System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting news, weather data, and social media; means for pre-processing and inputting the collected information into a generative AI model that predicts congestion; means for performing congestion prediction using the generative AI model and calculating an optimal avoidance route; means for transmitting the calculated avoidance route information to a vehicular navigation system; and means for the vehicular navigation system to notify a user of a proposed avoidance route.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Describe the "problem that the invention aims to solve" and the "means for solving the problem."

[0005] In recent years, automobiles have become an important means of transportation, but the risks of traffic congestion and accidents are increasing. Furthermore, there have been many cases of elderly drivers and dangerous driving due to emotion and human error, which hinder safe travel. Meanwhile, public transportation such as buses and trains lack convenience because they have fixed times and destinations. There is a need for a means to solve these issues and enable people to travel safely and comfortably. [Means for solving the problem]

[0006] The present invention solves the above problems by the following means. It provides a means for collecting news data, weather data, and social media data, preprocessing the collected data, and inputting it into a generative AI model to predict congestion. It also provides a means for calculating optimal avoidance routes based on the congestion prediction, transmitting the route information to a vehicle navigation system, and notifying the user of the suggested avoidance routes. It also provides a means for extracting past accident data, inputting it into a generative AI model, calculating a safe route, and transmitting the information to a vehicle navigation system to notify the user. It also provides a means for collecting a user's age, hobbies, and past driving history, inputting it into a generative AI model, and generating a driving course based on the user's hobbies and preferences. It also provides a means for providing a driving guide in real time that allows the user to enjoy the scenery.

[0007] "News Data" refers to data about traffic conditions and general information collected from news sources.

[0008] "Weather data" refers to data on meteorological information such as weather, temperature, and precipitation obtained from meteorological agencies.

[0009] "Social media data" is data obtained from information such as posts and comments on social networking services (SNS).

[0010] A "generative AI model" is an artificial intelligence model that primarily uses generative machine learning algorithms to analyze data and make predictions.

[0011] "Preprocessing" refers to a series of operations, including filtering, cleaning, and formatting, that transform collected data into an analyzable form.

[0012] "Traffic congestion forecasting" is the act of predicting future traffic congestion based on traffic volume and other related information.

[0013] An "avoidance route" is an optimized alternative route that avoids obstacles such as traffic jams or accidents.

[0014] A "vehicle navigation system" is an electronic system that is installed in a vehicle and provides route guidance to a destination.

[0015] "Accident data" refers to data relating to the occurrence and detailed information of past traffic accidents in a specific area.

[0016] "User data" is a collection of personal information related to a user, such as the user's age, hobbies, and past behavioral history.

[0017] A "drive" is a proposed route or path for a vehicle to travel.

[0018] "Tourist spot information" is data such as explanations and location information about tourist spots and scenic spots. [Brief explanation of the drawings]

[0019] [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

[0020] 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.

[0021] First, the terms used in the following description will be explained.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 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.

[0030] 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).

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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."

[0040] This invention relates to an autonomous driving system that improves traffic conditions and road safety and makes users' driving experiences more comfortable. The system collects news data, weather data, and social media data and uses a generative AI model to predict traffic congestion. The system also utilizes the collected data and the generative AI model to provide safe routes and real-time driving guidance tailored to the user's preferences.

[0041] Traffic congestion prediction and avoidance function

[0042] 1. Data Collection and Preprocessing:

[0043] The server collects traffic conditions, weather information, and social media posts from news APIs, weather APIs, and social media APIs.

[0044] The server preprocesses the collected data and performs text analysis and data cleansing.

[0045] 2. Traffic congestion prediction:

[0046] The server inputs the preprocessed data into a generative AI model to perform traffic congestion predictions.

[0047] Generative AI predicts the probability of traffic jams occurring on highways and major intersections.

[0048] 3. Calculating the Evasive Path:

[0049] The server calculates the optimal avoidance route based on the prediction results of the generated AI model.

[0050] The server sends the calculated avoidance route information to the terminal (vehicle navigation system).

[0051] 4. User Notice:

[0052] The device will display the new route on the navigation screen and notify the user.

[0053] The user reviews the proposed route and approves it if necessary.

[0054] Providing a safe route

[0055] 1. Accident data collection and analysis:

[0056] The server extracts accident data for a specific area from a database of past accidents.

[0057] The server uses the generated AI model to analyze the extracted accident data and identify dangerous areas.

[0058] 2. Calculating the safe path:

[0059] The server calculates a safe route that avoids accident-prone areas based on the generated AI model.

[0060] The server sends the calculated safe route information to the terminal.

[0061] 3. User Notice:

[0062] The device notifies the user of safe routes and displays them on the navigation screen.

[0063] The user reviews the suggested safe routes and selects one.

[0064] Real-time guide that takes into account individual interests

[0065] 1. Collection of User Data:

[0066] The device collects data such as the user's age, hobbies, and past driving history.

[0067] The terminal transmits this data to the server.

[0068] 2. Generate personalized driving itineraries:

[0069] The server inputs the collected user data into a generative AI model to generate a driving course based on the user's hobbies and preferences.

[0070] Generative AI suggests routes that stop off at natural landscapes and specific tourist spots.

[0071] 3. Providing tourist information:

[0072] The server acquires information on tourist spots along the proposed driving course in real time.

[0073] The server transmits tourist spot information to the terminal.

[0074] 4. User Notice:

[0075] The device will notify the user of guide information such as "The autumn leaves are beautiful on this road" and "Once you turn the next corner, you'll see a spectacular view."

[0076] Users can enjoy real-time guidance while driving.

[0077] Specific examples

[0078] For example, while a user is driving on a major road, the server receives information from a news API that "an accident has occurred on major road A." The generation AI analyzes this information, predicts that congestion will occur on major road A, calculates an alternative route, and sends it to the device. The device notifies the user of the new route, and the user accepts the proposal and heads to their destination via the new route.

[0079] Additionally, while the user is enjoying a drive, the device sends information about the user's hobbies to the server, and the AI ​​generator suggests driving routes with beautiful natural scenery based on the user's "love of nature" information. The server obtains tourist spot information in real time, and the device guides the user by saying, "Once you pass the next curve, you'll see a beautiful lake." In this way, the user can enjoy a comfortable and safe drive.

[0080] The processing flow will be explained below.

[0081] Traffic congestion prediction and avoidance function

[0082] Data collection and preprocessing

[0083] Step 1:

[0084] The server collects data about traffic conditions from the news API.

[0085] Step 2:

[0086] The server collects current weather information from a weather API.

[0087] Step 3:

[0088] The server retrieves real-time posting data from the social media API.

[0089] Step 4:

[0090] The server preprocesses the collected data, performing text analysis and data cleansing.

[0091] Traffic congestion forecast

[0092] Step 5:

[0093] The server inputs the preprocessed data into a generative AI model to perform congestion prediction.

[0094] Step 6:

[0095] The generative AI predicts the probability of traffic jams occurring on highways and major intersections.

[0096] Evasion route calculation

[0097] Step 7:

[0098] The server calculates the optimal avoidance route based on the prediction results of the generative AI model.

[0099] Step 8:

[0100] The server transmits the calculated avoidance route information to the terminal (vehicle navigation system).

[0101] User Notifications

[0102] Step 9:

[0103] The device will display the new route on the navigation screen and notify the user.

[0104] Step 10:

[0105] The user reviews the proposed route and approves it if necessary.

[0106] Providing a safe route

[0107] Accident data collection and analysis

[0108] Step 1:

[0109] The server extracts accident data for a specific area from a database of past accidents.

[0110] Step 2:

[0111] The server uses a generative AI model to analyze the extracted accident data and identify risky areas.

[0112] Safe Route Calculation

[0113] Step 3:

[0114] The server calculates a safe route that avoids accident-prone areas based on the generative AI model.

[0115] Step 4:

[0116] The server sends the calculated secure route information to the terminal.

[0117] User Notifications

[0118] Step 5:

[0119] The device notifies the user of safe routes and displays them on the navigation screen.

[0120] Step 6:

[0121] The user reviews the suggested safe routes and selects one.

[0122] Real-time guide that takes into account individual interests

[0123] User Data Collection

[0124] Step 1:

[0125] The device collects data such as the user's age, hobbies, and past driving history.

[0126] Step 2:

[0127] The terminal transmits this data to the server.

[0128] Generate individual driving routes

[0129] Step 3:

[0130] The server inputs the collected user data into a generative AI model to generate a driving course based on the user's hobbies and preferences.

[0131] Step 4:

[0132] The generative AI suggests routes that stop off at natural landscapes and specific tourist spots.

[0133] Providing tourist spot information

[0134] Step 5:

[0135] The server obtains information on tourist spots along the proposed driving course in real time.

[0136] Step 6:

[0137] The server transmits tourist spot information to the terminal.

[0138] User Notifications

[0139] Step 7:

[0140] The device will notify the user of guide information such as "The autumn leaves are beautiful on this road" and "Once you turn the next corner, you'll see a spectacular view."

[0141] Step 8:

[0142] Users can enjoy real-time guidance as they drive.

[0143] Example 1

[0144] 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."

[0145] For autonomous vehicles to operate safely and comfortably, it is necessary to acquire and analyze real-time traffic conditions, weather information, and accident data. However, there is no effective system for efficiently collecting this information and accurately predicting congestion and calculating safe routes. There is also a lack of technology to provide driving guidance tailored to the hobbies and preferences of individual users. There is a need to solve these issues.

[0146] 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.

[0147] In this invention, the server includes a means for collecting news data, weather data, and social networking service data, a means for preprocessing the collected data and performing text analysis and data cleansing, and a means for inputting the preprocessed data into a generative AI model to predict traffic congestion. This enables accurate analysis of traffic conditions, calculation of optimal avoidance routes, and transmission of the route to the vehicle navigation system. It also includes a function for analyzing past accident data to provide safe routes and suggest driving courses based on the user's age, preferences, and past travel history. This improves the safety and comfort of autonomous vehicles.

[0148] "News data" is data collected from the Internet and other sources, including information about traffic conditions and related events.

[0149] "Weather data" refers to data that includes information about weather conditions such as temperature, precipitation, and wind speed.

[0150] "Social networking service data" refers to data that includes information such as user posts and comments collected from social networking services.

[0151] "Preprocessing" is the process of processing collected data using techniques such as text analysis and data cleansing to extract necessary information.

[0152] A "generative AI model" is a model that uses machine learning and artificial intelligence techniques to analyze collected and preprocessed data as input and make predictions and judgments.

[0153] "Traffic congestion forecasting" refers to the use of generative AI models to predict the likelihood of traffic congestion in specific areas and at specific times.

[0154] An "avoidance route" is an alternative route proposed to avoid a predicted congestion or accident.

[0155] A "navigation system" is a system installed in a vehicle that uses GPS and other technologies to provide optimal routes and guide users to their destinations.

