system

Abstract

Provide a system. A data collection means; A means of obtaining data such as the current time of day, season, and weather, and A risk calculation means that uses a generative AI model that integrates the accident and incident information collected by the data collection means and the acquired data and analyzes them in real time; a means for converting the risk calculated by the risk calculation means into a numerical value and overlaying the numerical value on map information; A means for obtaining user location information; means for comparing the user's location information with the risk level and generating an alert when the user approaches a risk area; The system includes a means for notifying a user of the alert at a terminal.

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] Currently, it is not possible to grasp information about accidents and incidents in real time and provide users with appropriate warnings. In particular, users are unable to receive advance warnings when approaching dangerous locations, increasing the risk of being involved in an accident or incident. Furthermore, there is a lack of means to know when family members are in danger, making it difficult to take immediate action. This invention aims to solve these problems and provide an environment where vulnerable people, such as the elderly, children, and young women, can live safely. [Means for solving the problem]

[0005] The present invention provides a system including a data collection means for collecting accident and incident information, a means for acquiring data such as the current time of day, season, and weather, a risk calculation means that integrates the accident and incident information collected by the data collection means and the acquired data and uses a generative AI model to analyze it in real time, a means for quantifying the risk calculated by the risk calculation means and overlaying it on map information, a means for acquiring user location information, a means for comparing the user location information with the risk and generating an alert when the user approaches a dangerous area, and a means for notifying the user of the alert to their terminal.

[0006] This system integrates and analyzes accident and incident information in real time, and can immediately issue an alert when the user approaches a dangerous location. Furthermore, it has a function that can be set to notify alerts on family members' devices as well, allowing for a quick response and increasing the user's safety.

[0007] "Data collection means" refers to systems or devices that collect information about accidents and incidents in real time and manage it centrally.

[0008] "Means of acquiring data on the current time, season, weather, etc." refers to systems and devices for collecting and acquiring the current time, season, and weather conditions in real time.

[0009] "Danger calculation means" refers to a system or device that calculates the danger level using a generative AI model based on collected accident and incident information and acquired data such as the current time of day, season, and weather.

[0010] "Means for overlaying map information" refers to a system or device for quantifying the calculated risk level and overlaying it on a map.

[0011] "Means for obtaining user location information" refers to a system or device for obtaining the user's current location in real time.

[0012] "Means for generating an alert" means a system or device that generates an appropriate alert to warn a user when they are approaching a hazardous area.

[0013] "Means for notifying the user of the alert" refers to a system or device that notifies the user of the generated alert on their device, such as a smartphone or tablet.

[0014] "Public API" refers to an application programming interface provided by public institutions such as the police, fire department, and meteorological agency. [Brief explanation of the drawings]

[0015] [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

[0016] 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.

[0017] First, the terms used in the following description will be explained.

[0018] 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).

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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."

[0036] This invention is a system that collects accident and incident information in real time and issues appropriate warnings to users based on that information. This system functions in cooperation with a server, terminals, and users.

[0037] The server first obtains accident and incident information from public APIs such as those of the police, fire department, and meteorological agency using data collection methods. It also separately obtains weather data, seasons, time of day, and other information. This information is stored in an integrated database and analyzed in real time by a generative AI model. The AI ​​model considers factors such as past accident and incident data, the current time of day, season, and weather, and quantifies the risk level of each location. The calculated risk level is then quantified and overlaid on map information. The risk map is updated in real time and linked to the user's location information.

[0038] The device periodically obtains the user's current GPS location information and sends it to the server. When the server receives the user's location information, it compares it with a risk map. If it determines that the user is approaching a dangerous area, it generates an alert. This alert includes the type of danger, the risk level, recommended actions, and more. The generated alert is immediately sent to the user's device. Furthermore, depending on the settings, alerts may also be sent to family members' devices.

[0039] Users can check the danger information for the location based on the notification on their device. The alert contains detailed information about the dangerous area, allowing users to take appropriate action. For example, if they are approaching a dangerous area on their way to work, they can check the alert and choose an alternative route. Similarly, if a parent receives an alert that their child is approaching a dangerous area while playing outside, they can immediately contact their child or guide them to a safe location.

[0040] Example 1: Use on your commute route

[0041] A user opens the app on their way to work. The device obtains GPS location information and sends it to the server. The server calculates a predicted risk level based on the current time of day (morning commute), weather (rain), and information on accidents and incidents around the commute route, and displays it on a map. If the user approaches a dangerous area on their commute route (for example, an area where many traffic accidents have occurred in the past), an alert is generated and sent to the device. The device receives the alert and notifies the user, "There is a dangerous area on your commute route. Please be careful." The user then pays attention and either avoids the area or passes through it safely.

[0042] Example 2: Child monitoring function

[0043] When the child is playing outside, the user (parent) opens the app and turns on the monitoring function. The device (child's device) obtains GPS location information and sends it to the server. The server predicts the level of danger based on the latest incident information and weather conditions in the area. The server quantifies the level of danger in real time based on the evening hours when traffic accidents are most common in the child's area. If the child approaches a dangerous area, an alert is generated and a notification is also sent to the parent's device. The device notifies the parent, "Your child is approaching a dangerous area. Please check." The user (parent) can contact the child or guide them to a safe location.

[0044] This system allows users to receive real-time warnings when they approach dangerous areas, making it possible to prevent accidents and incidents.In addition, by simultaneously notifying family members of the alert, it encourages quick response and further increases the user's safety.

[0045] The processing flow will be explained below.

[0046] Step 1:

[0047] The server accesses public APIs from the police, fire department, meteorological agency, etc., to obtain accident and incident information and weather data in real time.

[0048] Step 2:

[0049] The server centralizes the acquired accident and incident information and weather data and stores them in an integrated database.

[0050] Step 3:

[0051] The server extracts the latest accident and incident data and weather data from the integrated database and inputs this into the generative AI model.

[0052] Step 4:

[0053] The server uses a generative AI model to calculate the risk level for each location in real time, taking into account factors such as the frequency of accidents and incidents, their severity, time of day, season, and weather.

[0054] Step 5:

[0055] The server quantifies the calculated risk and overlays it on map information, continuously updating the generated risk map in real time.

[0056] Step 6:

[0057] Your device periodically retrieves your GPS location, which by default is every minute.

[0058] Step 7:

[0059] The terminal transmits the acquired location information to the server.

[0060] Step 8:

[0061] The server receives the user's location information and compares it with a real-time risk map.

[0062] Step 9:

[0063] The server generates an alert when the user approaches a dangerous area, including the type of danger, the numerical danger level, and recommended actions.

[0064] Step 10:

[0065] The server sends the generated alert to the user's device, and depending on the settings, it can also notify family members' devices at the same time.

[0066] Step 11:

[0067] The device processes the alert received from the server and notifies the user of the alert by displaying it on the screen or by audio notification.

[0068] Step 12:

[0069] Users can check their current location and danger information based on notifications from their device and take recommended actions, such as avoiding dangerous areas or evacuating to a safe location.

[0070] Example 1

[0071] 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."

[0072] Conventional systems for collecting accident and incident information and notifying users have difficulty calculating the risk level in real time, making it difficult to issue prompt warnings. Furthermore, they lack the functionality to simultaneously notify alerts to users and their families, resulting in inadequate emergency response. To solve these problems, the present invention provides a system for collecting data from public APIs and analyzing risk levels in real time, thereby quickly issuing warnings to users and their families.

[0073] 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.

[0074] In this invention, the server includes a data collection means, a means for acquiring data such as the current time zone, season, and weather, a risk calculation means using a generative AI model that integrates the accident and incident information collected by the data collection means and the acquired data and analyzes them in real time, a means for quantifying the risk calculated by the risk calculation means and overlaying it on map information, a means for acquiring user location information, a means for comparing the user location information with the risk and generating an alert when the user approaches a dangerous area, a means for notifying the user's device of the alert, and a means for notifying the device of related family members of the alert by the notification means, thereby enabling the user and their family members to obtain risk information in real time and take prompt action.

[0075] "Data collection means" refers to means for collecting data from multiple sources, including accident and incident information.

[0076] The "risk calculation means" is a means for integrating collected data and calculating risk in real time using a generative AI model.

[0077] The "means for quantifying the risk level and overlaying it on map information" is a means for expressing the calculated risk level in a numerical format and overlaying that information on a map.

[0078] "Means for obtaining user location information" refers to means for obtaining the user's current location from the terminal.

[0079] "Means for generating an alert" refers to a means for issuing a warning when a user approaches a dangerous area.

[0080] The "notification means" is a means for transmitting the generated alert to the terminals of the user and related family members.

[0081] A "public API" is an application programming interface provided by public institutions such as the police, fire department, and meteorological agency.

[0082] The present invention is a system that aims to prevent accidents and incidents by providing real-time warnings when users approach dangerous locations. This system functions in cooperation with a server, terminals, and users.

[0083] server

[0084] The server first uses data collection tools (e.g., Python library requests, BeautifulSoup, etc.) to obtain accident and incident information from public APIs (e.g., NASA API, OpenWeatherMap API) of the police, fire department, meteorological agency, etc. It also separately obtains weather data, seasons, time periods, etc. All obtained information is stored in an integrated database (e.g., MySQL (registered trademark), PostgreSQL).

[0085] The stored data is then analyzed in real time using a generative AI model (e.g., TENSORFLOW®, PyTorch). The model calculates the risk level for each location by taking into account factors such as past accident and incident data, the current time of day, season, and weather. This risk level is then stored in a database and overlaid on map information (e.g., Google® Maps API, Mapbox). This risk map is updated in real time, and as new information is added, it is reflected on the map provided to users.

[0086] Terminal

[0087] The device periodically obtains the user's current location using the smartphone's built-in GPS module. This location information is updated at regular intervals (e.g., every 5 minutes) and sent to the server. The server compares the received location information with the current risk map to determine whether the user is approaching a dangerous area.

[0088] User

[0089] Users can check the danger information for the location based on the notification on their device. The alert contains detailed information about the dangerous area, allowing users to take appropriate action. For example, if they are approaching a dangerous area on their way to work, they can check the alert and choose an alternative route. Similarly, if a parent receives an alert that their child is approaching a dangerous area while playing outside, they can immediately contact their child or guide them to a safe location.

[0090] Examples:

[0091] Use on your commute route

[0092] A user opens the app on their way to work. The device obtains GPS location information and sends it to the server. The server calculates a predicted risk level based on the current time of day (morning commute), weather (rain), and information on accidents and incidents around the commute route, and displays it on a map. If the user approaches a dangerous area on their commute route (for example, an area where many traffic accidents have occurred in the past), an alert is generated and sent to the device. The device receives the alert and notifies the user, "There is a dangerous area on your commute route. Please be careful." The user then pays attention and either avoids the area or passes through it safely.

[0093] Child monitoring function

[0094] When the child is playing outside, the user (parent) opens the app and turns on the monitoring function. The device (child's device) obtains GPS location information and sends it to the server. The server predicts the level of danger based on the latest incident information and weather conditions in the area. The server quantifies the level of danger in real time based on the evening hours when traffic accidents are most common in the child's area. If the child approaches a dangerous area, an alert is generated and a notification is also sent to the parent's device. The device notifies the parent, "Your child is approaching a dangerous area. Please check." The user (parent) can contact the child or guide them to a safe location.

[0095] Prompt Sentence Examples

[0096] Use on your commute route

[0097] "It's morning commute time and you're heading to your destination in the rain. Please check to see if there are any dangerous areas along your route."

[0098] Child monitoring function

[0099] "My child is playing outside. I want to know the danger areas based on the latest incidents in the area and current weather conditions."

[0100] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0101] Step 1:

[0102] The server uses data collection tools to collect accident and incident information from public APIs (e.g., APIs of the police, fire department, and meteorological agency). The input is raw data from the API, which is parsed (analyzed) into required information (e.g., location, time, and type of accident). The output is the parsed accident information.

[0103] What it does: The server uses Python's requests library to call the OpenWeatherMap API to get current weather data, then uses BeautifulSoup to parse the data and extract the information it needs.

[0104] Step 2:

[0105] The server obtains each piece of information using a means to obtain data such as the current time, season, weather, etc. The input is raw data related to the current time, season, and weather, and the output is an organized form of this data.

[0106] Specific operation: The server obtains the current time zone from the system time, calls the Japan Meteorological Agency's API to obtain the latest weather data, and stores this information in an integrated database.

[0107] Step 3:

[0108] The server uses a generative AI model to analyze the acquired accident information, time of day, season, and weather data in real time to calculate the risk level for each location. The input is the integrated data, and the output is a quantified data of the risk level for each location.

[0109] Specific operation: The server uses a TensorFlow model to input past accident data and current weather data and quantify the risk level at each location.

[0110] Step 4:

[0111] The server overlays the calculated risk level on map information. The input is the quantified risk level data and map data, and the output is a map that visually displays the risk level.

[0112] What it does: The server uses the Google Maps API to highlight dangerous areas in red and updates the map in real time.

[0113] Step 5:

[0114] The terminal periodically obtains the user's location information using the smartphone's built-in GPS module. The input is the GPS location information, and the output is the location data sent to the server.

[0115] Specific operation: The device obtains latitude and longitude using the smartphone's GPS module and sends this to the server at regular intervals (e.g., every 5 minutes).

[0116] Step 6:

[0117] The server compares the received user location information with the risk map to determine whether the user is approaching a dangerous area. The input is the user location information and the risk map, and the output is the approach determination result.

[0118] Specific operation: The server retrieves the user's location information and danger map from the database and compares them to determine whether the user is in a danger zone.

[0119] Step 7:

[0120] If the server determines that the user is approaching a dangerous area, it generates an alert and notifies the user's device. The input is the approach judgment result, and the output is the generated alert and notification.

[0121] Specific operation: The server generates an alert stating, "You are approaching a dangerous area. Please check the app for details," and sends it as a push notification to the user's smartphone.

[0122] Step 8:

[0123] The terminal notifies the user of the alerts received from the server. The input is the alert from the server, and the output is the notification to the user.

[0124] What happens: The device receives a push notification and displays a message to the user saying, "There is a dangerous area on your commute route. Please be careful."

[0125] (Application example 1)

[0126] 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."

[0127] To ensure the safety of automated machinery and workers in factories, it is important to collect, analyze, and notify accident and abnormality information in real time. However, conventional systems have difficulty in providing comprehensive safety management in real time, and accidents are likely to occur when workers or machines approach dangerous areas. To solve this problem, the present invention aims to provide a system that utilizes a generative AI model to analyze accident and incident information in factories in real time, calculate the level of danger, and issue appropriate warnings to automated machinery and workers.

[0128] 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.

[0129] In this invention, the server includes a data acquisition means, a means for acquiring data such as the current time of day, season, and weather, a risk calculation means using a generative AI model that integrates the accident and incident information collected by the data acquisition means and the acquired data and analyzes it in real time, a means for quantifying the risk calculated by the risk calculation means and overlaying it on map information, a means for acquiring user location information, a means for comparing the user's location information with the risk and generating an alert when the user approaches a dangerous area, a means for notifying the user's terminal of the alert, a means for periodically acquiring location information of automatic machines and workers in the factory, analyzing it in coordination with the accident and incident information in the factory collected by the data acquisition means, calculating the risk and overlaying it on map information, and a means for generating an alert when the dangerous area is approached and notifying the terminals of machines and workers in the factory. This enables real-time safety management of accidents and abnormalities in the factory.

[0130] "Data acquisition means" refers to the means of collecting accident and abnormality information from automated machinery, sensors, cameras, GPS modules, etc. within the factory.

[0131] "Means for obtaining data such as the current time of day, season, and weather" refers to means for obtaining environmental information such as the current time of day, season, and weather using external APIs or databases.

[0132] A "generative AI model" is an artificial intelligence model that analyzes collected data in real time and compares it with past data to calculate the level of risk.

[0133] The "risk calculation means" is a means of quantifying the risk of accidents or abnormalities at each location using a generative AI model.

[0134] The "means for overlaying on map information" is a means for displaying the calculated risk level overlaid on map information.

[0135] "Means for obtaining user location information" refers to means for obtaining the current location of a user or an automated machine using a GPS module or the like.

[0136] The "means for generating an alert" is a means for generating a warning when approaching a dangerous area based on the risk calculation result and the user's location information.

[0137] "Means for notifying the user's device" refers to the means for notifying the generated alert to the user's device, such as a smartphone or tablet.

[0138] The "means for periodically acquiring location information of automated machines and workers in a factory" refers to a means for acquiring location information of various machines and workers in a factory at regular intervals and transmitting it to a server.

[0139] "Means for analyzing in coordination with information on accidents and incidents within factories" refers to a means for analyzing information on accidents and abnormalities that occur within factories in combination with the location information of automated machines and workers.

[0140] The present invention aims to provide a system for managing the safety of automated machinery and workers in a factory by collecting and analyzing information on accidents and abnormalities in real time and issuing appropriate warnings. Specific embodiments for realizing this system are described below.

[0141] Data Acquisition Method

[0142] The server collects information about accidents and abnormalities from various sensors, cameras, and GPS modules within the factory. This information is collected using a sensor network and IoT devices. For example, temperature sensors, vibration sensors, and cameras are used to detect chemical leaks and machine malfunctions. This data is then stored in an integrated database on the server side.

[0143] Environmental data acquisition method

[0144] The server utilizes external APIs and internal databases to obtain environmental information such as the current time of day, season, and weather. This includes data obtained through the Japan Meteorological Agency and other public APIs. Weather information and seasonal variations are also collected, as they may affect specific hazard levels.

[0145] Risk calculation method

[0146] The server analyzes the collected data in real time using a generative AI model and compares it with past data to calculate the risk level. For example, it uses past accident data and current environmental data as input to generate a risk score for each location. This is done using machine learning frameworks such as TensorFlow and PyTorch.

[0147] Map information overlay method

[0148] The calculated risk level is overlaid on map information by the server. This map information is based on the layout of the factory and is updated in real time. Dangerous areas are color-coded to make them visually clear.

[0149] User location information acquisition method

[0150] Each terminal (automated machine or worker's mobile device) periodically acquires its current location using a GPS module and sends it to the server, allowing the server to constantly track the location of the automated machine or worker.

[0151] Alert generation method

[0152] The server compares the user's location information with the risk level and generates an alert if the user is approaching a dangerous area. The alert includes the type of danger, the risk level, and recommended actions.

[0153] Alert notification method

[0154] The generated alerts are instantly sent to automated machines and workers in the factory, such as smartphones, tablets, and even robot control systems, using push notification services such as Firebase Cloud Messaging.

[0155] Examples of concrete examples and prompts

[0156] Example 1: A chemical leak is detected in a factory and workers are approaching the area.

[0157] Prompt: "You are approaching a chemical spill area. Please leave the area immediately."

[0158] Example 2: When a worker is approaching the forklift's driving area.

[0159] Prompt: "You are approaching a forklift area. Please be careful."

[0160] This system will strengthen safety management within the factory and enable real-time response to accidents and abnormalities.

[0161] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0162] Step 1: Collect information through data acquisition methods

[0163] The server collects data on accidents and abnormalities from sensors, cameras, and GPS modules within the factory. This includes collecting environmental data such as temperature and vibration through the sensor's API and detecting abnormalities through camera video analysis.

[0164] Input: Raw data from sensors, cameras, and GPS modules (temperature, vibration, video, location information)

[0165] Output: Collected accident and abnormality data

[0166] Step 2: Collect information through environmental data acquisition methods

[0167] The server retrieves environmental data such as the current time zone, season, and weather from external APIs and databases. This is a process of retrieving weather and time data using public APIs.

[0168] Input: Environment data from public API

[0169] Output: Current time zone, season, weather, etc.

[0170] Step 3: Data integration and analysis

[0171] The server stores the data acquired in steps 1 and 2 in an integrated database and analyzes it in real time using a generative AI model, which predicts the risk level based on past and current data.

[0172] Input: Historical data in the integrated database and current data obtained

[0173] Output: Risk score (numerical value) for each location

[0174] Step 4: Overlaying risk information onto the map

[0175] The server overlays the calculated risk level on the map information of the factory, which displays dangerous areas on the map in different colors.

[0176] Input: Risk score, factory map information

[0177] Output: Map with risk overlay

[0178] Step 5: Get the user's location

[0179] The terminal (automated machine or worker's portable device) periodically obtains its current location using a GPS module and transmits it to the server.

[0180] Input: Location information from the GPS module

[0181] Output: Current location data of the user

[0182] Step 6: Alert Generation

[0183] The server compares the user's current location with the risk level and generates an alert if the user is approaching a risk area, including the type of risk, a risk score, and recommended actions.

[0184] Input: User's current location data, map with risk level overlay

[0185] Output: Warning message (alert)

[0186] Step 7: Alert Notification

[0187] The generated alerts are immediately sent to the user's device using a push notification service, specifically, Firebase Cloud Messaging, which sends notifications to smartphones and tablets.

[0188] Input: Warning message (alert)

[0189] Output: Notification to user device

[0190] The above processing steps enable real-time safety management for accidents and abnormalities within a factory. As a concrete example, the following prompt sentence is used:

[0191] Example 1: A chemical leak is detected in a factory and workers are approaching the area.

[0192] "Approaching a chemical spill area. Leave the area immediately."

[0193] Example 2: When a worker is approaching the forklift's driving area.

