances in autonomous driving technology have led to an increasing number of people using autonomous vehicles. However, there are limited ways for users to know the safety of the area they are traveling in real time, which puts them at risk of entering dangerous areas. In addition, a user's emotional state can affect their driving; for example, if they are feeling nervous or anxious, they need appropriate advice and information on the level of danger. To solve these issues, a system is needed that utilizes the user's location information and emotional data to present the risk level of an area in real time in the form of a score.

[0283] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring the user's current location, means for referencing data on past incidents, accidents, and disaster risks, means for analyzing the referenced data and calculating the risk level in the form of a score, and means for acquiring the user's emotional data and reflecting it in the risk level score. This makes it possible to present a real-time risk level score that also takes into account the user's emotional state.

[0284] "Means for obtaining the user's current location" refers to the device or technology used to identify the user's current geographic location, and typically refers to a GPS module.

[0285] "Means for referencing data on past incidents, accidents, and disaster risks" refers to devices or technologies for obtaining and referencing information from databases that store information on past incidents, accidents, and disasters.

[0286] "Means for analyzing referenced data and calculating risk in the form of a score" refers to a device or technology that analyzes acquired data on past incidents, accidents, and disaster risks, and expresses the results of that analysis as a numerical risk level.

[0287] "Means for displaying the calculated risk score to the user" refers to a device or technology for visually informing the user of the calculated risk score, such as a display or smartphone screen.

[0288] "Means for acquiring user emotional data and reflecting it in the risk score" refers to devices or technologies for detecting and analyzing the user's emotional state and incorporating that data into the risk score calculation process, including emotion recognition engines and sensors.

[0289] The present invention is a system that analyzes past incident, accident, and disaster risk data in an area based on the current location of the autonomous vehicle the user is riding in, and provides a risk score that also takes emotion data into account. This system is realized using the following hardware and software.

[0290] First, the server uses the GPS module to obtain the user's current location. This allows the autonomous vehicle to determine its current latitude and longitude and send that information to the server. In practice, location information can be obtained using common location services (e.g., the Nominatim API in the Geopy library).

[0291] Next, the device acquires the user's emotional data. This is done by analyzing the user's facial expressions and voice using the smartphone's camera and microphone, and then using an emotion recognition engine to recognize the user's emotional state. Specifically, by using a library such as EmotionRecognizer, the device can analyze the user's emotions at that moment.

[0292] The server references past incidents, accidents, and disaster risk data from a database based on the acquired location information and emotion data, issuing appropriate API requests to retrieve relevant data and collect the information needed for analysis.

[0293] The server then analyzes the referenced data and calculates the risk level in the form of a score. Here, generative AI models and natural language processing technology are used to analyze patterns of past incidents and disasters, and a risk score is derived that takes into account emotional data. This process requires advanced data analysis using generative AI models.

[0294] The risk score calculated from the analysis results is sent to the device and displayed to the user. For example, the risk score and safety information can be displayed on the display of the self-driving vehicle or on the screen of a smartphone. The display format is a specific alert such as, "The risk score for this area is 8 / 10. Please drive carefully."

[0295] As a concrete example, if a user in an autonomous vehicle enters an area where many accidents have been reported, the server obtains the user's location information and references past accident data from a database. At the same time, if the user is feeling anxious, emotional data is also taken into account in the analysis. Analysis using a generative AI model calculates an overall risk score, and a message is displayed stating, "The risk score for this area is 8.5 / 10. Caution is advised."

[0296] Example prompt sentence:

[0297] If a user at latitude 35.6623, longitude 139.7034 sends emotional data saying they are "nervous," calculate a risk score based on past incidents, accidents, and disaster risks in this area.

[0298] In this way, the "safe driving navigation" of the present invention can present a real-time risk score that also takes into account the user's emotional state, thereby supporting safer driving.

[0299] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0300] Step 1:

[0301] Obtain the user's current location. The device uses a GPS module to obtain the current latitude and longitude, and then sends this location information to the server. The input is the location data obtained from the user's device, and the output is the latitude and longitude location information sent to the server. Specifically, the device's GPS module measures the current location and transmits this data to the server.

[0302] Step 2:

[0303] Acquires the user's emotional data. The device uses the smartphone's camera and microphone to capture the user's facial expressions and voice, which are then analyzed using an emotion recognition engine. The analyzed emotional data is sent to a server. The input is image data and voice data acquired from the user's device, and the output is the emotional state (e.g., tension, anxiety) sent to the server. Specifically, the device's camera captures the user's facial expressions and records their voice, and these data are analyzed using an emotion recognition engine.

[0304] Step 3:

[0305] Obtain data on past incidents, accidents, and disaster risks. The server issues a query to the database based on location information and emotion data to obtain related data. The input is the location information and emotion data sent to the server, and the output is data on past incidents, accidents, and disaster risks. Specifically, the server issues a query to the database based on location information and obtains the results.

[0306] Step 4:

[0307] The risk level is calculated in the form of a score. Using past data acquired by the server and user emotional data, the risk score is calculated using a generative AI model and natural language processing technology. The input is past incident, accident, and disaster risk data and emotional data, and the output is the calculated risk score. Specifically, the server uses the generative AI model to analyze the data, find past patterns, and derive a risk score that takes emotional data into account.

[0308] Step 5:

[0309] The danger score is displayed to the user. The server sends the calculated danger score to the terminal, which then visually displays it to the user. The input is the danger score sent from the server, and the output is the danger score and a warning message displayed on the terminal. Specifically, the server sends the danger score to the terminal, and the terminal displays "The danger score for this area is 8.5 / 10. Caution required."

[0310] Step 6:

[0311] Notifications are sent in real time. When the risk score exceeds a certain standard, the device will issue a real-time notification such as an alarm or vibration to alert the user. The input is the risk score from the server, and the output is the real-time notification action (alert, vibration, etc.). Specifically, the device analyzes the risk score and issues a real-time notification if the score exceeds the set standard.

[0312] Based on the above processing steps, the "safe driving navigation" of the present invention realizes a system that ensures the user's safety by presenting a real-time risk score based on the user's emotional state and location information.

[0313] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0314] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0315] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0316] [Second embodiment]

[0317] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0318] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0319] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0320] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0321] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0322] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0323] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0324] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0325] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0326] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0327] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0328] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0329] The present invention is a system that analyzes the risk of past incidents, accidents, and disasters based on the user's current location and displays the risk level of the area in the form of a score. Specific embodiments of this system will be described below.

[0330] First, the device held by the user is equipped with a GPS module. Using this GPS module, the device obtains the user's current location. For example, if the user is in Shibuya Ward, Tokyo, the device will obtain location information such as latitude 35.6623 and longitude 139.7034.

[0331] Once the location information is acquired, the device sends it to a server, which then queries a database to retrieve data on past incidents, accidents, and disaster risks. The data retrieved includes a series of past events and risk information related to the area.

[0332] The server analyzes the data retrieved from the database. Specifically, it utilizes chat generation AI and natural language processing technology to analyze patterns of past incidents and disasters. This allows it to calculate the level of danger in the area in the form of a score (for example, a number from 0 to 10). The score calculated in this way is intended to provide users with an intuitive, easy-to-understand indication of the danger level in the area.

[0333] After the score is calculated, the server sends the result to the terminal. The terminal analyzes the received data and displays the risk score to the user through a GUI (graphical user interface). For example, it may display a message such as, "The risk score for this area is 7 / 10."

[0334] As a concrete example, consider the case where a user is walking around Shibuya Ward while shopping. At this time, the device uses a GPS module to obtain the user's current location and sends this information to the server. The server retrieves past incident and accident data for Shibuya Ward from a database and calculates a danger score using natural language processing with a chat generation AI. Based on this analysis, the danger score for Shibuya Ward is calculated to be "7 / 10," and the server sends this score to the device. The device receives this score and displays on the user's screen, "The danger score for this area is 7 / 10." The user can view this information to understand the safety of the area they are in.

[0335] As described above, this system allows users to determine the risk level of their current location in real time and obtain reference information for taking safe actions. This function is extremely useful, especially when traveling in urban areas or areas with high disaster risk.

[0336] From this description, it will be understood that a specific embodiment of the present invention is shown, and that the present invention is a system that provides assistance to users in confirming safety anytime and anywhere.

[0337] The processing flow will be explained below.

[0338] Step 1: The device gets the user's current location

[0339] The device activates its built-in GPS module and acquires information about its current location. Specifically, the device receives signals from satellites and calculates its latitude and longitude. This location information is stored in the device's temporary memory.

[0340] Step 2: The device sends its location and request to the server

[0341] The device packages the user's request based on the location information it acquires. For example, if a user requests to know the current level of danger, the device combines the location information and the request into a single data package and sends it to the server over the network.

[0342] Step 3: The server retrieves the necessary data from the database

[0343] The server analyzes the data package received from the device and retrieves data on relevant past incidents, accidents, and disaster risks from a database based on the device's current location. Specifically, the server issues a database query using the location information as a key to retrieve the relevant data.

[0344] Step 4: The server parses the data

[0345] Based on the acquired data, the server uses chat generation AI to perform natural language processing. Specifically, it analyzes past data and identifies patterns of incidents, accidents, and disasters related to the current location. This then scores the area's risk level on a scale of 0 to 10.

[0346] Step 5: The server packages the analysis results and sends them to the device.

[0347] The server compiles the calculated risk score and related data into a package, which is then sent to the device via the network.

[0348] Step 6: The device receives the analysis results and displays them to the user

[0349] The device analyzes the data package received from the server and extracts a risk score. The device then launches a GUI and displays the result to the user, such as "The risk score for this area is 7 / 10."

[0350] Step 7: User confirms the results

[0351] Users can check their device screen and understand the risk score for their current location, which can provide them with information to help them decide on their course of action in that area.

[0352] Example 1

[0353] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0354] Currently, it is difficult for users to grasp their own safety in real time while traveling or out. In addition, there is a lack of means to instantly obtain information on past incidents, accidents, disaster risks, etc., and to intuitively understand the specific level of danger. As a result, the risk of encountering high-risk areas increases, potentially threatening the user's safety.

[0355] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0356] In this invention, the server includes a means for acquiring the user's current location, a means for referencing past risk data, and a means for analyzing the data and calculating a risk score, thereby enabling the user to grasp the risk level based on their current location in real time and take safe actions.

[0357] "User" refers to an individual or corporation that uses the system to obtain risk information about their current location.

[0358] "Current location" refers to the user's actual geographic location obtained through a GPS module or other location information acquisition means.

[0359] "Risk data" refers to data that comprehensively includes information on past incidents, accidents, and disaster risks.

[0360] "Database" refers to an information processing system for structuring and storing risk data.

[0361] "GPS module" refers to a hardware device for obtaining current location using the Global Positioning System.

[0362] The term "server" refers to an information processing device that analyzes risk data based on location information received from a user's terminal and returns the results to the terminal.

[0363] "Terminal" refers to a portable information processing device that is owned by a user and has a GPS module and communication functions.

[0364] "Chat generation AI" refers to artificial intelligence that uses natural language processing technology to analyze data and is designed to be able to have natural conversations with humans.

[0365] A "prompt sentence" refers to a sentence of instructions or questions that is entered into the chat generation AI to perform analysis.

[0366] An "HTTP request" refers to a form of communication protocol that a terminal sends to a server to request data.

[0367] "Danger score" refers to a numerical assessment of the danger level of a particular area based on data analysis.

[0368] "GUI" is an abbreviation for Graphical User Interface, and refers to an interface that provides information to users visually.

[0369] MODE FOR CARRYING OUT THE INVENTION

[0370] The present invention is a system that analyzes past incidents, accidents, and disaster risks based on the user's current location and displays the risk level of the area in the form of a score.

[0371] First, the user has a device equipped with a GPS module. This device uses the GPS module to obtain the user's current location. For example, if the user is in Shibuya Ward, Tokyo, the device will obtain location information such as latitude 35.6623 and longitude 139.7034.

[0372] The device then sends the location information to a server, typically via an HTTP request, which queries a database for past incidents, accidents, and disaster risk data.

[0373] The server uses a chat generation AI model to analyze past data. This AI model uses natural language processing technology to analyze risk data and calculate the risk level of the area in the form of a score. Specifically, the AI ​​is input with the prompt "Please give me an overview of incidents and accidents in Shibuya Ward over the past three years" to perform the analysis.

[0374] Once the analysis is complete, the server sends the calculated risk score to the device. Based on the received data, the device displays the risk score to the user via a GUI (graphical user interface). For example, the device might display "The risk score for this area is 7 / 10."

[0375] As a concrete example, consider the case where a user is walking around Shibuya Ward while shopping. At this time, the device uses a GPS module to obtain the user's current location and sends this information to the server. The server retrieves past incident and accident data for Shibuya Ward from a database and calculates a danger score using natural language processing with a chat generation AI. Based on this analysis, the danger score for Shibuya Ward is calculated to be "7 / 10," and the server sends this score to the device. The device receives this score and displays the message "The danger score for this area is 7 / 10" on the user's screen.

[0376] As described above, this system allows users to determine the risk level of their current location in real time and obtain reference information for safe behavior, which is particularly useful when traveling through urban areas or areas with high disaster risk.

[0377] The hardware used includes a GPS module and a terminal, and the software used includes a database management system, an HTTP communication library, a chat generation AI model, and a natural language processing library. By implementing this technology, users can obtain a real-time risk score and understand their safety.

[0378] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0379] Specific explanation of processing steps

[0380] Step 1: Get current location

[0381] A user carries a device with a GPS function.

[0382] Input: The user's current geographic location

[0383] The device periodically activates the GPS module and obtains its current location (latitude and longitude).

[0384] Output: Current location (e.g., latitude 35.6623, longitude 139.7034)

[0385] Specific behavior: The code is implemented so that the device obtains location information using the GPS API.

[0386] Step 2: Send location information

[0387] The device sends the current location data it has acquired to the server via an HTTP request.

