System

Abstract

A system is provided.SOLUTION: A navigation system for a vehicle, comprising: means for acquiring an identifier of an intersection; means for acquiring past accident data from a police agency; means for acquiring current location information; means for acquiring current date and time and weather information; means for analyzing accident risk based on the past accident data and the current date and time and weather information; and means for notifying a driver based on the analyzed accident risk.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional vehicle navigation systems are unable to properly alert drivers, especially at intersections where accidents frequently occur, resulting in situations where accidents are more likely to occur. These systems lack the ability to provide useful warnings to drivers due to insufficient risk analysis that takes into account past accident data and current environmental conditions (such as weather and time of day). Therefore, more effective methods are needed to reduce accident risks at specific high-risk intersections. [Means for solving the problem]

[0005] The present invention provides a system that effectively alerts drivers by integrating a generative AI that incorporates past accident data and current environmental conditions into a vehicle's navigation system. The system includes a means for acquiring intersection identifiers, a means for acquiring past accident data from the National Police Agency, a means for acquiring current location information, a means for acquiring current date, time, and weather information, a means for analyzing accident risk based on the past accident data, the current date, time, and weather information, and a means for notifying the driver based on the analyzed accident risk. In particular, the system uses generative AI to analyze accident risk and provides the driver with detailed notifications based on the risk level. This allows the driver to pay appropriate attention when approaching a specific intersection, thereby significantly reducing the risk of an accident.

[0006] A "navigation system" is a device or software installed in a vehicle that determines the current location and provides route guidance to the destination.

[0007] An "identifier" is a unique ID or code that identifies a particular intersection or point.

[0008] The "National Police Agency" is a national or local police agency that collects and manages accident data and public safety information.

[0009] "Accident data" refers to information about traffic accidents that have occurred in the past, and mainly includes the date and time of the accident, the location, the type of accident, and the extent of the damage.

[0010] "Generative AI" is a type of artificial intelligence technology that uses machine learning algorithms to analyze, predict, and solve problems.

[0011] "Location information" is information indicating the current geographical location of a vehicle obtained from sensor data such as GPS.

[0012] "Environmental conditions" refers to data that indicates the situation in which the vehicle is currently located, and specifically includes the current weather, date and time, etc.

[0013] "Risk analysis" is the process of assessing the likelihood of an accident occurring under specific circumstances based on collected data.

[0014] "Notification" is the means by which the analysis results are communicated to the driver, and may include visual or audio alerts. [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 effectively alerts drivers by integrating a generative AI that incorporates past accident data and current environmental conditions into a vehicle navigation system. The following is a specific example.

[0037] A natural language description of the program's operation

[0038] 1. Acquisition of initial data

[0039] The device obtains its current location and the identifier of the specific intersection, which is automatically obtained based on GPS data.

[0040] 2. Acquisition of accident data

[0041] The server receives the intersection identifier sent from the device and calls the National Police Agency's API to retrieve past accident data, including the number of accidents, type of accident, date and time of the accident, and details of the damage caused by the accident.

[0042] 3. Obtaining the current environmental conditions

[0043] The device obtains the current date, time, and weather information. The weather information is obtained using a weather forecast API, and specifically includes the current weather (sunny, cloudy, rainy, snowy, etc.) and temperature.

[0044] 4. Perform a risk analysis

[0045] The server uses a generative AI to perform risk analysis based on the acquired past accident data and current environmental conditions. The generative AI uses this data as input to predict the accident risk at a specific intersection. The prediction is output as a risk level on a scale of 1 to 10.

[0046] 5. Sending risk notifications

[0047] The device will then notify the driver based on the analysis results. The specific content of the notification will vary depending on the risk level.

[0048] If the risk level is 7 or higher, a message will be displayed saying, "Caution: This intersection has a high risk of accidents. Be careful, especially in bad weather."

[0049] If the risk level is between 4 and 7, the message "Warning: Many accidents have occurred at this intersection in the past. Please drive carefully" will be displayed.

[0050] If the risk level is below 4, the message "This intersection is relatively safe" will be displayed.

[0051] Specific examples

[0052] When the user approaches a specific intersection (e.g., intersection ID "abc123"), the device obtains the user's current location information and recognizes the intersection's identifier "abc123." The device then uses the recognized identifier to send a request to the server. The server then obtains accident data from the past five years via the National Police Agency's API, as well as the current date and time (e.g., 14:00, October 12, 2023) and weather information (e.g., cloudy).

[0053] Based on the acquired data, the server uses a generative AI to perform a risk analysis and determines that the risk level of the intersection is 7. Because the risk level is high, the device notifies the user with the message, "Caution: This intersection has a high risk of accidents. Be careful, especially in bad weather."

[0054] It is expected that users will receive this notification and pay particular attention when driving, thereby reducing the risk of accidents at intersections.

[0055] The processing flow will be explained below.

[0056] Step 1:

[0057] The device obtains its current location information from GPS, detects that it has approached a specific intersection, and identifies the identifier of the detected intersection.

[0058] Step 2:

[0059] The device sends the intersection identifier it has identified to the server, which includes the intersection ID and the current timestamp.

[0060] Step 3:

[0061] The server receives the intersection identifier and calls the National Police Agency's API to retrieve past accident data for that intersection, including the number of accidents, type of accident, date and time of the accident, and details of the damage caused by the accident.

[0062] Step 4:

[0063] The device obtains the current date, time, and weather information. Weather information is obtained using the weather forecast API, including the current weather (sunny, cloudy, rainy, snowy, etc.) and temperature.

[0064] Step 5:

[0065] The server uses the AI ​​generator to perform risk analysis based on the acquired past accident data, current date, time, and weather information. The AI ​​uses this data as input to predict the accident risk at a specific intersection. The predicted result is output as a risk level on a scale of 1 to 10.

[0066] Step 6:

[0067] The device receives the analysis results and generates notification content according to the risk level.

[0068] Step 7:

[0069] The device generates and displays notifications to the driver, which vary depending on the risk level.

[0070] If the risk level is 7 or higher, a message will be displayed saying, "Caution: This intersection has a high risk of accidents. Be careful, especially in bad weather."

[0071] If the risk level is between 4 and 7, the message "Warning: Many accidents have occurred at this intersection in the past. Please drive carefully" will be displayed.

[0072] If the risk level is below 4, the message "This intersection is relatively safe" will be displayed.

[0073] Step 8:

[0074] Users receive notifications and decide whether to drive with extra caution, and take measures such as slowing down if necessary.

[0075] Example 1

[0076] 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."

[0077] Current vehicle navigation systems lack mechanisms to effectively notify drivers of accident risks at specific intersections. In particular, risk analysis that takes into account past accident data and current environmental conditions is lacking. Therefore, effective means to promote safe driving are needed.

[0078] 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.

[0079] In this invention, the server includes a means for acquiring current location information, a means for acquiring an intersection identifier, and a means for acquiring past accident data from an external database, thereby enabling the server to analyze the accident risk at a specific intersection based on the past accident data and the current environmental conditions, and effectively notify the driver of the result.

[0080] A "vehicle navigation system" is an electronic system that provides map information and route guidance to a driver.

[0081] "Means for obtaining current location information" refers to a device or software for identifying the current location of a vehicle using a GPS module or the like.

[0082] The "means for acquiring an intersection identifier" is a device or software for acquiring a unique identification (ID) for identifying an intersection.

[0083] The "means for obtaining past accident data from an external database" refers to a communications interface and associated software for obtaining accident data from an external source such as the National Police Agency.

[0084] "Means for obtaining current date, time and weather information" refers to a device or software for obtaining the current date, time and weather conditions from calendar information or weather forecast APIs.

[0085] The "means for analyzing accident risk" is software that predicts and assesses accident risk using a generative AI model based on past accident data and current environmental conditions.

[0086] "Means for notifying the driver" means a device or software for presenting a visual or audio warning message to the driver based on the risk of an accident.

[0087] A "generative AI model" refers to an artificial intelligence algorithm that makes predictions or generates based on specific input data.

[0088] This invention is a system that incorporates past accident data and current environmental conditions into a vehicle's navigation system and uses a generative AI model to effectively alert the driver. Specific implementation methods are described in detail below.

[0089] Initial setup and data acquisition

[0090] The device obtains its current location using a GPS module, which pinpoints the vehicle's exact location, and automatically obtains an intersection identifier by matching it with an internal mapping database. This identifier uniquely identifies a particular intersection.

[0091] Acquisition of past accident data

[0092] The device generates a request with the acquired intersection identifier and sends it to the server. Based on the received request, the server calls an external database (for example, the National Police Agency's API) to acquire past accident data. This data includes the number of past accidents, the type of accident, the date and time of the accident, details of the damage caused by the accident, etc. The acquired accident data is stored in an internal database.

[0093] Get current environmental conditions

[0094] The device retrieves the system date and time to determine the current date and time. In addition, it calls the weather forecast API to obtain current weather information (e.g., sunny, cloudy, rainy, snowy, etc.) and temperature. This information is important to reflect real-time environmental conditions.

[0095] Performing risk analysis

[0096] The server compiles the acquired past accident data and current environmental conditions and inputs them into a generative AI model. This generative AI model is constructed using, for example, a deep learning algorithm. The server uses the generative AI model to predict the accident risk at a specific intersection on a scale of 1 to 10. The predicted result is evaluated as a risk level and sent to the device.

[0097] Driver risk notification

[0098] The device determines the notification message to the driver based on the risk level received as a result of the analysis. The notification content varies depending on the risk level as follows:

[0099] If the risk level is 7 or higher, the message "Caution: There is a high risk of accidents at this intersection. Be careful, especially in bad weather." will be displayed.

[0100] If the risk level is between 4 and 6: The message "Warning: This intersection has had many accidents in the past. Please drive carefully" will be displayed.

[0101] If the risk level is 3 or lower: The message "This intersection is relatively safe" will be displayed.

[0102] The device notifies the driver of these messages visually and audibly, allowing them to sense danger in advance and drive safely.

[0103] Specific examples

[0104] When the user approaches a specific intersection (e.g., intersection ID "abc123"), the device obtains the current location information and recognizes the intersection identifier "abc123." The device uses the recognized identifier to send a request to the server. The server obtains accident data from the past five years via an external database API, and also obtains the current date and time (e.g., 14:00, October 12, 2023) and weather information (e.g., cloudy).

[0105] Based on the acquired data, the server performs a risk analysis using a generative AI model and determines that the risk level of the intersection is 7. Because the risk level is high, the device notifies the user with a message saying, "Caution: This intersection has a high risk of accidents. Please be especially careful in bad weather." The user is expected to receive this notification and pay particular attention when driving, thereby reducing the risk of accidents at intersections.

[0106] Prompt Sentence Examples

[0107] To predict the accident risk at a specific intersection, use a generative AI model to analyze past accident data and current weather information. Intersection ID: abc123, Current Date and Time: October 12, 2023, 14:00, Current Weather: Cloudy. Output the risk level on a scale of 1 to 10.

[0108] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0109] Step 1:

[0110] The device obtains the current location.

[0111] Input: Data obtained using a GPS module.

[0112] Output: Current latitude and longitude information.

[0113] Specific behavior:

[0114] The device will activate its built-in GPS module and obtain its current location information.

[0115] The acquired latitude and longitude information is stored in temporary memory within the device.

[0116] Step 2:

[0117] The terminal obtains an identifier for a particular intersection.

[0118] Input: Current latitude and longitude information.

[0119] Output: Intersection identifier (e.g. intersection ID "abc123").

[0120] Specific behavior:

[0121] The device checks its internal mapping database to obtain the intersection identifier that corresponds to the current latitude and longitude.

[0122] The acquired intersection identifier is stored in memory for subsequent processing.

[0123] Step 3:

[0124] The terminal generates a request including the intersection identifier and sends it to the server.

[0125] Input: Intersection identifier.

[0126] Output: The request to the server.

[0127] Specific behavior:

[0128] The terminal generates a request in HTTP format that includes the intersection identifier.

[0129] Send the generated request to the server.

[0130] Step 4:

[0131] The server retrieves past accident data from an external database.

[0132] Input: A request containing an intersection identifier.

[0133] Output: Historical accident data.

[0134] Specific behavior:

[0135] The server analyzes the received request and extracts the intersection identifier.

[0136] The server calls the National Police Agency's API to obtain past accident data for the relevant intersection identifier.

[0137] The acquired accident data is stored in an internal database.

[0138] Step 5:

[0139] The device retrieves the current date, time, and weather information.

[0140] Input: Current date and time, Weather API.

[0141] Output: Current weather information (e.g. sunny, cloudy, rainy, snowy, etc.) and temperature.

[0142] Specific behavior:

[0143] The device obtains the current date and time using the system's built-in clock.

[0144] Call the weather forecast API to get current weather information and temperature.

[0145] The acquired weather information is stored in memory.

[0146] Step 6:

[0147] The server inputs past accident data and current environmental conditions into a generative AI model.

[0148] Input: Past accident data, current date and time, current weather information.

[0149] Output: Accident risk level (1 to 10).

[0150] Specific behavior:

[0151] The server compiles past accident data, the current date and time, and weather information.

[0152] The compiled data is fed into a generative AI model.

[0153] A generative AI model analyzes accident risk and predicts risk levels.

[0154] A risk level is obtained as a prediction result and sent to the terminal as necessary.

[0155] Step 7:

[0156] The device notifies the driver based on the analysis results.

[0157] Input: Risk level.

[0158] Output: A warning message to be displayed to the driver.

[0159] Specific behavior:

[0160] The terminal determines a message according to the received risk level.

[0161] If the risk level is 7 or higher: Display the message "Caution: This intersection has a high risk of accidents. Be careful, especially in bad weather."

[0162] If the risk level is between 4 and 6: Display the message "Warning: Many accidents have occurred at this intersection in the past. Please drive carefully."

[0163] If the risk level is 3 or lower: Display the message "This intersection is relatively safe."

[0164] The determined message is notified to the driver visually and audibly.

[0165] (Application example 1)

[0166] 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."

[0167] Although conventional vehicle navigation systems take into account current location and weather information, they lack the functionality to integrate past traffic accident data for risk analysis. This makes it difficult to provide appropriate risk warnings based on past accident data at intersections or specific locations. Furthermore, there is a need to utilize generative AI for risk analysis to perform more accurate traffic risk assessments in real time.

[0168] 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.

[0169] In this invention, the server includes means for acquiring intersection identifiers, means for acquiring past accident data, means for acquiring current location information, means for acquiring current date and time and weather information, means for analyzing traffic risks based on the past accident data, the current date and time and weather information, and means for notifying the driver based on the analyzed traffic risks. This makes it possible to analyze traffic risks at intersections or specific locations in real time for the driver and provide a risk assessment that integrates past data and current environmental conditions using a generation AI.

[0170] An "intersection identifier" is a code or number that uniquely identifies a particular intersection.

[0171] "Past accident data" refers to data on traffic accidents that have occurred in the past at specific locations or intersections, and includes the date and time of the accident, the type of accident, and the extent of the damage.

[0172] "Current location information" is data indicating the current location of the vehicle, and is usually obtained using a location information system such as GPS.

[0173] The "current date and time" is data indicating the date and time at which the vehicle is currently located.

[0174] "Weather information" is data that indicates the current weather conditions, and specifically includes weather such as sunny, cloudy, rainy, and snowy, as well as temperature and humidity.

[0175] "Traffic risk" is an index that indicates the degree of possibility of a traffic accident occurring at a particular location or intersection.

[0176] "Generative AI" is a type of artificial intelligence that autonomously analyzes and predicts based on acquired data, and refers to a model that provides the optimal risk assessment for the input data.

[0177] The "means for notifying" refers to a means for providing a specific message or warning to the driver through audio or visual means based on the analysis results.

[0178] The present invention includes a system that analyzes traffic risks based on intersection identifiers, past accident data, current location information, current date and time, and weather information, and notifies drivers.

[0179] This system mainly uses the following hardware and software: The hardware uses the on-board computer and GPS module in the autonomous vehicle, and the software includes acquisition using Python and API, risk analysis using generative AI, and generative AI models.

[0180] Specifically, the server uses a GPS module to obtain intersection identifiers. After obtaining the location information and intersection identifiers, it calls a traffic accident data provision API to obtain past accident data. It then uses date and time information and weather forecast APIs to obtain the current date and time and weather information.

[0181] Based on this data, the generative AI model performs a traffic risk analysis. The analysis results are output as a traffic risk level, and the notification content for the driver varies depending on the risk level. If the risk is high, a warning message is displayed, and if the risk is low, a safety message is displayed.

[0182] When a driver approaches a specific intersection, the device acquires their current location information and sends it along with the intersection's identifier to a server. The server then acquires past traffic accident data via the National Police Agency's API, as well as the current date, time, and weather information. Based on the acquired data, the generative AI model performs a risk analysis and notifies the driver of the resulting traffic risk level.

[0183] As a specific example, when a driver approaches a specific intersection (e.g., intersection ID "abc123"), the device acquires the current location information and recognizes the intersection identifier "abc123." The acquired identifier is sent to the server along with accident data and weather data, and the generative AI model performs a risk analysis. If the analysis results in a risk level of 7, the device notifies the driver with a message saying, "Caution: This intersection has a high risk of accidents. Be especially careful when the weather is bad."

[0184] An example of a prompt is:

[0185] "I'm approaching intersection ID abc123. Do you have accident data for the past five years?"

[0186] "The weather report is cloudy. What is the risk level?"

[0187] As described above, the embodiments for carrying out the present invention have been specifically shown, and the invention can be effectively carried out.

[0188] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0189] Step 1:

[0190] The device obtains the vehicle's current location information using the GPS module, which provides the latitude and longitude information of the vehicle's current location (e.g., "35.6895,139.6917"), and then automatically recognizes the identifier of a specific intersection (e.g., "abc123") based on the current location.

[0191] Step 2:

[0192] The device sends the intersection identifier it recognized to the server. The server receives the intersection identifier and calls the National Police Agency's API to retrieve past accident data. This data includes the number of past accidents, the type of accident, the date and time of the accident, and details of the damage caused by the accident.

[0193] Step 3:

[0194] The server obtains the current date and time information, which gives the current year, month, date, and time (e.g., "October 12, 2023, 14:00").

[0195] Step 4:

[0196] The server uses a weather forecast API to retrieve current weather information, including the current weather (sunny, cloudy, rainy, snowy, etc.) and temperature (e.g., "cloudy, 20 degrees").

[0197] Step 5:

[0198] The server performs risk analysis using a generative AI model using past accident data, current date and time information, and weather information.Past accident data and current environmental conditions are passed to the model as input, and a traffic risk level is output as a number (e.g., "Risk Level 7").

[0199] Step 6:

[0200] The server sends the analysis results to the device. The device notifies the driver based on the received risk level. Different warning messages are displayed depending on the risk level. If the risk is high (risk level 7 or higher), a warning message is displayed stating, "Caution: This intersection has a high risk of accidents. Be careful, especially in bad weather."

[0201] Step 7:

[0202] Users can check the warning message on their device and be urged to pay particular attention while driving. By encouraging users to pay particular attention and maintain safe driving, it is expected that the risk of accidents at intersections will be reduced.

[0203] 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.

[0204] This invention is a system that effectively alerts the driver by integrating a generative AI that incorporates past accident data and current environmental conditions into a vehicle navigation system, and further combining it with an emotion engine that recognizes the driver's emotional state. The following is a specific example.