[0194] "You are approaching a forklift driving area. Use caution."

[0195] 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.

[0196] This invention is a system that collects accident and incident information in real time and uses that information to provide appropriate warnings to users. This system functions through the mutual cooperation of a server, terminals, users, and an emotion engine.

[0197] Basic System Configuration

[0198] The server first obtains accident and incident information from public APIs such as those of the police, fire department, and meteorological agency using data collection methods. It also separately obtains weather data, seasons, time of day, and other information. This information is stored in an integrated database and analyzed in real time by a generative AI model. The AI ​​model considers factors such as past accident and incident data, the current time of day, season, and weather, and quantifies the risk level of each location. The calculated risk level is then quantified and overlaid on map information. The risk map is updated in real time and linked to the user's location information.

[0199] The device periodically obtains the user's current GPS location information and sends it to the server. When the server receives the user's location information, it compares it with a risk map. If it determines that the user is approaching a dangerous area, it generates an alert. This alert includes the type of danger, the risk level, recommended actions, and more. The generated alert is immediately sent to the user's device. Furthermore, depending on the settings, alerts may also be sent to family members' devices.

[0200] Emotion engine integration

[0201] The emotion engine recognizes the user's emotional state and adjusts the alert content and notification method based on that. It uses the device's built-in camera and microphone to analyze the user's facial expressions and tone of voice. The analysis results are sent to the server and fed back to the risk calculation means.

[0202] The server recalculates the risk level based on the user's emotional state received from the emotion engine and adjusts the content and notification method of the alert as necessary. For example, if the user is nervous, the server will send an alert earlier. If the user is relaxed, the server will adjust the frequency and intensity of notifications.

[0203] Specific examples

[0204] Example 1: Use on your commute route

[0205] A user opens the app on their way to work. The device obtains GPS location information and sends it to the server. The server calculates a predicted risk level based on the current time of day (morning commute), weather (rain), and information on accidents and incidents around the commute route, and displays it on a map. If the user approaches a dangerous area on their commute route (for example, an area where many traffic accidents have occurred in the past), an alert is generated and sent to the device.

[0206] The device also uses a camera and microphone to analyze the user's emotional state and sends the data to the server. The server analyzes the emotional data and, if the user is nervous, highlights the alert and notifies the user of the appropriate recommended action. When the device receives the alert, it notifies the user, "There is a dangerous area on your commute route. Please be careful." The user can then take care and either avoid the area or pass through it safely.

[0207] Example 2: Child monitoring function

[0208] When a user (parent) is playing outside, the user opens the app and turns on the monitoring function. The device (child's device) obtains GPS location information and sends it to the server. The server predicts the level of danger based on the latest incident information and weather conditions in the area. The server quantifies the level of danger in real time based on the evening hours when traffic accidents are most common in the child's area. If the child approaches a dangerous area, an alert is generated and a notification is also sent to the parent's device. The user (parent) can use the device's camera and microphone to send their emotional state to the server and receive recommended actions to take to respond more appropriately.

[0209] This system allows users to receive real-time warnings when approaching dangerous locations, preventing accidents and incidents before they occur. In addition, the introduction of an emotion engine enables more personalized alert notifications tailored to the user's emotional state, further enhancing user safety.

[0210] The processing flow will be explained below.

[0211] Step 1:

[0212] The server accesses public APIs from the police, fire department, meteorological agency, etc., to obtain real-time accident and incident information and weather data.

[0213] Step 2:

[0214] The server centralizes the acquired accident and incident information and weather data and stores them in an integrated database.

[0215] Step 3:

[0216] The server extracts the latest accident and incident data and weather data from the integrated database and inputs it into the generative AI model.

[0217] Step 4:

[0218] The server uses a generative AI model to calculate the risk level for each location in real time, taking into account factors such as the frequency of accidents and incidents, their severity, time of day, season, and weather.

[0219] Step 5:

[0220] The server quantifies the calculated risk and overlays it on map information, continuously updating the generated risk map in real time.

[0221] Step 6:

[0222] Your device periodically retrieves your GPS location, which by default is every minute.

[0223] Step 7:

[0224] The terminal transmits the acquired location information to the server.

[0225] Step 8:

[0226] The server receives the user's location information and compares it with a real-time risk map.

[0227] Step 9:

[0228] The server generates an alert when the user approaches a dangerous area, including the type of danger, the numerical danger level, and recommended actions.

[0229] Step 10:

[0230] The server sends the generated alert to the user's device, and depending on the settings, it can also notify family members' devices at the same time.

[0231] Step 11:

[0232] The device processes the alert received from the server and notifies the user of the alert by displaying it on the screen or by audio notification.

[0233] Step 12:

[0234] The device uses a camera and microphone to analyze the user's facial expressions and tone of voice, and sends the analysis data to a server.

[0235] Step 13:

[0236] The server analyzes the user's emotional state received from the emotion engine.

[0237] Step 14:

[0238] The server recalculates the risk level and adjusts the alert content and notification method based on the user's emotional state. For example, if the user is nervous, it generates an earlier and more emphasized alert.

[0239] Step 15:

[0240] The server then sends the adjusted alert back to the user's device.

[0241] Step 16:

[0242] The device will notify the user of the received alert in an appropriate manner.

[0243] Step 17:

[0244] Users can check their current location and danger information based on notifications on their device and take recommended actions, such as avoiding dangerous areas or evacuating to a safe location.

[0245] Example 2

[0246] 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."

[0247] Conventional systems for collecting information on accidents and incidents have difficulty predicting risk in real time, making it impossible to immediately ensure the safety of users. Furthermore, they only provided a uniform notification method without taking into account the user's emotional state, making it impossible to provide appropriate warnings according to their state of tension or relaxation. Furthermore, they lacked a function to notify the user's family members, leaving a need for improved safety.

[0248] 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.

[0249] In this invention, the server includes a data acquisition unit, a unit for acquiring data such as the current time of day, season, and weather conditions, a risk assessment unit using an artificial intelligence model that integrates the accident and incident information collected by the data acquisition unit and the acquired data and analyzes them in real time, a unit for quantifying the risk calculated by the risk assessment unit and overlaying it on map information, a unit for acquiring device location information, a unit for comparing the device location information with the risk level and generating a warning when the device approaches a dangerous area, a unit for notifying the device of the warning, and a unit for recognizing the user's emotional state using emotion analysis means installed in the device and adjusting the content and notification method of the warning. This allows the user to receive an immediate warning when facing danger and enables personalized notifications based on the user's emotional state. Safety can also be improved by notifying the user's family members.

[0250] "Data acquisition means" refers to the means for collecting various data, including accident and incident information.

[0251] A "generative AI model" is an artificial intelligence model that analyzes integrated data in real time and assesses the level of risk.

[0252] The "risk assessment means" is a means of analyzing collected data using a generative AI model and quantifying the risk level at each location.

[0253] The "means for overlaying on map information" is a means for overlaying the calculated risk level on map data.

[0254] "Means for obtaining location information" refers to means for periodically obtaining location information from the user's terminal.

[0255] The "means for generating a warning" is a means for generating a warning to notify the user of the type of danger and its details when the user's terminal approaches a dangerous area.

[0256] The "means for notifying a warning" is a means for sending the generated warning to the user's terminal.

[0257] An "emotion analysis means" is a means for analyzing a user's facial expression and tone of voice to recognize their emotional state.

[0258] A "public API" is an API provided by public organizations such as police, fire departments, and meteorological agencies, and is a data interface used to obtain information on accidents and incidents, weather data, etc.

[0259] "Terminal" refers to a mobile communication device carried by a user for sending and receiving location information and emotional state.

[0260] This invention is a system that collects accident and incident information in real time and uses that information to provide appropriate warnings to users. This system functions by linking together a server, terminals, users, and an emotion engine.

[0261] Basic System Configuration

[0262] The server first obtains accident and incident information from public APIs such as those of police, fire departments, and meteorological agencies using a data acquisition means. Next, it separately obtains weather data, seasons, time periods, and other information. This information is then stored in an integrated database. Specifically, cloud services (e.g., AWS (registered trademark) or Google Cloud Platform) are used. The collected data is stored in this integrated database, normalized, and prepared for analysis.

[0263] The server analyzes the information stored in the integrated database in real time using an artificial intelligence model (e.g., GPT-4 (registered trademark)). This model calculates the risk level for each location, taking into account factors such as past accident and incident data, the current time of day, season, and weather. The calculated risk level is quantified and overlaid on map information. The Google Maps API is used to depict the map information. The risk map is updated in real time to continually reflect the latest information.

[0264] The device periodically obtains the user's current GPS location information and sends it to a server. This is done using a mobile device such as a smartphone. The server compares the received location information with a risk map to determine whether the user is approaching a dangerous area. If it determines that the user is approaching a dangerous area, the server generates a warning. This warning includes the type of danger, the risk level, recommended actions, etc. The generated warning is immediately sent to the user's device. This notification method is push notification.

[0265] The device is also equipped with an emotion analysis function. It uses the camera and microphone to analyze the user's facial expressions and tone of voice, and sends the results to a server using technologies such as OpenCV and Google Cloud Speech-to-Text. The server uses these analysis results to recognize the user's emotional state and adjust the content and notification method of the alert. For example, if the user is nervous, the alert will be emphasized and the notification will be sent earlier. Also, if the user is relaxed, the frequency and intensity of the alert will be adjusted.

[0266] Specific examples

[0267] Example 1: Use on your commute route

[0268] A user opens the app on their way to work. The device obtains their GPS location and sends it to the server. The server calculates a predicted risk level based on the current time of day (morning commute), weather (rain), and information on accidents and incidents around the commute route, and displays it on a map. If the user approaches a dangerous area on their commute route, a warning is generated and sent to the device. For example, the device could not only display a text message saying, "There is a dangerous area on your commute route. Please be careful," but also use vibration and audio notifications to further amplify the warning. Additionally, a prompt message like, "Please tell me how to notify me if I approach a dangerous area on my commute. It's morning commute time and the weather is rainy." could be used.

[0269] Example 2: Child monitoring function

[0270] When the user (parent) is playing outside, the user opens the app and turns on the monitoring function. The device (child's device) obtains GPS location information and sends it to the server. The server predicts the level of danger based on the latest incident information and weather conditions in the area. The server quantifies the level of danger in real time based on the evening hours when traffic accidents are most common in the child's area. If the child approaches a dangerous area, a warning is generated and a notification is also sent to the parent's device. The parent's device is displayed with the text "Your child is approaching an area with a high incidence of traffic accidents. Please contact us immediately and ensure their safety." Additionally, a prompt such as "How can I be notified if my child approaches a dangerous area? It is evening and the weather is clear" can also be used.

[0271] This system allows users to receive real-time warnings when approaching dangerous areas, preventing accidents and incidents before they occur. In addition, the introduction of an emotion engine enables more personalized warning notifications tailored to the user's emotional state, further enhancing user safety.

[0272] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0273] Step 1: Collect data

[0274] The server collects accident and incident information from public APIs such as police, fire departments, and meteorological agencies.

[0275] Input: Accident and incident information from public APIs, weather data, time of day, and seasonal data.

[0276] Specific operation: Periodically send GET requests to each public API and receive response data in JSON format. For example, access the weather API to get weather information.

[0277] Output: A dataset containing collected accident and incident information and weather data.

[0278] Step 2: Integrate the data

[0279] The server stores the collected data in an integrated database.

[0280] Input: Collected accident and incident information, weather data, time of day, and seasonal data.

[0281] Specific behavior: Normalizes the received data and stores it in a SQL database, for example, inserting JSON data into the appropriate table.

[0282] Output: Data stored in the consolidated database.

[0283] Step 3: Preprocessing the data

[0284] The server extracts the necessary data from the integrated database and converts it into a format suitable for analysis.

[0285] Input: Various data in the integrated database.

[0286] Specific operations: Data cleansing, removing outliers, and imputing missing data (e.g., imputing missing values ​​with the mean).

[0287] Output: The preprocessed dataset.

[0288] Step 4: Risk analysis

[0289] The server uses a generative AI model to analyze the pre-processed data in real time and calculate the risk level.

[0290] Input: Preprocessed accident and incident information, weather data, time of day, and season data.

[0291] Specific operation: Input data into a generative AI model to quantify the risk level of each location. For example, run a predictive model based on similar past data.

[0292] Output: A dataset quantifying the risk at each location.

[0293] Step 5: Generate a risk map

[0294] The server overlays the calculated risk level onto map information to visualize it.

[0295] Input: Quantified risk data, map information.

[0296] Specific operation: Uses Google Maps API to display danger levels on a map in different colors. For example, high-danger areas are displayed in red.

[0297] Output: Hazard map.

[0298] Step 6: Get GPS location

[0299] The device periodically obtains the user's current GPS location information and sends it to the server.

[0300] Input: Location information from the device's GPS module.

[0301] Specific operation: The device uses the smartphone's GPS sensor to obtain location information and sends the encrypted data to a server via HTTPS.

[0302] Output: The location data sent to the server.

[0303] Step 7: Matching location information with risk maps

[0304] The server compares the received location information with a risk map to determine whether the user is approaching a dangerous area.

[0305] Input: Received location information, risk map.

[0306] Specific operation: The location information is compared with a risk map to determine whether there are any high-risk areas within a specified distance.

[0307] Output: Information on approaching dangerous areas.

[0308] Step 8: Generate and notify alerts

[0309] If the server determines that the user is approaching a dangerous area, it immediately generates a warning and notifies the user's terminal.

[0310] Input: Information about approaching a dangerous area.

[0311] Specific operation: Create a warning message and send it to the device using push notification. For example, send a message saying "You are approaching a dangerous area. Be careful."

[0312] Output: The alert notification sent to the user's device.

[0313] Step 9: Capturing Emotional State

[0314] The device uses a camera and microphone to recognize the user's emotional state and transmits the results to a server.

[0315] Input: The user's facial expressions and tone of voice.

[0316] Specific operations: Facial expression recognition using OpenCV and voice analysis using Google Cloud Speech-to-Text.

[0317] Output: Emotion recognition data sent to the server.

[0318] Step 10: Adjusting Emotion-Based Alerts

[0319] The server adjusts the content of the warning and notification method based on the emotion recognition data it receives.

[0320] Input: Emotion recognition data, warning notification data.

[0321] Specific behavior: Adjust the intensity and timing of alerts depending on the user's emotional state. For example, send an earlier and more emphasized alert to a user who is nervous.

[0322] Output: Reconciled alert notification data.

[0323] (Application example 2)

[0324] 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."

[0325] Conventional accident and incident information collection systems have limitations in real-time risk calculation and alert functions, and from the user's perspective, they have had issues with not being able to provide notifications that are adequately tailored to the urgency or individual situation. Furthermore, no previous systems have been able to provide alerts that take into account the user's emotional state, which has led to a lack of effective means of improving safety.

[0326] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0327] In this invention, the server includes a data collection means, a means for acquiring data such as the current time of day, season, and weather, a risk calculation means using a generative AI model that integrates the accident and incident information collected by the data collection means and the acquired data and analyzes them in real time, a means for quantifying the risk calculated by the risk calculation means and overlaying it on map information, a means for acquiring user location information, a means for comparing the user location information with the risk level and generating an alert when the user approaches a dangerous area, an emotion analysis means for recognizing the user's emotional state using a camera and microphone mounted on the terminal and adjusting the alert content and notification method based on the emotional state, and a means for notifying the user of the alert to the user's terminal. This enables real-time and personalized alert notifications when the user approaches a dangerous area, thereby improving safety.

[0328] "Data collection means" refers to the means for obtaining accident and incident information and other related data.

[0329] "Means for acquiring data such as the current time zone, season, and weather" refers to means for collecting information about the time zone, season, and weather at that time.

[0330] A "means for calculating risk using a generative AI model" is a means for utilizing a generative AI model that is used to integrate collected data, analyze it in real time, and calculate risk.

[0331] "Means for overlaying on map information" refers to a means for converting the calculated risk level into a number and displaying it overlaid on a map.

[0332] "Means for obtaining user location information" refers to means for obtaining the user's current location.

[0333] "Means for generating an alert" means a means for automatically generating a warning when a user approaches a hazardous area.

[0334] The "emotion analysis means" is a means for recognizing the emotional state of the user using a camera or microphone installed in the terminal, and adjusting the alert content and notification method based on the emotional state.

[0335] "Means for notifying the user's device" refers to means for sending the generated alert to the user's mobile device or the like.

[0336] The present invention is a system that collects accident and incident information in real time and issues appropriate warnings to users based on that information, and functions in cooperation with a server, terminal, user, and emotion analysis engine.

[0337] The server uses data collection methods to obtain accident and incident information from public APIs such as those of the police, fire department, and meteorological agency. It also separately obtains weather data, seasons, time of day, and other information. This information is stored in an integrated database and analyzed in real time by a generative AI model. The AI ​​model considers factors such as past accident and incident data, the current time of day, season, and weather, and quantifies the risk level of each location. The calculated risk level is quantified and overlaid on map information. The risk map is updated in real time and linked to the user's location information.

[0338] The device periodically obtains the user's current GPS location information and sends it to the server. When the server receives the user's location information, it compares it with a risk map. If it determines that the user is approaching a dangerous area, it generates an alert. This alert includes the type of danger, the risk level, recommended actions, and more. The generated alert is immediately sent to the user's device. Furthermore, depending on the settings, alerts may also be sent to family members' devices.

[0339] The emotion analysis engine has the ability to recognize the user's emotional state and adjust the alert content and notification method based on that. It uses the device's built-in camera and microphone to analyze the user's facial expressions and tone of voice. The analysis results are sent to the server and fed back to the risk level calculation means. The server recalculates the risk level based on the user's emotional state received from the emotion analysis engine, and adjusts the alert content and notification method as necessary. For example, if the user is nervous, the alert will be sent earlier. Also, if the user is relaxed, the frequency and intensity of notifications will be adjusted.

[0340] Specific examples

[0341] Example 1: Use on your commute route

[0342] A user opens the app on their way to work. The device obtains their GPS location and sends it to the server. The server calculates a predicted risk level based on the current time of day (morning commute), weather (rain), and information on accidents and incidents along the commute route, and displays it on a map. If the user approaches a dangerous area on their commute route (for example, an area where many traffic accidents have occurred in the past), an alert is generated and sent to the device. The device also uses its camera and microphone to analyze the user's emotional state and sends that data to the server. The server analyzes the emotional data and, if the user is nervous, emphasizes the alert content and notifies the user of appropriate recommended actions. The device receives the alert and notifies the user, "There is a dangerous area on your commute route. Please be careful." The user pays attention and either avoids the area or passes through it safely.

[0343] Example 2: Child monitoring function

[0344] When a user (parent) is playing outside, the user opens the app and turns on the monitoring function. The device (child's device) obtains GPS location information and sends it to the server. The server predicts the level of danger based on the latest incident information and weather conditions in the area. The server quantifies the level of danger in real time based on the evening hours when traffic accidents are most common in the child's area. If the child approaches a dangerous area, an alert is generated and a notification is also sent to the parent's device. The user (parent) can use the device's camera and microphone to send their emotional state to the server and receive recommended actions to take to respond more appropriately.

[0345] Prompt Sentence Examples

[0346] Prompt to calculate risk based on user location:

[0347] text

[0348] Based on the data collected from the API used, analyze accident and incident information within 1 kilometer of the user's current location and calculate the risk level.

[0349] Alert generation prompts taking into account sentiment analysis results:

[0350] text

[0351] If the user's emotional state is tense, generate appropriate alerts with earlier and more detailed information about the alert.

[0352] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0353] Step 1:

[0354] The server obtains accident and incident information from public APIs using data collection methods. Specifically, it sends requests to the APIs of the police, fire department, meteorological agency, etc. to obtain the latest accident and incident information.

[0355] Input: API request

[0356] Output: Accident and incident information dataset

[0357] Step 2:

[0358] The server also acquires additional data such as the current time of day, season, and weather, which allows for analysis that takes into account a variety of factors along with accident and incident data.

[0359] Input: API request for time, season, and weather data

[0360] Output: Time, season, weather data

[0361] Step 3:

[0362] The server aggregates all the collected data and performs real-time analysis using a generative AI model, which calculates the risk level for each location.

[0363] Input: Accident / incident data, time, season, weather data

[0364] Output: Risk level at each location

[0365] Step 4:

[0366] The server quantifies the calculated risk and overlays it on map information, resulting in a user-friendly visualization of the risk.

[0367] Input: Risk level at each location

[0368] Output: Map information showing risk levels

[0369] Step 5:

[0370] The device periodically obtains the user's current GPS location and sends it to the server for subsequent analysis.

[0371] Input: GPS location

[0372] Output: Location information sent to the server

[0373] Step 6:

[0374] The server compares the user's location against the risk map and generates an alert when the user approaches a risk area, including the type of risk, a risk level number, and recommended actions.

[0375] Input: User location, risk map

[0376] Output: Alert

[0377] Step 7:

[0378] The device uses the built-in camera and microphone to analyze the user's emotional state and sends the data to a server, where an emotion analysis engine is used for emotion analysis.

[0379] Input: Camera video, microphone audio

[0380] Output: Emotion data

[0381] Step 8:

[0382] The server recalculates the risk level based on the emotion data received from the emotion analysis engine and adjusts the alert content and notification method, for example, emphasizing the alert content if the user is nervous.