[0388] Input: Current location (latitude and longitude)

[0389] Output: Location information sent to the server

[0390] Specific operation: The device generates an HTTP request and posts the location information to the server in JSON format or similar.

[0391] Step 3: Obtaining historical data

[0392] Based on the location information received by the server, an SQL query is issued to the database to retrieve data on past incidents, accidents, and disaster risks.

[0393] Input: Location information sent to the server

[0394] The server issues a query to the database such as "SELECT FROM risk_data WHERE latitude=35.6623 AND longitude=139.7034".

[0395] Output: Past incidents, accidents, and disaster risk data

[0396] Specific operation: The server retrieves data from the database using an ORM such as SQLAlchemy.

[0397] Step 4: Analyze the data

[0398] The server uses chat generation AI and natural language processing technology to analyze past data.

[0399] Input: Historical risk data

[0400] The server inputs the prompt text "Please give me an overview of the incidents and accidents in Shibuya Ward over the past three years" into the chat generation AI, and the AI ​​performs the analysis.

[0401] Output: Hazard score for the area (e.g. 7 / 10)

[0402] Specific operation: The server sends a prompt to the AI ​​model and receives the analysis results.

[0403] Data processing: Analyze regular text data and convert it into a numerical risk score.

[0404] Step 5: Submit your score

[0405] The server sends the calculated risk score to the terminal in JSON format as an HTTP response.

[0406] Input: Calculated risk score

[0407] Output: Risk score sent to the device

[0408] Specific operation: The server generates an HTTP response and sends the risk score in JSON format to the device.

[0409] Step 6: View your score

[0410] The risk score received by the terminal is displayed to the user via a GUI (graphical user interface).

[0411] Input: Risk score sent from the server

[0412] Output: Risk score displayed to the user

[0413] Specific operation: The device uses JavaScript or native application code to dynamically display the risk score on the screen.

[0414] Example: The device screen displays, "The danger score for this area is 7 / 10."

[0415] (Application example 1)

[0416] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0417] With conventional safety confirmation systems, it was difficult for users to immediately grasp the risk level of their current location. Furthermore, there was a lack of a well-established mechanism for displaying the risk level of a location in real time, which could lead to delayed safety measures. Furthermore, there was a lack of technology to analyze detailed data on past incidents and disaster risks when calculating risk scores.

[0418] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0419] In this invention, the server includes a means for referencing data on past incidents, accidents, and disaster risks based on location information, a means for analyzing the referenced data using natural language processing technology and calculating a risk score using a generation AI model, and a means for displaying the risk score in real time, thereby enabling the user to instantly grasp the risk level of the area where they are currently located and take safe actions based on the risk score displayed in real time.

[0420] The "current location" is location information that indicates the latitude and longitude of the user when he or she is at a specific point.

[0421] The "reference means" is a means for obtaining data on incidents, accidents, and disaster risks that have occurred in the past from a database based on the user's current location.

[0422] The "means of analysis" refers to a method for calculating the risk level of an area in the form of a score based on the acquired data on past incidents, accidents, and disaster risks.

[0423] The "display means" is a means for visually presenting the calculated risk score to the user.

[0424] A "database" is an information system that accumulates information on past incidents, accidents, and disaster risks and stores it in a searchable format.

[0425] "Natural language processing" is a technology that allows computers to understand and analyze human language.

[0426] A "generative AI model" is an artificial intelligence model that learns patterns from past data to generate or analyze new data.

[0427] A "Global Positioning System (GPS) module" is a device that receives signals from satellites and uses them to determine one's current location on Earth.

[0428] A "prompt sentence" is an input sentence that gives specific analysis and generation instructions to a generative AI model.

[0429] The present invention is a system that analyzes the risk of past incidents, accidents, and disasters based on the user's current location and displays the risk level of the area in the form of a score. Specific embodiments of this system will be described below.

[0430] First, the device is equipped with a Global Positioning System (GPS) module, which allows the device to obtain the user's current location. For example, if the user is traveling within a metropolitan area, the device will obtain latitude and longitude location information.

[0431] Once the location information is acquired, the device sends it to a server. The server then uses the received location information to reference a database of data on past incidents, accidents, and disaster risks. The database contains detailed information on past incidents, accidents, and disaster risks.

[0432] The server analyzes the data retrieved from the database. This analysis uses natural language processing technology and a generative AI model to analyze patterns of past incidents and disasters. This pattern analysis calculates the risk level in the area in the form of a score (for example, a number from 0 to 10). Using a generative AI model makes it possible to calculate a risk score with greater accuracy.

[0433] After calculating the risk score, the server sends the results to the terminal. The terminal analyzes the received data and displays the risk score to the user in real time through a graphical user interface (GUI). For example, it may display "The risk score for this area is 7 / 10." This allows the user to instantly understand the safety of the area and obtain reference information for taking safe actions.

[0434] As a concrete example, consider a user walking through an unfamiliar city at night. The device uses a GPS module to obtain the user's current location and sends that information to a server. The server then retrieves past incident and accident data for that city from a database and analyzes it using natural language processing technology. A highly accurate risk score is calculated using a generative AI model. For example, if the analysis determines that "the risk score for this area is 8 / 10," the server sends this score to the device. The device receives this score and displays "The risk score for this area is 8 / 10" on the user's screen. By viewing this information, the user can immediately understand the safety of the area and take safety-first actions.

[0435] An example prompt is:

[0436] The user is currently in Shinjuku Ward. Please calculate the risk score for this area based on incident, accident, and disaster risk data for Shinjuku Ward over the past five years. The score should be a number between 0 and 10, and should be output as, for example, "The risk score for this area is 7 / 10."

[0437] In this way, the present invention is a system that allows a user to immediately grasp the degree of danger in the area where he or she is currently located and provides useful information for quickly taking safety measures.

[0438] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0439] Step 1:

[0440] The device uses the GPS module to obtain the user's current location (latitude and longitude), which is used as input data.

[0441] Step 2:

[0442] The device sends the current location information (latitude and longitude) to the server.

[0443] Step 3:

[0444] Based on the location information received by the server, a query is issued to the database to retrieve data on past incidents, accidents, and disaster risks. This query outputs past data related to the specified location information from the database.

[0445] Step 4:

[0446] The server analyzes data on past incidents, accidents, and disaster risks using generative AI models and natural language processing technology. This analysis calculates a risk score for the area. The input data is data on past incidents, accidents, and disaster risks, and the output data is the risk score.

[0447] Step 5:

[0448] The server sends the calculated risk score to the terminal. The data sent is the risk score.

[0449] Step 6:

[0450] The terminal analyzes the received risk score and displays it to the user in real time through a graphical user interface (GUI). The operation is to visually present the risk score to the user.

[0451] Step 7:

[0452] The user checks the screen of the device and takes safe actions based on the risk score displayed in real time. In this step, the risk score plays a role in supporting the user's decision-making.

[0453] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0454] The present invention combines a system that analyzes past incidents, accidents, and disaster risks based on the user's current location and displays the risk level of the area in the form of a score with an emotion engine that recognizes the user's emotions. A specific embodiment of this system will be described below.

[0455] First, the user's device is equipped with a GPS module and an emotion recognition engine. Using the GPS module, the device obtains the user's current location. For example, if the user is in Shibuya Ward, Tokyo, the device obtains location information such as latitude 35.6623 and longitude 139.7034.

[0456] Once the location information is acquired, the device sends this location information and the user's emotional data acquired by the emotion recognition engine to the server. The emotion recognition engine analyzes the user's emotions using voice input or a facial recognition camera. Specifically, if the user indicates an emotion such as "I'm nervous right now," that information is also sent to the server.

[0457] Based on the received location information and emotion data, the server issues a query to the database to reference data on past incidents, accidents, and disaster risks. This query retrieves past data for the relevant area.

[0458] The server then analyzes the data retrieved from the database. Utilizing chat generation AI and natural language processing technology, the server analyzes patterns of past incidents and disasters. The results of this analysis are combined with the user's emotional data to calculate the danger level of the area in the form of a score. For example, if the user is nervous, the danger score may be set higher.

[0459] After the score is calculated, the server sends the results to the device, which analyzes the data and displays the risk score to the user through a GUI. For example, it might say, "The risk score for this area is 7 / 10. Caution is advised."

[0460] As a concrete example, consider a user walking through Shibuya Ward while shopping. At this time, the device uses a GPS module to obtain the user's current location and sends that information to the server. At the same time, emotional data, which the user recognizes as "anxiety," is also sent. The server retrieves past incident and accident data for Shibuya Ward from a database and uses natural language processing with chat generation AI to calculate a danger score. Based on this analysis, the danger score for Shibuya Ward is calculated as "7 / 10." The emotional data is then taken into account and the score is finally adjusted to "7.5 / 10." The server then sends this score to the device. The device receives the score and displays a message on the user's screen saying, "The danger score for this area is 7.5 / 10. Caution is advised." Using this information, the user can understand the safety of their area.

[0461] As described above, this system, which combines an emotion recognition engine, allows users to determine the risk level of their current location in real time with greater accuracy, and provides reference information for taking safe actions. This type of function is extremely useful, especially when traveling in urban areas or areas with a high risk of disasters.

[0462] From this description, it will be understood that a specific embodiment of the present invention is shown, and that the system provides assistance to users in checking information that takes into consideration their safety and their emotional state, anytime and anywhere.

[0463] The processing flow will be explained below.

[0464] Step 1: The device gets the user's current location

[0465] The device activates its built-in GPS module and acquires information about its current location. Specifically, the device receives signals from satellites and calculates its latitude and longitude. This location information is stored in the device's temporary memory.

[0466] Step 2: The device recognizes the user's emotions

[0467] The device's built-in emotion recognition engine detects the user's emotions. It uses voice input and a facial recognition camera to determine the user's emotions and generates emotion data such as "tension," "anxiety," or "relaxation." This emotion data is also temporarily stored on the device.

[0468] Step 3: The device sends location and emotion data to the server.

[0469] The device packages the location information and emotion data it acquires and sends them to a server via the network. Specifically, location information (e.g., latitude 35.6623, longitude 139.7034) and emotion data (e.g., "anxiety") are combined into a single data package.

[0470] Step 4: The server retrieves the necessary data from the database

[0471] The server analyzes the location and emotion data received from the device and issues a database query based on the location information. The database returns data on past incidents, accidents, and disaster risks related to the area to the server.

[0472] Step 5: The server parses the data

[0473] Using the acquired data, the server operates a chat generation AI. Specifically, it analyzes data on past incidents, accidents, and disaster risks using natural language processing technology, and calculates the risk level in the form of a score (e.g., 0 to 10) taking into account location information and emotional data. If the emotional data indicates "anxiety," the risk score is adjusted higher.

[0474] Step 6: The server packages the analysis results and sends them to the device.

[0475] The server combines the calculated risk score and analysis data into a single package and sends it to the terminal.

[0476] Step 7: The device receives the analysis results and displays them to the user

[0477] The device analyzes the data package received from the server and extracts a risk score.The device then launches a GUI and displays the results to the user in the form of, for example, "The risk score for this area is 7.5 / 10. Caution is advised."

[0478] Step 8: User confirms the results

[0479] Users can check their device screen and understand the risk score for their current location, which can help them decide how to proceed in that area.

[0480] Example 2

[0481] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0482] Conventional risk assessment systems display the risk level of a user's current area in the form of a score based on past incident, accident, and disaster risk data, but do not take the user's emotional state into consideration. As a result, risk assessments cannot reflect the user's subjective feelings, such as anxiety or a sense of security, and risk scores may not be appropriate for the user. Therefore, there is a need for a method of more accurate and practical risk assessment for users that takes the user's emotional state into consideration.

[0483] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0484] In this invention, the server includes a means for acquiring the user's current location, a means for acquiring data on past incidents, accidents, and disaster risks from a database, and a means for analyzing the data using natural language processing, thereby enabling risk assessment that reflects the user's emotional state.

[0485] "User's current location" is data that indicates the geographic location of a user at a particular time, typically expressed as latitude and longitude coordinate information.

[0486] An "incident" is data that indicates a criminal act that occurred at a specific place and time.

[0487] An "incident" is data that indicates an unexpected adverse occurrence caused by human or natural factors.

[0488] "Disaster risk" is data that indicates the danger that may occur due to natural or man-made disasters.

[0489] A "database" is a system that systematically stores information on past incidents, accidents, and disaster risks.

[0490] "Emotion recognition" is a technology that analyzes and determines a user's emotional state from their voice, facial expressions, etc.

[0491] "Natural language processing" is a technology that enables computers to understand and analyze human language.

[0492] The "risk score" is a numerical representation of the risk in a particular location, and is an index that indicates the risk level for the user.

[0493] A "server" is a computer system for processing and storing data.

[0494] A "terminal" is a computing device that is directly operated by a user.

[0495] MODE FOR CARRYING OUT THE INVENTION

[0496] The present invention combines a system that analyzes past incidents, accidents, and disaster risks based on the user's current location and displays the risk level of the area in the form of a score with an emotion engine that recognizes the user's emotions. A specific embodiment of this system will be described below.

[0497] First, the device held by the user is equipped with a GPS module and an emotion recognition engine. Using the GPS module, the device obtains the user's current location. For example, if the user is in Shibuya Ward, Tokyo, the device obtains location information such as latitude 35.6623 and longitude 139.7034.

[0498] Once the location information is acquired, the device sends this location information and the user's emotional data acquired by the emotion recognition engine to the server. The emotion recognition engine analyzes the user's emotions using voice input or a facial recognition camera. Specifically, if the user expresses emotions such as "I'm nervous" or "anxious," that information is also sent to the server.

[0499] Based on the received location information and emotion data, the server issues a query to the database to reference data on past incidents, accidents, and disaster risks. This query retrieves past data for the relevant area.

[0500] The server then analyzes the data retrieved from the database. It uses natural language processing technology to analyze patterns of past incidents and disasters. The results of this analysis are combined with the user's emotional data to calculate the danger level of the area in the form of a score. For example, if the user is nervous, the danger score may be set higher.