[0156] "Accident data" is data extracted from a database containing information about past traffic accidents.

[0157] "User data" refers to data that includes information about the user's age, preferences, and past travel history.

[0158] "Tourist destination information" is data that includes real-time information about tourist attractions and scenic spots.

[0159] A "safe route" is a route calculated to avoid areas prone to accidents and reach the destination as safely as possible.

[0160] A "driving course" is a driving route suggested based on the user's preferences and tastes.

[0161] This invention relates to an autonomous driving system that improves traffic conditions and road safety and makes users' driving experiences more comfortable. This system collects news data, weather data, and social networking service data and predicts traffic congestion using a generative AI model. It also utilizes the collected data and the generative AI model to provide safe routes and real-time driving guidance tailored to the user's preferences.

[0162] Traffic congestion prediction and avoidance function

[0163] Data collection and preprocessing

[0164] The server collects data on traffic conditions, weather information, and social media posts from news APIs (e.g., Google News API), weather APIs (e.g., OpenWeatherMap API), and social media APIs (e.g., Twitter API). The server sends requests to these APIs to retrieve the latest news articles, weather information, and social media posts every hour. The collected data is preprocessed using text analysis and data cleansing techniques. For news data, text mining techniques are used to extract information about traffic accidents and cleanse unnecessary information. For weather data, variables such as temperature, precipitation, and wind speed are analyzed to identify traffic-related factors.

[0165] Traffic congestion forecast

[0166] The server inputs the preprocessed data into a generative AI model (e.g., LSTM model) to predict traffic congestion. The generative AI predicts traffic conditions and calculates the probability of congestion occurring at a specific location and time. For example, it predicts that there is a 70% chance of congestion occurring on major road A at 8 a.m.

[0167] Evasion route calculation

[0168] The server calculates the optimal avoidance route based on the prediction results of the generative AI model. It uses the Google Maps API to obtain alternative route information and searches for and verifies routes with a low probability of congestion and accidents. The calculated avoidance route information is sent to the vehicle's navigation system.

[0169] User Notifications

[0170] The device will display the new route on the navigation screen and notify the user. For example, it will display a message such as, "Congestion is predicted on main road A, so we suggest a route via main road B." The user can then review the proposed route and approve it if necessary.

[0171] Providing a safe route

[0172] Accident data collection and analysis

[0173] The server extracts accident data for a specific area from a database of past accidents (e.g., a public traffic accident statistics database). The extracted accident data is input into a generative AI model to identify areas where accidents frequently occur. The server uses the generative AI model to calculate a safe route that avoids areas where accidents frequently occur. The calculated safe route information is sent to the vehicle's navigation system. The device notifies the user of the safe route and displays it on the navigation screen.

[0174] Real-time guide that takes into account individual interests

[0175] User Data Collection

[0176] The device collects data such as the user's age, hobbies, past driving history, etc. For example, if the user has set information such as "I like nature," the device sends that information to the server.

[0177] Generate individual driving routes

[0178] The server inputs the collected user data into a generative AI model to generate a driving course based on the user's hobbies and preferences. The generative AI then suggests routes that stop off at natural landscapes and specific tourist spots.

[0179] Providing tourist spot information

[0180] The server retrieves tourist spot information along the proposed driving course in real time. The tourist spot information is obtained from the tourist information API and sent to the device. The device then displays a notification to the user saying, "You will see a beautiful lake after passing the next curve."

[0181] Here are some example prompts to input to the generative AI model:

[0182] "Please explain a program that uses news APIs, weather APIs, and social media APIs to collect traffic information and use this data to predict congestion."

[0183] In this way, the user can enjoy a comfortable and safe drive.

[0184] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0185] Step 1: Data collection

[0186] Input: Requests to the news API, weather API, or social media API

[0187] Processing: The server accesses these APIs to collect data on traffic conditions, weather information, and social media posts.

[0188] Output: Collected news data, weather data, and social media data

[0189] Specifically, the server sends a request to the API every hour to retrieve new news articles, the latest weather information, and the latest social media posts.

[0190] Step 2: Data Preprocessing

[0191] Input: Collected news data, weather data, and social media data

[0192] Processing: The server preprocesses the data using text analysis and data cleansing techniques. For example, it extracts information about traffic accidents from news data and removes unnecessary information. For weather data, it normalizes variables such as temperature, precipitation, and wind speed.

[0193] Output: Preprocessed and clean data

[0194] Specifically, the server uses a text mining algorithm to extract keywords related to traffic accidents from news articles, and only retains the necessary weather data.

[0195] Step 3: Traffic congestion prediction

[0196] Input: Preprocessed clean data

[0197] Processing: The server inputs the preprocessed data into a generative AI model (e.g., an LSTM model) to predict traffic congestion.

[0198] Output: Predicted probability of traffic jams

[0199] Specifically, the server converts the preprocessed data into tensor format and sends it to the generative AI model, which then obtains a prediction result such as "There is a 70% probability that traffic congestion will occur on major road A at 8 a.m."

[0200] Step 4: Calculate the optimal escape path

[0201] Input: Predicted result of traffic congestion probability

[0202] Processing: The server calculates the optimal avoidance route based on the prediction results of the generated AI model using Google Maps API etc.

[0203] Output: Calculated avoidance path information

[0204] Specifically, the server uses the Google Maps API to search for alternative routes to avoid areas where congestion is predicted, and finds the optimal avoidance route.

[0205] Step 5: Sending avoidance route information

[0206] Input: Calculated avoidance path information

[0207] Processing: The server sends the calculated avoidance route information to the vehicle's navigation system.

[0208] Output: Avoidance route information displayed on the vehicle navigation system

[0209] Specifically, the server sends an API request to the navigation system to transmit the new route information.

[0210] Step 6: User Notification

[0211] Input: Avoidance route information displayed on the vehicle navigation system

[0212] Processing: The terminal (vehicle navigation system) notifies the user of the new route.

[0213] Output: Avoidance route information displayed and notified to the user

[0214] Specifically, the navigation system will display a message on its screen saying, "Congestion is predicted on main road A, so we suggest a route via main road B," to notify the user.

[0215] Step 7: Collect and analyze accident data

[0216] Input: Past accident database

[0217] Processing: The server extracts accident data for specific areas from a database of past accidents and inputs it into a generative AI model to identify risky areas.

[0218] Output: Information on identified dangerous areas

[0219] Specifically, the server executes a query to retrieve accident information from the accident database for the past 10 years, and then analyzes it using an AI model to identify dangerous intersections and roads.

[0220] Step 8: Calculating a safe path

[0221] Input: Information on identified risk areas

[0222] Processing: The server uses the generative AI model to calculate a safe route that avoids accident-prone areas.

[0223] Output: Calculated safe route information

[0224] Specifically, the server inputs parameters to avoid dangerous areas into the generative AI model and generates a safe route.

[0225] Step 9: Send secure routing information

[0226] Input: Calculated safe route information

[0227] Processing: The server sends the calculated safe route information to the vehicle's navigation system.

[0228] Output: Safe route information displayed on the vehicle navigation system

[0229] Specifically, the server sends an API request to the navigation system again and transmits safe route information.

[0230] Step 10: Generate individual driving routes

[0231] Input: User's age, hobbies, past driving history

[0232] Processing: The device collects this data and sends it to a server. The server inputs the collected user data into a generative AI model to generate a driving course based on the user's hobbies and preferences.

[0233] Output: Generated driving course information

[0234] Specifically, the device collects user information such as "I like nature" and sends it to the server, which then uses a generative AI model to generate a driving course, for example, a "mountain route."

[0235] Step 11: Providing tourist spot information

[0236] Input: Generated driving course information

[0237] Processing: The server obtains tourist spot information along the proposed driving course in real time. It uses the tourist information API to obtain the spot information and sends it to the device.

[0238] Output: Tourist attraction information displayed on the vehicle navigation system

[0239] Specifically, the server obtains information such as "Once you go around the next curve, you will see a beautiful lake" and sends it to the terminal.

[0240] Step 12: User Notification

[0241] Input: Tourist attraction information displayed on vehicle navigation system

[0242] Processing: The terminal notifies the user of tourist spot information.

[0243] Output: Tourist spot information displayed and notified to the user

[0244] Specifically, the device displays a notification to the user saying, "Once you turn the next curve, you'll see a beautiful lake," allowing the user to enjoy the scenery.

[0245] (Application example 1)

[0246] 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."

[0247] Autonomous vehicles are expected to improve traffic congestion and road safety, and to provide a more comfortable driving experience for users. However, conventional technologies have had difficulty in effectively predicting congestion in real time, providing avoidance routes, and providing travel guidance based on users' hobbies and interests. Therefore, the present invention aims to solve these problems and make navigation systems for autonomous vehicles more advanced and useful for users.

[0248] 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.

[0249] In this invention, the server includes means for collecting news data, weather data, and social media data, means for preprocessing the collected data and inputting it into a generative AI model that predicts congestion, means for predicting congestion using the generative AI model and calculating an optimal avoidance route, means for transmitting the calculated avoidance route information to a mobile navigation system, means for the mobile navigation system to notify the user of the proposed avoidance route, means for collecting tourist spot information based on the user's hobbies and interests, means for inputting the collected tourist spot information into the generative AI model and generating travel guidance based on the user's interests, and means for transmitting the generated travel guidance to the mobile navigation system and notifying the user. This makes it possible to provide effective congestion predictions and avoidance routes in real time, and further makes it possible to provide travel guidance based on the user's hobbies and interests in real time.

[0250] "News data" refers to data containing the latest events and information distributed via the Internet or other information media.

[0251] "Weather data" refers to data that includes meteorological information such as temperature, humidity, precipitation, and wind speed.

[0252] "Social media data" refers to data that includes information such as text, images, and videos posted on SNS (social networking services).

[0253] A "generative AI model" is an algorithm that uses machine learning and deep learning to learn patterns from large amounts of data and makes predictions and generates data based on new data.

[0254] A "mobile navigation system" is a system installed in a vehicle or other mobile object that provides map information, route guidance, and traffic information.

[0255] "User" means an individual or group of people who use an automated driving vehicle.

[0256] "Hobbies" are activities or interests that a user is interested in and engages in for enjoyment.

[0257] "Tourist spot information" is data including the location, characteristics, and usage information of tourist spots and famous places.

[0258] "Travel guidance" is a service that provides information on routes to destinations and tourist spots, as well as guidance and advice to help users travel comfortably and enjoyably.

[0259] "Real-time" refers to a state in which current information can be processed immediately and provided without delay.

[0260] The present invention relates to a navigation system for autonomous vehicles. The system aims to improve traffic congestion and road safety and to provide a comfortable driving experience for users. Specific embodiments for carrying out the present invention will be described below.