[0383] Input: Emotion data, existing risk data

[0384] Output: Throttled alerts

[0385] Step 9:

[0386] The device will notify the user of the generated alert, and depending on the settings, the same alert will also be sent to family devices.

[0387] Input: alert

[0388] Output: Notification to user and family devices

[0389] 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.

[0390] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (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.

[0391] 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.

[0392] [Second embodiment]

[0393] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0394] 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.

[0395] 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).

[0396] 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.

[0397] 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.

[0398] 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).

[0399] 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.

[0400] 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.

[0401] 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.

[0402] 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.

[0403] 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.

[0404] 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."

[0405] This invention is a system that collects accident and incident information in real time and issues appropriate warnings to users based on that information. This system functions in cooperation with a server, terminals, and users.

[0406] The server first obtains accident and incident information from public APIs such as those of the police, fire department, and meteorological agency using data collection methods. It also separately obtains weather data, seasons, time of day, and other information. This information is stored in an integrated database and analyzed in real time by a generative AI model. The AI ​​model considers factors such as past accident and incident data, the current time of day, season, and weather, and quantifies the risk level of each location. The calculated risk level is then quantified and overlaid on map information. The risk map is updated in real time and linked to the user's location information.

[0407] The device periodically obtains the user's current GPS location information and sends it to the server. When the server receives the user's location information, it compares it with a risk map. If it determines that the user is approaching a dangerous area, it generates an alert. This alert includes the type of danger, the risk level, recommended actions, and more. The generated alert is immediately sent to the user's device. Furthermore, depending on the settings, alerts may also be sent to family members' devices.

[0408] Users can check the danger information for the location based on the notification on their device. The alert contains detailed information about the dangerous area, allowing users to take appropriate action. For example, if they are approaching a dangerous area on their way to work, they can check the alert and choose an alternative route. Similarly, if a parent receives an alert that their child is approaching a dangerous area while playing outside, they can immediately contact their child or guide them to a safe location.

[0409] Example 1: Use on your commute route

[0410] A user opens the app on their way to work. The device obtains GPS location information and sends it to the server. The server calculates a predicted risk level based on the current time of day (morning commute), weather (rain), and information on accidents and incidents around the commute route, and displays it on a map. If the user approaches a dangerous area on their commute route (for example, an area where many traffic accidents have occurred in the past), an alert is generated and sent to the device. The device receives the alert and notifies the user, "There is a dangerous area on your commute route. Please be careful." The user then pays attention and either avoids the area or passes through it safely.

[0411] Example 2: Child monitoring function

[0412] When the child is playing outside, the user (parent) opens the app and turns on the monitoring function. The device (child's device) obtains GPS location information and sends it to the server. The server predicts the level of danger based on the latest incident information and weather conditions in the area. The server quantifies the level of danger in real time based on the evening hours when traffic accidents are most common in the child's area. If the child approaches a dangerous area, an alert is generated and a notification is also sent to the parent's device. The device notifies the parent, "Your child is approaching a dangerous area. Please check." The user (parent) can contact the child or guide them to a safe location.

[0413] This system allows users to receive real-time warnings when they approach dangerous areas, making it possible to prevent accidents and incidents.In addition, by simultaneously notifying family members of the alert, it encourages quick response and further increases the user's safety.

[0414] The processing flow will be explained below.

[0415] Step 1:

[0416] The server accesses public APIs from the police, fire department, meteorological agency, etc., to obtain accident and incident information and weather data in real time.

[0417] Step 2:

[0418] The server centralizes the acquired accident and incident information and weather data and stores them in an integrated database.

[0419] Step 3:

[0420] The server extracts the latest accident and incident data and weather data from the integrated database and inputs this into the generative AI model.

[0421] Step 4:

[0422] The server uses a generative AI model to calculate the risk level for each location in real time, taking into account factors such as the frequency of accidents and incidents, their severity, time of day, season, and weather.

[0423] Step 5:

[0424] The server quantifies the calculated risk and overlays it on map information, continuously updating the generated risk map in real time.

[0425] Step 6:

[0426] Your device periodically retrieves your GPS location, which by default is every minute.

[0427] Step 7:

[0428] The terminal transmits the acquired location information to the server.

[0429] Step 8:

[0430] The server receives the user's location information and compares it with a real-time risk map.

[0431] Step 9:

[0432] The server generates an alert when the user approaches a dangerous area, including the type of danger, the numerical danger level, and recommended actions.

[0433] Step 10:

[0434] The server sends the generated alert to the user's device, and depending on the settings, it can also notify family members' devices at the same time.

[0435] Step 11:

[0436] The device processes the alert received from the server and notifies the user of the alert by displaying it on the screen or by audio notification.

[0437] Step 12:

[0438] Users can check their current location and danger information based on notifications from their device and take recommended actions, such as avoiding dangerous areas or evacuating to a safe location.

[0439] Example 1

[0440] 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."

[0441] Conventional systems for collecting accident and incident information and notifying users have difficulty calculating the risk level in real time, making it difficult to issue prompt warnings. Furthermore, they lack the functionality to simultaneously notify alerts to users and their families, resulting in inadequate emergency response. To solve these problems, the present invention provides a system for collecting data from public APIs and analyzing risk levels in real time, thereby quickly issuing warnings to users and their families.

[0442] 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.

[0443] In this invention, the server includes a data collection means, a means for acquiring data such as the current time zone, season, and weather, a risk calculation means using a generative AI model that integrates the accident and incident information collected by the data collection means and the acquired data and analyzes them in real time, a means for quantifying the risk calculated by the risk calculation means and overlaying it on map information, a means for acquiring user location information, a means for comparing the user location information with the risk and generating an alert when the user approaches a dangerous area, a means for notifying the user's device of the alert, and a means for notifying the device of related family members of the alert by the notification means, thereby enabling the user and their family members to obtain risk information in real time and take prompt action.

[0444] "Data collection means" refers to means for collecting data from multiple sources, including accident and incident information.

[0445] The "risk calculation means" is a means for integrating collected data and calculating risk in real time using a generative AI model.

[0446] The "means for quantifying the risk level and overlaying it on map information" is a means for expressing the calculated risk level in a numerical format and overlaying that information on a map.

[0447] "Means for obtaining user location information" refers to means for obtaining the user's current location from the terminal.

[0448] "Means for generating an alert" refers to a means for issuing a warning when a user approaches a dangerous area.

[0449] The "notification means" is a means for transmitting the generated alert to the terminals of the user and related family members.

[0450] A "public API" is an application programming interface provided by public institutions such as the police, fire department, and meteorological agency.

[0451] The present invention is a system that aims to prevent accidents and incidents by providing real-time warnings when users approach dangerous locations. This system functions in cooperation with a server, terminals, and users.

[0452] server

[0453] The server first uses data collection tools (e.g., Python library requests, BeautifulSoup, etc.) to obtain accident and incident information from public APIs (e.g., NASA API, OpenWeatherMap API) of the police, fire department, meteorological agency, etc. It also separately obtains weather data, seasons, time periods, etc. All obtained information is stored in an integrated database (e.g., MySQL, PostgreSQL).

[0454] The stored data is then analyzed in real time using a generative AI model (e.g., TensorFlow, PyTorch). The model calculates the risk level for each location, taking into account factors such as past accident and incident data, the current time of day, season, and weather. This risk level is then stored in a database and overlaid on map information (e.g., Google Maps API, Mapbox). This risk map is updated in real time, and as new information is added, it is reflected on the map provided to users.

[0455] Terminal

[0456] The device periodically obtains the user's current location using the smartphone's built-in GPS module. This location information is updated at regular intervals (e.g., every 5 minutes) and sent to the server. The server compares the received location information with the current risk map to determine whether the user is approaching a dangerous area.

[0457] User

[0458] Users can check the danger information for the location based on the notification on their device. The alert contains detailed information about the dangerous area, allowing users to take appropriate action. For example, if they are approaching a dangerous area on their way to work, they can check the alert and choose an alternative route. Similarly, if a parent receives an alert that their child is approaching a dangerous area while playing outside, they can immediately contact their child or guide them to a safe location.

[0459] Examples:

[0460] Use on your commute route

[0461] A user opens the app on their way to work. The device obtains GPS location information and sends it to the server. The server calculates a predicted risk level based on the current time of day (morning commute), weather (rain), and information on accidents and incidents around the commute route, and displays it on a map. If the user approaches a dangerous area on their commute route (for example, an area where many traffic accidents have occurred in the past), an alert is generated and sent to the device. The device receives the alert and notifies the user, "There is a dangerous area on your commute route. Please be careful." The user then pays attention and either avoids the area or passes through it safely.

[0462] Child monitoring function

[0463] When the child is playing outside, the user (parent) opens the app and turns on the monitoring function. The device (child's device) obtains GPS location information and sends it to the server. The server predicts the level of danger based on the latest incident information and weather conditions in the area. The server quantifies the level of danger in real time based on the evening hours when traffic accidents are most common in the child's area. If the child approaches a dangerous area, an alert is generated and a notification is also sent to the parent's device. The device notifies the parent, "Your child is approaching a dangerous area. Please check." The user (parent) can contact the child or guide them to a safe location.

[0464] Prompt Sentence Examples

[0465] Use on your commute route

[0466] "It's morning commute time and you're heading to your destination in the rain. Please check to see if there are any dangerous areas along your route."

[0467] Child monitoring function

[0468] "My child is playing outside. I want to know the danger areas based on the latest incidents in the area and current weather conditions."

[0469] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0470] Step 1:

[0471] The server uses data collection tools to collect accident and incident information from public APIs (e.g., APIs of the police, fire department, and meteorological agency). The input is raw data from the API, which is parsed (analyzed) into required information (e.g., location, time, and type of accident). The output is the parsed accident information.

[0472] What it does: The server uses Python's requests library to call the OpenWeatherMap API to get current weather data, then uses BeautifulSoup to parse the data and extract the information it needs.

[0473] Step 2:

[0474] The server obtains each piece of information using a means to obtain data such as the current time, season, weather, etc. The input is raw data related to the current time, season, and weather, and the output is an organized form of this data.

[0475] Specific operation: The server obtains the current time zone from the system time, calls the Japan Meteorological Agency's API to obtain the latest weather data, and stores this information in an integrated database.

[0476] Step 3:

[0477] The server uses a generative AI model to analyze the acquired accident information, time of day, season, and weather data in real time to calculate the risk level for each location. The input is the integrated data, and the output is a quantified data of the risk level for each location.

[0478] Specific operation: The server uses a TensorFlow model to input past accident data and current weather data and quantify the risk level at each location.

[0479] Step 4:

[0480] The server overlays the calculated risk level on map information. The input is the quantified risk level data and map data, and the output is a map that visually displays the risk level.

[0481] What it does: The server uses the Google Maps API to highlight dangerous areas in red and updates the map in real time.

[0482] Step 5:

[0483] The terminal periodically obtains the user's location information using the smartphone's built-in GPS module. The input is the GPS location information, and the output is the location data sent to the server.

[0484] Specific operation: The device obtains latitude and longitude using the smartphone's GPS module and sends this to the server at regular intervals (e.g., every 5 minutes).

[0485] Step 6:

[0486] The server compares the received user location information with the risk map to determine whether the user is approaching a dangerous area. The input is the user location information and the risk map, and the output is the approach determination result.

[0487] Specific operation: The server retrieves the user's location information and danger map from the database and compares them to determine whether the user is in a danger zone.

[0488] Step 7:

[0489] If the server determines that the user is approaching a dangerous area, it generates an alert and notifies the user's device. The input is the approach judgment result, and the output is the generated alert and notification.

[0490] Specific operation: The server generates an alert stating, "You are approaching a dangerous area. Please check the app for details," and sends it as a push notification to the user's smartphone.

[0491] Step 8:

[0492] The terminal notifies the user of the alerts received from the server. The input is the alert from the server, and the output is the notification to the user.

[0493] What happens: The device receives a push notification and displays a message to the user saying, "There is a dangerous area on your commute route. Please be careful."

[0494] (Application example 1)

[0495] 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."

[0496] To ensure the safety of automated machinery and workers in factories, it is important to collect, analyze, and notify accident and abnormality information in real time. However, conventional systems have difficulty in providing comprehensive safety management in real time, and accidents are likely to occur when workers or machines approach dangerous areas. To solve this problem, the present invention aims to provide a system that utilizes a generative AI model to analyze accident and incident information in factories in real time, calculate the level of danger, and issue appropriate warnings to automated machinery and workers.

[0497] 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.

[0498] In this invention, the server includes a data acquisition means, a means for acquiring data such as the current time of day, season, and weather, a risk calculation means using a generative AI model that integrates the accident and incident information collected by the data acquisition means and the acquired data and analyzes it in real time, a means for quantifying the risk calculated by the risk calculation means and overlaying it on map information, a means for acquiring user location information, a means for comparing the user's location information with the risk and generating an alert when the user approaches a dangerous area, a means for notifying the user's terminal of the alert, a means for periodically acquiring location information of automatic machines and workers in the factory, analyzing it in coordination with the accident and incident information in the factory collected by the data acquisition means, calculating the risk and overlaying it on map information, and a means for generating an alert when the dangerous area is approached and notifying the terminals of machines and workers in the factory. This enables real-time safety management of accidents and abnormalities in the factory.

[0499] "Data acquisition means" refers to the means of collecting accident and abnormality information from automated machinery, sensors, cameras, GPS modules, etc. within the factory.

[0500] "Means for obtaining data such as the current time of day, season, and weather" refers to means for obtaining environmental information such as the current time of day, season, and weather using external APIs or databases.

[0501] A "generative AI model" is an artificial intelligence model that analyzes collected data in real time and compares it with past data to calculate the level of risk.

[0502] The "risk calculation means" is a means of quantifying the risk of accidents or abnormalities at each location using a generative AI model.

[0503] The "means for overlaying on map information" is a means for displaying the calculated risk level overlaid on map information.

[0504] "Means for obtaining user location information" refers to means for obtaining the current location of a user or an automated machine using a GPS module or the like.

[0505] The "means for generating an alert" is a means for generating a warning when approaching a dangerous area based on the risk calculation result and the user's location information.

[0506] "Means for notifying the user's device" refers to the means for notifying the generated alert to the user's device, such as a smartphone or tablet.

[0507] The "means for periodically acquiring location information of automated machines and workers in a factory" refers to a means for acquiring location information of various machines and workers in a factory at regular intervals and transmitting it to a server.

[0508] "Means for analyzing in coordination with information on accidents and incidents within factories" refers to a means for analyzing information on accidents and abnormalities that occur within factories in combination with the location information of automated machines and workers.

[0509] The present invention aims to provide a system for managing the safety of automated machinery and workers in a factory by collecting and analyzing information on accidents and abnormalities in real time and issuing appropriate warnings. Specific embodiments for realizing this system are described below.

[0510] Data Acquisition Method

[0511] The server collects information about accidents and abnormalities from various sensors, cameras, and GPS modules within the factory. This information is collected using a sensor network and IoT devices. For example, temperature sensors, vibration sensors, and cameras are used to detect chemical leaks and machine malfunctions. This data is then stored in an integrated database on the server side.

[0512] Environmental data acquisition method

[0513] The server utilizes external APIs and internal databases to obtain environmental information such as the current time of day, season, and weather. This includes data obtained through the Japan Meteorological Agency and other public APIs. Weather information and seasonal variations are also collected, as they may affect specific hazard levels.

[0514] Risk calculation method

[0515] The server analyzes the collected data in real time using a generative AI model and compares it with past data to calculate the risk level. For example, it uses past accident data and current environmental data as input to generate a risk score for each location. This is done using machine learning frameworks such as TensorFlow and PyTorch.

[0516] Map information overlay method

[0517] The calculated risk level is overlaid on map information by the server. This map information is based on the layout of the factory and is updated in real time. Dangerous areas are color-coded to make them visually clear.

[0518] User location information acquisition method

[0519] Each terminal (automated machine or worker's mobile device) periodically acquires its current location using a GPS module and sends it to the server, allowing the server to constantly track the location of the automated machine or worker.

[0520] Alert generation method

[0521] The server compares the user's location information with the risk level and generates an alert if the user is approaching a dangerous area. The alert includes the type of danger, the risk level, and recommended actions.

[0522] Alert notification method

[0523] The generated alerts are instantly sent to automated machines and workers in the factory, such as smartphones, tablets, and even robot control systems, using push notification services such as Firebase Cloud Messaging.

[0524] Examples of concrete examples and prompts

[0525] Example 1: A chemical leak is detected in a factory and workers are approaching the area.

[0526] Prompt: "You are approaching a chemical spill area. Please leave the area immediately."

[0527] Example 2: When a worker is approaching the forklift's driving area.

[0528] Prompt: "You are approaching a forklift area. Please be careful."

[0529] This system will strengthen safety management within the factory and enable real-time response to accidents and abnormalities.

[0530] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0531] Step 1: Collect information through data acquisition methods

[0532] The server collects data on accidents and abnormalities from sensors, cameras, and GPS modules within the factory. This includes collecting environmental data such as temperature and vibration through the sensor's API and detecting abnormalities through camera video analysis.

[0533] Input: Raw data from sensors, cameras, and GPS modules (temperature, vibration, video, location information)

[0534] Output: Collected accident and abnormality data

[0535] Step 2: Collect information through environmental data acquisition methods

[0536] The server retrieves environmental data such as the current time zone, season, and weather from external APIs and databases. This is a process of retrieving weather and time data using public APIs.

[0537] Input: Environment data from public API

[0538] Output: Current time zone, season, weather, etc.

[0539] Step 3: Data integration and analysis

[0540] The server stores the data acquired in steps 1 and 2 in an integrated database and analyzes it in real time using a generative AI model, which predicts the risk level based on past and current data.

[0541] Input: Historical data in the integrated database and current data obtained

[0542] Output: Risk score (numerical value) for each location

[0543] Step 4: Overlaying risk information onto the map

[0544] The server overlays the calculated risk level on the map information of the factory, which displays dangerous areas on the map in different colors.

[0545] Input: Risk score, factory map information

[0546] Output: Map with risk overlay

[0547] Step 5: Get the user's location

[0548] The terminal (automated machine or worker's portable device) periodically obtains its current location using a GPS module and transmits it to the server.

[0549] Input: Location information from the GPS module

[0550] Output: Current location data of the user

[0551] Step 6: Alert Generation

[0552] The server compares the user's current location with the risk level and generates an alert if the user is approaching a risk area, including the type of risk, a risk score, and recommended actions.

[0553] Input: User's current location data, map with risk level overlay

[0554] Output: Warning message (alert)

[0555] Step 7: Alert Notification

[0556] The generated alerts are immediately sent to the user's device using a push notification service, specifically, Firebase Cloud Messaging, which sends notifications to smartphones and tablets.

[0557] Input: Warning message (alert)

[0558] Output: Notification to user device

[0559] The above processing steps enable real-time safety management for accidents and abnormalities within a factory. As a concrete example, the following prompt sentence is used:

[0560] Example 1: A chemical leak is detected in a factory and workers are approaching the area.

[0561] "Approaching a chemical spill area. Leave the area immediately."

[0562] Example 2: When a worker is approaching the forklift's driving area.

[0563] "You are approaching a forklift driving area. Use caution."

[0564] 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.

[0565] This invention is a system that collects accident and incident information in real time and uses that information to provide appropriate warnings to users. This system functions through the mutual cooperation of a server, terminals, users, and an emotion engine.

[0566] Basic System Configuration

[0567] The server first obtains accident and incident information from public APIs such as those of the police, fire department, and meteorological agency using data collection methods. It also separately obtains weather data, seasons, time of day, and other information. This information is stored in an integrated database and analyzed in real time by a generative AI model. The AI ​​model considers factors such as past accident and incident data, the current time of day, season, and weather, and quantifies the risk level of each location. The calculated risk level is then quantified and overlaid on map information. The risk map is updated in real time and linked to the user's location information.

[0568] The device periodically obtains the user's current GPS location information and sends it to the server. When the server receives the user's location information, it compares it with a risk map. If it determines that the user is approaching a dangerous area, it generates an alert. This alert includes the type of danger, the risk level, recommended actions, and more. The generated alert is immediately sent to the user's device. Furthermore, depending on the settings, alerts may also be sent to family members' devices.

[0569] Emotion engine integration

[0570] The emotion engine recognizes the user's emotional state and adjusts the alert content and notification method based on that. It uses the device's built-in camera and microphone to analyze the user's facial expressions and tone of voice. The analysis results are sent to the server and fed back to the risk calculation means.

[0571] The server recalculates the risk level based on the user's emotional state received from the emotion engine and adjusts the content and notification method of the alert as necessary. For example, if the user is nervous, the server will send an alert earlier. If the user is relaxed, the server will adjust the frequency and intensity of notifications.

[0572] Specific examples

[0573] Example 1: Use on your commute route

[0574] A user opens the app on their way to work. The device obtains GPS location information and sends it to the server. The server calculates a predicted risk level based on the current time of day (morning commute), weather (rain), and information on accidents and incidents around the commute route, and displays it on a map. If the user approaches a dangerous area on their commute route (for example, an area where many traffic accidents have occurred in the past), an alert is generated and sent to the device.