[0501] After the score is calculated, the server sends the results to the device, which analyzes the data and displays the risk score to the user through a GUI. For example, it might say, "The risk score for this area is 7 / 10. Caution is advised."

[0502] As a concrete example, consider the case where a user is walking around Shibuya Ward while shopping. At this time, the device uses a GPS module to obtain the user's current location and sends that information to the server. At the same time, emotional data, which the user recognizes as "anxiety," is also sent. The server retrieves past incident and accident data for Shibuya Ward from a database and calculates a danger score using natural language processing technology. Based on this analysis, the danger score for Shibuya Ward is calculated to be "7 / 10." The emotional data is then taken into account and the score is finally adjusted to "7.5 / 10." The server then sends this score to the device. The device receives this score and displays a message on the user's screen saying, "The danger score for this area is 7.5 / 10. Caution is advised." Using this information, the user can understand the safety of their area.

[0503] An example prompt for querying the generative AI model about this system is as follows:

[0504] plaintext

[0505] We have a system that analyzes past incidents, accidents, and disaster risks based on the user's current location and emotional data, and displays the risk level in the form of a score. For example, if a user feels "anxious" in Shibuya Ward, the system will display the risk level score for that area as "7.5 / 10." Please tell me the specific processing steps of this system.

[0506] As described above, this system integrates a risk assessment function based on the user's current location and emotional data, allowing users to check the safety of the area in real time, providing useful information for travel, especially in urban areas and areas with high disaster risk.

[0507] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0508] Processing flow

[0509] Step 1: Get the user's current location

[0510] explanation

[0511] The GPS module installed on the device is activated and the user's current location is obtained. The hardware used is a GPS module.

[0512] Input and Output

[0513] Input: None (the device itself obtains the current location)

[0514] Data processing and data calculation: The GPS module calculates the position information from the satellite signals

[0515] Output: Latitude and longitude (e.g. 35.6623, 139.7034)

[0516] Specific actions

[0517] When the user is in Shibuya Ward, the device activates the GPS module and obtains location information of latitude 35.6623 and longitude 139.7034.

[0518] Step 2: Obtain user emotion data

[0519] explanation

[0520] The emotion recognition engine installed in the device is activated, and emotion data is acquired using the user's voice input or facial expression recognition camera.

[0521] Input and Output

[0522] Input: Audio data or video data (user's facial expression)

[0523] Data processing and data calculation: Estimating emotional states through speech or image analysis

[0524] Output: Emotion data such as "anxiety"

[0525] Specific actions

[0526] If the user is feeling anxious, the device's emotion recognition engine analyzes their voice and facial expressions, and as a result, obtains the emotion data "anxiety."

[0527] Step 3: Send location and emotion data to the server

[0528] explanation

[0529] When the location information and emotion data acquired by the device is sent to the server, it is encrypted using SSL / TLS to ensure the security of the data.

[0530] Input and Output

[0531] Input: Location (35.6623, 139.7034) and emotion data ("anxiety")

[0532] Data processing and data calculation: Data is organized into packets, encrypted, and sent to the server

[0533] Output: Data sent to server completed

[0534] Specific actions

[0535] The device sends location information (35.6623, 139.7034) and emotion data ("anxiety") to the server using SSL / TLS encryption.

[0536] Step 4: Retrieve historical data from the database

[0537] explanation

[0538] Based on the location information and emotion data received by the server, a query is issued to the database to obtain data on past incidents, accidents, and disaster risks.

[0539] Input and Output

[0540] Input: Location information (35.6623, 139.7034)

[0541] Data manipulation and data calculations: Search past data using SQL queries

[0542] Output: Past incidents, accidents, and disaster data for a specific area (Shibuya Ward)

[0543] Specific actions

[0544] The server queries the database based on the location information and retrieves data on past incidents, accidents, and disasters in Shibuya Ward.

[0545] Step 5: Data analysis and risk score calculation

[0546] explanation

[0547] The server combines the data acquired with the user's emotional data and calculates a risk score using natural language processing technology.

[0548] Input and Output

[0549] Input: Past incident, accident, and disaster data and emotional data ("anxiety")

[0550] Data processing and data calculations: Analyze data using natural language processing techniques and generative AI models to calculate risk scores

[0551] Output: Risk score (e.g. 7.5 / 10)

[0552] Specific actions

[0553] The server uses past data and the user's emotional data of "anxiety" to perform an analysis using natural language processing and calculates a risk score of 7.5 / 10.

[0554] Step 6: Submit your risk score

[0555] explanation

[0556] The server sends the calculated risk score to the terminal.

[0557] Input and Output

[0558] Input: Risk Score (7.5 / 10)

[0559] Data processing and calculation: The scores are packed into packets and sent to the terminal.

[0560] Output: Data sent to the terminal completed

[0561] Specific actions

[0562] The server sends a risk score of 7.5 / 10 to the device.

[0563] Step 7: View your risk score

[0564] explanation

[0565] The device analyzes the received risk score and displays it to the user using a GUI.

[0566] Input and Output

[0567] Input: Risk Score (7.5 / 10)

[0568] Data processing and data calculation: converting scores into a format that can be displayed in the GUI

[0569] Output: Display of danger score (e.g. "This area has a danger score of 7.5 / 10. Caution required.")

[0570] Specific actions

[0571] The device receives a danger score of 7.5 / 10 and displays on the GUI, "The danger score for this area is 7.5 / 10. Caution is required."

[0572] (Application example 2)

[0573] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0574] In recent years, advances in autonomous driving technology have led to an increasing number of people using autonomous vehicles. However, there are limited ways for users to know the safety of the area they are traveling in real time, which puts them at risk of entering dangerous areas. In addition, a user's emotional state can affect their driving; for example, if they are feeling nervous or anxious, they need appropriate advice and information on the level of danger. To solve these issues, a system is needed that utilizes the user's location information and emotional data to present the risk level of an area in real time in the form of a score.

[0575] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring the user's current location, means for referencing data on past incidents, accidents, and disaster risks, means for analyzing the referenced data and calculating the risk level in the form of a score, and means for acquiring the user's emotional data and reflecting it in the risk level score. This makes it possible to present a real-time risk level score that also takes into account the user's emotional state.

[0576] "Means for obtaining the user's current location" refers to the device or technology used to identify the user's current geographic location, and typically refers to a GPS module.

[0577] "Means for referencing data on past incidents, accidents, and disaster risks" refers to devices or technologies for obtaining and referencing information from databases that store information on past incidents, accidents, and disasters.

[0578] "Means for analyzing referenced data and calculating risk in the form of a score" refers to a device or technology that analyzes acquired data on past incidents, accidents, and disaster risks, and expresses the results of that analysis as a numerical risk level.

[0579] "Means for displaying the calculated risk score to the user" refers to a device or technology for visually informing the user of the calculated risk score, such as a display or smartphone screen.

[0580] "Means for acquiring user emotional data and reflecting it in the risk score" refers to devices or technologies for detecting and analyzing the user's emotional state and incorporating that data into the risk score calculation process, including emotion recognition engines and sensors.

[0581] The present invention is a system that analyzes past incident, accident, and disaster risk data in an area based on the current location of the autonomous vehicle the user is riding in, and provides a risk score that also takes emotion data into account. This system is realized using the following hardware and software.

[0582] First, the server uses the GPS module to obtain the user's current location. This allows the autonomous vehicle to determine its current latitude and longitude and send that information to the server. In practice, location information can be obtained using common location services (e.g., the Nominatim API in the Geopy library).

[0583] Next, the device acquires the user's emotional data. This is done by analyzing the user's facial expressions and voice using the smartphone's camera and microphone, and then using an emotion recognition engine to recognize the user's emotional state. Specifically, by using a library such as EmotionRecognizer, the device can analyze the user's emotions at that moment.

[0584] The server references past incidents, accidents, and disaster risk data from a database based on the acquired location information and emotion data, issuing appropriate API requests to retrieve relevant data and collect the information needed for analysis.

[0585] The server then analyzes the referenced data and calculates the risk level in the form of a score. Here, generative AI models and natural language processing technology are used to analyze patterns of past incidents and disasters, and a risk score is derived that takes into account emotional data. This process requires advanced data analysis using generative AI models.

[0586] The risk score calculated from the analysis results is sent to the device and displayed to the user. For example, the risk score and safety information can be displayed on the display of the self-driving vehicle or on the screen of a smartphone. The display format is a specific alert such as, "The risk score for this area is 8 / 10. Please drive carefully."

[0587] As a concrete example, if a user in an autonomous vehicle enters an area where many accidents have been reported, the server obtains the user's location information and references past accident data from a database. At the same time, if the user is feeling anxious, emotional data is also taken into account in the analysis. Analysis using a generative AI model calculates an overall risk score, and a message is displayed stating, "The risk score for this area is 8.5 / 10. Caution is advised."

[0588] Example prompt sentence:

[0589] If a user at latitude 35.6623, longitude 139.7034 sends emotional data saying they are "nervous," calculate a risk score based on past incidents, accidents, and disaster risks in this area.

[0590] In this way, the "safe driving navigation" of the present invention can present a real-time risk score that also takes into account the user's emotional state, thereby supporting safer driving.

[0591] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0592] Step 1:

[0593] Obtain the user's current location. The device uses a GPS module to obtain the current latitude and longitude, and then sends this location information to the server. The input is the location data obtained from the user's device, and the output is the latitude and longitude location information sent to the server. Specifically, the device's GPS module measures the current location and transmits this data to the server.

[0594] Step 2:

[0595] Acquires the user's emotional data. The device uses the smartphone's camera and microphone to capture the user's facial expressions and voice, which are then analyzed using an emotion recognition engine. The analyzed emotional data is sent to a server. The input is image data and voice data acquired from the user's device, and the output is the emotional state (e.g., tension, anxiety) sent to the server. Specifically, the device's camera captures the user's facial expressions and records their voice, and these data are analyzed using an emotion recognition engine.

[0596] Step 3:

[0597] Obtain data on past incidents, accidents, and disaster risks. The server issues a query to the database based on location information and emotion data to obtain related data. The input is the location information and emotion data sent to the server, and the output is data on past incidents, accidents, and disaster risks. Specifically, the server issues a query to the database based on location information and obtains the results.

[0598] Step 4:

[0599] The risk level is calculated in the form of a score. Using past data acquired by the server and user emotional data, the risk score is calculated using a generative AI model and natural language processing technology. The input is past incident, accident, and disaster risk data and emotional data, and the output is the calculated risk score. Specifically, the server uses the generative AI model to analyze the data, find past patterns, and derive a risk score that takes emotional data into account.

[0600] Step 5:

[0601] The danger score is displayed to the user. The server sends the calculated danger score to the terminal, which then visually displays it to the user. The input is the danger score sent from the server, and the output is the danger score and a warning message displayed on the terminal. Specifically, the server sends the danger score to the terminal, and the terminal displays "The danger score for this area is 8.5 / 10. Caution required."

[0602] Step 6:

[0603] Notifications are sent in real time. When the risk score exceeds a certain standard, the device will issue a real-time notification such as an alarm or vibration to alert the user. The input is the risk score from the server, and the output is the real-time notification action (alert, vibration, etc.). Specifically, the device analyzes the risk score and issues a real-time notification if the score exceeds the set standard.

[0604] Based on the above processing steps, the "safe driving navigation" of the present invention realizes a system that ensures the user's safety by presenting a real-time risk score based on the user's emotional state and location information.

[0605] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0606] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0607] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0608] [Third embodiment]

[0609] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0610] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0611] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0612] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0613] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0614] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0615] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0616] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0617] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0618] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0619] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0620] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0621] The present invention is a system that analyzes the risk of past incidents, accidents, and disasters based on the user's current location and displays the risk level of the area in the form of a score. Specific embodiments of this system will be described below.

[0622] First, the device held by the user is equipped with a GPS module. Using this GPS module, the device obtains the user's current location. For example, if the user is in Shibuya Ward, Tokyo, the device will obtain location information such as latitude 35.6623 and longitude 139.7034.

[0623] Once the location information is acquired, the device sends it to a server, which then queries a database to retrieve data on past incidents, accidents, and disaster risks. The data retrieved includes a series of past events and risk information related to the area.

[0624] The server analyzes the data retrieved from the database. Specifically, it utilizes chat generation AI and natural language processing technology to analyze patterns of past incidents and disasters. This allows it to calculate the level of danger in the area in the form of a score (for example, a number from 0 to 10). The score calculated in this way is intended to provide users with an intuitive, easy-to-understand indication of the danger level in the area.

[0625] After the score is calculated, the server sends the result to the terminal. The terminal analyzes the received data and displays the risk score to the user through a GUI (graphical user interface). For example, it may display a message such as, "The risk score for this area is 7 / 10."

[0626] As a concrete example, consider the case where a user is walking around Shibuya Ward while shopping. At this time, the device uses a GPS module to obtain the user's current location and sends this information to the server. The server retrieves past incident and accident data for Shibuya Ward from a database and calculates a danger score using natural language processing with a chat generation AI. Based on this analysis, the danger score for Shibuya Ward is calculated to be "7 / 10," and the server sends this score to the device. The device receives this score and displays on the user's screen, "The danger score for this area is 7 / 10." The user can view this information to understand the safety of the area they are in.

[0627] As described above, this system allows users to determine the risk level of their current location in real time and obtain reference information for taking safe actions. This function is extremely useful, especially when traveling in urban areas or areas with high disaster risk.

[0628] From this description, it will be understood that a specific embodiment of the present invention is shown, and that the present invention is a system that provides assistance to users in confirming safety anytime and anywhere.

[0629] The processing flow will be explained below.

[0630] Step 1: The device gets the user's current location

[0631] The device activates its built-in GPS module and acquires information about its current location. Specifically, the device receives signals from satellites and calculates its latitude and longitude. This location information is stored in the device's temporary memory.