[0205] A natural language description of the program's operation

[0206] 1. Acquisition of initial data

[0207] The device obtains its current location information from GPS, detects that it has approached a specific intersection, and identifies the identifier of the detected intersection.

[0208] 2. Acquisition of accident data

[0209] The server receives the intersection identifier sent from the device and calls the National Police Agency's API to retrieve past accident data for that intersection, including the number of accidents, type of accident, date and time of the accident, and details of the damage caused by the accident.

[0210] 3. Obtaining the current environmental conditions

[0211] The device obtains the current date, time, and weather information. The weather information includes the current weather (sunny, cloudy, rainy, snowy, etc.) and temperature using the weather forecast API.

[0212] 4. Perform a risk analysis

[0213] The server uses a generation AI to perform risk analysis based on the acquired past accident data and current environmental conditions. The generation AI uses this data as input to predict the accident risk at a specific intersection. The prediction result is output as a risk level on a scale of 1 to 10.

[0214] 5. Emotional state analysis

[0215] The device activates an emotion engine to determine the driver's emotions. The emotion engine analyzes the driver's facial expressions and tone of voice through a camera and voice recognition system installed in the vehicle to evaluate the driver's emotional state. The evaluation results include the driver's stress level, attention state, and excitement level.

[0216] 6. Sending Risk Notifications

[0217] The device adjusts the notification content based on the risk analysis results and the driver's emotional state. For example, if the driver is under stress, the notification content will be more specific and detailed.

[0218] 7. Generating and Displaying Notification Content

[0219] The device will then take into account the results of the emotion engine and generate the most appropriate notification content to display to the driver. The specific notification content is as follows:

[0220] If the risk level is 7 or higher and the driver's stress level is high, a message will be displayed saying, "Warning: There is a high risk of accidents at this intersection. Please slow down and be aware of your surroundings."

[0221] If the risk level is 7 or higher and the driver's stress level is low, the system displays the message, "Caution: This intersection has a high risk of accidents. Be careful, especially in bad weather."

[0222] If the risk level is between 4 and 7, the message "Warning: Many accidents have occurred at this intersection in the past. Please drive carefully" will be displayed.

[0223] If the risk level is below 4, the message "This intersection is relatively safe" will be displayed.

[0224] Specific examples

[0225] When the user approaches a specific intersection (e.g., intersection ID "abc123"), the device obtains the current location information and recognizes the intersection's identifier "abc123." The device uses the identifier to send a request to the server. The server obtains accident data from the past five years via the National Police Agency's API, as well as the current date and time (e.g., 14:00, October 12, 2023) and weather information (e.g., cloudy).

[0226] Based on the acquired data, the server uses a generative AI to perform a risk analysis and determine the risk level as 7. At the same time, the device activates its emotion engine and determines that the driver is in a high stress state. Based on this, the device generates a notification message to the user: "Caution: There is a high risk of an accident at this intersection. Slow down and pay attention to your surroundings."

[0227] It is expected that users will receive this notification and take measures such as paying extra attention when driving and slowing down, thereby reducing the risk of accidents at intersections.

[0228] The processing flow will be explained below.

[0229] Step 1:

[0230] The device obtains its current location information from GPS, detects that it has approached a specific intersection, and identifies the identifier of the detected intersection.

[0231] Step 2:

[0232] The device sends the intersection identifier it has identified to the server, which includes the intersection ID and the current timestamp.

[0233] Step 3:

[0234] The server receives the intersection identifier and calls the National Police Agency's API to retrieve past accident data for that intersection, including the number of accidents, type of accident, date and time of the accident, and details of the damage caused by the accident.

[0235] Step 4:

[0236] The device obtains the current date, time, and weather information. Weather information is obtained using the weather forecast API to obtain the current weather (sunny, cloudy, rainy, snowy, etc.) and temperature.

[0237] Step 5:

[0238] The server uses a generation AI to perform risk analysis based on the acquired past accident data and current environmental conditions. The generation AI uses this data as input to predict the accident risk at a specific intersection. The prediction result is output as a risk level on a scale of 1 to 10.

[0239] Step 6:

[0240] The device activates an emotion engine to recognize the driver's emotional state. The emotion engine analyzes the driver's facial expressions and tone of voice through a camera and voice recognition system installed in the vehicle, and evaluates the driver's emotional state. The evaluation results include the driver's stress level, attention state, and excitement level.

[0241] Step 7:

[0242] The device adjusts the notification content based on the risk analysis results and the driver's emotional state. For example, if the driver is under stress, the notification content will be more specific and detailed.

[0243] Step 8:

[0244] The device generates and displays notifications to the driver, which vary depending on the risk level and the driver's emotional state.

[0245] If the risk level is 7 or higher and the driver's stress level is high, a message will be displayed saying, "Warning: There is a high risk of accidents at this intersection. Please slow down and be aware of your surroundings."

[0246] If the risk level is 7 or higher and the driver's stress level is low, the system displays the message, "Caution: This intersection has a high risk of accidents. Be careful, especially in bad weather."

[0247] If the risk level is between 4 and 7, the message "Warning: Many accidents have occurred at this intersection in the past. Please drive carefully" will be displayed.

[0248] If the risk level is below 4, the message "This intersection is relatively safe" will be displayed.

[0249] Step 9:

[0250] Users receive notifications and decide whether to drive with extra caution, and take measures such as slowing down if necessary.

[0251] Example 2

[0252] 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."

[0253] Conventional vehicle navigation systems have provided driver warnings based on location information and past accident data, but these alone are unable to adequately assess risk by taking into account the current environmental conditions and the driver's emotional state, making it difficult to provide effective warnings. In particular, the lack of proper consideration of the driver's emotional state can lead to incorrect decisions in stressful situations.

[0254] 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.

[0255] In this invention, the server includes means for acquiring current location information, means for acquiring intersection identifiers, means for acquiring past accident data, means for acquiring the current date and time and environmental conditions, means for analyzing the emotional state of the driver, means for analyzing the accident risk based on the past accident data, the current date and time, environmental conditions, and the emotional state of the driver, and means for notifying the driver based on the analyzed accident risk. This enables more accurate risk assessment based on the current environmental conditions and the emotional state of the driver, and warnings appropriate for each individual driver.

[0256] "Current location information" means data about the vehicle's real-time geographic location obtained by the vehicle's navigation system using location technology such as GPS.

[0257] An "intersection identifier" is an identification number or code that uniquely identifies a particular intersection.

[0258] "Past accident data" is a record of accidents that have occurred in specific areas or intersections, and includes detailed information such as the number of accidents, the type of accident, the date and time, and the extent of the damage.

[0259] "Current date and time" refers to real-time time and date information.

[0260] "Environmental conditions" is information that indicates the external environmental state, such as the current weather (sunny, cloudy, rainy, snowy, etc.) and temperature.

[0261] "Driver's emotional state" refers to the driver's psychological state, such as stress level, attention state, and excitement level, which is analyzed using sensors such as cameras and voice recognition systems.

[0262] "Accident risk" is a score or index that indicates the likelihood of an accident occurring at a particular location, assessed based on acquired data.

[0263] "Generative AI" is an artificial intelligence model that uses acquired data to predict accident risk.

[0264] "Notification" refers to a message or warning provided to the driver based on the results of risk analysis.

[0265] This invention is a system that performs risk analysis by combining past accident data, current environmental conditions, and the emotional state of the driver to improve safety in vehicle navigation systems, and provides optimal warnings to the driver.

[0266] 1. Acquisition of initial data

[0267] The device obtains current location information from a GPS module (e.g., u-blox NEO-M8N). This allows the device to determine the vehicle's current location in real time and, by comparing it with a database, detect when it has approached a specific intersection. The device then obtains the identifier of the detected intersection (e.g., ID "abc123").

[0268] 2. Acquisition of accident data

[0269] The server receives the intersection identifier sent from the device and calls the National Police Agency's API to retrieve past accident data for that intersection, including the number of accidents, type of accident, date and time of the accident, and details of damage caused by the accident.

[0270] 3. Obtaining the current environmental conditions

[0271] The device obtains the current date, time, and weather information. The weather information is obtained from the weather forecast API and includes the current weather (sunny, cloudy, rainy, snowy, etc.) and temperature.

[0272] 4. Perform a risk analysis

[0273] The server uses a generative AI model to analyze risk based on past accident data and current environmental conditions. The generative AI model (e.g., a model using TENSORFLOW® or PyTorch) takes this data as input and predicts the accident risk at a particular intersection on a scale of 1 to 10.

[0274] 5. Emotional state analysis

[0275] The device activates an emotion engine to determine the driver's emotional state. The emotion engine uses an in-car camera (e.g., a standard webcam) and a voice recognition system (e.g., a voice recognition API) to analyze the driver's facial expressions and tone of voice to assess the driver's stress level, attention state, and excitement level.

[0276] 6. Sending Risk Notifications

[0277] The device adjusts the notification content based on the results of risk analysis and the driver's emotional state. If the driver is in a high stress state, the notification content will be more specific and detailed, depending on the situation.

[0278] 7. Generating and Displaying Notification Content

[0279] The device will then take into account the results of the emotion engine to generate and display the most appropriate notification content to the driver. For example, if the risk level is 7 or higher and the driver's stress level is high, the device will display the message "Caution: There is a high risk of an accident at this intersection. Please reduce your speed and be aware of your surroundings."

[0280] Specific examples

[0281] When a user approaches a specific intersection (e.g., intersection ID "abc123"), the device obtains the user's current location and recognizes the intersection's identifier "abc123." This identifier is used to send a request to the server, which obtains accident data from the past five years via the National Police Agency's API, as well as the current date and time (e.g., 14:00, October 12, 2023) and weather information (e.g., cloudy). The server analyzes this data and determines that the risk level is 7. If the emotion engine also determines that the driver is in a high state of stress, the device generates and displays a notification to the user stating, "Caution: There is a high risk of an accident at this intersection. Slow down and pay attention to your surroundings."

[0282] Prompt Sentence Examples

[0283] "Generate notifications for drivers approaching specific intersections based on accident risk and the driver's emotional state. Use historical accident data, current weather conditions, and driver emotion analysis as data sources."

[0284] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0285] Step 1:

[0286] The device obtains current location information. Using a GPS module (e.g., u-blox NEO-M8N) as input, the device obtains the vehicle's current location data as output. The data is then processed by checking the location information against the OpenStreetMap database to determine whether the device has reached a specific intersection and extracting the intersection's identifier (e.g., ID "abc123").

[0287] Step 2:

[0288] The terminal sends the extracted intersection identifier to the server. The intersection identifier is the input and the request sent to the server is the output. The LTE module is used for communication.

[0289] Step 3:

[0290] Based on the intersection identifier received by the server, the server calls the National Police Agency's API to obtain past accident data. The input is the intersection identifier, and the output is past accident data (number of accidents, type, date and time, damage details). The data is calculated by processing the API request and response.

[0291] Step 4:

[0292] The device obtains the current date and time and weather information. The current date and time and weather forecast API are used as input, and the current weather (sunny, cloudy, rainy, snowy, etc.) and temperature are obtained as output. Data processing involves processing API requests and responses.

[0293] Step 5:

[0294] The server performs risk analysis using a generative AI model based on past accident data and current environmental conditions. The inputs are past accident data and current environmental conditions, and the output is a risk level (on a scale of 1 to 10). For data calculations, the data is input into a generative AI model (e.g., TensorFlow or PyTorch) to predict the risk level.

[0295] Step 6:

[0296] The device runs an emotion engine to analyze the driver's emotional state. It uses an in-car camera (e.g., a standard webcam) and a voice recognition system (e.g., a voice recognition API) as input, and evaluates the driver's stress level, attention state, and excitement level as output. Data calculations analyze video and audio data to determine the driver's emotional state.

[0297] Step 7:

[0298] The device adjusts the notification content based on the risk analysis results and the driver's emotional state. The inputs are the risk level and the driver's emotional state, and the output is the adjusted notification message. The data is then processed to generate an appropriate message based on the risk level and emotional state.

[0299] Step 8:

[0300] The terminal displays the generated notification content on the driver panel. The adjusted notification message is the input, and the display to the driver is the output. Specifically, the terminal sends an instruction to the display system to display the message on the panel.

[0301] (Application example 2)

[0302] 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."

[0303] Conventional vehicle navigation systems lack the functionality to warn drivers by taking into account past accident data and environmental information, and therefore do not contribute to sufficient improvements in road safety. Another problem is that they are unable to analyze the driver's emotional state in real time and provide appropriate notifications based on that state. Therefore, there is a need for a system that can provide appropriate and effective warnings when a vehicle approaches an intersection or a high-risk location.

[0304] 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.

[0305] In this invention, the server includes means for acquiring geographic information including intersections, means for acquiring past accident data from information providers, means for acquiring current location data, means for acquiring current time and weather information, means for assessing accident risk based on past accident data, current time and weather information, means for issuing a warning to the driver based on the assessed accident risk, means for assessing the emotional state of the driver, and means for adjusting the content of the warning based on the risk assessment result and the emotional state of the driver. This enables risk analysis based on past accident data and current environmental information and appropriate warnings according to the emotional state of the driver.

[0306] "Geographic information including intersections" refers to all information on a map, including the layout of roads and the locations of intersections.

[0307] "Information providers" are public or private organizations that provide past traffic accident data and weather information.

[0308] "Current location data" means information indicating the current geographic location of the vehicle, primarily obtained from GPS.

[0309] "Current time and weather information" is information including the current date, time, and weather conditions (for example, sunny, rainy, snowy, etc.).

[0310] "Means for assessing accident risk" are techniques and methods that use past accident data and current environmental conditions to analyze the possibility of an accident occurring at a specific location.

[0311] "Means of warning" refers to technologies and methods that warn drivers by voice, screen display, etc., based on the analyzed accident risk.

[0312] "Driver's emotional state" refers to the driver's mental state, including states such as stress, distraction, excitement, and relaxation.

[0313] The "means for assessing emotional state" refers to a technology or method that uses a camera or a voice recognition system to analyze the driver's facial expressions and tone of voice to assess the driver's emotional state.

[0314] "Means for adjusting the warning content" refers to a technology or method for generating and displaying a warning message with optimal content and format based on the driver's emotional state and the results of risk assessment.

[0315] A "generative AI model" is an artificial intelligence model that generates new information and results based on data, and is primarily used to analyze accident risks.

[0316] This invention is a system that effectively alerts the driver by integrating a generative AI that incorporates past accident data and current environmental conditions into a vehicle navigation system, and by combining it with an emotion engine that recognizes the driver's emotional state. Each element will be explained in detail below.

[0317] The system is composed of the following hardware and software: First, a GPS module is used to obtain the vehicle's current location data, which allows the system to identify when the vehicle will approach a specific intersection. The current date, time, and weather information is obtained using a weather forecast API, which allows the system to obtain the latest information about the driving environment.

[0318] Next, a request is sent via a REST API to obtain past accident data from an information provider (e.g., the National Police Agency). The obtained accident data includes the number of past accidents, the type of accident, the date of the accident, and details of the damage caused by the accident.

[0319] The server uses a generative AI model to assess risk based on the acquired past accident data and current environmental conditions. The generative AI model uses this data as input to predict the accident risk at a specific intersection. The prediction result is output as an accident risk level on a scale of 1 to 10.

[0320] Furthermore, a camera and voice recognition system are installed inside the vehicle to assess the driver's emotional state. The camera recognizes the driver's facial expressions, and the voice recognition system analyzes the driver's tone of voice. Based on this data, the emotion engine assesses the driver's emotional state (e.g., stress level, distraction level, excitement level, etc.).

[0321] The device adjusts the notification content based on the risk assessment result and the driver's emotional state. The notification is displayed visually and audibly to the driver. For example, if the risk level is high and the driver is stressed, the device will display a message saying, "Caution: There is a high risk of an accident at this intersection. Please reduce your speed and be aware of your surroundings."

[0322] As a specific example, when a user approaches a specific intersection (e.g., intersection ID "abc123"), the device obtains its current location information and recognizes the intersection's identifier "abc123." When the device sends a request to the server using the identifier, the server obtains accident data from the past five years via the information provider's API, as well as the current date, time, and weather information. Based on the obtained data, the server performs a risk analysis using a generative AI model and determines that the risk level is 7. At the same time, the device activates its emotion engine and determines that the driver is in a state of high stress. Based on this, the device generates a notification message to the user: "Caution: There is a high risk of accidents at this intersection. Slow down and pay attention to your surroundings."

[0323] An example of a prompt to input to a generative AI model is as follows:

[0324] Input data: accident data = { 'intersection_id': 'abc123', 'accidents': [ {'date': '2022-03-01', 'type': 'vehicle-vehicle', 'severity': 'minor injury'}, {'date': '2022-06-15', 'type': 'pedestrian-vehicle', 'severity': 'serious injury'} ]}, weather information = { 'date': '2023-10-12', 'weather': 'cloudy', 'temperature': 20} Please rate the accident risk level at this intersection from 1 to 10.

[0325] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0326] Step 1:

[0327] The device retrieves the current location data.

[0328] Input: Vehicle GPS data

[0329] How it works: The device uses the GPS module to get its current location and determine that an intersection is nearby.

[0330] Output: Current latitude and longitude and intersection identifier

[0331] Step 2:

[0332] The device obtains past accident data from information providers.

[0333] Input: Current location data and intersection identifier

[0334] How it works: The device uses the intersection identifier to send a request to the API of an information provider (e.g., the National Police Agency) to retrieve past accident data for a specific intersection.

[0335] Output: Past accident data (e.g., number of past accidents, type of accident, date and time of accident, details of damage caused by accident)

[0336] Step 3:

[0337] The device retrieves the current date, time, and weather information.

[0338] Input: Current system time

[0339] How it works: The device uses the weather forecast API to get the current time (e.g., date and time) and current weather information (e.g., weather, temperature).

[0340] Output: Current date, time and weather information

[0341] Step 4:

[0342] Risk assessment is performed using a generative AI model based on the data acquired by the server.

[0343] Input: Past accident data, current date and time, and weather information

[0344] How it works: The server inputs this data into a generative AI model to analyze the accident risk at a particular intersection. The generative AI model outputs a risk level on a scale of 1 to 10 based on the input data.

[0345] Output: Accident risk level

[0346] Step 5:

[0347] The device assesses the driver's emotional state.

[0348] Input: Driver's facial expression data and voice tone data

[0349] How it works: The device uses the vehicle's camera and voice recognition system to collect the driver's facial expressions and tone of voice. An emotion engine analyzes this data to assess the driver's emotional state (e.g., stress level, distraction, excitement).

[0350] Output: Driver's emotional state

[0351] Step 6:

[0352] The device tailors the notification content based on the risk assessment results and the driver's emotional state.

[0353] Input: Accident risk level, driver's emotional state

[0354] How it works: The device generates the most appropriate alert based on your risk level and emotional state. High-risk and high-stress alerts are more detailed and specific.

[0355] Output: Adjusted notification content

[0356] Step 7:

[0357] The terminal displays the notification content to the user.

[0358] Input: Adjusted notification content

[0359] Action: The device displays the notification to the user visually or audibly, for example, by displaying a message on the screen and providing a voice prompt.