[0575] The device also uses a camera and microphone to analyze the user's emotional state and sends the data to the server. The server analyzes the emotional data and, if the user is nervous, highlights the alert and notifies the user of the appropriate recommended action. When the device receives the alert, it notifies the user, "There is a dangerous area on your commute route. Please be careful." The user can then take care and either avoid the area or pass through it safely.

[0576] Example 2: Child monitoring function

[0577] When a user (parent) is playing outside, the user opens the app and turns on the monitoring function. The device (child's device) obtains GPS location information and sends it to the server. The server predicts the level of danger based on the latest incident information and weather conditions in the area. The server quantifies the level of danger in real time based on the evening hours when traffic accidents are most common in the child's area. If the child approaches a dangerous area, an alert is generated and a notification is also sent to the parent's device. The user (parent) can use the device's camera and microphone to send their emotional state to the server and receive recommended actions to take to respond more appropriately.

[0578] This system allows users to receive real-time warnings when approaching dangerous locations, preventing accidents and incidents before they occur. In addition, the introduction of an emotion engine enables more personalized alert notifications tailored to the user's emotional state, further enhancing user safety.

[0579] The processing flow will be explained below.

[0580] Step 1:

[0581] The server accesses public APIs from the police, fire department, meteorological agency, etc., to obtain real-time accident and incident information and weather data.

[0582] Step 2:

[0583] The server centralizes the acquired accident and incident information and weather data and stores them in an integrated database.

[0584] Step 3:

[0585] The server extracts the latest accident and incident data and weather data from the integrated database and inputs it into the generative AI model.

[0586] Step 4:

[0587] The server uses a generative AI model to calculate the risk level for each location in real time, taking into account factors such as the frequency of accidents and incidents, their severity, time of day, season, and weather.

[0588] Step 5:

[0589] The server quantifies the calculated risk and overlays it on map information, continuously updating the generated risk map in real time.

[0590] Step 6:

[0591] Your device periodically retrieves your GPS location, which by default is every minute.

[0592] Step 7:

[0593] The terminal transmits the acquired location information to the server.

[0594] Step 8:

[0595] The server receives the user's location information and compares it with a real-time risk map.

[0596] Step 9:

[0597] The server generates an alert when the user approaches a dangerous area, including the type of danger, the numerical danger level, and recommended actions.

[0598] Step 10:

[0599] The server sends the generated alert to the user's device, and depending on the settings, it can also notify family members' devices at the same time.

[0600] Step 11:

[0601] The device processes the alert received from the server and notifies the user of the alert by displaying it on the screen or by audio notification.

[0602] Step 12:

[0603] The device uses a camera and microphone to analyze the user's facial expressions and tone of voice, and sends the analysis data to a server.

[0604] Step 13:

[0605] The server analyzes the user's emotional state received from the emotion engine.

[0606] Step 14:

[0607] The server recalculates the risk level and adjusts the alert content and notification method based on the user's emotional state. For example, if the user is nervous, it generates an earlier and more emphasized alert.

[0608] Step 15:

[0609] The server then sends the adjusted alert back to the user's device.

[0610] Step 16:

[0611] The device will notify the user of the received alert in an appropriate manner.

[0612] Step 17:

[0613] Users can check their current location and danger information based on notifications on their device and take recommended actions, such as avoiding dangerous areas or evacuating to a safe location.

[0614] Example 2

[0615] 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."

[0616] Conventional systems for collecting information on accidents and incidents have difficulty predicting risk in real time, making it impossible to immediately ensure the safety of users. Furthermore, they only provided a uniform notification method without taking into account the user's emotional state, making it impossible to provide appropriate warnings according to their state of tension or relaxation. Furthermore, they lacked a function to notify the user's family members, leaving a need for improved safety.

[0617] 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.

[0618] In this invention, the server includes a data acquisition unit, a unit for acquiring data such as the current time of day, season, and weather conditions, a risk assessment unit using an artificial intelligence model that integrates the accident and incident information collected by the data acquisition unit and the acquired data and analyzes them in real time, a unit for quantifying the risk calculated by the risk assessment unit and overlaying it on map information, a unit for acquiring device location information, a unit for comparing the device location information with the risk level and generating a warning when the device approaches a dangerous area, a unit for notifying the device of the warning, and a unit for recognizing the user's emotional state using emotion analysis means installed in the device and adjusting the content and notification method of the warning. This allows the user to receive an immediate warning when facing danger and enables personalized notifications based on the user's emotional state. Safety can also be improved by notifying the user's family members.

[0619] "Data acquisition means" refers to the means for collecting various data, including accident and incident information.

[0620] A "generative AI model" is an artificial intelligence model that analyzes integrated data in real time and assesses the level of risk.

[0621] The "risk assessment means" is a means of analyzing collected data using a generative AI model and quantifying the risk level at each location.

[0622] The "means for overlaying on map information" is a means for overlaying the calculated risk level on map data.

[0623] "Means for obtaining location information" refers to means for periodically obtaining location information from the user's terminal.

[0624] The "means for generating a warning" is a means for generating a warning to notify the user of the type of danger and its details when the user's terminal approaches a dangerous area.

[0625] The "means for notifying a warning" is a means for sending the generated warning to the user's terminal.

[0626] An "emotion analysis means" is a means for analyzing a user's facial expression and tone of voice to recognize their emotional state.

[0627] A "public API" is an API provided by public organizations such as police, fire departments, and meteorological agencies, and is a data interface used to obtain information on accidents and incidents, weather data, etc.

[0628] "Terminal" refers to a mobile communication device carried by a user for sending and receiving location information and emotional state.

[0629] This invention is a system that collects accident and incident information in real time and uses that information to provide appropriate warnings to users. This system functions by linking together a server, terminals, users, and an emotion engine.

[0630] Basic System Configuration

[0631] The server first obtains accident and incident information from public APIs such as those of police, fire departments, and meteorological agencies using a data acquisition method. It then separately obtains weather data, seasons, time periods, and other information. This information is then stored in an integrated database. Specifically, cloud services (such as AWS or Google Cloud Platform) are used. The collected data is stored in this integrated database, normalized, and prepared for analysis.

[0632] The server analyzes the information stored in the integrated database in real time using an artificial intelligence model (e.g., GPT-4). This model calculates the risk level for each location, taking into account factors such as past accident and incident data, the current time of day, season, and weather. The calculated risk level is quantified and overlaid on map information. The Google Maps API is used to render the map information. The risk map is updated in real time to continually reflect the latest information.

[0633] The device periodically obtains the user's current GPS location information and sends it to a server. This is done using a mobile device such as a smartphone. The server compares the received location information with a risk map to determine whether the user is approaching a dangerous area. If it determines that the user is approaching a dangerous area, the server generates a warning. This warning includes the type of danger, the risk level, recommended actions, etc. The generated warning is immediately sent to the user's device. This notification method is push notification.

[0634] The device is also equipped with an emotion analysis function. It uses the camera and microphone to analyze the user's facial expressions and tone of voice, and sends the results to a server using technologies such as OpenCV and Google Cloud Speech-to-Text. The server uses these analysis results to recognize the user's emotional state and adjust the content and notification method of the alert. For example, if the user is nervous, the alert will be emphasized and the notification will be sent earlier. Also, if the user is relaxed, the frequency and intensity of the alert will be adjusted.

[0635] Specific examples

[0636] Example 1: Use on your commute route

[0637] A user opens the app on their way to work. The device obtains their GPS location and sends it to the server. The server calculates a predicted risk level based on the current time of day (morning commute), weather (rain), and information on accidents and incidents around the commute route, and displays it on a map. If the user approaches a dangerous area on their commute route, a warning is generated and sent to the device. For example, the device could not only display a text message saying, "There is a dangerous area on your commute route. Please be careful," but also use vibration and audio notifications to further amplify the warning. Additionally, a prompt message like, "Please tell me how to notify me if I approach a dangerous area on my commute. It's morning commute time and the weather is rainy." could be used.

[0638] Example 2: Child monitoring function

[0639] When the user (parent) is playing outside, the user opens the app and turns on the monitoring function. The device (child's device) obtains GPS location information and sends it to the server. The server predicts the level of danger based on the latest incident information and weather conditions in the area. The server quantifies the level of danger in real time based on the evening hours when traffic accidents are most common in the child's area. If the child approaches a dangerous area, a warning is generated and a notification is also sent to the parent's device. The parent's device is displayed with the text "Your child is approaching an area with a high incidence of traffic accidents. Please contact us immediately and ensure their safety." Additionally, a prompt such as "How can I be notified if my child approaches a dangerous area? It is evening and the weather is clear" can also be used.

[0640] This system allows users to receive real-time warnings when approaching dangerous areas, preventing accidents and incidents before they occur. In addition, the introduction of an emotion engine enables more personalized warning notifications tailored to the user's emotional state, further enhancing user safety.

[0641] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0642] Step 1: Collect data

[0643] The server collects accident and incident information from public APIs such as police, fire departments, and meteorological agencies.

[0644] Input: Accident and incident information from public APIs, weather data, time of day, and seasonal data.

[0645] Specific operation: Periodically send GET requests to each public API and receive response data in JSON format. For example, access the weather API to get weather information.

[0646] Output: A dataset containing collected accident and incident information and weather data.

[0647] Step 2: Integrate the data

[0648] The server stores the collected data in an integrated database.

[0649] Input: Collected accident and incident information, weather data, time of day, and seasonal data.

[0650] Specific behavior: Normalizes the received data and stores it in a SQL database, for example, inserting JSON data into the appropriate table.

[0651] Output: Data stored in the consolidated database.

[0652] Step 3: Preprocessing the data

[0653] The server extracts the necessary data from the integrated database and converts it into a format suitable for analysis.

[0654] Input: Various data in the integrated database.

[0655] Specific operations: Data cleansing, removing outliers, and imputing missing data (e.g., imputing missing values ​​with the mean).

[0656] Output: The preprocessed dataset.

[0657] Step 4: Risk analysis

[0658] The server uses a generative AI model to analyze the pre-processed data in real time and calculate the risk level.

[0659] Input: Preprocessed accident and incident information, weather data, time of day, and season data.

[0660] Specific operation: Input data into a generative AI model to quantify the risk level of each location. For example, run a predictive model based on similar past data.

[0661] Output: A dataset quantifying the risk at each location.

[0662] Step 5: Generate a risk map

[0663] The server overlays the calculated risk level onto map information to visualize it.

[0664] Input: Quantified risk data, map information.

[0665] Specific operation: Uses Google Maps API to display danger levels on a map in different colors. For example, high-danger areas are displayed in red.

[0666] Output: Hazard map.

[0667] Step 6: Get GPS location

[0668] The device periodically obtains the user's current GPS location information and sends it to the server.

[0669] Input: Location information from the device's GPS module.

[0670] Specific operation: The device uses the smartphone's GPS sensor to obtain location information and sends the encrypted data to a server via HTTPS.

[0671] Output: The location data sent to the server.

[0672] Step 7: Matching location information with risk maps

[0673] The server compares the received location information with a risk map to determine whether the user is approaching a dangerous area.

[0674] Input: Received location information, risk map.

[0675] Specific operation: The location information is compared with a risk map to determine whether there are any high-risk areas within a specified distance.

[0676] Output: Information on approaching dangerous areas.

[0677] Step 8: Generate and notify alerts

[0678] If the server determines that the user is approaching a dangerous area, it immediately generates a warning and notifies the user's terminal.

[0679] Input: Information about approaching a dangerous area.

[0680] Specific operation: Create a warning message and send it to the device using push notification. For example, send a message saying "You are approaching a dangerous area. Be careful."

[0681] Output: The alert notification sent to the user's device.

[0682] Step 9: Capturing Emotional State

[0683] The device uses a camera and microphone to recognize the user's emotional state and transmits the results to a server.

[0684] Input: The user's facial expressions and tone of voice.

[0685] Specific operations: Facial expression recognition using OpenCV and voice analysis using Google Cloud Speech-to-Text.

[0686] Output: Emotion recognition data sent to the server.

[0687] Step 10: Adjusting Emotion-Based Alerts

[0688] The server adjusts the content of the warning and notification method based on the emotion recognition data it receives.

[0689] Input: Emotion recognition data, warning notification data.

[0690] Specific behavior: Adjust the intensity and timing of alerts depending on the user's emotional state. For example, send an earlier and more emphasized alert to a user who is nervous.

[0691] Output: Reconciled alert notification data.

[0692] (Application example 2)

[0693] 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."

[0694] Conventional accident and incident information collection systems have limitations in real-time risk calculation and alert functions, and from the user's perspective, they have had issues with not being able to provide notifications that are adequately tailored to the urgency or individual situation. Furthermore, no previous systems have been able to provide alerts that take into account the user's emotional state, which has led to a lack of effective means of improving safety.

[0695] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0696] In this invention, the server includes a data collection means, a means for acquiring data such as the current time of day, season, and weather, a risk calculation means using a generative AI model that integrates the accident and incident information collected by the data collection means and the acquired data and analyzes them in real time, a means for quantifying the risk calculated by the risk calculation means and overlaying it on map information, a means for acquiring user location information, a means for comparing the user location information with the risk level and generating an alert when the user approaches a dangerous area, an emotion analysis means for recognizing the user's emotional state using a camera and microphone mounted on the terminal and adjusting the alert content and notification method based on the emotional state, and a means for notifying the user of the alert to the user's terminal. This enables real-time and personalized alert notifications when the user approaches a dangerous area, thereby improving safety.

[0697] "Data collection means" refers to the means for obtaining accident and incident information and other related data.

[0698] "Means for acquiring data such as the current time zone, season, and weather" refers to means for collecting information about the time zone, season, and weather at that time.

[0699] A "means for calculating risk using a generative AI model" is a means for utilizing a generative AI model that is used to integrate collected data, analyze it in real time, and calculate risk.

[0700] "Means for overlaying on map information" refers to a means for converting the calculated risk level into a number and displaying it overlaid on a map.

[0701] "Means for obtaining user location information" refers to means for obtaining the user's current location.

[0702] "Means for generating an alert" means a means for automatically generating a warning when a user approaches a hazardous area.

[0703] The "emotion analysis means" is a means for recognizing the emotional state of the user using a camera or microphone installed in the terminal, and adjusting the alert content and notification method based on the emotional state.

[0704] "Means for notifying the user's device" refers to means for sending the generated alert to the user's mobile device or the like.

[0705] The present invention is a system that collects accident and incident information in real time and issues appropriate warnings to users based on that information, and functions in cooperation with a server, terminal, user, and emotion analysis engine.

[0706] The server uses data collection methods to obtain accident and incident information from public APIs such as those of the police, fire department, and meteorological agency. It also separately obtains weather data, seasons, time of day, and other information. This information is stored in an integrated database and analyzed in real time by a generative AI model. The AI ​​model considers factors such as past accident and incident data, the current time of day, season, and weather, and quantifies the risk level of each location. The calculated risk level is quantified and overlaid on map information. The risk map is updated in real time and linked to the user's location information.

[0707] The device periodically obtains the user's current GPS location information and sends it to the server. When the server receives the user's location information, it compares it with a risk map. If it determines that the user is approaching a dangerous area, it generates an alert. This alert includes the type of danger, the risk level, recommended actions, and more. The generated alert is immediately sent to the user's device. Furthermore, depending on the settings, alerts may also be sent to family members' devices.

[0708] The emotion analysis engine has the ability to recognize the user's emotional state and adjust the alert content and notification method based on that. It uses the device's built-in camera and microphone to analyze the user's facial expressions and tone of voice. The analysis results are sent to the server and fed back to the risk level calculation means. The server recalculates the risk level based on the user's emotional state received from the emotion analysis engine, and adjusts the alert content and notification method as necessary. For example, if the user is nervous, the alert will be sent earlier. Also, if the user is relaxed, the frequency and intensity of notifications will be adjusted.

[0709] Specific examples

[0710] Example 1: Use on your commute route

[0711] A user opens the app on their way to work. The device obtains their GPS location and sends it to the server. The server calculates a predicted risk level based on the current time of day (morning commute), weather (rain), and information on accidents and incidents along the commute route, and displays it on a map. If the user approaches a dangerous area on their commute route (for example, an area where many traffic accidents have occurred in the past), an alert is generated and sent to the device. The device also uses its camera and microphone to analyze the user's emotional state and sends that data to the server. The server analyzes the emotional data and, if the user is nervous, emphasizes the alert content and notifies the user of appropriate recommended actions. The device receives the alert and notifies the user, "There is a dangerous area on your commute route. Please be careful." The user pays attention and either avoids the area or passes through it safely.

[0712] Example 2: Child monitoring function

[0713] When a user (parent) is playing outside, the user opens the app and turns on the monitoring function. The device (child's device) obtains GPS location information and sends it to the server. The server predicts the level of danger based on the latest incident information and weather conditions in the area. The server quantifies the level of danger in real time based on the evening hours when traffic accidents are most common in the child's area. If the child approaches a dangerous area, an alert is generated and a notification is also sent to the parent's device. The user (parent) can use the device's camera and microphone to send their emotional state to the server and receive recommended actions to take to respond more appropriately.

[0714] Prompt Sentence Examples

[0715] Prompt to calculate risk based on user location:

[0716] text

[0717] Based on the data collected from the API used, analyze accident and incident information within 1 kilometer of the user's current location and calculate the risk level.

[0718] Alert generation prompts taking into account sentiment analysis results:

[0719] text

[0720] If the user's emotional state is tense, generate appropriate alerts with earlier and more detailed information about the alert.

[0721] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0722] Step 1:

[0723] The server obtains accident and incident information from public APIs using data collection methods. Specifically, it sends requests to the APIs of the police, fire department, meteorological agency, etc. to obtain the latest accident and incident information.

[0724] Input: API request

[0725] Output: Accident and incident information dataset

[0726] Step 2:

[0727] The server also acquires additional data such as the current time of day, season, and weather, which allows for analysis that takes into account a variety of factors along with accident and incident data.

[0728] Input: API request for time, season, and weather data

[0729] Output: Time, season, weather data

[0730] Step 3:

[0731] The server aggregates all the collected data and performs real-time analysis using a generative AI model, which calculates the risk level for each location.

[0732] Input: Accident / incident data, time, season, weather data

[0733] Output: Risk level at each location

[0734] Step 4:

[0735] The server quantifies the calculated risk and overlays it on map information, resulting in a user-friendly visualization of the risk.

[0736] Input: Risk level at each location

[0737] Output: Map information showing risk levels

[0738] Step 5:

[0739] The device periodically obtains the user's current GPS location and sends it to the server for subsequent analysis.

[0740] Input: GPS location

[0741] Output: Location information sent to the server

[0742] Step 6:

[0743] The server compares the user's location against the risk map and generates an alert when the user approaches a risk area, including the type of risk, a risk level number, and recommended actions.

[0744] Input: User location, risk map

[0745] Output: Alert

[0746] Step 7:

[0747] The device uses the built-in camera and microphone to analyze the user's emotional state and sends the data to a server, where an emotion analysis engine is used for emotion analysis.

[0748] Input: Camera video, microphone audio

[0749] Output: Emotion data

[0750] Step 8:

[0751] The server recalculates the risk level based on the emotion data received from the emotion analysis engine and adjusts the alert content and notification method, for example, emphasizing the alert content if the user is nervous.

[0752] Input: Emotion data, existing risk data

[0753] Output: Throttled alerts

[0754] Step 9:

[0755] The device will notify the user of the generated alert, and depending on the settings, the same alert will also be sent to family devices.

[0756] Input: alert

[0757] Output: Notification to user and family devices

[0758] 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.

[0759] 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.

[0760] 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.

[0761] [Third embodiment]

[0762] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0763] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0764] 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).

[0765] 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.

[0766] 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.

[0767] 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).

[0768] 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.

[0769] 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.

[0770] 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.

[0771] 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.

[0772] 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.

[0773] 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."

[0774] This invention is a system that collects accident and incident information in real time and issues appropriate warnings to users based on that information. This system functions in cooperation with a server, terminals, and users.

[0775] The server first obtains accident and incident information from public APIs such as those of the police, fire department, and meteorological agency using data collection methods. It also separately obtains weather data, seasons, time of day, and other information. This information is stored in an integrated database and analyzed in real time by a generative AI model. The AI ​​model considers factors such as past accident and incident data, the current time of day, season, and weather, and quantifies the risk level of each location. The calculated risk level is then quantified and overlaid on map information. The risk map is updated in real time and linked to the user's location information.

[0776] The device periodically obtains the user's current GPS location information and sends it to the server. When the server receives the user's location information, it compares it with a risk map. If it determines that the user is approaching a dangerous area, it generates an alert. This alert includes the type of danger, the risk level, recommended actions, and more. The generated alert is immediately sent to the user's device. Furthermore, depending on the settings, alerts may also be sent to family members' devices.

[0777] Users can check the danger information for the location based on the notification on their device. The alert contains detailed information about the dangerous area, allowing users to take appropriate action. For example, if they are approaching a dangerous area on their way to work, they can check the alert and choose an alternative route. Similarly, if a parent receives an alert that their child is approaching a dangerous area while playing outside, they can immediately contact their child or guide them to a safe location.

[0778] Example 1: Use on your commute route

[0779] A user opens the app on their way to work. The device obtains GPS location information and sends it to the server. The server calculates a predicted risk level based on the current time of day (morning commute), weather (rain), and information on accidents and incidents around the commute route, and displays it on a map. If the user approaches a dangerous area on their commute route (for example, an area where many traffic accidents have occurred in the past), an alert is generated and sent to the device. The device receives the alert and notifies the user, "There is a dangerous area on your commute route. Please be careful." The user then pays attention and either avoids the area or passes through it safely.