[0632] Step 2: The device sends its location and request to the server

[0633] The device packages the user's request based on the location information it acquires. For example, if a user requests to know the current level of danger, the device combines the location information and the request into a single data package and sends it to the server over the network.

[0634] Step 3: The server retrieves the necessary data from the database

[0635] The server analyzes the data package received from the device and retrieves data on relevant past incidents, accidents, and disaster risks from a database based on the device's current location. Specifically, the server issues a database query using the location information as a key to retrieve the relevant data.

[0636] Step 4: The server parses the data

[0637] Based on the acquired data, the server uses chat generation AI to perform natural language processing. Specifically, it analyzes past data and identifies patterns of incidents, accidents, and disasters related to the current location. This then scores the area's risk level on a scale of 0 to 10.

[0638] Step 5: The server packages the analysis results and sends them to the device.

[0639] The server compiles the calculated risk score and related data into a package, which is then sent to the device via the network.

[0640] Step 6: The device receives the analysis results and displays them to the user

[0641] The device analyzes the data package received from the server and extracts a risk score. The device then launches a GUI and displays the result to the user, such as "The risk score for this area is 7 / 10."

[0642] Step 7: User confirms the results

[0643] Users can check their device screen and understand the risk score for their current location, which can provide them with information to help them decide on their course of action in that area.

[0644] Example 1

[0645] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0646] Currently, it is difficult for users to grasp their own safety in real time while traveling or out. In addition, there is a lack of means to instantly obtain information on past incidents, accidents, disaster risks, etc., and to intuitively understand the specific level of danger. As a result, the risk of encountering high-risk areas increases, potentially threatening the user's safety.

[0647] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0648] In this invention, the server includes a means for acquiring the user's current location, a means for referencing past risk data, and a means for analyzing the data and calculating a risk score, thereby enabling the user to grasp the risk level based on their current location in real time and take safe actions.

[0649] "User" refers to an individual or corporation that uses the system to obtain risk information about their current location.

[0650] "Current location" refers to the user's actual geographic location obtained through a GPS module or other location information acquisition means.

[0651] "Risk data" refers to data that comprehensively includes information on past incidents, accidents, and disaster risks.

[0652] "Database" refers to an information processing system for structuring and storing risk data.

[0653] "GPS module" refers to a hardware device for obtaining current location using the Global Positioning System.

[0654] The term "server" refers to an information processing device that analyzes risk data based on location information received from a user's terminal and returns the results to the terminal.

[0655] "Terminal" refers to a portable information processing device that is owned by a user and has a GPS module and communication functions.

[0656] "Chat generation AI" refers to artificial intelligence that uses natural language processing technology to analyze data and is designed to be able to have natural conversations with humans.

[0657] A "prompt sentence" refers to a sentence of instructions or questions that is entered into the chat generation AI to perform analysis.

[0658] An "HTTP request" refers to a form of communication protocol that a terminal sends to a server to request data.

[0659] "Danger score" refers to a numerical assessment of the danger level of a particular area based on data analysis.

[0660] "GUI" is an abbreviation for Graphical User Interface, and refers to an interface that provides information to users visually.

[0661] MODE FOR CARRYING OUT THE INVENTION

[0662] The present invention is a system that analyzes past incidents, accidents, and disaster risks based on the user's current location and displays the risk level of the area in the form of a score.

[0663] First, the user has a device equipped with a GPS module. This device uses the GPS module to obtain the user's current location. For example, if the user is in Shibuya Ward, Tokyo, the device will obtain location information such as latitude 35.6623 and longitude 139.7034.

[0664] The device then sends the location information to a server, typically via an HTTP request, which queries a database for past incidents, accidents, and disaster risk data.

[0665] The server uses a chat generation AI model to analyze past data. This AI model uses natural language processing technology to analyze risk data and calculate the risk level of the area in the form of a score. Specifically, the AI ​​is input with the prompt "Please give me an overview of incidents and accidents in Shibuya Ward over the past three years" to perform the analysis.

[0666] Once the analysis is complete, the server sends the calculated risk score to the device. Based on the received data, the device displays the risk score to the user via a GUI (graphical user interface). For example, the device might display "The risk score for this area is 7 / 10."

[0667] As a concrete example, consider the case where a user is walking around Shibuya Ward while shopping. At this time, the device uses a GPS module to obtain the user's current location and sends this information to the server. The server retrieves past incident and accident data for Shibuya Ward from a database and calculates a danger score using natural language processing with a chat generation AI. Based on this analysis, the danger score for Shibuya Ward is calculated to be "7 / 10," and the server sends this score to the device. The device receives this score and displays the message "The danger score for this area is 7 / 10" on the user's screen.

[0668] As described above, this system allows users to determine the risk level of their current location in real time and obtain reference information for safe behavior, which is particularly useful when traveling through urban areas or areas with high disaster risk.

[0669] The hardware used includes a GPS module and a terminal, and the software used includes a database management system, an HTTP communication library, a chat generation AI model, and a natural language processing library. By implementing this technology, users can obtain a real-time risk score and understand their safety.

[0670] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0671] Specific explanation of processing steps

[0672] Step 1: Get current location

[0673] A user carries a device with a GPS function.

[0674] Input: The user's current geographic location

[0675] The device periodically activates the GPS module and obtains its current location (latitude and longitude).

[0676] Output: Current location (e.g., latitude 35.6623, longitude 139.7034)

[0677] Specific behavior: The code is implemented so that the device obtains location information using the GPS API.

[0678] Step 2: Send location information

[0679] The device sends the current location data it has acquired to the server via an HTTP request.

[0680] Input: Current location (latitude and longitude)

[0681] Output: Location information sent to the server

[0682] Specific operation: The device generates an HTTP request and posts the location information to the server in JSON format or similar.

[0683] Step 3: Obtaining historical data

[0684] Based on the location information received by the server, an SQL query is issued to the database to retrieve data on past incidents, accidents, and disaster risks.

[0685] Input: Location information sent to the server

[0686] The server issues a query to the database such as "SELECT FROM risk_data WHERE latitude=35.6623 AND longitude=139.7034".

[0687] Output: Past incidents, accidents, and disaster risk data

[0688] Specific operation: The server retrieves data from the database using an ORM such as SQLAlchemy.

[0689] Step 4: Analyze the data

[0690] The server uses chat generation AI and natural language processing technology to analyze past data.

[0691] Input: Historical risk data

[0692] The server inputs the prompt text "Please give me an overview of the incidents and accidents in Shibuya Ward over the past three years" into the chat generation AI, and the AI ​​performs the analysis.

[0693] Output: Hazard score for the area (e.g. 7 / 10)

[0694] Specific operation: The server sends a prompt to the AI ​​model and receives the analysis results.

[0695] Data processing: Analyze regular text data and convert it into a numerical risk score.

[0696] Step 5: Submit your score

[0697] The server sends the calculated risk score to the terminal in JSON format as an HTTP response.

[0698] Input: Calculated risk score

[0699] Output: Risk score sent to the device

[0700] Specific operation: The server generates an HTTP response and sends the risk score in JSON format to the device.

[0701] Step 6: View your score

[0702] The risk score received by the terminal is displayed to the user via a GUI (graphical user interface).

[0703] Input: Risk score sent from the server

[0704] Output: Risk score displayed to the user

[0705] Specific operation: The device uses JavaScript or native application code to dynamically display the risk score on the screen.

[0706] Example: The device screen displays, "The danger score for this area is 7 / 10."

[0707] (Application example 1)

[0708] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0709] With conventional safety confirmation systems, it was difficult for users to immediately grasp the risk level of their current location. Furthermore, there was a lack of a well-established mechanism for displaying the risk level of a location in real time, which could lead to delayed safety measures. Furthermore, there was a lack of technology to analyze detailed data on past incidents and disaster risks when calculating risk scores.

[0710] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0711] In this invention, the server includes a means for referencing data on past incidents, accidents, and disaster risks based on location information, a means for analyzing the referenced data using natural language processing technology and calculating a risk score using a generation AI model, and a means for displaying the risk score in real time, thereby enabling the user to instantly grasp the risk level of the area where they are currently located and take safe actions based on the risk score displayed in real time.

[0712] The "current location" is location information that indicates the latitude and longitude of the user when he or she is at a specific point.

[0713] The "reference means" is a means for obtaining data on incidents, accidents, and disaster risks that have occurred in the past from a database based on the user's current location.

[0714] The "means of analysis" refers to a method for calculating the risk level of an area in the form of a score based on the acquired data on past incidents, accidents, and disaster risks.

[0715] The "display means" is a means for visually presenting the calculated risk score to the user.

[0716] A "database" is an information system that accumulates information on past incidents, accidents, and disaster risks and stores it in a searchable format.

[0717] "Natural language processing" is a technology that allows computers to understand and analyze human language.

[0718] A "generative AI model" is an artificial intelligence model that learns patterns from past data to generate or analyze new data.

[0719] A "Global Positioning System (GPS) module" is a device that receives signals from satellites and uses them to determine one's current location on Earth.

[0720] A "prompt sentence" is an input sentence that gives specific analysis and generation instructions to a generative AI model.

[0721] The present invention is a system that analyzes the risk of past incidents, accidents, and disasters based on the user's current location and displays the risk level of the area in the form of a score. Specific embodiments of this system will be described below.

[0722] First, the device is equipped with a Global Positioning System (GPS) module, which allows the device to obtain the user's current location. For example, if the user is traveling within a metropolitan area, the device will obtain latitude and longitude location information.

[0723] Once the location information is acquired, the device sends it to a server. The server then uses the received location information to reference a database of data on past incidents, accidents, and disaster risks. The database contains detailed information on past incidents, accidents, and disaster risks.

[0724] The server analyzes the data retrieved from the database. This analysis uses natural language processing technology and a generative AI model to analyze patterns of past incidents and disasters. This pattern analysis calculates the risk level in the area in the form of a score (for example, a number from 0 to 10). Using a generative AI model makes it possible to calculate a risk score with greater accuracy.

[0725] After calculating the risk score, the server sends the results to the terminal. The terminal analyzes the received data and displays the risk score to the user in real time through a graphical user interface (GUI). For example, it may display "The risk score for this area is 7 / 10." This allows the user to instantly understand the safety of the area and obtain reference information for taking safe actions.

[0726] As a concrete example, consider a user walking through an unfamiliar city at night. The device uses a GPS module to obtain the user's current location and sends that information to a server. The server then retrieves past incident and accident data for that city from a database and analyzes it using natural language processing technology. A highly accurate risk score is calculated using a generative AI model. For example, if the analysis determines that "the risk score for this area is 8 / 10," the server sends this score to the device. The device receives this score and displays "The risk score for this area is 8 / 10" on the user's screen. By viewing this information, the user can immediately understand the safety of the area and take safety-first actions.

[0727] An example prompt is:

[0728] The user is currently in Shinjuku Ward. Please calculate the risk score for this area based on incident, accident, and disaster risk data for Shinjuku Ward over the past five years. The score should be a number between 0 and 10, and should be output as, for example, "The risk score for this area is 7 / 10."

[0729] In this way, the present invention is a system that allows a user to immediately grasp the degree of danger in the area where he or she is currently located and provides useful information for quickly taking safety measures.

[0730] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0731] Step 1:

[0732] The device uses the GPS module to obtain the user's current location (latitude and longitude), which is used as input data.

[0733] Step 2:

[0734] The device sends the current location information (latitude and longitude) to the server.

[0735] Step 3:

[0736] Based on the location information received by the server, a query is issued to the database to retrieve data on past incidents, accidents, and disaster risks. This query outputs past data related to the specified location information from the database.

[0737] Step 4:

[0738] The server analyzes data on past incidents, accidents, and disaster risks using generative AI models and natural language processing technology. This analysis calculates a risk score for the area. The input data is data on past incidents, accidents, and disaster risks, and the output data is the risk score.

[0739] Step 5:

[0740] The server sends the calculated risk score to the terminal. The data sent is the risk score.

[0741] Step 6:

[0742] The terminal analyzes the received risk score and displays it to the user in real time through a graphical user interface (GUI). The operation is to visually present the risk score to the user.

[0743] Step 7:

[0744] The user checks the screen of the device and takes safe actions based on the risk score displayed in real time. In this step, the risk score plays a role in supporting the user's decision-making.

[0745] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0746] The present invention combines a system that analyzes past incidents, accidents, and disaster risks based on the user's current location and displays the risk level of the area in the form of a score with an emotion engine that recognizes the user's emotions. A specific embodiment of this system will be described below.

[0747] First, the user's device is equipped with a GPS module and an emotion recognition engine. Using the GPS module, the device obtains the user's current location. For example, if the user is in Shibuya Ward, Tokyo, the device obtains location information such as latitude 35.6623 and longitude 139.7034.

[0748] Once the location information is acquired, the device sends this location information and the user's emotional data acquired by the emotion recognition engine to the server. The emotion recognition engine analyzes the user's emotions using voice input or a facial recognition camera. Specifically, if the user indicates an emotion such as "I'm nervous right now," that information is also sent to the server.

[0749] Based on the received location information and emotion data, the server issues a query to the database to reference data on past incidents, accidents, and disaster risks. This query retrieves past data for the relevant area.

[0750] The server then analyzes the data retrieved from the database. Utilizing chat generation AI and natural language processing technology, the server analyzes patterns of past incidents and disasters. The results of this analysis are combined with the user's emotional data to calculate the danger level of the area in the form of a score. For example, if the user is nervous, the danger score may be set higher.

[0751] After the score is calculated, the server sends the results to the device, which analyzes the data and displays the risk score to the user through a GUI. For example, it might say, "The risk score for this area is 7 / 10. Caution is advised."