[0261] System Configuration

[0262] The system according to the present invention includes the following main components:

[0263] server

[0264] Mobile navigation systems (vehicle navigation systems, smartphones, etc.)

[0265] Internet connection

[0266] News data, weather data, social media data APIs

[0267] Data collection

[0268] The server collects data in real time from news APIs, weather APIs, and social media APIs. The data is automatically retrieved via the internet, allowing you to get the latest traffic and weather information, as well as the information you need from social media posts.

[0269] Data Preprocessing

[0270] The server preprocesses the collected data, which includes removing unnecessary data and normalizing and cleaning the text, preparing the data for input into the generative AI model.

[0271] Traffic congestion prediction and calculation of avoidance routes

[0272] The server inputs the preprocessed data into a generative AI model to predict congestion. This generative AI model uses a machine learning algorithm and learns from past data. Based on the results of the congestion prediction, it calculates the optimal avoidance route.

[0273] Sending and notifying route information

[0274] The server sends the calculated avoidance route information to the mobile navigation system, which then notifies the user of the new route information. Notification methods include voice guidance and visual navigation displays.

[0275] Travel guides based on hobbies and interests

[0276] The server collects tourist spot information based on the user's hobbies and interests. The collected information is input into a generative AI model to generate travel guides based on the user's interests. The generated travel guides are sent to the mobile navigation system and notified to the user.

[0277] Hardware and software used

[0278] Hardware: Servers, smartphones, vehicle navigation systems

[0279] Software: Python, generative AI model, external API (news API, weather API, SNS API)

[0280] Specific examples

[0281] For example, while a user is on a long-distance drive, the server receives information from a news API that "an accident occurred on major road A." This information is analyzed by a generative AI model, which predicts that a traffic jam will occur on major road A. The server calculates an alternative route and sends it to the mobile navigation system. The mobile navigation system notifies the user of the new route, and the user accepts the suggestion and heads to their destination via the new route.

[0282] Additionally, while the user is enjoying their drive, the server collects information about the user's hobbies, and the generative AI model suggests driving routes with beautiful natural scenery based on the user's "love of nature" information. The server obtains tourist spot information in real time, and the mobile navigation system guides the user, saying, "Once you turn the next corner, you'll see a beautiful lake." In this way, users can enjoy a comfortable and safe drive.

[0283] Prompt Sentence Examples

[0284] Get the latest information on "traffic accidents" from the news API

[0285] Preprocess social media data to extract posts related to traffic congestion

[0286] Calculate the best route to avoid traffic congestion based on the results of generative AI models.

[0287] Notify your driver of new suggested routes

[0288] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0289] Step 1:

[0290] The server collects data in real time from news APIs, weather APIs, and SNS APIs. Specifically, it sends requests to each API to collect news data, weather data, and social media data, and receives the acquired data. The input is the response data from each API, and the output is the collected news, weather, and SNS post data.

[0291] Step 2:

[0292] The server preprocesses the collected data. Data preprocessing includes removing unnecessary data, normalizing text, and cleaning. For example, summarizing news articles or extracting important parts of weather information. The input is the collected news, weather, and social media data, and the output is the preprocessed data.

[0293] Step 3:

[0294] The server inputs the preprocessed data into a generative AI model to perform congestion prediction. The generative AI model uses patterns learned from past data to predict future traffic congestion. The input is the preprocessed data, and the output is the congestion prediction result.

[0295] Step 4:

[0296] The server calculates the optimal avoidance route based on the congestion prediction results of the generated AI model. The avoidance route calculation also includes map database and road condition data. Specifically, a routing algorithm is used to calculate a route that avoids the predicted congestion. The inputs are the congestion prediction results, map data, and road condition data, and the output is information on the optimal avoidance route.

[0297] Step 5:

[0298] The server sends the calculated avoidance route information to the mobile navigation system. The sent avoidance route information is reflected in the navigation system display in real time. The input is the optimal avoidance route information, and the output is the route guidance information in the navigation system.

[0299] Step 6:

[0300] The terminal (mobile navigation system) notifies the user of the proposed avoidance route. This notification is done both audibly and visually. Specifically, the new route is displayed on the navigation screen and guided by voice. The input is the avoidance route information sent from the server, and the output is the notification and guidance to the user.

[0301] Step 7:

[0302] The server collects tourist spot information based on the user's hobbies and interests. For example, it obtains tourist spot information from the Internet and uses data that reflects the user's past driving history and interests. The input is the user's hobby data and tourist spot information, and the output is input data for the generative AI model.

[0303] Step 8:

[0304] The server inputs the collected information into a generative AI model to generate travel guides based on the user's interests. The generative AI model suggests optimal sightseeing routes and spots based on the user's hobbies and past history. The input is the collected user hobby data and tourist spot information, and the output is travel guide information.

[0305] Step 9:

[0306] The server sends the generated travel guide to the mobile navigation system and notifies the user. In this way, tourist information is provided in real time while traveling. Specifically, the navigation system displays information about tourist spots and provides audio guidance. The input is the generated travel guide, and the output is notifications and guidance for the user.

[0307] 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.

[0308] This invention relates to an autonomous driving system that improves traffic conditions and road safety and makes the user's driving experience more comfortable and emotionally satisfying. The system not only collects news data, weather data, and social media data and predicts traffic congestion using a generative AI model, but also includes an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's voice and facial expression data and provides personalized feedback and suggestions based on their emotional state.

[0309] Traffic congestion prediction and avoidance function

[0310] Data collection and preprocessing

[0311] 1. The server collects traffic and weather information, as well as real-time social media posting data, from news APIs, weather APIs, and social media APIs.

[0312] 2. The server preprocesses the collected data and performs text analysis and data cleansing.

[0313] Traffic congestion forecast

[0314] 3. The server inputs the preprocessed data into the generative AI model to perform congestion prediction.

[0315] 4. Generative AI predicts the probability of traffic jams occurring on highways and major intersections.

[0316] Evasion route calculation

[0317] 5. The server calculates the optimal avoidance path based on the prediction results of the generative AI model.

[0318] 6. The server sends the calculated avoidance route information to the vehicle navigation system (terminal).

[0319] User Notifications

[0320] 7. The device displays the new route on the navigation screen and notifies the user.

[0321] 8. The user reviews the proposed route and approves it if necessary.

[0322] Providing a safe route

[0323] Accident data collection and analysis

[0324] 1. The server extracts accident data for a specific area from a database of past accidents.

[0325] 2. The server uses a generative AI model to analyze the extracted accident data and identify risk areas.

[0326] Safe Route Calculation

[0327] 3. The server calculates a safe route that avoids accident-prone areas based on the generative AI model.

[0328] 4. The server sends the calculated safe route information to the vehicle navigation system (terminal).

[0329] User Notifications

[0330] 5. The device notifies the user of the safe route and displays it on the navigation screen.

[0331] 6. The user reviews the suggested safe routes and selects one.

[0332] Real-time guide that takes into account individual interests

[0333] User Data Collection

[0334] 1. The device collects data such as the user's age, hobbies, and past driving history.

[0335] 2. The device sends this data to the server.

[0336] Generate individual driving routes

[0337] 3. The server inputs the collected user data into a generative AI model and generates a driving course based on the user's hobbies and preferences.

[0338] 4. The generative AI suggests routes that stop off at natural landscapes and specific tourist spots.

[0339] Providing tourist spot information

[0340] 5. The server obtains real-time information about tourist spots along the proposed driving course.

[0341] 6. The server sends the tourist spot information to the vehicle navigation system (terminal).

[0342] User Notifications

[0343] 7. The device notifies the user of guide information such as, "The autumn leaves are beautiful on this road," or "A spectacular view will unfold once you turn the next corner."

[0344] 8. Users can enjoy real-time guidance while driving.

[0345] Incorporating an emotion engine

[0346] Collecting Emotional Data

[0347] 1. The device collects the user's voice and facial expression data in real time.

[0348] Emotion analysis

[0349] 2. The device uses an emotion engine that analyzes collected voice and facial expression data to recognize the user's emotions.

[0350] 3. The emotion engine identifies the user's current emotional state.

[0351] Route suggestions and content adjustments

[0352] 4. The server adjusts the generated avoidance routes and tourist information based on the emotional state recognized by the emotion engine.

[0353] 5. The server sends the adjusted route information and tourist information to the vehicle navigation system (terminal).

[0354] Specific examples

[0355] For example, while a user is driving on a major road, the server receives information from a news API that "an accident occurred on major road A." The generation AI analyzes this information, predicts that a traffic jam will occur on major road A, calculates an alternative route, and sends it to the device. The device then collects the user's voice data, and the emotion engine recognizes that the user is frustrated. Based on this information, the server suggests a scenic route that will allow the user to relax and notifies the user. The user then accepts the suggestion and heads to their destination via the new route. In this way, the user can enjoy a comfortable and safe drive.

[0356] The processing flow will be explained below.

[0357] Traffic congestion prediction and avoidance function

[0358] Data collection and preprocessing

[0359] Step 1:

[0360] The server collects the latest traffic data from the news API.

[0361] Step 2:

[0362] The server retrieves current and forecast weather information from a weather API.

[0363] Step 3:

[0364] The server collects real-time posting data from social media APIs.

[0365] Step 4:

[0366] The server preprocesses the collected news, weather, and social media data, removing unnecessary information and converting it into a unified format.

[0367] Traffic congestion forecast

[0368] Step 5:

[0369] The server inputs the preprocessed data into the generative AI model.

[0370] Step 6:

[0371] The generative AI analyzes the input data and predicts the probability of traffic jams occurring on highways and major intersections.

[0372] Evasion route calculation

[0373] Step 7:

[0374] The server calculates the optimal avoidance route based on the prediction results of the generative AI model.

[0375] Step 8:

[0376] The server transmits the calculated avoidance route information to the vehicle navigation system (terminal).

[0377] User Notifications

[0378] Step 9:

[0379] The device will display the new route on the navigation screen and notify the user.

[0380] Step 10:

[0381] The user reviews the proposed route and approves it if necessary.

[0382] Providing a safe route

[0383] Accident data collection and analysis

[0384] Step 1:

[0385] The server extracts accident data for a specific area from a database of past accidents.

[0386] Step 2:

[0387] The server uses a generative AI model to analyze the extracted accident data and identify risky areas.

[0388] Safe Route Calculation

[0389] Step 3:

[0390] The server calculates a safe route that avoids accident-prone areas based on the generative AI model.

[0391] Step 4:

[0392] The server sends the calculated safe route information to the vehicle navigation system (terminal).

[0393] User Notifications

[0394] Step 5:

[0395] The device notifies the user of safe routes and displays them on the navigation screen.

[0396] Step 6:

[0397] The user reviews the suggested safe routes and selects one.

[0398] Real-time guide that takes into account individual interests

[0399] User Data Collection

[0400] Step 1:

[0401] The device collects data such as the user's age, hobbies, and past driving history.