[0780] Example 2: Child monitoring function

[0781] When the child is playing outside, the user (parent) opens the app and turns on the monitoring function. The device (child's device) obtains GPS location information and sends it to the server. The server predicts the level of danger based on the latest incident information and weather conditions in the area. The server quantifies the level of danger in real time based on the evening hours when traffic accidents are most common in the child's area. If the child approaches a dangerous area, an alert is generated and a notification is also sent to the parent's device. The device notifies the parent, "Your child is approaching a dangerous area. Please check." The user (parent) can contact the child or guide them to a safe location.

[0782] This system allows users to receive real-time warnings when they approach dangerous areas, making it possible to prevent accidents and incidents.In addition, by simultaneously notifying family members of the alert, it encourages quick response and further increases the user's safety.

[0783] The processing flow will be explained below.

[0784] Step 1:

[0785] The server accesses public APIs from the police, fire department, meteorological agency, etc., to obtain accident and incident information and weather data in real time.

[0786] Step 2:

[0787] The server centralizes the acquired accident and incident information and weather data and stores them in an integrated database.

[0788] Step 3:

[0789] The server extracts the latest accident and incident data and weather data from the integrated database and inputs this into the generative AI model.

[0790] Step 4:

[0791] The server uses a generative AI model to calculate the risk level for each location in real time, taking into account factors such as the frequency of accidents and incidents, their severity, time of day, season, and weather.

[0792] Step 5:

[0793] The server quantifies the calculated risk and overlays it on map information, continuously updating the generated risk map in real time.

[0794] Step 6:

[0795] Your device periodically retrieves your GPS location, which by default is every minute.

[0796] Step 7:

[0797] The terminal transmits the acquired location information to the server.

[0798] Step 8:

[0799] The server receives the user's location information and compares it with a real-time risk map.

[0800] Step 9:

[0801] The server generates an alert when the user approaches a dangerous area, including the type of danger, the numerical danger level, and recommended actions.

[0802] Step 10:

[0803] The server sends the generated alert to the user's device, and depending on the settings, it can also notify family members' devices at the same time.

[0804] Step 11:

[0805] The device processes the alert received from the server and notifies the user of the alert by displaying it on the screen or by audio notification.

[0806] Step 12:

[0807] Users can check their current location and danger information based on notifications from their device and take recommended actions, such as avoiding dangerous areas or evacuating to a safe location.

[0808] Example 1

[0809] 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."

[0810] Conventional systems for collecting accident and incident information and notifying users have difficulty calculating the risk level in real time, making it difficult to issue prompt warnings. Furthermore, they lack the functionality to simultaneously notify alerts to users and their families, resulting in inadequate emergency response. To solve these problems, the present invention provides a system for collecting data from public APIs and analyzing risk levels in real time, thereby quickly issuing warnings to users and their families.

[0811] 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.

[0812] In this invention, the server includes a data collection means, a means for acquiring data such as the current time zone, season, and weather, a risk calculation means using a generative AI model that integrates the accident and incident information collected by the data collection means and the acquired data and analyzes them in real time, a means for quantifying the risk calculated by the risk calculation means and overlaying it on map information, a means for acquiring user location information, a means for comparing the user location information with the risk and generating an alert when the user approaches a dangerous area, a means for notifying the user's device of the alert, and a means for notifying the device of related family members of the alert by the notification means, thereby enabling the user and their family members to obtain risk information in real time and take prompt action.

[0813] "Data collection means" refers to means for collecting data from multiple sources, including accident and incident information.

[0814] The "risk calculation means" is a means for integrating collected data and calculating risk in real time using a generative AI model.

[0815] The "means for quantifying the risk level and overlaying it on map information" is a means for expressing the calculated risk level in a numerical format and overlaying that information on a map.

[0816] "Means for obtaining user location information" refers to means for obtaining the user's current location from the terminal.

[0817] "Means for generating an alert" refers to a means for issuing a warning when a user approaches a dangerous area.

[0818] The "notification means" is a means for transmitting the generated alert to the terminals of the user and related family members.

[0819] A "public API" is an application programming interface provided by public institutions such as the police, fire department, and meteorological agency.

[0820] The present invention is a system that aims to prevent accidents and incidents by providing real-time warnings when users approach dangerous locations. This system functions in cooperation with a server, terminals, and users.

[0821] server

[0822] The server first uses data collection tools (e.g., Python library requests, BeautifulSoup, etc.) to obtain accident and incident information from public APIs (e.g., NASA API, OpenWeatherMap API) of the police, fire department, meteorological agency, etc. It also separately obtains weather data, seasons, time periods, etc. All obtained information is stored in an integrated database (e.g., MySQL, PostgreSQL).

[0823] The stored data is then analyzed in real time using a generative AI model (e.g., TensorFlow, PyTorch). The model calculates the risk level for each location, taking into account factors such as past accident and incident data, the current time of day, season, and weather. This risk level is then stored in a database and overlaid on map information (e.g., Google Maps API, Mapbox). This risk map is updated in real time, and as new information is added, it is reflected on the map provided to users.

[0824] Terminal

[0825] The device periodically obtains the user's current location using the smartphone's built-in GPS module. This location information is updated at regular intervals (e.g., every 5 minutes) and sent to the server. The server compares the received location information with the current risk map to determine whether the user is approaching a dangerous area.

[0826] User

[0827] Users can check the danger information for the location based on the notification on their device. The alert contains detailed information about the dangerous area, allowing users to take appropriate action. For example, if they are approaching a dangerous area on their way to work, they can check the alert and choose an alternative route. Similarly, if a parent receives an alert that their child is approaching a dangerous area while playing outside, they can immediately contact their child or guide them to a safe location.

[0828] Examples:

[0829] Use on your commute route

[0830] A user opens the app on their way to work. The device obtains GPS location information and sends it to the server. The server calculates a predicted risk level based on the current time of day (morning commute), weather (rain), and information on accidents and incidents around the commute route, and displays it on a map. If the user approaches a dangerous area on their commute route (for example, an area where many traffic accidents have occurred in the past), an alert is generated and sent to the device. The device receives the alert and notifies the user, "There is a dangerous area on your commute route. Please be careful." The user then pays attention and either avoids the area or passes through it safely.

[0831] Child monitoring function

[0832] When the child is playing outside, the user (parent) opens the app and turns on the monitoring function. The device (child's device) obtains GPS location information and sends it to the server. The server predicts the level of danger based on the latest incident information and weather conditions in the area. The server quantifies the level of danger in real time based on the evening hours when traffic accidents are most common in the child's area. If the child approaches a dangerous area, an alert is generated and a notification is also sent to the parent's device. The device notifies the parent, "Your child is approaching a dangerous area. Please check." The user (parent) can contact the child or guide them to a safe location.

[0833] Prompt Sentence Examples

[0834] Use on your commute route

[0835] "It's morning commute time and you're heading to your destination in the rain. Please check to see if there are any dangerous areas along your route."

[0836] Child monitoring function

[0837] "My child is playing outside. I want to know the danger areas based on the latest incidents in the area and current weather conditions."

[0838] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0839] Step 1:

[0840] The server uses data collection tools to collect accident and incident information from public APIs (e.g., APIs of the police, fire department, and meteorological agency). The input is raw data from the API, which is parsed (analyzed) into required information (e.g., location, time, and type of accident). The output is the parsed accident information.

[0841] What it does: The server uses Python's requests library to call the OpenWeatherMap API to get current weather data, then uses BeautifulSoup to parse the data and extract the information it needs.

[0842] Step 2:

[0843] The server obtains each piece of information using a means to obtain data such as the current time, season, weather, etc. The input is raw data related to the current time, season, and weather, and the output is an organized form of this data.

[0844] Specific operation: The server obtains the current time zone from the system time, calls the Japan Meteorological Agency's API to obtain the latest weather data, and stores this information in an integrated database.

[0845] Step 3:

[0846] The server uses a generative AI model to analyze the acquired accident information, time of day, season, and weather data in real time to calculate the risk level for each location. The input is the integrated data, and the output is a quantified data of the risk level for each location.

[0847] Specific operation: The server uses a TensorFlow model to input past accident data and current weather data and quantify the risk level at each location.

[0848] Step 4:

[0849] The server overlays the calculated risk level on map information. The input is the quantified risk level data and map data, and the output is a map that visually displays the risk level.

[0850] What it does: The server uses the Google Maps API to highlight dangerous areas in red and updates the map in real time.

[0851] Step 5:

[0852] The terminal periodically obtains the user's location information using the smartphone's built-in GPS module. The input is the GPS location information, and the output is the location data sent to the server.

[0853] Specific operation: The device obtains latitude and longitude using the smartphone's GPS module and sends this to the server at regular intervals (e.g., every 5 minutes).

[0854] Step 6:

[0855] The server compares the received user location information with the risk map to determine whether the user is approaching a dangerous area. The input is the user location information and the risk map, and the output is the approach determination result.

[0856] Specific operation: The server retrieves the user's location information and danger map from the database and compares them to determine whether the user is in a danger zone.

[0857] Step 7:

[0858] If the server determines that the user is approaching a dangerous area, it generates an alert and notifies the user's device. The input is the approach judgment result, and the output is the generated alert and notification.

[0859] Specific operation: The server generates an alert stating, "You are approaching a dangerous area. Please check the app for details," and sends it as a push notification to the user's smartphone.

[0860] Step 8:

[0861] The terminal notifies the user of the alerts received from the server. The input is the alert from the server, and the output is the notification to the user.

[0862] What happens: The device receives a push notification and displays a message to the user saying, "There is a dangerous area on your commute route. Please be careful."

[0863] (Application example 1)

[0864] 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."

[0865] To ensure the safety of automated machinery and workers in factories, it is important to collect, analyze, and notify accident and abnormality information in real time. However, conventional systems have difficulty in providing comprehensive safety management in real time, and accidents are likely to occur when workers or machines approach dangerous areas. To solve this problem, the present invention aims to provide a system that utilizes a generative AI model to analyze accident and incident information in factories in real time, calculate the level of danger, and issue appropriate warnings to automated machinery and workers.

[0866] 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.

[0867] In this invention, the server includes a data acquisition means, a means for acquiring data such as the current time of day, season, and weather, a risk calculation means using a generative AI model that integrates the accident and incident information collected by the data acquisition means and the acquired data and analyzes it in real time, a means for quantifying the risk calculated by the risk calculation means and overlaying it on map information, a means for acquiring user location information, a means for comparing the user's location information with the risk and generating an alert when the user approaches a dangerous area, a means for notifying the user's terminal of the alert, a means for periodically acquiring location information of automatic machines and workers in the factory, analyzing it in coordination with the accident and incident information in the factory collected by the data acquisition means, calculating the risk and overlaying it on map information, and a means for generating an alert when the dangerous area is approached and notifying the terminals of machines and workers in the factory. This enables real-time safety management of accidents and abnormalities in the factory.

[0868] "Data acquisition means" refers to the means of collecting accident and abnormality information from automated machinery, sensors, cameras, GPS modules, etc. within the factory.

[0869] "Means for obtaining data such as the current time of day, season, and weather" refers to means for obtaining environmental information such as the current time of day, season, and weather using external APIs or databases.

[0870] A "generative AI model" is an artificial intelligence model that analyzes collected data in real time and compares it with past data to calculate the level of risk.

[0871] The "risk calculation means" is a means of quantifying the risk of accidents or abnormalities at each location using a generative AI model.

[0872] The "means for overlaying on map information" is a means for displaying the calculated risk level overlaid on map information.

[0873] "Means for obtaining user location information" refers to means for obtaining the current location of a user or an automated machine using a GPS module or the like.

[0874] The "means for generating an alert" is a means for generating a warning when approaching a dangerous area based on the risk calculation result and the user's location information.

[0875] "Means for notifying the user's device" refers to the means for notifying the generated alert to the user's device, such as a smartphone or tablet.

[0876] The "means for periodically acquiring location information of automated machines and workers in a factory" refers to a means for acquiring location information of various machines and workers in a factory at regular intervals and transmitting it to a server.

[0877] "Means for analyzing in coordination with information on accidents and incidents within factories" refers to a means for analyzing information on accidents and abnormalities that occur within factories in combination with the location information of automated machines and workers.

[0878] The present invention aims to provide a system for managing the safety of automated machinery and workers in a factory by collecting and analyzing information on accidents and abnormalities in real time and issuing appropriate warnings. Specific embodiments for realizing this system are described below.

[0879] Data Acquisition Method

[0880] The server collects information about accidents and abnormalities from various sensors, cameras, and GPS modules within the factory. This information is collected using a sensor network and IoT devices. For example, temperature sensors, vibration sensors, and cameras are used to detect chemical leaks and machine malfunctions. This data is then stored in an integrated database on the server side.

[0881] Environmental data acquisition method

[0882] The server utilizes external APIs and internal databases to obtain environmental information such as the current time of day, season, and weather. This includes data obtained through the Japan Meteorological Agency and other public APIs. Weather information and seasonal variations are also collected, as they may affect specific hazard levels.

[0883] Risk calculation method

[0884] The server analyzes the collected data in real time using a generative AI model and compares it with past data to calculate the risk level. For example, it uses past accident data and current environmental data as input to generate a risk score for each location. This is done using machine learning frameworks such as TensorFlow and PyTorch.

[0885] Map information overlay method

[0886] The calculated risk level is overlaid on map information by the server. This map information is based on the layout of the factory and is updated in real time. Dangerous areas are color-coded to make them visually clear.

[0887] User location information acquisition method

[0888] Each terminal (automated machine or worker's mobile device) periodically acquires its current location using a GPS module and sends it to the server, allowing the server to constantly track the location of the automated machine or worker.

[0889] Alert generation method

[0890] The server compares the user's location information with the risk level and generates an alert if the user is approaching a dangerous area. The alert includes the type of danger, the risk level, and recommended actions.

[0891] Alert notification method

[0892] The generated alerts are instantly sent to automated machines and workers in the factory, such as smartphones, tablets, and even robot control systems, using push notification services such as Firebase Cloud Messaging.

[0893] Examples of concrete examples and prompts

[0894] Example 1: A chemical leak is detected in a factory and workers are approaching the area.

[0895] Prompt: "You are approaching a chemical spill area. Please leave the area immediately."

[0896] Example 2: When a worker is approaching the forklift's driving area.

[0897] Prompt: "You are approaching a forklift area. Please be careful."

[0898] This system will strengthen safety management within the factory and enable real-time response to accidents and abnormalities.

[0899] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0900] Step 1: Collect information through data acquisition methods

[0901] The server collects data on accidents and abnormalities from sensors, cameras, and GPS modules within the factory. This includes collecting environmental data such as temperature and vibration through the sensor's API and detecting abnormalities through camera video analysis.

[0902] Input: Raw data from sensors, cameras, and GPS modules (temperature, vibration, video, location information)

[0903] Output: Collected accident and abnormality data

[0904] Step 2: Collect information through environmental data acquisition methods

[0905] The server retrieves environmental data such as the current time zone, season, and weather from external APIs and databases. This is a process of retrieving weather and time data using public APIs.

[0906] Input: Environment data from public API

[0907] Output: Current time zone, season, weather, etc.

[0908] Step 3: Data integration and analysis

[0909] The server stores the data acquired in steps 1 and 2 in an integrated database and analyzes it in real time using a generative AI model, which predicts the risk level based on past and current data.

[0910] Input: Historical data in the integrated database and current data obtained

[0911] Output: Risk score (numerical value) for each location

[0912] Step 4: Overlaying risk information onto the map

[0913] The server overlays the calculated risk level on the map information of the factory, which displays dangerous areas on the map in different colors.

[0914] Input: Risk score, factory map information

[0915] Output: Map with risk overlay

[0916] Step 5: Get the user's location

[0917] The terminal (automated machine or worker's portable device) periodically obtains its current location using a GPS module and transmits it to the server.

[0918] Input: Location information from the GPS module

[0919] Output: Current location data of the user

[0920] Step 6: Alert Generation

[0921] The server compares the user's current location with the risk level and generates an alert if the user is approaching a risk area, including the type of risk, a risk score, and recommended actions.

[0922] Input: User's current location data, map with risk level overlay

[0923] Output: Warning message (alert)

[0924] Step 7: Alert Notification

[0925] The generated alerts are immediately sent to the user's device using a push notification service, specifically, Firebase Cloud Messaging, which sends notifications to smartphones and tablets.

[0926] Input: Warning message (alert)

[0927] Output: Notification to user device

[0928] The above processing steps enable real-time safety management for accidents and abnormalities within a factory. As a concrete example, the following prompt sentence is used:

[0929] Example 1: A chemical leak is detected in a factory and workers are approaching the area.

[0930] "Approaching a chemical spill area. Leave the area immediately."

[0931] Example 2: When a worker is approaching the forklift's driving area.

[0932] "You are approaching a forklift driving area. Use caution."

[0933] 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.

[0934] This invention is a system that collects accident and incident information in real time and uses that information to provide appropriate warnings to users. This system functions through the mutual cooperation of a server, terminals, users, and an emotion engine.

[0935] Basic System Configuration

[0936] The server first obtains accident and incident information from public APIs such as those of the police, fire department, and meteorological agency using data collection methods. It also separately obtains weather data, seasons, time of day, and other information. This information is stored in an integrated database and analyzed in real time by a generative AI model. The AI ​​model considers factors such as past accident and incident data, the current time of day, season, and weather, and quantifies the risk level of each location. The calculated risk level is then quantified and overlaid on map information. The risk map is updated in real time and linked to the user's location information.

[0937] The device periodically obtains the user's current GPS location information and sends it to the server. When the server receives the user's location information, it compares it with a risk map. If it determines that the user is approaching a dangerous area, it generates an alert. This alert includes the type of danger, the risk level, recommended actions, and more. The generated alert is immediately sent to the user's device. Furthermore, depending on the settings, alerts may also be sent to family members' devices.

[0938] Emotion engine integration

[0939] The emotion engine recognizes the user's emotional state and adjusts the alert content and notification method based on that. It uses the device's built-in camera and microphone to analyze the user's facial expressions and tone of voice. The analysis results are sent to the server and fed back to the risk calculation means.

[0940] The server recalculates the risk level based on the user's emotional state received from the emotion engine and adjusts the content and notification method of the alert as necessary. For example, if the user is nervous, the server will send an alert earlier. If the user is relaxed, the server will adjust the frequency and intensity of notifications.

[0941] Specific examples

[0942] Example 1: Use on your commute route

[0943] A user opens the app on their way to work. The device obtains GPS location information and sends it to the server. The server calculates a predicted risk level based on the current time of day (morning commute), weather (rain), and information on accidents and incidents around the commute route, and displays it on a map. If the user approaches a dangerous area on their commute route (for example, an area where many traffic accidents have occurred in the past), an alert is generated and sent to the device.

[0944] The device also uses a camera and microphone to analyze the user's emotional state and sends the data to the server. The server analyzes the emotional data and, if the user is nervous, highlights the alert and notifies the user of the appropriate recommended action. When the device receives the alert, it notifies the user, "There is a dangerous area on your commute route. Please be careful." The user can then take care and either avoid the area or pass through it safely.

[0945] Example 2: Child monitoring function

[0946] When a user (parent) is playing outside, the user opens the app and turns on the monitoring function. The device (child's device) obtains GPS location information and sends it to the server. The server predicts the level of danger based on the latest incident information and weather conditions in the area. The server quantifies the level of danger in real time based on the evening hours when traffic accidents are most common in the child's area. If the child approaches a dangerous area, an alert is generated and a notification is also sent to the parent's device. The user (parent) can use the device's camera and microphone to send their emotional state to the server and receive recommended actions to take to respond more appropriately.

[0947] This system allows users to receive real-time warnings when approaching dangerous locations, preventing accidents and incidents before they occur. In addition, the introduction of an emotion engine enables more personalized alert notifications tailored to the user's emotional state, further enhancing user safety.

[0948] The processing flow will be explained below.

[0949] Step 1:

[0950] The server accesses public APIs from the police, fire department, meteorological agency, etc., to obtain real-time accident and incident information and weather data.

[0951] Step 2:

[0952] The server centralizes the acquired accident and incident information and weather data and stores them in an integrated database.

[0953] Step 3:

[0954] The server extracts the latest accident and incident data and weather data from the integrated database and inputs it into the generative AI model.

[0955] Step 4:

[0956] The server uses a generative AI model to calculate the risk level for each location in real time, taking into account factors such as the frequency of accidents and incidents, their severity, time of day, season, and weather.

[0957] Step 5:

[0958] The server quantifies the calculated risk and overlays it on map information, continuously updating the generated risk map in real time.

[0959] Step 6:

[0960] Your device periodically retrieves your GPS location, which by default is every minute.

[0961] Step 7:

[0962] The terminal transmits the acquired location information to the server.

[0963] Step 8:

[0964] The server receives the user's location information and compares it with a real-time risk map.

[0965] Step 9:

[0966] The server generates an alert when the user approaches a dangerous area, including the type of danger, the numerical danger level, and recommended actions.

[0967] Step 10:

[0968] The server sends the generated alert to the user's device, and depending on the settings, it can also notify family members' devices at the same time.