[0752] As a concrete example, consider a user walking through Shibuya Ward while shopping. At this time, the device uses a GPS module to obtain the user's current location and sends that information to the server. At the same time, emotional data, which the user recognizes as "anxiety," is also sent. The server retrieves past incident and accident data for Shibuya Ward from a database and uses natural language processing with chat generation AI to calculate a danger score. Based on this analysis, the danger score for Shibuya Ward is calculated as "7 / 10." The emotional data is then taken into account and the score is finally adjusted to "7.5 / 10." The server then sends this score to the device. The device receives the score and displays a message on the user's screen saying, "The danger score for this area is 7.5 / 10. Caution is advised." Using this information, the user can understand the safety of their area.

[0753] As described above, this system, which combines an emotion recognition engine, allows users to determine the risk level of their current location in real time with greater accuracy, and provides reference information for taking safe actions. This type of function is extremely useful, especially when traveling in urban areas or areas with a high risk of disasters.

[0754] From this description, it will be understood that a specific embodiment of the present invention is shown, and that the system provides assistance to users in checking information that takes into consideration their safety and their emotional state, anytime and anywhere.

[0755] The processing flow will be explained below.

[0756] Step 1: The device gets the user's current location

[0757] The device activates its built-in GPS module and acquires information about its current location. Specifically, the device receives signals from satellites and calculates its latitude and longitude. This location information is stored in the device's temporary memory.

[0758] Step 2: The device recognizes the user's emotions

[0759] The device's built-in emotion recognition engine detects the user's emotions. It uses voice input and a facial recognition camera to determine the user's emotions and generates emotion data such as "tension," "anxiety," or "relaxation." This emotion data is also temporarily stored on the device.

[0760] Step 3: The device sends location and emotion data to the server.

[0761] The device packages the location information and emotion data it acquires and sends them to a server via the network. Specifically, location information (e.g., latitude 35.6623, longitude 139.7034) and emotion data (e.g., "anxiety") are combined into a single data package.

[0762] Step 4: The server retrieves the necessary data from the database

[0763] The server analyzes the location and emotion data received from the device and issues a database query based on the location information. The database returns data on past incidents, accidents, and disaster risks related to the area to the server.

[0764] Step 5: The server parses the data

[0765] Using the acquired data, the server operates a chat generation AI. Specifically, it analyzes data on past incidents, accidents, and disaster risks using natural language processing technology, and calculates the risk level in the form of a score (e.g., 0 to 10) taking into account location information and emotional data. If the emotional data indicates "anxiety," the risk score is adjusted higher.

[0766] Step 6: The server packages the analysis results and sends them to the device.

[0767] The server combines the calculated risk score and analysis data into a single package and sends it to the terminal.

[0768] Step 7: The device receives the analysis results and displays them to the user

[0769] The device analyzes the data package received from the server and extracts a risk score.The device then launches a GUI and displays the results to the user in the form of, for example, "The risk score for this area is 7.5 / 10. Caution is advised."

[0770] Step 8: User confirms the results

[0771] Users can check their device screen and understand the risk score for their current location, which can help them decide how to proceed in that area.

[0772] Example 2

[0773] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0774] Conventional risk assessment systems display the risk level of a user's current area in the form of a score based on past incident, accident, and disaster risk data, but do not take the user's emotional state into consideration. As a result, risk assessments cannot reflect the user's subjective feelings, such as anxiety or a sense of security, and risk scores may not be appropriate for the user. Therefore, there is a need for a method of more accurate and practical risk assessment for users that takes the user's emotional state into consideration.

[0775] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0776] In this invention, the server includes a means for acquiring the user's current location, a means for acquiring data on past incidents, accidents, and disaster risks from a database, and a means for analyzing the data using natural language processing, thereby enabling risk assessment that reflects the user's emotional state.

[0777] "User's current location" is data that indicates the geographic location of a user at a particular time, typically expressed as latitude and longitude coordinate information.

[0778] An "incident" is data that indicates a criminal act that occurred at a specific place and time.

[0779] An "incident" is data that indicates an unexpected adverse occurrence caused by human or natural factors.

[0780] "Disaster risk" is data that indicates the danger that may occur due to natural or man-made disasters.

[0781] A "database" is a system that systematically stores information on past incidents, accidents, and disaster risks.

[0782] "Emotion recognition" is a technology that analyzes and determines a user's emotional state from their voice, facial expressions, etc.

[0783] "Natural language processing" is a technology that enables computers to understand and analyze human language.

[0784] The "risk score" is a numerical representation of the risk in a particular location, and is an index that indicates the risk level for the user.

[0785] A "server" is a computer system for processing and storing data.

[0786] A "terminal" is a computing device that is directly operated by a user.

[0787] MODE FOR CARRYING OUT THE INVENTION

[0788] The present invention combines a system that analyzes past incidents, accidents, and disaster risks based on the user's current location and displays the risk level of the area in the form of a score with an emotion engine that recognizes the user's emotions. A specific embodiment of this system will be described below.

[0789] First, the device held by the user is equipped with a GPS module and an emotion recognition engine. Using the GPS module, the device obtains the user's current location. For example, if the user is in Shibuya Ward, Tokyo, the device obtains location information such as latitude 35.6623 and longitude 139.7034.

[0790] Once the location information is acquired, the device sends this location information and the user's emotional data acquired by the emotion recognition engine to the server. The emotion recognition engine analyzes the user's emotions using voice input or a facial recognition camera. Specifically, if the user expresses emotions such as "I'm nervous" or "anxious," that information is also sent to the server.

[0791] Based on the received location information and emotion data, the server issues a query to the database to reference data on past incidents, accidents, and disaster risks. This query retrieves past data for the relevant area.

[0792] The server then analyzes the data retrieved from the database. It uses natural language processing technology to analyze patterns of past incidents and disasters. The results of this analysis are combined with the user's emotional data to calculate the danger level of the area in the form of a score. For example, if the user is nervous, the danger score may be set higher.

[0793] After the score is calculated, the server sends the results to the device, which analyzes the data and displays the risk score to the user through a GUI. For example, it might say, "The risk score for this area is 7 / 10. Caution is advised."

[0794] As a concrete example, consider the case where a user is walking around Shibuya Ward while shopping. At this time, the device uses a GPS module to obtain the user's current location and sends that information to the server. At the same time, emotional data, which the user recognizes as "anxiety," is also sent. The server retrieves past incident and accident data for Shibuya Ward from a database and calculates a danger score using natural language processing technology. Based on this analysis, the danger score for Shibuya Ward is calculated to be "7 / 10." The emotional data is then taken into account and the score is finally adjusted to "7.5 / 10." The server then sends this score to the device. The device receives this score and displays a message on the user's screen saying, "The danger score for this area is 7.5 / 10. Caution is advised." Using this information, the user can understand the safety of their area.

[0795] An example prompt for querying the generative AI model about this system is as follows:

[0796] plaintext

[0797] We have a system that analyzes past incidents, accidents, and disaster risks based on the user's current location and emotional data, and displays the risk level in the form of a score. For example, if a user feels "anxious" in Shibuya Ward, the system will display the risk level score for that area as "7.5 / 10." Please tell me the specific processing steps of this system.

[0798] As described above, this system integrates a risk assessment function based on the user's current location and emotional data, allowing users to check the safety of the area in real time, providing useful information for travel, especially in urban areas and areas with high disaster risk.

[0799] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0800] Processing flow

[0801] Step 1: Get the user's current location

[0802] explanation

[0803] The GPS module installed on the device is activated and the user's current location is obtained. The hardware used is a GPS module.

[0804] Input and Output

[0805] Input: None (the device itself obtains the current location)

[0806] Data processing and data calculation: The GPS module calculates the position information from the satellite signals

[0807] Output: Latitude and longitude (e.g. 35.6623, 139.7034)

[0808] Specific actions

[0809] When the user is in Shibuya Ward, the device activates the GPS module and obtains location information of latitude 35.6623 and longitude 139.7034.

[0810] Step 2: Obtain user emotion data

[0811] explanation

[0812] The emotion recognition engine installed in the device is activated, and emotion data is acquired using the user's voice input or facial expression recognition camera.

[0813] Input and Output

[0814] Input: Audio data or video data (user's facial expression)

[0815] Data processing and data calculation: Estimating emotional states through speech or image analysis

[0816] Output: Emotion data such as "anxiety"

[0817] Specific actions

[0818] If the user is feeling anxious, the device's emotion recognition engine analyzes their voice and facial expressions, and as a result, obtains the emotion data "anxiety."

[0819] Step 3: Send location and emotion data to the server

[0820] explanation

[0821] When the location information and emotion data acquired by the device is sent to the server, it is encrypted using SSL / TLS to ensure the security of the data.

[0822] Input and Output

[0823] Input: Location (35.6623, 139.7034) and emotion data ("anxiety")

[0824] Data processing and data calculation: Data is organized into packets, encrypted, and sent to the server

[0825] Output: Data sent to server completed

[0826] Specific actions

[0827] The device sends location information (35.6623, 139.7034) and emotion data ("anxiety") to the server using SSL / TLS encryption.

[0828] Step 4: Retrieve historical data from the database

[0829] explanation

[0830] Based on the location information and emotion data received by the server, a query is issued to the database to obtain data on past incidents, accidents, and disaster risks.

[0831] Input and Output

[0832] Input: Location information (35.6623, 139.7034)

[0833] Data manipulation and data calculations: Search past data using SQL queries

[0834] Output: Past incidents, accidents, and disaster data for a specific area (Shibuya Ward)

[0835] Specific actions

[0836] The server queries the database based on the location information and retrieves data on past incidents, accidents, and disasters in Shibuya Ward.

[0837] Step 5: Data analysis and risk score calculation

[0838] explanation

[0839] The server combines the data acquired with the user's emotional data and calculates a risk score using natural language processing technology.

[0840] Input and Output

[0841] Input: Past incident, accident, and disaster data and emotional data ("anxiety")

[0842] Data processing and data calculations: Analyze data using natural language processing techniques and generative AI models to calculate risk scores

[0843] Output: Risk score (e.g. 7.5 / 10)

[0844] Specific actions

[0845] The server uses past data and the user's emotional data of "anxiety" to perform an analysis using natural language processing and calculates a risk score of 7.5 / 10.

[0846] Step 6: Submit your risk score

[0847] explanation

[0848] The server sends the calculated risk score to the terminal.

[0849] Input and Output

[0850] Input: Risk Score (7.5 / 10)

[0851] Data processing and calculation: The scores are packed into packets and sent to the terminal.

[0852] Output: Data sent to the terminal completed

[0853] Specific actions

[0854] The server sends a risk score of 7.5 / 10 to the device.

[0855] Step 7: View your risk score

[0856] explanation

[0857] The device analyzes the received risk score and displays it to the user using a GUI.

[0858] Input and Output

[0859] Input: Risk Score (7.5 / 10)

[0860] Data processing and data calculation: converting scores into a format that can be displayed in the GUI

[0861] Output: Display of danger score (e.g. "This area has a danger score of 7.5 / 10. Caution required.")

[0862] Specific actions

[0863] The device receives a danger score of 7.5 / 10 and displays on the GUI, "The danger score for this area is 7.5 / 10. Caution is required."

[0864] (Application example 2)

[0865] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0866] In recent years, advances in autonomous driving technology have led to an increasing number of people using autonomous vehicles. However, there are limited ways for users to know the safety of the area they are traveling in real time, which puts them at risk of entering dangerous areas. In addition, a user's emotional state can affect their driving; for example, if they are feeling nervous or anxious, they need appropriate advice and information on the level of danger. To solve these issues, a system is needed that utilizes the user's location information and emotional data to present the risk level of an area in real time in the form of a score.

[0867] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring the user's current location, means for referencing data on past incidents, accidents, and disaster risks, means for analyzing the referenced data and calculating the risk level in the form of a score, and means for acquiring the user's emotional data and reflecting it in the risk level score. This makes it possible to present a real-time risk level score that also takes into account the user's emotional state.

[0868] "Means for obtaining the user's current location" refers to the device or technology used to identify the user's current geographic location, and typically refers to a GPS module.

[0869] "Means for referencing data on past incidents, accidents, and disaster risks" refers to devices or technologies for obtaining and referencing information from databases that store information on past incidents, accidents, and disasters.

[0870] "Means for analyzing referenced data and calculating risk in the form of a score" refers to a device or technology that analyzes acquired data on past incidents, accidents, and disaster risks, and expresses the results of that analysis as a numerical risk level.

[0871] "Means for displaying the calculated risk score to the user" refers to a device or technology for visually informing the user of the calculated risk score, such as a display or smartphone screen.

[0872] "Means for acquiring user emotional data and reflecting it in the risk score" refers to devices or technologies for detecting and analyzing the user's emotional state and incorporating that data into the risk score calculation process, including emotion recognition engines and sensors.

[0873] The present invention is a system that analyzes past incident, accident, and disaster risk data in an area based on the current location of the autonomous vehicle the user is riding in, and provides a risk score that also takes emotion data into account. This system is realized using the following hardware and software.

[0874] First, the server uses the GPS module to obtain the user's current location. This allows the autonomous vehicle to determine its current latitude and longitude and send that information to the server. In practice, location information can be obtained using common location services (e.g., the Nominatim API in the Geopy library).

[0875] Next, the device acquires the user's emotional data. This is done by analyzing the user's facial expressions and voice using the smartphone's camera and microphone, and then using an emotion recognition engine to recognize the user's emotional state. Specifically, by using a library such as EmotionRecognizer, the device can analyze the user's emotions at that moment.

[0876] The server references past incidents, accidents, and disaster risk data from a database based on the acquired location information and emotion data, issuing appropriate API requests to retrieve relevant data and collect the information needed for analysis.

[0877] The server then analyzes the referenced data and calculates the risk level in the form of a score. Here, generative AI models and natural language processing technology are used to analyze patterns of past incidents and disasters, and a risk score is derived that takes into account emotional data. This process requires advanced data analysis using generative AI models.

[0878] The risk score calculated from the analysis results is sent to the device and displayed to the user. For example, the risk score and safety information can be displayed on the display of the self-driving vehicle or on the screen of a smartphone. The display format is a specific alert such as, "The risk score for this area is 8 / 10. Please drive carefully."

