system

Abstract

Provide a system. [Solution] A means for collecting traffic accident information from the police; A means for storing the collected traffic accident information in a database; A means of analyzing past traffic accident data and identifying accident risk areas, A means for displaying the identified accident risk areas in combination with map data; A means of providing real-time accident risk information to car navigation systems, a means for displaying the provided accident risk information on a car navigation system and issuing a warning to a user; A system including:

Description

[Technical Field]

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

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

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

[0004] Currently, systems for predicting and preventing traffic accidents are not fully developed. In particular, there is a lack of means for effectively utilizing past accident data to warn drivers in real time. This leads to the problem that drivers continue driving without recognizing their own risk areas and are unable to avoid accidents in areas where accidents frequently occur. The present invention aims to solve this problem by providing a system that identifies accident risk areas based on past traffic accident data and effectively warns drivers. [Means for solving the problem]

[0005] The present invention solves the above problems by the following means. Specifically, it comprises a means for collecting traffic accident information from the police and a means for storing the collected traffic accident information in a database. It also comprises a means for analyzing past traffic accident data and identifying accident risk areas, and a means for integrating and displaying the identified accident risk areas with map data. It also includes a means for providing accident risk information to a car navigation system in real time, and a means for displaying the provided accident risk information on the car navigation system and issuing a warning to the user. As a result, drivers can recognize their own risk areas in advance and drive carefully, thereby reducing the risk of accidents occurring.

[0006] "Police" refers to an organization established by the national or local government to prevent and crack down on crime in order to maintain public safety and order.

[0007] "Traffic accident information" is data including the date and time, location, cause, circumstances, and details of damage caused by a traffic accident.

[0008] A "database" is a system for effectively storing, retrieving, and managing diverse collections of data.

[0009] "Past traffic accident data" is historical information about traffic accidents that occurred within a certain period of time.

[0010] An "accident risk area" is a geographic area that has been identified as having a high rate of traffic accidents in the past or a high probability of accidents occurring.

[0011] "Map data" is a collection of digital or analog data that represents geographic information.

[0012] "Real-time" refers to the immediate processing and provision of data and information without delay.

[0013] A "car navigation system" is a navigation system installed in a vehicle that displays map information and provides route guidance to a destination.

[0014] "User" refers to the driver or operator who uses this system.

[0015] A "warning" is a notification that notifies the user of danger or risk and calls their attention.

[0016] "Analysis" is the process of examining collected data and extracting meaningful information. [Brief explanation of the drawings]

[0017] [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

[0018] 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.

[0019] First, the terms used in the following description will be explained.

[0020] 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).

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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."

[0038] The system of this invention mainly consists of a server, a terminal (car navigation system), and a user. The functions and specific operations of each will be explained below.

[0039] 1. Data Collection

[0040] server

[0041] The server periodically connects to the police traffic accident database and collects traffic accident information, including the date, time, location, cause, circumstances, and damage details of the traffic accident.

[0042] The collected data is stored by the server in an internal database, which can use a relational database system such as SQLite or MySQL (registered trademark).

[0043] 2. Data analysis

[0044] server

[0045] The server queries and retrieves past traffic accident data from its built-in database.

[0046] The acquired data is analyzed to identify areas at risk of accidents. This analysis uses statistical methods to identify the locations, causes, and frequency of past accidents.

[0047] Identified risk areas are classified into high, medium, and low risk areas, for example, by setting risk levels based on the frequency and severity of accidents.

[0048] 3. Integration with map data

[0049] server

[0050] The location information (latitude and longitude data) of high-risk areas will be integrated with map data using GIS tools.

[0051] This integration allows risk areas to be visually displayed on a map with specific colors and icons, for example, red for high risk areas, yellow for medium risk areas, and green for low risk areas.

[0052] 4. Display on car navigation systems

[0053] Terminal (car navigation system)

[0054] The car navigation device retrieves risk information in real time from the server, which updates the data periodically using API calls.

[0055] The car navigation system visualizes the acquired risk information on a map, and displays icons and colors indicating risk areas on the map on the device to visually warn the user.

[0056] 5. Notice to Users

[0057] User

[0058] When a user approaches a risk area while driving using a car navigation device, the car navigation system will warn them with a voice message.

[0059] This voice warning includes detailed information about the risk area (for example, "This intersection is prone to collisions when turning right") and provides the user with specific precautions to take.

[0060] In addition, a warning message will be displayed on the car navigation screen, allowing users to visually recognize risk areas.

[0061] Specific examples

[0062] For example, suppose there have been more than 10 right-turn collisions at a certain intersection in the city center in the past year. Based on this information, the server identifies the intersection as "high risk" and integrates the latitude and longitude data into a map. The car navigation device retrieves this information from the server in real time and displays it on the map as a red icon.

[0063] When the user approaches this intersection, the car navigation system issues a voice warning saying, "There are many collisions when turning right at this intersection. Please drive carefully." At the same time, a warning message is displayed on the screen. This allows the user to recognize the risks in advance and drive carefully.

[0064] This system effectively utilizes past traffic accident data and provides users with realistic and immediate risk information, making it possible to prevent traffic accidents from occurring.

[0065] The processing flow will be explained below.

[0066] Step 1:

[0067] The server periodically connects to the police traffic accident database to collect traffic accident information, including the date, time, location, cause, circumstances, and details of the accident.

[0068] Step 2:

[0069] The server stores the collected traffic accident information in a built-in database, which can be used to efficiently manage and search the accident information using SQL queries.

[0070] Step 3:

[0071] The server queries the database for past traffic accident data and extracts the necessary information, particularly the location of the accident, the cause of the accident, and the frequency of the accident.

[0072] Step 4:

[0073] The server analyzes the extracted data to identify areas at risk of accidents, and uses statistical methods to evaluate the risk level of specific locations based on past accident data.

[0074] Step 5:

[0075] Based on the analysis results, the server classifies the identified accident risk areas into high, medium, and low risk categories, allowing for detailed risk assessment of each area.

[0076] Step 6:

[0077] The server integrates the location information (latitude and longitude data) of the risk area with map data, and this integration uses GIS tools to visually locate the risk area on a map.

[0078] Step 7:

[0079] The server displays risk areas on the map data in different colors: high risk areas in red, medium risk areas in yellow, and low risk areas in green.

[0080] Step 8:

[0081] The device (car navigation system) retrieves the latest accident risk information from the server in real time. This retrieval is periodically updated using API calls.

[0082] Step 9:

[0083] The risk information acquired by the device (car navigation system) is displayed on a map. Icons and colors indicating risk areas are reflected on the map, allowing users to visually confirm risks.

[0084] Step 10:

[0085] When the user approaches a risk area, the device (car navigation system) warns the user with a voice message, which includes specific points to be aware of (for example, "This intersection is prone to collisions when turning right").

[0086] Step 11:

[0087] The device (car navigation system) also displays a warning message on the screen, allowing the user to visually and audibly recognize and pay attention to risk information.

[0088] By repeating these steps, the risk of traffic accidents can be effectively reduced and users can be supported in safe driving.

[0089] Example 1

[0090] 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."

[0091] Conventional traffic information systems lack sufficient functionality to notify users of traffic accident risks in advance, and users are unable to recognize the risk even when they approach an accident risk area. In particular, there is a lack of methods to effectively utilize past accident data to prevent future traffic accidents.

[0092] 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.

[0093] In this invention, the server includes means for collecting traffic accident information from the police, means for storing the collected traffic accident information in a database, means for analyzing past traffic accident data and identifying accident risk areas, means for integrating and displaying the identified accident risk areas with map data, means for providing the accident risk information to the car navigation system in real time, means for displaying the provided accident risk information on the car navigation system and warning the user, and means for warning the user by voice message when the user approaches an accident risk area. This enables the user to recognize risk areas in advance while driving and encourages safe driving.

[0094] "Police" is a public institution used to collect traffic accident information.

[0095] "Traffic accident information" is data that includes the date, time, location, cause, circumstances, and details of damages related to traffic accidents.

[0096] A "database" is a system for systematically storing, managing, and searching collected traffic accident information.

[0097] "Analysis" is the process of evaluating and analyzing collected traffic accident information using statistical methods and identifying accident risk areas.

[0098] An "accident risk area" is a specific geographical area that is considered to have a high risk of traffic accidents based on past traffic accident data.

[0099] "Map Data" means a dataset containing geographic information represented using a Geographic Information System (GIS).

[0100] A "car navigation system" is an in-vehicle navigation system that displays real-time location information and map data and provides navigation information to users.

[0101] "Real time" is a time concept in which the latest information is processed and provided immediately.

[0102] A "voice message" is a communication method that conveys information to a user using voice.

[0103] "GIS tools" are software for creating, analyzing, and visualizing geographic information system data.

[0104] The system of this invention mainly consists of a server, a terminal (car navigation system), and a user, and while clarifying the roles of each component, it supports safe driving by notifying the user of traffic accident risks in advance. Specific examples are described below.

[0105] server

[0106] Data collection

[0107] The server periodically connects to the police traffic accident database to collect traffic accident information. Specifically, the server connects to the database via the police API at 2:00 AM every day to obtain the date and time of the accident, location (latitude and longitude), cause of the accident, accident situation, and details of the damage. This collected data is stored in an SQLite or MySQL database.

[0108] Data analysis

[0109] The server periodically queries and retrieves traffic accident data from the database for the past year. The retrieved data is analyzed using Python's Pandas library to identify accident risk areas. This analysis classifies areas into high, medium, or low risk based on the location, cause, and frequency of accidents. For example, an area with more than 10 accidents in a year is considered high risk.

[0110] Integration with map data

[0111] The location information (latitude and longitude data) of the identified accident risk areas is integrated with map data using a GIS tool such as QGIS. The integrated data is generated as a color-coded shapefile to visually display the risk areas. High-risk areas are shown in red, medium-risk areas in yellow, and low-risk areas in green.

[0112] Terminal (car navigation system)

[0113] Real-time information acquisition

[0114] The car navigation device makes an API call to the server every five minutes to obtain the latest accident risk information. This information is obtained using networks such as Wi-Fi and LTE.

[0115] Information Visualization

[0116] The acquired risk information is immediately reflected on the map, with red icons indicating high-risk areas, yellow icons indicating medium-risk areas, and green icons indicating low-risk areas.

[0117] User

[0118] Notification of approach to risk area

[0119] When a user approaches within 500 meters of an accident risk area while driving, the car navigation system will issue a warning voice message. For example, it may say, "There are many collisions when turning right at this intersection. Please drive carefully." At the same time, a warning message will also be displayed on the car navigation system screen. This will allow users to recognize the risk in advance and encourage safe driving.

[0120] Specific examples

[0121] If a certain intersection in a city center has more than 10 right-turn collisions per year, the server identifies this intersection as a "high-risk" area and integrates the latitude and longitude data into a map.

[0122] The car navigation device retrieves this information from the server in real time and displays it as a red icon on the map.

[0123] When the user approaches this intersection, a voice warning will sound, saying, "There are many collisions when turning right at this intersection. Please drive carefully." A risk area warning message will also be displayed on the screen.

[0124] Based on the above specific operational examples, this system effectively utilizes past traffic accident data and provides users with realistic and immediate risk information, thereby making it possible to prevent traffic accidents from occurring.

[0125] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0126] Step 1: Data collection

[0127] The server connects to the police traffic accident database. Through the API, it obtains the date and time of the traffic accident, location (latitude and longitude), cause, situation, and details of the damage. The input is raw data from the API, and the output is this data in a structured format (for example, JSON format).

[0128] The server stores the acquired traffic accident information in an SQLite or MySQL database. The input is structured traffic accident information, and the output is data saved in the database.

[0129] Step 2: Data analysis

[0130] The server queries and retrieves the traffic accident data from the database for the past year. It extracts the data using SQL queries. The input is the traffic accident data stored in the database, and the output is the dataset of the query results.

[0131] The server analyzes the acquired data using Python's Pandas library. The input is the query result dataset, and the output is the identification of accident risk areas (including locations, causes, and frequency).

[0132] Based on the analysis results, accident risk areas are classified as high risk, medium risk, or low risk. For example, an area where 10 or more accidents occur per year is classified as high risk. The input is the analysis results, and the output is area information classified by risk level.

[0133] Step 3: Integrating with map data

[0134] The server uses GIS tools such as QGIS to integrate the location information (latitude and longitude data) of identified accident risk areas into map data. The input is the location information of the risk area and the original map data, and the output is the integrated map data.

[0135] The merged data is generated as a color-coded shapefile, with high-risk areas shown in red, medium-risk areas in yellow, and low-risk areas in green. The input is the merged map data, and the output is a color-coded shapefile.

[0136] Step 4: Display on the car navigation system

[0137] The device (car navigation system) makes an API call to the server every five minutes to obtain the latest accident risk information. The input is an API request to the server, and the output is real-time accident risk information.

[0138] The acquired risk information is displayed on a map. Red icons are displayed for high-risk areas, yellow for medium-risk areas, and green for low-risk areas. The input is the acquired risk information, and the output is a visualized map display.

[0139] Step 5: Inform users of the risk

[0140] When the user approaches a risk area, the car navigation system will warn them with a voice message. The distance is measured using GPS data, and a warning is issued when the user approaches within 500 meters. The input is GPS location data, and the output is a voice message.

[0141] A warning message is also displayed on the car navigation screen, allowing users to visually recognize the risk. The input is GPS location data, and the output is a warning message on the screen.

[0142] (Application example 1)

[0143] 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."

[0144] For current autonomous vehicles, systems that provide immediate and appropriate warnings and responses to traffic accident risk areas have not been fully developed. As a result, it is difficult to detect traffic accident risks at specific locations in advance and respond appropriately, and the risk of accidents remains high. To solve this issue, a system is needed that issues real-time warnings when an autonomous vehicle approaches a traffic accident risk area and adjusts the vehicle's operation.

[0145] 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.

[0146] In this invention, the server includes means for collecting traffic accident information from the police, means for storing the collected traffic accident information in a database, and means for analyzing past traffic accident data and identifying accident risk areas, which enables means for integrating the identified accident risk areas with map data and displaying them, means for providing accident risk information to autonomous vehicles in real time, and means for displaying the provided accident risk information on the autonomous vehicles and adjusting their operation.

[0147] The "means of collecting traffic accident information from the police" refers to a system for automatically obtaining data on traffic accidents held by police agencies using communication means such as the Internet.

[0148] "Means for storing collected traffic accident information in a database" refers to technology for efficiently storing and managing acquired traffic accident data using a database management system such as SQL or NoSQL.

[0149] "Means for analyzing past traffic accident data and identifying accident risk areas" refers to a method for applying algorithms such as statistical analysis and machine learning to stored traffic accident data to evaluate and identify accident risks in specific areas based on past trends and patterns.

[0150] "Means for integrating and displaying identified accident risk areas with map data" refers to GIS (geographic information system) technology that integrates the location information (latitude and longitude data) of identified risk areas into digital map data and displays them visually.

[0151] "Means for providing accident risk information to autonomous vehicles in real time" refers to technology for instantly transmitting accident risk information analyzed on a server to autonomous vehicles via the Internet or a dedicated communication network.

[0152] "Means for displaying the provided accident risk information on the autonomous vehicle and adjusting the vehicle's operation" refers to technology that conveys the received accident risk information to the driver using displays and speakers inside the vehicle, and further issues warnings and instructions to adjust the vehicle's operation to the vehicle's control system.

[0153] The system that realizes this invention mainly includes three elements: a server, a terminal (a computer of an autonomous vehicle), and a user. Below, we will explain how each element works.

[0154] server

[0155] The server first collects traffic accident information from the police. This involves periodically connecting to the police traffic accident database via the Internet to obtain information such as the date, time, location, cause, circumstances, and details of the accident. The obtained data is stored using a relational database system such as SQLite or MySQL.

[0156] The server then queries and analyzes historical traffic accident data from its built-in database, using statistical methods and machine learning algorithms to classify accident risk areas into high, medium, or low risk categories, with risk levels determined based on the frequency and severity of accidents.

[0157] Furthermore, the server integrates the location information (latitude and longitude data) of high-risk areas with map data using GIS tools, which allows the risk areas to be visually displayed on the map with specific colors (e.g., red for high risk) and icons.

[0158] Terminal (autonomous vehicle computer)

[0159] The autonomous vehicle's computer retrieves risk information from the server in real time. This is done using an API, with the latest data being updated regularly. The acquired risk information is then communicated to the user via the vehicle's display and speaker. For example, a voice message or a screen display can be used to warn of risk areas.

[0160] The autonomous vehicle's computer can also automatically adjust the vehicle's behavior when approaching a risk area, for example by reducing speed or changing course.

[0161] User

[0162] Users receive warnings from this system while riding in an autonomous vehicle. Specifically, when approaching a risk area, they receive a voice message saying, "There are many accidents when turning right at this intersection. Please be careful." In addition, the risk area is displayed in color on the vehicle's display, allowing users to visually recognize the risk.

[0163] Specific examples

[0164] For example, if a certain intersection in a city center has experienced more than 10 right-turn collisions in the past year, the server will use this information to identify the intersection as "high risk" and integrate the latitude and longitude data into a map. The autonomous vehicle's computer will retrieve this information from the server in real time and display it as a red icon on the map. When the user approaches this intersection, a voice warning will sound, saying, "This intersection has a high rate of right-turn collisions. Please drive carefully," and the vehicle's speed will automatically decrease.

[0165] Prompt Sentence Examples

[0166] For example, a sample prompt for building this system using a generative AI model is as follows:

[0167] Please create a Python program to retrieve past traffic accident data from a traffic accident database and identify risk areas for traffic accidents. Please also include functionality to integrate this into the control system of an autonomous vehicle, including risk areas, and provide risk warnings in real time.

[0168] It retrieves data from the server, analyzes the data, identifies risk areas, and integrates the control of the autonomous vehicle. It also displays warnings based on the vehicle's current location and adjusts vehicle control if necessary.

[0169] In this way, by describing the specific embodiments of the invention, anyone can carry out the invention.

[0170] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0171] Step 1:

[0172] The server periodically connects to the police traffic accident database via the Internet to collect traffic accident information. Specifically, it obtains the date, time, location, cause, circumstances, and damage details of the traffic accident. The input of this process is the police database connection information, and the output is the obtained traffic accident data.

[0173] Step 2:

[0174] The server stores the acquired traffic accident data in a database (e.g., SQLite or MySQL), which allows for data organization and efficient management. The input of this process is the acquired traffic accident data, and the output is the information stored in the database.

[0175] Step 3:

[0176] The server queries past traffic accident data from its built-in database and performs data analysis, for example, using statistical methods and machine learning algorithms to analyze accident frequency and causes and identify accident risk areas. The input to this process is the traffic accident data stored in the database, and the output is the identified accident risk area information.

[0177] Step 4:

[0178] The server integrates the location information (latitude and longitude data) of the identified accident risk areas with map data using GIS tools. This integration makes it possible to visually display the risk areas on a map with specific colors and icons. The input of this process is accident risk area information, and the output is visualized map data.

[0179] Step 5:

[0180] The terminal (the computer in the autonomous vehicle) retrieves risk information from the server in real time. The latest data is updated periodically using an API. The input to this process is the latest risk information provided by the server, and the output is the risk information taken into the vehicle.

[0181] Step 6:

[0182] The terminal notifies the user of the acquired risk information through the display or speaker of the autonomous vehicle. For example, when approaching a specific risk area, a warning is given by voice message or on-screen display. The input of this process is the risk information taken into the vehicle, and the output is a visual and audio warning to the user.

[0183] Step 7:

[0184] The terminal automatically adjusts the vehicle's behavior when approaching a risk area, for example by slowing the vehicle down or instructing it to change course. The input to this process is real-time location and risk information, and the output is adjusted vehicle behavior.

[0185] Step 8:

[0186] While riding in an autonomous vehicle, the user receives warnings from the system. Specifically, when approaching a risk area, the user follows the voice message and visual display to drive safely. The input of this process is the warning information from the terminal, and the output is appropriate driving behavior.

[0187] Through these steps, the system provides appropriate traffic accident risk information to autonomous vehicles, enabling users and vehicles to work together to ensure safe driving.

[0188] 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.

[0189] The system of this invention consists of a server, a terminal (car navigation system), an emotion engine, and a user. The functions and specific operations of each will be explained below.

[0190] 1. Data Collection

[0191] server

[0192] The server periodically connects to the police traffic accident database to collect traffic accident information, including the date, time, location, cause, circumstances, and damage details of the accident.

[0193] This data is stored in an internal database and can be efficiently managed and searched using SQL queries.