[0360] Output: User notification

[0361] Specifically, when a user approaches a specific intersection, the device obtains location data and identifies the intersection's identifier. The device then obtains past accident data from information providers, as well as the current date, time, and weather information. The server uses this data to perform a risk assessment using a generative AI model. The device then analyzes the driver's facial expressions and tone of voice to assess their emotional state. The device then generates optimal notification content based on the risk assessment results and the driver's emotional state, and notifies the user visually and audibly.

[0362] 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.

[0363] 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.

[0364] 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.

[0365] [Second embodiment]

[0366] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0367] 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.

[0368] 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).

[0369] 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.

[0370] 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.

[0371] 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).

[0372] 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.

[0373] 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.

[0374] 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.

[0375] 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.

[0376] 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.

[0377] 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."

[0378] This invention is a system that effectively alerts drivers by integrating a generative AI that incorporates past accident data and current environmental conditions into a vehicle navigation system. The following is a specific example.

[0379] A natural language description of the program's operation

[0380] 1. Acquisition of initial data

[0381] The device obtains its current location and the identifier of the specific intersection, which is automatically obtained based on GPS data.

[0382] 2. Acquisition of accident data

[0383] The server receives the intersection identifier sent from the device and calls the National Police Agency's API to retrieve past accident data, including the number of accidents, type of accident, date and time of the accident, and details of the damage caused by the accident.

[0384] 3. Obtaining the current environmental conditions

[0385] The device obtains the current date, time, and weather information. The weather information is obtained using a weather forecast API, and specifically includes the current weather (sunny, cloudy, rainy, snowy, etc.) and temperature.

[0386] 4. Perform a risk analysis

[0387] The server uses a generative AI to perform risk analysis based on the acquired past accident data and current environmental conditions. The generative AI uses this data as input to predict the accident risk at a specific intersection. The prediction is output as a risk level on a scale of 1 to 10.

[0388] 5. Sending risk notifications

[0389] The device will then notify the driver based on the analysis results. The specific content of the notification will vary depending on the risk level.

[0390] If the risk level is 7 or higher, a message will be displayed saying, "Caution: This intersection has a high risk of accidents. Be careful, especially in bad weather."

[0391] If the risk level is between 4 and 7, the message "Warning: Many accidents have occurred at this intersection in the past. Please drive carefully" will be displayed.

[0392] If the risk level is below 4, the message "This intersection is relatively safe" will be displayed.

[0393] Specific examples

[0394] When the user approaches a specific intersection (e.g., intersection ID "abc123"), the device obtains the user's current location information and recognizes the intersection's identifier "abc123." The device then uses the recognized identifier to send a request to the server. The server then obtains accident data from the past five years via the National Police Agency's API, as well as the current date and time (e.g., 14:00, October 12, 2023) and weather information (e.g., cloudy).

[0395] Based on the acquired data, the server uses a generative AI to perform a risk analysis and determines that the risk level of the intersection is 7. Because the risk level is high, the device notifies the user with the message, "Caution: This intersection has a high risk of accidents. Be careful, especially in bad weather."

[0396] It is expected that users will receive this notification and pay particular attention when driving, thereby reducing the risk of accidents at intersections.

[0397] The processing flow will be explained below.

[0398] Step 1:

[0399] The device obtains its current location information from GPS, detects that it has approached a specific intersection, and identifies the identifier of the detected intersection.

[0400] Step 2:

[0401] The device sends the intersection identifier it has identified to the server, which includes the intersection ID and the current timestamp.

[0402] Step 3:

[0403] The server receives the intersection identifier and calls the National Police Agency's API to retrieve past accident data for that intersection, including the number of accidents, type of accident, date and time of the accident, and details of the damage caused by the accident.

[0404] Step 4:

[0405] The device obtains the current date, time, and weather information. Weather information is obtained using the weather forecast API, including the current weather (sunny, cloudy, rainy, snowy, etc.) and temperature.

[0406] Step 5:

[0407] The server uses the AI ​​generator to perform risk analysis based on the acquired past accident data, current date, time, and weather information. The AI ​​uses this data as input to predict the accident risk at a specific intersection. The predicted result is output as a risk level on a scale of 1 to 10.

[0408] Step 6:

[0409] The device receives the analysis results and generates notification content according to the risk level.

[0410] Step 7:

[0411] The device generates and displays notifications to the driver, which vary depending on the risk level.

[0412] If the risk level is 7 or higher, a message will be displayed saying, "Caution: This intersection has a high risk of accidents. Be careful, especially in bad weather."

[0413] If the risk level is between 4 and 7, the message "Warning: Many accidents have occurred at this intersection in the past. Please drive carefully" will be displayed.

[0414] If the risk level is below 4, the message "This intersection is relatively safe" will be displayed.

[0415] Step 8:

[0416] Users receive notifications and decide whether to drive with extra caution, and take measures such as slowing down if necessary.

[0417] Example 1

[0418] 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."

[0419] Current vehicle navigation systems lack mechanisms to effectively notify drivers of accident risks at specific intersections. In particular, risk analysis that takes into account past accident data and current environmental conditions is lacking. Therefore, effective means to promote safe driving are needed.

[0420] 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.

[0421] In this invention, the server includes a means for acquiring current location information, a means for acquiring an intersection identifier, and a means for acquiring past accident data from an external database, thereby enabling the server to analyze the accident risk at a specific intersection based on the past accident data and the current environmental conditions, and effectively notify the driver of the result.

[0422] A "vehicle navigation system" is an electronic system that provides map information and route guidance to a driver.

[0423] "Means for obtaining current location information" refers to a device or software for identifying the current location of a vehicle using a GPS module or the like.

[0424] The "means for acquiring an intersection identifier" is a device or software for acquiring a unique identification (ID) for identifying an intersection.

[0425] The "means for obtaining past accident data from an external database" refers to a communications interface and associated software for obtaining accident data from an external source such as the National Police Agency.

[0426] "Means for obtaining current date, time and weather information" refers to a device or software for obtaining the current date, time and weather conditions from calendar information or weather forecast APIs.

[0427] The "means for analyzing accident risk" is software that predicts and assesses accident risk using a generative AI model based on past accident data and current environmental conditions.

[0428] "Means for notifying the driver" means a device or software for presenting a visual or audio warning message to the driver based on the risk of an accident.

[0429] A "generative AI model" refers to an artificial intelligence algorithm that makes predictions or generates based on specific input data.

[0430] This invention is a system that incorporates past accident data and current environmental conditions into a vehicle's navigation system and uses a generative AI model to effectively alert the driver. Specific implementation methods are described in detail below.

[0431] Initial setup and data acquisition

[0432] The device obtains its current location using a GPS module, which pinpoints the vehicle's exact location, and automatically obtains an intersection identifier by matching it with an internal mapping database. This identifier uniquely identifies a particular intersection.

[0433] Acquisition of past accident data

[0434] The device generates a request with the acquired intersection identifier and sends it to the server. Based on the received request, the server calls an external database (for example, the National Police Agency's API) to acquire past accident data. This data includes the number of past accidents, the type of accident, the date and time of the accident, details of the damage caused by the accident, etc. The acquired accident data is stored in an internal database.

[0435] Get current environmental conditions

[0436] The device retrieves the system date and time to determine the current date and time. In addition, it calls the weather forecast API to obtain current weather information (e.g., sunny, cloudy, rainy, snowy, etc.) and temperature. This information is important to reflect real-time environmental conditions.

[0437] Performing risk analysis

[0438] The server compiles the acquired past accident data and current environmental conditions and inputs them into a generative AI model. This generative AI model is constructed using, for example, a deep learning algorithm. The server uses the generative AI model to predict the accident risk at a specific intersection on a scale of 1 to 10. The predicted result is evaluated as a risk level and sent to the device.

[0439] Driver risk notification

[0440] The device determines the notification message to the driver based on the risk level received as a result of the analysis. The notification content varies depending on the risk level as follows:

[0441] If the risk level is 7 or higher, the message "Caution: There is a high risk of accidents at this intersection. Be careful, especially in bad weather." will be displayed.

[0442] If the risk level is between 4 and 6: The message "Warning: This intersection has had many accidents in the past. Please drive carefully" will be displayed.

[0443] If the risk level is 3 or lower: The message "This intersection is relatively safe" will be displayed.

[0444] The device notifies the driver of these messages visually and audibly, allowing them to sense danger in advance and drive safely.

[0445] Specific examples

[0446] When the user approaches a specific intersection (e.g., intersection ID "abc123"), the device obtains the current location information and recognizes the intersection identifier "abc123." The device uses the recognized identifier to send a request to the server. The server obtains accident data from the past five years via an external database API, and also obtains the current date and time (e.g., 14:00, October 12, 2023) and weather information (e.g., cloudy).

[0447] Based on the acquired data, the server performs a risk analysis using a generative AI model and determines that the risk level of the intersection is 7. Because the risk level is high, the device notifies the user with a message saying, "Caution: This intersection has a high risk of accidents. Please be especially careful in bad weather." The user is expected to receive this notification and pay particular attention when driving, thereby reducing the risk of accidents at intersections.

[0448] Prompt Sentence Examples

[0449] To predict the accident risk at a specific intersection, use a generative AI model to analyze past accident data and current weather information. Intersection ID: abc123, Current Date and Time: October 12, 2023, 14:00, Current Weather: Cloudy. Output the risk level on a scale of 1 to 10.

[0450] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0451] Step 1:

[0452] The device obtains the current location.

[0453] Input: Data obtained using a GPS module.

[0454] Output: Current latitude and longitude information.

[0455] Specific behavior:

[0456] The device will activate its built-in GPS module and obtain its current location information.

[0457] The acquired latitude and longitude information is stored in temporary memory within the device.

[0458] Step 2:

[0459] The terminal obtains an identifier for a particular intersection.

[0460] Input: Current latitude and longitude information.

[0461] Output: Intersection identifier (e.g. intersection ID "abc123").

[0462] Specific behavior:

[0463] The device checks its internal mapping database to obtain the intersection identifier that corresponds to the current latitude and longitude.

[0464] The acquired intersection identifier is stored in memory for subsequent processing.

[0465] Step 3:

[0466] The terminal generates a request including the intersection identifier and sends it to the server.

[0467] Input: Intersection identifier.

[0468] Output: The request to the server.

[0469] Specific behavior:

[0470] The terminal generates a request in HTTP format that includes the intersection identifier.

[0471] Send the generated request to the server.

[0472] Step 4:

[0473] The server retrieves past accident data from an external database.

[0474] Input: A request containing an intersection identifier.

[0475] Output: Historical accident data.

[0476] Specific behavior:

[0477] The server analyzes the received request and extracts the intersection identifier.

[0478] The server calls the National Police Agency's API to obtain past accident data for the relevant intersection identifier.

[0479] The acquired accident data is stored in an internal database.

[0480] Step 5:

[0481] The device retrieves the current date, time, and weather information.

[0482] Input: Current date and time, Weather API.

[0483] Output: Current weather information (e.g. sunny, cloudy, rainy, snowy, etc.) and temperature.

[0484] Specific behavior:

[0485] The device obtains the current date and time using the system's built-in clock.

[0486] Call the weather forecast API to get current weather information and temperature.

[0487] The acquired weather information is stored in memory.

[0488] Step 6:

[0489] The server inputs past accident data and current environmental conditions into a generative AI model.

[0490] Input: Past accident data, current date and time, current weather information.

[0491] Output: Accident risk level (1 to 10).

[0492] Specific behavior:

[0493] The server compiles past accident data, the current date and time, and weather information.

[0494] The compiled data is fed into a generative AI model.

[0495] A generative AI model analyzes accident risk and predicts risk levels.

[0496] A risk level is obtained as a prediction result and sent to the terminal as necessary.

[0497] Step 7:

[0498] The device notifies the driver based on the analysis results.

[0499] Input: Risk level.

[0500] Output: A warning message to be displayed to the driver.

[0501] Specific behavior:

[0502] The terminal determines a message according to the received risk level.

[0503] If the risk level is 7 or higher: Display the message "Caution: This intersection has a high risk of accidents. Be careful, especially in bad weather."

[0504] If the risk level is between 4 and 6: Display the message "Warning: Many accidents have occurred at this intersection in the past. Please drive carefully."

[0505] If the risk level is 3 or lower: Display the message "This intersection is relatively safe."

[0506] The determined message is notified to the driver visually and audibly.

[0507] (Application example 1)

[0508] 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."

[0509] Although conventional vehicle navigation systems take into account current location and weather information, they lack the functionality to integrate past traffic accident data for risk analysis. This makes it difficult to provide appropriate risk warnings based on past accident data at intersections or specific locations. Furthermore, there is a need to utilize generative AI for risk analysis to perform more accurate traffic risk assessments in real time.

[0510] 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.

[0511] In this invention, the server includes means for acquiring intersection identifiers, means for acquiring past accident data, means for acquiring current location information, means for acquiring current date and time and weather information, means for analyzing traffic risks based on the past accident data, the current date and time and weather information, and means for notifying the driver based on the analyzed traffic risks. This makes it possible to analyze traffic risks at intersections or specific locations in real time for the driver and provide a risk assessment that integrates past data and current environmental conditions using a generation AI.

[0512] An "intersection identifier" is a code or number that uniquely identifies a particular intersection.

[0513] "Past accident data" refers to data on traffic accidents that have occurred in the past at specific locations or intersections, and includes the date and time of the accident, the type of accident, and the extent of the damage.

[0514] "Current location information" is data indicating the current location of the vehicle, and is usually obtained using a location information system such as GPS.

[0515] The "current date and time" is data indicating the date and time at which the vehicle is currently located.

[0516] "Weather information" is data that indicates the current weather conditions, and specifically includes weather such as sunny, cloudy, rainy, and snowy, as well as temperature and humidity.

[0517] "Traffic risk" is an index that indicates the degree of possibility of a traffic accident occurring at a particular location or intersection.

[0518] "Generative AI" is a type of artificial intelligence that autonomously analyzes and predicts based on acquired data, and refers to a model that provides the optimal risk assessment for the input data.

[0519] The "means for notifying" refers to a means for providing a specific message or warning to the driver through audio or visual means based on the analysis results.

[0520] The present invention includes a system that analyzes traffic risks based on intersection identifiers, past accident data, current location information, current date and time, and weather information, and notifies drivers.

[0521] This system mainly uses the following hardware and software: The hardware uses the on-board computer and GPS module in the autonomous vehicle, and the software includes acquisition using Python and API, risk analysis using generative AI, and generative AI models.

[0522] Specifically, the server uses a GPS module to obtain intersection identifiers. After obtaining the location information and intersection identifiers, it calls a traffic accident data provision API to obtain past accident data. It then uses date and time information and weather forecast APIs to obtain the current date and time and weather information.

[0523] Based on this data, the generative AI model performs a traffic risk analysis. The analysis results are output as a traffic risk level, and the notification content for the driver varies depending on the risk level. If the risk is high, a warning message is displayed, and if the risk is low, a safety message is displayed.

[0524] When a driver approaches a specific intersection, the device acquires their current location information and sends it along with the intersection's identifier to a server. The server then acquires past traffic accident data via the National Police Agency's API, as well as the current date, time, and weather information. Based on the acquired data, the generative AI model performs a risk analysis and notifies the driver of the resulting traffic risk level.

[0525] As a specific example, when a driver approaches a specific intersection (e.g., intersection ID "abc123"), the device acquires the current location information and recognizes the intersection identifier "abc123." The acquired identifier is sent to the server along with accident data and weather data, and the generative AI model performs a risk analysis. If the analysis results in a risk level of 7, the device notifies the driver with a message saying, "Caution: This intersection has a high risk of accidents. Be especially careful when the weather is bad."

[0526] An example of a prompt is:

[0527] "I'm approaching intersection ID abc123. Do you have accident data for the past five years?"

[0528] "The weather report is cloudy. What is the risk level?"

[0529] As described above, the embodiments for carrying out the present invention have been specifically shown, and the invention can be effectively carried out.

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

[0531] Step 1:

[0532] The device obtains the vehicle's current location information using the GPS module, which provides the latitude and longitude information of the vehicle's current location (e.g., "35.6895,139.6917"), and then automatically recognizes the identifier of a specific intersection (e.g., "abc123") based on the current location.

[0533] Step 2:

[0534] The device sends the intersection identifier it recognized to the server. The server receives the intersection identifier and calls the National Police Agency's API to retrieve past accident data. This data includes the number of past accidents, the type of accident, the date and time of the accident, and details of the damage caused by the accident.

[0535] Step 3:

[0536] The server obtains the current date and time information, which gives the current year, month, date, and time (e.g., "October 12, 2023, 14:00").

[0537] Step 4:

[0538] The server uses a weather forecast API to retrieve current weather information, including the current weather (sunny, cloudy, rainy, snowy, etc.) and temperature (e.g., "cloudy, 20 degrees").

[0539] Step 5:

[0540] The server performs risk analysis using a generative AI model using past accident data, current date and time information, and weather information.Past accident data and current environmental conditions are passed to the model as input, and a traffic risk level is output as a number (e.g., "Risk Level 7").

[0541] Step 6:

[0542] The server sends the analysis results to the device. The device notifies the driver based on the received risk level. Different warning messages are displayed depending on the risk level. If the risk is high (risk level 7 or higher), a warning message is displayed stating, "Caution: This intersection has a high risk of accidents. Be careful, especially in bad weather."

[0543] Step 7:

[0544] Users can check the warning message on their device and be urged to pay particular attention while driving. By encouraging users to pay particular attention and maintain safe driving, it is expected that the risk of accidents at intersections will be reduced.

[0545] 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.

[0546] This invention is a system that effectively alerts the driver by integrating a generative AI that incorporates past accident data and current environmental conditions into a vehicle navigation system, and further combining it with an emotion engine that recognizes the driver's emotional state. The following is a specific example.

[0547] A natural language description of the program's operation

[0548] 1. Acquisition of initial data

[0549] The device obtains its current location information from GPS, detects that it has approached a specific intersection, and identifies the identifier of the detected intersection.

[0550] 2. Acquisition of accident data

[0551] The server receives the intersection identifier sent from the device and calls the National Police Agency's API to retrieve past accident data for that intersection, including the number of accidents, type of accident, date and time of the accident, and details of the damage caused by the accident.

[0552] 3. Obtaining the current environmental conditions

[0553] The device obtains the current date, time, and weather information. The weather information includes the current weather (sunny, cloudy, rainy, snowy, etc.) and temperature using the weather forecast API.

[0554] 4. Perform a risk analysis

[0555] The server uses a generation AI to perform risk analysis based on the acquired past accident data and current environmental conditions. The generation AI uses this data as input to predict the accident risk at a specific intersection. The prediction result is output as a risk level on a scale of 1 to 10.

[0556] 5. Emotional state analysis

[0557] The device activates an emotion engine to determine the driver's emotions. The emotion engine analyzes the driver's facial expressions and tone of voice through a camera and voice recognition system installed in the vehicle to evaluate the driver's emotional state. The evaluation results include the driver's stress level, attention state, and excitement level.

[0558] 6. Sending Risk Notifications

[0559] The device adjusts the notification content based on the risk analysis results and the driver's emotional state. For example, if the driver is under stress, the notification content will be more specific and detailed.

[0560] 7. Generating and Displaying Notification Content

[0561] The device will then take into account the results of the emotion engine and generate the most appropriate notification content to display to the driver. The specific notification content is as follows:

[0562] If the risk level is 7 or higher and the driver's stress level is high, a message will be displayed saying, "Warning: There is a high risk of accidents at this intersection. Please slow down and be aware of your surroundings."