[0879] As a concrete example, if a user in an autonomous vehicle enters an area where many accidents have been reported, the server obtains the user's location information and references past accident data from a database. At the same time, if the user is feeling anxious, emotional data is also taken into account in the analysis. Analysis using a generative AI model calculates an overall risk score, and a message is displayed stating, "The risk score for this area is 8.5 / 10. Caution is advised."

[0880] Example prompt sentence:

[0881] If a user at latitude 35.6623, longitude 139.7034 sends emotional data saying they are "nervous," calculate a risk score based on past incidents, accidents, and disaster risks in this area.

[0882] In this way, the "safe driving navigation" of the present invention can present a real-time risk score that also takes into account the user's emotional state, thereby supporting safer driving.

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

[0884] Step 1:

[0885] Obtain the user's current location. The device uses a GPS module to obtain the current latitude and longitude, and then sends this location information to the server. The input is the location data obtained from the user's device, and the output is the latitude and longitude location information sent to the server. Specifically, the device's GPS module measures the current location and transmits this data to the server.

[0886] Step 2:

[0887] Acquires the user's emotional data. The device uses the smartphone's camera and microphone to capture the user's facial expressions and voice, which are then analyzed using an emotion recognition engine. The analyzed emotional data is sent to a server. The input is image data and voice data acquired from the user's device, and the output is the emotional state (e.g., tension, anxiety) sent to the server. Specifically, the device's camera captures the user's facial expressions and records their voice, and these data are analyzed using an emotion recognition engine.

[0888] Step 3:

[0889] Obtain data on past incidents, accidents, and disaster risks. The server issues a query to the database based on location information and emotion data to obtain related data. The input is the location information and emotion data sent to the server, and the output is data on past incidents, accidents, and disaster risks. Specifically, the server issues a query to the database based on location information and obtains the results.

[0890] Step 4:

[0891] The risk level is calculated in the form of a score. Using past data acquired by the server and user emotional data, the risk score is calculated using a generative AI model and natural language processing technology. The input is past incident, accident, and disaster risk data and emotional data, and the output is the calculated risk score. Specifically, the server uses the generative AI model to analyze the data, find past patterns, and derive a risk score that takes emotional data into account.

[0892] Step 5:

[0893] The danger score is displayed to the user. The server sends the calculated danger score to the terminal, which then visually displays it to the user. The input is the danger score sent from the server, and the output is the danger score and a warning message displayed on the terminal. Specifically, the server sends the danger score to the terminal, and the terminal displays "The danger score for this area is 8.5 / 10. Caution required."

[0894] Step 6:

[0895] Notifications are sent in real time. When the risk score exceeds a certain standard, the device will issue a real-time notification such as an alarm or vibration to alert the user. The input is the risk score from the server, and the output is the real-time notification action (alert, vibration, etc.). Specifically, the device analyzes the risk score and issues a real-time notification if the score exceeds the set standard.

[0896] Based on the above processing steps, the "safe driving navigation" of the present invention realizes a system that ensures the user's safety by presenting a real-time risk score based on the user's emotional state and location information.

[0897] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0898] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0899] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[0900] [Fourth embodiment]

[0901] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0902] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0903] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0904] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0905] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0906] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0907] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0908] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0909] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0910] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0911] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0912] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0913] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0914] The present invention is a system that analyzes the risk of past incidents, accidents, and disasters based on the user's current location and displays the risk level of the area in the form of a score. Specific embodiments of this system will be described below.

[0915] First, the device held by the user is equipped with a GPS module. Using this GPS module, the device obtains the user's current location. For example, if the user is in Shibuya Ward, Tokyo, the device will obtain location information such as latitude 35.6623 and longitude 139.7034.

[0916] Once the location information is acquired, the device sends it to a server, which then queries a database to retrieve data on past incidents, accidents, and disaster risks. The data retrieved includes a series of past events and risk information related to the area.

[0917] The server analyzes the data retrieved from the database. Specifically, it utilizes chat generation AI and natural language processing technology to analyze patterns of past incidents and disasters. This allows it to calculate the level of danger in the area in the form of a score (for example, a number from 0 to 10). The score calculated in this way is intended to provide users with an intuitive, easy-to-understand indication of the danger level in the area.

[0918] After the score is calculated, the server sends the result to the terminal. The terminal analyzes the received data and displays the risk score to the user through a GUI (graphical user interface). For example, it may display a message such as, "The risk score for this area is 7 / 10."

[0919] As a concrete example, consider the case where a user is walking around Shibuya Ward while shopping. At this time, the device uses a GPS module to obtain the user's current location and sends this information to the server. The server retrieves past incident and accident data for Shibuya Ward from a database and calculates a danger score using natural language processing with a chat generation AI. Based on this analysis, the danger score for Shibuya Ward is calculated to be "7 / 10," and the server sends this score to the device. The device receives this score and displays on the user's screen, "The danger score for this area is 7 / 10." The user can view this information to understand the safety of the area they are in.

[0920] As described above, this system allows users to determine the risk level of their current location in real time and obtain reference information for taking safe actions. This function is extremely useful, especially when traveling in urban areas or areas with high disaster risk.

[0921] From this description, it will be understood that a specific embodiment of the present invention is shown, and that the present invention is a system that provides assistance to users in confirming safety anytime and anywhere.

[0922] The processing flow will be explained below.

[0923] Step 1: The device gets the user's current location

[0924] The device activates its built-in GPS module and acquires information about its current location. Specifically, the device receives signals from satellites and calculates its latitude and longitude. This location information is stored in the device's temporary memory.

[0925] Step 2: The device sends its location and request to the server

[0926] The device packages the user's request based on the location information it acquires. For example, if a user requests to know the current level of danger, the device combines the location information and the request into a single data package and sends it to the server over the network.

[0927] Step 3: The server retrieves the necessary data from the database

[0928] The server analyzes the data package received from the device and retrieves data on relevant past incidents, accidents, and disaster risks from a database based on the device's current location. Specifically, the server issues a database query using the location information as a key to retrieve the relevant data.

[0929] Step 4: The server parses the data

[0930] Based on the acquired data, the server uses chat generation AI to perform natural language processing. Specifically, it analyzes past data and identifies patterns of incidents, accidents, and disasters related to the current location. This then scores the area's risk level on a scale of 0 to 10.

[0931] Step 5: The server packages the analysis results and sends them to the device.

[0932] The server compiles the calculated risk score and related data into a package, which is then sent to the device via the network.

[0933] Step 6: The device receives the analysis results and displays them to the user

[0934] The device analyzes the data package received from the server and extracts a risk score. The device then launches a GUI and displays the result to the user, such as "The risk score for this area is 7 / 10."

[0935] Step 7: User confirms the results

[0936] Users can check their device screen and understand the risk score for their current location, which can provide them with information to help them decide on their course of action in that area.

[0937] Example 1

[0938] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0939] Currently, it is difficult for users to grasp their own safety in real time while traveling or out. In addition, there is a lack of means to instantly obtain information on past incidents, accidents, disaster risks, etc., and to intuitively understand the specific level of danger. As a result, the risk of encountering high-risk areas increases, potentially threatening the user's safety.

[0940] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0941] In this invention, the server includes a means for acquiring the user's current location, a means for referencing past risk data, and a means for analyzing the data and calculating a risk score, thereby enabling the user to grasp the risk level based on their current location in real time and take safe actions.

[0942] "User" refers to an individual or corporation that uses the system to obtain risk information about their current location.

[0943] "Current location" refers to the user's actual geographic location obtained through a GPS module or other location information acquisition means.

[0944] "Risk data" refers to data that comprehensively includes information on past incidents, accidents, and disaster risks.

[0945] "Database" refers to an information processing system for structuring and storing risk data.

[0946] "GPS module" refers to a hardware device for obtaining current location using the Global Positioning System.

[0947] The term "server" refers to an information processing device that analyzes risk data based on location information received from a user's terminal and returns the results to the terminal.

[0948] "Terminal" refers to a portable information processing device that is owned by a user and has a GPS module and communication functions.

[0949] "Chat generation AI" refers to artificial intelligence that uses natural language processing technology to analyze data and is designed to be able to have natural conversations with humans.

[0950] A "prompt sentence" refers to a sentence of instructions or questions that is entered into the chat generation AI to perform analysis.

[0951] An "HTTP request" refers to a form of communication protocol that a terminal sends to a server to request data.

[0952] "Danger score" refers to a numerical assessment of the danger level of a particular area based on data analysis.

[0953] "GUI" is an abbreviation for Graphical User Interface, and refers to an interface that provides information to users visually.

[0954] MODE FOR CARRYING OUT THE INVENTION

[0955] The present invention is a system that analyzes past incidents, accidents, and disaster risks based on the user's current location and displays the risk level of the area in the form of a score.

[0956] First, the user has a device equipped with a GPS module. This device uses the GPS module to obtain the user's current location. For example, if the user is in Shibuya Ward, Tokyo, the device will obtain location information such as latitude 35.6623 and longitude 139.7034.

[0957] The device then sends the location information to a server, typically via an HTTP request, which queries a database for past incidents, accidents, and disaster risk data.

[0958] The server uses a chat generation AI model to analyze past data. This AI model uses natural language processing technology to analyze risk data and calculate the risk level of the area in the form of a score. Specifically, the AI ​​is input with the prompt "Please give me an overview of incidents and accidents in Shibuya Ward over the past three years" to perform the analysis.

[0959] Once the analysis is complete, the server sends the calculated risk score to the device. Based on the received data, the device displays the risk score to the user via a GUI (graphical user interface). For example, the device might display "The risk score for this area is 7 / 10."

[0960] As a concrete example, consider the case where a user is walking around Shibuya Ward while shopping. At this time, the device uses a GPS module to obtain the user's current location and sends this information to the server. The server retrieves past incident and accident data for Shibuya Ward from a database and calculates a danger score using natural language processing with a chat generation AI. Based on this analysis, the danger score for Shibuya Ward is calculated to be "7 / 10," and the server sends this score to the device. The device receives this score and displays the message "The danger score for this area is 7 / 10" on the user's screen.

[0961] As described above, this system allows users to determine the risk level of their current location in real time and obtain reference information for safe behavior, which is particularly useful when traveling through urban areas or areas with high disaster risk.

[0962] The hardware used includes a GPS module and a terminal, and the software used includes a database management system, an HTTP communication library, a chat generation AI model, and a natural language processing library. By implementing this technology, users can obtain a real-time risk score and understand their safety.

[0963] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0964] Specific explanation of processing steps

[0965] Step 1: Get current location

[0966] A user carries a device with a GPS function.

[0967] Input: The user's current geographic location

[0968] The device periodically activates the GPS module and obtains its current location (latitude and longitude).

[0969] Output: Current location (e.g., latitude 35.6623, longitude 139.7034)

[0970] Specific behavior: The code is implemented so that the device obtains location information using the GPS API.

[0971] Step 2: Send location information

[0972] The device sends the current location data it has acquired to the server via an HTTP request.

[0973] Input: Current location (latitude and longitude)

[0974] Output: Location information sent to the server

[0975] Specific operation: The device generates an HTTP request and posts the location information to the server in JSON format or similar.

[0976] Step 3: Obtaining historical data

[0977] Based on the location information received by the server, an SQL query is issued to the database to retrieve data on past incidents, accidents, and disaster risks.

[0978] Input: Location information sent to the server

[0979] The server issues a query to the database such as "SELECT FROM risk_data WHERE latitude=35.6623 AND longitude=139.7034".

[0980] Output: Past incidents, accidents, and disaster risk data

[0981] Specific operation: The server retrieves data from the database using an ORM such as SQLAlchemy.

[0982] Step 4: Analyze the data

[0983] The server uses chat generation AI and natural language processing technology to analyze past data.

[0984] Input: Historical risk data

[0985] The server inputs the prompt text "Please give me an overview of the incidents and accidents in Shibuya Ward over the past three years" into the chat generation AI, and the AI ​​performs the analysis.

[0986] Output: Hazard score for the area (e.g. 7 / 10)

[0987] Specific operation: The server sends a prompt to the AI ​​model and receives the analysis results.

[0988] Data processing: Analyze regular text data and convert it into a numerical risk score.

[0989] Step 5: Submit your score

[0990] The server sends the calculated risk score to the terminal in JSON format as an HTTP response.

[0991] Input: Calculated risk score

[0992] Output: Risk score sent to the device

[0993] Specific operation: The server generates an HTTP response and sends the risk score in JSON format to the device.

[0994] Step 6: View your score

[0995] The risk score received by the terminal is displayed to the user via a GUI (graphical user interface).

[0996] Input: Risk score sent from the server

[0997] Output: Risk score displayed to the user

[0998] Specific operation: The device uses JavaScript or native application code to dynamically display the risk score on the screen.

[0999] Example: The device screen displays, "The danger score for this area is 7 / 10."

[1000] (Application example 1)

[1001] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1002] With conventional safety confirmation systems, it was difficult for users to immediately grasp the risk level of their current location. Furthermore, there was a lack of a well-established mechanism for displaying the risk level of a location in real time, which could lead to delayed safety measures. Furthermore, there was a lack of technology to analyze detailed data on past incidents and disaster risks when calculating risk scores.

[1003] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1004] In this invention, the server includes a means for referencing data on past incidents, accidents, and disaster risks based on location information, a means for analyzing the referenced data using natural language processing technology and calculating a risk score using a generation AI model, and a means for displaying the risk score in real time, thereby enabling the user to instantly grasp the risk level of the area where they are currently located and take safe actions based on the risk score displayed in real time.

[1005] The "current location" is location information that indicates the latitude and longitude of the user when he or she is at a specific point.

[1006] The "reference means" is a means for obtaining data on incidents, accidents, and disaster risks that have occurred in the past from a database based on the user's current location.

[1007] The "means of analysis" refers to a method for calculating the risk level of an area in the form of a score based on the acquired data on past incidents, accidents, and disaster risks.