[0194] 2. Data analysis

[0195] server

[0196] The server queries and retrieves past traffic accident data from the database.

[0197] The acquired data is analyzed to identify areas at risk of accidents. Statistical methods are used to identify areas where accidents have occurred in the past, including their causes and frequency.

[0198] Based on the results of the risk assessment, the identified accident risk areas are classified as high risk, medium risk, or low risk.

[0199] 3. Integration with map data

[0200] server

[0201] The server integrates the location information (latitude and longitude data) of the risk area with map data using GIS tools.

[0202] The combined risk areas are displayed on a map in a color-coded format: high risk is red, medium risk is yellow, and low risk is green.

[0203] 4. Display on car navigation systems

[0204] Terminal (car navigation system)

[0205] The device retrieves the latest accident risk information from the server in real time, and this retrieval is performed periodically using API calls.

[0206] The acquired risk information is reflected on a map, and icons and colors indicating risk areas are visually displayed.

[0207] 5. Emotional engine recognition and adjustment

[0208] Terminal (car navigation system)

[0209] The device is equipped with an emotion engine that recognizes the user's emotions and determines the user's emotional state based on voice and facial expression analysis.

[0210] The emotion engine recognizes the user's emotions and adjusts the content and intensity of the warnings. For example, if the user is feeling anxious, a calm voice message will be provided to encourage them to drive calmly.

[0211] 6. Notice to Users

[0212] User

[0213] When the user approaches a risk area, the device (car navigation system) issues a voice message warning, which includes specific points to be aware of (for example, "This intersection is prone to collisions when turning right").

[0214] The emotion engine recognizes the user's emotional state and adjusts the tone and wording of the voice message accordingly. For example, if the user is in a relaxed state, a standard warning tone will be used to notify the user.

[0215] The device also displays warning messages on the screen, allowing users to visually and audibly recognize risk information and drive carefully.

[0216] Specific examples

[0217] For example, suppose there have been more than 10 right-turn collisions at a certain intersection in the city center in the past year. Based on this information, the server identifies the intersection as "high risk" and integrates the latitude and longitude data into a map. The car navigation device retrieves this information from the server in real time and displays it on the map as a red icon.

[0218] When the user approaches this intersection, the car navigation system issues a voice warning saying, "There are many collisions when turning right at this intersection. Please drive carefully." At the same time, a warning message is displayed on the screen. If the emotion engine recognizes the user's emotional state as "anxious," it softens the tone of the warning and adds a message encouraging the user to drive calmly.

[0219] This system effectively integrates past traffic accident data with the user's real-time emotional state, providing users with realistic and immediate risk information, thereby preventing traffic accidents from occurring.

[0220] The processing flow will be explained below.

[0221] Step 1:

[0222] The server connects to the police traffic accident database and collects the latest traffic accident information, including the date, time, location, cause, circumstances, and details of the damage.

[0223] Step 2:

[0224] The server collects traffic accident information and stores it in a built-in database. The data is managed using a relational database such as SQL.

[0225] Step 3:

[0226] The server queries the database for past traffic accident data and extracts information such as the location, cause, and frequency of accidents.

[0227] Step 4:

[0228] The server analyzes the extracted accident data to identify accident risk areas, and uses statistical methods to evaluate accident frequency and trends.

[0229] Step 5:

[0230] The server classifies the identified risk areas into high, medium, and low risk categories based on the frequency and severity of accidents.

[0231] Step 6:

[0232] The server integrates the location information (latitude and longitude) of the risk area with map data using a GIS tool, allowing the risk area to be visually displayed on a map.

[0233] Step 7:

[0234] The server displays risk areas on the map data in different colors: high risk areas in red, medium risk areas in yellow, and low risk areas in green.

[0235] Step 8:

[0236] The device (car navigation system) retrieves the latest risk information from the server in real time, and this information is updated periodically using API calls.

[0237] Step 9:

[0238] Based on the risk information acquired by the device (car navigation system), risk areas are displayed on a map. Icons and colors are used so that users can visually identify risk areas.

[0239] Step 10:

[0240] The device (car navigation system) uses an emotion engine that recognizes the user's emotions to analyze the user's emotional state from their voice and facial expressions.

[0241] Step 11:

[0242] The device (car navigation system) adjusts the content and intensity of the warning based on the user's emotional state. For example, if the user is feeling anxious, it will provide a calm voice message encouraging them to drive calmly.

[0243] Step 12:

[0244] When the user approaches a risk area, the device (car navigation system) warns the user with a voice message, including specific warnings such as, "There are many collisions when turning right at this intersection. Please drive carefully."

[0245] Step 13:

[0246] The device (car navigation system) also displays a warning message on the screen, allowing the user to visually and audibly recognize risk information and drive carefully.

[0247] Through these steps, the system can combine past traffic accident data with the user's emotional state to more effectively reduce accident risk.

[0248] Example 2

[0249] 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."

[0250] Conventional traffic accident risk warning systems have issues with the accuracy and timeliness of the accident risk information they obtain in real time, making it difficult to effectively alert users to driving. In addition, warnings are not adjusted to take into account the user's emotional state, making it difficult to encourage appropriate decisions and actions by users.

[0251] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting traffic accident information, means for storing the collected traffic accident information in a data management device, means for analyzing past traffic accident data and identifying accident risk areas, means for integrating the identified accident risk areas with map data and displaying them, means for providing accident risk information to a guidance device in real time, means for displaying the provided accident risk information on the guidance device and issuing a warning to the user, and means for recognizing the user's emotional state and adjusting the content of the warning. This makes it possible to provide the user with appropriate accident risk information in real time and to issue a warning while taking the user's emotional state into consideration.

[0252] "Traffic accident information" is data including the date and time, location, cause, circumstances, and details of damage caused by a traffic accident.

[0253] "Data management device" refers to a database for storing and managing collected data and its control device.

[0254] "Accident risk areas" are areas with a high risk of accidents, analyzed based on past traffic accident data.

[0255] The "guidance device" is a device including a car navigation system installed in an automobile.

[0256] "Emotional state" refers to the user's psychological and emotional state, and is determined by facial expressions, tone of voice, etc.

[0257] "Warning content" is the audio or visual warning message provided to the user.

[0258] The system of this invention is mainly composed of a server, a terminal, and a user. The functions and specific operations of each will be explained below.

[0259] Server Features

[0260] server

[0261] The server first periodically connects to the police's traffic accident database to collect traffic accident information. This information includes the date, time, location, cause, circumstances, and damage details of the accident. This data is stored in a built-in database, and is managed and searched using a PostgreSQL database and SQL queries. The server then queries and retrieves past traffic accident data from the database and identifies accident risk areas using statistical methods. This analysis is performed using Python libraries such as pandas and scikit-learn. The identified risk areas are then classified into high, medium, and low risk, and are further integrated with map data using GIS tools (e.g., ArcGIS).

[0262] Device Features

[0263] Terminal (car navigation system)

[0264] The terminal periodically obtains the latest accident risk information from the server via an API call, and the obtained data is displayed on a map in real time using map display software. Web mapping libraries such as OpenLayers and Leaflet are used for this.

[0265] Additionally, the device is equipped with an emotion engine that recognizes the user's emotions. This emotion engine uses the Microsoft® Azure® Emotion API to analyze voice and facial expressions to determine the user's emotional state. Based on this information, the device adjusts the content and tone of warning messages.

[0266] User Experience

[0267] User

[0268] When the user approaches a risk area, the device will alert them with a voice message and a visual warning. For example, if the user approaches an intersection where more than 10 right-turn accidents have occurred in the past year, the device will issue a voice warning saying, "This intersection has a high incidence of right-turn collisions. Please drive carefully." A similar warning message will also be displayed on the device screen. If the emotion engine recognizes the user's emotional state as "anxious," the tone of the warning will become gentler and a message urging the user to drive calmly will be added.

[0269] Specific examples

[0270] For example, if a certain intersection in the city center has experienced more than 10 right-turn collisions in the past year, the server will identify the intersection as "high risk" based on this information and integrate the latitude and longitude data into the map. The car navigation device will obtain this information from the server in real time and display it as a red icon on the map. When the user approaches this intersection, a voice warning will be issued saying, "This intersection has seen many right-turn collisions. Please drive carefully." A warning message will also be displayed on the screen at the same time. If the emotion engine recognizes the user's emotional state as "anxious," it will soften the tone of the warning and add a message encouraging them to drive calmly.

[0271] Prompt Sentence Examples

[0272] The input prompt for the generative AI model is as follows:

[0273] Please explain how the Traffic Accident Risk Warning System program works, step by step, including the specific data collection procedures, data analysis methods, risk information map integration methods, and sentiment analysis methods for user notification.

[0274] This makes it possible to provide users with appropriate and real-time accident risk information and to issue warnings that take into account the user's emotional state.

[0275] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0276] Step 1: Collect traffic accident information

[0277] server

[0278] Input: Request to access police traffic accident database

[0279] Processing: The server periodically sends HTTP requests to the police traffic accident database and retrieves traffic accident information in JSON format, including the date, time, location, cause, circumstances, and damage details of the accident.

[0280] Output: Acquired traffic accident information

[0281] Specific operation: The server sends an API request using the curl command, and the received JSON data is parsed by a Python script and recorded in a log file.

[0282] Step 2: Save your data

[0283] server

[0284] Input: Acquired traffic accident information

[0285] Processing: The server saves the acquired traffic accident information in the built-in database (PostgreSQL). The information is stored in a table with fields for the accident date and time, location, cause, situation, and details of the damage.

[0286] Output: Traffic accident information stored in a database

[0287] Specific operation: Using Python's psycopg2 library, the parsed data is converted into an SQL insert statement and inserted into the database.

[0288] Step 3: Analyze the data

[0289] server

[0290] Input: Past traffic accident data stored in a database

[0291] Processing: The server retrieves past traffic accident data using SQL queries and identifies accident risk areas using statistical methods. Specifically, it analyzes the data using libraries such as pandas and scikit-learn and classifies risk areas into high, medium, and low risk.

[0292] Output: Identified accident risk area information

[0293] Specific operation: Executes the SQL query SELECT location, COUNT() FROM accidents WHERE date BETWEEN(R) '2022-01-01' AND '2022-12-31' GROUP BY location and saves the aggregated results in an Excel file.

[0294] Step 4: Integrating with map data

[0295] server

[0296] Input: Identified accident risk area information

[0297] Processing: The server integrates the latitude and longitude data of the identified risk areas with map data using a GIS tool (e.g., ArcGIS) and displays them in color. High risk is displayed in red, medium risk in yellow, and low risk in green.

[0298] Output: Integrated map data

[0299] Specific operation: Using Python's geopandas library, latitude and longitude information of risk areas is read and plotted on a map, generating a color-coded map image.

[0300] Step 5: Obtaining accident risk information

[0301] Terminal (car navigation system)

[0302] Input: Make an API call to the server to request risk area information

[0303] Processing: The device retrieves the latest risk area information from the server and integrates the data into the map application. The API is implemented in a RESTful format, and requests are made using the HTTP GET method.

[0304] Output: Obtained risk area information

[0305] Specific operation: The device uses the requests library to send a request to the server endpoint http: / / example.com / api / risks and stores the retrieved data in memory.

[0306] Step 6: Map risk information

[0307] Terminal (car navigation system)

[0308] Input: Obtained risk area information

[0309] Processing: The risk information acquired by the device is integrated into map display software and displayed on the map in real time. A web mapping library (e.g., OpenLayers or Leaflet) is used to display risk areas.

[0310] Output: Map showing risk areas

[0311] Specific operation: Loads the GeoJSON data of risk areas into the device's map app and plots it as a map layer. High-risk areas are displayed in red, medium-risk areas in yellow, and low-risk areas in green.

[0312] Step 7: Recognizing user emotions

[0313] Terminal (car navigation system)

[0314] Input: User's facial expression data and voice data

[0315] Processing: The device's built-in emotion engine analyzes the user's facial expression data and voice data acquired through the camera and microphone to determine the user's emotional state. This is done using Microsoft Azure's Emotion API, among other things.

[0316] Output: Recognized emotional state of the user

[0317] Specific operation: The device captures an image of the user with its camera and sends it to the Azure Emotion API, where it receives an emotion label such as "angry" or "calm."

[0318] Step 8: User Notification

[0319] Terminal (car navigation system)

[0320] Input: Risk area information, user emotional state

[0321] Treatment: When the user approaches a risk area, audio messages and visual warnings are used to alert the user. The content and tone of the messages are adjusted based on the emotional state recognized by the emotion engine.

[0322] Output: Warning message

[0323] Specific operation: If the user is in a hurry, a voice message will be played in a calm tone saying, "There are many accidents when turning right at this intersection. Please drive calmly," and a similar warning message will be displayed on the screen.

[0324] (Application example 2)

[0325] 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."

[0326] To prevent traffic accidents, it is important to predict dangerous areas based on past accident data and to provide appropriate warnings accordingly. However, current systems have difficulty providing appropriate warnings in real time based on individual users' situations and emotional states. Therefore, there is a need to develop a system that can efficiently provide accident risk information and provide appropriate warnings based on the user's emotional state.

[0327] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting traffic accident information from the police, means for storing the collected traffic accident information in a database, and means for analyzing past traffic accident data and identifying accident risk areas. This makes it possible to predict traffic accident risk areas and provide them to autonomously driven vehicles in real time. In addition, by including means for displaying on the autonomous driving system and issuing a warning to the user, means for recognizing the user's emotional state, and means for adjusting the warning message based on the recognized emotional state, it is possible to provide an appropriate warning according to the user's state and prevent traffic accidents from occurring.

[0328] The "police" is a government agency that maintains public safety and order and protects the lives and property of citizens.

[0329] "Means for collecting traffic accident information" refers to a method or system for obtaining details of the date, time, location, cause, circumstances, and damage of an accident from the police traffic accident database.

[0330] "Means of storing in a database" refers to a system or method for systematically storing collected traffic accident information and keeping it in a state that can be efficiently managed and searched.

[0331] "Means of analyzing past traffic accident data and identifying accident risk areas" refers to techniques and methods for analyzing accumulated traffic accident data using statistical methods to identify areas and situations where accidents occur frequently.

[0332] "Means for integrating and displaying with map data" refers to techniques and methods for visually displaying the location information of identified accident risk areas in combination with map information.

[0333] "Means for providing to autonomous vehicles" refers to the communication means and protocols for transmitting accident risk information from the server to autonomous vehicles in real time.

[0334] "Means for displaying on the automated driving system and issuing a warning to the user" refers to a method or system for notifying the user of accident risk areas and urging their attention using the display or audio output device of the automated driving system.

[0335] "Means for recognizing the user's emotional state" refers to techniques or methods for analyzing the user's facial expressions and tone of voice using a camera, voice analysis device, etc., to determine the user's emotional state.

[0336] The "means for adjusting the warning message" refers to a technique or method for appropriately changing the warning content, such as audio or displayed on a display, based on the recognized emotional state of the user.

[0337] The system of this invention consists of a server, a terminal of an autonomous vehicle, an emotion engine, and a user. The functions and specific operations of each will be explained below.

[0338] 1. Data Collection

[0339] server

[0340] The server periodically connects to the police traffic accident database to collect traffic accident information. The collected data includes the date, time, location, cause, circumstances, and damage details of the accident. This data is stored in the built-in database and can be efficiently managed and searched using SQL queries.

[0341] 2. Data analysis

[0342] server

[0343] The server queries and retrieves past traffic accident data from a database. The retrieved data is analyzed to identify accident risk areas. Statistical methods such as past accident locations, causes, and frequency are used for identification. Based on the results of the risk assessment, the identified accident risk areas are classified as high risk, medium risk, or low risk.

[0344] 3. Integration with map data

[0345] server

[0346] The server integrates the location information (latitude and longitude data) of risk areas with map data using GIS tools. The integrated risk areas are color-coded and displayed on the map. It is possible to set the display color to red for high risk, yellow for medium risk, and green for low risk.

[0347] 4. Display on autonomous vehicles

[0348] Terminal (autonomous vehicle)

[0349] The device retrieves the latest accident risk information from the server in real time. This retrieval is performed periodically using API calls. The retrieved risk information is reflected in the autonomous driving system, and icons and colors indicating risk areas are visually displayed.

[0350] 5. Emotional engine recognition and adjustment

[0351] Terminal (autonomous vehicle)

[0352] The device is equipped with an emotion engine that recognizes the user's emotions. This emotion engine determines the user's emotional state based on the camera and voice analysis device. Based on the user's emotions recognized by the emotion engine, the content and intensity of the warnings are adjusted. For example, if the user is feeling anxious, a calm voice message urging them to drive calmly is provided.

[0353] 6. Notice to Users

[0354] User

[0355] When the user approaches a risk area, the device (autonomous vehicle) will issue a voice warning. The voice warning will include specific points to be aware of (for example, "This intersection is prone to right-turn collisions"). The tone and wording of the voice message will be adjusted appropriately based on the user's emotional state as recognized by the emotion engine. For example, if the user is in a relaxed state, the notification will be issued in a standard warning tone. The device will also display a warning message on the screen. This allows the user to recognize risk information visually and audibly and drive carefully.

[0356] Specific examples

[0357] For example, suppose there have been more than 10 right-turn collisions at a certain intersection in the city center over the past year. Based on this information, the server identifies the intersection as "high risk" and integrates the latitude and longitude data into a map. The autonomous vehicle's device obtains this information from the server in real time and displays it as a red icon on the map. When the user approaches this intersection, the device issues a voice warning saying, "This intersection has a high rate of right-turn collisions. Please drive carefully." At the same time, a warning message is also displayed on the screen. If the emotion engine recognizes the user's emotional state as "anxious," it softens the tone of the warning and adds a message encouraging them to drive calmly.

[0358] Example of generative AI model and prompt

[0359] The emotion engine uses a face recognition model using OpenCV and an emotion classification model using TENSORFLOW (registered trademark). An example of a prompt is, "Analyze image data to determine whether the user is relaxed or anxious. The output will be emotion labels such as relaxed, anxious, or angry, along with their reliability scores."

[0360] This effectively integrates past traffic accident data with the user's real-time emotional state, providing users with realistic and immediate risk information, thereby preventing traffic accidents from occurring.

[0361] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0362] Step 1:

[0363] The server collects traffic accident information

[0364] The server periodically connects to the police traffic accident database to retrieve accident information. At this time, the date and time of the accident, location, cause, circumstances, and details of the damage are collected as data. The collected data is stored in the database. Specifically, data is inserted and updated in the database using SQL queries.

[0365] Input: Police traffic accident database

[0366] Output: Traffic accident data stored in a database

[0367] Step 2:

[0368] The server analyzes past traffic accident data and identifies areas at risk of accidents.

[0369] The server analyzes the accumulated traffic accident data to identify areas where accidents frequently occur, and then uses statistical methods to analyze the frequency and causes of accidents, thereby classifying areas into high-risk, medium-risk, and low-risk.

[0370] Input: Traffic accident data in the database

[0371] Output: Classified accident risk areas

[0372] Step 3:

[0373] The server integrates location information of accident risk areas with map data.

[0374] The server integrates the latitude and longitude data of risk areas with map information and visually displays them using a GIS tool. High-risk areas are displayed in red, medium-risk areas in yellow, and low-risk areas in green.

[0375] Input: Latitude and longitude data of classified accident risk areas

[0376] Output: Map data of color-coded risk areas

[0377] Step 4:

[0378] The device obtains the latest accident risk information from the server.

[0379] The terminal (autonomous vehicle) periodically uses an API call to obtain accident risk information from the server and displays it on the autonomous driving system. The obtained information includes the location information of risk areas and their risk levels.

[0380] Input: Accident risk information provided by the server

[0381] Output: Risk information displayed on the automated driving system

[0382] Step 5:

[0383] The device recognizes the user's emotional state

[0384] The device is equipped with an emotion engine that uses a camera and voice analysis device to recognize the user's emotional state in real time, using generative AI models (e.g., OpenCV, TensorFlow) for image processing and voice analysis.

[0385] Input: User's facial image and voice data

[0386] Output: Emotional state (relaxed, anxious, etc.) label and confidence score

[0387] Step 6:

[0388] The device adjusts warning messages based on the user's perceived emotional state.

[0389] The device adjusts the content and tone of the warning message based on the emotional state provided by the emotion engine: if the user is anxious, a calm message is provided, and if the user is relaxed, a standard message is provided.