[0563] If the risk level is 7 or higher and the driver's stress level is low, the system displays the message, "Caution: This intersection has a high risk of accidents. Be careful, especially in bad weather."

[0564] If the risk level is between 4 and 7, the message "Warning: Many accidents have occurred at this intersection in the past. Please drive carefully" will be displayed.

[0565] If the risk level is below 4, the message "This intersection is relatively safe" will be displayed.

[0566] Specific examples

[0567] When the user approaches a specific intersection (e.g., intersection ID "abc123"), the device obtains the current location information and recognizes the intersection's identifier "abc123." The device uses the identifier to send a request to the server. The server obtains accident data from the past five years via the National Police Agency's API, as well as the current date and time (e.g., 14:00, October 12, 2023) and weather information (e.g., cloudy).

[0568] Based on the acquired data, the server uses a generative AI to perform a risk analysis and determine the risk level as 7. At the same time, the device activates its emotion engine and determines that the driver is in a high stress state. Based on this, the device generates a notification message to the user: "Caution: There is a high risk of an accident at this intersection. Slow down and pay attention to your surroundings."

[0569] It is expected that users will receive this notification and take measures such as paying extra attention when driving and slowing down, thereby reducing the risk of accidents at intersections.

[0570] The processing flow will be explained below.

[0571] Step 1:

[0572] The device obtains its current location information from GPS, detects that it has approached a specific intersection, and identifies the identifier of the detected intersection.

[0573] Step 2:

[0574] The device sends the intersection identifier it has identified to the server, which includes the intersection ID and the current timestamp.

[0575] Step 3:

[0576] The server receives the intersection identifier and calls the National Police Agency's API to retrieve past accident data for that intersection, including the number of accidents, type of accident, date and time of the accident, and details of the damage caused by the accident.

[0577] Step 4:

[0578] The device obtains the current date, time, and weather information. Weather information is obtained using the weather forecast API to obtain the current weather (sunny, cloudy, rainy, snowy, etc.) and temperature.

[0579] Step 5:

[0580] The server uses a generation AI to perform risk analysis based on the acquired past accident data and current environmental conditions. The generation AI uses this data as input to predict the accident risk at a specific intersection. The prediction result is output as a risk level on a scale of 1 to 10.

[0581] Step 6:

[0582] The device activates an emotion engine to recognize the driver's emotional state. The emotion engine analyzes the driver's facial expressions and tone of voice through a camera and voice recognition system installed in the vehicle, and evaluates the driver's emotional state. The evaluation results include the driver's stress level, attention state, and excitement level.

[0583] Step 7:

[0584] The device adjusts the notification content based on the risk analysis results and the driver's emotional state. For example, if the driver is under stress, the notification content will be more specific and detailed.

[0585] Step 8:

[0586] The device generates and displays notifications to the driver, which vary depending on the risk level and the driver's emotional state.

[0587] If the risk level is 7 or higher and the driver's stress level is high, a message will be displayed saying, "Warning: There is a high risk of accidents at this intersection. Please slow down and be aware of your surroundings."

[0588] If the risk level is 7 or higher and the driver's stress level is low, the system displays the message, "Caution: This intersection has a high risk of accidents. Be careful, especially in bad weather."

[0589] If the risk level is between 4 and 7, the message "Warning: Many accidents have occurred at this intersection in the past. Please drive carefully" will be displayed.

[0590] If the risk level is below 4, the message "This intersection is relatively safe" will be displayed.

[0591] Step 9:

[0592] Users receive notifications and decide whether to drive with extra caution, and take measures such as slowing down if necessary.

[0593] Example 2

[0594] 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."

[0595] Conventional vehicle navigation systems have provided driver warnings based on location information and past accident data, but these alone are unable to adequately assess risk by taking into account the current environmental conditions and the driver's emotional state, making it difficult to provide effective warnings. In particular, the lack of proper consideration of the driver's emotional state can lead to incorrect decisions in stressful situations.

[0596] 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.

[0597] In this invention, the server includes means for acquiring current location information, means for acquiring intersection identifiers, means for acquiring past accident data, means for acquiring the current date and time and environmental conditions, means for analyzing the emotional state of the driver, means for analyzing the accident risk based on the past accident data, the current date and time, environmental conditions, and the emotional state of the driver, and means for notifying the driver based on the analyzed accident risk. This enables more accurate risk assessment based on the current environmental conditions and the emotional state of the driver, and warnings appropriate for each individual driver.

[0598] "Current location information" means data about the vehicle's real-time geographic location obtained by the vehicle's navigation system using location technology such as GPS.

[0599] An "intersection identifier" is an identification number or code that uniquely identifies a particular intersection.

[0600] "Past accident data" is a record of accidents that have occurred in specific areas or intersections, and includes detailed information such as the number of accidents, the type of accident, the date and time, and the extent of the damage.

[0601] "Current date and time" refers to real-time time and date information.

[0602] "Environmental conditions" is information that indicates the external environmental state, such as the current weather (sunny, cloudy, rainy, snowy, etc.) and temperature.

[0603] "Driver's emotional state" refers to the driver's psychological state, such as stress level, attention state, and excitement level, which is analyzed using sensors such as cameras and voice recognition systems.

[0604] "Accident risk" is a score or index that indicates the likelihood of an accident occurring at a particular location, assessed based on acquired data.

[0605] "Generative AI" is an artificial intelligence model that uses acquired data to predict accident risk.

[0606] "Notification" refers to a message or warning provided to the driver based on the results of risk analysis.

[0607] This invention is a system that performs risk analysis by combining past accident data, current environmental conditions, and the emotional state of the driver to improve safety in vehicle navigation systems, and provides optimal warnings to the driver.

[0608] 1. Acquisition of initial data

[0609] The device obtains current location information from a GPS module (e.g., u-blox NEO-M8N). This allows the device to determine the vehicle's current location in real time and, by comparing it with a database, detect when it has approached a specific intersection. The device then obtains the identifier of the detected intersection (e.g., ID "abc123").

[0610] 2. Acquisition of accident data

[0611] The server receives the intersection identifier sent from the device and calls the National Police Agency's API to retrieve past accident data for that intersection, including the number of accidents, type of accident, date and time of the accident, and details of damage caused by the accident.

[0612] 3. Obtaining the current environmental conditions

[0613] The device obtains the current date, time, and weather information. The weather information is obtained from the weather forecast API and includes the current weather (sunny, cloudy, rainy, snowy, etc.) and temperature.

[0614] 4. Perform a risk analysis

[0615] The server uses a generative AI model to analyze risk based on past accident data and current environmental conditions. The generative AI model (e.g., a model using TensorFlow or PyTorch) takes this data as input and predicts the accident risk at a particular intersection on a scale of 1 to 10.

[0616] 5. Emotional state analysis

[0617] The device activates an emotion engine to determine the driver's emotional state. The emotion engine uses an in-car camera (e.g., a standard webcam) and a voice recognition system (e.g., a voice recognition API) to analyze the driver's facial expressions and tone of voice to assess the driver's stress level, attention state, and excitement level.

[0618] 6. Sending Risk Notifications

[0619] The device adjusts the notification content based on the results of risk analysis and the driver's emotional state. If the driver is in a high stress state, the notification content will be more specific and detailed, depending on the situation.

[0620] 7. Generating and Displaying Notification Content

[0621] The device will then take into account the results of the emotion engine to generate and display the most appropriate notification content to the driver. For example, if the risk level is 7 or higher and the driver's stress level is high, the device will display the message "Caution: There is a high risk of an accident at this intersection. Please reduce your speed and be aware of your surroundings."

[0622] Specific examples

[0623] When a user approaches a specific intersection (e.g., intersection ID "abc123"), the device obtains the user's current location and recognizes the intersection's identifier "abc123." This identifier is used to send a request to the server, which obtains accident data from the past five years via the National Police Agency's API, as well as the current date and time (e.g., 14:00, October 12, 2023) and weather information (e.g., cloudy). The server analyzes this data and determines that the risk level is 7. If the emotion engine also determines that the driver is in a high state of stress, the device generates and displays a notification to the user stating, "Caution: There is a high risk of an accident at this intersection. Slow down and pay attention to your surroundings."

[0624] Prompt Sentence Examples

[0625] "Generate notifications for drivers approaching specific intersections based on accident risk and the driver's emotional state. Use historical accident data, current weather conditions, and driver emotion analysis as data sources."

[0626] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0627] Step 1:

[0628] The device obtains current location information. Using a GPS module (e.g., u-blox NEO-M8N) as input, the device obtains the vehicle's current location data as output. The data is then processed by checking the location information against the OpenStreetMap database to determine whether the device has reached a specific intersection and extracting the intersection's identifier (e.g., ID "abc123").

[0629] Step 2:

[0630] The terminal sends the extracted intersection identifier to the server. The intersection identifier is the input and the request sent to the server is the output. The LTE module is used for communication.

[0631] Step 3:

[0632] Based on the intersection identifier received by the server, the server calls the National Police Agency's API to obtain past accident data. The input is the intersection identifier, and the output is past accident data (number of accidents, type, date and time, damage details). The data is calculated by processing the API request and response.

[0633] Step 4:

[0634] The device obtains the current date and time and weather information. The current date and time and weather forecast API are used as input, and the current weather (sunny, cloudy, rainy, snowy, etc.) and temperature are obtained as output. Data processing involves processing API requests and responses.

[0635] Step 5:

[0636] The server performs risk analysis using a generative AI model based on past accident data and current environmental conditions. The inputs are past accident data and current environmental conditions, and the output is a risk level (on a scale of 1 to 10). For data calculations, the data is input into a generative AI model (e.g., TensorFlow or PyTorch) to predict the risk level.

[0637] Step 6:

[0638] The device runs an emotion engine to analyze the driver's emotional state. It uses an in-car camera (e.g., a standard webcam) and a voice recognition system (e.g., a voice recognition API) as input, and evaluates the driver's stress level, attention state, and excitement level as output. Data calculations analyze video and audio data to determine the driver's emotional state.

[0639] Step 7:

[0640] The device adjusts the notification content based on the risk analysis results and the driver's emotional state. The inputs are the risk level and the driver's emotional state, and the output is the adjusted notification message. The data is then processed to generate an appropriate message based on the risk level and emotional state.

[0641] Step 8:

[0642] The terminal displays the generated notification content on the driver panel. The adjusted notification message is the input, and the display to the driver is the output. Specifically, the terminal sends an instruction to the display system to display the message on the panel.

[0643] (Application example 2)

[0644] 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."

[0645] Conventional vehicle navigation systems lack the functionality to warn drivers by taking into account past accident data and environmental information, and therefore do not contribute to sufficient improvements in road safety. Another problem is that they are unable to analyze the driver's emotional state in real time and provide appropriate notifications based on that state. Therefore, there is a need for a system that can provide appropriate and effective warnings when a vehicle approaches an intersection or a high-risk location.

[0646] 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.

[0647] In this invention, the server includes means for acquiring geographic information including intersections, means for acquiring past accident data from information providers, means for acquiring current location data, means for acquiring current time and weather information, means for assessing accident risk based on past accident data, current time and weather information, means for issuing a warning to the driver based on the assessed accident risk, means for assessing the emotional state of the driver, and means for adjusting the content of the warning based on the risk assessment result and the emotional state of the driver. This enables risk analysis based on past accident data and current environmental information and appropriate warnings according to the emotional state of the driver.

[0648] "Geographic information including intersections" refers to all information on a map, including the layout of roads and the locations of intersections.

[0649] "Information providers" are public or private organizations that provide past traffic accident data and weather information.

[0650] "Current location data" means information indicating the current geographic location of the vehicle, primarily obtained from GPS.

[0651] "Current time and weather information" is information including the current date, time, and weather conditions (for example, sunny, rainy, snowy, etc.).

[0652] "Means for assessing accident risk" are techniques and methods that use past accident data and current environmental conditions to analyze the possibility of an accident occurring at a specific location.

[0653] "Means of warning" refers to technologies and methods that warn drivers by voice, screen display, etc., based on the analyzed accident risk.

[0654] "Driver's emotional state" refers to the driver's mental state, including states such as stress, distraction, excitement, and relaxation.

[0655] The "means for assessing emotional state" refers to a technology or method that uses a camera or a voice recognition system to analyze the driver's facial expressions and tone of voice to assess the driver's emotional state.

[0656] "Means for adjusting the warning content" refers to a technology or method for generating and displaying a warning message with optimal content and format based on the driver's emotional state and the results of risk assessment.

[0657] A "generative AI model" is an artificial intelligence model that generates new information and results based on data, and is primarily used to analyze accident risks.

[0658] This invention is a system that effectively alerts the driver by integrating a generative AI that incorporates past accident data and current environmental conditions into a vehicle navigation system, and by combining it with an emotion engine that recognizes the driver's emotional state. Each element will be explained in detail below.

[0659] The system is composed of the following hardware and software: First, a GPS module is used to obtain the vehicle's current location data, which allows the system to identify when the vehicle will approach a specific intersection. The current date, time, and weather information is obtained using a weather forecast API, which allows the system to obtain the latest information about the driving environment.

[0660] Next, a request is sent via a REST API to obtain past accident data from an information provider (e.g., the National Police Agency). The obtained accident data includes the number of past accidents, the type of accident, the date of the accident, and details of the damage caused by the accident.

[0661] The server uses a generative AI model to assess risk based on the acquired past accident data and current environmental conditions. The generative AI model uses this data as input to predict the accident risk at a specific intersection. The prediction result is output as an accident risk level on a scale of 1 to 10.

[0662] Furthermore, a camera and voice recognition system are installed inside the vehicle to assess the driver's emotional state. The camera recognizes the driver's facial expressions, and the voice recognition system analyzes the driver's tone of voice. Based on this data, the emotion engine assesses the driver's emotional state (e.g., stress level, distraction level, excitement level, etc.).

[0663] The device adjusts the notification content based on the risk assessment result and the driver's emotional state. The notification is displayed visually and audibly to the driver. For example, if the risk level is high and the driver is stressed, the device will display a message saying, "Caution: There is a high risk of an accident at this intersection. Please reduce your speed and be aware of your surroundings."

[0664] As a specific example, when a user approaches a specific intersection (e.g., intersection ID "abc123"), the device obtains its current location information and recognizes the intersection's identifier "abc123." When the device sends a request to the server using the identifier, the server obtains accident data from the past five years via the information provider's API, as well as the current date, time, and weather information. Based on the obtained data, the server performs a risk analysis using a generative AI model and determines that the risk level is 7. At the same time, the device activates its emotion engine and determines that the driver is in a state of high stress. Based on this, the device generates a notification message to the user: "Caution: There is a high risk of accidents at this intersection. Slow down and pay attention to your surroundings."

[0665] An example of a prompt to input to a generative AI model is as follows:

[0666] Input data: accident data = { 'intersection_id': 'abc123', 'accidents': [ {'date': '2022-03-01', 'type': 'vehicle-vehicle', 'severity': 'minor injury'}, {'date': '2022-06-15', 'type': 'pedestrian-vehicle', 'severity': 'serious injury'} ]}, weather information = { 'date': '2023-10-12', 'weather': 'cloudy', 'temperature': 20} Please rate the accident risk level at this intersection from 1 to 10.

[0667] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0668] Step 1:

[0669] The device retrieves the current location data.

[0670] Input: Vehicle GPS data

[0671] How it works: The device uses the GPS module to get its current location and determine that an intersection is nearby.

[0672] Output: Current latitude and longitude and intersection identifier

[0673] Step 2:

[0674] The device obtains past accident data from information providers.

[0675] Input: Current location data and intersection identifier

[0676] How it works: The device uses the intersection identifier to send a request to the API of an information provider (e.g., the National Police Agency) to retrieve past accident data for a specific intersection.

[0677] Output: Past accident data (e.g., number of past accidents, type of accident, date and time of accident, details of damage caused by accident)

[0678] Step 3:

[0679] The device retrieves the current date, time, and weather information.

[0680] Input: Current system time

[0681] How it works: The device uses the weather forecast API to get the current time (e.g., date and time) and current weather information (e.g., weather, temperature).

[0682] Output: Current date, time and weather information

[0683] Step 4:

[0684] Risk assessment is performed using a generative AI model based on the data acquired by the server.

[0685] Input: Past accident data, current date and time, and weather information

[0686] How it works: The server inputs this data into a generative AI model to analyze the accident risk at a particular intersection. The generative AI model outputs a risk level on a scale of 1 to 10 based on the input data.

[0687] Output: Accident risk level

[0688] Step 5:

[0689] The device assesses the driver's emotional state.

[0690] Input: Driver's facial expression data and voice tone data

[0691] How it works: The device uses the vehicle's camera and voice recognition system to collect the driver's facial expressions and tone of voice. An emotion engine analyzes this data to assess the driver's emotional state (e.g., stress level, distraction, excitement).

[0692] Output: Driver's emotional state

[0693] Step 6:

[0694] The device tailors the notification content based on the risk assessment results and the driver's emotional state.

[0695] Input: Accident risk level, driver's emotional state

[0696] How it works: The device generates the most appropriate alert based on your risk level and emotional state. High-risk and high-stress alerts are more detailed and specific.

[0697] Output: Adjusted notification content

[0698] Step 7:

[0699] The terminal displays the notification content to the user.

[0700] Input: Adjusted notification content

[0701] Action: The device displays the notification to the user visually or audibly, for example, by displaying a message on the screen and providing a voice prompt.

[0702] Output: User notification

[0703] Specifically, when a user approaches a specific intersection, the device obtains location data and identifies the intersection's identifier. The device then obtains past accident data from information providers, as well as the current date, time, and weather information. The server uses this data to perform a risk assessment using a generative AI model. The device then analyzes the driver's facial expressions and tone of voice to assess their emotional state. The device then generates optimal notification content based on the risk assessment results and the driver's emotional state, and notifies the user visually and audibly.

[0704] 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.

[0705] 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.

[0706] 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.

[0707] [Third embodiment]

[0708] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0709] 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.

[0710] 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).

[0711] 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.

[0712] 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.

[0713] 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).

[0714] 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.

[0715] 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.

[0716] 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.

[0717] 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.

[0718] 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.

[0719] 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."

[0720] This invention is a system that effectively alerts drivers by integrating a generative AI that incorporates past accident data and current environmental conditions into a vehicle navigation system. The following is a specific example.

[0721] A natural language description of the program's operation

[0722] 1. Acquisition of initial data

[0723] The device obtains its current location and the identifier of the specific intersection, which is automatically obtained based on GPS data.

[0724] 2. Acquisition of accident data

[0725] The server receives the intersection identifier sent from the device and calls the National Police Agency's API to retrieve past accident data, including the number of accidents, type of accident, date and time of the accident, and details of the damage caused by the accident.

[0726] 3. Obtaining the current environmental conditions

[0727] The device obtains the current date, time, and weather information. The weather information is obtained using a weather forecast API, and specifically includes the current weather (sunny, cloudy, rainy, snowy, etc.) and temperature.

[0728] 4. Perform a risk analysis

[0729] The server uses a generative AI to perform risk analysis based on the acquired past accident data and current environmental conditions. The generative AI uses this data as input to predict the accident risk at a specific intersection. The prediction is output as a risk level on a scale of 1 to 10.