[1008] The "display means" is a means for visually presenting the calculated risk score to the user.

[1009] A "database" is an information system that accumulates information on past incidents, accidents, and disaster risks and stores it in a searchable format.

[1010] "Natural language processing" is a technology that allows computers to understand and analyze human language.

[1011] A "generative AI model" is an artificial intelligence model that learns patterns from past data to generate or analyze new data.

[1012] A "Global Positioning System (GPS) module" is a device that receives signals from satellites and uses them to determine one's current location on Earth.

[1013] A "prompt sentence" is an input sentence that gives specific analysis and generation instructions to a generative AI model.

[1014] The present invention is a system that analyzes the risk of past incidents, accidents, and disasters based on the user's current location and displays the risk level of the area in the form of a score. Specific embodiments of this system will be described below.

[1015] First, the device is equipped with a Global Positioning System (GPS) module, which allows the device to obtain the user's current location. For example, if the user is traveling within a metropolitan area, the device will obtain latitude and longitude location information.

[1016] Once the location information is acquired, the device sends it to a server. The server then uses the received location information to reference a database of data on past incidents, accidents, and disaster risks. The database contains detailed information on past incidents, accidents, and disaster risks.

[1017] The server analyzes the data retrieved from the database. This analysis uses natural language processing technology and a generative AI model to analyze patterns of past incidents and disasters. This pattern analysis calculates the risk level in the area in the form of a score (for example, a number from 0 to 10). Using a generative AI model makes it possible to calculate a risk score with greater accuracy.

[1018] After calculating the risk score, the server sends the results to the terminal. The terminal analyzes the received data and displays the risk score to the user in real time through a graphical user interface (GUI). For example, it may display "The risk score for this area is 7 / 10." This allows the user to instantly understand the safety of the area and obtain reference information for taking safe actions.

[1019] As a concrete example, consider a user walking through an unfamiliar city at night. The device uses a GPS module to obtain the user's current location and sends that information to a server. The server then retrieves past incident and accident data for that city from a database and analyzes it using natural language processing technology. A highly accurate risk score is calculated using a generative AI model. For example, if the analysis determines that "the risk score for this area is 8 / 10," the server sends this score to the device. The device receives this score and displays "The risk score for this area is 8 / 10" on the user's screen. By viewing this information, the user can immediately understand the safety of the area and take safety-first actions.

[1020] An example prompt is:

[1021] The user is currently in Shinjuku Ward. Please calculate the risk score for this area based on incident, accident, and disaster risk data for Shinjuku Ward over the past five years. The score should be a number between 0 and 10, and should be output as, for example, "The risk score for this area is 7 / 10."

[1022] In this way, the present invention is a system that allows a user to immediately grasp the degree of danger in the area where he or she is currently located and provides useful information for quickly taking safety measures.

[1023] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1024] Step 1:

[1025] The device uses the GPS module to obtain the user's current location (latitude and longitude), which is used as input data.

[1026] Step 2:

[1027] The device sends the current location information (latitude and longitude) to the server.

[1028] Step 3:

[1029] Based on the location information received by the server, a query is issued to the database to retrieve data on past incidents, accidents, and disaster risks. This query outputs past data related to the specified location information from the database.

[1030] Step 4:

[1031] The server analyzes data on past incidents, accidents, and disaster risks using generative AI models and natural language processing technology. This analysis calculates a risk score for the area. The input data is data on past incidents, accidents, and disaster risks, and the output data is the risk score.

[1032] Step 5:

[1033] The server sends the calculated risk score to the terminal. The data sent is the risk score.

[1034] Step 6:

[1035] The terminal analyzes the received risk score and displays it to the user in real time through a graphical user interface (GUI). The operation is to visually present the risk score to the user.

[1036] Step 7:

[1037] The user checks the screen of the device and takes safe actions based on the risk score displayed in real time. In this step, the risk score plays a role in supporting the user's decision-making.

[1038] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1039] The present invention combines a system that analyzes past incidents, accidents, and disaster risks based on the user's current location and displays the risk level of the area in the form of a score with an emotion engine that recognizes the user's emotions. A specific embodiment of this system will be described below.

[1040] First, the user's device is equipped with a GPS module and an emotion recognition engine. Using the GPS module, the device obtains the user's current location. For example, if the user is in Shibuya Ward, Tokyo, the device obtains location information such as latitude 35.6623 and longitude 139.7034.

[1041] Once the location information is acquired, the device sends this location information and the user's emotional data acquired by the emotion recognition engine to the server. The emotion recognition engine analyzes the user's emotions using voice input or a facial recognition camera. Specifically, if the user indicates an emotion such as "I'm nervous right now," that information is also sent to the server.

[1042] Based on the received location information and emotion data, the server issues a query to the database to reference data on past incidents, accidents, and disaster risks. This query retrieves past data for the relevant area.

[1043] The server then analyzes the data retrieved from the database. Utilizing chat generation AI and natural language processing technology, the server analyzes patterns of past incidents and disasters. The results of this analysis are combined with the user's emotional data to calculate the danger level of the area in the form of a score. For example, if the user is nervous, the danger score may be set higher.

[1044] After the score is calculated, the server sends the results to the device, which analyzes the data and displays the risk score to the user through a GUI. For example, it might say, "The risk score for this area is 7 / 10. Caution is advised."

[1045] As a concrete example, consider a user walking through Shibuya Ward while shopping. At this time, the device uses a GPS module to obtain the user's current location and sends that information to the server. At the same time, emotional data, which the user recognizes as "anxiety," is also sent. The server retrieves past incident and accident data for Shibuya Ward from a database and uses natural language processing with chat generation AI to calculate a danger score. Based on this analysis, the danger score for Shibuya Ward is calculated as "7 / 10." The emotional data is then taken into account and the score is finally adjusted to "7.5 / 10." The server then sends this score to the device. The device receives the score and displays a message on the user's screen saying, "The danger score for this area is 7.5 / 10. Caution is advised." Using this information, the user can understand the safety of their area.

[1046] As described above, this system, which combines an emotion recognition engine, allows users to determine the risk level of their current location in real time with greater accuracy, and provides reference information for taking safe actions. This type of function is extremely useful, especially when traveling in urban areas or areas with a high risk of disasters.

[1047] From this description, it will be understood that a specific embodiment of the present invention is shown, and that the system provides assistance to users in checking information that takes into consideration their safety and their emotional state, anytime and anywhere.

[1048] The processing flow will be explained below.

[1049] Step 1: The device gets the user's current location

[1050] The device activates its built-in GPS module and acquires information about its current location. Specifically, the device receives signals from satellites and calculates its latitude and longitude. This location information is stored in the device's temporary memory.

[1051] Step 2: The device recognizes the user's emotions

[1052] The device's built-in emotion recognition engine detects the user's emotions. It uses voice input and a facial recognition camera to determine the user's emotions and generates emotion data such as "tension," "anxiety," or "relaxation." This emotion data is also temporarily stored on the device.

[1053] Step 3: The device sends location and emotion data to the server.

[1054] The device packages the location information and emotion data it acquires and sends them to a server via the network. Specifically, location information (e.g., latitude 35.6623, longitude 139.7034) and emotion data (e.g., "anxiety") are combined into a single data package.

[1055] Step 4: The server retrieves the necessary data from the database

[1056] The server analyzes the location and emotion data received from the device and issues a database query based on the location information. The database returns data on past incidents, accidents, and disaster risks related to the area to the server.

[1057] Step 5: The server parses the data

[1058] Using the acquired data, the server operates a chat generation AI. Specifically, it analyzes data on past incidents, accidents, and disaster risks using natural language processing technology, and calculates the risk level in the form of a score (e.g., 0 to 10) taking into account location information and emotional data. If the emotional data indicates "anxiety," the risk score is adjusted higher.

[1059] Step 6: The server packages the analysis results and sends them to the device.

[1060] The server combines the calculated risk score and analysis data into a single package and sends it to the terminal.

[1061] Step 7: The device receives the analysis results and displays them to the user

[1062] The device analyzes the data package received from the server and extracts a risk score.The device then launches a GUI and displays the results to the user in the form of, for example, "The risk score for this area is 7.5 / 10. Caution is advised."

[1063] Step 8: User confirms the results

[1064] Users can check their device screen and understand the risk score for their current location, which can help them decide how to proceed in that area.

[1065] Example 2

[1066] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1067] Conventional risk assessment systems display the risk level of a user's current area in the form of a score based on past incident, accident, and disaster risk data, but do not take the user's emotional state into consideration. As a result, risk assessments cannot reflect the user's subjective feelings, such as anxiety or a sense of security, and risk scores may not be appropriate for the user. Therefore, there is a need for a method of more accurate and practical risk assessment for users that takes the user's emotional state into consideration.

[1068] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1069] In this invention, the server includes a means for acquiring the user's current location, a means for acquiring data on past incidents, accidents, and disaster risks from a database, and a means for analyzing the data using natural language processing, thereby enabling risk assessment that reflects the user's emotional state.

[1070] "User's current location" is data that indicates the geographic location of a user at a particular time, typically expressed as latitude and longitude coordinate information.

[1071] An "incident" is data that indicates a criminal act that occurred at a specific place and time.

[1072] An "incident" is data that indicates an unexpected adverse occurrence caused by human or natural factors.

[1073] "Disaster risk" is data that indicates the danger that may occur due to natural or man-made disasters.

[1074] A "database" is a system that systematically stores information on past incidents, accidents, and disaster risks.

[1075] "Emotion recognition" is a technology that analyzes and determines a user's emotional state from their voice, facial expressions, etc.

[1076] "Natural language processing" is a technology that enables computers to understand and analyze human language.

[1077] The "risk score" is a numerical representation of the risk in a particular location, and is an index that indicates the risk level for the user.

[1078] A "server" is a computer system for processing and storing data.

[1079] A "terminal" is a computing device that is directly operated by a user.

[1080] MODE FOR CARRYING OUT THE INVENTION

[1081] The present invention combines a system that analyzes past incidents, accidents, and disaster risks based on the user's current location and displays the risk level of the area in the form of a score with an emotion engine that recognizes the user's emotions. A specific embodiment of this system will be described below.

[1082] First, the device held by the user is equipped with a GPS module and an emotion recognition engine. Using the GPS module, the device obtains the user's current location. For example, if the user is in Shibuya Ward, Tokyo, the device obtains location information such as latitude 35.6623 and longitude 139.7034.

[1083] Once the location information is acquired, the device sends this location information and the user's emotional data acquired by the emotion recognition engine to the server. The emotion recognition engine analyzes the user's emotions using voice input or a facial recognition camera. Specifically, if the user expresses emotions such as "I'm nervous" or "anxious," that information is also sent to the server.

[1084] Based on the received location information and emotion data, the server issues a query to the database to reference data on past incidents, accidents, and disaster risks. This query retrieves past data for the relevant area.

[1085] The server then analyzes the data retrieved from the database. It uses natural language processing technology to analyze patterns of past incidents and disasters. The results of this analysis are combined with the user's emotional data to calculate the danger level of the area in the form of a score. For example, if the user is nervous, the danger score may be set higher.

[1086] After the score is calculated, the server sends the results to the device, which analyzes the data and displays the risk score to the user through a GUI. For example, it might say, "The risk score for this area is 7 / 10. Caution is advised."

[1087] As a concrete example, consider the case where a user is walking around Shibuya Ward while shopping. At this time, the device uses a GPS module to obtain the user's current location and sends that information to the server. At the same time, emotional data, which the user recognizes as "anxiety," is also sent. The server retrieves past incident and accident data for Shibuya Ward from a database and calculates a danger score using natural language processing technology. Based on this analysis, the danger score for Shibuya Ward is calculated to be "7 / 10." The emotional data is then taken into account and the score is finally adjusted to "7.5 / 10." The server then sends this score to the device. The device receives this score and displays a message on the user's screen saying, "The danger score for this area is 7.5 / 10. Caution is advised." Using this information, the user can understand the safety of their area.

[1088] An example prompt for querying the generative AI model about this system is as follows:

[1089] plaintext

[1090] We have a system that analyzes past incidents, accidents, and disaster risks based on the user's current location and emotional data, and displays the risk level in the form of a score. For example, if a user feels "anxious" in Shibuya Ward, the system will display the risk level score for that area as "7.5 / 10." Please tell me the specific processing steps of this system.

[1091] As described above, this system integrates a risk assessment function based on the user's current location and emotional data, allowing users to check the safety of the area in real time, providing useful information for travel, especially in urban areas and areas with high disaster risk.

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

[1093] Processing flow

[1094] Step 1: Get the user's current location

[1095] explanation

[1096] The GPS module installed on the device is activated and the user's current location is obtained. The hardware used is a GPS module.

[1097] Input and Output

[1098] Input: None (the device itself obtains the current location)

[1099] Data processing and data calculation: The GPS module calculates the position information from the satellite signals

[1100] Output: Latitude and longitude (e.g. 35.6623, 139.7034)

[1101] Specific actions

[1102] When the user is in Shibuya Ward, the device activates the GPS module and obtains location information of latitude 35.6623 and longitude 139.7034.

[1103] Step 2: Obtain user emotion data

[1104] explanation

[1105] The emotion recognition engine installed in the device is activated, and emotion data is acquired using the user's voice input or facial expression recognition camera.

[1106] Input and Output

[1107] Input: Audio data or video data (user's facial expression)

[1108] Data processing and data calculation: Estimating emotional states through speech or image analysis

[1109] Output: Emotion data such as "anxiety"

[1110] Specific actions

[1111] If the user is feeling anxious, the device's emotion recognition engine analyzes their voice and facial expressions, and as a result, obtains the emotion data "anxiety."

[1112] Step 3: Send location and emotion data to the server

[1113] explanation

[1114] When the location information and emotion data acquired by the device is sent to the server, it is encrypted using SSL / TLS to ensure the security of the data.