[0969] Step 11:

[0970] The device processes the alert received from the server and notifies the user of the alert by displaying it on the screen or by audio notification.

[0971] Step 12:

[0972] The device uses a camera and microphone to analyze the user's facial expressions and tone of voice, and sends the analysis data to a server.

[0973] Step 13:

[0974] The server analyzes the user's emotional state received from the emotion engine.

[0975] Step 14:

[0976] The server recalculates the risk level and adjusts the alert content and notification method based on the user's emotional state. For example, if the user is nervous, it generates an earlier and more emphasized alert.

[0977] Step 15:

[0978] The server then sends the adjusted alert back to the user's device.

[0979] Step 16:

[0980] The device will notify the user of the received alert in an appropriate manner.

[0981] Step 17:

[0982] Users can check their current location and danger information based on notifications on their device and take recommended actions, such as avoiding dangerous areas or evacuating to a safe location.

[0983] Example 2

[0984] 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."

[0985] Conventional systems for collecting information on accidents and incidents have difficulty predicting risk in real time, making it impossible to immediately ensure the safety of users. Furthermore, they only provided a uniform notification method without taking into account the user's emotional state, making it impossible to provide appropriate warnings according to their state of tension or relaxation. Furthermore, they lacked a function to notify the user's family members, leaving a need for improved safety.

[0986] 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.

[0987] In this invention, the server includes a data acquisition unit, a unit for acquiring data such as the current time of day, season, and weather conditions, a risk assessment unit using an artificial intelligence model that integrates the accident and incident information collected by the data acquisition unit and the acquired data and analyzes them in real time, a unit for quantifying the risk calculated by the risk assessment unit and overlaying it on map information, a unit for acquiring device location information, a unit for comparing the device location information with the risk level and generating a warning when the device approaches a dangerous area, a unit for notifying the device of the warning, and a unit for recognizing the user's emotional state using emotion analysis means installed in the device and adjusting the content and notification method of the warning. This allows the user to receive an immediate warning when facing danger and enables personalized notifications based on the user's emotional state. Safety can also be improved by notifying the user's family members.

[0988] "Data acquisition means" refers to the means for collecting various data, including accident and incident information.

[0989] A "generative AI model" is an artificial intelligence model that analyzes integrated data in real time and assesses the level of risk.

[0990] The "risk assessment means" is a means of analyzing collected data using a generative AI model and quantifying the risk level at each location.

[0991] The "means for overlaying on map information" is a means for overlaying the calculated risk level on map data.

[0992] "Means for obtaining location information" refers to means for periodically obtaining location information from the user's terminal.

[0993] The "means for generating a warning" is a means for generating a warning to notify the user of the type of danger and its details when the user's terminal approaches a dangerous area.

[0994] The "means for notifying a warning" is a means for sending the generated warning to the user's terminal.

[0995] An "emotion analysis means" is a means for analyzing a user's facial expression and tone of voice to recognize their emotional state.

[0996] A "public API" is an API provided by public organizations such as police, fire departments, and meteorological agencies, and is a data interface used to obtain information on accidents and incidents, weather data, etc.

[0997] "Terminal" refers to a mobile communication device carried by a user for sending and receiving location information and emotional state.

[0998] This invention is a system that collects accident and incident information in real time and uses that information to provide appropriate warnings to users. This system functions by linking together a server, terminals, users, and an emotion engine.

[0999] Basic System Configuration

[1000] The server first obtains accident and incident information from public APIs such as those of police, fire departments, and meteorological agencies using a data acquisition method. It then separately obtains weather data, seasons, time periods, and other information. This information is then stored in an integrated database. Specifically, cloud services (such as AWS or Google Cloud Platform) are used. The collected data is stored in this integrated database, normalized, and prepared for analysis.

[1001] The server analyzes the information stored in the integrated database in real time using an artificial intelligence model (e.g., GPT-4). This model calculates the risk level for each location, taking into account factors such as past accident and incident data, the current time of day, season, and weather. The calculated risk level is quantified and overlaid on map information. The Google Maps API is used to render the map information. The risk map is updated in real time to continually reflect the latest information.

[1002] The device periodically obtains the user's current GPS location information and sends it to a server. This is done using a mobile device such as a smartphone. The server compares the received location information with a risk map to determine whether the user is approaching a dangerous area. If it determines that the user is approaching a dangerous area, the server generates a warning. This warning includes the type of danger, the risk level, recommended actions, etc. The generated warning is immediately sent to the user's device. This notification method is push notification.

[1003] The device is also equipped with an emotion analysis function. It uses the camera and microphone to analyze the user's facial expressions and tone of voice, and sends the results to a server using technologies such as OpenCV and Google Cloud Speech-to-Text. The server uses these analysis results to recognize the user's emotional state and adjust the content and notification method of the alert. For example, if the user is nervous, the alert will be emphasized and the notification will be sent earlier. Also, if the user is relaxed, the frequency and intensity of the alert will be adjusted.

[1004] Specific examples

[1005] Example 1: Use on your commute route

[1006] A user opens the app on their way to work. The device obtains their GPS location and sends it to the server. The server calculates a predicted risk level based on the current time of day (morning commute), weather (rain), and information on accidents and incidents around the commute route, and displays it on a map. If the user approaches a dangerous area on their commute route, a warning is generated and sent to the device. For example, the device could not only display a text message saying, "There is a dangerous area on your commute route. Please be careful," but also use vibration and audio notifications to further amplify the warning. Additionally, a prompt message like, "Please tell me how to notify me if I approach a dangerous area on my commute. It's morning commute time and the weather is rainy." could be used.

[1007] Example 2: Child monitoring function

[1008] When the user (parent) is playing outside, the user opens the app and turns on the monitoring function. The device (child's device) obtains GPS location information and sends it to the server. The server predicts the level of danger based on the latest incident information and weather conditions in the area. The server quantifies the level of danger in real time based on the evening hours when traffic accidents are most common in the child's area. If the child approaches a dangerous area, a warning is generated and a notification is also sent to the parent's device. The parent's device is displayed with the text "Your child is approaching an area with a high incidence of traffic accidents. Please contact us immediately and ensure their safety." Additionally, a prompt such as "How can I be notified if my child approaches a dangerous area? It is evening and the weather is clear" can also be used.

[1009] This system allows users to receive real-time warnings when approaching dangerous areas, preventing accidents and incidents before they occur. In addition, the introduction of an emotion engine enables more personalized warning notifications tailored to the user's emotional state, further enhancing user safety.

[1010] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1011] Step 1: Collect data

[1012] The server collects accident and incident information from public APIs such as police, fire departments, and meteorological agencies.

[1013] Input: Accident and incident information from public APIs, weather data, time of day, and seasonal data.

[1014] Specific operation: Periodically send GET requests to each public API and receive response data in JSON format. For example, access the weather API to get weather information.

[1015] Output: A dataset containing collected accident and incident information and weather data.

[1016] Step 2: Integrate the data

[1017] The server stores the collected data in an integrated database.

[1018] Input: Collected accident and incident information, weather data, time of day, and seasonal data.

[1019] Specific behavior: Normalizes the received data and stores it in a SQL database, for example, inserting JSON data into the appropriate table.

[1020] Output: Data stored in the consolidated database.

[1021] Step 3: Preprocessing the data

[1022] The server extracts the necessary data from the integrated database and converts it into a format suitable for analysis.

[1023] Input: Various data in the integrated database.

[1024] Specific operations: Data cleansing, removing outliers, and imputing missing data (e.g., imputing missing values ​​with the mean).

[1025] Output: The preprocessed dataset.

[1026] Step 4: Risk analysis

[1027] The server uses a generative AI model to analyze the pre-processed data in real time and calculate the risk level.

[1028] Input: Preprocessed accident and incident information, weather data, time of day, and season data.

[1029] Specific operation: Input data into a generative AI model to quantify the risk level of each location. For example, run a predictive model based on similar past data.

[1030] Output: A dataset quantifying the risk at each location.

[1031] Step 5: Generate a risk map

[1032] The server overlays the calculated risk level onto map information to visualize it.

[1033] Input: Quantified risk data, map information.

[1034] Specific operation: Uses Google Maps API to display danger levels on a map in different colors. For example, high-danger areas are displayed in red.

[1035] Output: Hazard map.

[1036] Step 6: Get GPS location

[1037] The device periodically obtains the user's current GPS location information and sends it to the server.

[1038] Input: Location information from the device's GPS module.

[1039] Specific operation: The device uses the smartphone's GPS sensor to obtain location information and sends the encrypted data to a server via HTTPS.

[1040] Output: The location data sent to the server.

[1041] Step 7: Matching location information with risk maps

[1042] The server compares the received location information with a risk map to determine whether the user is approaching a dangerous area.

[1043] Input: Received location information, risk map.

[1044] Specific operation: The location information is compared with a risk map to determine whether there are any high-risk areas within a specified distance.

[1045] Output: Information on approaching dangerous areas.

[1046] Step 8: Generate and notify alerts

[1047] If the server determines that the user is approaching a dangerous area, it immediately generates a warning and notifies the user's terminal.

[1048] Input: Information about approaching a dangerous area.

[1049] Specific operation: Create a warning message and send it to the device using push notification. For example, send a message saying "You are approaching a dangerous area. Be careful."

[1050] Output: The alert notification sent to the user's device.

[1051] Step 9: Capturing Emotional State

[1052] The device uses a camera and microphone to recognize the user's emotional state and transmits the results to a server.

[1053] Input: The user's facial expressions and tone of voice.

[1054] Specific operations: Facial expression recognition using OpenCV and voice analysis using Google Cloud Speech-to-Text.

[1055] Output: Emotion recognition data sent to the server.

[1056] Step 10: Adjusting Emotion-Based Alerts

[1057] The server adjusts the content of the warning and notification method based on the emotion recognition data it receives.

[1058] Input: Emotion recognition data, warning notification data.

[1059] Specific behavior: Adjust the intensity and timing of alerts depending on the user's emotional state. For example, send an earlier and more emphasized alert to a user who is nervous.

[1060] Output: Reconciled alert notification data.

[1061] (Application example 2)

[1062] 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."

[1063] Conventional accident and incident information collection systems have limitations in real-time risk calculation and alert functions, and from the user's perspective, they have had issues with not being able to provide notifications that are adequately tailored to the urgency or individual situation. Furthermore, no previous systems have been able to provide alerts that take into account the user's emotional state, which has led to a lack of effective means of improving safety.

[1064] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1065] In this invention, the server includes a data collection means, a means for acquiring data such as the current time of day, season, and weather, a risk calculation means using a generative AI model that integrates the accident and incident information collected by the data collection means and the acquired data and analyzes them in real time, a means for quantifying the risk calculated by the risk calculation means and overlaying it on map information, a means for acquiring user location information, a means for comparing the user location information with the risk level and generating an alert when the user approaches a dangerous area, an emotion analysis means for recognizing the user's emotional state using a camera and microphone mounted on the terminal and adjusting the alert content and notification method based on the emotional state, and a means for notifying the user of the alert to the user's terminal. This enables real-time and personalized alert notifications when the user approaches a dangerous area, thereby improving safety.

[1066] "Data collection means" refers to the means for obtaining accident and incident information and other related data.

[1067] "Means for acquiring data such as the current time zone, season, and weather" refers to means for collecting information about the time zone, season, and weather at that time.

[1068] A "means for calculating risk using a generative AI model" is a means for utilizing a generative AI model that is used to integrate collected data, analyze it in real time, and calculate risk.

[1069] "Means for overlaying on map information" refers to a means for converting the calculated risk level into a number and displaying it overlaid on a map.

[1070] "Means for obtaining user location information" refers to means for obtaining the user's current location.

[1071] "Means for generating an alert" means a means for automatically generating a warning when a user approaches a hazardous area.

[1072] The "emotion analysis means" is a means for recognizing the emotional state of the user using a camera or microphone installed in the terminal, and adjusting the alert content and notification method based on the emotional state.

[1073] "Means for notifying the user's device" refers to means for sending the generated alert to the user's mobile device or the like.

[1074] The present invention is a system that collects accident and incident information in real time and issues appropriate warnings to users based on that information, and functions in cooperation with a server, terminal, user, and emotion analysis engine.

[1075] The server uses data collection methods to obtain accident and incident information from public APIs such as those of the police, fire department, and meteorological agency. It also separately obtains weather data, seasons, time of day, and other information. This information is stored in an integrated database and analyzed in real time by a generative AI model. The AI ​​model considers factors such as past accident and incident data, the current time of day, season, and weather, and quantifies the risk level of each location. The calculated risk level is quantified and overlaid on map information. The risk map is updated in real time and linked to the user's location information.

[1076] The device periodically obtains the user's current GPS location information and sends it to the server. When the server receives the user's location information, it compares it with a risk map. If it determines that the user is approaching a dangerous area, it generates an alert. This alert includes the type of danger, the risk level, recommended actions, and more. The generated alert is immediately sent to the user's device. Furthermore, depending on the settings, alerts may also be sent to family members' devices.

[1077] The emotion analysis engine has the ability to recognize the user's emotional state and adjust the alert content and notification method based on that. It uses the device's built-in camera and microphone to analyze the user's facial expressions and tone of voice. The analysis results are sent to the server and fed back to the risk level calculation means. The server recalculates the risk level based on the user's emotional state received from the emotion analysis engine, and adjusts the alert content and notification method as necessary. For example, if the user is nervous, the alert will be sent earlier. Also, if the user is relaxed, the frequency and intensity of notifications will be adjusted.

[1078] Specific examples

[1079] Example 1: Use on your commute route

[1080] A user opens the app on their way to work. The device obtains their GPS location and sends it to the server. The server calculates a predicted risk level based on the current time of day (morning commute), weather (rain), and information on accidents and incidents along the commute route, and displays it on a map. If the user approaches a dangerous area on their commute route (for example, an area where many traffic accidents have occurred in the past), an alert is generated and sent to the device. The device also uses its camera and microphone to analyze the user's emotional state and sends that data to the server. The server analyzes the emotional data and, if the user is nervous, emphasizes the alert content and notifies the user of appropriate recommended actions. The device receives the alert and notifies the user, "There is a dangerous area on your commute route. Please be careful." The user pays attention and either avoids the area or passes through it safely.

[1081] Example 2: Child monitoring function

[1082] When a user (parent) is playing outside, the user opens the app and turns on the monitoring function. The device (child's device) obtains GPS location information and sends it to the server. The server predicts the level of danger based on the latest incident information and weather conditions in the area. The server quantifies the level of danger in real time based on the evening hours when traffic accidents are most common in the child's area. If the child approaches a dangerous area, an alert is generated and a notification is also sent to the parent's device. The user (parent) can use the device's camera and microphone to send their emotional state to the server and receive recommended actions to take to respond more appropriately.

[1083] Prompt Sentence Examples

[1084] Prompt to calculate risk based on user location:

[1085] text

[1086] Based on the data collected from the API used, analyze accident and incident information within 1 kilometer of the user's current location and calculate the risk level.

[1087] Alert generation prompts taking into account sentiment analysis results:

[1088] text

[1089] If the user's emotional state is tense, generate appropriate alerts with earlier and more detailed information about the alert.

[1090] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1091] Step 1:

[1092] The server obtains accident and incident information from public APIs using data collection methods. Specifically, it sends requests to the APIs of the police, fire department, meteorological agency, etc. to obtain the latest accident and incident information.

[1093] Input: API request

[1094] Output: Accident and incident information dataset

[1095] Step 2:

[1096] The server also acquires additional data such as the current time of day, season, and weather, which allows for analysis that takes into account a variety of factors along with accident and incident data.

[1097] Input: API request for time, season, and weather data

[1098] Output: Time, season, weather data

[1099] Step 3:

[1100] The server aggregates all the collected data and performs real-time analysis using a generative AI model, which calculates the risk level for each location.

[1101] Input: Accident / incident data, time, season, weather data

[1102] Output: Risk level at each location

[1103] Step 4:

[1104] The server quantifies the calculated risk and overlays it on map information, resulting in a user-friendly visualization of the risk.

[1105] Input: Risk level at each location

[1106] Output: Map information showing risk levels

[1107] Step 5:

[1108] The device periodically obtains the user's current GPS location and sends it to the server for subsequent analysis.

[1109] Input: GPS location

[1110] Output: Location information sent to the server

[1111] Step 6:

[1112] The server compares the user's location against the risk map and generates an alert when the user approaches a risk area, including the type of risk, a risk level number, and recommended actions.

[1113] Input: User location, risk map

[1114] Output: Alert

[1115] Step 7:

[1116] The device uses the built-in camera and microphone to analyze the user's emotional state and sends the data to a server, where an emotion analysis engine is used for emotion analysis.

[1117] Input: Camera video, microphone audio

[1118] Output: Emotion data

[1119] Step 8:

[1120] The server recalculates the risk level based on the emotion data received from the emotion analysis engine and adjusts the alert content and notification method, for example, emphasizing the alert content if the user is nervous.

[1121] Input: Emotion data, existing risk data

[1122] Output: Throttled alerts

[1123] Step 9:

[1124] The device will notify the user of the generated alert, and depending on the settings, the same alert will also be sent to family devices.

[1125] Input: alert

[1126] Output: Notification to user and family devices

[1127] 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.

[1128] 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.

[1129] 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.

[1130] [Fourth embodiment]

[1131] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1132] 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.

[1133] 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).

[1134] 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.

[1135] 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.

[1136] 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).

[1137] 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.

[1138] 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.

[1139] 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.

[1140] 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.

[1141] 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.

[1142] 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.

[1143] 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."

[1144] This invention is a system that collects accident and incident information in real time and issues appropriate warnings to users based on that information. This system functions in cooperation with a server, terminals, and users.

[1145] The server first obtains accident and incident information from public APIs such as those of the police, fire department, and meteorological agency using data collection methods. It also separately obtains weather data, seasons, time of day, and other information. This information is stored in an integrated database and analyzed in real time by a generative AI model. The AI ​​model considers factors such as past accident and incident data, the current time of day, season, and weather, and quantifies the risk level of each location. The calculated risk level is then quantified and overlaid on map information. The risk map is updated in real time and linked to the user's location information.

[1146] The device periodically obtains the user's current GPS location information and sends it to the server. When the server receives the user's location information, it compares it with a risk map. If it determines that the user is approaching a dangerous area, it generates an alert. This alert includes the type of danger, the risk level, recommended actions, and more. The generated alert is immediately sent to the user's device. Furthermore, depending on the settings, alerts may also be sent to family members' devices.

[1147] Users can check the danger information for the location based on the notification on their device. The alert contains detailed information about the dangerous area, allowing users to take appropriate action. For example, if they are approaching a dangerous area on their way to work, they can check the alert and choose an alternative route. Similarly, if a parent receives an alert that their child is approaching a dangerous area while playing outside, they can immediately contact their child or guide them to a safe location.

[1148] Example 1: Use on your commute route

[1149] A user opens the app on their way to work. The device obtains GPS location information and sends it to the server. The server calculates a predicted risk level based on the current time of day (morning commute), weather (rain), and information on accidents and incidents around the commute route, and displays it on a map. If the user approaches a dangerous area on their commute route (for example, an area where many traffic accidents have occurred in the past), an alert is generated and sent to the device. The device receives the alert and notifies the user, "There is a dangerous area on your commute route. Please be careful." The user then pays attention and either avoids the area or passes through it safely.

[1150] Example 2: Child monitoring function

[1151] When the child is playing outside, the user (parent) opens the app and turns on the monitoring function. The device (child's device) obtains GPS location information and sends it to the server. The server predicts the level of danger based on the latest incident information and weather conditions in the area. The server quantifies the level of danger in real time based on the evening hours when traffic accidents are most common in the child's area. If the child approaches a dangerous area, an alert is generated and a notification is also sent to the parent's device. The device notifies the parent, "Your child is approaching a dangerous area. Please check." The user (parent) can contact the child or guide them to a safe location.

[1152] This system allows users to receive real-time warnings when they approach dangerous areas, making it possible to prevent accidents and incidents.In addition, by simultaneously notifying family members of the alert, it encourages quick response and further increases the user's safety.

[1153] The processing flow will be explained below.

[1154] Step 1:

[1155] The server accesses public APIs from the police, fire department, meteorological agency, etc., to obtain accident and incident information and weather data in real time.

[1156] Step 2:

[1157] The server centralizes the acquired accident and incident information and weather data and stores them in an integrated database.

[1158] Step 3:

[1159] The server extracts the latest accident and incident data and weather data from the integrated database and inputs this into the generative AI model.

[1160] Step 4:

[1161] The server uses a generative AI model to calculate the risk level for each location in real time, taking into account factors such as the frequency of accidents and incidents, their severity, time of day, season, and weather.

[1162] Step 5:

[1163] The server quantifies the calculated risk and overlays it on map information, continuously updating the generated risk map in real time.

[1164] Step 6:

[1165] Your device periodically retrieves your GPS location, which by default is every minute.

[1166] Step 7:

[1167] The terminal transmits the acquired location information to the server.

[1168] Step 8:

[1169] The server receives the user's location information and compares it with a real-time risk map.

[1170] Step 9:

[1171] The server generates an alert when the user approaches a dangerous area, including the type of danger, the numerical danger level, and recommended actions.