[0730] 5. Sending risk notifications

[0731] The device will then notify the driver based on the analysis results. The specific content of the notification will vary depending on the risk level.

[0732] If the risk level is 7 or higher, a message will be displayed saying, "Caution: This intersection has a high risk of accidents. Be careful, especially in bad weather."

[0733] If the risk level is between 4 and 7, the message "Warning: Many accidents have occurred at this intersection in the past. Please drive carefully" will be displayed.

[0734] If the risk level is below 4, the message "This intersection is relatively safe" will be displayed.

[0735] Specific examples

[0736] When the user approaches a specific intersection (e.g., intersection ID "abc123"), the device obtains the user's current location information and recognizes the intersection's identifier "abc123." The device then uses the recognized identifier to send a request to the server. The server then obtains accident data from the past five years via the National Police Agency's API, as well as the current date and time (e.g., 14:00, October 12, 2023) and weather information (e.g., cloudy).

[0737] Based on the acquired data, the server uses a generative AI to perform a risk analysis and determines that the risk level of the intersection is 7. Because the risk level is high, the device notifies the user with the message, "Caution: This intersection has a high risk of accidents. Be careful, especially in bad weather."

[0738] It is expected that users will receive this notification and pay particular attention when driving, thereby reducing the risk of accidents at intersections.

[0739] The processing flow will be explained below.

[0740] Step 1:

[0741] The device obtains its current location information from GPS, detects that it has approached a specific intersection, and identifies the identifier of the detected intersection.

[0742] Step 2:

[0743] The device sends the intersection identifier it has identified to the server, which includes the intersection ID and the current timestamp.

[0744] Step 3:

[0745] The server receives the intersection identifier and calls the National Police Agency's API to retrieve past accident data for that intersection, including the number of accidents, type of accident, date and time of the accident, and details of the damage caused by the accident.

[0746] Step 4:

[0747] The device obtains the current date, time, and weather information. Weather information is obtained using the weather forecast API, including the current weather (sunny, cloudy, rainy, snowy, etc.) and temperature.

[0748] Step 5:

[0749] The server uses the AI ​​generator to perform risk analysis based on the acquired past accident data, current date, time, and weather information. The AI ​​uses this data as input to predict the accident risk at a specific intersection. The predicted result is output as a risk level on a scale of 1 to 10.

[0750] Step 6:

[0751] The device receives the analysis results and generates notification content according to the risk level.

[0752] Step 7:

[0753] The device generates and displays notifications to the driver, which vary depending on the risk level.

[0754] If the risk level is 7 or higher, a message will be displayed saying, "Caution: This intersection has a high risk of accidents. Be careful, especially in bad weather."

[0755] If the risk level is between 4 and 7, the message "Warning: Many accidents have occurred at this intersection in the past. Please drive carefully" will be displayed.

[0756] If the risk level is below 4, the message "This intersection is relatively safe" will be displayed.

[0757] Step 8:

[0758] Users receive notifications and decide whether to drive with extra caution, and take measures such as slowing down if necessary.

[0759] Example 1

[0760] 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."

[0761] Current vehicle navigation systems lack mechanisms to effectively notify drivers of accident risks at specific intersections. In particular, risk analysis that takes into account past accident data and current environmental conditions is lacking. Therefore, effective means to promote safe driving are needed.

[0762] 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.

[0763] In this invention, the server includes a means for acquiring current location information, a means for acquiring an intersection identifier, and a means for acquiring past accident data from an external database, thereby enabling the server to analyze the accident risk at a specific intersection based on the past accident data and the current environmental conditions, and effectively notify the driver of the result.

[0764] A "vehicle navigation system" is an electronic system that provides map information and route guidance to a driver.

[0765] "Means for obtaining current location information" refers to a device or software for identifying the current location of a vehicle using a GPS module or the like.

[0766] The "means for acquiring an intersection identifier" is a device or software for acquiring a unique identification (ID) for identifying an intersection.

[0767] The "means for obtaining past accident data from an external database" refers to a communications interface and associated software for obtaining accident data from an external source such as the National Police Agency.

[0768] "Means for obtaining current date, time and weather information" refers to a device or software for obtaining the current date, time and weather conditions from calendar information or weather forecast APIs.

[0769] The "means for analyzing accident risk" is software that predicts and assesses accident risk using a generative AI model based on past accident data and current environmental conditions.

[0770] "Means for notifying the driver" means a device or software for presenting a visual or audio warning message to the driver based on the risk of an accident.

[0771] A "generative AI model" refers to an artificial intelligence algorithm that makes predictions or generates based on specific input data.

[0772] This invention is a system that incorporates past accident data and current environmental conditions into a vehicle's navigation system and uses a generative AI model to effectively alert the driver. Specific implementation methods are described in detail below.

[0773] Initial setup and data acquisition

[0774] The device obtains its current location using a GPS module, which pinpoints the vehicle's exact location, and automatically obtains an intersection identifier by matching it with an internal mapping database. This identifier uniquely identifies a particular intersection.

[0775] Acquisition of past accident data

[0776] The device generates a request with the acquired intersection identifier and sends it to the server. Based on the received request, the server calls an external database (for example, the National Police Agency's API) to acquire past accident data. This data includes the number of past accidents, the type of accident, the date and time of the accident, details of the damage caused by the accident, etc. The acquired accident data is stored in an internal database.

[0777] Get current environmental conditions

[0778] The device retrieves the system date and time to determine the current date and time. In addition, it calls the weather forecast API to obtain current weather information (e.g., sunny, cloudy, rainy, snowy, etc.) and temperature. This information is important to reflect real-time environmental conditions.

[0779] Performing risk analysis

[0780] The server compiles the acquired past accident data and current environmental conditions and inputs them into a generative AI model. This generative AI model is constructed using, for example, a deep learning algorithm. The server uses the generative AI model to predict the accident risk at a specific intersection on a scale of 1 to 10. The predicted result is evaluated as a risk level and sent to the device.

[0781] Driver risk notification

[0782] The device determines the notification message to the driver based on the risk level received as a result of the analysis. The notification content varies depending on the risk level as follows:

[0783] If the risk level is 7 or higher, the message "Caution: There is a high risk of accidents at this intersection. Be careful, especially in bad weather." will be displayed.

[0784] If the risk level is between 4 and 6: The message "Warning: This intersection has had many accidents in the past. Please drive carefully" will be displayed.

[0785] If the risk level is 3 or lower: The message "This intersection is relatively safe" will be displayed.

[0786] The device notifies the driver of these messages visually and audibly, allowing them to sense danger in advance and drive safely.

[0787] Specific examples

[0788] When the user approaches a specific intersection (e.g., intersection ID "abc123"), the device obtains the current location information and recognizes the intersection identifier "abc123." The device uses the recognized identifier to send a request to the server. The server obtains accident data from the past five years via an external database API, and also obtains the current date and time (e.g., 14:00, October 12, 2023) and weather information (e.g., cloudy).

[0789] Based on the acquired data, the server performs a risk analysis using a generative AI model and determines that the risk level of the intersection is 7. Because the risk level is high, the device notifies the user with a message saying, "Caution: This intersection has a high risk of accidents. Please be especially careful in bad weather." The user is expected to receive this notification and pay particular attention when driving, thereby reducing the risk of accidents at intersections.

[0790] Prompt Sentence Examples

[0791] To predict the accident risk at a specific intersection, use a generative AI model to analyze past accident data and current weather information. Intersection ID: abc123, Current Date and Time: October 12, 2023, 14:00, Current Weather: Cloudy. Output the risk level on a scale of 1 to 10.

[0792] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0793] Step 1:

[0794] The device obtains the current location.

[0795] Input: Data obtained using a GPS module.

[0796] Output: Current latitude and longitude information.

[0797] Specific behavior:

[0798] The device will activate its built-in GPS module and obtain its current location information.

[0799] The acquired latitude and longitude information is stored in temporary memory within the device.

[0800] Step 2:

[0801] The terminal obtains an identifier for a particular intersection.

[0802] Input: Current latitude and longitude information.

[0803] Output: Intersection identifier (e.g. intersection ID "abc123").

[0804] Specific behavior:

[0805] The device checks its internal mapping database to obtain the intersection identifier that corresponds to the current latitude and longitude.

[0806] The acquired intersection identifier is stored in memory for subsequent processing.

[0807] Step 3:

[0808] The terminal generates a request including the intersection identifier and sends it to the server.

[0809] Input: Intersection identifier.

[0810] Output: The request to the server.

[0811] Specific behavior:

[0812] The terminal generates a request in HTTP format that includes the intersection identifier.

[0813] Send the generated request to the server.

[0814] Step 4:

[0815] The server retrieves past accident data from an external database.

[0816] Input: A request containing an intersection identifier.

[0817] Output: Historical accident data.

[0818] Specific behavior:

[0819] The server analyzes the received request and extracts the intersection identifier.

[0820] The server calls the National Police Agency's API to obtain past accident data for the relevant intersection identifier.

[0821] The acquired accident data is stored in an internal database.

[0822] Step 5:

[0823] The device retrieves the current date, time, and weather information.

[0824] Input: Current date and time, Weather API.

[0825] Output: Current weather information (e.g. sunny, cloudy, rainy, snowy, etc.) and temperature.

[0826] Specific behavior:

[0827] The device obtains the current date and time using the system's built-in clock.

[0828] Call the weather forecast API to get current weather information and temperature.

[0829] The acquired weather information is stored in memory.

[0830] Step 6:

[0831] The server inputs past accident data and current environmental conditions into a generative AI model.

[0832] Input: Past accident data, current date and time, current weather information.

[0833] Output: Accident risk level (1 to 10).

[0834] Specific behavior:

[0835] The server compiles past accident data, the current date and time, and weather information.

[0836] The compiled data is fed into a generative AI model.

[0837] A generative AI model analyzes accident risk and predicts risk levels.

[0838] A risk level is obtained as a prediction result and sent to the terminal as necessary.

[0839] Step 7:

[0840] The device notifies the driver based on the analysis results.

[0841] Input: Risk level.

[0842] Output: A warning message to be displayed to the driver.

[0843] Specific behavior:

[0844] The terminal determines a message according to the received risk level.

[0845] If the risk level is 7 or higher: Display the message "Caution: This intersection has a high risk of accidents. Be careful, especially in bad weather."

[0846] If the risk level is between 4 and 6: Display the message "Warning: Many accidents have occurred at this intersection in the past. Please drive carefully."

[0847] If the risk level is 3 or lower: Display the message "This intersection is relatively safe."

[0848] The determined message is notified to the driver visually and audibly.

[0849] (Application example 1)

[0850] 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."

[0851] Although conventional vehicle navigation systems take into account current location and weather information, they lack the functionality to integrate past traffic accident data for risk analysis. This makes it difficult to provide appropriate risk warnings based on past accident data at intersections or specific locations. Furthermore, there is a need to utilize generative AI for risk analysis to perform more accurate traffic risk assessments in real time.

[0852] 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.

[0853] In this invention, the server includes means for acquiring intersection identifiers, means for acquiring past accident data, means for acquiring current location information, means for acquiring current date and time and weather information, means for analyzing traffic risks based on the past accident data, the current date and time and weather information, and means for notifying the driver based on the analyzed traffic risks. This makes it possible to analyze traffic risks at intersections or specific locations in real time for the driver and provide a risk assessment that integrates past data and current environmental conditions using a generation AI.

[0854] An "intersection identifier" is a code or number that uniquely identifies a particular intersection.

[0855] "Past accident data" refers to data on traffic accidents that have occurred in the past at specific locations or intersections, and includes the date and time of the accident, the type of accident, and the extent of the damage.

[0856] "Current location information" is data indicating the current location of the vehicle, and is usually obtained using a location information system such as GPS.

[0857] The "current date and time" is data indicating the date and time at which the vehicle is currently located.

[0858] "Weather information" is data that indicates the current weather conditions, and specifically includes weather such as sunny, cloudy, rainy, and snowy, as well as temperature and humidity.

[0859] "Traffic risk" is an index that indicates the degree of possibility of a traffic accident occurring at a particular location or intersection.

[0860] "Generative AI" is a type of artificial intelligence that autonomously analyzes and predicts based on acquired data, and refers to a model that provides the optimal risk assessment for the input data.

[0861] The "means for notifying" refers to a means for providing a specific message or warning to the driver through audio or visual means based on the analysis results.

[0862] The present invention includes a system that analyzes traffic risks based on intersection identifiers, past accident data, current location information, current date and time, and weather information, and notifies drivers.

[0863] This system mainly uses the following hardware and software: The hardware uses the on-board computer and GPS module in the autonomous vehicle, and the software includes acquisition using Python and API, risk analysis using generative AI, and generative AI models.

[0864] Specifically, the server uses a GPS module to obtain intersection identifiers. After obtaining the location information and intersection identifiers, it calls a traffic accident data provision API to obtain past accident data. It then uses date and time information and weather forecast APIs to obtain the current date and time and weather information.

[0865] Based on this data, the generative AI model performs a traffic risk analysis. The analysis results are output as a traffic risk level, and the notification content for the driver varies depending on the risk level. If the risk is high, a warning message is displayed, and if the risk is low, a safety message is displayed.

[0866] When a driver approaches a specific intersection, the device acquires their current location information and sends it along with the intersection's identifier to a server. The server then acquires past traffic accident data via the National Police Agency's API, as well as the current date, time, and weather information. Based on the acquired data, the generative AI model performs a risk analysis and notifies the driver of the resulting traffic risk level.

[0867] As a specific example, when a driver approaches a specific intersection (e.g., intersection ID "abc123"), the device acquires the current location information and recognizes the intersection identifier "abc123." The acquired identifier is sent to the server along with accident data and weather data, and the generative AI model performs a risk analysis. If the analysis results in a risk level of 7, the device notifies the driver with a message saying, "Caution: This intersection has a high risk of accidents. Be especially careful when the weather is bad."

[0868] An example of a prompt is:

[0869] "I'm approaching intersection ID abc123. Do you have accident data for the past five years?"

[0870] "The weather report is cloudy. What is the risk level?"

[0871] As described above, the embodiments for carrying out the present invention have been specifically shown, and the invention can be effectively carried out.

[0872] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0873] Step 1:

[0874] The device obtains the vehicle's current location information using the GPS module, which provides the latitude and longitude information of the vehicle's current location (e.g., "35.6895,139.6917"), and then automatically recognizes the identifier of a specific intersection (e.g., "abc123") based on the current location.

[0875] Step 2:

[0876] The device sends the intersection identifier it recognized to the server. The server receives the intersection identifier and calls the National Police Agency's API to retrieve past accident data. This data includes the number of past accidents, the type of accident, the date and time of the accident, and details of the damage caused by the accident.

[0877] Step 3:

[0878] The server obtains the current date and time information, which gives the current year, month, date, and time (e.g., "October 12, 2023, 14:00").

[0879] Step 4:

[0880] The server uses a weather forecast API to retrieve current weather information, including the current weather (sunny, cloudy, rainy, snowy, etc.) and temperature (e.g., "cloudy, 20 degrees").

[0881] Step 5:

[0882] The server performs risk analysis using a generative AI model using past accident data, current date and time information, and weather information.Past accident data and current environmental conditions are passed to the model as input, and a traffic risk level is output as a number (e.g., "Risk Level 7").

[0883] Step 6:

[0884] The server sends the analysis results to the device. The device notifies the driver based on the received risk level. Different warning messages are displayed depending on the risk level. If the risk is high (risk level 7 or higher), a warning message is displayed stating, "Caution: This intersection has a high risk of accidents. Be careful, especially in bad weather."

[0885] Step 7:

[0886] Users can check the warning message on their device and be urged to pay particular attention while driving. By encouraging users to pay particular attention and maintain safe driving, it is expected that the risk of accidents at intersections will be reduced.

[0887] 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.

[0888] This invention is a system that effectively alerts the driver by integrating a generative AI that incorporates past accident data and current environmental conditions into a vehicle navigation system, and further combining it with an emotion engine that recognizes the driver's emotional state. The following is a specific example.

[0889] A natural language description of the program's operation

[0890] 1. Acquisition of initial data

[0891] The device obtains its current location information from GPS, detects that it has approached a specific intersection, and identifies the identifier of the detected intersection.

[0892] 2. Acquisition of accident data

[0893] The server receives the intersection identifier sent from the device and calls the National Police Agency's API to retrieve past accident data for that intersection, including the number of accidents, type of accident, date and time of the accident, and details of the damage caused by the accident.

[0894] 3. Obtaining the current environmental conditions

[0895] The device obtains the current date, time, and weather information. The weather information includes the current weather (sunny, cloudy, rainy, snowy, etc.) and temperature using the weather forecast API.

[0896] 4. Perform a risk analysis

[0897] The server uses a generation AI to perform risk analysis based on the acquired past accident data and current environmental conditions. The generation AI uses this data as input to predict the accident risk at a specific intersection. The prediction result is output as a risk level on a scale of 1 to 10.

[0898] 5. Emotional state analysis

[0899] The device activates an emotion engine to determine the driver's emotions. The emotion engine analyzes the driver's facial expressions and tone of voice through a camera and voice recognition system installed in the vehicle to evaluate the driver's emotional state. The evaluation results include the driver's stress level, attention state, and excitement level.

[0900] 6. Sending Risk Notifications

[0901] The device adjusts the notification content based on the risk analysis results and the driver's emotional state. For example, if the driver is under stress, the notification content will be more specific and detailed.

[0902] 7. Generating and Displaying Notification Content

[0903] The device will then take into account the results of the emotion engine and generate the most appropriate notification content to display to the driver. The specific notification content is as follows:

[0904] If the risk level is 7 or higher and the driver's stress level is high, a message will be displayed saying, "Warning: There is a high risk of accidents at this intersection. Please slow down and be aware of your surroundings."

[0905] If the risk level is 7 or higher and the driver's stress level is low, the system displays the message, "Caution: This intersection has a high risk of accidents. Be careful, especially in bad weather."

[0906] If the risk level is between 4 and 7, the message "Warning: Many accidents have occurred at this intersection in the past. Please drive carefully" will be displayed.

[0907] If the risk level is below 4, the message "This intersection is relatively safe" will be displayed.

[0908] Specific examples

[0909] When the user approaches a specific intersection (e.g., intersection ID "abc123"), the device obtains the current location information and recognizes the intersection's identifier "abc123." The device uses the identifier to send a request to the server. The server obtains accident data from the past five years via the National Police Agency's API, as well as the current date and time (e.g., 14:00, October 12, 2023) and weather information (e.g., cloudy).

[0910] Based on the acquired data, the server uses a generative AI to perform a risk analysis and determine the risk level as 7. At the same time, the device activates its emotion engine and determines that the driver is in a high stress state. Based on this, the device generates a notification message to the user: "Caution: There is a high risk of an accident at this intersection. Slow down and pay attention to your surroundings."

[0911] It is expected that users will receive this notification and take measures such as paying extra attention when driving and slowing down, thereby reducing the risk of accidents at intersections.

[0912] The processing flow will be explained below.

[0913] Step 1:

[0914] The device obtains its current location information from GPS, detects that it has approached a specific intersection, and identifies the identifier of the detected intersection.

[0915] Step 2:

[0916] The device sends the intersection identifier it has identified to the server, which includes the intersection ID and the current timestamp.