[0390] Input: Emotional state label and confidence score

[0391] Output: Adjusted warning message

[0392] Step 7:

[0393] Notify the user when the device approaches a risk area

[0394] When a user approaches a risk area, the device will issue a warning via voice and display. The warning will include specific risk information (e.g., "This intersection has a high incidence of right-turn collisions") and will be delivered in a tone and content that takes into account the user's emotional state.

[0395] Input: Risk area information displayed on the device, warning messages based on emotional state

[0396] Output: Audio and visual warnings to the user

[0397] 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.

[0398] 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.

[0399] 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.

[0400] [Second embodiment]

[0401] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0402] 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.

[0403] 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).

[0404] 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.

[0405] 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.

[0406] 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).

[0407] 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.

[0408] 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.

[0409] 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.

[0410] 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.

[0411] 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.

[0412] 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."

[0413] The system of this invention mainly consists of a server, a terminal (car navigation system), and a user. The functions and specific operations of each will be explained below.

[0414] 1. Data Collection

[0415] server

[0416] The server periodically connects to the police traffic accident database and collects traffic accident information, including the date, time, location, cause, circumstances, and damage details of the traffic accident.

[0417] The collected data is stored by the server in an internal database, which can use a relational database system such as SQLite or MySQL.

[0418] 2. Data analysis

[0419] server

[0420] The server queries and retrieves past traffic accident data from its built-in database.

[0421] The acquired data is analyzed to identify areas at risk of accidents. This analysis uses statistical methods to identify the locations, causes, and frequency of past accidents.

[0422] Identified risk areas are classified into high, medium, and low risk areas, for example, by setting risk levels based on the frequency and severity of accidents.

[0423] 3. Integration with map data

[0424] server

[0425] The location information (latitude and longitude data) of high-risk areas will be integrated with map data using GIS tools.

[0426] This integration allows risk areas to be visually displayed on a map with specific colors and icons, for example, red for high risk areas, yellow for medium risk areas, and green for low risk areas.

[0427] 4. Display on car navigation systems

[0428] Terminal (car navigation system)

[0429] The car navigation device retrieves risk information in real time from the server, which updates the data periodically using API calls.

[0430] The car navigation system visualizes the acquired risk information on a map, and displays icons and colors indicating risk areas on the map on the device to visually warn the user.

[0431] 5. Notice to Users

[0432] User

[0433] When a user approaches a risk area while driving using a car navigation device, the car navigation system will warn them with a voice message.

[0434] This voice warning includes detailed information about the risk area (for example, "This intersection is prone to collisions when turning right") and provides the user with specific precautions to take.

[0435] In addition, a warning message will be displayed on the car navigation screen, allowing users to visually recognize risk areas.

[0436] Specific examples

[0437] For example, suppose there have been more than 10 right-turn collisions at a certain intersection in the city center in the past year. Based on this information, the server identifies the intersection as "high risk" and integrates the latitude and longitude data into a map. The car navigation device retrieves this information from the server in real time and displays it on the map as a red icon.

[0438] When the user approaches this intersection, the car navigation system issues a voice warning saying, "There are many collisions when turning right at this intersection. Please drive carefully." At the same time, a warning message is displayed on the screen. This allows the user to recognize the risks in advance and drive carefully.

[0439] This system effectively utilizes past traffic accident data and provides users with realistic and immediate risk information, making it possible to prevent traffic accidents from occurring.

[0440] The processing flow will be explained below.

[0441] Step 1:

[0442] The server periodically connects to the police traffic accident database to collect traffic accident information, including the date, time, location, cause, circumstances, and details of the accident.

[0443] Step 2:

[0444] The server stores the collected traffic accident information in a built-in database, which can be used to efficiently manage and search the accident information using SQL queries.

[0445] Step 3:

[0446] The server queries the database for past traffic accident data and extracts the necessary information, particularly the location of the accident, the cause of the accident, and the frequency of the accident.

[0447] Step 4:

[0448] The server analyzes the extracted data to identify areas at risk of accidents, and uses statistical methods to evaluate the risk level of specific locations based on past accident data.

[0449] Step 5:

[0450] Based on the analysis results, the server classifies the identified accident risk areas into high, medium, and low risk categories, allowing for detailed risk assessment of each area.

[0451] Step 6:

[0452] The server integrates the location information (latitude and longitude data) of the risk area with map data, and this integration uses GIS tools to visually locate the risk area on a map.

[0453] Step 7:

[0454] The server displays risk areas on the map data in different colors: high risk areas in red, medium risk areas in yellow, and low risk areas in green.

[0455] Step 8:

[0456] The device (car navigation system) retrieves the latest accident risk information from the server in real time. This retrieval is periodically updated using API calls.

[0457] Step 9:

[0458] The risk information acquired by the device (car navigation system) is displayed on a map. Icons and colors indicating risk areas are reflected on the map, allowing users to visually confirm risks.

[0459] Step 10:

[0460] When the user approaches a risk area, the device (car navigation system) warns the user with a voice message, which includes specific points to be aware of (for example, "This intersection is prone to collisions when turning right").

[0461] Step 11:

[0462] The device (car navigation system) also displays a warning message on the screen, allowing the user to visually and audibly recognize and pay attention to risk information.

[0463] By repeating these steps, the risk of traffic accidents can be effectively reduced and users can be supported in safe driving.

[0464] Example 1

[0465] 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."

[0466] Conventional traffic information systems lack sufficient functionality to notify users of traffic accident risks in advance, and users are unable to recognize the risk even when they approach an accident risk area. In particular, there is a lack of methods to effectively utilize past accident data to prevent future traffic accidents.

[0467] 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.

[0468] In this invention, the server includes means for collecting traffic accident information from the police, means for storing the collected traffic accident information in a database, means for analyzing past traffic accident data and identifying accident risk areas, means for integrating and displaying the identified accident risk areas with map data, means for providing the accident risk information to the car navigation system in real time, means for displaying the provided accident risk information on the car navigation system and warning the user, and means for warning the user by voice message when the user approaches an accident risk area. This enables the user to recognize risk areas in advance while driving and encourages safe driving.

[0469] "Police" is a public institution used to collect traffic accident information.

[0470] "Traffic accident information" is data that includes the date, time, location, cause, circumstances, and details of damages related to traffic accidents.

[0471] A "database" is a system for systematically storing, managing, and searching collected traffic accident information.

[0472] "Analysis" is the process of evaluating and analyzing collected traffic accident information using statistical methods and identifying accident risk areas.

[0473] An "accident risk area" is a specific geographical area that is considered to have a high risk of traffic accidents based on past traffic accident data.

[0474] "Map Data" means a dataset containing geographic information represented using a Geographic Information System (GIS).

[0475] A "car navigation system" is an in-vehicle navigation system that displays real-time location information and map data and provides navigation information to users.

[0476] "Real time" is a time concept in which the latest information is processed and provided immediately.

[0477] A "voice message" is a communication method that conveys information to a user using voice.

[0478] "GIS tools" are software for creating, analyzing, and visualizing geographic information system data.

[0479] The system of this invention mainly consists of a server, a terminal (car navigation system), and a user, and while clarifying the roles of each component, it supports safe driving by notifying the user of traffic accident risks in advance. Specific examples are described below.

[0480] server

[0481] Data collection

[0482] The server periodically connects to the police traffic accident database to collect traffic accident information. Specifically, the server connects to the database via the police API at 2:00 AM every day to obtain the date and time of the accident, location (latitude and longitude), cause of the accident, accident situation, and details of the damage. This collected data is stored in an SQLite or MySQL database.

[0483] Data analysis

[0484] The server periodically queries and retrieves traffic accident data from the database for the past year. The retrieved data is analyzed using Python's Pandas library to identify accident risk areas. This analysis classifies areas into high, medium, or low risk based on the location, cause, and frequency of accidents. For example, an area with more than 10 accidents in a year is considered high risk.

[0485] Integration with map data

[0486] The location information (latitude and longitude data) of the identified accident risk areas is integrated with map data using a GIS tool such as QGIS. The integrated data is generated as a color-coded shapefile to visually display the risk areas. High-risk areas are shown in red, medium-risk areas in yellow, and low-risk areas in green.

[0487] Terminal (car navigation system)

[0488] Real-time information acquisition

[0489] The car navigation device makes an API call to the server every five minutes to obtain the latest accident risk information. This information is obtained using networks such as Wi-Fi and LTE.

[0490] Information Visualization

[0491] The acquired risk information is immediately reflected on the map, with red icons indicating high-risk areas, yellow icons indicating medium-risk areas, and green icons indicating low-risk areas.

[0492] User

[0493] Notification of approach to risk area

[0494] When a user approaches within 500 meters of an accident risk area while driving, the car navigation system will issue a warning voice message. For example, it may say, "There are many collisions when turning right at this intersection. Please drive carefully." At the same time, a warning message will also be displayed on the car navigation system screen. This will allow users to recognize the risk in advance and encourage safe driving.

[0495] Specific examples

[0496] If a certain intersection in a city center has more than 10 right-turn collisions per year, the server identifies this intersection as a "high-risk" area and integrates the latitude and longitude data into a map.

[0497] The car navigation device retrieves this information from the server in real time and displays it as a red icon on the map.

[0498] When the user approaches this intersection, a voice warning will sound, saying, "There are many collisions when turning right at this intersection. Please drive carefully." A risk area warning message will also be displayed on the screen.

[0499] Based on the above specific operational examples, this system effectively utilizes past traffic accident data and provides users with realistic and immediate risk information, thereby making it possible to prevent traffic accidents from occurring.

[0500] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0501] Step 1: Data collection

[0502] The server connects to the police traffic accident database. Through the API, it obtains the date and time of the traffic accident, location (latitude and longitude), cause, situation, and details of the damage. The input is raw data from the API, and the output is this data in a structured format (for example, JSON format).

[0503] The server stores the acquired traffic accident information in an SQLite or MySQL database. The input is structured traffic accident information, and the output is data saved in the database.

[0504] Step 2: Data analysis

[0505] The server queries and retrieves the traffic accident data from the database for the past year. It extracts the data using SQL queries. The input is the traffic accident data stored in the database, and the output is the dataset of the query results.

[0506] The server analyzes the acquired data using Python's Pandas library. The input is the query result dataset, and the output is the identification of accident risk areas (including locations, causes, and frequency).

[0507] Based on the analysis results, accident risk areas are classified as high risk, medium risk, or low risk. For example, an area where 10 or more accidents occur per year is classified as high risk. The input is the analysis results, and the output is area information classified by risk level.

[0508] Step 3: Integrating with map data

[0509] The server uses GIS tools such as QGIS to integrate the location information (latitude and longitude data) of identified accident risk areas into map data. The input is the location information of the risk area and the original map data, and the output is the integrated map data.

[0510] The merged data is generated as a color-coded shapefile, with high-risk areas shown in red, medium-risk areas in yellow, and low-risk areas in green. The input is the merged map data, and the output is a color-coded shapefile.

[0511] Step 4: Display on the car navigation system

[0512] The device (car navigation system) makes an API call to the server every five minutes to obtain the latest accident risk information. The input is an API request to the server, and the output is real-time accident risk information.

[0513] The acquired risk information is displayed on a map. Red icons are displayed for high-risk areas, yellow for medium-risk areas, and green for low-risk areas. The input is the acquired risk information, and the output is a visualized map display.

[0514] Step 5: Inform users of the risk

[0515] When the user approaches a risk area, the car navigation system will warn them with a voice message. The distance is measured using GPS data, and a warning is issued when the user approaches within 500 meters. The input is GPS location data, and the output is a voice message.

[0516] A warning message is also displayed on the car navigation screen, allowing users to visually recognize the risk. The input is GPS location data, and the output is a warning message on the screen.

[0517] (Application example 1)

[0518] 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."

[0519] For current autonomous vehicles, systems that provide immediate and appropriate warnings and responses to traffic accident risk areas have not been fully developed. As a result, it is difficult to detect traffic accident risks at specific locations in advance and respond appropriately, and the risk of accidents remains high. To solve this issue, a system is needed that issues real-time warnings when an autonomous vehicle approaches a traffic accident risk area and adjusts the vehicle's operation.

[0520] 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.

[0521] In this invention, the server includes means for collecting traffic accident information from the police, means for storing the collected traffic accident information in a database, and means for analyzing past traffic accident data and identifying accident risk areas, which enables means for integrating the identified accident risk areas with map data and displaying them, means for providing accident risk information to autonomous vehicles in real time, and means for displaying the provided accident risk information on the autonomous vehicles and adjusting their operation.

[0522] The "means of collecting traffic accident information from the police" refers to a system for automatically obtaining data on traffic accidents held by police agencies using communication means such as the Internet.

[0523] "Means for storing collected traffic accident information in a database" refers to technology for efficiently storing and managing acquired traffic accident data using a database management system such as SQL or NoSQL.

[0524] "Means for analyzing past traffic accident data and identifying accident risk areas" refers to a method for applying algorithms such as statistical analysis and machine learning to stored traffic accident data to evaluate and identify accident risks in specific areas based on past trends and patterns.

[0525] "Means for integrating and displaying identified accident risk areas with map data" refers to GIS (geographic information system) technology that integrates the location information (latitude and longitude data) of identified risk areas into digital map data and displays them visually.

[0526] "Means for providing accident risk information to autonomous vehicles in real time" refers to technology for instantly transmitting accident risk information analyzed on a server to autonomous vehicles via the Internet or a dedicated communication network.

[0527] "Means for displaying the provided accident risk information on the autonomous vehicle and adjusting the vehicle's operation" refers to technology that conveys the received accident risk information to the driver using displays and speakers inside the vehicle, and further issues warnings and instructions to adjust the vehicle's operation to the vehicle's control system.

[0528] The system that realizes this invention mainly includes three elements: a server, a terminal (a computer of an autonomous vehicle), and a user. Below, we will explain how each element works.

[0529] server

[0530] The server first collects traffic accident information from the police. This involves periodically connecting to the police traffic accident database via the Internet to obtain information such as the date, time, location, cause, circumstances, and details of the accident. The obtained data is stored using a relational database system such as SQLite or MySQL.

[0531] The server then queries and analyzes historical traffic accident data from its built-in database, using statistical methods and machine learning algorithms to classify accident risk areas into high, medium, or low risk categories, with risk levels determined based on the frequency and severity of accidents.

[0532] Furthermore, the server integrates the location information (latitude and longitude data) of high-risk areas with map data using GIS tools, which allows the risk areas to be visually displayed on the map with specific colors (e.g., red for high risk) and icons.

[0533] Terminal (autonomous vehicle computer)

[0534] The autonomous vehicle's computer retrieves risk information from the server in real time. This is done using an API, with the latest data being updated regularly. The acquired risk information is then communicated to the user via the vehicle's display and speaker. For example, a voice message or a screen display can be used to warn of risk areas.

[0535] The autonomous vehicle's computer can also automatically adjust the vehicle's behavior when approaching a risk area, for example by reducing speed or changing course.

[0536] User

[0537] Users receive warnings from this system while riding in an autonomous vehicle. Specifically, when approaching a risk area, they receive a voice message saying, "There are many accidents when turning right at this intersection. Please be careful." In addition, the risk area is displayed in color on the vehicle's display, allowing users to visually recognize the risk.

[0538] Specific examples

[0539] For example, if a certain intersection in a city center has experienced more than 10 right-turn collisions in the past year, the server will use this information to identify the intersection as "high risk" and integrate the latitude and longitude data into a map. The autonomous vehicle's computer will retrieve this information from the server in real time and display it as a red icon on the map. When the user approaches this intersection, a voice warning will sound, saying, "This intersection has a high rate of right-turn collisions. Please drive carefully," and the vehicle's speed will automatically decrease.

[0540] Prompt Sentence Examples

[0541] For example, a sample prompt for building this system using a generative AI model is as follows:

[0542] Please create a Python program to retrieve past traffic accident data from a traffic accident database and identify risk areas for traffic accidents. Please also include functionality to integrate this into the control system of an autonomous vehicle, including risk areas, and provide risk warnings in real time.

[0543] It retrieves data from the server, analyzes the data, identifies risk areas, and integrates the control of the autonomous vehicle. It also displays warnings based on the vehicle's current location and adjusts vehicle control if necessary.

[0544] In this way, by describing the specific embodiments of the invention, anyone can carry out the invention.

[0545] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0546] Step 1:

[0547] The server periodically connects to the police traffic accident database via the Internet to collect traffic accident information. Specifically, it obtains the date, time, location, cause, circumstances, and damage details of the traffic accident. The input of this process is the police database connection information, and the output is the obtained traffic accident data.

[0548] Step 2:

[0549] The server stores the acquired traffic accident data in a database (e.g., SQLite or MySQL), which allows for data organization and efficient management. The input of this process is the acquired traffic accident data, and the output is the information stored in the database.

[0550] Step 3:

[0551] The server queries past traffic accident data from its built-in database and performs data analysis, for example, using statistical methods and machine learning algorithms to analyze accident frequency and causes and identify accident risk areas. The input to this process is the traffic accident data stored in the database, and the output is the identified accident risk area information.

[0552] Step 4:

[0553] The server integrates the location information (latitude and longitude data) of the identified accident risk areas with map data using GIS tools. This integration makes it possible to visually display the risk areas on a map with specific colors and icons. The input of this process is accident risk area information, and the output is visualized map data.

[0554] Step 5:

[0555] The terminal (the computer in the autonomous vehicle) retrieves risk information from the server in real time. The latest data is updated periodically using an API. The input to this process is the latest risk information provided by the server, and the output is the risk information taken into the vehicle.

[0556] Step 6:

[0557] The terminal notifies the user of the acquired risk information through the display or speaker of the autonomous vehicle. For example, when approaching a specific risk area, a warning is given by voice message or on-screen display. The input of this process is the risk information taken into the vehicle, and the output is a visual and audio warning to the user.

[0558] Step 7:

[0559] The terminal automatically adjusts the vehicle's behavior when approaching a risk area, for example by slowing the vehicle down or instructing it to change course. The input to this process is real-time location and risk information, and the output is adjusted vehicle behavior.

[0560] Step 8:

[0561] While riding in an autonomous vehicle, the user receives warnings from the system. Specifically, when approaching a risk area, the user follows the voice message and visual display to drive safely. The input of this process is the warning information from the terminal, and the output is appropriate driving behavior.

[0562] Through these steps, the system provides appropriate traffic accident risk information to autonomous vehicles, enabling users and vehicles to work together to ensure safe driving.

[0563] 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.

[0564] The system of this invention consists of a server, a terminal (car navigation system), an emotion engine, and a user. The functions and specific operations of each will be explained below.

[0565] 1. Data Collection

[0566] server

[0567] The server periodically connects to the police traffic accident database to collect traffic accident information, including the date, time, location, cause, circumstances, and damage details of the accident.

[0568] This data is stored in an internal database and can be efficiently managed and searched using SQL queries.

[0569] 2. Data analysis

[0570] server

[0571] The server queries and retrieves past traffic accident data from the database.

[0572] The acquired data is analyzed to identify areas at risk of accidents. Statistical methods are used to identify areas where accidents have occurred in the past, including their causes and frequency.

[0573] Based on the results of the risk assessment, the identified accident risk areas are classified as high risk, medium risk, or low risk.

[0574] 3. Integration with map data

[0575] server

[0576] The server integrates the location information (latitude and longitude data) of the risk area with map data using GIS tools.

[0577] The combined risk areas are displayed on a map in a color-coded format: high risk is red, medium risk is yellow, and low risk is green.

[0578] 4. Display on car navigation systems

[0579] Terminal (car navigation system)

[0580] The device retrieves the latest accident risk information from the server in real time, and this retrieval is performed periodically using API calls.

[0581] The acquired risk information is reflected on a map, and icons and colors indicating risk areas are visually displayed.

[0582] 5. Emotional engine recognition and adjustment

[0583] Terminal (car navigation system)

[0584] The device is equipped with an emotion engine that recognizes the user's emotions and determines the user's emotional state based on voice and facial expression analysis.

[0585] The emotion engine recognizes the user's emotions and adjusts the content and intensity of the warnings. For example, if the user is feeling anxious, a calm voice message will be provided to encourage them to drive calmly.

[0586] 6. Notice to Users

[0587] User

[0588] When the user approaches a risk area, the device (car navigation system) issues a voice message warning, which includes specific points to be aware of (for example, "This intersection is prone to collisions when turning right").

[0589] The emotion engine recognizes the user's emotional state and adjusts the tone and wording of the voice message accordingly. For example, if the user is in a relaxed state, a standard warning tone will be used to notify the user.

[0590] The device also displays warning messages on the screen, allowing users to visually and audibly recognize risk information and drive carefully.