[0402] Step 2:

[0403] The terminal transmits this data to the server.

[0404] Generate individual driving routes

[0405] Step 3:

[0406] The server inputs the collected user data into a generative AI model to generate a driving course based on the user's hobbies and preferences.

[0407] Step 4:

[0408] The generative AI suggests routes that stop off at natural landscapes and specific tourist spots.

[0409] Providing tourist spot information

[0410] Step 5:

[0411] The server obtains information on tourist spots along the proposed driving course in real time.

[0412] Step 6:

[0413] The server transmits tourist spot information to the vehicle navigation system (terminal).

[0414] User Notifications

[0415] Step 7:

[0416] The device will notify the user of guide information such as "The autumn leaves are beautiful on this road" and "Once you turn the next corner, you'll see a spectacular view."

[0417] Step 8:

[0418] Users can enjoy real-time guidance as they drive.

[0419] Incorporating an emotion engine

[0420] Collecting Emotional Data

[0421] Step 1:

[0422] The device collects the user's voice and facial expression data in real time.

[0423] Emotion analysis

[0424] Step 2:

[0425] The device uses an emotion engine that analyzes collected voice and facial expression data to recognize the user's emotions.

[0426] Step 3:

[0427] The emotion engine identifies the user's current emotional state.

[0428] Route suggestions and content adjustments

[0429] Step 4:

[0430] The server adjusts the generated avoidance routes and tourist information based on the emotional state recognized by the emotion engine.

[0431] Step 5:

[0432] The server sends the adjusted route information and tourist information to the vehicle navigation system (terminal).

[0433] Specific examples

[0434] For example, while a user is driving on a major road, the server receives information from a news API that "an accident occurred on major road A." The generation AI analyzes this information, predicts that a traffic jam will occur on major road A, calculates an alternative route, and sends it to the device. The device then collects the user's voice data, and the emotion engine recognizes that the user is frustrated. Based on this information, the server suggests a scenic route that will allow the user to relax and notifies the user. The user then accepts the suggestion and heads to their destination via the new route. In this way, the user can enjoy a comfortable and safe drive.

[0435] Example 2

[0436] 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."

[0437] Conventional navigation systems are limited to simple route guidance and are unable to flexibly respond to the user's emotions and circumstances. This makes it difficult to present optimal routes that take traffic congestion and accident information into account. It is also difficult to provide a driving experience based on the user's individual preferences. Furthermore, because they are unable to propose routes based on the user's emotional state, they are unable to reduce stress or provide comfort during driving.

[0438] 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 news data, weather data, and social media data, means for preprocessing the collected data and inputting it into a generative AI model that predicts congestion, means for predicting congestion using the generative AI model and calculating an optimal avoidance route, means for transmitting the calculated avoidance route information to a vehicle navigation system, means for the vehicle navigation system to notify the user of the proposed avoidance route, and means for collecting voice and facial expression data of the user to recognize emotions and adjust the route proposal based on the emotions. This makes it possible for the user to avoid congestion, be provided with a safe route, and receive optimal route guidance according to their emotions.

[0439] "News Data" refers to data including traffic conditions, accident information, and other related information obtained through the News API.

[0440] "Weather Data" means data regarding current and forecasted weather conditions obtained through the Weather API.

[0441] "Social media data" refers to data including user posts and real-time comments obtained through SNS APIs.

[0442] "Preprocessing" is the process of converting collected data into a format that is easier to analyze and removing unnecessary information.

[0443] A "generative AI model" is an artificial intelligence model that predicts congestion and traffic conditions based on collected data.

[0444] An "emotion engine" is software or algorithm that analyzes a user's voice and facial expression data to recognize their current emotional state.

[0445] A "vehicle navigation system" is an in-vehicle device equipped with a computer that provides route guidance and displays various information.

[0446] An "avoidance route" is an alternative travel route calculated to avoid congestion or accidents.

[0447] A "safe route" is a travel route that is deemed to have low risk based on past accident data.

[0448] "Tourist attraction information" is information about sights and tourist attractions that can be visited during navigation.

[0449] This invention relates to an autonomous driving system that improves traffic conditions and road safety, and provides a more comfortable and emotionally satisfying driving experience for users. The system collects news, weather, and social media data and predicts traffic congestion using a generative AI model. It also incorporates an emotion engine that recognizes the user's emotions, analyzes their voice and facial expression data, and provides route suggestions and feedback based on their emotional state.

[0450] Traffic congestion prediction and avoidance function

[0451] The server collects traffic and weather information, as well as real-time posting data, from news APIs, weather APIs, and social media APIs. The collected data is preprocessed, and text analysis and data cleansing are performed. The preprocessed data is then input into a generative AI model to perform congestion prediction. The generative AI model predicts the probability of congestion on highways and major intersections. Based on the prediction results, the server calculates the optimal avoidance route and sends this information to the vehicle navigation system. The device displays the new route information on the navigation screen and notifies the user. The user then approves the proposed route and heads to their destination via the new route.

[0452] Providing a safe route

[0453] The server extracts accident data for specific areas from a database of past accidents, inputs it into a generative AI model for analysis, and identifies risk areas. Based on the generative AI model, the server calculates a safe route that avoids accident-prone areas and sends this information to the vehicle navigation system. The device notifies the user of the safe route, and the user selects a new, safer route.

[0454] Real-time guide that takes into account individual interests

[0455] The device collects data such as the user's age, hobbies, and past driving history, and sends this to a server. The server inputs the collected data into a generative AI model to generate a driving course based on the user's hobbies and preferences. Information on tourist spots along the generated driving course is obtained in real time and sent to the vehicle navigation system. The device notifies the user of guide information such as "The autumn leaves are beautiful on this road" or "A spectacular view will unfold once you turn the next corner," allowing the user to enjoy their drive.

[0456] Incorporating an emotion engine

[0457] The device collects the user's voice and facial expression data in real time and analyzes it using an emotion engine. The emotion engine identifies the user's current emotional state and sends the results to the server. The server then adjusts route suggestions and tourist information based on the user's emotional state and sends the new information to the vehicle navigation system. This allows the user to enjoy an optimal driving experience tailored to their emotions.

[0458] Specific examples

[0459] For example, while a user is driving on a major road, the server receives information from a news API that "an accident occurred on major road A." The generative AI model analyzes this information, predicts that a traffic jam will occur on major road A, calculates an alternative route, and sends it to the device. The device then collects the user's voice data, and the emotion engine recognizes that the user is frustrated. Based on this information, the server suggests a scenic route that will allow the user to relax and notifies the user. The user then accepts the suggestion and heads to their destination via the new route. In this way, the user can enjoy a comfortable and safe drive.

[0460] Prompt Sentence Examples

[0461] "Please explain how to obtain traffic accident information from a server, predict congestion, and provide an alternative route while the user is driving on main road A."

[0462] "Give us a concrete example of how you designed a system that uses an emotion engine to improve the driving experience based on the user's emotional state."

[0463] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0464] Traffic congestion prediction and avoidance function

[0465] Data collection and preprocessing

[0466] Step 1:

[0467] The server collects traffic conditions, weather information, and real-time social media posting data from news APIs, weather APIs, and social media APIs.

[0468] Input: Data request from API

[0469] Output: JSON format data

[0470] Specific operation: The server sends an HTTP GET request to each API and receives JSON formatted data as a response. Example: "https: / / newsapi.org / v2 / top-headlines?category=traffic&apiKey=YOUR_API_KEY".

[0471] Step 2:

[0472] The server preprocesses the collected data and performs text analysis and data cleansing.

[0473] Input: Collected JSON data

[0474] Output: Cleansed data

[0475] Specific operation: The server parses the received data and removes unnecessary information. For example, it extracts only data containing keywords such as "accident" or "traffic jam." This process uses text analysis libraries and regular expressions.

[0476] Traffic congestion forecast

[0477] Step 3:

[0478] The server inputs the preprocessed data into a generative AI model to perform congestion prediction.

[0479] Input: Preprocessed data

[0480] Output: Traffic congestion prediction results

[0481] Specific operation: The server converts the preprocessed data into a format suitable for the AI ​​model and inputs it into the model, for example, using TensorFlow or PyTorch to make predictions.

[0482] Step 4:

[0483] The generative AI model predicts the probability of traffic jams occurring on highways and major intersections.

[0484] Input: Transformed data

[0485] Output: Probability of congestion

[0486] Specific operation: The model processes input data and outputs the probability of congestion at each point. Example: "The probability of congestion on Expressway A is 80%."

[0487] Evasion route calculation

[0488] Step 5:

[0489] The server calculates the optimal avoidance route based on the prediction results of the generative AI model.

[0490] Input: Traffic congestion prediction results

[0491] Output: Optimal avoidance route information

[0492] Specific operation: The server takes the prediction results into consideration and calculates an alternative route that can reach the destination in the shortest time. The route calculation is performed using Dijkstra or A algorithm.

[0493] Step 6:

[0494] The server transmits the calculated avoidance route information to the vehicle navigation system (terminal).

[0495] Input: Optimal avoidance route information

[0496] Output: Sent to terminal

[0497] Specific operation: The server encodes the route information in JSON format and sends it to the device, often using an HTTP POST request.

[0498] User Notifications

[0499] Step 7:

[0500] The terminal displays the new route on the navigation screen and notifies the user.

[0501] Input: Optimal avoidance route information

[0502] Output: Update navigation screen

[0503] Specific operation: The device updates the navigation screen based on the received data and notifies the user, "Main road A is congested. Please use alternative route B."

[0504] Step 8:

[0505] The user reviews the proposed route and approves it if necessary.

[0506] Input: New route information

[0507] Output: Route approval

[0508] Specific operation: The user checks the new route on the screen and presses the approval button on a touch panel or the like.

[0509] Providing a safe route

[0510] Accident data collection and analysis

[0511] Step 1:

[0512] The server extracts accident data for a specific area from a database of past accidents.

[0513] Input:Specify a specific area

[0514] Output: Accident data

[0515] Specific operation: The server retrieves accident data for the target region from the database using an SQL query, e.g., "SELECT FROM accident_data WHERE region='specified region'".

[0516] Step 2:

[0517] The server uses a generative AI model to analyze the extracted accident data and identify risk areas.

[0518] Input: Extracted accident data

[0519] Output: Identification of dangerous areas

[0520] Specific operation: The server inputs the accident data as features into the AI ​​model and identifies risk areas. Example: "Intersection C has a high accident rate."

[0521] Safe Route Calculation

[0522] Step 3:

[0523] The server calculates a safe route that avoids accident-prone areas based on a generative AI model.

[0524] Input: Identification results of dangerous areas

[0525] Output: Safe route information

[0526] Specific operation: The server executes a safe route calculation algorithm based on the risk assessment. Example: "Choose route D to avoid intersection C."