[0917] Step 3:

[0918] The server receives the intersection identifier and calls the National Police Agency's API to retrieve past accident data for that intersection, including the number of accidents, type of accident, date and time of the accident, and details of the damage caused by the accident.

[0919] Step 4:

[0920] The device obtains the current date, time, and weather information. Weather information is obtained using the weather forecast API to obtain the current weather (sunny, cloudy, rainy, snowy, etc.) and temperature.

[0921] Step 5:

[0922] The server uses a generation AI to perform risk analysis based on the acquired past accident data and current environmental conditions. The generation AI uses this data as input to predict the accident risk at a specific intersection. The prediction result is output as a risk level on a scale of 1 to 10.

[0923] Step 6:

[0924] The device activates an emotion engine to recognize the driver's emotional state. The emotion engine analyzes the driver's facial expressions and tone of voice through a camera and voice recognition system installed in the vehicle, and evaluates the driver's emotional state. The evaluation results include the driver's stress level, attention state, and excitement level.

[0925] Step 7:

[0926] The device adjusts the notification content based on the risk analysis results and the driver's emotional state. For example, if the driver is under stress, the notification content will be more specific and detailed.

[0927] Step 8:

[0928] The device generates and displays notifications to the driver, which vary depending on the risk level and the driver's emotional state.

[0929] If the risk level is 7 or higher and the driver's stress level is high, a message will be displayed saying, "Warning: There is a high risk of accidents at this intersection. Please slow down and be aware of your surroundings."

[0930] If the risk level is 7 or higher and the driver's stress level is low, the system displays the message, "Caution: This intersection has a high risk of accidents. Be careful, especially in bad weather."

[0931] If the risk level is between 4 and 7, the message "Warning: Many accidents have occurred at this intersection in the past. Please drive carefully" will be displayed.

[0932] If the risk level is below 4, the message "This intersection is relatively safe" will be displayed.

[0933] Step 9:

[0934] Users receive notifications and decide whether to drive with extra caution, and take measures such as slowing down if necessary.

[0935] Example 2

[0936] 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."

[0937] Conventional vehicle navigation systems have provided driver warnings based on location information and past accident data, but these alone are unable to adequately assess risk by taking into account the current environmental conditions and the driver's emotional state, making it difficult to provide effective warnings. In particular, the lack of proper consideration of the driver's emotional state can lead to incorrect decisions in stressful situations.

[0938] 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.

[0939] In this invention, the server includes means for acquiring current location information, means for acquiring intersection identifiers, means for acquiring past accident data, means for acquiring the current date and time and environmental conditions, means for analyzing the emotional state of the driver, means for analyzing the accident risk based on the past accident data, the current date and time, environmental conditions, and the emotional state of the driver, and means for notifying the driver based on the analyzed accident risk. This enables more accurate risk assessment based on the current environmental conditions and the emotional state of the driver, and warnings appropriate for each individual driver.

[0940] "Current location information" means data about the vehicle's real-time geographic location obtained by the vehicle's navigation system using location technology such as GPS.

[0941] An "intersection identifier" is an identification number or code that uniquely identifies a particular intersection.

[0942] "Past accident data" is a record of accidents that have occurred in specific areas or intersections, and includes detailed information such as the number of accidents, the type of accident, the date and time, and the extent of the damage.

[0943] "Current date and time" refers to real-time time and date information.

[0944] "Environmental conditions" is information that indicates the external environmental state, such as the current weather (sunny, cloudy, rainy, snowy, etc.) and temperature.

[0945] "Driver's emotional state" refers to the driver's psychological state, such as stress level, attention state, and excitement level, which is analyzed using sensors such as cameras and voice recognition systems.

[0946] "Accident risk" is a score or index that indicates the likelihood of an accident occurring at a particular location, assessed based on acquired data.

[0947] "Generative AI" is an artificial intelligence model that uses acquired data to predict accident risk.

[0948] "Notification" refers to a message or warning provided to the driver based on the results of risk analysis.

[0949] This invention is a system that performs risk analysis by combining past accident data, current environmental conditions, and the emotional state of the driver to improve safety in vehicle navigation systems, and provides optimal warnings to the driver.

[0950] 1. Acquisition of initial data

[0951] The device obtains current location information from a GPS module (e.g., u-blox NEO-M8N). This allows the device to determine the vehicle's current location in real time and, by comparing it with a database, detect when it has approached a specific intersection. The device then obtains the identifier of the detected intersection (e.g., ID "abc123").

[0952] 2. Acquisition of accident data

[0953] The server receives the intersection identifier sent from the device and calls the National Police Agency's API to retrieve past accident data for that intersection, including the number of accidents, type of accident, date and time of the accident, and details of damage caused by the accident.

[0954] 3. Obtaining the current environmental conditions

[0955] The device obtains the current date, time, and weather information. The weather information is obtained from the weather forecast API and includes the current weather (sunny, cloudy, rainy, snowy, etc.) and temperature.

[0956] 4. Perform a risk analysis

[0957] The server uses a generative AI model to analyze risk based on past accident data and current environmental conditions. The generative AI model (e.g., a model using TensorFlow or PyTorch) takes this data as input and predicts the accident risk at a particular intersection on a scale of 1 to 10.

[0958] 5. Emotional state analysis

[0959] The device activates an emotion engine to determine the driver's emotional state. The emotion engine uses an in-car camera (e.g., a standard webcam) and a voice recognition system (e.g., a voice recognition API) to analyze the driver's facial expressions and tone of voice to assess the driver's stress level, attention state, and excitement level.

[0960] 6. Sending Risk Notifications

[0961] The device adjusts the notification content based on the results of risk analysis and the driver's emotional state. If the driver is in a high stress state, the notification content will be more specific and detailed, depending on the situation.

[0962] 7. Generating and Displaying Notification Content

[0963] The device will then take into account the results of the emotion engine to generate and display the most appropriate notification content to the driver. For example, if the risk level is 7 or higher and the driver's stress level is high, the device will display the message "Caution: There is a high risk of an accident at this intersection. Please reduce your speed and be aware of your surroundings."

[0964] Specific examples

[0965] When a user approaches a specific intersection (e.g., intersection ID "abc123"), the device obtains the user's current location and recognizes the intersection's identifier "abc123." This identifier is used to send a request to the server, which obtains accident data from the past five years via the National Police Agency's API, as well as the current date and time (e.g., 14:00, October 12, 2023) and weather information (e.g., cloudy). The server analyzes this data and determines that the risk level is 7. If the emotion engine also determines that the driver is in a high state of stress, the device generates and displays a notification to the user stating, "Caution: There is a high risk of an accident at this intersection. Slow down and pay attention to your surroundings."

[0966] Prompt Sentence Examples

[0967] "Generate notifications for drivers approaching specific intersections based on accident risk and the driver's emotional state. Use historical accident data, current weather conditions, and driver emotion analysis as data sources."

[0968] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0969] Step 1:

[0970] The device obtains current location information. Using a GPS module (e.g., u-blox NEO-M8N) as input, the device obtains the vehicle's current location data as output. The data is then processed by checking the location information against the OpenStreetMap database to determine whether the device has reached a specific intersection and extracting the intersection's identifier (e.g., ID "abc123").

[0971] Step 2:

[0972] The terminal sends the extracted intersection identifier to the server. The intersection identifier is the input and the request sent to the server is the output. The LTE module is used for communication.

[0973] Step 3:

[0974] Based on the intersection identifier received by the server, the server calls the National Police Agency's API to obtain past accident data. The input is the intersection identifier, and the output is past accident data (number of accidents, type, date and time, damage details). The data is calculated by processing the API request and response.

[0975] Step 4:

[0976] The device obtains the current date and time and weather information. The current date and time and weather forecast API are used as input, and the current weather (sunny, cloudy, rainy, snowy, etc.) and temperature are obtained as output. Data processing involves processing API requests and responses.

[0977] Step 5:

[0978] The server performs risk analysis using a generative AI model based on past accident data and current environmental conditions. The inputs are past accident data and current environmental conditions, and the output is a risk level (on a scale of 1 to 10). For data calculations, the data is input into a generative AI model (e.g., TensorFlow or PyTorch) to predict the risk level.

[0979] Step 6:

[0980] The device runs an emotion engine to analyze the driver's emotional state. It uses an in-car camera (e.g., a standard webcam) and a voice recognition system (e.g., a voice recognition API) as input, and evaluates the driver's stress level, attention state, and excitement level as output. Data calculations analyze video and audio data to determine the driver's emotional state.

[0981] Step 7:

[0982] The device adjusts the notification content based on the risk analysis results and the driver's emotional state. The inputs are the risk level and the driver's emotional state, and the output is the adjusted notification message. The data is then processed to generate an appropriate message based on the risk level and emotional state.

[0983] Step 8:

[0984] The terminal displays the generated notification content on the driver panel. The adjusted notification message is the input, and the display to the driver is the output. Specifically, the terminal sends an instruction to the display system to display the message on the panel.

[0985] (Application example 2)

[0986] 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."

[0987] Conventional vehicle navigation systems lack the functionality to warn drivers by taking into account past accident data and environmental information, and therefore do not contribute to sufficient improvements in road safety. Another problem is that they are unable to analyze the driver's emotional state in real time and provide appropriate notifications based on that state. Therefore, there is a need for a system that can provide appropriate and effective warnings when a vehicle approaches an intersection or a high-risk location.

[0988] 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.

[0989] In this invention, the server includes means for acquiring geographic information including intersections, means for acquiring past accident data from information providers, means for acquiring current location data, means for acquiring current time and weather information, means for assessing accident risk based on past accident data, current time and weather information, means for issuing a warning to the driver based on the assessed accident risk, means for assessing the emotional state of the driver, and means for adjusting the content of the warning based on the risk assessment result and the emotional state of the driver. This enables risk analysis based on past accident data and current environmental information and appropriate warnings according to the emotional state of the driver.

[0990] "Geographic information including intersections" refers to all information on a map, including the layout of roads and the locations of intersections.

[0991] "Information providers" are public or private organizations that provide past traffic accident data and weather information.

[0992] "Current location data" means information indicating the current geographic location of the vehicle, primarily obtained from GPS.

[0993] "Current time and weather information" is information including the current date, time, and weather conditions (for example, sunny, rainy, snowy, etc.).

[0994] "Means for assessing accident risk" are techniques and methods that use past accident data and current environmental conditions to analyze the possibility of an accident occurring at a specific location.

[0995] "Means of warning" refers to technologies and methods that warn drivers by voice, screen display, etc., based on the analyzed accident risk.

[0996] "Driver's emotional state" refers to the driver's mental state, including states such as stress, distraction, excitement, and relaxation.

[0997] The "means for assessing emotional state" refers to a technology or method that uses a camera or a voice recognition system to analyze the driver's facial expressions and tone of voice to assess the driver's emotional state.

[0998] "Means for adjusting the warning content" refers to a technology or method for generating and displaying a warning message with optimal content and format based on the driver's emotional state and the results of risk assessment.

[0999] A "generative AI model" is an artificial intelligence model that generates new information and results based on data, and is primarily used to analyze accident risks.

[1000] This invention is a system that effectively alerts the driver by integrating a generative AI that incorporates past accident data and current environmental conditions into a vehicle navigation system, and by combining it with an emotion engine that recognizes the driver's emotional state. Each element will be explained in detail below.

[1001] The system is composed of the following hardware and software: First, a GPS module is used to obtain the vehicle's current location data, which allows the system to identify when the vehicle will approach a specific intersection. The current date, time, and weather information is obtained using a weather forecast API, which allows the system to obtain the latest information about the driving environment.

[1002] Next, a request is sent via a REST API to obtain past accident data from an information provider (e.g., the National Police Agency). The obtained accident data includes the number of past accidents, the type of accident, the date of the accident, and details of the damage caused by the accident.

[1003] The server uses a generative AI model to assess risk based on the acquired past accident data and current environmental conditions. The generative AI model uses this data as input to predict the accident risk at a specific intersection. The prediction result is output as an accident risk level on a scale of 1 to 10.

[1004] Furthermore, a camera and voice recognition system are installed inside the vehicle to assess the driver's emotional state. The camera recognizes the driver's facial expressions, and the voice recognition system analyzes the driver's tone of voice. Based on this data, the emotion engine assesses the driver's emotional state (e.g., stress level, distraction level, excitement level, etc.).

[1005] The device adjusts the notification content based on the risk assessment result and the driver's emotional state. The notification is displayed visually and audibly to the driver. For example, if the risk level is high and the driver is stressed, the device will display a message saying, "Caution: There is a high risk of an accident at this intersection. Please reduce your speed and be aware of your surroundings."

[1006] As a specific example, when a user approaches a specific intersection (e.g., intersection ID "abc123"), the device obtains its current location information and recognizes the intersection's identifier "abc123." When the device sends a request to the server using the identifier, the server obtains accident data from the past five years via the information provider's API, as well as the current date, time, and weather information. Based on the obtained data, the server performs a risk analysis using a generative AI model and determines that the risk level is 7. At the same time, the device activates its emotion engine and determines that the driver is in a state of high stress. Based on this, the device generates a notification message to the user: "Caution: There is a high risk of accidents at this intersection. Slow down and pay attention to your surroundings."

[1007] An example of a prompt to input to a generative AI model is as follows:

[1008] Input data: accident data = { 'intersection_id': 'abc123', 'accidents': [ {'date': '2022-03-01', 'type': 'vehicle-vehicle', 'severity': 'minor injury'}, {'date': '2022-06-15', 'type': 'pedestrian-vehicle', 'severity': 'serious injury'} ]}, weather information = { 'date': '2023-10-12', 'weather': 'cloudy', 'temperature': 20} Please rate the accident risk level at this intersection from 1 to 10.

[1009] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1010] Step 1:

[1011] The device retrieves the current location data.

[1012] Input: Vehicle GPS data

[1013] How it works: The device uses the GPS module to get its current location and determine that an intersection is nearby.

[1014] Output: Current latitude and longitude and intersection identifier

[1015] Step 2:

[1016] The device obtains past accident data from information providers.

[1017] Input: Current location data and intersection identifier

[1018] How it works: The device uses the intersection identifier to send a request to the API of an information provider (e.g., the National Police Agency) to retrieve past accident data for a specific intersection.

[1019] Output: Past accident data (e.g., number of past accidents, type of accident, date and time of accident, details of damage caused by accident)

[1020] Step 3:

[1021] The device retrieves the current date, time, and weather information.

[1022] Input: Current system time

[1023] How it works: The device uses the weather forecast API to get the current time (e.g., date and time) and current weather information (e.g., weather, temperature).

[1024] Output: Current date, time and weather information

[1025] Step 4:

[1026] Risk assessment is performed using a generative AI model based on the data acquired by the server.

[1027] Input: Past accident data, current date and time, and weather information

[1028] How it works: The server inputs this data into a generative AI model to analyze the accident risk at a particular intersection. The generative AI model outputs a risk level on a scale of 1 to 10 based on the input data.

[1029] Output: Accident risk level

[1030] Step 5:

[1031] The device assesses the driver's emotional state.

[1032] Input: Driver's facial expression data and voice tone data

[1033] How it works: The device uses the vehicle's camera and voice recognition system to collect the driver's facial expressions and tone of voice. An emotion engine analyzes this data to assess the driver's emotional state (e.g., stress level, distraction, excitement).

[1034] Output: Driver's emotional state

[1035] Step 6:

[1036] The device tailors the notification content based on the risk assessment results and the driver's emotional state.

[1037] Input: Accident risk level, driver's emotional state

[1038] How it works: The device generates the most appropriate alert based on your risk level and emotional state. High-risk and high-stress alerts are more detailed and specific.

[1039] Output: Adjusted notification content

[1040] Step 7:

[1041] The terminal displays the notification content to the user.

[1042] Input: Adjusted notification content

[1043] Action: The device displays the notification to the user visually or audibly, for example, by displaying a message on the screen and providing a voice prompt.

[1044] Output: User notification

[1045] Specifically, when a user approaches a specific intersection, the device obtains location data and identifies the intersection's identifier. The device then obtains past accident data from information providers, as well as the current date, time, and weather information. The server uses this data to perform a risk assessment using a generative AI model. The device then analyzes the driver's facial expressions and tone of voice to assess their emotional state. The device then generates optimal notification content based on the risk assessment results and the driver's emotional state, and notifies the user visually and audibly.

[1046] 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.

[1047] 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.

[1048] 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.

[1049] [Fourth embodiment]

[1050] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1051] 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.

[1052] 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).

[1053] 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.

[1054] 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.

[1055] 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).

[1056] 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.

[1057] 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.

[1058] 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.

[1059] 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.

[1060] 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.

[1061] 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.

[1062] 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."

[1063] This invention is a system that effectively alerts drivers by integrating a generative AI that incorporates past accident data and current environmental conditions into a vehicle navigation system. The following is a specific example.

[1064] A natural language description of the program's operation

[1065] 1. Acquisition of initial data

[1066] The device obtains its current location and the identifier of the specific intersection, which is automatically obtained based on GPS data.

[1067] 2. Acquisition of accident data

[1068] The server receives the intersection identifier sent from the device and calls the National Police Agency's API to retrieve past accident data, including the number of accidents, type of accident, date and time of the accident, and details of the damage caused by the accident.

[1069] 3. Obtaining the current environmental conditions

[1070] The device obtains the current date, time, and weather information. The weather information is obtained using a weather forecast API, and specifically includes the current weather (sunny, cloudy, rainy, snowy, etc.) and temperature.

[1071] 4. Perform a risk analysis

[1072] The server uses a generative AI to perform risk analysis based on the acquired past accident data and current environmental conditions. The generative AI uses this data as input to predict the accident risk at a specific intersection. The prediction is output as a risk level on a scale of 1 to 10.

[1073] 5. Sending risk notifications

[1074] The device will then notify the driver based on the analysis results. The specific content of the notification will vary depending on the risk level.

[1075] If the risk level is 7 or higher, a message will be displayed saying, "Caution: This intersection has a high risk of accidents. Be careful, especially in bad weather."

[1076] If the risk level is between 4 and 7, the message "Warning: Many accidents have occurred at this intersection in the past. Please drive carefully" will be displayed.

[1077] If the risk level is below 4, the message "This intersection is relatively safe" will be displayed.

[1078] Specific examples

[1079] When the user approaches a specific intersection (e.g., intersection ID "abc123"), the device obtains the user's current location information and recognizes the intersection's identifier "abc123." The device then uses the recognized identifier to send a request to the server. The server then obtains accident data from the past five years via the National Police Agency's API, as well as the current date and time (e.g., 14:00, October 12, 2023) and weather information (e.g., cloudy).

[1080] Based on the acquired data, the server uses a generative AI to perform a risk analysis and determines that the risk level of the intersection is 7. Because the risk level is high, the device notifies the user with the message, "Caution: This intersection has a high risk of accidents. Be careful, especially in bad weather."

[1081] It is expected that users will receive this notification and pay particular attention when driving, thereby reducing the risk of accidents at intersections.

[1082] The processing flow will be explained below.

[1083] Step 1:

[1084] The device obtains its current location information from GPS, detects that it has approached a specific intersection, and identifies the identifier of the detected intersection.

[1085] Step 2:

[1086] The device sends the intersection identifier it has identified to the server, which includes the intersection ID and the current timestamp.