[0591] Specific examples

[0592] For example, suppose there have been more than 10 right-turn collisions at a certain intersection in the city center in the past year. Based on this information, the server identifies the intersection as "high risk" and integrates the latitude and longitude data into a map. The car navigation device retrieves this information from the server in real time and displays it on the map as a red icon.

[0593] When the user approaches this intersection, the car navigation system issues a voice warning saying, "There are many collisions when turning right at this intersection. Please drive carefully." At the same time, a warning message is displayed on the screen. If the emotion engine recognizes the user's emotional state as "anxious," it softens the tone of the warning and adds a message encouraging the user to drive calmly.

[0594] This system effectively integrates past traffic accident data with the user's real-time emotional state, providing users with realistic and immediate risk information, thereby preventing traffic accidents from occurring.

[0595] The processing flow will be explained below.

[0596] Step 1:

[0597] The server connects to the police traffic accident database and collects the latest traffic accident information, including the date, time, location, cause, circumstances, and details of the damage.

[0598] Step 2:

[0599] The server collects traffic accident information and stores it in a built-in database. The data is managed using a relational database such as SQL.

[0600] Step 3:

[0601] The server queries the database for past traffic accident data and extracts information such as the location, cause, and frequency of accidents.

[0602] Step 4:

[0603] The server analyzes the extracted accident data to identify accident risk areas, and uses statistical methods to evaluate accident frequency and trends.

[0604] Step 5:

[0605] The server classifies the identified risk areas into high, medium, and low risk categories based on the frequency and severity of accidents.

[0606] Step 6:

[0607] The server integrates the location information (latitude and longitude) of the risk area with map data using a GIS tool, allowing the risk area to be visually displayed on a map.

[0608] Step 7:

[0609] The server displays risk areas on the map data in different colors: high risk areas in red, medium risk areas in yellow, and low risk areas in green.

[0610] Step 8:

[0611] The device (car navigation system) retrieves the latest risk information from the server in real time, and this information is updated periodically using API calls.

[0612] Step 9:

[0613] Based on the risk information acquired by the device (car navigation system), risk areas are displayed on a map. Icons and colors are used so that users can visually identify risk areas.

[0614] Step 10:

[0615] The device (car navigation system) uses an emotion engine that recognizes the user's emotions to analyze the user's emotional state from their voice and facial expressions.

[0616] Step 11:

[0617] The device (car navigation system) adjusts the content and intensity of the warning based on the user's emotional state. For example, if the user is feeling anxious, it will provide a calm voice message encouraging them to drive calmly.

[0618] Step 12:

[0619] When the user approaches a risk area, the device (car navigation system) warns the user with a voice message, including specific warnings such as, "There are many collisions when turning right at this intersection. Please drive carefully."

[0620] Step 13:

[0621] The device (car navigation system) also displays a warning message on the screen, allowing the user to visually and audibly recognize risk information and drive carefully.

[0622] Through these steps, the system can combine past traffic accident data with the user's emotional state to more effectively reduce accident risk.

[0623] Example 2

[0624] 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."

[0625] Conventional traffic accident risk warning systems have issues with the accuracy and timeliness of the accident risk information they obtain in real time, making it difficult to effectively alert users to driving. In addition, warnings are not adjusted to take into account the user's emotional state, making it difficult to encourage appropriate decisions and actions by users.

[0626] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting traffic accident information, means for storing the collected traffic accident information in a data management device, means for analyzing past traffic accident data and identifying accident risk areas, means for integrating the identified accident risk areas with map data and displaying them, means for providing accident risk information to a guidance device in real time, means for displaying the provided accident risk information on the guidance device and issuing a warning to the user, and means for recognizing the user's emotional state and adjusting the content of the warning. This makes it possible to provide the user with appropriate accident risk information in real time and to issue a warning while taking the user's emotional state into consideration.

[0627] "Traffic accident information" is data including the date and time, location, cause, circumstances, and details of damage caused by a traffic accident.

[0628] "Data management device" refers to a database for storing and managing collected data and its control device.

[0629] "Accident risk areas" are areas with a high risk of accidents, analyzed based on past traffic accident data.

[0630] The "guidance device" is a device including a car navigation system installed in an automobile.

[0631] "Emotional state" refers to the user's psychological and emotional state, and is determined by facial expressions, tone of voice, etc.

[0632] "Warning content" is the audio or visual warning message provided to the user.

[0633] The system of this invention is mainly composed of a server, a terminal, and a user. The functions and specific operations of each will be explained below.

[0634] Server Features

[0635] server

[0636] The server first periodically connects to the police's traffic accident database to collect traffic accident information. This information includes the date, time, location, cause, circumstances, and damage details of the accident. This data is stored in a built-in database, and is managed and searched using a PostgreSQL database and SQL queries. The server then queries and retrieves past traffic accident data from the database and identifies accident risk areas using statistical methods. This analysis is performed using Python libraries such as pandas and scikit-learn. The identified risk areas are then classified into high, medium, and low risk, and are further integrated with map data using GIS tools (e.g., ArcGIS).

[0637] Device Features

[0638] Terminal (car navigation system)

[0639] The terminal periodically obtains the latest accident risk information from the server via an API call, and the obtained data is displayed on a map in real time using map display software. Web mapping libraries such as OpenLayers and Leaflet are used for this.

[0640] Additionally, the device is equipped with an emotion engine that recognizes the user's emotions. This emotion engine uses Microsoft Azure's Emotion API to analyze voice and facial expressions to determine the user's emotional state. Based on this information, the device can adjust the content and tone of warning messages.

[0641] User Experience

[0642] User

[0643] When the user approaches a risk area, the device will alert them with a voice message and a visual warning. For example, if the user approaches an intersection where more than 10 right-turn accidents have occurred in the past year, the device will issue a voice warning saying, "This intersection has a high incidence of right-turn collisions. Please drive carefully." A similar warning message will also be displayed on the device screen. If the emotion engine recognizes the user's emotional state as "anxious," the tone of the warning will become gentler and a message urging the user to drive calmly will be added.

[0644] Specific examples

[0645] For example, if a certain intersection in the city center has experienced more than 10 right-turn collisions in the past year, the server will identify the intersection as "high risk" based on this information and integrate the latitude and longitude data into the map. The car navigation device will obtain this information from the server in real time and display it as a red icon on the map. When the user approaches this intersection, a voice warning will be issued saying, "This intersection has seen many right-turn collisions. Please drive carefully." A warning message will also be displayed on the screen at the same time. If the emotion engine recognizes the user's emotional state as "anxious," it will soften the tone of the warning and add a message encouraging them to drive calmly.

[0646] Prompt Sentence Examples

[0647] The input prompt for the generative AI model is as follows:

[0648] Please explain how the Traffic Accident Risk Warning System program works, step by step, including the specific data collection procedures, data analysis methods, risk information map integration methods, and sentiment analysis methods for user notification.

[0649] This makes it possible to provide users with appropriate and real-time accident risk information and to issue warnings that take into account the user's emotional state.

[0650] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0651] Step 1: Collect traffic accident information

[0652] server

[0653] Input: Request to access police traffic accident database

[0654] Processing: The server periodically sends HTTP requests to the police traffic accident database and retrieves traffic accident information in JSON format, including the date, time, location, cause, circumstances, and damage details of the accident.

[0655] Output: Acquired traffic accident information

[0656] Specific operation: The server sends an API request using the curl command, and the received JSON data is parsed by a Python script and recorded in a log file.

[0657] Step 2: Save your data

[0658] server

[0659] Input: Acquired traffic accident information

[0660] Processing: The server saves the acquired traffic accident information in the built-in database (PostgreSQL). The information is stored in a table with fields for the accident date and time, location, cause, situation, and details of the damage.

[0661] Output: Traffic accident information stored in a database

[0662] Specific operation: Using Python's psycopg2 library, the parsed data is converted into an SQL insert statement and inserted into the database.

[0663] Step 3: Analyze the data

[0664] server

[0665] Input: Past traffic accident data stored in a database

[0666] Processing: The server retrieves past traffic accident data using SQL queries and identifies accident risk areas using statistical methods. Specifically, it analyzes the data using libraries such as pandas and scikit-learn and classifies risk areas into high, medium, and low risk.

[0667] Output: Identified accident risk area information

[0668] Specific operation: Executes the SQL query SELECT location, COUNT() FROM accidents WHERE date BETWEEN '2022-01-01' AND '2022-12-31' GROUP BY location and saves the aggregated results in an Excel file.

[0669] Step 4: Integrating with map data

[0670] server

[0671] Input: Identified accident risk area information

[0672] Processing: The server integrates the latitude and longitude data of the identified risk areas with map data using a GIS tool (e.g., ArcGIS) and displays them in color. High risk is displayed in red, medium risk in yellow, and low risk in green.

[0673] Output: Integrated map data

[0674] Specific operation: Using Python's geopandas library, latitude and longitude information of risk areas is read and plotted on a map, generating a color-coded map image.

[0675] Step 5: Obtaining accident risk information

[0676] Terminal (car navigation system)

[0677] Input: Make an API call to the server to request risk area information

[0678] Processing: The device retrieves the latest risk area information from the server and integrates the data into the map application. The API is implemented in a RESTful format, and requests are made using the HTTP GET method.

[0679] Output: Obtained risk area information

[0680] Specific operation: The device uses the requests library to send a request to the server endpoint http: / / example.com / api / risks and stores the retrieved data in memory.

[0681] Step 6: Map risk information

[0682] Terminal (car navigation system)

[0683] Input: Obtained risk area information

[0684] Processing: The risk information acquired by the device is integrated into map display software and displayed on the map in real time. A web mapping library (e.g., OpenLayers or Leaflet) is used to display risk areas.

[0685] Output: Map showing risk areas

[0686] Specific operation: Loads the GeoJSON data of risk areas into the device's map app and plots it as a map layer. High-risk areas are displayed in red, medium-risk areas in yellow, and low-risk areas in green.

[0687] Step 7: Recognizing user emotions

[0688] Terminal (car navigation system)

[0689] Input: User's facial expression data and voice data

[0690] Processing: The device's built-in emotion engine analyzes the user's facial expression data and voice data acquired through the camera and microphone to determine the user's emotional state. This is done using Microsoft Azure's Emotion API, among other things.

[0691] Output: Recognized emotional state of the user

[0692] Specific operation: The device captures an image of the user with its camera and sends it to the Azure Emotion API, where it receives an emotion label such as "angry" or "calm."

[0693] Step 8: User Notification

[0694] Terminal (car navigation system)

[0695] Input: Risk area information, user emotional state

[0696] Treatment: When the user approaches a risk area, audio messages and visual warnings are used to alert the user. The content and tone of the messages are adjusted based on the emotional state recognized by the emotion engine.

[0697] Output: Warning message

[0698] Specific operation: If the user is in a hurry, a voice message will be played in a calm tone saying, "There are many accidents when turning right at this intersection. Please drive calmly," and a similar warning message will be displayed on the screen.

[0699] (Application example 2)

[0700] 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."

[0701] To prevent traffic accidents, it is important to predict dangerous areas based on past accident data and to provide appropriate warnings accordingly. However, current systems have difficulty providing appropriate warnings in real time based on individual users' situations and emotional states. Therefore, there is a need to develop a system that can efficiently provide accident risk information and provide appropriate warnings based on the user's emotional state.

[0702] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting traffic accident information from the police, means for storing the collected traffic accident information in a database, and means for analyzing past traffic accident data and identifying accident risk areas. This makes it possible to predict traffic accident risk areas and provide them to autonomously driven vehicles in real time. In addition, by including means for displaying on the autonomous driving system and issuing a warning to the user, means for recognizing the user's emotional state, and means for adjusting the warning message based on the recognized emotional state, it is possible to provide an appropriate warning according to the user's state and prevent traffic accidents from occurring.

[0703] The "police" is a government agency that maintains public safety and order and protects the lives and property of citizens.

[0704] "Means for collecting traffic accident information" refers to a method or system for obtaining details of the date, time, location, cause, circumstances, and damage of an accident from the police traffic accident database.

[0705] "Means of storing in a database" refers to a system or method for systematically storing collected traffic accident information and keeping it in a state that can be efficiently managed and searched.

[0706] "Means of analyzing past traffic accident data and identifying accident risk areas" refers to techniques and methods for analyzing accumulated traffic accident data using statistical methods to identify areas and situations where accidents occur frequently.

[0707] "Means for integrating and displaying with map data" refers to techniques and methods for visually displaying the location information of identified accident risk areas in combination with map information.

[0708] "Means for providing to autonomous vehicles" refers to the communication means and protocols for transmitting accident risk information from the server to autonomous vehicles in real time.

[0709] "Means for displaying on the automated driving system and issuing a warning to the user" refers to a method or system for notifying the user of accident risk areas and urging their attention using the display or audio output device of the automated driving system.

[0710] "Means for recognizing the user's emotional state" refers to techniques or methods for analyzing the user's facial expressions and tone of voice using a camera, voice analysis device, etc., to determine the user's emotional state.

[0711] The "means for adjusting the warning message" refers to a technique or method for appropriately changing the warning content, such as audio or displayed on a display, based on the recognized emotional state of the user.

[0712] The system of this invention consists of a server, a terminal of an autonomous vehicle, an emotion engine, and a user. The functions and specific operations of each will be explained below.

[0713] 1. Data Collection

[0714] server

[0715] The server periodically connects to the police traffic accident database to collect traffic accident information. The collected data includes the date, time, location, cause, circumstances, and damage details of the accident. This data is stored in the built-in database and can be efficiently managed and searched using SQL queries.

[0716] 2. Data analysis

[0717] server

[0718] The server queries and retrieves past traffic accident data from a database. The retrieved data is analyzed to identify accident risk areas. Statistical methods such as past accident locations, causes, and frequency are used for identification. Based on the results of the risk assessment, the identified accident risk areas are classified as high risk, medium risk, or low risk.

[0719] 3. Integration with map data

[0720] server

[0721] The server integrates the location information (latitude and longitude data) of risk areas with map data using GIS tools. The integrated risk areas are color-coded and displayed on the map. It is possible to set the display color to red for high risk, yellow for medium risk, and green for low risk.

[0722] 4. Display on autonomous vehicles

[0723] Terminal (autonomous vehicle)

[0724] The device retrieves the latest accident risk information from the server in real time. This retrieval is performed periodically using API calls. The retrieved risk information is reflected in the autonomous driving system, and icons and colors indicating risk areas are visually displayed.

[0725] 5. Emotional engine recognition and adjustment

[0726] Terminal (autonomous vehicle)

[0727] The device is equipped with an emotion engine that recognizes the user's emotions. This emotion engine determines the user's emotional state based on the camera and voice analysis device. Based on the user's emotions recognized by the emotion engine, the content and intensity of the warnings are adjusted. For example, if the user is feeling anxious, a calm voice message urging them to drive calmly is provided.

[0728] 6. Notice to Users

[0729] User

[0730] When the user approaches a risk area, the device (autonomous vehicle) will issue a voice warning. The voice warning will include specific points to be aware of (for example, "This intersection is prone to right-turn collisions"). The tone and wording of the voice message will be adjusted appropriately based on the user's emotional state as recognized by the emotion engine. For example, if the user is in a relaxed state, the notification will be issued in a standard warning tone. The device will also display a warning message on the screen. This allows the user to recognize risk information visually and audibly and drive carefully.

[0731] Specific examples

[0732] For example, suppose there have been more than 10 right-turn collisions at a certain intersection in the city center over the past year. Based on this information, the server identifies the intersection as "high risk" and integrates the latitude and longitude data into a map. The autonomous vehicle's device obtains this information from the server in real time and displays it as a red icon on the map. When the user approaches this intersection, the device issues a voice warning saying, "This intersection has a high rate of right-turn collisions. Please drive carefully." At the same time, a warning message is also displayed on the screen. If the emotion engine recognizes the user's emotional state as "anxious," it softens the tone of the warning and adds a message encouraging them to drive calmly.

[0733] Example of generative AI model and prompt

[0734] The emotion engine uses a facial recognition model using OpenCV and an emotion classification model using TensorFlow. An example prompt is, "Analyze image data to determine whether the user is relaxed or anxious. The output will be an emotion label such as relaxed, anxious, or angry, along with its confidence score."

[0735] This effectively integrates past traffic accident data with the user's real-time emotional state, providing users with realistic and immediate risk information, thereby preventing traffic accidents from occurring.

[0736] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0737] Step 1:

[0738] The server collects traffic accident information

[0739] The server periodically connects to the police traffic accident database to retrieve accident information. At this time, the date and time of the accident, location, cause, circumstances, and details of the damage are collected as data. The collected data is stored in the database. Specifically, data is inserted and updated in the database using SQL queries.

[0740] Input: Police traffic accident database

[0741] Output: Traffic accident data stored in a database

[0742] Step 2:

[0743] The server analyzes past traffic accident data and identifies areas at risk of accidents.

[0744] The server analyzes the accumulated traffic accident data to identify areas where accidents frequently occur, and then uses statistical methods to analyze the frequency and causes of accidents, thereby classifying areas into high-risk, medium-risk, and low-risk.

[0745] Input: Traffic accident data in the database

[0746] Output: Classified accident risk areas

[0747] Step 3:

[0748] The server integrates location information of accident risk areas with map data.

[0749] The server integrates the latitude and longitude data of risk areas with map information and visually displays them using a GIS tool. High-risk areas are displayed in red, medium-risk areas in yellow, and low-risk areas in green.

[0750] Input: Latitude and longitude data of classified accident risk areas

[0751] Output: Map data of color-coded risk areas

[0752] Step 4:

[0753] The device obtains the latest accident risk information from the server.

[0754] The terminal (autonomous vehicle) periodically uses an API call to obtain accident risk information from the server and displays it on the autonomous driving system. The obtained information includes the location information of risk areas and their risk levels.

[0755] Input: Accident risk information provided by the server

[0756] Output: Risk information displayed on the automated driving system

[0757] Step 5:

[0758] The device recognizes the user's emotional state

[0759] The device is equipped with an emotion engine that uses a camera and voice analysis device to recognize the user's emotional state in real time, using generative AI models (e.g., OpenCV, TensorFlow) for image processing and voice analysis.

[0760] Input: User's facial image and voice data

[0761] Output: Emotional state (relaxed, anxious, etc.) label and confidence score

[0762] Step 6:

[0763] The device adjusts warning messages based on the user's perceived emotional state.

[0764] The device adjusts the content and tone of the warning message based on the emotional state provided by the emotion engine: if the user is anxious, a calm message is provided, and if the user is relaxed, a standard message is provided.

[0765] Input: Emotional state label and confidence score

[0766] Output: Adjusted warning message

[0767] Step 7:

[0768] Notify the user when the device approaches a risk area

[0769] When a user approaches a risk area, the device will issue a warning via voice and display. The warning will include specific risk information (e.g., "This intersection has a high incidence of right-turn collisions") and will be delivered in a tone and content that takes into account the user's emotional state.

[0770] Input: Risk area information displayed on the device, warning messages based on emotional state

[0771] Output: Audio and visual warnings to the user

[0772] 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.

[0773] 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.

[0774] 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.

[0775] [Third embodiment]

[0776] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0777] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0778] 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).

[0779] 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.

[0780] 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.

[0781] 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).

[0782] 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.

[0783] 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.

[0784] 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.

[0785] 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.

[0786] 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.

[0787] 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."

[0788] The system of this invention mainly consists of a server, a terminal (car navigation system), and a user. The functions and specific operations of each will be explained below.

[0789] 1. Data Collection

[0790] server

[0791] The server periodically connects to the police traffic accident database and collects traffic accident information, including the date, time, location, cause, circumstances, and damage details of the traffic accident.

[0792] The collected data is stored by the server in an internal database, which can use a relational database system such as SQLite or MySQL.

[0793] 2. Data analysis

[0794] server

[0795] The server queries and retrieves past traffic accident data from its built-in database.

[0796] The acquired data is analyzed to identify areas at risk of accidents. This analysis uses statistical methods to identify the locations, causes, and frequency of past accidents.

[0797] Identified risk areas are classified into high, medium, and low risk areas, for example, by setting risk levels based on the frequency and severity of accidents.

[0798] 3. Integration with map data

[0799] server

[0800] The location information (latitude and longitude data) of high-risk areas will be integrated with map data using GIS tools.

[0801] This integration allows risk areas to be visually displayed on a map with specific colors and icons, for example, red for high risk areas, yellow for medium risk areas, and green for low risk areas.

[0802] 4. Display on car navigation systems

[0803] Terminal (car navigation system)

[0804] The car navigation device retrieves risk information in real time from the server, which updates the data periodically using API calls.