[0527] Step 4:

[0528] The server transmits the calculated safe route information to the vehicle navigation system (terminal).

[0529] Input: Secure route information

[0530] Output: Sent to terminal

[0531] Specific operation: The server encodes the secure route information in JSON format and sends it to the terminal.

[0532] User Notifications

[0533] Step 5:

[0534] The terminal notifies the user of a safe route and displays it on the navigation screen.

[0535] Input: Secure route information

[0536] Output: Update navigation screen

[0537] Specific operation: The device displays the new route information on the screen and notifies the user that "this route avoids areas prone to accidents."

[0538] Step 6:

[0539] The user reviews the suggested safe routes and selects one.

[0540] Input: Secure route information

[0541] Output: Route selection

[0542] Specific operation: The user looks at the navigation screen and selects a new route.

[0543] Real-time guide that takes into account individual interests

[0544] User Data Collection

[0545] Step 1:

[0546] The terminal collects data such as the user's age, hobbies, and past driving history.

[0547] Input: User input information, past navigation records

[0548] Output: Collected user data

[0549] Specific operation: The device collects necessary data from the user's input data and past navigation records. For example, "The user's age is 30, and his hobby is hiking."

[0550] Step 2:

[0551] The terminal transmits this data to the server.

[0552] Input: Collected user data

[0553] Output: Sending to server completed

[0554] Specific operation: The device sends the collected data to the server in JSON format.

[0555] Generate individual driving routes

[0556] Step 3:

[0557] The server inputs the collected user data into a generative AI model and generates a driving course based on the user's hobbies and preferences.

[0558] Input: Collected user data

[0559] Output: Generated driving course information

[0560] Specific operation: Based on the collected data, the server uses an AI model to calculate the optimal driving route for the user. For example, it generates a "route that allows you to enjoy natural scenery" or a "route that visits tourist spots."

[0561] Step 4:

[0562] The generative AI model suggests routes that stop off at natural landscapes and specific tourist spots.

[0563] Input: Transformed user data

[0564] Output: Proposed route

[0565] How it works: The generative AI model suggests routes tailored to the user's hobbies and preferences. For example, "This route passes through popular tourist spots."

[0566] Providing tourist spot information

[0567] Step 5:

[0568] The server obtains information on tourist spots along the proposed driving course in real time.

[0569] Input: Proposed driving route information

[0570] Output: Tourist attraction information

[0571] Specific operation: The server retrieves spot data from the tourist information API. Example: "https: / / touristapi.com / getSpots?routeID=123"

[0572] Step 6:

[0573] The server transmits the tourist spot information to the vehicle navigation system (terminal).

[0574] Input: Tourist attraction information

[0575] Output: Sent to terminal

[0576] Specific operation: The server sends the acquired tourist information to the terminal in JSON format.

[0577] User Notifications

[0578] Step 7:

[0579] The device will notify the user of guide information such as "The autumn leaves are beautiful on this road" and "Once you turn the next corner, you'll see a spectacular view."

[0580] Input: Tourist attraction information

[0581] Output: Navigation screen update, voice notification

[0582] Specific operation: The terminal updates the navigation screen based on the received tourist spot information and provides visual and audio guidance to the user.

[0583] Step 8:

[0584] Users can enjoy real-time guidance as they drive.

[0585] Input: Guide information

[0586] Output: Drive progress

[0587] Specific operation: The user enjoys driving based on the guidance on the device and proceeds while referring to the tourist information provided.

[0588] Incorporating an emotion engine

[0589] Collecting Emotional Data

[0590] Step 1:

[0591] The device collects the user's voice and facial expression data in real time.

[0592] Input: User's voice and facial expression data

[0593] Output: Collected emotion data

[0594] Specific operation: The device uses the built-in microphone and camera to capture the user's voice and facial expressions. For example, the microphone captures the tone of voice and the camera records facial expressions.

[0595] Emotion analysis

[0596] Step 2:

[0597] The device uses an emotion engine that analyzes collected voice and facial expression data to recognize the user's emotions.

[0598] Input: Collected emotion data

[0599] Output: User's emotional state

[0600] Specific behavior: The device analyzes voice and facial expression data using emotion recognition algorithms. Examples: "The user is irritated" or "Relaxed."

[0601] Step 3:

[0602] The emotional engine identifies the user's current emotional state.

[0603] Input: Parsed emotion data

[0604] Output: Identified emotional state

[0605] Specific operation: The emotion engine evaluates the user's emotional state based on the analysis results and suggests a response appropriate to the situation.

[0606] Route suggestions and content adjustments

[0607] Step 4:

[0608] The server adjusts the generated avoidance routes and tourist information based on the emotional state recognized by the emotion engine.

[0609] Input: Identified emotional state, route information, tourist information

[0610] Output: Adjusted route information, tourist information

[0611] Specific behavior: The server optimizes routes and tourist information by taking into account the user's emotional state. Example: "For an irritated user, suggest a scenic route that will help them relax."

[0612] Step 5:

[0613] The server transmits the adjusted route information and tourist information to the vehicle navigation system (terminal).

[0614] Input: Adjusted route information, tourist information

[0615] Output: Sent to terminal

[0616] Specific operation: The server sends information according to the emotional state to the terminal in JSON format.

[0617] Specific examples

[0618] For example, while a user is driving on a major road, the server receives information from a news API that "an accident occurred on major road A." The generation AI analyzes this information, predicts that a traffic jam will occur on major road A, calculates an alternative route, and sends it to the device. The device then collects the user's voice data, and the emotion engine recognizes that the user is frustrated. Based on this information, the server suggests a scenic route that will allow the user to relax and notifies the user. The user then accepts the suggestion and heads to their destination via the new route. In this way, the user can enjoy a comfortable and safe drive.

[0619] (Application example 2)

[0620] 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."

[0621] Conventional autonomous driving systems mainly calculate routes based on traffic congestion and accident information, but do not provide sufficient feedback or route suggestions based on the user's emotions and preferences. Furthermore, because the user's emotional state is not reflected, the driving experience can be uncomfortable. This poses a challenge: how to reduce user stress and provide a more satisfying driving experience.

[0622] The specific processing by the specific 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 news data, weather data, and social media data, means for preprocessing the collected data and inputting it into a generative AI model that predicts congestion, means for predicting congestion using the generative AI model and calculating an optimal avoidance route, means for transmitting the calculated avoidance route information to a vehicle navigation system, means for collecting user voice and facial expression data, means for analyzing the collected voice and facial expression data and using an emotion engine that recognizes the user's emotions, means for the generative AI model to adjust the avoidance route based on the recognized emotional state, and means for transmitting the adjusted route information to the vehicle navigation system. This enables real-time route suggestions and feedback based on the user's current emotional state and preferences.

[0623] "News data" refers to data on traffic conditions and accident information collected from online news sources.

[0624] "Weather data" refers to data on weather conditions such as temperature, precipitation, and wind speed obtained from a service that provides weather information.

[0625] "Social media data" refers to data regarding user posts and reactions obtained from social networking services (SNS).

[0626] "Collection means" refers to a system for obtaining information such as news data, weather data, and social media data through online APIs, etc.

[0627] "Preprocessing means" refers to a system that processes collected data using methods such as text analysis and data cleansing to prepare it in a format that can be input into a generative AI model.

[0628] A "generative AI model" is an artificial intelligence model that uses machine learning and deep learning techniques to predict traffic congestion and recognize users' emotional states.

[0629] The "route calculation means" is a system that calculates optimal avoidance routes and safe routes based on the prediction results of the generative AI model.

[0630] A "vehicle navigation system" is a system that uses a navigation device installed in a vehicle to notify the user of calculated route information.

[0631] "Voice data" refers to data relating to the user's speaking voice or voice input collected using a microphone.

[0632] "Facial expression data" refers to data relating to the facial expressions and movements of a user collected using a camera.

[0633] The "emotion engine" is a system that analyzes collected voice data and facial expression data to recognize the user's emotional state.

[0634] The "adjustment method" is a system in which the generative AI model adjusts the optimal avoidance route or route that suits the user's preferences based on the recognized emotional state.

[0635] The "notification means" is a system for notifying the user of calculated or adjusted route information and tourist spot information via the vehicle navigation system.

[0636] This invention relates to an autonomous driving system that improves traffic conditions and road safety, and provides a more comfortable and satisfying driving experience for users. The system not only collects news data, weather data, and social media data and uses generative AI models to predict traffic congestion, but also includes an emotion engine that recognizes user emotions. The following describes specific embodiments of the invention.

[0637] System configuration

[0638] The system includes the following major hardware and software components:

[0639] Hardware:

[0640] In-vehicle display

[0641] Smartphone (iPhone, Android)

[0642] Emotion recognition camera (facial recognition compatible)

[0643] Microphone (for collecting audio data)

[0644] software:

[0645] News API (certain news services)

[0646] Weather API (OpenWeatherMap)

[0647] SNS API (Twitter API, etc.)

[0648] Generative AI models (e.g., GPT-4)

[0649] Emotion engine (Microsoft Azure Emotion API, Watson Tone Analyzer, etc.)

[0650] Data processing libraries (Pandas, NumPy, etc.)

[0651] Front-end (React Native, Flutter, etc.)

[0652] What the system does

[0653] 1. Data Collection and Preprocessing:

[0654] The server collects traffic, weather, and social media data using news APIs, weather APIs, and social media APIs.

[0655] The collected data is pre-processed using text analysis and data cleansing.

[0656] 2. Congestion prediction and avoidance route calculation:

[0657] The server inputs the preprocessed data into a generative AI model to perform congestion prediction.

[0658] The generative AI model predicts traffic congestion and calculates optimal avoidance routes.

[0659] The calculated avoidance path information is transmitted to the vehicle navigation system.

[0660] 3. Providing a safe route:

[0661] The server extracts past accident data around the destination and inputs it into a generative AI model to calculate a safe route.

[0662] The calculated safe route information is transmitted to the vehicle navigation system.

[0663] 4. Providing real-time guides:

[0664] The server collects the user's age, hobbies, and past driving history, and inputs this into a generative AI model to generate a driving course based on the user's hobbies and preferences.

[0665] The generated tourist spot information along the driving course is transmitted to the vehicle navigation system and notified to the user.

[0666] 5. Incorporating an emotional engine:

[0667] The device collects the user's voice and facial expression data in real time and analyzes it using an emotion engine.

[0668] The emotional engine identifies the user's current emotional state.

[0669] The server adjusts avoidance routes and tourist information using a generative AI model based on the emotional state recognized by the emotion engine.

[0670] The adjusted route and tourist information is sent to the vehicle navigation system.

[0671] Specific examples

[0672] For example, if the user is in a hurry, a prompt might look like this:

[0673] "There's been an accident on major road A, and traffic congestion is expected. The user is calm but concerned about time. Please suggest a route that prioritizes the shortest time over comfort."