[1172] Step 10:

[1173] The server sends the generated alert to the user's device, and depending on the settings, it can also notify family members' devices at the same time.

[1174] Step 11:

[1175] The device processes the alert received from the server and notifies the user of the alert by displaying it on the screen or by audio notification.

[1176] Step 12:

[1177] Users can check their current location and danger information based on notifications from their device and take recommended actions, such as avoiding dangerous areas or evacuating to a safe location.

[1178] Example 1

[1179] 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."

[1180] Conventional systems for collecting accident and incident information and notifying users have difficulty calculating the risk level in real time, making it difficult to issue prompt warnings. Furthermore, they lack the functionality to simultaneously notify alerts to users and their families, resulting in inadequate emergency response. To solve these problems, the present invention provides a system for collecting data from public APIs and analyzing risk levels in real time, thereby quickly issuing warnings to users and their families.

[1181] 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.

[1182] In this invention, the server includes a data collection means, a means for acquiring data such as the current time zone, season, and weather, a risk calculation means using a generative AI model that integrates the accident and incident information collected by the data collection means and the acquired data and analyzes them in real time, a means for quantifying the risk calculated by the risk calculation means and overlaying it on map information, a means for acquiring user location information, a means for comparing the user location information with the risk and generating an alert when the user approaches a dangerous area, a means for notifying the user's device of the alert, and a means for notifying the device of related family members of the alert by the notification means, thereby enabling the user and their family members to obtain risk information in real time and take prompt action.

[1183] "Data collection means" refers to means for collecting data from multiple sources, including accident and incident information.

[1184] The "risk calculation means" is a means for integrating collected data and calculating risk in real time using a generative AI model.

[1185] The "means for quantifying the risk level and overlaying it on map information" is a means for expressing the calculated risk level in a numerical format and overlaying that information on a map.

[1186] "Means for obtaining user location information" refers to means for obtaining the user's current location from the terminal.

[1187] "Means for generating an alert" refers to a means for issuing a warning when a user approaches a dangerous area.

[1188] The "notification means" is a means for transmitting the generated alert to the terminals of the user and related family members.

[1189] A "public API" is an application programming interface provided by public institutions such as the police, fire department, and meteorological agency.

[1190] The present invention is a system that aims to prevent accidents and incidents by providing real-time warnings when users approach dangerous locations. This system functions in cooperation with a server, terminals, and users.

[1191] server

[1192] The server first uses data collection tools (e.g., Python library requests, BeautifulSoup, etc.) to obtain accident and incident information from public APIs (e.g., NASA API, OpenWeatherMap API) of the police, fire department, meteorological agency, etc. It also separately obtains weather data, seasons, time periods, etc. All obtained information is stored in an integrated database (e.g., MySQL, PostgreSQL).

[1193] The stored data is then analyzed in real time using a generative AI model (e.g., TensorFlow, PyTorch). The model calculates the risk level for each location, taking into account factors such as past accident and incident data, the current time of day, season, and weather. This risk level is then stored in a database and overlaid on map information (e.g., Google Maps API, Mapbox). This risk map is updated in real time, and as new information is added, it is reflected on the map provided to users.

[1194] Terminal

[1195] The device periodically obtains the user's current location using the smartphone's built-in GPS module. This location information is updated at regular intervals (e.g., every 5 minutes) and sent to the server. The server compares the received location information with the current risk map to determine whether the user is approaching a dangerous area.

[1196] User

[1197] Users can check the danger information for the location based on the notification on their device. The alert contains detailed information about the dangerous area, allowing users to take appropriate action. For example, if they are approaching a dangerous area on their way to work, they can check the alert and choose an alternative route. Similarly, if a parent receives an alert that their child is approaching a dangerous area while playing outside, they can immediately contact their child or guide them to a safe location.

[1198] Examples:

[1199] Use on your commute route

[1200] A user opens the app on their way to work. The device obtains GPS location information and sends it to the server. The server calculates a predicted risk level based on the current time of day (morning commute), weather (rain), and information on accidents and incidents around the commute route, and displays it on a map. If the user approaches a dangerous area on their commute route (for example, an area where many traffic accidents have occurred in the past), an alert is generated and sent to the device. The device receives the alert and notifies the user, "There is a dangerous area on your commute route. Please be careful." The user then pays attention and either avoids the area or passes through it safely.

[1201] Child monitoring function

[1202] When the child is playing outside, the user (parent) opens the app and turns on the monitoring function. The device (child's device) obtains GPS location information and sends it to the server. The server predicts the level of danger based on the latest incident information and weather conditions in the area. The server quantifies the level of danger in real time based on the evening hours when traffic accidents are most common in the child's area. If the child approaches a dangerous area, an alert is generated and a notification is also sent to the parent's device. The device notifies the parent, "Your child is approaching a dangerous area. Please check." The user (parent) can contact the child or guide them to a safe location.

[1203] Prompt Sentence Examples

[1204] Use on your commute route

[1205] "It's morning commute time and you're heading to your destination in the rain. Please check to see if there are any dangerous areas along your route."

[1206] Child monitoring function

[1207] "My child is playing outside. I want to know the danger areas based on the latest incidents in the area and current weather conditions."

[1208] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1209] Step 1:

[1210] The server uses data collection tools to collect accident and incident information from public APIs (e.g., APIs of the police, fire department, and meteorological agency). The input is raw data from the API, which is parsed (analyzed) into required information (e.g., location, time, and type of accident). The output is the parsed accident information.

[1211] What it does: The server uses Python's requests library to call the OpenWeatherMap API to get current weather data, then uses BeautifulSoup to parse the data and extract the information it needs.

[1212] Step 2:

[1213] The server obtains each piece of information using a means to obtain data such as the current time, season, weather, etc. The input is raw data related to the current time, season, and weather, and the output is an organized form of this data.

[1214] Specific operation: The server obtains the current time zone from the system time, calls the Japan Meteorological Agency's API to obtain the latest weather data, and stores this information in an integrated database.

[1215] Step 3:

[1216] The server uses a generative AI model to analyze the acquired accident information, time of day, season, and weather data in real time to calculate the risk level for each location. The input is the integrated data, and the output is a quantified data of the risk level for each location.

[1217] Specific operation: The server uses a TensorFlow model to input past accident data and current weather data and quantify the risk level at each location.

[1218] Step 4:

[1219] The server overlays the calculated risk level on map information. The input is the quantified risk level data and map data, and the output is a map that visually displays the risk level.

[1220] What it does: The server uses the Google Maps API to highlight dangerous areas in red and updates the map in real time.

[1221] Step 5:

[1222] The terminal periodically obtains the user's location information using the smartphone's built-in GPS module. The input is the GPS location information, and the output is the location data sent to the server.

[1223] Specific operation: The device obtains latitude and longitude using the smartphone's GPS module and sends this to the server at regular intervals (e.g., every 5 minutes).

[1224] Step 6:

[1225] The server compares the received user location information with the risk map to determine whether the user is approaching a dangerous area. The input is the user location information and the risk map, and the output is the approach determination result.

[1226] Specific operation: The server retrieves the user's location information and danger map from the database and compares them to determine whether the user is in a danger zone.

[1227] Step 7:

[1228] If the server determines that the user is approaching a dangerous area, it generates an alert and notifies the user's device. The input is the approach judgment result, and the output is the generated alert and notification.

[1229] Specific operation: The server generates an alert stating, "You are approaching a dangerous area. Please check the app for details," and sends it as a push notification to the user's smartphone.

[1230] Step 8:

[1231] The terminal notifies the user of the alerts received from the server. The input is the alert from the server, and the output is the notification to the user.

[1232] What happens: The device receives a push notification and displays a message to the user saying, "There is a dangerous area on your commute route. Please be careful."

[1233] (Application example 1)

[1234] 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."

[1235] To ensure the safety of automated machinery and workers in factories, it is important to collect, analyze, and notify accident and abnormality information in real time. However, conventional systems have difficulty in providing comprehensive safety management in real time, and accidents are likely to occur when workers or machines approach dangerous areas. To solve this problem, the present invention aims to provide a system that utilizes a generative AI model to analyze accident and incident information in factories in real time, calculate the level of danger, and issue appropriate warnings to automated machinery and workers.

[1236] 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.

[1237] In this invention, the server includes a data acquisition means, a means for acquiring data such as the current time of day, season, and weather, a risk calculation means using a generative AI model that integrates the accident and incident information collected by the data acquisition means and the acquired data and analyzes it in real time, a means for quantifying the risk calculated by the risk calculation means and overlaying it on map information, a means for acquiring user location information, a means for comparing the user's location information with the risk and generating an alert when the user approaches a dangerous area, a means for notifying the user's terminal of the alert, a means for periodically acquiring location information of automatic machines and workers in the factory, analyzing it in coordination with the accident and incident information in the factory collected by the data acquisition means, calculating the risk and overlaying it on map information, and a means for generating an alert when the dangerous area is approached and notifying the terminals of machines and workers in the factory. This enables real-time safety management of accidents and abnormalities in the factory.

[1238] "Data acquisition means" refers to the means of collecting accident and abnormality information from automated machinery, sensors, cameras, GPS modules, etc. within the factory.

[1239] "Means for obtaining data such as the current time of day, season, and weather" refers to means for obtaining environmental information such as the current time of day, season, and weather using external APIs or databases.

[1240] A "generative AI model" is an artificial intelligence model that analyzes collected data in real time and compares it with past data to calculate the level of risk.

[1241] The "risk calculation means" is a means of quantifying the risk of accidents or abnormalities at each location using a generative AI model.

[1242] The "means for overlaying on map information" is a means for displaying the calculated risk level overlaid on map information.

[1243] "Means for obtaining user location information" refers to means for obtaining the current location of a user or an automated machine using a GPS module or the like.

[1244] The "means for generating an alert" is a means for generating a warning when approaching a dangerous area based on the risk calculation result and the user's location information.

[1245] "Means for notifying the user's device" refers to the means for notifying the generated alert to the user's device, such as a smartphone or tablet.

[1246] The "means for periodically acquiring location information of automated machines and workers in a factory" refers to a means for acquiring location information of various machines and workers in a factory at regular intervals and transmitting it to a server.

[1247] "Means for analyzing in coordination with information on accidents and incidents within factories" refers to a means for analyzing information on accidents and abnormalities that occur within factories in combination with the location information of automated machines and workers.

[1248] The present invention aims to provide a system for managing the safety of automated machinery and workers in a factory by collecting and analyzing information on accidents and abnormalities in real time and issuing appropriate warnings. Specific embodiments for realizing this system are described below.

[1249] Data Acquisition Method

[1250] The server collects information about accidents and abnormalities from various sensors, cameras, and GPS modules within the factory. This information is collected using a sensor network and IoT devices. For example, temperature sensors, vibration sensors, and cameras are used to detect chemical leaks and machine malfunctions. This data is then stored in an integrated database on the server side.

[1251] Environmental data acquisition method

[1252] The server utilizes external APIs and internal databases to obtain environmental information such as the current time of day, season, and weather. This includes data obtained through the Japan Meteorological Agency and other public APIs. Weather information and seasonal variations are also collected, as they may affect specific hazard levels.

[1253] Risk calculation method

[1254] The server analyzes the collected data in real time using a generative AI model and compares it with past data to calculate the risk level. For example, it uses past accident data and current environmental data as input to generate a risk score for each location. This is done using machine learning frameworks such as TensorFlow and PyTorch.

[1255] Map information overlay method

[1256] The calculated risk level is overlaid on map information by the server. This map information is based on the layout of the factory and is updated in real time. Dangerous areas are color-coded to make them visually clear.

[1257] User location information acquisition method

[1258] Each terminal (automated machine or worker's mobile device) periodically acquires its current location using a GPS module and sends it to the server, allowing the server to constantly track the location of the automated machine or worker.

[1259] Alert generation method

[1260] The server compares the user's location information with the risk level and generates an alert if the user is approaching a dangerous area. The alert includes the type of danger, the risk level, and recommended actions.

[1261] Alert notification method

[1262] The generated alerts are instantly sent to automated machines and workers in the factory, such as smartphones, tablets, and even robot control systems, using push notification services such as Firebase Cloud Messaging.

[1263] Examples of concrete examples and prompts

[1264] Example 1: A chemical leak is detected in a factory and workers are approaching the area.

[1265] Prompt: "You are approaching a chemical spill area. Please leave the area immediately."

[1266] Example 2: When a worker is approaching the forklift's driving area.

[1267] Prompt: "You are approaching a forklift area. Please be careful."

[1268] This system will strengthen safety management within the factory and enable real-time response to accidents and abnormalities.

[1269] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1270] Step 1: Collect information through data acquisition methods

[1271] The server collects data on accidents and abnormalities from sensors, cameras, and GPS modules within the factory. This includes collecting environmental data such as temperature and vibration through the sensor's API and detecting abnormalities through camera video analysis.

[1272] Input: Raw data from sensors, cameras, and GPS modules (temperature, vibration, video, location information)

[1273] Output: Collected accident and abnormality data

[1274] Step 2: Collect information through environmental data acquisition methods

[1275] The server retrieves environmental data such as the current time zone, season, and weather from external APIs and databases. This is a process of retrieving weather and time data using public APIs.

[1276] Input: Environment data from public API

[1277] Output: Current time zone, season, weather, etc.

[1278] Step 3: Data integration and analysis

[1279] The server stores the data acquired in steps 1 and 2 in an integrated database and analyzes it in real time using a generative AI model, which predicts the risk level based on past and current data.

[1280] Input: Historical data in the integrated database and current data obtained

[1281] Output: Risk score (numerical value) for each location

[1282] Step 4: Overlaying risk information onto the map

[1283] The server overlays the calculated risk level on the map information of the factory, which displays dangerous areas on the map in different colors.

[1284] Input: Risk score, factory map information

[1285] Output: Map with risk overlay

[1286] Step 5: Get the user's location

[1287] The terminal (automated machine or worker's portable device) periodically obtains its current location using a GPS module and transmits it to the server.

[1288] Input: Location information from the GPS module

[1289] Output: Current location data of the user

[1290] Step 6: Alert Generation

[1291] The server compares the user's current location with the risk level and generates an alert if the user is approaching a risk area, including the type of risk, a risk score, and recommended actions.

[1292] Input: User's current location data, map with risk level overlay

[1293] Output: Warning message (alert)

[1294] Step 7: Alert Notification

[1295] The generated alerts are immediately sent to the user's device using a push notification service, specifically, Firebase Cloud Messaging, which sends notifications to smartphones and tablets.

[1296] Input: Warning message (alert)

[1297] Output: Notification to user device

[1298] The above processing steps enable real-time safety management for accidents and abnormalities within a factory. As a concrete example, the following prompt sentence is used:

[1299] Example 1: A chemical leak is detected in a factory and workers are approaching the area.

[1300] "Approaching a chemical spill area. Leave the area immediately."

[1301] Example 2: When a worker is approaching the forklift's driving area.

[1302] "You are approaching a forklift driving area. Use caution."

[1303] 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.

[1304] This invention is a system that collects accident and incident information in real time and uses that information to provide appropriate warnings to users. This system functions through the mutual cooperation of a server, terminals, users, and an emotion engine.

[1305] Basic System Configuration

[1306] The server first obtains accident and incident information from public APIs such as those of the police, fire department, and meteorological agency using data collection methods. It also separately obtains weather data, seasons, time of day, and other information. This information is stored in an integrated database and analyzed in real time by a generative AI model. The AI ​​model considers factors such as past accident and incident data, the current time of day, season, and weather, and quantifies the risk level of each location. The calculated risk level is then quantified and overlaid on map information. The risk map is updated in real time and linked to the user's location information.

[1307] The device periodically obtains the user's current GPS location information and sends it to the server. When the server receives the user's location information, it compares it with a risk map. If it determines that the user is approaching a dangerous area, it generates an alert. This alert includes the type of danger, the risk level, recommended actions, and more. The generated alert is immediately sent to the user's device. Furthermore, depending on the settings, alerts may also be sent to family members' devices.

[1308] Emotion engine integration

[1309] The emotion engine recognizes the user's emotional state and adjusts the alert content and notification method based on that. It uses the device's built-in camera and microphone to analyze the user's facial expressions and tone of voice. The analysis results are sent to the server and fed back to the risk calculation means.

[1310] The server recalculates the risk level based on the user's emotional state received from the emotion engine and adjusts the content and notification method of the alert as necessary. For example, if the user is nervous, the server will send an alert earlier. If the user is relaxed, the server will adjust the frequency and intensity of notifications.

[1311] Specific examples

[1312] Example 1: Use on your commute route

[1313] A user opens the app on their way to work. The device obtains GPS location information and sends it to the server. The server calculates a predicted risk level based on the current time of day (morning commute), weather (rain), and information on accidents and incidents around the commute route, and displays it on a map. If the user approaches a dangerous area on their commute route (for example, an area where many traffic accidents have occurred in the past), an alert is generated and sent to the device.

[1314] The device also uses a camera and microphone to analyze the user's emotional state and sends the data to the server. The server analyzes the emotional data and, if the user is nervous, highlights the alert and notifies the user of the appropriate recommended action. When the device receives the alert, it notifies the user, "There is a dangerous area on your commute route. Please be careful." The user can then take care and either avoid the area or pass through it safely.

[1315] Example 2: Child monitoring function

[1316] When a user (parent) is playing outside, the user opens the app and turns on the monitoring function. The device (child's device) obtains GPS location information and sends it to the server. The server predicts the level of danger based on the latest incident information and weather conditions in the area. The server quantifies the level of danger in real time based on the evening hours when traffic accidents are most common in the child's area. If the child approaches a dangerous area, an alert is generated and a notification is also sent to the parent's device. The user (parent) can use the device's camera and microphone to send their emotional state to the server and receive recommended actions to take to respond more appropriately.

[1317] This system allows users to receive real-time warnings when approaching dangerous locations, preventing accidents and incidents before they occur. In addition, the introduction of an emotion engine enables more personalized alert notifications tailored to the user's emotional state, further enhancing user safety.

[1318] The processing flow will be explained below.

[1319] Step 1:

[1320] The server accesses public APIs from the police, fire department, meteorological agency, etc., to obtain real-time accident and incident information and weather data.

[1321] Step 2:

[1322] The server centralizes the acquired accident and incident information and weather data and stores them in an integrated database.

[1323] Step 3:

[1324] The server extracts the latest accident and incident data and weather data from the integrated database and inputs it into the generative AI model.

[1325] Step 4:

[1326] The server uses a generative AI model to calculate the risk level for each location in real time, taking into account factors such as the frequency of accidents and incidents, their severity, time of day, season, and weather.

[1327] Step 5:

[1328] The server quantifies the calculated risk and overlays it on map information, continuously updating the generated risk map in real time.

[1329] Step 6:

[1330] Your device periodically retrieves your GPS location, which by default is every minute.

[1331] Step 7:

[1332] The terminal transmits the acquired location information to the server.

[1333] Step 8:

[1334] The server receives the user's location information and compares it with a real-time risk map.

[1335] Step 9:

[1336] The server generates an alert when the user approaches a dangerous area, including the type of danger, the numerical danger level, and recommended actions.

[1337] Step 10:

[1338] The server sends the generated alert to the user's device, and depending on the settings, it can also notify family members' devices at the same time.

[1339] Step 11:

[1340] The device processes the alert received from the server and notifies the user of the alert by displaying it on the screen or by audio notification.

[1341] Step 12:

[1342] The device uses a camera and microphone to analyze the user's facial expressions and tone of voice, and sends the analysis data to a server.

[1343] Step 13:

[1344] The server analyzes the user's emotional state received from the emotion engine.

[1345] Step 14:

[1346] The server recalculates the risk level and adjusts the alert content and notification method based on the user's emotional state. For example, if the user is nervous, it generates an earlier and more emphasized alert.

[1347] Step 15:

[1348] The server then sends the adjusted alert back to the user's device.

[1349] Step 16:

[1350] The device will notify the user of the received alert in an appropriate manner.

[1351] Step 17:

[1352] Users can check their current location and danger information based on notifications on their device and take recommended actions, such as avoiding dangerous areas or evacuating to a safe location.

[1353] Example 2

[1354] 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."

[1355] Conventional systems for collecting information on accidents and incidents have difficulty predicting risk in real time, making it impossible to immediately ensure the safety of users. Furthermore, they only provided a uniform notification method without taking into account the user's emotional state, making it impossible to provide appropriate warnings according to their state of tension or relaxation. Furthermore, they lacked a function to notify the user's family members, leaving a need for improved safety.

[1356] 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.

[1357] In this invention, the server includes a data acquisition unit, a unit for acquiring data such as the current time of day, season, and weather conditions, a risk assessment unit using an artificial intelligence model that integrates the accident and incident information collected by the data acquisition unit and the acquired data and analyzes them in real time, a unit for quantifying the risk calculated by the risk assessment unit and overlaying it on map information, a unit for acquiring device location information, a unit for comparing the device location information with the risk level and generating a warning when the device approaches a dangerous area, a unit for notifying the device of the warning, and a unit for recognizing the user's emotional state using emotion analysis means installed in the device and adjusting the content and notification method of the warning. This allows the user to receive an immediate warning when facing danger and enables personalized notifications based on the user's emotional state. Safety can also be improved by notifying the user's family members.

[1358] "Data acquisition means" refers to the means for collecting various data, including accident and incident information.