[1087] Step 3:

[1088] The server receives the intersection identifier and calls the National Police Agency's API to retrieve past accident data for that intersection, including the number of accidents, type of accident, date and time of the accident, and details of the damage caused by the accident.

[1089] Step 4:

[1090] The device obtains the current date, time, and weather information. Weather information is obtained using the weather forecast API, including the current weather (sunny, cloudy, rainy, snowy, etc.) and temperature.

[1091] Step 5:

[1092] The server uses the AI ​​generator to perform risk analysis based on the acquired past accident data, current date, time, and weather information. The AI ​​uses this data as input to predict the accident risk at a specific intersection. The predicted result is output as a risk level on a scale of 1 to 10.

[1093] Step 6:

[1094] The device receives the analysis results and generates notification content according to the risk level.

[1095] Step 7:

[1096] The device generates and displays notifications to the driver, which vary depending on the risk level.

[1097] If the risk level is 7 or higher, a message will be displayed saying, "Caution: This intersection has a high risk of accidents. Be careful, especially in bad weather."

[1098] If the risk level is between 4 and 7, the message "Warning: Many accidents have occurred at this intersection in the past. Please drive carefully" will be displayed.

[1099] If the risk level is below 4, the message "This intersection is relatively safe" will be displayed.

[1100] Step 8:

[1101] Users receive notifications and decide whether to drive with extra caution, and take measures such as slowing down if necessary.

[1102] Example 1

[1103] 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."

[1104] Current vehicle navigation systems lack mechanisms to effectively notify drivers of accident risks at specific intersections. In particular, risk analysis that takes into account past accident data and current environmental conditions is lacking. Therefore, effective means to promote safe driving are needed.

[1105] 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.

[1106] In this invention, the server includes a means for acquiring current location information, a means for acquiring an intersection identifier, and a means for acquiring past accident data from an external database, thereby enabling the server to analyze the accident risk at a specific intersection based on the past accident data and the current environmental conditions, and effectively notify the driver of the result.

[1107] A "vehicle navigation system" is an electronic system that provides map information and route guidance to a driver.

[1108] "Means for obtaining current location information" refers to a device or software for identifying the current location of a vehicle using a GPS module or the like.

[1109] The "means for acquiring an intersection identifier" is a device or software for acquiring a unique identification (ID) for identifying an intersection.

[1110] The "means for obtaining past accident data from an external database" refers to a communications interface and associated software for obtaining accident data from an external source such as the National Police Agency.

[1111] "Means for obtaining current date, time and weather information" refers to a device or software for obtaining the current date, time and weather conditions from calendar information or weather forecast APIs.

[1112] The "means for analyzing accident risk" is software that predicts and assesses accident risk using a generative AI model based on past accident data and current environmental conditions.

[1113] "Means for notifying the driver" means a device or software for presenting a visual or audio warning message to the driver based on the risk of an accident.

[1114] A "generative AI model" refers to an artificial intelligence algorithm that makes predictions or generates based on specific input data.

[1115] This invention is a system that incorporates past accident data and current environmental conditions into a vehicle's navigation system and uses a generative AI model to effectively alert the driver. Specific implementation methods are described in detail below.

[1116] Initial setup and data acquisition

[1117] The device obtains its current location using a GPS module, which pinpoints the vehicle's exact location, and automatically obtains an intersection identifier by matching it with an internal mapping database. This identifier uniquely identifies a particular intersection.

[1118] Acquisition of past accident data

[1119] The device generates a request with the acquired intersection identifier and sends it to the server. Based on the received request, the server calls an external database (for example, the National Police Agency's API) to acquire past accident data. This data includes the number of past accidents, the type of accident, the date and time of the accident, details of the damage caused by the accident, etc. The acquired accident data is stored in an internal database.

[1120] Get current environmental conditions

[1121] The device retrieves the system date and time to determine the current date and time. In addition, it calls the weather forecast API to obtain current weather information (e.g., sunny, cloudy, rainy, snowy, etc.) and temperature. This information is important to reflect real-time environmental conditions.

[1122] Performing risk analysis

[1123] The server compiles the acquired past accident data and current environmental conditions and inputs them into a generative AI model. This generative AI model is constructed using, for example, a deep learning algorithm. The server uses the generative AI model to predict the accident risk at a specific intersection on a scale of 1 to 10. The predicted result is evaluated as a risk level and sent to the device.

[1124] Driver risk notification

[1125] The device determines the notification message to the driver based on the risk level received as a result of the analysis. The notification content varies depending on the risk level as follows:

[1126] If the risk level is 7 or higher, the message "Caution: There is a high risk of accidents at this intersection. Be careful, especially in bad weather." will be displayed.

[1127] If the risk level is between 4 and 6: The message "Warning: This intersection has had many accidents in the past. Please drive carefully" will be displayed.

[1128] If the risk level is 3 or lower: The message "This intersection is relatively safe" will be displayed.

[1129] The device notifies the driver of these messages visually and audibly, allowing them to sense danger in advance and drive safely.

[1130] Specific examples

[1131] When the user approaches a specific intersection (e.g., intersection ID "abc123"), the device obtains the current location information and recognizes the intersection identifier "abc123." The device uses the recognized identifier to send a request to the server. The server obtains accident data from the past five years via an external database API, and also obtains the current date and time (e.g., 14:00, October 12, 2023) and weather information (e.g., cloudy).

[1132] Based on the acquired data, the server performs a risk analysis using a generative AI model and determines that the risk level of the intersection is 7. Because the risk level is high, the device notifies the user with a message saying, "Caution: This intersection has a high risk of accidents. Please be especially careful in bad weather." The user is expected to receive this notification and pay particular attention when driving, thereby reducing the risk of accidents at intersections.

[1133] Prompt Sentence Examples

[1134] To predict the accident risk at a specific intersection, use a generative AI model to analyze past accident data and current weather information. Intersection ID: abc123, Current Date and Time: October 12, 2023, 14:00, Current Weather: Cloudy. Output the risk level on a scale of 1 to 10.

[1135] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1136] Step 1:

[1137] The device obtains the current location.

[1138] Input: Data obtained using a GPS module.

[1139] Output: Current latitude and longitude information.

[1140] Specific behavior:

[1141] The device will activate its built-in GPS module and obtain its current location information.

[1142] The acquired latitude and longitude information is stored in temporary memory within the device.

[1143] Step 2:

[1144] The terminal obtains an identifier for a particular intersection.

[1145] Input: Current latitude and longitude information.

[1146] Output: Intersection identifier (e.g. intersection ID "abc123").

[1147] Specific behavior:

[1148] The device checks its internal mapping database to obtain the intersection identifier that corresponds to the current latitude and longitude.

[1149] The acquired intersection identifier is stored in memory for subsequent processing.

[1150] Step 3:

[1151] The terminal generates a request including the intersection identifier and sends it to the server.

[1152] Input: Intersection identifier.

[1153] Output: The request to the server.

[1154] Specific behavior:

[1155] The terminal generates a request in HTTP format that includes the intersection identifier.

[1156] Send the generated request to the server.

[1157] Step 4:

[1158] The server retrieves past accident data from an external database.

[1159] Input: A request containing an intersection identifier.

[1160] Output: Historical accident data.

[1161] Specific behavior:

[1162] The server analyzes the received request and extracts the intersection identifier.

[1163] The server calls the National Police Agency's API to obtain past accident data for the relevant intersection identifier.

[1164] The acquired accident data is stored in an internal database.

[1165] Step 5:

[1166] The device retrieves the current date, time, and weather information.

[1167] Input: Current date and time, Weather API.

[1168] Output: Current weather information (e.g. sunny, cloudy, rainy, snowy, etc.) and temperature.

[1169] Specific behavior:

[1170] The device obtains the current date and time using the system's built-in clock.

[1171] Call the weather forecast API to get current weather information and temperature.

[1172] The acquired weather information is stored in memory.

[1173] Step 6:

[1174] The server inputs past accident data and current environmental conditions into a generative AI model.

[1175] Input: Past accident data, current date and time, current weather information.

[1176] Output: Accident risk level (1 to 10).

[1177] Specific behavior:

[1178] The server compiles past accident data, the current date and time, and weather information.

[1179] The compiled data is fed into a generative AI model.

[1180] A generative AI model analyzes accident risk and predicts risk levels.

[1181] A risk level is obtained as a prediction result and sent to the terminal as necessary.

[1182] Step 7:

[1183] The device notifies the driver based on the analysis results.

[1184] Input: Risk level.

[1185] Output: A warning message to be displayed to the driver.

[1186] Specific behavior:

[1187] The terminal determines a message according to the received risk level.

[1188] If the risk level is 7 or higher: Display the message "Caution: This intersection has a high risk of accidents. Be careful, especially in bad weather."

[1189] If the risk level is between 4 and 6: Display the message "Warning: Many accidents have occurred at this intersection in the past. Please drive carefully."

[1190] If the risk level is 3 or lower: Display the message "This intersection is relatively safe."

[1191] The determined message is notified to the driver visually and audibly.

[1192] (Application example 1)

[1193] 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."

[1194] Although conventional vehicle navigation systems take into account current location and weather information, they lack the functionality to integrate past traffic accident data for risk analysis. This makes it difficult to provide appropriate risk warnings based on past accident data at intersections or specific locations. Furthermore, there is a need to utilize generative AI for risk analysis to perform more accurate traffic risk assessments in real time.

[1195] 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.

[1196] In this invention, the server includes means for acquiring intersection identifiers, means for acquiring past accident data, means for acquiring current location information, means for acquiring current date and time and weather information, means for analyzing traffic risks based on the past accident data, the current date and time and weather information, and means for notifying the driver based on the analyzed traffic risks. This makes it possible to analyze traffic risks at intersections or specific locations in real time for the driver and provide a risk assessment that integrates past data and current environmental conditions using a generation AI.

[1197] An "intersection identifier" is a code or number that uniquely identifies a particular intersection.

[1198] "Past accident data" refers to data on traffic accidents that have occurred in the past at specific locations or intersections, and includes the date and time of the accident, the type of accident, and the extent of the damage.

[1199] "Current location information" is data indicating the current location of the vehicle, and is usually obtained using a location information system such as GPS.

[1200] The "current date and time" is data indicating the date and time at which the vehicle is currently located.

[1201] "Weather information" is data that indicates the current weather conditions, and specifically includes weather such as sunny, cloudy, rainy, and snowy, as well as temperature and humidity.

[1202] "Traffic risk" is an index that indicates the degree of possibility of a traffic accident occurring at a particular location or intersection.

[1203] "Generative AI" is a type of artificial intelligence that autonomously analyzes and predicts based on acquired data, and refers to a model that provides the optimal risk assessment for the input data.

[1204] The "means for notifying" refers to a means for providing a specific message or warning to the driver through audio or visual means based on the analysis results.

[1205] The present invention includes a system that analyzes traffic risks based on intersection identifiers, past accident data, current location information, current date and time, and weather information, and notifies drivers.

[1206] This system mainly uses the following hardware and software: The hardware uses the on-board computer and GPS module in the autonomous vehicle, and the software includes acquisition using Python and API, risk analysis using generative AI, and generative AI models.

[1207] Specifically, the server uses a GPS module to obtain intersection identifiers. After obtaining the location information and intersection identifiers, it calls a traffic accident data provision API to obtain past accident data. It then uses date and time information and weather forecast APIs to obtain the current date and time and weather information.

[1208] Based on this data, the generative AI model performs a traffic risk analysis. The analysis results are output as a traffic risk level, and the notification content for the driver varies depending on the risk level. If the risk is high, a warning message is displayed, and if the risk is low, a safety message is displayed.

[1209] When a driver approaches a specific intersection, the device acquires their current location information and sends it along with the intersection's identifier to a server. The server then acquires past traffic accident data via the National Police Agency's API, as well as the current date, time, and weather information. Based on the acquired data, the generative AI model performs a risk analysis and notifies the driver of the resulting traffic risk level.

[1210] As a specific example, when a driver approaches a specific intersection (e.g., intersection ID "abc123"), the device acquires the current location information and recognizes the intersection identifier "abc123." The acquired identifier is sent to the server along with accident data and weather data, and the generative AI model performs a risk analysis. If the analysis results in a risk level of 7, the device notifies the driver with a message saying, "Caution: This intersection has a high risk of accidents. Be especially careful when the weather is bad."

[1211] An example of a prompt is:

[1212] "I'm approaching intersection ID abc123. Do you have accident data for the past five years?"

[1213] "The weather report is cloudy. What is the risk level?"

[1214] As described above, the embodiments for carrying out the present invention have been specifically shown, and the invention can be effectively carried out.

[1215] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1216] Step 1:

[1217] The device obtains the vehicle's current location information using the GPS module, which provides the latitude and longitude information of the vehicle's current location (e.g., "35.6895,139.6917"), and then automatically recognizes the identifier of a specific intersection (e.g., "abc123") based on the current location.

[1218] Step 2:

[1219] The device sends the intersection identifier it recognized to the server. The server receives the intersection identifier and calls the National Police Agency's API to retrieve past accident data. This data includes the number of past accidents, the type of accident, the date and time of the accident, and details of the damage caused by the accident.

[1220] Step 3:

[1221] The server obtains the current date and time information, which gives the current year, month, date, and time (e.g., "October 12, 2023, 14:00").

[1222] Step 4:

[1223] The server uses a weather forecast API to retrieve current weather information, including the current weather (sunny, cloudy, rainy, snowy, etc.) and temperature (e.g., "cloudy, 20 degrees").

[1224] Step 5:

[1225] The server performs risk analysis using a generative AI model using past accident data, current date and time information, and weather information.Past accident data and current environmental conditions are passed to the model as input, and a traffic risk level is output as a number (e.g., "Risk Level 7").

[1226] Step 6:

[1227] The server sends the analysis results to the device. The device notifies the driver based on the received risk level. Different warning messages are displayed depending on the risk level. If the risk is high (risk level 7 or higher), a warning message is displayed stating, "Caution: This intersection has a high risk of accidents. Be careful, especially in bad weather."

[1228] Step 7:

[1229] Users can check the warning message on their device and be urged to pay particular attention while driving. By encouraging users to pay particular attention and maintain safe driving, it is expected that the risk of accidents at intersections will be reduced.

[1230] 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.

[1231] This invention is a system that effectively alerts the driver by integrating a generative AI that incorporates past accident data and current environmental conditions into a vehicle navigation system, and further combining it with an emotion engine that recognizes the driver's emotional state. The following is a specific example.

[1232] A natural language description of the program's operation

[1233] 1. Acquisition of initial data

[1234] The device obtains its current location information from GPS, detects that it has approached a specific intersection, and identifies the identifier of the detected intersection.

[1235] 2. Acquisition of accident data

[1236] The server receives the intersection identifier sent from the device and calls the National Police Agency's API to retrieve past accident data for that intersection, including the number of accidents, type of accident, date and time of the accident, and details of the damage caused by the accident.

[1237] 3. Obtaining the current environmental conditions

[1238] The device obtains the current date, time, and weather information. The weather information includes the current weather (sunny, cloudy, rainy, snowy, etc.) and temperature using the weather forecast API.

[1239] 4. Perform a risk analysis

[1240] The server uses a generation AI to perform risk analysis based on the acquired past accident data and current environmental conditions. The generation AI uses this data as input to predict the accident risk at a specific intersection. The prediction result is output as a risk level on a scale of 1 to 10.

[1241] 5. Emotional state analysis

[1242] The device activates an emotion engine to determine the driver's emotions. The emotion engine analyzes the driver's facial expressions and tone of voice through a camera and voice recognition system installed in the vehicle to evaluate the driver's emotional state. The evaluation results include the driver's stress level, attention state, and excitement level.

[1243] 6. Sending Risk Notifications

[1244] The device adjusts the notification content based on the risk analysis results and the driver's emotional state. For example, if the driver is under stress, the notification content will be more specific and detailed.

[1245] 7. Generating and Displaying Notification Content

[1246] The device will then take into account the results of the emotion engine and generate the most appropriate notification content to display to the driver. The specific notification content is as follows:

[1247] If the risk level is 7 or higher and the driver's stress level is high, a message will be displayed saying, "Warning: There is a high risk of accidents at this intersection. Please slow down and be aware of your surroundings."

[1248] If the risk level is 7 or higher and the driver's stress level is low, the system displays the message, "Caution: This intersection has a high risk of accidents. Be careful, especially in bad weather."

[1249] If the risk level is between 4 and 7, the message "Warning: Many accidents have occurred at this intersection in the past. Please drive carefully" will be displayed.

[1250] If the risk level is below 4, the message "This intersection is relatively safe" will be displayed.

[1251] Specific examples

[1252] When the user approaches a specific intersection (e.g., intersection ID "abc123"), the device obtains the current location information and recognizes the intersection's identifier "abc123." The device uses the identifier to send a request to the server. The server obtains accident data from the past five years via the National Police Agency's API, as well as the current date and time (e.g., 14:00, October 12, 2023) and weather information (e.g., cloudy).

[1253] Based on the acquired data, the server uses a generative AI to perform a risk analysis and determine the risk level as 7. At the same time, the device activates its emotion engine and determines that the driver is in a high stress state. Based on this, the device generates a notification message to the user: "Caution: There is a high risk of an accident at this intersection. Slow down and pay attention to your surroundings."

[1254] It is expected that users will receive this notification and take measures such as paying extra attention when driving and slowing down, thereby reducing the risk of accidents at intersections.

[1255] The processing flow will be explained below.

[1256] Step 1:

[1257] The device obtains its current location information from GPS, detects that it has approached a specific intersection, and identifies the identifier of the detected intersection.

[1258] Step 2:

[1259] The device sends the intersection identifier it has identified to the server, which includes the intersection ID and the current timestamp.

[1260] Step 3:

[1261] The server receives the intersection identifier and calls the National Police Agency's API to retrieve past accident data for that intersection, including the number of accidents, type of accident, date and time of the accident, and details of the damage caused by the accident.

[1262] Step 4:

[1263] The device obtains the current date, time, and weather information. Weather information is obtained using the weather forecast API to obtain the current weather (sunny, cloudy, rainy, snowy, etc.) and temperature.

[1264] Step 5:

[1265] The server uses a generation AI to perform risk analysis based on the acquired past accident data and current environmental conditions. The generation AI uses this data as input to predict the accident risk at a specific intersection. The prediction result is output as a risk level on a scale of 1 to 10.

[1266] Step 6:

[1267] The device activates an emotion engine to recognize the driver's emotional state. The emotion engine analyzes the driver's facial expressions and tone of voice through a camera and voice recognition system installed in the vehicle, and evaluates the driver's emotional state. The evaluation results include the driver's stress level, attention state, and excitement level.

[1268] Step 7:

[1269] The device adjusts the notification content based on the risk analysis results and the driver's emotional state. For example, if the driver is under stress, the notification content will be more specific and detailed.

[1270] Step 8:

[1271] The device generates and displays notifications to the driver, which vary depending on the risk level and the driver's emotional state.

[1272] If the risk level is 7 or higher and the driver's stress level is high, a message will be displayed saying, "Warning: There is a high risk of accidents at this intersection. Please slow down and be aware of your surroundings."

[1273] If the risk level is 7 or higher and the driver's stress level is low, the system displays the message, "Caution: This intersection has a high risk of accidents. Be careful, especially in bad weather."

[1274] If the risk level is between 4 and 7, the message "Warning: Many accidents have occurred at this intersection in the past. Please drive carefully" will be displayed.