[0674] In this way, the system can provide a comfortable and satisfying driving experience based on the user's emotional state.

[0675] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0676] Step 1:

[0677] The server collects news data, weather data, and social media data using the news API, weather API, and SNS API. The input is data from each API, and the output is the collected raw data. Traffic article data is obtained from the news API, local weather data from the weather API, and related post data from SNS.

[0678] Step 2:

[0679] The server preprocesses the collected raw data. The input is the collected raw data, and the output is the preprocessed data. Specifically, it performs text analysis and data cleansing to remove noise and extract necessary data. It uses data processing libraries such as Pandas and NumPy.

[0680] Step 3:

[0681] The server inputs the preprocessed data into a generative AI model to predict traffic congestion. The input is the preprocessed data, and the output is the congestion prediction result. A generative AI model (e.g., GPT-4) is used to predict the probability of congestion occurring on highways and major intersections.

[0682] Step 4:

[0683] The server calculates the optimal avoidance route based on the prediction results of the generative AI model. The input is the congestion prediction result, and the output is the avoidance route information. Multiple route candidates are evaluated, and the route with good traffic conditions that allows the driver to reach the destination in the shortest time is selected.

[0684] Step 5:

[0685] The server sends the calculated avoidance route information to the vehicle navigation system. The input is the avoidance route information, and the output is the route information sent to the vehicle navigation system. The server notifies the user via hardware such as an in-vehicle display.

[0686] Step 6:

[0687] The device collects the user's voice and facial expression data in real time. The input is the user's voice and facial expression, and the output is the collected voice and facial expression data. It uses a facial recognition-enabled camera and microphone.

[0688] Step 7:

[0689] The device uses an emotion engine that analyzes collected voice and facial expression data and recognizes the user's emotions. The input is the collected voice and facial expression data, and the output is the user's emotional state. It uses the Microsoft Azure Emotion API and Watson Tone Analyzer.

[0690] Step 8:

[0691] The server adjusts the avoidance route and tourist information based on the recognized emotional state. The input is the user's emotional state and existing avoidance route information, and the output is the adjusted route information and tourist information. The route selection and tourist attraction list are updated according to the emotional state.

[0692] Step 9:

[0693] The server transmits the adjusted route information and sightseeing information to the vehicle navigation system. The input is the adjusted route information and sightseeing information, and the output is the information transmitted to the vehicle navigation system. This allows the user to have a more satisfying driving experience based on the recognized emotional state.

[0694] Through the above processing steps, the user can enjoy appropriate traffic situation prediction and a comfortable driving experience.

[0695] 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.

[0696] 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.

[0697] 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.

[0698] [Second embodiment]

[0699] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0700] 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.

[0701] 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).

[0702] 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.

[0703] 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.

[0704] 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).

[0705] 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. 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.

[0706] 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.

[0707] 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.

[0708] 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.

[0709] In the smart glasses 214, 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.

[0710] 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."

[0711] This invention relates to an autonomous driving system that improves traffic conditions and road safety and makes users' driving experiences more comfortable. The system collects news data, weather data, and social media data and uses a generative AI model to predict traffic congestion. The system also utilizes the collected data and the generative AI model to provide safe routes and real-time driving guidance tailored to the user's preferences.

[0712] Traffic congestion prediction and avoidance function

[0713] 1. Data Collection and Preprocessing:

[0714] The server collects traffic conditions, weather information, and social media posts from news APIs, weather APIs, and social media APIs.

[0715] The server preprocesses the collected data and performs text analysis and data cleansing.

[0716] 2. Traffic congestion prediction:

[0717] The server inputs the preprocessed data into a generative AI model to perform traffic congestion predictions.

[0718] Generative AI predicts the probability of traffic jams occurring on highways and major intersections.

[0719] 3. Calculating the Evasive Path:

[0720] The server calculates the optimal avoidance route based on the prediction results of the generated AI model.

[0721] The server sends the calculated avoidance route information to the terminal (vehicle navigation system).

[0722] 4. User Notice:

[0723] The device will display the new route on the navigation screen and notify the user.

[0724] The user reviews the proposed route and approves it if necessary.

[0725] Providing a safe route

[0726] 1. Accident data collection and analysis:

[0727] The server extracts accident data for a specific area from a database of past accidents.

[0728] The server uses the generated AI model to analyze the extracted accident data and identify dangerous areas.

[0729] 2. Calculating the safe path:

[0730] The server calculates a safe route that avoids accident-prone areas based on the generated AI model.

[0731] The server sends the calculated safe route information to the terminal.

[0732] 3. User Notice:

[0733] The device notifies the user of safe routes and displays them on the navigation screen.

[0734] The user reviews the suggested safe routes and selects one.

[0735] Real-time guide that takes into account individual interests

[0736] 1. Collection of User Data:

[0737] The device collects data such as the user's age, hobbies, and past driving history.

[0738] The terminal transmits this data to the server.

[0739] 2. Generate personalized driving itineraries:

[0740] The server inputs the collected user data into a generative AI model to generate a driving course based on the user's hobbies and preferences.

[0741] Generative AI suggests routes that stop off at natural landscapes and specific tourist spots.

[0742] 3. Providing tourist information:

[0743] The server acquires information on tourist spots along the proposed driving course in real time.

[0744] The server transmits tourist spot information to the terminal.

[0745] 4. User Notice:

[0746] The device will notify the user of guide information such as "The autumn leaves are beautiful on this road" and "Once you turn the next corner, you'll see a spectacular view."

[0747] Users can enjoy real-time guidance while driving.

[0748] Specific examples

[0749] For example, while a user is driving on a major road, the server receives information from a news API that "an accident has occurred on major road A." The generation AI analyzes this information, predicts that congestion will occur on major road A, calculates an alternative route, and sends it to the device. The device notifies the user of the new route, and the user accepts the proposal and heads to their destination via the new route.

[0750] Additionally, while the user is enjoying a drive, the device sends information about the user's hobbies to the server, and the AI ​​generator suggests driving routes with beautiful natural scenery based on the user's "love of nature" information. The server obtains tourist spot information in real time, and the device guides the user by saying, "Once you pass the next curve, you'll see a beautiful lake." In this way, the user can enjoy a comfortable and safe drive.

[0751] The processing flow will be explained below.

[0752] Traffic congestion prediction and avoidance function

[0753] Data collection and preprocessing

[0754] Step 1:

[0755] The server collects data about traffic conditions from the news API.

[0756] Step 2:

[0757] The server collects current weather information from a weather API.

[0758] Step 3:

[0759] The server retrieves real-time posting data from the social media API.

[0760] Step 4:

[0761] The server preprocesses the collected data, performing text analysis and data cleansing.

[0762] Traffic congestion forecast

[0763] Step 5:

[0764] The server inputs the preprocessed data into a generative AI model to perform congestion prediction.

[0765] Step 6:

[0766] The generative AI predicts the probability of traffic jams occurring on highways and major intersections.

[0767] Evasion route calculation

[0768] Step 7:

[0769] The server calculates the optimal avoidance route based on the prediction results of the generative AI model.

[0770] Step 8:

[0771] The server transmits the calculated avoidance route information to the terminal (vehicle navigation system).

[0772] User Notifications

[0773] Step 9:

[0774] The device will display the new route on the navigation screen and notify the user.

[0775] Step 10:

[0776] The user reviews the proposed route and approves it if necessary.

[0777] Providing a safe route

[0778] Accident data collection and analysis

[0779] Step 1:

[0780] The server extracts accident data for a specific area from a database of past accidents.

[0781] Step 2:

[0782] The server uses a generative AI model to analyze the extracted accident data and identify risky areas.

[0783] Safe Route Calculation

[0784] Step 3:

[0785] The server calculates a safe route that avoids accident-prone areas based on the generative AI model.

[0786] Step 4:

[0787] The server sends the calculated secure route information to the terminal.

[0788] User Notifications

[0789] Step 5:

[0790] The device notifies the user of safe routes and displays them on the navigation screen.

[0791] Step 6:

[0792] The user reviews the suggested safe routes and selects one.

[0793] Real-time guide that takes into account individual interests

[0794] User Data Collection

[0795] Step 1:

[0796] The device collects data such as the user's age, hobbies, and past driving history.

[0797] Step 2:

[0798] The terminal transmits this data to the server.

[0799] Generate individual driving routes

[0800] Step 3:

[0801] The server inputs the collected user data into a generative AI model to generate a driving course based on the user's hobbies and preferences.

[0802] Step 4:

[0803] The generative AI suggests routes that stop off at natural landscapes and specific tourist spots.

[0804] Providing tourist spot information

[0805] Step 5:

[0806] The server obtains information on tourist spots along the proposed driving course in real time.

[0807] Step 6:

[0808] The server transmits tourist spot information to the terminal.

[0809] User Notifications

[0810] Step 7:

[0811] The device will notify the user of guide information such as "The autumn leaves are beautiful on this road" and "Once you turn the next corner, you'll see a spectacular view."

[0812] Step 8:

[0813] Users can enjoy real-time guidance as they drive.

[0814] Example 1

[0815] 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."

[0816] For autonomous vehicles to operate safely and comfortably, it is necessary to acquire and analyze real-time traffic conditions, weather information, and accident data. However, there is no effective system for efficiently collecting this information and accurately predicting congestion and calculating safe routes. There is also a lack of technology to provide driving guidance tailored to the hobbies and preferences of individual users. There is a need to solve these issues.

[0817] 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.

[0818] In this invention, the server includes a means for collecting news data, weather data, and social networking service data, a means for preprocessing the collected data and performing text analysis and data cleansing, and a means for inputting the preprocessed data into a generative AI model to predict traffic congestion. This enables accurate analysis of traffic conditions, calculation of optimal avoidance routes, and transmission of the route to the vehicle navigation system. It also includes a function for analyzing past accident data to provide safe routes and suggest driving courses based on the user's age, preferences, and past travel history. This improves the safety and comfort of autonomous vehicles.

[0819] "News data" is data collected from the Internet and other sources, including information about traffic conditions and related events.

[0820] "Weather data" refers to data that includes information about weather conditions such as temperature, precipitation, and wind speed.

[0821] "Social networking service data" refers to data that includes information such as user posts and comments collected from social networking services.

[0822] "Preprocessing" is the process of processing collected data using techniques such as text analysis and data cleansing to extract necessary information.

[0823] A "generative AI model" is a model that uses machine learning and artificial intelligence techniques to analyze collected and preprocessed data as input and make predictions and judgments.

[0824] "Traffic congestion forecasting" refers to the use of generative AI models to predict the likelihood of traffic congestion in specific areas and at specific times.

[0825] An "avoidance route" is an alternative route proposed to avoid a predicted congestion or accident.

[0826] A "navigation system" is a system installed in a vehicle that uses GPS and other technologies to provide optimal routes and guide users to their destinations.