[0805] The car navigation system visualizes the acquired risk information on a map, and displays icons and colors indicating risk areas on the map on the device to visually warn the user.

[0806] 5. Notice to Users

[0807] User

[0808] When a user approaches a risk area while driving using a car navigation device, the car navigation system will warn them with a voice message.

[0809] This voice warning includes detailed information about the risk area (for example, "This intersection is prone to collisions when turning right") and provides the user with specific precautions to take.

[0810] In addition, a warning message will be displayed on the car navigation screen, allowing users to visually recognize risk areas.

[0811] Specific examples

[0812] For example, suppose there have been more than 10 right-turn collisions at a certain intersection in the city center in the past year. Based on this information, the server identifies the intersection as "high risk" and integrates the latitude and longitude data into a map. The car navigation device retrieves this information from the server in real time and displays it on the map as a red icon.

[0813] When the user approaches this intersection, the car navigation system issues a voice warning saying, "There are many collisions when turning right at this intersection. Please drive carefully." At the same time, a warning message is displayed on the screen. This allows the user to recognize the risks in advance and drive carefully.

[0814] This system effectively utilizes past traffic accident data and provides users with realistic and immediate risk information, making it possible to prevent traffic accidents from occurring.

[0815] The processing flow will be explained below.

[0816] Step 1:

[0817] The server periodically connects to the police traffic accident database to collect traffic accident information, including the date, time, location, cause, circumstances, and details of the accident.

[0818] Step 2:

[0819] The server stores the collected traffic accident information in a built-in database, which can be used to efficiently manage and search the accident information using SQL queries.

[0820] Step 3:

[0821] The server queries the database for past traffic accident data and extracts the necessary information, particularly the location of the accident, the cause of the accident, and the frequency of the accident.

[0822] Step 4:

[0823] The server analyzes the extracted data to identify areas at risk of accidents, and uses statistical methods to evaluate the risk level of specific locations based on past accident data.

[0824] Step 5:

[0825] Based on the analysis results, the server classifies the identified accident risk areas into high, medium, and low risk categories, allowing for detailed risk assessment of each area.

[0826] Step 6:

[0827] The server integrates the location information (latitude and longitude data) of the risk area with map data, and this integration uses GIS tools to visually locate the risk area on a map.

[0828] Step 7:

[0829] The server displays risk areas on the map data in different colors: high risk areas in red, medium risk areas in yellow, and low risk areas in green.

[0830] Step 8:

[0831] The device (car navigation system) retrieves the latest accident risk information from the server in real time. This retrieval is periodically updated using API calls.

[0832] Step 9:

[0833] The risk information acquired by the device (car navigation system) is displayed on a map. Icons and colors indicating risk areas are reflected on the map, allowing users to visually confirm risks.

[0834] Step 10:

[0835] When the user approaches a risk area, the device (car navigation system) warns the user with a voice message, which includes specific points to be aware of (for example, "This intersection is prone to collisions when turning right").

[0836] Step 11:

[0837] The device (car navigation system) also displays a warning message on the screen, allowing the user to visually and audibly recognize and pay attention to risk information.

[0838] By repeating these steps, the risk of traffic accidents can be effectively reduced and users can be supported in safe driving.

[0839] Example 1

[0840] 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."

[0841] Conventional traffic information systems lack sufficient functionality to notify users of traffic accident risks in advance, and users are unable to recognize the risk even when they approach an accident risk area. In particular, there is a lack of methods to effectively utilize past accident data to prevent future traffic accidents.

[0842] 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.

[0843] In this invention, the server includes means for collecting traffic accident information from the police, means for storing the collected traffic accident information in a database, means for analyzing past traffic accident data and identifying accident risk areas, means for integrating and displaying the identified accident risk areas with map data, means for providing the accident risk information to the car navigation system in real time, means for displaying the provided accident risk information on the car navigation system and warning the user, and means for warning the user by voice message when the user approaches an accident risk area. This enables the user to recognize risk areas in advance while driving and encourages safe driving.

[0844] "Police" is a public institution used to collect traffic accident information.

[0845] "Traffic accident information" is data that includes the date, time, location, cause, circumstances, and details of damages related to traffic accidents.

[0846] A "database" is a system for systematically storing, managing, and searching collected traffic accident information.

[0847] "Analysis" is the process of evaluating and analyzing collected traffic accident information using statistical methods and identifying accident risk areas.

[0848] An "accident risk area" is a specific geographical area that is considered to have a high risk of traffic accidents based on past traffic accident data.

[0849] "Map Data" means a dataset containing geographic information represented using a Geographic Information System (GIS).

[0850] A "car navigation system" is an in-vehicle navigation system that displays real-time location information and map data and provides navigation information to users.

[0851] "Real time" is a time concept in which the latest information is processed and provided immediately.

[0852] A "voice message" is a communication method that conveys information to a user using voice.

[0853] "GIS tools" are software for creating, analyzing, and visualizing geographic information system data.

[0854] The system of this invention mainly consists of a server, a terminal (car navigation system), and a user, and while clarifying the roles of each component, it supports safe driving by notifying the user of traffic accident risks in advance. Specific examples are described below.

[0855] server

[0856] Data collection

[0857] The server periodically connects to the police traffic accident database to collect traffic accident information. Specifically, the server connects to the database via the police API at 2:00 AM every day to obtain the date and time of the accident, location (latitude and longitude), cause of the accident, accident situation, and details of the damage. This collected data is stored in an SQLite or MySQL database.

[0858] Data analysis

[0859] The server periodically queries and retrieves traffic accident data from the database for the past year. The retrieved data is analyzed using Python's Pandas library to identify accident risk areas. This analysis classifies areas into high, medium, or low risk based on the location, cause, and frequency of accidents. For example, an area with more than 10 accidents in a year is considered high risk.

[0860] Integration with map data

[0861] The location information (latitude and longitude data) of the identified accident risk areas is integrated with map data using a GIS tool such as QGIS. The integrated data is generated as a color-coded shapefile to visually display the risk areas. High-risk areas are shown in red, medium-risk areas in yellow, and low-risk areas in green.

[0862] Terminal (car navigation system)

[0863] Real-time information acquisition

[0864] The car navigation device makes an API call to the server every five minutes to obtain the latest accident risk information. This information is obtained using networks such as Wi-Fi and LTE.

[0865] Information Visualization

[0866] The acquired risk information is immediately reflected on the map, with red icons indicating high-risk areas, yellow icons indicating medium-risk areas, and green icons indicating low-risk areas.

[0867] User

[0868] Notification of approach to risk area

[0869] When a user approaches within 500 meters of an accident risk area while driving, the car navigation system will issue a warning voice message. For example, it may say, "There are many collisions when turning right at this intersection. Please drive carefully." At the same time, a warning message will also be displayed on the car navigation system screen. This will allow users to recognize the risk in advance and encourage safe driving.

[0870] Specific examples

[0871] If a certain intersection in a city center has more than 10 right-turn collisions per year, the server identifies this intersection as a "high-risk" area and integrates the latitude and longitude data into a map.

[0872] The car navigation device retrieves this information from the server in real time and displays it as a red icon on the map.

[0873] When the user approaches this intersection, a voice warning will sound, saying, "There are many collisions when turning right at this intersection. Please drive carefully." A risk area warning message will also be displayed on the screen.

[0874] Based on the above specific operational examples, this system effectively utilizes past traffic accident data and provides users with realistic and immediate risk information, thereby making it possible to prevent traffic accidents from occurring.

[0875] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0876] Step 1: Data collection

[0877] The server connects to the police traffic accident database. Through the API, it obtains the date and time of the traffic accident, location (latitude and longitude), cause, situation, and details of the damage. The input is raw data from the API, and the output is this data in a structured format (for example, JSON format).

[0878] The server stores the acquired traffic accident information in an SQLite or MySQL database. The input is structured traffic accident information, and the output is data saved in the database.

[0879] Step 2: Data analysis

[0880] The server queries and retrieves the traffic accident data from the database for the past year. It extracts the data using SQL queries. The input is the traffic accident data stored in the database, and the output is the dataset of the query results.

[0881] The server analyzes the acquired data using Python's Pandas library. The input is the query result dataset, and the output is the identification of accident risk areas (including locations, causes, and frequency).

[0882] Based on the analysis results, accident risk areas are classified as high risk, medium risk, or low risk. For example, an area where 10 or more accidents occur per year is classified as high risk. The input is the analysis results, and the output is area information classified by risk level.

[0883] Step 3: Integrating with map data

[0884] The server uses GIS tools such as QGIS to integrate the location information (latitude and longitude data) of identified accident risk areas into map data. The input is the location information of the risk area and the original map data, and the output is the integrated map data.

[0885] The merged data is generated as a color-coded shapefile, with high-risk areas shown in red, medium-risk areas in yellow, and low-risk areas in green. The input is the merged map data, and the output is a color-coded shapefile.

[0886] Step 4: Display on the car navigation system

[0887] The device (car navigation system) makes an API call to the server every five minutes to obtain the latest accident risk information. The input is an API request to the server, and the output is real-time accident risk information.

[0888] The acquired risk information is displayed on a map. Red icons are displayed for high-risk areas, yellow for medium-risk areas, and green for low-risk areas. The input is the acquired risk information, and the output is a visualized map display.

[0889] Step 5: Inform users of the risk

[0890] When the user approaches a risk area, the car navigation system will warn them with a voice message. The distance is measured using GPS data, and a warning is issued when the user approaches within 500 meters. The input is GPS location data, and the output is a voice message.

[0891] A warning message is also displayed on the car navigation screen, allowing users to visually recognize the risk. The input is GPS location data, and the output is a warning message on the screen.

[0892] (Application example 1)

[0893] 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."

[0894] For current autonomous vehicles, systems that provide immediate and appropriate warnings and responses to traffic accident risk areas have not been fully developed. As a result, it is difficult to detect traffic accident risks at specific locations in advance and respond appropriately, and the risk of accidents remains high. To solve this issue, a system is needed that issues real-time warnings when an autonomous vehicle approaches a traffic accident risk area and adjusts the vehicle's operation.

[0895] 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.

[0896] In this invention, the server includes means for collecting traffic accident information from the police, means for storing the collected traffic accident information in a database, and means for analyzing past traffic accident data and identifying accident risk areas, which enables means for integrating the identified accident risk areas with map data and displaying them, means for providing accident risk information to autonomous vehicles in real time, and means for displaying the provided accident risk information on the autonomous vehicles and adjusting their operation.

[0897] The "means of collecting traffic accident information from the police" refers to a system for automatically obtaining data on traffic accidents held by police agencies using communication means such as the Internet.

[0898] "Means for storing collected traffic accident information in a database" refers to technology for efficiently storing and managing acquired traffic accident data using a database management system such as SQL or NoSQL.

[0899] "Means for analyzing past traffic accident data and identifying accident risk areas" refers to a method for applying algorithms such as statistical analysis and machine learning to stored traffic accident data to evaluate and identify accident risks in specific areas based on past trends and patterns.

[0900] "Means for integrating and displaying identified accident risk areas with map data" refers to GIS (geographic information system) technology that integrates the location information (latitude and longitude data) of identified risk areas into digital map data and displays them visually.

[0901] "Means for providing accident risk information to autonomous vehicles in real time" refers to technology for instantly transmitting accident risk information analyzed on a server to autonomous vehicles via the Internet or a dedicated communication network.

[0902] "Means for displaying the provided accident risk information on the autonomous vehicle and adjusting the vehicle's operation" refers to technology that conveys the received accident risk information to the driver using displays and speakers inside the vehicle, and further issues warnings and instructions to adjust the vehicle's operation to the vehicle's control system.

[0903] The system that realizes this invention mainly includes three elements: a server, a terminal (a computer of an autonomous vehicle), and a user. Below, we will explain how each element works.

[0904] server

[0905] The server first collects traffic accident information from the police. This involves periodically connecting to the police traffic accident database via the Internet to obtain information such as the date, time, location, cause, circumstances, and details of the accident. The obtained data is stored using a relational database system such as SQLite or MySQL.

[0906] The server then queries and analyzes historical traffic accident data from its built-in database, using statistical methods and machine learning algorithms to classify accident risk areas into high, medium, or low risk categories, with risk levels determined based on the frequency and severity of accidents.

[0907] Furthermore, the server integrates the location information (latitude and longitude data) of high-risk areas with map data using GIS tools, which allows the risk areas to be visually displayed on the map with specific colors (e.g., red for high risk) and icons.

[0908] Terminal (autonomous vehicle computer)

[0909] The autonomous vehicle's computer retrieves risk information from the server in real time. This is done using an API, with the latest data being updated regularly. The acquired risk information is then communicated to the user via the vehicle's display and speaker. For example, a voice message or a screen display can be used to warn of risk areas.

[0910] The autonomous vehicle's computer can also automatically adjust the vehicle's behavior when approaching a risk area, for example by reducing speed or changing course.

[0911] User

[0912] Users receive warnings from this system while riding in an autonomous vehicle. Specifically, when approaching a risk area, they receive a voice message saying, "There are many accidents when turning right at this intersection. Please be careful." In addition, the risk area is displayed in color on the vehicle's display, allowing users to visually recognize the risk.

[0913] Specific examples

[0914] For example, if a certain intersection in a city center has experienced more than 10 right-turn collisions in the past year, the server will use this information to identify the intersection as "high risk" and integrate the latitude and longitude data into a map. The autonomous vehicle's computer will retrieve this information from the server in real time and display it as a red icon on the map. When the user approaches this intersection, a voice warning will sound, saying, "This intersection has a high rate of right-turn collisions. Please drive carefully," and the vehicle's speed will automatically decrease.

[0915] Prompt Sentence Examples

[0916] For example, a sample prompt for building this system using a generative AI model is as follows:

[0917] Please create a Python program to retrieve past traffic accident data from a traffic accident database and identify risk areas for traffic accidents. Please also include functionality to integrate this into the control system of an autonomous vehicle, including risk areas, and provide risk warnings in real time.

[0918] It retrieves data from the server, analyzes the data, identifies risk areas, and integrates the control of the autonomous vehicle. It also displays warnings based on the vehicle's current location and adjusts vehicle control if necessary.

[0919] In this way, by describing the specific embodiments of the invention, anyone can carry out the invention.

[0920] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0921] Step 1:

[0922] The server periodically connects to the police traffic accident database via the Internet to collect traffic accident information. Specifically, it obtains the date, time, location, cause, circumstances, and damage details of the traffic accident. The input of this process is the police database connection information, and the output is the obtained traffic accident data.

[0923] Step 2:

[0924] The server stores the acquired traffic accident data in a database (e.g., SQLite or MySQL), which allows for data organization and efficient management. The input of this process is the acquired traffic accident data, and the output is the information stored in the database.

[0925] Step 3:

[0926] The server queries past traffic accident data from its built-in database and performs data analysis, for example, using statistical methods and machine learning algorithms to analyze accident frequency and causes and identify accident risk areas. The input to this process is the traffic accident data stored in the database, and the output is the identified accident risk area information.

[0927] Step 4:

[0928] The server integrates the location information (latitude and longitude data) of the identified accident risk areas with map data using GIS tools. This integration makes it possible to visually display the risk areas on a map with specific colors and icons. The input of this process is accident risk area information, and the output is visualized map data.

[0929] Step 5:

[0930] The terminal (the computer in the autonomous vehicle) retrieves risk information from the server in real time. The latest data is updated periodically using an API. The input to this process is the latest risk information provided by the server, and the output is the risk information taken into the vehicle.

[0931] Step 6:

[0932] The terminal notifies the user of the acquired risk information through the display or speaker of the autonomous vehicle. For example, when approaching a specific risk area, a warning is given by voice message or on-screen display. The input of this process is the risk information taken into the vehicle, and the output is a visual and audio warning to the user.

[0933] Step 7:

[0934] The terminal automatically adjusts the vehicle's behavior when approaching a risk area, for example by slowing the vehicle down or instructing it to change course. The input to this process is real-time location and risk information, and the output is adjusted vehicle behavior.

[0935] Step 8:

[0936] While riding in an autonomous vehicle, the user receives warnings from the system. Specifically, when approaching a risk area, the user follows the voice message and visual display to drive safely. The input of this process is the warning information from the terminal, and the output is appropriate driving behavior.

[0937] Through these steps, the system provides appropriate traffic accident risk information to autonomous vehicles, enabling users and vehicles to work together to ensure safe driving.

[0938] 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.

[0939] The system of this invention consists of a server, a terminal (car navigation system), an emotion engine, and a user. The functions and specific operations of each will be explained below.

[0940] 1. Data Collection

[0941] server

[0942] The server periodically connects to the police traffic accident database to collect traffic accident information, including the date, time, location, cause, circumstances, and damage details of the accident.

[0943] This data is stored in an internal database and can be efficiently managed and searched using SQL queries.

[0944] 2. Data analysis

[0945] server

[0946] The server queries and retrieves past traffic accident data from the database.

[0947] The acquired data is analyzed to identify areas at risk of accidents. Statistical methods are used to identify areas where accidents have occurred in the past, including their causes and frequency.

[0948] Based on the results of the risk assessment, the identified accident risk areas are classified as high risk, medium risk, or low risk.

[0949] 3. Integration with map data

[0950] server

[0951] The server integrates the location information (latitude and longitude data) of the risk area with map data using GIS tools.

[0952] The combined risk areas are displayed on a map in a color-coded format: high risk is red, medium risk is yellow, and low risk is green.

[0953] 4. Display on car navigation systems

[0954] Terminal (car navigation system)

[0955] The device retrieves the latest accident risk information from the server in real time, and this retrieval is performed periodically using API calls.

[0956] The acquired risk information is reflected on a map, and icons and colors indicating risk areas are visually displayed.

[0957] 5. Emotional engine recognition and adjustment

[0958] Terminal (car navigation system)

[0959] The device is equipped with an emotion engine that recognizes the user's emotions and determines the user's emotional state based on voice and facial expression analysis.

[0960] The emotion engine recognizes the user's emotions and adjusts the content and intensity of the warnings. For example, if the user is feeling anxious, a calm voice message will be provided to encourage them to drive calmly.

[0961] 6. Notice to Users

[0962] User

[0963] When the user approaches a risk area, the device (car navigation system) issues a voice message warning, which includes specific points to be aware of (for example, "This intersection is prone to collisions when turning right").

[0964] The emotion engine recognizes the user's emotional state and adjusts the tone and wording of the voice message accordingly. For example, if the user is in a relaxed state, a standard warning tone will be used to notify the user.

[0965] The device also displays warning messages on the screen, allowing users to visually and audibly recognize risk information and drive carefully.

[0966] Specific examples

[0967] For example, suppose there have been more than 10 right-turn collisions at a certain intersection in the city center in the past year. Based on this information, the server identifies the intersection as "high risk" and integrates the latitude and longitude data into a map. The car navigation device retrieves this information from the server in real time and displays it on the map as a red icon.

[0968] When the user approaches this intersection, the car navigation system issues a voice warning saying, "There are many collisions when turning right at this intersection. Please drive carefully." At the same time, a warning message is displayed on the screen. If the emotion engine recognizes the user's emotional state as "anxious," it softens the tone of the warning and adds a message encouraging the user to drive calmly.

[0969] This system effectively integrates past traffic accident data with the user's real-time emotional state, providing users with realistic and immediate risk information, thereby preventing traffic accidents from occurring.

[0970] The processing flow will be explained below.

[0971] Step 1:

[0972] The server connects to the police traffic accident database and collects the latest traffic accident information, including the date, time, location, cause, circumstances, and details of the damage.

[0973] Step 2:

[0974] The server collects traffic accident information and stores it in a built-in database. The data is managed using a relational database such as SQL.

[0975] Step 3:

[0976] The server queries the database for past traffic accident data and extracts information such as the location, cause, and frequency of accidents.

[0977] Step 4:

[0978] The server analyzes the extracted accident data to identify accident risk areas, and uses statistical methods to evaluate accident frequency and trends.

[0979] Step 5:

[0980] The server classifies the identified risk areas into high, medium, and low risk categories based on the frequency and severity of accidents.

[0981] Step 6:

[0982] The server integrates the location information (latitude and longitude) of the risk area with map data using a GIS tool, allowing the risk area to be visually displayed on a map.

[0983] Step 7:

[0984] The server displays risk areas on the map data in different colors: high risk areas in red, medium risk areas in yellow, and low risk areas in green.

[0985] Step 8:

[0986] The device (car navigation system) retrieves the latest risk information from the server in real time, and this information is updated periodically using API calls.