[1275] If the risk level is below 4, the message "This intersection is relatively safe" will be displayed.

[1276] Step 9:

[1277] Users receive notifications and decide whether to drive with extra caution, and take measures such as slowing down if necessary.

[1278] Example 2

[1279] 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."

[1280] Conventional vehicle navigation systems have provided driver warnings based on location information and past accident data, but these alone are unable to adequately assess risk by taking into account the current environmental conditions and the driver's emotional state, making it difficult to provide effective warnings. In particular, the lack of proper consideration of the driver's emotional state can lead to incorrect decisions in stressful situations.

[1281] 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.

[1282] In this invention, the server includes means for acquiring current location information, means for acquiring intersection identifiers, means for acquiring past accident data, means for acquiring the current date and time and environmental conditions, means for analyzing the emotional state of the driver, means for analyzing the accident risk based on the past accident data, the current date and time, environmental conditions, and the emotional state of the driver, and means for notifying the driver based on the analyzed accident risk. This enables more accurate risk assessment based on the current environmental conditions and the emotional state of the driver, and warnings appropriate for each individual driver.

[1283] "Current location information" means data about the vehicle's real-time geographic location obtained by the vehicle's navigation system using location technology such as GPS.

[1284] An "intersection identifier" is an identification number or code that uniquely identifies a particular intersection.

[1285] "Past accident data" is a record of accidents that have occurred in specific areas or intersections, and includes detailed information such as the number of accidents, the type of accident, the date and time, and the extent of the damage.

[1286] "Current date and time" refers to real-time time and date information.

[1287] "Environmental conditions" is information that indicates the external environmental state, such as the current weather (sunny, cloudy, rainy, snowy, etc.) and temperature.

[1288] "Driver's emotional state" refers to the driver's psychological state, such as stress level, attention state, and excitement level, which is analyzed using sensors such as cameras and voice recognition systems.

[1289] "Accident risk" is a score or index that indicates the likelihood of an accident occurring at a particular location, assessed based on acquired data.

[1290] "Generative AI" is an artificial intelligence model that uses acquired data to predict accident risk.

[1291] "Notification" refers to a message or warning provided to the driver based on the results of risk analysis.

[1292] This invention is a system that performs risk analysis by combining past accident data, current environmental conditions, and the emotional state of the driver to improve safety in vehicle navigation systems, and provides optimal warnings to the driver.

[1293] 1. Acquisition of initial data

[1294] The device obtains current location information from a GPS module (e.g., u-blox NEO-M8N). This allows the device to determine the vehicle's current location in real time and, by comparing it with a database, detect when it has approached a specific intersection. The device then obtains the identifier of the detected intersection (e.g., ID "abc123").

[1295] 2. Acquisition of accident data

[1296] The server receives the intersection identifier sent from the device and calls the National Police Agency's API to retrieve past accident data for that intersection, including the number of accidents, type of accident, date and time of the accident, and details of damage caused by the accident.

[1297] 3. Obtaining the current environmental conditions

[1298] The device obtains the current date, time, and weather information. The weather information is obtained from the weather forecast API and includes the current weather (sunny, cloudy, rainy, snowy, etc.) and temperature.

[1299] 4. Perform a risk analysis

[1300] The server uses a generative AI model to analyze risk based on past accident data and current environmental conditions. The generative AI model (e.g., a model using TensorFlow or PyTorch) takes this data as input and predicts the accident risk at a particular intersection on a scale of 1 to 10.

[1301] 5. Emotional state analysis

[1302] The device activates an emotion engine to determine the driver's emotional state. The emotion engine uses an in-car camera (e.g., a standard webcam) and a voice recognition system (e.g., a voice recognition API) to analyze the driver's facial expressions and tone of voice to assess the driver's stress level, attention state, and excitement level.

[1303] 6. Sending Risk Notifications

[1304] The device adjusts the notification content based on the results of risk analysis and the driver's emotional state. If the driver is in a high stress state, the notification content will be more specific and detailed, depending on the situation.

[1305] 7. Generating and Displaying Notification Content

[1306] The device will then take into account the results of the emotion engine to generate and display the most appropriate notification content to the driver. For example, if the risk level is 7 or higher and the driver's stress level is high, the device will display the message "Caution: There is a high risk of an accident at this intersection. Please reduce your speed and be aware of your surroundings."

[1307] Specific examples

[1308] When a user approaches a specific intersection (e.g., intersection ID "abc123"), the device obtains the user's current location and recognizes the intersection's identifier "abc123." This identifier is used to send a request to the server, which obtains accident data from the past five years via the National Police Agency's API, as well as the current date and time (e.g., 14:00, October 12, 2023) and weather information (e.g., cloudy). The server analyzes this data and determines that the risk level is 7. If the emotion engine also determines that the driver is in a high state of stress, the device generates and displays a notification to the user stating, "Caution: There is a high risk of an accident at this intersection. Slow down and pay attention to your surroundings."

[1309] Prompt Sentence Examples

[1310] "Generate notifications for drivers approaching specific intersections based on accident risk and the driver's emotional state. Use historical accident data, current weather conditions, and driver emotion analysis as data sources."

[1311] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1312] Step 1:

[1313] The device obtains current location information. Using a GPS module (e.g., u-blox NEO-M8N) as input, the device obtains the vehicle's current location data as output. The data is then processed by checking the location information against the OpenStreetMap database to determine whether the device has reached a specific intersection and extracting the intersection's identifier (e.g., ID "abc123").

[1314] Step 2:

[1315] The terminal sends the extracted intersection identifier to the server. The intersection identifier is the input and the request sent to the server is the output. The LTE module is used for communication.

[1316] Step 3:

[1317] Based on the intersection identifier received by the server, the server calls the National Police Agency's API to obtain past accident data. The input is the intersection identifier, and the output is past accident data (number of accidents, type, date and time, damage details). The data is calculated by processing the API request and response.

[1318] Step 4:

[1319] The device obtains the current date and time and weather information. The current date and time and weather forecast API are used as input, and the current weather (sunny, cloudy, rainy, snowy, etc.) and temperature are obtained as output. Data processing involves processing API requests and responses.

[1320] Step 5:

[1321] The server performs risk analysis using a generative AI model based on past accident data and current environmental conditions. The inputs are past accident data and current environmental conditions, and the output is a risk level (on a scale of 1 to 10). For data calculations, the data is input into a generative AI model (e.g., TensorFlow or PyTorch) to predict the risk level.

[1322] Step 6:

[1323] The device runs an emotion engine to analyze the driver's emotional state. It uses an in-car camera (e.g., a standard webcam) and a voice recognition system (e.g., a voice recognition API) as input, and evaluates the driver's stress level, attention state, and excitement level as output. Data calculations analyze video and audio data to determine the driver's emotional state.

[1324] Step 7:

[1325] The device adjusts the notification content based on the risk analysis results and the driver's emotional state. The inputs are the risk level and the driver's emotional state, and the output is the adjusted notification message. The data is then processed to generate an appropriate message based on the risk level and emotional state.

[1326] Step 8:

[1327] The terminal displays the generated notification content on the driver panel. The adjusted notification message is the input, and the display to the driver is the output. Specifically, the terminal sends an instruction to the display system to display the message on the panel.

[1328] (Application example 2)

[1329] 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."

[1330] Conventional vehicle navigation systems lack the functionality to warn drivers by taking into account past accident data and environmental information, and therefore do not contribute to sufficient improvements in road safety. Another problem is that they are unable to analyze the driver's emotional state in real time and provide appropriate notifications based on that state. Therefore, there is a need for a system that can provide appropriate and effective warnings when a vehicle approaches an intersection or a high-risk location.

[1331] 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.

[1332] In this invention, the server includes means for acquiring geographic information including intersections, means for acquiring past accident data from information providers, means for acquiring current location data, means for acquiring current time and weather information, means for assessing accident risk based on past accident data, current time and weather information, means for issuing a warning to the driver based on the assessed accident risk, means for assessing the emotional state of the driver, and means for adjusting the content of the warning based on the risk assessment result and the emotional state of the driver. This enables risk analysis based on past accident data and current environmental information and appropriate warnings according to the emotional state of the driver.

[1333] "Geographic information including intersections" refers to all information on a map, including the layout of roads and the locations of intersections.

[1334] "Information providers" are public or private organizations that provide past traffic accident data and weather information.

[1335] "Current location data" means information indicating the current geographic location of the vehicle, primarily obtained from GPS.

[1336] "Current time and weather information" is information including the current date, time, and weather conditions (for example, sunny, rainy, snowy, etc.).

[1337] "Means for assessing accident risk" are techniques and methods that use past accident data and current environmental conditions to analyze the possibility of an accident occurring at a specific location.

[1338] "Means of warning" refers to technologies and methods that warn drivers by voice, screen display, etc., based on the analyzed accident risk.

[1339] "Driver's emotional state" refers to the driver's mental state, including states such as stress, distraction, excitement, and relaxation.

[1340] The "means for assessing emotional state" refers to a technology or method that uses a camera or a voice recognition system to analyze the driver's facial expressions and tone of voice to assess the driver's emotional state.

[1341] "Means for adjusting the warning content" refers to a technology or method for generating and displaying a warning message with optimal content and format based on the driver's emotional state and the results of risk assessment.

[1342] A "generative AI model" is an artificial intelligence model that generates new information and results based on data, and is primarily used to analyze accident risks.

[1343] This invention is a system that effectively alerts the driver by integrating a generative AI that incorporates past accident data and current environmental conditions into a vehicle navigation system, and by combining it with an emotion engine that recognizes the driver's emotional state. Each element will be explained in detail below.

[1344] The system is composed of the following hardware and software: First, a GPS module is used to obtain the vehicle's current location data, which allows the system to identify when the vehicle will approach a specific intersection. The current date, time, and weather information is obtained using a weather forecast API, which allows the system to obtain the latest information about the driving environment.

[1345] Next, a request is sent via a REST API to obtain past accident data from an information provider (e.g., the National Police Agency). The obtained accident data includes the number of past accidents, the type of accident, the date of the accident, and details of the damage caused by the accident.

[1346] The server uses a generative AI model to assess risk based on the acquired past accident data and current environmental conditions. The generative AI model uses this data as input to predict the accident risk at a specific intersection. The prediction result is output as an accident risk level on a scale of 1 to 10.

[1347] Furthermore, a camera and voice recognition system are installed inside the vehicle to assess the driver's emotional state. The camera recognizes the driver's facial expressions, and the voice recognition system analyzes the driver's tone of voice. Based on this data, the emotion engine assesses the driver's emotional state (e.g., stress level, distraction level, excitement level, etc.).

[1348] The device adjusts the notification content based on the risk assessment result and the driver's emotional state. The notification is displayed visually and audibly to the driver. For example, if the risk level is high and the driver is stressed, the device will display a message saying, "Caution: There is a high risk of an accident at this intersection. Please reduce your speed and be aware of your surroundings."

[1349] As a specific example, when a user approaches a specific intersection (e.g., intersection ID "abc123"), the device obtains its current location information and recognizes the intersection's identifier "abc123." When the device sends a request to the server using the identifier, the server obtains accident data from the past five years via the information provider's API, as well as the current date, time, and weather information. Based on the obtained data, the server performs a risk analysis using a generative AI model and determines that the risk level is 7. At the same time, the device activates its emotion engine and determines that the driver is in a state of high stress. Based on this, the device generates a notification message to the user: "Caution: There is a high risk of accidents at this intersection. Slow down and pay attention to your surroundings."

[1350] An example of a prompt to input to a generative AI model is as follows:

[1351] Input data: accident data = { 'intersection_id': 'abc123', 'accidents': [ {'date': '2022-03-01', 'type': 'vehicle-vehicle', 'severity': 'minor injury'}, {'date': '2022-06-15', 'type': 'pedestrian-vehicle', 'severity': 'serious injury'} ]}, weather information = { 'date': '2023-10-12', 'weather': 'cloudy', 'temperature': 20} Please rate the accident risk level at this intersection from 1 to 10.

[1352] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1353] Step 1:

[1354] The device retrieves the current location data.

[1355] Input: Vehicle GPS data

[1356] How it works: The device uses the GPS module to get its current location and determine that an intersection is nearby.

[1357] Output: Current latitude and longitude and intersection identifier

[1358] Step 2:

[1359] The device obtains past accident data from information providers.

[1360] Input: Current location data and intersection identifier

[1361] How it works: The device uses the intersection identifier to send a request to the API of an information provider (e.g., the National Police Agency) to retrieve past accident data for a specific intersection.

[1362] Output: Past accident data (e.g., number of past accidents, type of accident, date and time of accident, details of damage caused by accident)

[1363] Step 3:

[1364] The device retrieves the current date, time, and weather information.

[1365] Input: Current system time

[1366] How it works: The device uses the weather forecast API to get the current time (e.g., date and time) and current weather information (e.g., weather, temperature).

[1367] Output: Current date, time and weather information

[1368] Step 4:

[1369] Risk assessment is performed using a generative AI model based on the data acquired by the server.

[1370] Input: Past accident data, current date and time, and weather information

[1371] How it works: The server inputs this data into a generative AI model to analyze the accident risk at a particular intersection. The generative AI model outputs a risk level on a scale of 1 to 10 based on the input data.

[1372] Output: Accident risk level

[1373] Step 5:

[1374] The device assesses the driver's emotional state.

[1375] Input: Driver's facial expression data and voice tone data

[1376] How it works: The device uses the vehicle's camera and voice recognition system to collect the driver's facial expressions and tone of voice. An emotion engine analyzes this data to assess the driver's emotional state (e.g., stress level, distraction, excitement).

[1377] Output: Driver's emotional state

[1378] Step 6:

[1379] The device tailors the notification content based on the risk assessment results and the driver's emotional state.

[1380] Input: Accident risk level, driver's emotional state

[1381] How it works: The device generates the most appropriate alert based on your risk level and emotional state. High-risk and high-stress alerts are more detailed and specific.

[1382] Output: Adjusted notification content

[1383] Step 7:

[1384] The terminal displays the notification content to the user.

[1385] Input: Adjusted notification content

[1386] Action: The device displays the notification to the user visually or audibly, for example, by displaying a message on the screen and providing a voice prompt.

[1387] Output: User notification

[1388] Specifically, when a user approaches a specific intersection, the device obtains location data and identifies the intersection's identifier. The device then obtains past accident data from information providers, as well as the current date, time, and weather information. The server uses this data to perform a risk assessment using a generative AI model. The device then analyzes the driver's facial expressions and tone of voice to assess their emotional state. The device then generates optimal notification content based on the risk assessment results and the driver's emotional state, and notifies the user visually and audibly.

[1389] 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.

[1390] 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.

[1391] 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.

[1392] 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.

[1393] 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.

[1394] 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.

[1395] 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).

[1396] 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.

[1397] 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."

[1398] 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.

[1399] 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).

[1400] 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.

[1401] 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.

[1402] 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.

[1403] 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.

[1404] 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.

[1405] 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.

[1406] 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.

[1407] 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.

[1408] 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.

[1409] 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.

[1410] The following is further disclosed regarding the above embodiment.

[1411] (Claim 1)

[1412] means for obtaining an intersection identifier in a navigation system of the vehicle;

[1413] A means of obtaining past accident data from the National Police Agency,

[1414] A means for obtaining current location information;

[1415] means for obtaining current date, time and weather information;

[1416] A means for analyzing accident risks based on past accident data, current date and time, and weather information;

[1417] a means for notifying a driver based on the analyzed accident risk;

[1418] A system including:

[1419] (Claim 2)

[1420] The system according to claim 1, wherein the analysis of accident risk is performed by generative AI.

[1421] (Claim 3)

[1422] 2. The system according to claim 1, wherein the notification to the driver includes a means for displaying a warning message with different content depending on the accident risk level.

[1423] "Example 1"

[1424] (Claim 1)

[1425] a means for acquiring current position information in a vehicle navigation system;

[1426] means for obtaining an intersection identifier;

[1427] A means for obtaining past accident data from an external database;

[1428] means for obtaining current date, time and weather information;

[1429] A means for analyzing accident risks based on past accident data, current date and time, and weather information;

[1430] a means for notifying a driver based on the analyzed accident risk;

[1431] A system including:

[1432] (Claim 2)

[1433] The system of claim 1, wherein the analysis of accident risk is performed using a generative AI model.

[1434] (Claim 3)

[1435] 2. The system according to claim 1, wherein the notification to the driver includes a means for displaying a warning message with different content depending on the accident risk level.

[1436] "Application Example 1"

[1437] (Claim 1)

[1438] means for obtaining an intersection identifier;

[1439] A means for obtaining past accident data;

[1440] A means for obtaining current location information;

[1441] means for obtaining the current date, time and weather information;

[1442] A means of analyzing traffic risks based on past accident data, current date and time, and weather information;

[1443] means for notifying a driver based on the analyzed traffic risk;

[1444] A system including:

[1445] (Claim 2)

[1446] The system of claim 1, wherein traffic risk analysis is performed by generative AI.

[1447] (Claim 3)

[1448] 2. The system of claim 1, wherein the notification to the driver includes a means for displaying a warning message with different content depending on the traffic risk level.

[1449] "Example 2: Combining Emotion Engines"

[1450] (Claim 1)

[1451] A means for obtaining current location information;

[1452] means for obtaining an intersection identifier;

[1453] A means for obtaining past accident data;

[1454] means for obtaining the current date, time and environmental conditions;

[1455] a means for analyzing the emotional state of the driver;

[1456] A means for analyzing accident risk based on past accident data, current date and time, environmental conditions, and the emotional state of the driver;

[1457] a means for notifying a driver based on the analyzed accident risk;

[1458] A system including:

[1459] (Claim 2)

[1460] The system according to claim 1, wherein the analysis of accident risk is performed by generative AI.

[1461] (Claim 3)

[1462] 2. The system of claim 1, wherein the notification to the driver includes displaying warning messages with different content depending on the accident risk level and the emotional state of the driver.

[1463] "Application example 2 when combining emotion engines"

[1464] (Claim 1)

[1465] A means for acquiring geographic information including intersections;

[1466] A means for obtaining past accident data from information providers;

[1467] a means for obtaining current location data;

[1468] a means of obtaining current weather information and weather information;

[1469] A means of assessing accident risk based on past accident data, current timing and weather information;

[1470] a means for issuing a driver's warning based on the assessed accident risk;

[1471] a means for assessing the emotional state of the driver;

[1472] a means for adjusting the warning content based on the risk assessment result and the driver's emotional state;

[1473] A system including:

[1474] (Claim 2)

[1475] The system of claim 1, wherein the assessment of accident risk is performed using a generative AI model.

[1476] (Claim 3)

[1477] 2. The system of claim 1, wherein the notification to the driver includes displaying a warning message with different content depending on the accident risk level and the emotional state of the driver. [Explanation of symbols]

[1478] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for obtaining an intersection identifier in a navigation system of the vehicle; A means of obtaining past accident data from the National Police Agency, A means for obtaining current location information; means for obtaining current date, time and weather information; A means for analyzing accident risks based on past accident data, current date and time, and weather information; a means for notifying a driver based on the analyzed accident risk; A system including:

2. The system according to claim 1, wherein the analysis of accident risk is performed by a generation AI.

3. 2. The system according to claim 1, wherein the notification to the driver includes a means for displaying a warning message with different content depending on the accident risk level.

Images