[0827] "Accident data" is data extracted from a database containing information about past traffic accidents.

[0828] "User data" refers to data that includes information about the user's age, preferences, and past travel history.

[0829] "Tourist destination information" is data that includes real-time information about tourist attractions and scenic spots.

[0830] A "safe route" is a route calculated to avoid areas prone to accidents and reach the destination as safely as possible.

[0831] A "driving course" is a driving route suggested based on the user's preferences and tastes.

[0832] This invention relates to an autonomous driving system that improves traffic conditions and road safety and makes users' driving experiences more comfortable. This system collects news data, weather data, and social networking service data and predicts traffic congestion using a generative AI model. It also utilizes the collected data and the generative AI model to provide safe routes and real-time driving guidance tailored to the user's preferences.

[0833] Traffic congestion prediction and avoidance function

[0834] Data collection and preprocessing

[0835] The server collects data on traffic conditions, weather information, and social media posts from news APIs (e.g., Google News API), weather APIs (e.g., OpenWeatherMap API), and social media APIs (e.g., Twitter API). The server sends requests to these APIs to retrieve the latest news articles, weather information, and social media posts every hour. The collected data is preprocessed using text analysis and data cleansing techniques. For news data, text mining techniques are used to extract information about traffic accidents and cleanse unnecessary information. For weather data, variables such as temperature, precipitation, and wind speed are analyzed to identify traffic-related factors.

[0836] Traffic congestion forecast

[0837] The server inputs the preprocessed data into a generative AI model (e.g., LSTM model) to predict traffic congestion. The generative AI predicts traffic conditions and calculates the probability of congestion occurring at a specific location and time. For example, it predicts that there is a 70% chance of congestion occurring on major road A at 8 a.m.

[0838] Evasion route calculation

[0839] The server calculates the optimal avoidance route based on the prediction results of the generative AI model. It uses the Google Maps API to obtain alternative route information and searches for and verifies routes with a low probability of congestion and accidents. The calculated avoidance route information is sent to the vehicle's navigation system.

[0840] User Notifications

[0841] The device will display the new route on the navigation screen and notify the user. For example, it will display a message such as, "Congestion is predicted on main road A, so we suggest a route via main road B." The user can then review the proposed route and approve it if necessary.

[0842] Providing a safe route

[0843] Accident data collection and analysis

[0844] The server extracts accident data for a specific area from a database of past accidents (e.g., a public traffic accident statistics database). The extracted accident data is input into a generative AI model to identify areas where accidents frequently occur. The server uses the generative AI model to calculate a safe route that avoids areas where accidents frequently occur. The calculated safe route information is sent to the vehicle's navigation system. The device notifies the user of the safe route and displays it on the navigation screen.

[0845] Real-time guide that takes into account individual interests

[0846] User Data Collection

[0847] The device collects data such as the user's age, hobbies, past driving history, etc. For example, if the user has set information such as "I like nature," the device sends that information to the server.

[0848] Generate individual driving routes

[0849] The server inputs the collected user data into a generative AI model to generate a driving course based on the user's hobbies and preferences. The generative AI then suggests routes that stop off at natural landscapes and specific tourist spots.

[0850] Providing tourist spot information

[0851] The server retrieves tourist spot information along the proposed driving course in real time. The tourist spot information is obtained from the tourist information API and sent to the device. The device then displays a notification to the user saying, "You will see a beautiful lake after passing the next curve."

[0852] Here are some example prompts to input to the generative AI model:

[0853] "Please explain a program that uses news APIs, weather APIs, and social media APIs to collect traffic information and use this data to predict congestion."

[0854] In this way, the user can enjoy a comfortable and safe drive.

[0855] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0856] Step 1: Data collection

[0857] Input: Requests to the news API, weather API, or social media API

[0858] Processing: The server accesses these APIs to collect data on traffic conditions, weather information, and social media posts.

[0859] Output: Collected news data, weather data, and social media data

[0860] Specifically, the server sends a request to the API every hour to retrieve new news articles, the latest weather information, and the latest social media posts.

[0861] Step 2: Data Preprocessing

[0862] Input: Collected news data, weather data, and social media data

[0863] Processing: The server preprocesses the data using text analysis and data cleansing techniques. For example, it extracts information about traffic accidents from news data and removes unnecessary information. For weather data, it normalizes variables such as temperature, precipitation, and wind speed.

[0864] Output: Preprocessed and clean data

[0865] Specifically, the server uses a text mining algorithm to extract keywords related to traffic accidents from news articles, and only retains the necessary weather data.

[0866] Step 3: Traffic congestion prediction

[0867] Input: Preprocessed clean data

[0868] Processing: The server inputs the preprocessed data into a generative AI model (e.g., an LSTM model) to predict traffic congestion.

[0869] Output: Predicted probability of traffic jams

[0870] Specifically, the server converts the preprocessed data into tensor format and sends it to the generative AI model, which then obtains a prediction result such as "There is a 70% probability that traffic congestion will occur on major road A at 8 a.m."

[0871] Step 4: Calculate the optimal escape path

[0872] Input: Predicted result of traffic congestion probability

[0873] Processing: The server calculates the optimal avoidance route based on the prediction results of the generated AI model using Google Maps API etc.

[0874] Output: Calculated avoidance path information

[0875] Specifically, the server uses the Google Maps API to search for alternative routes to avoid areas where congestion is predicted, and finds the optimal avoidance route.

[0876] Step 5: Sending avoidance route information

[0877] Input: Calculated avoidance path information

[0878] Processing: The server sends the calculated avoidance route information to the vehicle's navigation system.

[0879] Output: Avoidance route information displayed on the vehicle navigation system

[0880] Specifically, the server sends an API request to the navigation system to transmit the new route information.

[0881] Step 6: User Notification

[0882] Input: Avoidance route information displayed on the vehicle navigation system

[0883] Processing: The terminal (vehicle navigation system) notifies the user of the new route.

[0884] Output: Avoidance route information displayed and notified to the user

[0885] Specifically, the navigation system will display a message on its screen saying, "Congestion is predicted on main road A, so we suggest a route via main road B," to notify the user.

[0886] Step 7: Collect and analyze accident data

[0887] Input: Past accident database

[0888] Processing: The server extracts accident data for specific areas from a database of past accidents and inputs it into a generative AI model to identify risky areas.

[0889] Output: Information on identified dangerous areas

[0890] Specifically, the server executes a query to retrieve accident information from the accident database for the past 10 years, and then analyzes it using an AI model to identify dangerous intersections and roads.

[0891] Step 8: Calculating a safe path

[0892] Input: Information on identified risk areas

[0893] Processing: The server uses the generative AI model to calculate a safe route that avoids accident-prone areas.

[0894] Output: Calculated safe route information

[0895] Specifically, the server inputs parameters to avoid dangerous areas into the generative AI model and generates a safe route.

[0896] Step 9: Send secure routing information

[0897] Input: Calculated safe route information

[0898] Processing: The server sends the calculated safe route information to the vehicle's navigation system.

[0899] Output: Safe route information displayed on the vehicle navigation system

[0900] Specifically, the server sends an API request to the navigation system again and transmits safe route information.

[0901] Step 10: Generate individual driving routes

[0902] Input: User's age, hobbies, past driving history

[0903] Processing: The device collects this data and sends it to a server. The server inputs the collected user data into a generative AI model to generate a driving course based on the user's hobbies and preferences.

[0904] Output: Generated driving course information

[0905] Specifically, the device collects user information such as "I like nature" and sends it to the server, which then uses a generative AI model to generate a driving course, for example, a "mountain route."

[0906] Step 11: Providing tourist spot information

[0907] Input: Generated driving course information

[0908] Processing: The server obtains tourist spot information along the proposed driving course in real time. It uses the tourist information API to obtain the spot information and sends it to the device.

[0909] Output: Tourist attraction information displayed on the vehicle navigation system

[0910] Specifically, the server obtains information such as "Once you go around the next curve, you will see a beautiful lake" and sends it to the terminal.

[0911] Step 12: User Notification

[0912] Input: Tourist attraction information displayed on vehicle navigation system

[0913] Processing: The terminal notifies the user of tourist spot information.

[0914] Output: Tourist spot information displayed and notified to the user

[0915] Specifically, the device displays a notification to the user saying, "Once you turn the next curve, you'll see a beautiful lake," allowing the user to enjoy the scenery.

[0916] (Application example 1)

[0917] 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."

[0918] Autonomous vehicles are expected to improve traffic congestion and road safety, and to provide a more comfortable driving experience for users. However, conventional technologies have had difficulty in effectively predicting congestion in real time, providing avoidance routes, and providing travel guidance based on users' hobbies and interests. Therefore, the present invention aims to solve these problems and make navigation systems for autonomous vehicles more advanced and useful for users.

[0919] 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.

[0920] In this invention, the server includes means for collecting news data, weather data, and social media data, means for preprocessing the collected data and inputting it into a generative AI model that predicts congestion, means for predicting congestion using the generative AI model and calculating an optimal avoidance route, means for transmitting the calculated avoidance route information to a mobile navigation system, means for the mobile navigation system to notify the user of the proposed avoidance route, means for collecting tourist spot information based on the user's hobbies and interests, means for inputting the collected tourist spot information into the generative AI model and generating travel guidance based on the user's interests, and means for transmitting the generated travel guidance to the mobile navigation system and notifying the user. This makes it possible to provide effective congestion predictions and avoidance routes in real time, and further makes it possible to provide travel guidance based on the user's hobbies and interests in real time.

[0921] "News data" refers to data containing the latest events and information distributed via the Internet or other information media.

[0922] "Weather data" refers to data that includes meteorological information such as temperature, humidity, precipitation, and wind speed.

[0923] "Social media data" refers to data that includes information such as text, images, and videos posted on SNS (social networking services).

[0924] A "generative AI model" is an algorithm that uses machine learning and deep learning to learn patterns from large amounts of data and makes predictions and generates data based on new data.

[0925] A "mobile navigation system" is a system installed in a vehicle or other mobile object that provides map information, route guidance, and traffic information.

[0926] "User" means an individual or group of people who use an automated driving vehicle.

[0927] "Hobbies" are activities or interests that a user is interested in and engages in for enjoyment.

[0928] "Tourist spot information" is data including the location, characteristics, and usage information of tourist spots and famous places.

[0929] "Travel guidance" is a service that provides information on routes to destinations and tourist spots, as well as guidance and advice to help users travel comfortably and enjoyably.

[0930] "Real-time" refers to a state in which current information can be processed immediately and provided without delay.

[0931] The present invention relates to a navigation system for autonomous vehicles. The system aims to improve traffic congestion and road safety and to provide a comfortable driving experience for users. Specific embodiments for carrying out the present invention will be described below.

[0932] System Configuration

[0933] The system according to the present invention includes the following main components:

[0934] server

[0935] Mobile navigation systems (vehicle navigation systems, smartphones, etc.)