[0987] Step 9:

[0988] Based on the risk information acquired by the device (car navigation system), risk areas are displayed on a map. Icons and colors are used so that users can visually identify risk areas.

[0989] Step 10:

[0990] The device (car navigation system) uses an emotion engine that recognizes the user's emotions to analyze the user's emotional state from their voice and facial expressions.

[0991] Step 11:

[0992] The device (car navigation system) adjusts the content and intensity of the warning based on the user's emotional state. For example, if the user is feeling anxious, it will provide a calm voice message encouraging them to drive calmly.

[0993] Step 12:

[0994] When the user approaches a risk area, the device (car navigation system) warns the user with a voice message, including specific warnings such as, "There are many collisions when turning right at this intersection. Please drive carefully."

[0995] Step 13:

[0996] The device (car navigation system) also displays a warning message on the screen, allowing the user to visually and audibly recognize risk information and drive carefully.

[0997] Through these steps, the system can combine past traffic accident data with the user's emotional state to more effectively reduce accident risk.

[0998] Example 2

[0999] 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."

[1000] Conventional traffic accident risk warning systems have issues with the accuracy and timeliness of the accident risk information they obtain in real time, making it difficult to effectively alert users to driving. In addition, warnings are not adjusted to take into account the user's emotional state, making it difficult to encourage appropriate decisions and actions by users.

[1001] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting traffic accident information, means for storing the collected traffic accident information in a data management device, means for analyzing past traffic accident data and identifying accident risk areas, means for integrating the identified accident risk areas with map data and displaying them, means for providing accident risk information to a guidance device in real time, means for displaying the provided accident risk information on the guidance device and issuing a warning to the user, and means for recognizing the user's emotional state and adjusting the content of the warning. This makes it possible to provide the user with appropriate accident risk information in real time and to issue a warning while taking the user's emotional state into consideration.

[1002] "Traffic accident information" is data including the date and time, location, cause, circumstances, and details of damage caused by a traffic accident.

[1003] "Data management device" refers to a database for storing and managing collected data and its control device.

[1004] "Accident risk areas" are areas with a high risk of accidents, analyzed based on past traffic accident data.

[1005] The "guidance device" is a device including a car navigation system installed in an automobile.

[1006] "Emotional state" refers to the user's psychological and emotional state, and is determined by facial expressions, tone of voice, etc.

[1007] "Warning content" is the audio or visual warning message provided to the user.

[1008] The system of this invention is mainly composed of a server, a terminal, and a user. The functions and specific operations of each will be explained below.

[1009] Server Features

[1010] server

[1011] The server first periodically connects to the police's traffic accident database to collect traffic accident information. This information includes the date, time, location, cause, circumstances, and damage details of the accident. This data is stored in a built-in database, and is managed and searched using a PostgreSQL database and SQL queries. The server then queries and retrieves past traffic accident data from the database and identifies accident risk areas using statistical methods. This analysis is performed using Python libraries such as pandas and scikit-learn. The identified risk areas are then classified into high, medium, and low risk, and are further integrated with map data using GIS tools (e.g., ArcGIS).

[1012] Device Features

[1013] Terminal (car navigation system)

[1014] The terminal periodically obtains the latest accident risk information from the server via an API call, and the obtained data is displayed on a map in real time using map display software. Web mapping libraries such as OpenLayers and Leaflet are used for this.

[1015] Additionally, the device is equipped with an emotion engine that recognizes the user's emotions. This emotion engine uses Microsoft Azure's Emotion API to analyze voice and facial expressions to determine the user's emotional state. Based on this information, the device can adjust the content and tone of warning messages.

[1016] User Experience

[1017] User

[1018] When the user approaches a risk area, the device will alert them with a voice message and a visual warning. For example, if the user approaches an intersection where more than 10 right-turn accidents have occurred in the past year, the device will issue a voice warning saying, "This intersection has a high incidence of right-turn collisions. Please drive carefully." A similar warning message will also be displayed on the device screen. If the emotion engine recognizes the user's emotional state as "anxious," the tone of the warning will become gentler and a message urging the user to drive calmly will be added.

[1019] Specific examples

[1020] For example, if a certain intersection in the city center has experienced more than 10 right-turn collisions in the past year, the server will identify the intersection as "high risk" based on this information and integrate the latitude and longitude data into the map. The car navigation device will obtain this information from the server in real time and display it as a red icon on the map. When the user approaches this intersection, a voice warning will be issued saying, "This intersection has seen many right-turn collisions. Please drive carefully." A warning message will also be displayed on the screen at the same time. If the emotion engine recognizes the user's emotional state as "anxious," it will soften the tone of the warning and add a message encouraging them to drive calmly.

[1021] Prompt Sentence Examples

[1022] The input prompt for the generative AI model is as follows:

[1023] Please explain how the Traffic Accident Risk Warning System program works, step by step, including the specific data collection procedures, data analysis methods, risk information map integration methods, and sentiment analysis methods for user notification.

[1024] This makes it possible to provide users with appropriate and real-time accident risk information and to issue warnings that take into account the user's emotional state.

[1025] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1026] Step 1: Collect traffic accident information

[1027] server

[1028] Input: Request to access police traffic accident database

[1029] Processing: The server periodically sends HTTP requests to the police traffic accident database and retrieves traffic accident information in JSON format, including the date, time, location, cause, circumstances, and damage details of the accident.

[1030] Output: Acquired traffic accident information

[1031] Specific operation: The server sends an API request using the curl command, and the received JSON data is parsed by a Python script and recorded in a log file.

[1032] Step 2: Save your data

[1033] server

[1034] Input: Acquired traffic accident information

[1035] Processing: The server saves the acquired traffic accident information in the built-in database (PostgreSQL). The information is stored in a table with fields for the accident date and time, location, cause, situation, and details of the damage.

[1036] Output: Traffic accident information stored in a database

[1037] Specific operation: Using Python's psycopg2 library, the parsed data is converted into an SQL insert statement and inserted into the database.

[1038] Step 3: Analyze the data

[1039] server

[1040] Input: Past traffic accident data stored in a database

[1041] Processing: The server retrieves past traffic accident data using SQL queries and identifies accident risk areas using statistical methods. Specifically, it analyzes the data using libraries such as pandas and scikit-learn and classifies risk areas into high, medium, and low risk.

[1042] Output: Identified accident risk area information

[1043] Specific operation: Executes the SQL query SELECT location, COUNT() FROM accidents WHERE date BETWEEN '2022-01-01' AND '2022-12-31' GROUP BY location and saves the aggregated results in an Excel file.

[1044] Step 4: Integrating with map data

[1045] server

[1046] Input: Identified accident risk area information

[1047] Processing: The server integrates the latitude and longitude data of the identified risk areas with map data using a GIS tool (e.g., ArcGIS) and displays them in color. High risk is displayed in red, medium risk in yellow, and low risk in green.

[1048] Output: Integrated map data

[1049] Specific operation: Using Python's geopandas library, latitude and longitude information of risk areas is read and plotted on a map, generating a color-coded map image.

[1050] Step 5: Obtaining accident risk information

[1051] Terminal (car navigation system)

[1052] Input: Make an API call to the server to request risk area information

[1053] Processing: The device retrieves the latest risk area information from the server and integrates the data into the map application. The API is implemented in a RESTful format, and requests are made using the HTTP GET method.

[1054] Output: Obtained risk area information

[1055] Specific operation: The device uses the requests library to send a request to the server endpoint http: / / example.com / api / risks and stores the retrieved data in memory.

[1056] Step 6: Map risk information

[1057] Terminal (car navigation system)

[1058] Input: Obtained risk area information

[1059] Processing: The risk information acquired by the device is integrated into map display software and displayed on the map in real time. A web mapping library (e.g., OpenLayers or Leaflet) is used to display risk areas.

[1060] Output: Map showing risk areas

[1061] Specific operation: Loads the GeoJSON data of risk areas into the device's map app and plots it as a map layer. High-risk areas are displayed in red, medium-risk areas in yellow, and low-risk areas in green.

[1062] Step 7: Recognizing user emotions

[1063] Terminal (car navigation system)

[1064] Input: User's facial expression data and voice data

[1065] Processing: The device's built-in emotion engine analyzes the user's facial expression data and voice data acquired through the camera and microphone to determine the user's emotional state. This is done using Microsoft Azure's Emotion API, among other things.

[1066] Output: Recognized emotional state of the user

[1067] Specific operation: The device captures an image of the user with its camera and sends it to the Azure Emotion API, where it receives an emotion label such as "angry" or "calm."

[1068] Step 8: User Notification

[1069] Terminal (car navigation system)

[1070] Input: Risk area information, user emotional state

[1071] Treatment: When the user approaches a risk area, audio messages and visual warnings are used to alert the user. The content and tone of the messages are adjusted based on the emotional state recognized by the emotion engine.

[1072] Output: Warning message

[1073] Specific operation: If the user is in a hurry, a voice message will be played in a calm tone saying, "There are many accidents when turning right at this intersection. Please drive calmly," and a similar warning message will be displayed on the screen.

[1074] (Application example 2)

[1075] 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."

[1076] To prevent traffic accidents, it is important to predict dangerous areas based on past accident data and to provide appropriate warnings accordingly. However, current systems have difficulty providing appropriate warnings in real time based on individual users' situations and emotional states. Therefore, there is a need to develop a system that can efficiently provide accident risk information and provide appropriate warnings based on the user's emotional state.

[1077] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting traffic accident information from the police, means for storing the collected traffic accident information in a database, and means for analyzing past traffic accident data and identifying accident risk areas. This makes it possible to predict traffic accident risk areas and provide them to autonomously driven vehicles in real time. In addition, by including means for displaying on the autonomous driving system and issuing a warning to the user, means for recognizing the user's emotional state, and means for adjusting the warning message based on the recognized emotional state, it is possible to provide an appropriate warning according to the user's state and prevent traffic accidents from occurring.

[1078] The "police" is a government agency that maintains public safety and order and protects the lives and property of citizens.

[1079] "Means for collecting traffic accident information" refers to a method or system for obtaining details of the date, time, location, cause, circumstances, and damage of an accident from the police traffic accident database.

[1080] "Means of storing in a database" refers to a system or method for systematically storing collected traffic accident information and keeping it in a state that can be efficiently managed and searched.

[1081] "Means of analyzing past traffic accident data and identifying accident risk areas" refers to techniques and methods for analyzing accumulated traffic accident data using statistical methods to identify areas and situations where accidents occur frequently.

[1082] "Means for integrating and displaying with map data" refers to techniques and methods for visually displaying the location information of identified accident risk areas in combination with map information.

[1083] "Means for providing to autonomous vehicles" refers to the communication means and protocols for transmitting accident risk information from the server to autonomous vehicles in real time.

[1084] "Means for displaying on the automated driving system and issuing a warning to the user" refers to a method or system for notifying the user of accident risk areas and urging their attention using the display or audio output device of the automated driving system.

[1085] "Means for recognizing the user's emotional state" refers to techniques or methods for analyzing the user's facial expressions and tone of voice using a camera, voice analysis device, etc., to determine the user's emotional state.

[1086] The "means for adjusting the warning message" refers to a technique or method for appropriately changing the warning content, such as audio or displayed on a display, based on the recognized emotional state of the user.

[1087] The system of this invention consists of a server, a terminal of an autonomous vehicle, an emotion engine, and a user. The functions and specific operations of each will be explained below.

[1088] 1. Data Collection

[1089] server

[1090] The server periodically connects to the police traffic accident database to collect traffic accident information. The collected data includes the date, time, location, cause, circumstances, and damage details of the accident. This data is stored in the built-in database and can be efficiently managed and searched using SQL queries.

[1091] 2. Data analysis

[1092] server

[1093] The server queries and retrieves past traffic accident data from a database. The retrieved data is analyzed to identify accident risk areas. Statistical methods such as past accident locations, causes, and frequency are used for identification. Based on the results of the risk assessment, the identified accident risk areas are classified as high risk, medium risk, or low risk.

[1094] 3. Integration with map data

[1095] server

[1096] The server integrates the location information (latitude and longitude data) of risk areas with map data using GIS tools. The integrated risk areas are color-coded and displayed on the map. It is possible to set the display color to red for high risk, yellow for medium risk, and green for low risk.

[1097] 4. Display on autonomous vehicles

[1098] Terminal (autonomous vehicle)

[1099] The device retrieves the latest accident risk information from the server in real time. This retrieval is performed periodically using API calls. The retrieved risk information is reflected in the autonomous driving system, and icons and colors indicating risk areas are visually displayed.

[1100] 5. Emotional engine recognition and adjustment

[1101] Terminal (autonomous vehicle)

[1102] The device is equipped with an emotion engine that recognizes the user's emotions. This emotion engine determines the user's emotional state based on the camera and voice analysis device. Based on the user's emotions recognized by the emotion engine, the content and intensity of the warnings are adjusted. For example, if the user is feeling anxious, a calm voice message urging them to drive calmly is provided.

[1103] 6. Notice to Users

[1104] User

[1105] When the user approaches a risk area, the device (autonomous vehicle) will issue a voice warning. The voice warning will include specific points to be aware of (for example, "This intersection is prone to right-turn collisions"). The tone and wording of the voice message will be adjusted appropriately based on the user's emotional state as recognized by the emotion engine. For example, if the user is in a relaxed state, the notification will be issued in a standard warning tone. The device will also display a warning message on the screen. This allows the user to recognize risk information visually and audibly and drive carefully.

[1106] Specific examples

[1107] For example, suppose there have been more than 10 right-turn collisions at a certain intersection in the city center over the past year. Based on this information, the server identifies the intersection as "high risk" and integrates the latitude and longitude data into a map. The autonomous vehicle's device obtains this information from the server in real time and displays it as a red icon on the map. When the user approaches this intersection, the device issues a voice warning saying, "This intersection has a high rate of right-turn collisions. Please drive carefully." At the same time, a warning message is also displayed on the screen. If the emotion engine recognizes the user's emotional state as "anxious," it softens the tone of the warning and adds a message encouraging them to drive calmly.

[1108] Example of generative AI model and prompt

[1109] The emotion engine uses a facial recognition model using OpenCV and an emotion classification model using TensorFlow. An example prompt is, "Analyze image data to determine whether the user is relaxed or anxious. The output will be an emotion label such as relaxed, anxious, or angry, along with its confidence score."

[1110] This effectively integrates past traffic accident data with the user's real-time emotional state, providing users with realistic and immediate risk information, thereby preventing traffic accidents from occurring.

[1111] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1112] Step 1:

[1113] The server collects traffic accident information

[1114] The server periodically connects to the police traffic accident database to retrieve accident information. At this time, the date and time of the accident, location, cause, circumstances, and details of the damage are collected as data. The collected data is stored in the database. Specifically, data is inserted and updated in the database using SQL queries.

[1115] Input: Police traffic accident database

[1116] Output: Traffic accident data stored in a database

[1117] Step 2:

[1118] The server analyzes past traffic accident data and identifies areas at risk of accidents.

[1119] The server analyzes the accumulated traffic accident data to identify areas where accidents frequently occur, and then uses statistical methods to analyze the frequency and causes of accidents, thereby classifying areas into high-risk, medium-risk, and low-risk.

[1120] Input: Traffic accident data in the database

[1121] Output: Classified accident risk areas

[1122] Step 3:

[1123] The server integrates location information of accident risk areas with map data.

[1124] The server integrates the latitude and longitude data of risk areas with map information and visually displays them using a GIS tool. High-risk areas are displayed in red, medium-risk areas in yellow, and low-risk areas in green.

[1125] Input: Latitude and longitude data of classified accident risk areas

[1126] Output: Map data of color-coded risk areas

[1127] Step 4:

[1128] The device obtains the latest accident risk information from the server.

[1129] The terminal (autonomous vehicle) periodically uses an API call to obtain accident risk information from the server and displays it on the autonomous driving system. The obtained information includes the location information of risk areas and their risk levels.

[1130] Input: Accident risk information provided by the server

[1131] Output: Risk information displayed on the automated driving system

[1132] Step 5:

[1133] The device recognizes the user's emotional state

[1134] The device is equipped with an emotion engine that uses a camera and voice analysis device to recognize the user's emotional state in real time, using generative AI models (e.g., OpenCV, TensorFlow) for image processing and voice analysis.

[1135] Input: User's facial image and voice data

[1136] Output: Emotional state (relaxed, anxious, etc.) label and confidence score

[1137] Step 6:

[1138] The device adjusts warning messages based on the user's perceived emotional state.

[1139] The device adjusts the content and tone of the warning message based on the emotional state provided by the emotion engine: if the user is anxious, a calm message is provided, and if the user is relaxed, a standard message is provided.

[1140] Input: Emotional state label and confidence score

[1141] Output: Adjusted warning message

[1142] Step 7:

[1143] Notify the user when the device approaches a risk area

[1144] When a user approaches a risk area, the device will issue a warning via voice and display. The warning will include specific risk information (e.g., "This intersection has a high incidence of right-turn collisions") and will be delivered in a tone and content that takes into account the user's emotional state.

[1145] Input: Risk area information displayed on the device, warning messages based on emotional state

[1146] Output: Audio and visual warnings to the user

[1147] 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.

[1148] 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.

[1149] 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.

[1150] [Fourth embodiment]

[1151] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1152] 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.

[1153] 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).

[1154] 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.

[1155] 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.

[1156] 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).

[1157] 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.

[1158] 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.

[1159] 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.

[1160] 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.

[1161] 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.

[1162] 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.

[1163] 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."

[1164] The system of this invention mainly consists of a server, a terminal (car navigation system), and a user. The functions and specific operations of each will be explained below.

[1165] 1. Data Collection

[1166] server

[1167] The server periodically connects to the police traffic accident database and collects traffic accident information, including the date, time, location, cause, circumstances, and damage details of the traffic accident.

[1168] The collected data is stored by the server in an internal database, which can use a relational database system such as SQLite or MySQL.

[1169] 2. Data analysis

[1170] server

[1171] The server queries and retrieves past traffic accident data from its built-in database.

[1172] The acquired data is analyzed to identify areas at risk of accidents. This analysis uses statistical methods to identify the locations, causes, and frequency of past accidents.

[1173] Identified risk areas are classified into high, medium, and low risk areas, for example, by setting risk levels based on the frequency and severity of accidents.

[1174] 3. Integration with map data

[1175] server

[1176] The location information (latitude and longitude data) of high-risk areas will be integrated with map data using GIS tools.

[1177] This integration allows risk areas to be visually displayed on a map with specific colors and icons, for example, red for high risk areas, yellow for medium risk areas, and green for low risk areas.

[1178] 4. Display on car navigation systems

[1179] Terminal (car navigation system)

[1180] The car navigation device retrieves risk information in real time from the server, which updates the data periodically using API calls.

[1181] The car navigation system visualizes the acquired risk information on a map, and displays icons and colors indicating risk areas on the map on the device to visually warn the user.

[1182] 5. Notice to Users

[1183] User

[1184] When a user approaches a risk area while driving using a car navigation device, the car navigation system will warn them with a voice message.

[1185] This voice warning includes detailed information about the risk area (for example, "This intersection is prone to collisions when turning right") and provides the user with specific precautions to take.

[1186] In addition, a warning message will be displayed on the car navigation screen, allowing users to visually recognize risk areas.

[1187] Specific examples

[1188] For example, suppose there have been more than 10 right-turn collisions at a certain intersection in the city center in the past year. Based on this information, the server identifies the intersection as "high risk" and integrates the latitude and longitude data into a map. The car navigation device retrieves this information from the server in real time and displays it on the map as a red icon.

[1189] When the user approaches this intersection, the car navigation system issues a voice warning saying, "There are many collisions when turning right at this intersection. Please drive carefully." At the same time, a warning message is displayed on the screen. This allows the user to recognize the risks in advance and drive carefully.

[1190] This system effectively utilizes past traffic accident data and provides users with realistic and immediate risk information, making it possible to prevent traffic accidents from occurring.

[1191] The processing flow will be explained below.

[1192] Step 1:

[1193] The server periodically connects to the police traffic accident database to collect traffic accident information, including the date, time, location, cause, circumstances, and details of the accident.

[1194] Step 2:

[1195] The server stores the collected traffic accident information in a built-in database, which can be used to efficiently manage and search the accident information using SQL queries.

[1196] Step 3:

[1197] The server queries the database for past traffic accident data and extracts the necessary information, particularly the location of the accident, the cause of the accident, and the frequency of the accident.

[1198] Step 4:

[1199] The server analyzes the extracted data to identify areas at risk of accidents, and uses statistical methods to evaluate the risk level of specific locations based on past accident data.