[1115] Input and Output

[1116] Input: Location (35.6623, 139.7034) and emotion data ("anxiety")

[1117] Data processing and data calculation: Data is organized into packets, encrypted, and sent to the server

[1118] Output: Data sent to server completed

[1119] Specific actions

[1120] The device sends location information (35.6623, 139.7034) and emotion data ("anxiety") to the server using SSL / TLS encryption.

[1121] Step 4: Retrieve historical data from the database

[1122] explanation

[1123] Based on the location information and emotion data received by the server, a query is issued to the database to obtain data on past incidents, accidents, and disaster risks.

[1124] Input and Output

[1125] Input: Location information (35.6623, 139.7034)

[1126] Data manipulation and data calculations: Search past data using SQL queries

[1127] Output: Past incidents, accidents, and disaster data for a specific area (Shibuya Ward)

[1128] Specific actions

[1129] The server queries the database based on the location information and retrieves data on past incidents, accidents, and disasters in Shibuya Ward.

[1130] Step 5: Data analysis and risk score calculation

[1131] explanation

[1132] The server combines the data acquired with the user's emotional data and calculates a risk score using natural language processing technology.

[1133] Input and Output

[1134] Input: Past incident, accident, and disaster data and emotional data ("anxiety")

[1135] Data processing and data calculations: Analyze data using natural language processing techniques and generative AI models to calculate risk scores

[1136] Output: Risk score (e.g. 7.5 / 10)

[1137] Specific actions

[1138] The server uses past data and the user's emotional data of "anxiety" to perform an analysis using natural language processing and calculates a risk score of 7.5 / 10.

[1139] Step 6: Submit your risk score

[1140] explanation

[1141] The server sends the calculated risk score to the terminal.

[1142] Input and Output

[1143] Input: Risk Score (7.5 / 10)

[1144] Data processing and calculation: The scores are packed into packets and sent to the terminal.

[1145] Output: Data sent to the terminal completed

[1146] Specific actions

[1147] The server sends a risk score of 7.5 / 10 to the device.

[1148] Step 7: View your risk score

[1149] explanation

[1150] The device analyzes the received risk score and displays it to the user using a GUI.

[1151] Input and Output

[1152] Input: Risk Score (7.5 / 10)

[1153] Data processing and data calculation: converting scores into a format that can be displayed in the GUI

[1154] Output: Display of danger score (e.g. "This area has a danger score of 7.5 / 10. Caution required.")

[1155] Specific actions

[1156] The device receives a danger score of 7.5 / 10 and displays on the GUI, "The danger score for this area is 7.5 / 10. Caution is required."

[1157] (Application example 2)

[1158] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1159] In recent years, advances in autonomous driving technology have led to an increasing number of people using autonomous vehicles. However, there are limited ways for users to know the safety of the area they are traveling in real time, which puts them at risk of entering dangerous areas. In addition, a user's emotional state can affect their driving; for example, if they are feeling nervous or anxious, they need appropriate advice and information on the level of danger. To solve these issues, a system is needed that utilizes the user's location information and emotional data to present the risk level of an area in real time in the form of a score.

[1160] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring the user's current location, means for referencing data on past incidents, accidents, and disaster risks, means for analyzing the referenced data and calculating the risk level in the form of a score, and means for acquiring the user's emotional data and reflecting it in the risk level score. This makes it possible to present a real-time risk level score that also takes into account the user's emotional state.

[1161] "Means for obtaining the user's current location" refers to the device or technology used to identify the user's current geographic location, and typically refers to a GPS module.

[1162] "Means for referencing data on past incidents, accidents, and disaster risks" refers to devices or technologies for obtaining and referencing information from databases that store information on past incidents, accidents, and disasters.

[1163] "Means for analyzing referenced data and calculating risk in the form of a score" refers to a device or technology that analyzes acquired data on past incidents, accidents, and disaster risks, and expresses the results of that analysis as a numerical risk level.

[1164] "Means for displaying the calculated risk score to the user" refers to a device or technology for visually informing the user of the calculated risk score, such as a display or smartphone screen.

[1165] "Means for acquiring user emotional data and reflecting it in the risk score" refers to devices or technologies for detecting and analyzing the user's emotional state and incorporating that data into the risk score calculation process, including emotion recognition engines and sensors.

[1166] The present invention is a system that analyzes past incident, accident, and disaster risk data in an area based on the current location of the autonomous vehicle the user is riding in, and provides a risk score that also takes emotion data into account. This system is realized using the following hardware and software.

[1167] First, the server uses the GPS module to obtain the user's current location. This allows the autonomous vehicle to determine its current latitude and longitude and send that information to the server. In practice, location information can be obtained using common location services (e.g., the Nominatim API in the Geopy library).

[1168] Next, the device acquires the user's emotional data. This is done by analyzing the user's facial expressions and voice using the smartphone's camera and microphone, and then using an emotion recognition engine to recognize the user's emotional state. Specifically, by using a library such as EmotionRecognizer, the device can analyze the user's emotions at that moment.

[1169] The server references past incidents, accidents, and disaster risk data from a database based on the acquired location information and emotion data, issuing appropriate API requests to retrieve relevant data and collect the information needed for analysis.

[1170] The server then analyzes the referenced data and calculates the risk level in the form of a score. Here, generative AI models and natural language processing technology are used to analyze patterns of past incidents and disasters, and a risk score is derived that takes into account emotional data. This process requires advanced data analysis using generative AI models.

[1171] The risk score calculated from the analysis results is sent to the device and displayed to the user. For example, the risk score and safety information can be displayed on the display of the self-driving vehicle or on the screen of a smartphone. The display format is a specific alert such as, "The risk score for this area is 8 / 10. Please drive carefully."

[1172] As a concrete example, if a user in an autonomous vehicle enters an area where many accidents have been reported, the server obtains the user's location information and references past accident data from a database. At the same time, if the user is feeling anxious, emotional data is also taken into account in the analysis. Analysis using a generative AI model calculates an overall risk score, and a message is displayed stating, "The risk score for this area is 8.5 / 10. Caution is advised."

[1173] Example prompt sentence:

[1174] If a user at latitude 35.6623, longitude 139.7034 sends emotional data saying they are "nervous," calculate a risk score based on past incidents, accidents, and disaster risks in this area.

[1175] In this way, the "safe driving navigation" of the present invention can present a real-time risk score that also takes into account the user's emotional state, thereby supporting safer driving.

[1176] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1177] Step 1:

[1178] Obtain the user's current location. The device uses a GPS module to obtain the current latitude and longitude, and then sends this location information to the server. The input is the location data obtained from the user's device, and the output is the latitude and longitude location information sent to the server. Specifically, the device's GPS module measures the current location and transmits this data to the server.

[1179] Step 2:

[1180] Acquires the user's emotional data. The device uses the smartphone's camera and microphone to capture the user's facial expressions and voice, which are then analyzed using an emotion recognition engine. The analyzed emotional data is sent to a server. The input is image data and voice data acquired from the user's device, and the output is the emotional state (e.g., tension, anxiety) sent to the server. Specifically, the device's camera captures the user's facial expressions and records their voice, and these data are analyzed using an emotion recognition engine.

[1181] Step 3:

[1182] Obtain data on past incidents, accidents, and disaster risks. The server issues a query to the database based on location information and emotion data to obtain related data. The input is the location information and emotion data sent to the server, and the output is data on past incidents, accidents, and disaster risks. Specifically, the server issues a query to the database based on location information and obtains the results.

[1183] Step 4:

[1184] The risk level is calculated in the form of a score. Using past data acquired by the server and user emotional data, the risk score is calculated using a generative AI model and natural language processing technology. The input is past incident, accident, and disaster risk data and emotional data, and the output is the calculated risk score. Specifically, the server uses the generative AI model to analyze the data, find past patterns, and derive a risk score that takes emotional data into account.

[1185] Step 5:

[1186] The danger score is displayed to the user. The server sends the calculated danger score to the terminal, which then visually displays it to the user. The input is the danger score sent from the server, and the output is the danger score and a warning message displayed on the terminal. Specifically, the server sends the danger score to the terminal, and the terminal displays "The danger score for this area is 8.5 / 10. Caution required."

[1187] Step 6:

[1188] Notifications are sent in real time. When the risk score exceeds a certain standard, the device will issue a real-time notification such as an alarm or vibration to alert the user. The input is the risk score from the server, and the output is the real-time notification action (alert, vibration, etc.). Specifically, the device analyzes the risk score and issues a real-time notification if the score exceeds the set standard.

[1189] Based on the above processing steps, the "safe driving navigation" of the present invention realizes a system that ensures the user's safety by presenting a real-time risk score based on the user's emotional state and location information.

[1190] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1191] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1192] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1193] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1194] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1195] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1196] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1197] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1198] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1199] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1200] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1201] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1202] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1203] 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.

[1204] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1205] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1206] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1207] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1208] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1209] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1210] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1211] The following is further disclosed regarding the above embodiment.

[1212] (Claim 1)

[1213] means for obtaining a user's current location;

[1214] A means for referencing data on past incidents, accidents, and disaster risks based on the acquired current location;

[1215] means for analyzing the referenced data and calculating the degree of risk in the form of a score;

[1216] means for displaying the calculated risk score to a user;

[1217] A system including:

[1218] (Claim 2)

[1219] 2. The system of claim 1, further comprising means for obtaining data on past incidents, accidents, and disaster risks from a database.

[1220] (Claim 3)

[1221] 10. The system of claim 1, wherein the analyzing means includes means for analyzing the data using natural language processing.

[1222] (Claim 4)

[1223] 2. The system of claim 1, wherein the risk score ranges from 0 to 10.

[1224] (Claim 5)

[1225] 2. The system according to claim 1, further comprising means for acquiring the current location of the user using a GPS module.

[1226] "Example 1"

[1227] (Claim 1)

[1228] means for obtaining a user's current location;

[1229] a means for referencing past risk data based on the acquired current location;

[1230] means for analyzing the referenced data and calculating the degree of risk in the form of a score;

[1231] means for displaying the calculated risk score to a user;

[1232] A means for obtaining the current location using a GPS module;

[1233] A means for retrieving historical risk data from a database;

[1234] A method for analyzing data using chat generation AI,

[1235] A means for transmitting the acquired score to a user's terminal;

[1236] A system including:

[1237] (Claim 2)

[1238] 2. The system according to claim 1, wherein the chat generation AI further comprises means for receiving and analyzing a prompt sentence.

[1239] (Claim 3)

[1240] 2. The system of claim 1, wherein the user's terminal includes means for transmitting the relevant location information to a server.

[1241] "Application Example 1"

[1242] (Claim 1)

[1243] means for obtaining a user's current location;

[1244] A means for referencing data on past incidents, accidents, and disaster risks based on the acquired current location;

[1245] means for analyzing the referenced data and calculating the degree of risk in the form of a score;

[1246] means for displaying the calculated risk score to a user;

[1247] A system including:

[1248] (Claim 2)

[1249] 2. The system of claim 1, further comprising means for obtaining data on past incidents, accidents, and disaster risks from a database.

[1250] (Claim 3)

[1251] 10. The system of claim 1, wherein the analyzing means includes means for analyzing the data using natural language processing.

[1252] (Claim 4)

[1253] 2. The system according to claim 1, wherein the display means includes means for displaying in real time the risk score calculated based on the user's current location.

[1254] (Claim 5)

[1255] 2. The system of claim 1, wherein the means for calculating the risk score includes means for calculating the score using a generative AI model.

[1256] (Claim 6)

[1257] 10. The system of claim 1, wherein the means for obtaining the user's current location includes means for using a Global Positioning System (GPS) module.

[1258] (Claim 7)

[1259] 2. The system of claim 1, wherein the referencing means includes means for generating prompt sentences using natural language processing technology and obtaining past incident, accident, and disaster risk data.

[1260] "Example 2: Combining Emotion Engines"

[1261] (Claim 1)

[1262] means for obtaining a user's current location;

[1263] A means for referencing data on past incidents, accidents, and disaster risks based on the acquired current location;

[1264] means for analyzing the referenced data and calculating the degree of risk in the form of a score;

[1265] means for recognizing a user's emotion;

[1266] means for analyzing the recognized emotion data together with the reference data and adjusting a risk score;

[1267] means for displaying the calculated and adjusted risk score to a user;

[1268] A system including:

[1269] (Claim 2)

[1270] 2. The system of claim 1, further comprising means for obtaining data on past incidents, accidents, and disaster risks from a database.

[1271] (Claim 3)

[1272] 10. The system of claim 1, wherein the analyzing means includes means for analyzing the data using natural language processing.

[1273] "Application example 2 when combining emotion engines"

[1274] (Claim 1)

[1275] means for obtaining a user's current location;

[1276] A means for referencing data on past incidents, accidents, and disaster risks based on the acquired current location;

[1277] means for analyzing the referenced data and calculating the degree of risk in the form of a score;

[1278] means for displaying the calculated risk score to a user;

[1279] means for acquiring user emotion data and reflecting the data in the risk score;

[1280] A system including:

[1281] (Claim 2)

[1282] 10. The system of claim 1, further comprising means for retrieving data on past incidents, accidents, and disaster risks from a database.

[1283] (Claim 3)

[1284] 10. The system of claim 1, wherein the analyzing means includes means for analyzing the data using natural language processing. [Explanation of symbols]

[1285] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for obtaining a user's current location; A means for referencing data on past incidents, accidents, and disaster risks based on the acquired current location; means for analyzing the referenced data and calculating the degree of risk in the form of a score; means for displaying the calculated risk score to a user; A system including:

2. The system of claim 1 , further comprising means for obtaining the data on past incidents, accidents, and disaster risks from a database.

3. 2. The system of claim 1, wherein the analyzing means includes means for analyzing the data using natural language processing.

4. The system of claim 1 , wherein the risk score ranges from 0 to 10.

5. 2. The system according to claim 1, further comprising means for acquiring the current location of the user using a GPS module.

Images