[1359] A "generative AI model" is an artificial intelligence model that analyzes integrated data in real time and assesses the level of risk.

[1360] The "risk assessment means" is a means of analyzing collected data using a generative AI model and quantifying the risk level at each location.

[1361] The "means for overlaying on map information" is a means for overlaying the calculated risk level on map data.

[1362] "Means for obtaining location information" refers to means for periodically obtaining location information from the user's terminal.

[1363] The "means for generating a warning" is a means for generating a warning to notify the user of the type of danger and its details when the user's terminal approaches a dangerous area.

[1364] The "means for notifying a warning" is a means for sending the generated warning to the user's terminal.

[1365] An "emotion analysis means" is a means for analyzing a user's facial expression and tone of voice to recognize their emotional state.

[1366] A "public API" is an API provided by public organizations such as police, fire departments, and meteorological agencies, and is a data interface used to obtain information on accidents and incidents, weather data, etc.

[1367] "Terminal" refers to a mobile communication device carried by a user for sending and receiving location information and emotional state.

[1368] This invention is a system that collects accident and incident information in real time and uses that information to provide appropriate warnings to users. This system functions by linking together a server, terminals, users, and an emotion engine.

[1369] Basic System Configuration

[1370] The server first obtains accident and incident information from public APIs such as those of police, fire departments, and meteorological agencies using a data acquisition method. It then separately obtains weather data, seasons, time periods, and other information. This information is then stored in an integrated database. Specifically, cloud services (such as AWS or Google Cloud Platform) are used. The collected data is stored in this integrated database, normalized, and prepared for analysis.

[1371] The server analyzes the information stored in the integrated database in real time using an artificial intelligence model (e.g., GPT-4). This model calculates the risk level for each location, taking into account factors such as past accident and incident data, the current time of day, season, and weather. The calculated risk level is quantified and overlaid on map information. The Google Maps API is used to render the map information. The risk map is updated in real time to continually reflect the latest information.

[1372] The device periodically obtains the user's current GPS location information and sends it to a server. This is done using a mobile device such as a smartphone. The server compares the received location information with a risk map to determine whether the user is approaching a dangerous area. If it determines that the user is approaching a dangerous area, the server generates a warning. This warning includes the type of danger, the risk level, recommended actions, etc. The generated warning is immediately sent to the user's device. This notification method is push notification.

[1373] The device is also equipped with an emotion analysis function. It uses the camera and microphone to analyze the user's facial expressions and tone of voice, and sends the results to a server using technologies such as OpenCV and Google Cloud Speech-to-Text. The server uses these analysis results to recognize the user's emotional state and adjust the content and notification method of the alert. For example, if the user is nervous, the alert will be emphasized and the notification will be sent earlier. Also, if the user is relaxed, the frequency and intensity of the alert will be adjusted.

[1374] Specific examples

[1375] Example 1: Use on your commute route

[1376] A user opens the app on their way to work. The device obtains their GPS location and sends it to the server. The server calculates a predicted risk level based on the current time of day (morning commute), weather (rain), and information on accidents and incidents around the commute route, and displays it on a map. If the user approaches a dangerous area on their commute route, a warning is generated and sent to the device. For example, the device could not only display a text message saying, "There is a dangerous area on your commute route. Please be careful," but also use vibration and audio notifications to further amplify the warning. Additionally, a prompt message like, "Please tell me how to notify me if I approach a dangerous area on my commute. It's morning commute time and the weather is rainy." could be used.

[1377] Example 2: Child monitoring function

[1378] When the user (parent) is playing outside, the user opens the app and turns on the monitoring function. The device (child's device) obtains GPS location information and sends it to the server. The server predicts the level of danger based on the latest incident information and weather conditions in the area. The server quantifies the level of danger in real time based on the evening hours when traffic accidents are most common in the child's area. If the child approaches a dangerous area, a warning is generated and a notification is also sent to the parent's device. The parent's device is displayed with the text "Your child is approaching an area with a high incidence of traffic accidents. Please contact us immediately and ensure their safety." Additionally, a prompt such as "How can I be notified if my child approaches a dangerous area? It is evening and the weather is clear" can also be used.

[1379] This system allows users to receive real-time warnings when approaching dangerous areas, preventing accidents and incidents before they occur. In addition, the introduction of an emotion engine enables more personalized warning notifications tailored to the user's emotional state, further enhancing user safety.

[1380] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1381] Step 1: Collect data

[1382] The server collects accident and incident information from public APIs such as police, fire departments, and meteorological agencies.

[1383] Input: Accident and incident information from public APIs, weather data, time of day, and seasonal data.

[1384] Specific operation: Periodically send GET requests to each public API and receive response data in JSON format. For example, access the weather API to get weather information.

[1385] Output: A dataset containing collected accident and incident information and weather data.

[1386] Step 2: Integrate the data

[1387] The server stores the collected data in an integrated database.

[1388] Input: Collected accident and incident information, weather data, time of day, and seasonal data.

[1389] Specific behavior: Normalizes the received data and stores it in a SQL database, for example, inserting JSON data into the appropriate table.

[1390] Output: Data stored in the consolidated database.

[1391] Step 3: Preprocessing the data

[1392] The server extracts the necessary data from the integrated database and converts it into a format suitable for analysis.

[1393] Input: Various data in the integrated database.

[1394] Specific operations: Data cleansing, removing outliers, and imputing missing data (e.g., imputing missing values ​​with the mean).

[1395] Output: The preprocessed dataset.

[1396] Step 4: Risk analysis

[1397] The server uses a generative AI model to analyze the pre-processed data in real time and calculate the risk level.

[1398] Input: Preprocessed accident and incident information, weather data, time of day, and season data.

[1399] Specific operation: Input data into a generative AI model to quantify the risk level of each location. For example, run a predictive model based on similar past data.

[1400] Output: A dataset quantifying the risk at each location.

[1401] Step 5: Generate a risk map

[1402] The server overlays the calculated risk level onto map information to visualize it.

[1403] Input: Quantified risk data, map information.

[1404] Specific operation: Uses Google Maps API to display danger levels on a map in different colors. For example, high-danger areas are displayed in red.

[1405] Output: Hazard map.

[1406] Step 6: Get GPS location

[1407] The device periodically obtains the user's current GPS location information and sends it to the server.

[1408] Input: Location information from the device's GPS module.

[1409] Specific operation: The device uses the smartphone's GPS sensor to obtain location information and sends the encrypted data to a server via HTTPS.

[1410] Output: The location data sent to the server.

[1411] Step 7: Matching location information with risk maps

[1412] The server compares the received location information with a risk map to determine whether the user is approaching a dangerous area.

[1413] Input: Received location information, risk map.

[1414] Specific operation: The location information is compared with a risk map to determine whether there are any high-risk areas within a specified distance.

[1415] Output: Information on approaching dangerous areas.

[1416] Step 8: Generate and notify alerts

[1417] If the server determines that the user is approaching a dangerous area, it immediately generates a warning and notifies the user's terminal.

[1418] Input: Information about approaching a dangerous area.

[1419] Specific operation: Create a warning message and send it to the device using push notification. For example, send a message saying "You are approaching a dangerous area. Be careful."

[1420] Output: The alert notification sent to the user's device.

[1421] Step 9: Capturing Emotional State

[1422] The device uses a camera and microphone to recognize the user's emotional state and transmits the results to a server.

[1423] Input: The user's facial expressions and tone of voice.

[1424] Specific operations: Facial expression recognition using OpenCV and voice analysis using Google Cloud Speech-to-Text.

[1425] Output: Emotion recognition data sent to the server.

[1426] Step 10: Adjusting Emotion-Based Alerts

[1427] The server adjusts the content of the warning and notification method based on the emotion recognition data it receives.

[1428] Input: Emotion recognition data, warning notification data.

[1429] Specific behavior: Adjust the intensity and timing of alerts depending on the user's emotional state. For example, send an earlier and more emphasized alert to a user who is nervous.

[1430] Output: Reconciled alert notification data.

[1431] (Application example 2)

[1432] 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."

[1433] Conventional accident and incident information collection systems have limitations in real-time risk calculation and alert functions, and from the user's perspective, they have had issues with not being able to provide notifications that are adequately tailored to the urgency or individual situation. Furthermore, no previous systems have been able to provide alerts that take into account the user's emotional state, which has led to a lack of effective means of improving safety.

[1434] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1435] In this invention, the server includes a data collection means, a means for acquiring data such as the current time of day, season, and weather, a risk calculation means using a generative AI model that integrates the accident and incident information collected by the data collection means and the acquired data and analyzes them in real time, a means for quantifying the risk calculated by the risk calculation means and overlaying it on map information, a means for acquiring user location information, a means for comparing the user location information with the risk level and generating an alert when the user approaches a dangerous area, an emotion analysis means for recognizing the user's emotional state using a camera and microphone mounted on the terminal and adjusting the alert content and notification method based on the emotional state, and a means for notifying the user of the alert to the user's terminal. This enables real-time and personalized alert notifications when the user approaches a dangerous area, thereby improving safety.

[1436] "Data collection means" refers to the means for obtaining accident and incident information and other related data.

[1437] "Means for acquiring data such as the current time zone, season, and weather" refers to means for collecting information about the time zone, season, and weather at that time.

[1438] A "means for calculating risk using a generative AI model" is a means for utilizing a generative AI model that is used to integrate collected data, analyze it in real time, and calculate risk.

[1439] "Means for overlaying on map information" refers to a means for converting the calculated risk level into a number and displaying it overlaid on a map.

[1440] "Means for obtaining user location information" refers to means for obtaining the user's current location.

[1441] "Means for generating an alert" means a means for automatically generating a warning when a user approaches a hazardous area.

[1442] The "emotion analysis means" is a means for recognizing the emotional state of the user using a camera or microphone installed in the terminal, and adjusting the alert content and notification method based on the emotional state.

[1443] "Means for notifying the user's device" refers to means for sending the generated alert to the user's mobile device or the like.

[1444] The present invention is a system that collects accident and incident information in real time and issues appropriate warnings to users based on that information, and functions in cooperation with a server, terminal, user, and emotion analysis engine.

[1445] The server uses data collection methods to obtain accident and incident information from public APIs such as those of the police, fire department, and meteorological agency. It also separately obtains weather data, seasons, time of day, and other information. This information is stored in an integrated database and analyzed in real time by a generative AI model. The AI ​​model considers factors such as past accident and incident data, the current time of day, season, and weather, and quantifies the risk level of each location. The calculated risk level is quantified and overlaid on map information. The risk map is updated in real time and linked to the user's location information.

[1446] The device periodically obtains the user's current GPS location information and sends it to the server. When the server receives the user's location information, it compares it with a risk map. If it determines that the user is approaching a dangerous area, it generates an alert. This alert includes the type of danger, the risk level, recommended actions, and more. The generated alert is immediately sent to the user's device. Furthermore, depending on the settings, alerts may also be sent to family members' devices.

[1447] The emotion analysis engine has the ability to recognize the user's emotional state and adjust the alert content and notification method based on that. It uses the device's built-in camera and microphone to analyze the user's facial expressions and tone of voice. The analysis results are sent to the server and fed back to the risk level calculation means. The server recalculates the risk level based on the user's emotional state received from the emotion analysis engine, and adjusts the alert content and notification method as necessary. For example, if the user is nervous, the alert will be sent earlier. Also, if the user is relaxed, the frequency and intensity of notifications will be adjusted.

[1448] Specific examples

[1449] Example 1: Use on your commute route

[1450] A user opens the app on their way to work. The device obtains their GPS location and sends it to the server. The server calculates a predicted risk level based on the current time of day (morning commute), weather (rain), and information on accidents and incidents along the commute route, and displays it on a map. If the user approaches a dangerous area on their commute route (for example, an area where many traffic accidents have occurred in the past), an alert is generated and sent to the device. The device also uses its camera and microphone to analyze the user's emotional state and sends that data to the server. The server analyzes the emotional data and, if the user is nervous, emphasizes the alert content and notifies the user of appropriate recommended actions. The device receives the alert and notifies the user, "There is a dangerous area on your commute route. Please be careful." The user pays attention and either avoids the area or passes through it safely.

[1451] Example 2: Child monitoring function

[1452] When a user (parent) is playing outside, the user opens the app and turns on the monitoring function. The device (child's device) obtains GPS location information and sends it to the server. The server predicts the level of danger based on the latest incident information and weather conditions in the area. The server quantifies the level of danger in real time based on the evening hours when traffic accidents are most common in the child's area. If the child approaches a dangerous area, an alert is generated and a notification is also sent to the parent's device. The user (parent) can use the device's camera and microphone to send their emotional state to the server and receive recommended actions to take to respond more appropriately.

[1453] Prompt Sentence Examples

[1454] Prompt to calculate risk based on user location:

[1455] text

[1456] Based on the data collected from the API used, analyze accident and incident information within 1 kilometer of the user's current location and calculate the risk level.

[1457] Alert generation prompts taking into account sentiment analysis results:

[1458] text

[1459] If the user's emotional state is tense, generate appropriate alerts with earlier and more detailed information about the alert.

[1460] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1461] Step 1:

[1462] The server obtains accident and incident information from public APIs using data collection methods. Specifically, it sends requests to the APIs of the police, fire department, meteorological agency, etc. to obtain the latest accident and incident information.

[1463] Input: API request

[1464] Output: Accident and incident information dataset

[1465] Step 2:

[1466] The server also acquires additional data such as the current time of day, season, and weather, which allows for analysis that takes into account a variety of factors along with accident and incident data.

[1467] Input: API request for time, season, and weather data

[1468] Output: Time, season, weather data

[1469] Step 3:

[1470] The server aggregates all the collected data and performs real-time analysis using a generative AI model, which calculates the risk level for each location.

[1471] Input: Accident / incident data, time, season, weather data

[1472] Output: Risk level at each location

[1473] Step 4:

[1474] The server quantifies the calculated risk and overlays it on map information, resulting in a user-friendly visualization of the risk.

[1475] Input: Risk level at each location

[1476] Output: Map information showing risk levels

[1477] Step 5:

[1478] The device periodically obtains the user's current GPS location and sends it to the server for subsequent analysis.

[1479] Input: GPS location

[1480] Output: Location information sent to the server

[1481] Step 6:

[1482] The server compares the user's location against the risk map and generates an alert when the user approaches a risk area, including the type of risk, a risk level number, and recommended actions.

[1483] Input: User location, risk map

[1484] Output: Alert

[1485] Step 7:

[1486] The device uses the built-in camera and microphone to analyze the user's emotional state and sends the data to a server, where an emotion analysis engine is used for emotion analysis.

[1487] Input: Camera video, microphone audio

[1488] Output: Emotion data

[1489] Step 8:

[1490] The server recalculates the risk level based on the emotion data received from the emotion analysis engine and adjusts the alert content and notification method, for example, emphasizing the alert content if the user is nervous.

[1491] Input: Emotion data, existing risk data

[1492] Output: Throttled alerts

[1493] Step 9:

[1494] The device will notify the user of the generated alert, and depending on the settings, the same alert will also be sent to family devices.

[1495] Input: alert

[1496] Output: Notification to user and family devices

[1497] 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.

[1498] 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.

[1499] 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.

[1500] 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.

[1501] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1502] 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.

[1503] 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).

[1504] 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.

[1505] 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."

[1506] 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.

[1507] 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).

[1508] 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.

[1509] 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.

[1510] 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.

[1511] 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.

[1512] 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.

[1513] 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.

[1514] 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.

[1515] 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.

[1516] 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.

[1517] 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.

[1518] The following is further disclosed regarding the above embodiment.

[1519] (Claim 1)

[1520] data collection means;

[1521] A means of obtaining data such as the current time of day, season, and weather, and

[1522] A risk calculation means that uses a generative AI model that integrates the accident and incident information collected by the data collection means and the acquired data and analyzes them in real time;

[1523] a means for converting the risk calculated by the risk calculation means into a numerical value and overlaying the numerical value on map information;

[1524] A means for obtaining user location information;

[1525] means for comparing the user's location information with the risk level and generating an alert when the user approaches a risk area;

[1526] The system includes a means for notifying a user of the alert at a terminal.

[1527] (Claim 2)

[1528] The system of claim 1 , further comprising means for notifying the alert to terminals of associated family members of the user.

[1529] (Claim 3)

[1530] The system of claim 1, further comprising means for obtaining the accident and incident information from a public API such as the police, fire department, or meteorological agency.

[1531] "Example 1"

[1532] (Claim 1)

[1533] data collection means;

[1534] A means of obtaining data such as the current time of day, season, and weather, and

[1535] A risk calculation means that uses a generative AI model that integrates the accident and incident information collected by the data collection means and the acquired data and analyzes them in real time;

[1536] a means for converting the risk calculated by the risk calculation means into a numerical value and overlaying the numerical value on map information;

[1537] A means for obtaining user location information;

[1538] means for comparing the user's location information with the risk level and generating an alert when the user approaches a risk area;

[1539] means for notifying a user terminal of the alert;

[1540] means for notifying the alert to a terminal of a related family member by the notification means;

[1541] A system including:

[1542] (Claim 2)

[1543] The system of claim 1 , further comprising means for obtaining the accident and incident information from a public API.

[1544] (Claim 3)

[1545] 2. The system of claim 1, wherein the means for obtaining the user's location information includes means for periodically transmitting the user's location information to a server.

[1546] "Application Example 1"

[1547] (Claim 1)

[1548] A data acquisition means;

[1549] A means of obtaining data such as the current time of day, season, and weather, and

[1550] A risk calculation means that uses a generative AI model that integrates the accident and incident information collected by the data acquisition means and the acquired data and analyzes them in real time;

[1551] a means for converting the risk calculated by the risk calculation means into a numerical value and overlaying the numerical value on map information;

[1552] A means for obtaining user location information;

[1553] means for comparing the user's location information with the risk level and generating an alert when the user approaches a risk area;

[1554] means for notifying a user terminal of the alert;

[1555] a means for periodically acquiring location information of automated machines and workers in the factory, analyzing the information in cooperation with the accident and incident information in the factory collected by the data acquisition means, calculating the degree of danger, and overlaying the calculated information on map information;

[1556] The system includes a means for generating an alert when the dangerous area is approached and notifying the machines and workers' terminals in the factory.

[1557] (Claim 2)

[1558] The system of claim 1 , further comprising means for notifying the alert to terminals of associated family members of the user.

[1559] (Claim 3)

[1560] The system of claim 1, further comprising means for obtaining the accident and incident information from a public API such as the police, fire department, or meteorological agency.

[1561] "Example 2: Combining Emotion Engines"

[1562] (Claim 1)

[1563] A data acquisition means;

[1564] A means of obtaining data such as the current time of day, season, and weather conditions;

[1565] A risk assessment means using an artificial intelligence model that integrates the accident and incident information collected by the data acquisition means and the acquired data and analyzes them in real time;

[1566] a means for converting the degree of risk calculated by the risk assessment means into a numerical value and overlaying the numerical value on map information;

[1567] A means for acquiring location information of the terminal;

[1568] means for comparing the location information of the terminal with the degree of danger and generating a warning when the terminal approaches a dangerous area;

[1569] means for notifying a terminal of the warning;

[1570] The system includes a means for recognizing the emotional state of the user using emotion analysis means installed in the terminal and adjusting the content of the warning and the notification method.

[1571] (Claim 2)

[1572] The system of claim 1 , further comprising means for notifying said alert to terminals of associated family members of the user.

[1573] (Claim 3)

[1574] The system of claim 1, further comprising means for obtaining the accident and incident information from public APIs such as police, fire department, and meteorological agencies.

[1575] "Application example 2 when combining emotion engines"

[1576] (Claim 1)

[1577] data collection means;

[1578] A means of obtaining data such as the current time of day, season, and weather, and

[1579] A risk calculation means that uses a generative AI model that integrates the accident and incident information collected by the data collection means and the acquired data and analyzes them in real time;

[1580] a means for converting the risk calculated by the risk calculation means into a numerical value and overlaying the numerical value on map information;

[1581] A means for obtaining user location information;

[1582] means for comparing the user's location information with the risk level and generating an alert when the user approaches a risk area;

[1583] an emotion analysis means for recognizing the emotional state of a user using a camera or microphone mounted on the terminal and adjusting the alert content and notification method based on the emotional state;

[1584] The system includes a means for notifying a user of the alert at a terminal.

[1585] (Claim 2)

[1586] The system of claim 1 , further comprising means for notifying the alert to terminals of associated family members of the user.

[1587] (Claim 3)

[1588] The system of claim 1, further comprising means for obtaining the accident and incident information from a public API such as the police, fire department, or meteorological agency. [Explanation of symbols]

[1589] 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. data collection means; A means of obtaining data such as the current time of day, season, and weather, and a risk calculation means that uses a generative AI model that integrates the accident and incident information collected by the data collection means and the acquired data and analyzes them in real time; a means for converting the risk calculated by the risk calculation means into a numerical value and overlaying the numerical value on map information; A means for obtaining user location information; means for comparing the user's location information with the risk level and generating an alert when the user approaches a risk area; The system includes a means for notifying a user of the alert at a terminal.

2. The system of claim 1 , further comprising means for notifying the alert to terminals of related family members of the user.

3. The system according to claim 1 , further comprising means for acquiring the accident / incident information from a public API such as the police, fire department, or meteorological agency.

Images