[1200] Step 5:

[1201] Based on the analysis results, the server classifies the identified accident risk areas into high, medium, and low risk categories, allowing for detailed risk assessment of each area.

[1202] Step 6:

[1203] The server integrates the location information (latitude and longitude data) of the risk area with map data, and this integration uses GIS tools to visually locate the risk area on a map.

[1204] Step 7:

[1205] The server displays risk areas on the map data in different colors: high risk areas in red, medium risk areas in yellow, and low risk areas in green.

[1206] Step 8:

[1207] The device (car navigation system) retrieves the latest accident risk information from the server in real time. This retrieval is periodically updated using API calls.

[1208] Step 9:

[1209] The risk information acquired by the device (car navigation system) is displayed on a map. Icons and colors indicating risk areas are reflected on the map, allowing users to visually confirm risks.

[1210] Step 10:

[1211] When the user approaches a risk area, the device (car navigation system) warns the user with a voice message, which includes specific points to be aware of (for example, "This intersection is prone to collisions when turning right").

[1212] Step 11:

[1213] The device (car navigation system) also displays a warning message on the screen, allowing the user to visually and audibly recognize and pay attention to risk information.

[1214] By repeating these steps, the risk of traffic accidents can be effectively reduced and users can be supported in safe driving.

[1215] Example 1

[1216] 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."

[1217] Conventional traffic information systems lack sufficient functionality to notify users of traffic accident risks in advance, and users are unable to recognize the risk even when they approach an accident risk area. In particular, there is a lack of methods to effectively utilize past accident data to prevent future traffic accidents.

[1218] 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.

[1219] In this invention, the server includes means for collecting traffic accident information from the police, means for storing the collected traffic accident information in a database, means for analyzing past traffic accident data and identifying accident risk areas, means for integrating and displaying the identified accident risk areas with map data, means for providing the accident risk information to the car navigation system in real time, means for displaying the provided accident risk information on the car navigation system and warning the user, and means for warning the user by voice message when the user approaches an accident risk area. This enables the user to recognize risk areas in advance while driving and encourages safe driving.

[1220] "Police" is a public institution used to collect traffic accident information.

[1221] "Traffic accident information" is data that includes the date, time, location, cause, circumstances, and details of damages related to traffic accidents.

[1222] A "database" is a system for systematically storing, managing, and searching collected traffic accident information.

[1223] "Analysis" is the process of evaluating and analyzing collected traffic accident information using statistical methods and identifying accident risk areas.

[1224] An "accident risk area" is a specific geographical area that is considered to have a high risk of traffic accidents based on past traffic accident data.

[1225] "Map Data" means a dataset containing geographic information represented using a Geographic Information System (GIS).

[1226] A "car navigation system" is an in-vehicle navigation system that displays real-time location information and map data and provides navigation information to users.

[1227] "Real time" is a time concept in which the latest information is processed and provided immediately.

[1228] A "voice message" is a communication method that conveys information to a user using voice.

[1229] "GIS tools" are software for creating, analyzing, and visualizing geographic information system data.

[1230] The system of this invention mainly consists of a server, a terminal (car navigation system), and a user, and while clarifying the roles of each component, it supports safe driving by notifying the user of traffic accident risks in advance. Specific examples are described below.

[1231] server

[1232] Data collection

[1233] The server periodically connects to the police traffic accident database to collect traffic accident information. Specifically, the server connects to the database via the police API at 2:00 AM every day to obtain the date and time of the accident, location (latitude and longitude), cause of the accident, accident situation, and details of the damage. This collected data is stored in an SQLite or MySQL database.

[1234] Data analysis

[1235] The server periodically queries and retrieves traffic accident data from the database for the past year. The retrieved data is analyzed using Python's Pandas library to identify accident risk areas. This analysis classifies areas into high, medium, or low risk based on the location, cause, and frequency of accidents. For example, an area with more than 10 accidents in a year is considered high risk.

[1236] Integration with map data

[1237] The location information (latitude and longitude data) of the identified accident risk areas is integrated with map data using a GIS tool such as QGIS. The integrated data is generated as a color-coded shapefile to visually display the risk areas. High-risk areas are shown in red, medium-risk areas in yellow, and low-risk areas in green.

[1238] Terminal (car navigation system)

[1239] Real-time information acquisition

[1240] The car navigation device makes an API call to the server every five minutes to obtain the latest accident risk information. This information is obtained using networks such as Wi-Fi and LTE.

[1241] Information Visualization

[1242] The acquired risk information is immediately reflected on the map, with red icons indicating high-risk areas, yellow icons indicating medium-risk areas, and green icons indicating low-risk areas.

[1243] User

[1244] Notification of approach to risk area

[1245] When a user approaches within 500 meters of an accident risk area while driving, the car navigation system will issue a warning voice message. For example, it may say, "There are many collisions when turning right at this intersection. Please drive carefully." At the same time, a warning message will also be displayed on the car navigation system screen. This will allow users to recognize the risk in advance and encourage safe driving.

[1246] Specific examples

[1247] If a certain intersection in a city center has more than 10 right-turn collisions per year, the server identifies this intersection as a "high-risk" area and integrates the latitude and longitude data into a map.

[1248] The car navigation device retrieves this information from the server in real time and displays it as a red icon on the map.

[1249] When the user approaches this intersection, a voice warning will sound, saying, "There are many collisions when turning right at this intersection. Please drive carefully." A risk area warning message will also be displayed on the screen.

[1250] Based on the above specific operational examples, this system effectively utilizes past traffic accident data and provides users with realistic and immediate risk information, thereby making it possible to prevent traffic accidents from occurring.

[1251] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1252] Step 1: Data collection

[1253] The server connects to the police traffic accident database. Through the API, it obtains the date and time of the traffic accident, location (latitude and longitude), cause, situation, and details of the damage. The input is raw data from the API, and the output is this data in a structured format (for example, JSON format).

[1254] The server stores the acquired traffic accident information in an SQLite or MySQL database. The input is structured traffic accident information, and the output is data saved in the database.

[1255] Step 2: Data analysis

[1256] The server queries and retrieves the traffic accident data from the database for the past year. It extracts the data using SQL queries. The input is the traffic accident data stored in the database, and the output is the dataset of the query results.

[1257] The server analyzes the acquired data using Python's Pandas library. The input is the query result dataset, and the output is the identification of accident risk areas (including locations, causes, and frequency).

[1258] Based on the analysis results, accident risk areas are classified as high risk, medium risk, or low risk. For example, an area where 10 or more accidents occur per year is classified as high risk. The input is the analysis results, and the output is area information classified by risk level.

[1259] Step 3: Integrating with map data

[1260] The server uses GIS tools such as QGIS to integrate the location information (latitude and longitude data) of identified accident risk areas into map data. The input is the location information of the risk area and the original map data, and the output is the integrated map data.

[1261] The merged data is generated as a color-coded shapefile, with high-risk areas shown in red, medium-risk areas in yellow, and low-risk areas in green. The input is the merged map data, and the output is a color-coded shapefile.

[1262] Step 4: Display on the car navigation system

[1263] The device (car navigation system) makes an API call to the server every five minutes to obtain the latest accident risk information. The input is an API request to the server, and the output is real-time accident risk information.

[1264] The acquired risk information is displayed on a map. Red icons are displayed for high-risk areas, yellow for medium-risk areas, and green for low-risk areas. The input is the acquired risk information, and the output is a visualized map display.

[1265] Step 5: Inform users of the risk

[1266] When the user approaches a risk area, the car navigation system will warn them with a voice message. The distance is measured using GPS data, and a warning is issued when the user approaches within 500 meters. The input is GPS location data, and the output is a voice message.

[1267] A warning message is also displayed on the car navigation screen, allowing users to visually recognize the risk. The input is GPS location data, and the output is a warning message on the screen.

[1268] (Application example 1)

[1269] 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."

[1270] For current autonomous vehicles, systems that provide immediate and appropriate warnings and responses to traffic accident risk areas have not been fully developed. As a result, it is difficult to detect traffic accident risks at specific locations in advance and respond appropriately, and the risk of accidents remains high. To solve this issue, a system is needed that issues real-time warnings when an autonomous vehicle approaches a traffic accident risk area and adjusts the vehicle's operation.

[1271] 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.

[1272] In this invention, the server includes means for collecting traffic accident information from the police, means for storing the collected traffic accident information in a database, and means for analyzing past traffic accident data and identifying accident risk areas, which enables means for integrating the identified accident risk areas with map data and displaying them, means for providing accident risk information to autonomous vehicles in real time, and means for displaying the provided accident risk information on the autonomous vehicles and adjusting their operation.

[1273] The "means of collecting traffic accident information from the police" refers to a system for automatically obtaining data on traffic accidents held by police agencies using communication means such as the Internet.

[1274] "Means for storing collected traffic accident information in a database" refers to technology for efficiently storing and managing acquired traffic accident data using a database management system such as SQL or NoSQL.

[1275] "Means for analyzing past traffic accident data and identifying accident risk areas" refers to a method for applying algorithms such as statistical analysis and machine learning to stored traffic accident data to evaluate and identify accident risks in specific areas based on past trends and patterns.

[1276] "Means for integrating and displaying identified accident risk areas with map data" refers to GIS (geographic information system) technology that integrates the location information (latitude and longitude data) of identified risk areas into digital map data and displays them visually.

[1277] "Means for providing accident risk information to autonomous vehicles in real time" refers to technology for instantly transmitting accident risk information analyzed on a server to autonomous vehicles via the Internet or a dedicated communication network.

[1278] "Means for displaying the provided accident risk information on the autonomous vehicle and adjusting the vehicle's operation" refers to technology that conveys the received accident risk information to the driver using displays and speakers inside the vehicle, and further issues warnings and instructions to adjust the vehicle's operation to the vehicle's control system.

[1279] The system that realizes this invention mainly includes three elements: a server, a terminal (a computer of an autonomous vehicle), and a user. Below, we will explain how each element works.

[1280] server

[1281] The server first collects traffic accident information from the police. This involves periodically connecting to the police traffic accident database via the Internet to obtain information such as the date, time, location, cause, circumstances, and details of the accident. The obtained data is stored using a relational database system such as SQLite or MySQL.

[1282] The server then queries and analyzes historical traffic accident data from its built-in database, using statistical methods and machine learning algorithms to classify accident risk areas into high, medium, or low risk categories, with risk levels determined based on the frequency and severity of accidents.

[1283] Furthermore, the server integrates the location information (latitude and longitude data) of high-risk areas with map data using GIS tools, which allows the risk areas to be visually displayed on the map with specific colors (e.g., red for high risk) and icons.

[1284] Terminal (autonomous vehicle computer)

[1285] The autonomous vehicle's computer retrieves risk information from the server in real time. This is done using an API, with the latest data being updated regularly. The acquired risk information is then communicated to the user via the vehicle's display and speaker. For example, a voice message or a screen display can be used to warn of risk areas.

[1286] The autonomous vehicle's computer can also automatically adjust the vehicle's behavior when approaching a risk area, for example by reducing speed or changing course.

[1287] User

[1288] Users receive warnings from this system while riding in an autonomous vehicle. Specifically, when approaching a risk area, they receive a voice message saying, "There are many accidents when turning right at this intersection. Please be careful." In addition, the risk area is displayed in color on the vehicle's display, allowing users to visually recognize the risk.

[1289] Specific examples

[1290] For example, if a certain intersection in a city center has experienced more than 10 right-turn collisions in the past year, the server will use this information to identify the intersection as "high risk" and integrate the latitude and longitude data into a map. The autonomous vehicle's computer will retrieve this information from the server in real time and display it as a red icon on the map. When the user approaches this intersection, a voice warning will sound, saying, "This intersection has a high rate of right-turn collisions. Please drive carefully," and the vehicle's speed will automatically decrease.

[1291] Prompt Sentence Examples

[1292] For example, a sample prompt for building this system using a generative AI model is as follows:

[1293] Please create a Python program to retrieve past traffic accident data from a traffic accident database and identify risk areas for traffic accidents. Please also include functionality to integrate this into the control system of an autonomous vehicle, including risk areas, and provide risk warnings in real time.

[1294] It retrieves data from the server, analyzes the data, identifies risk areas, and integrates the control of the autonomous vehicle. It also displays warnings based on the vehicle's current location and adjusts vehicle control if necessary.

[1295] In this way, by describing the specific embodiments of the invention, anyone can carry out the invention.

[1296] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1297] Step 1:

[1298] The server periodically connects to the police traffic accident database via the Internet to collect traffic accident information. Specifically, it obtains the date, time, location, cause, circumstances, and damage details of the traffic accident. The input of this process is the police database connection information, and the output is the obtained traffic accident data.

[1299] Step 2:

[1300] The server stores the acquired traffic accident data in a database (e.g., SQLite or MySQL), which allows for data organization and efficient management. The input of this process is the acquired traffic accident data, and the output is the information stored in the database.

[1301] Step 3:

[1302] The server queries past traffic accident data from its built-in database and performs data analysis, for example, using statistical methods and machine learning algorithms to analyze accident frequency and causes and identify accident risk areas. The input to this process is the traffic accident data stored in the database, and the output is the identified accident risk area information.

[1303] Step 4:

[1304] The server integrates the location information (latitude and longitude data) of the identified accident risk areas with map data using GIS tools. This integration makes it possible to visually display the risk areas on a map with specific colors and icons. The input of this process is accident risk area information, and the output is visualized map data.

[1305] Step 5:

[1306] The terminal (the computer in the autonomous vehicle) retrieves risk information from the server in real time. The latest data is updated periodically using an API. The input to this process is the latest risk information provided by the server, and the output is the risk information taken into the vehicle.

[1307] Step 6:

[1308] The terminal notifies the user of the acquired risk information through the display or speaker of the autonomous vehicle. For example, when approaching a specific risk area, a warning is given by voice message or on-screen display. The input of this process is the risk information taken into the vehicle, and the output is a visual and audio warning to the user.

[1309] Step 7:

[1310] The terminal automatically adjusts the vehicle's behavior when approaching a risk area, for example by slowing the vehicle down or instructing it to change course. The input to this process is real-time location and risk information, and the output is adjusted vehicle behavior.

[1311] Step 8:

[1312] While riding in an autonomous vehicle, the user receives warnings from the system. Specifically, when approaching a risk area, the user follows the voice message and visual display to drive safely. The input of this process is the warning information from the terminal, and the output is appropriate driving behavior.

[1313] Through these steps, the system provides appropriate traffic accident risk information to autonomous vehicles, enabling users and vehicles to work together to ensure safe driving.

[1314] 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.

[1315] The system of this invention consists of a server, a terminal (car navigation system), an emotion engine, and a user. The functions and specific operations of each will be explained below.

[1316] 1. Data Collection

[1317] server

[1318] The server periodically connects to the police traffic accident database to collect traffic accident information, including the date, time, location, cause, circumstances, and damage details of the accident.

[1319] This data is stored in an internal database and can be efficiently managed and searched using SQL queries.

[1320] 2. Data analysis

[1321] server

[1322] The server queries and retrieves past traffic accident data from the database.

[1323] The acquired data is analyzed to identify areas at risk of accidents. Statistical methods are used to identify areas where accidents have occurred in the past, including their causes and frequency.

[1324] Based on the results of the risk assessment, the identified accident risk areas are classified as high risk, medium risk, or low risk.

[1325] 3. Integration with map data

[1326] server

[1327] The server integrates the location information (latitude and longitude data) of the risk area with map data using GIS tools.

[1328] The combined risk areas are displayed on a map in a color-coded format: high risk is red, medium risk is yellow, and low risk is green.

[1329] 4. Display on car navigation systems

[1330] Terminal (car navigation system)

[1331] The device retrieves the latest accident risk information from the server in real time, and this retrieval is performed periodically using API calls.

[1332] The acquired risk information is reflected on a map, and icons and colors indicating risk areas are visually displayed.

[1333] 5. Emotional engine recognition and adjustment

[1334] Terminal (car navigation system)

[1335] The device is equipped with an emotion engine that recognizes the user's emotions and determines the user's emotional state based on voice and facial expression analysis.

[1336] The emotion engine recognizes the user's emotions and adjusts the content and intensity of the warnings. For example, if the user is feeling anxious, a calm voice message will be provided to encourage them to drive calmly.

[1337] 6. Notice to Users

[1338] User

[1339] When the user approaches a risk area, the device (car navigation system) issues a voice message warning, which includes specific points to be aware of (for example, "This intersection is prone to collisions when turning right").

[1340] The emotion engine recognizes the user's emotional state and adjusts the tone and wording of the voice message accordingly. For example, if the user is in a relaxed state, a standard warning tone will be used to notify the user.

[1341] The device also displays warning messages on the screen, allowing users to visually and audibly recognize risk information and drive carefully.

[1342] Specific examples

[1343] For example, suppose there have been more than 10 right-turn collisions at a certain intersection in the city center in the past year. Based on this information, the server identifies the intersection as "high risk" and integrates the latitude and longitude data into a map. The car navigation device retrieves this information from the server in real time and displays it on the map as a red icon.

[1344] When the user approaches this intersection, the car navigation system issues a voice warning saying, "There are many collisions when turning right at this intersection. Please drive carefully." At the same time, a warning message is displayed on the screen. If the emotion engine recognizes the user's emotional state as "anxious," it softens the tone of the warning and adds a message encouraging the user to drive calmly.

[1345] This system effectively integrates past traffic accident data with the user's real-time emotional state, providing users with realistic and immediate risk information, thereby preventing traffic accidents from occurring.

[1346] The processing flow will be explained below.

[1347] Step 1:

[1348] The server connects to the police traffic accident database and collects the latest traffic accident information, including the date, time, location, cause, circumstances, and details of the damage.

[1349] Step 2:

[1350] The server collects traffic accident information and stores it in a built-in database. The data is managed using a relational database such as SQL.

[1351] Step 3:

[1352] The server queries the database for past traffic accident data and extracts information such as the location, cause, and frequency of accidents.

[1353] Step 4:

[1354] The server analyzes the extracted accident data to identify accident risk areas, and uses statistical methods to evaluate accident frequency and trends.

[1355] Step 5:

[1356] The server classifies the identified risk areas into high, medium, and low risk categories based on the frequency and severity of accidents.

[1357] Step 6:

[1358] The server integrates the location information (latitude and longitude) of the risk area with map data using a GIS tool, allowing the risk area to be visually displayed on a map.

[1359] Step 7:

[1360] The server displays risk areas on the map data in different colors: high risk areas in red, medium risk areas in yellow, and low risk areas in green.

[1361] Step 8:

[1362] The device (car navigation system) retrieves the latest risk information from the server in real time, and this information is updated periodically using API calls.

[1363] Step 9:

[1364] Based on the risk information acquired by the device (car navigation system), risk areas are displayed on a map. Icons and colors are used so that users can visually identify risk areas.

[1365] Step 10:

[1366] The device (car navigation system) uses an emotion engine that recognizes the user's emotions to analyze the user's emotional state from their voice and facial expressions.

[1367] Step 11:

[1368] The device (car navigation system) adjusts the content and intensity of the warning based on the user's emotional state. For example, if the user is feeling anxious, it will provide a calm voice message encouraging them to drive calmly.

[1369] Step 12:

[1370] When the user approaches a risk area, the device (car navigation system) warns the user with a voice message, including specific warnings such as, "There are many collisions when turning right at this intersection. Please drive carefully."

[1371] Step 13:

[1372] The device (car navigation system) also displays a warning message on the screen, allowing the user to visually and audibly recognize risk information and drive carefully.

[1373] Through these steps, the system can combine past traffic accident data with the user's emotional state to more effectively reduce accident risk.

[1374] Example 2

[1375] 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."

[1376] Conventional traffic accident risk warning systems have issues with the accuracy and timeliness of the accident risk information they obtain in real time, making it difficult to effectively alert users to driving. In addition, warnings are not adjusted to take into account the user's emotional state, making it difficult to encourage appropriate decisions and actions by users.

[1377] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting traffic accident information, means for storing the collected traffic accident information in a data management device, means for analyzing past traffic accident data and identifying accident risk areas, means for integrating the identified accident risk areas with map data and displaying them, means for providing accident risk information to a guidance device in real time, means for displaying the provided accident risk information on the guidance device and issuing a warning to the user, and means for recognizing the user's emotional state and adjusting the content of the warning. This makes it possible to provide the user with appropriate accident risk information in real time and to issue a warning while taking the user's emotional state into consideration.

[1378] "Traffic accident information" is data including the date and time, location, cause, circumstances, and details of damage caused by a traffic accident.

[1379] "Data management device" refers to a database for storing and managing collected data and its control device.

[1380] "Accident risk areas" are areas with a high risk of accidents, analyzed based on past traffic accident data.

[1381] The "guidance device" is a device including a car navigation system installed in an automobile.

[1382] "Emotional state" refers to the user's psychological and emotional state, and is determined by facial expressions, tone of voice, etc.

[1383] "Warning content" is the audio or visual warning message provided to the user.

[1384] The system of this invention is mainly composed of a server, a terminal, and a user. The functions and specific operations of each will be explained below.

[1385] Server Features

[1386] server

[1387] The server first periodically connects to the police's traffic accident database to collect traffic accident information. This information includes the date, time, location, cause, circumstances, and damage details of the accident. This data is stored in a built-in database, and is managed and searched using a PostgreSQL database and SQL queries. The server then queries and retrieves past traffic accident data from the database and identifies accident risk areas using statistical methods. This analysis is performed using Python libraries such as pandas and scikit-learn. The identified risk areas are then classified into high, medium, and low risk, and are further integrated with map data using GIS tools (e.g., ArcGIS).

[1388] Device Features

[1389] Terminal (car navigation system)

[1390] The terminal periodically obtains the latest accident risk information from the server via an API call, and the obtained data is displayed on a map in real time using map display software. Web mapping libraries such as OpenLayers and Leaflet are used for this.

[1391] Additionally, the device is equipped with an emotion engine that recognizes the user's emotions. This emotion engine uses Microsoft Azure's Emotion API to analyze voice and facial expressions to determine the user's emotional state. Based on this information, the device can adjust the content and tone of warning messages.

[1392] User Experience

[1393] User

[1394] When the user approaches a risk area, the device will alert them with a voice message and a visual warning. For example, if the user approaches an intersection where more than 10 right-turn accidents have occurred in the past year, the device will issue a voice warning saying, "This intersection has a high incidence of right-turn collisions. Please drive carefully." A similar warning message will also be displayed on the device screen. If the emotion engine recognizes the user's emotional state as "anxious," the tone of the warning will become gentler and a message urging the user to drive calmly will be added.

[1395] Specific examples

[1396] For example, if a certain intersection in the city center has experienced more than 10 right-turn collisions in the past year, the server will identify the intersection as "high risk" based on this information and integrate the latitude and longitude data into the map. The car navigation device will obtain this information from the server in real time and display it as a red icon on the map. When the user approaches this intersection, a voice warning will be issued saying, "This intersection has seen many right-turn collisions. Please drive carefully." A warning message will also be displayed on the screen at the same time. If the emotion engine recognizes the user's emotional state as "anxious," it will soften the tone of the warning and add a message encouraging them to drive calmly.

[1397] Prompt Sentence Examples

[1398] The input prompt for the generative AI model is as follows:

[1399] Please explain how the Traffic Accident Risk Warning System program works, step by step, including the specific data collection procedures, data analysis methods, risk information map integration methods, and sentiment analysis methods for user notification.

[1400] This makes it possible to provide users with appropriate and real-time accident risk information and to issue warnings that take into account the user's emotional state.

[1401] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1402] Step 1: Collect traffic accident information

[1403] server

[1404] Input: Request to access police traffic accident database

[1405] Processing: The server periodically sends HTTP requests to the police traffic accident database and retrieves traffic accident information in JSON format, including the date, time, location, cause, circumstances, and damage details of the accident.

[1406] Output: Acquired traffic accident information

[1407] Specific operation: The server sends an API request using the curl command, and the received JSON data is parsed by a Python script and recorded in a log file.

[1408] Step 2: Save your data

[1409] server

[1410] Input: Acquired traffic accident information

[1411] Processing: The server saves the acquired traffic accident information in the built-in database (PostgreSQL). The information is stored in a table with fields for the accident date and time, location, cause, situation, and details of the damage.

[1412] Output: Traffic accident information stored in a database

[1413] Specific operation: Using Python's psycopg2 library, the parsed data is converted into an SQL insert statement and inserted into the database.

[1414] Step 3: Analyze the data

[1415] server

[1416] Input: Past traffic accident data stored in a database

[1417] Processing: The server retrieves past traffic accident data using SQL queries and identifies accident risk areas using statistical methods. Specifically, it analyzes the data using libraries such as pandas and scikit-learn and classifies risk areas into high, medium, and low risk.

[1418] Output: Identified accident risk area information

[1419] Specific operation: Executes the SQL query SELECT location, COUNT() FROM accidents WHERE date BETWEEN '2022-01-01' AND '2022-12-31' GROUP BY location and saves the aggregated results in an Excel file.

[1420] Step 4: Integrating with map data

[1421] server

[1422] Input: Identified accident risk area information

[1423] Processing: The server integrates the latitude and longitude data of the identified risk areas with map data using a GIS tool (e.g., ArcGIS) and displays them in color. High risk is displayed in red, medium risk in yellow, and low risk in green.

[1424] Output: Integrated map data

[1425] Specific operation: Using Python's geopandas library, latitude and longitude information of risk areas is read and plotted on a map, generating a color-coded map image.

[1426] Step 5: Obtaining accident risk information

[1427] Terminal (car navigation system)

[1428] Input: Make an API call to the server to request risk area information

[1429] Processing: The device retrieves the latest risk area information from the server and integrates the data into the map application. The API is implemented in a RESTful format, and requests are made using the HTTP GET method.

[1430] Output: Obtained risk area information

[1431] Specific operation: The device uses the requests library to send a request to the server endpoint http: / / example.com / api / risks and stores the retrieved data in memory.

[1432] Step 6: Map risk information

[1433] Terminal (car navigation system)

[1434] Input: Obtained risk area information

[1435] Processing: The risk information acquired by the device is integrated into map display software and displayed on the map in real time. A web mapping library (e.g., OpenLayers or Leaflet) is used to display risk areas.

[1436] Output: Map showing risk areas

[1437] Specific operation: Loads the GeoJSON data of risk areas into the device's map app and plots it as a map layer. High-risk areas are displayed in red, medium-risk areas in yellow, and low-risk areas in green.

[1438] Step 7: Recognizing user emotions

[1439] Terminal (car navigation system)

[1440] Input: User's facial expression data and voice data

[1441] Processing: The device's built-in emotion engine analyzes the user's facial expression data and voice data acquired through the camera and microphone to determine the user's emotional state. This is done using Microsoft Azure's Emotion API, among other things.

[1442] Output: Recognized emotional state of the user

[1443] Specific operation: The device captures an image of the user with its camera and sends it to the Azure Emotion API, where it receives an emotion label such as "angry" or "calm."

[1444] Step 8: User Notification

[1445] Terminal (car navigation system)

[1446] Input: Risk area information, user emotional state

[1447] Treatment: When the user approaches a risk area, audio messages and visual warnings are used to alert the user. The content and tone of the messages are adjusted based on the emotional state recognized by the emotion engine.

[1448] Output: Warning message

[1449] Specific operation: If the user is in a hurry, a voice message will be played in a calm tone saying, "There are many accidents when turning right at this intersection. Please drive calmly," and a similar warning message will be displayed on the screen.

[1450] (Application example 2)

[1451] 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."

[1452] To prevent traffic accidents, it is important to predict dangerous areas based on past accident data and to provide appropriate warnings accordingly. However, current systems have difficulty providing appropriate warnings in real time based on individual users' situations and emotional states. Therefore, there is a need to develop a system that can efficiently provide accident risk information and provide appropriate warnings based on the user's emotional state.

[1453] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting traffic accident information from the police, means for storing the collected traffic accident information in a database, and means for analyzing past traffic accident data and identifying accident risk areas. This makes it possible to predict traffic accident risk areas and provide them to autonomously driven vehicles in real time. In addition, by including means for displaying on the autonomous driving system and issuing a warning to the user, means for recognizing the user's emotional state, and means for adjusting the warning message based on the recognized emotional state, it is possible to provide an appropriate warning according to the user's state and prevent traffic accidents from occurring.

[1454] The "police" is a government agency that maintains public safety and order and protects the lives and property of citizens.

[1455] "Means for collecting traffic accident information" refers to a method or system for obtaining details of the date, time, location, cause, circumstances, and damage of an accident from the police traffic accident database.

[1456] "Means of storing in a database" refers to a system or method for systematically storing collected traffic accident information and keeping it in a state that can be efficiently managed and searched.

[1457] "Means of analyzing past traffic accident data and identifying accident risk areas" refers to techniques and methods for analyzing accumulated traffic accident data using statistical methods to identify areas and situations where accidents occur frequently.

[1458] "Means for integrating and displaying with map data" refers to techniques and methods for visually displaying the location information of identified accident risk areas in combination with map information.

[1459] "Means for providing to autonomous vehicles" refers to the communication means and protocols for transmitting accident risk information from the server to autonomous vehicles in real time.

[1460] "Means for displaying on the automated driving system and issuing a warning to the user" refers to a method or system for notifying the user of accident risk areas and urging their attention using the display or audio output device of the automated driving system.

[1461] "Means for recognizing the user's emotional state" refers to techniques or methods for analyzing the user's facial expressions and tone of voice using a camera, voice analysis device, etc., to determine the user's emotional state.

[1462] The "means for adjusting the warning message" refers to a technique or method for appropriately changing the warning content, such as audio or displayed on a display, based on the recognized emotional state of the user.

[1463] The system of this invention consists of a server, a terminal of an autonomous vehicle, an emotion engine, and a user. The functions and specific operations of each will be explained below.

[1464] 1. Data Collection

[1465] server

[1466] The server periodically connects to the police traffic accident database to collect traffic accident information. The collected data includes the date, time, location, cause, circumstances, and damage details of the accident. This data is stored in the built-in database and can be efficiently managed and searched using SQL queries.

[1467] 2. Data analysis

[1468] server

[1469] The server queries and retrieves past traffic accident data from a database. The retrieved data is analyzed to identify accident risk areas. Statistical methods such as past accident locations, causes, and frequency are used for identification. Based on the results of the risk assessment, the identified accident risk areas are classified as high risk, medium risk, or low risk.

[1470] 3. Integration with map data

[1471] server

[1472] The server integrates the location information (latitude and longitude data) of risk areas with map data using GIS tools. The integrated risk areas are color-coded and displayed on the map. It is possible to set the display color to red for high risk, yellow for medium risk, and green for low risk.

[1473] 4. Display on autonomous vehicles

[1474] Terminal (autonomous vehicle)

[1475] The device retrieves the latest accident risk information from the server in real time. This retrieval is performed periodically using API calls. The retrieved risk information is reflected in the autonomous driving system, and icons and colors indicating risk areas are visually displayed.

[1476] 5. Emotional engine recognition and adjustment

[1477] Terminal (autonomous vehicle)

[1478] The device is equipped with an emotion engine that recognizes the user's emotions. This emotion engine determines the user's emotional state based on the camera and voice analysis device. Based on the user's emotions recognized by the emotion engine, the content and intensity of the warnings are adjusted. For example, if the user is feeling anxious, a calm voice message urging them to drive calmly is provided.

[1479] 6. Notice to Users

[1480] User

[1481] When the user approaches a risk area, the device (autonomous vehicle) will issue a voice warning. The voice warning will include specific points to be aware of (for example, "This intersection is prone to right-turn collisions"). The tone and wording of the voice message will be adjusted appropriately based on the user's emotional state as recognized by the emotion engine. For example, if the user is in a relaxed state, the notification will be issued in a standard warning tone. The device will also display a warning message on the screen. This allows the user to recognize risk information visually and audibly and drive carefully.

[1482] Specific examples

[1483] For example, suppose there have been more than 10 right-turn collisions at a certain intersection in the city center over the past year. Based on this information, the server identifies the intersection as "high risk" and integrates the latitude and longitude data into a map. The autonomous vehicle's device obtains this information from the server in real time and displays it as a red icon on the map. When the user approaches this intersection, the device issues a voice warning saying, "This intersection has a high rate of right-turn collisions. Please drive carefully." At the same time, a warning message is also displayed on the screen. If the emotion engine recognizes the user's emotional state as "anxious," it softens the tone of the warning and adds a message encouraging them to drive calmly.

[1484] Example of generative AI model and prompt

[1485] The emotion engine uses a facial recognition model using OpenCV and an emotion classification model using TensorFlow. An example prompt is, "Analyze image data to determine whether the user is relaxed or anxious. The output will be an emotion label such as relaxed, anxious, or angry, along with its confidence score."

[1486] This effectively integrates past traffic accident data with the user's real-time emotional state, providing users with realistic and immediate risk information, thereby preventing traffic accidents from occurring.

[1487] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1488] Step 1:

[1489] The server collects traffic accident information

[1490] The server periodically connects to the police traffic accident database to retrieve accident information. At this time, the date and time of the accident, location, cause, circumstances, and details of the damage are collected as data. The collected data is stored in the database. Specifically, data is inserted and updated in the database using SQL queries.

[1491] Input: Police traffic accident database

[1492] Output: Traffic accident data stored in a database

[1493] Step 2:

[1494] The server analyzes past traffic accident data and identifies areas at risk of accidents.

[1495] The server analyzes the accumulated traffic accident data to identify areas where accidents frequently occur, and then uses statistical methods to analyze the frequency and causes of accidents, thereby classifying areas into high-risk, medium-risk, and low-risk.

[1496] Input: Traffic accident data in the database

[1497] Output: Classified accident risk areas

[1498] Step 3:

[1499] The server integrates location information of accident risk areas with map data.

[1500] The server integrates the latitude and longitude data of risk areas with map information and visually displays them using a GIS tool. High-risk areas are displayed in red, medium-risk areas in yellow, and low-risk areas in green.

[1501] Input: Latitude and longitude data of classified accident risk areas

[1502] Output: Map data of color-coded risk areas

[1503] Step 4:

[1504] The device obtains the latest accident risk information from the server.

[1505] The terminal (autonomous vehicle) periodically uses an API call to obtain accident risk information from the server and displays it on the autonomous driving system. The obtained information includes the location information of risk areas and their risk levels.

[1506] Input: Accident risk information provided by the server

[1507] Output: Risk information displayed on the automated driving system

[1508] Step 5:

[1509] The device recognizes the user's emotional state

[1510] The device is equipped with an emotion engine that uses a camera and voice analysis device to recognize the user's emotional state in real time, using generative AI models (e.g., OpenCV, TensorFlow) for image processing and voice analysis.

[1511] Input: User's facial image and voice data

[1512] Output: Emotional state (relaxed, anxious, etc.) label and confidence score

[1513] Step 6:

[1514] The device adjusts warning messages based on the user's perceived emotional state.

[1515] The device adjusts the content and tone of the warning message based on the emotional state provided by the emotion engine: if the user is anxious, a calm message is provided, and if the user is relaxed, a standard message is provided.

[1516] Input: Emotional state label and confidence score

[1517] Output: Adjusted warning message

[1518] Step 7:

[1519] Notify the user when the device approaches a risk area

[1520] When a user approaches a risk area, the device will issue a warning via voice and display. The warning will include specific risk information (e.g., "This intersection has a high incidence of right-turn collisions") and will be delivered in a tone and content that takes into account the user's emotional state.

[1521] Input: Risk area information displayed on the device, warning messages based on emotional state

[1522] Output: Audio and visual warnings to the user

[1523] 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.

[1524] 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.

[1525] 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.

[1526] 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.

[1527] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1528] 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.

[1529] 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).

[1530] 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.

[1531] 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."

[1532] 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.

[1533] 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).

[1534] 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.

[1535] 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.

[1536] 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.

[1537] 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.

[1538] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, 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 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.

[1539] 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.

[1540] 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.

[1541] 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.

[1542] 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.

[1543] 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.

[1544] The following is further disclosed regarding the above embodiment.

[1545] (Claim 1)

[1546] A means of collecting traffic accident information from the police;

[1547] A means for storing the collected traffic accident information in a database;

[1548] A means of analyzing past traffic accident data and identifying accident risk areas,

[1549] A means for displaying the identified accident risk areas in combination with map data;

[1550] A means of providing real-time accident risk information to car navigation systems,

[1551] a means for displaying the provided accident risk information on a car navigation system and issuing a warning to a user;

[1552] A system including:

[1553] (Claim 2)

[1554] 10. The system of claim 1, further comprising means for warning a user with an audio message when approaching an accident risk area.

[1555] (Claim 3)

[1556] 2. The system according to claim 1, further comprising means for storing location information of the identified accident risk area as latitude and longitude data and displaying the data in different colors on a map.

[1557] "Example 1"

[1558] (Claim 1)

[1559] A means of collecting traffic accident information from the police;

[1560] A means for storing the collected traffic accident information in a database;

[1561] A means of analyzing past traffic accident data and identifying accident risk areas,

[1562] A means for displaying the identified accident risk areas in combination with map data;

[1563] A means of providing real-time accident risk information to car navigation systems,

[1564] a means for displaying the provided accident risk information on a car navigation system and issuing a warning to a user;

[1565] a means for issuing a warning by voice message when the user approaches an accident risk area;

[1566] A system including:

[1567] (Claim 2)

[1568] 2. The system according to claim 1, further comprising means for classifying and displaying accident risk areas into low risk, medium risk, and high risk.

[1569] (Claim 3)

[1570] 2. The system according to claim 1, further comprising means for storing location information of the accident risk area as latitude and longitude data using a GIS tool and displaying the data in different colors on a map.

[1571] "Application Example 1"

[1572] (Claim 1)

[1573] A means of collecting traffic accident information from the police;

[1574] A means for storing the collected traffic accident information in a database;

[1575] A means of analyzing past traffic accident data and identifying accident risk areas,

[1576] A means for displaying the identified accident risk areas in combination with map data;

[1577] a means of providing real-time accident risk information to autonomous vehicles; and

[1578] a means for displaying the provided accident risk information on the autonomous vehicle and adjusting the operation of the vehicle;

[1579] A system including:

[1580] (Claim 2)

[1581] 10. The system of claim 1, further comprising means for warning a user with an audio message when approaching an accident risk area.

[1582] (Claim 3)

[1583] 2. The system according to claim 1, further comprising means for storing location information of the identified accident risk area as latitude and longitude data and displaying the data in different colors on a map.

[1584] "Example 2: Combining Emotion Engines"

[1585] (Claim 1)

[1586] A means of collecting traffic accident information;

[1587] means for storing the collected traffic accident information in a data management device;

[1588] A means for analyzing past traffic accident data and identifying areas at risk of accidents;

[1589] a means for displaying the identified accident risk area in combination with map data;

[1590] means for providing accident risk information to a guidance device in real time;

[1591] a means for displaying the provided accident risk information on a guidance device and issuing a warning to a user;

[1592] The system includes a means to recognize the user's emotional state and adjust the alert content.

[1593] (Claim 2)

[1594] 2. The system according to claim 1, wherein the system warns the user by a voice message when approaching an accident risk area.

[1595] (Claim 3)

[1596] 2. The system according to claim 1, wherein the location information of the identified accident risk area is saved as latitude and longitude data and displayed in different colors on a map.

[1597] "Application example 2 when combining emotion engines"

[1598] (Claim 1)

[1599] A means of collecting traffic accident information from the police;

[1600] A means for storing the collected traffic accident information in a database;

[1601] A means of analyzing past traffic accident data and identifying accident risk areas,

[1602] A means for displaying the identified accident risk areas in combination with map data;

[1603] a means of providing real-time accident risk information to autonomous vehicles; and

[1604] a means for displaying the provided accident risk information on the automated driving system and issuing a warning to the user;

[1605] means for recognizing the emotional state of a user;

[1606] means for tailoring the warning message based on the perceived emotional state;

[1607] A system including:

[1608] (Claim 2)

[1609] 10. The system of claim 1, further comprising means for warning the user with a voice message based on the user's emotional state when approaching an accident risk area.

[1610] (Claim 3)

[1611] 2. The system according to claim 1, further comprising means for saving location information of the identified accident risk area as latitude and longitude data and displaying the data in different colors on a map. [Explanation of symbols]

[1612] 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. A means of collecting traffic accident information from the police; A means for storing the collected traffic accident information in a database; A means of analyzing past traffic accident data and identifying accident risk areas, A means for displaying the identified accident risk areas in combination with map data; A means of providing real-time accident risk information to car navigation systems, a means for displaying the provided accident risk information on a car navigation system and issuing a warning to a user; A system including:

2. 10. The system of claim 1, further comprising means for warning the user with an audio message when approaching an accident risk area.

3. 2. The system according to claim 1, further comprising means for storing location information of the identified accident risk areas as latitude and longitude data and displaying the data in different colors on a map.

Images