[0936] Internet connection

[0937] News data, weather data, social media data APIs

[0938] Data collection

[0939] The server collects data in real time from news APIs, weather APIs, and social media APIs. The data is automatically retrieved via the internet, allowing you to get the latest traffic and weather information, as well as the information you need from social media posts.

[0940] Data Preprocessing

[0941] The server preprocesses the collected data, which includes removing unnecessary data and normalizing and cleaning the text, preparing the data for input into the generative AI model.

[0942] Traffic congestion prediction and calculation of avoidance routes

[0943] The server inputs the preprocessed data into a generative AI model to predict congestion. This generative AI model uses a machine learning algorithm and learns from past data. Based on the results of the congestion prediction, it calculates the optimal avoidance route.

[0944] Sending and notifying route information

[0945] The server sends the calculated avoidance route information to the mobile navigation system, which then notifies the user of the new route information. Notification methods include voice guidance and visual navigation displays.

[0946] Travel guides based on hobbies and interests

[0947] The server collects tourist spot information based on the user's hobbies and interests. The collected information is input into a generative AI model to generate travel guides based on the user's interests. The generated travel guides are sent to the mobile navigation system and notified to the user.

[0948] Hardware and software used

[0949] Hardware: Servers, smartphones, vehicle navigation systems

[0950] Software: Python, generative AI model, external API (news API, weather API, SNS API)

[0951] Specific examples

[0952] For example, while a user is on a long-distance drive, the server receives information from a news API that "an accident occurred on major road A." This information is analyzed by a generative AI model, which predicts that a traffic jam will occur on major road A. The server calculates an alternative route and sends it to the mobile navigation system. The mobile navigation system notifies the user of the new route, and the user accepts the suggestion and heads to their destination via the new route.

[0953] Additionally, while the user is enjoying their drive, the server collects information about the user's hobbies, and the generative AI model suggests driving routes with beautiful natural scenery based on the user's "love of nature" information. The server obtains tourist spot information in real time, and the mobile navigation system guides the user, saying, "Once you turn the next corner, you'll see a beautiful lake." In this way, users can enjoy a comfortable and safe drive.

[0954] Prompt Sentence Examples

[0955] Get the latest information on "traffic accidents" from the news API

[0956] Preprocess social media data to extract posts related to traffic congestion

[0957] Calculate the best route to avoid traffic congestion based on the results of generative AI models.

[0958] Notify your driver of new suggested routes

[0959] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0960] Step 1:

[0961] The server collects data in real time from news APIs, weather APIs, and SNS APIs. Specifically, it sends requests to each API to collect news data, weather data, and social media data, and receives the acquired data. The input is the response data from each API, and the output is the collected news, weather, and SNS post data.

[0962] Step 2:

[0963] The server preprocesses the collected data. Data preprocessing includes removing unnecessary data, normalizing text, and cleaning. For example, summarizing news articles or extracting important parts of weather information. The input is the collected news, weather, and social media data, and the output is the preprocessed data.

[0964] Step 3:

[0965] The server inputs the preprocessed data into a generative AI model to perform congestion prediction. The generative AI model uses patterns learned from past data to predict future traffic congestion. The input is the preprocessed data, and the output is the congestion prediction result.

[0966] Step 4:

[0967] The server calculates the optimal avoidance route based on the congestion prediction results of the generated AI model. The avoidance route calculation also includes map database and road condition data. Specifically, a routing algorithm is used to calculate a route that avoids the predicted congestion. The inputs are the congestion prediction results, map data, and road condition data, and the output is information on the optimal avoidance route.

[0968] Step 5:

[0969] The server sends the calculated avoidance route information to the mobile navigation system. The sent avoidance route information is reflected in the navigation system display in real time. The input is the optimal avoidance route information, and the output is the route guidance information in the navigation system.

[0970] Step 6:

[0971] The terminal (mobile navigation system) notifies the user of the proposed avoidance route. This notification is done both audibly and visually. Specifically, the new route is displayed on the navigation screen and guided by voice. The input is the avoidance route information sent from the server, and the output is the notification and guidance to the user.

[0972] Step 7:

[0973] The server collects tourist spot information based on the user's hobbies and interests. For example, it obtains tourist spot information from the Internet and uses data that reflects the user's past driving history and interests. The input is the user's hobby data and tourist spot information, and the output is input data for the generative AI model.

[0974] Step 8:

[0975] The server inputs the collected information into a generative AI model to generate travel guides based on the user's interests. The generative AI model suggests optimal sightseeing routes and spots based on the user's hobbies and past history. The input is the collected user hobby data and tourist spot information, and the output is travel guide information.

[0976] Step 9:

[0977] The server sends the generated travel guide to the mobile navigation system and notifies the user. In this way, tourist information is provided in real time while traveling. Specifically, the navigation system displays information about tourist spots and provides audio guidance. The input is the generated travel guide, and the output is notifications and guidance for the user.

[0978] 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.

[0979] This invention relates to an autonomous driving system that improves traffic conditions and road safety and makes the user's driving experience more comfortable and emotionally satisfying. The system not only collects news data, weather data, and social media data and predicts traffic congestion using a generative AI model, but also includes an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's voice and facial expression data and provides personalized feedback and suggestions based on their emotional state.

[0980] Traffic congestion prediction and avoidance function

[0981] Data collection and preprocessing

[0982] 1. The server collects traffic and weather information, as well as real-time social media posting data, from news APIs, weather APIs, and social media APIs.

[0983] 2. The server preprocesses the collected data and performs text analysis and data cleansing.

[0984] Traffic congestion forecast

[0985] 3. The server inputs the preprocessed data into the generative AI model to perform congestion prediction.

[0986] 4. Generative AI predicts the probability of traffic jams occurring on highways and major intersections.

[0987] Evasion route calculation

[0988] 5. The server calculates the optimal avoidance path based on the prediction results of the generative AI model.

[0989] 6. The server sends the calculated avoidance route information to the vehicle navigation system (terminal).

[0990] User Notifications

[0991] 7. The device displays the new route on the navigation screen and notifies the user.

[0992] 8. The user reviews the proposed route and approves it if necessary.

[0993] Providing a safe route

[0994] Accident data collection and analysis

[0995] 1. The server extracts accident data for a specific area from a database of past accidents.

[0996] 2. The server uses a generative AI model to analyze the extracted accident data and identify risk areas.

[0997] Safe Route Calculation

[0998] 3. The server calculates a safe route that avoids accident-prone areas based on the generative AI model.

[0999] 4. The server sends the calculated safe route information to the vehicle navigation system (terminal).

[1000] User Notifications

[1001] 5. The device notifies the user of the safe route and displays it on the navigation screen.

[1002] 6. The user reviews the suggested safe routes and selects one.

[1003] Real-time guide that takes into account individual interests

[1004] User Data Collection

[1005] 1. The device collects data such as the user's age, hobbies, and past driving history.

[1006] 2. The device sends this data to the server.

[1007] Generate individual driving routes

[1008] 3. The server inputs the collected user data into a generative AI model and generates a driving course based on the user's hobbies and preferences.

[1009] 4. The generative AI suggests routes that stop off at natural landscapes and specific tourist spots.

[1010] Providing tourist spot information

[1011] 5. The server obtains real-time information about tourist spots along the proposed driving course.

[1012] 6. The server sends the tourist spot information to the vehicle navigation system (terminal).

[1013] User Notifications

[1014] 7. The device notifies the user of guide information such as, "The autumn leaves are beautiful on this road," or "A spectacular view will unfold once you turn the next corner."

[1015] 8. Users can enjoy real-time guidance while driving.

[1016] Incorporating an emotion engine

[1017] Collecting Emotional Data

[1018] 1. The device collects the user's voice and facial expression data in real time.

[1019] Emotion analysis

[1020] 2. The device uses an emotion engine that analyzes collected voice and facial expression data to recognize the user's emotions.

[1021] 3. The emotion engine identifies the user's current emotional state.

[1022] Route suggestions and content adjustments

[1023] 4. The server adjusts the generated avoidance routes and tourist information based on the emotional state recognized by the emotion engine.

[1024] 5. The server sends the adjusted route information and tourist information to the vehicle navigation system (terminal).

[1025] Specific examples

[1026] For example, while a user is driving on a major road, the server receives information from a news API that "an accident occurred on major road A." The generation AI analyzes this information, predicts that a traffic jam will occur on major road A, calculates an alternative route, and sends it to the device. The device then collects the user's voice data, and the emotion engine recognizes that the user is frustrated. Based on this information, the server suggests a scenic route that will allow the user to relax and notifies the user. The user then accepts the suggestion and heads to their destination via the new route. In this way, the user can enjoy a comfortable and safe drive.

[1027] The processing flow will be explained below.

[1028] Traffic congestion prediction and avoidance function

[1029] Data collection and preprocessing

[1030] Step 1:

[1031] The server collects the latest traffic data from the news API.

[1032] Step 2:

[1033] The server retrieves current and forecast weather information from a weather API.

[1034] Step 3:

[1035] The server collects real-time posting data from social media APIs.

[1036] Step 4:

[1037] The server preprocesses the collected news, weather, and social media data, removing unnecessary information and converting it into a unified format.

[1038] Traffic congestion forecast

[1039] Step 5:

[1040] The server inputs the preprocessed data into the generative AI model.

[1041] Step 6:

[1042] The generative AI analyzes the input data and predicts the probability of traffic jams occurring on highways and major intersections.

[1043] Evasion route calculation

[1044] Step 7:

[1045] The server calculates the optimal avoidance route based on the prediction results of the generative AI model.

[1046] Step 8:

[1047] The server transmits the calculated avoidance route information to the vehicle navigation system (terminal).

[1048] User Notifications

[1049] Step 9:

[1050] The device will display the new route on the navigation screen and notify the user.

[1051] Step 10:

[1052] The user reviews the proposed route and approves it if necessary.

[1053] Providing a safe route

[1054] Accident data collection and analysis

[1055] Step 1:

[1056] The server extracts accident data for a specific area from a database of past accidents.

[1057] Step 2:

[1058] The server uses a generative AI model to analyze the extracted accident data and identify risky areas.

[1059] Safe Route Calculation

[1060] Step 3:

[1061] The server calculates a safe route that avoids accident-prone areas based on the generative AI model.

[1062] Step 4:

[1063] The server sends the calculated safe route information to the vehicle navigation system (terminal).

[1064] User Notifications

[1065] Step 5:

[1066] The device notifies the user of safe routes and displays them on the navigation screen.

[1067] Step 6:

[1068] The user reviews the suggested safe routes and selects one.

[1069] Real-time guide that takes into account individual interests

[1070] User Data Collection

[1071] Step 1:

[1072] The device collects data such as the user's age, hobbies, and past driving history.

[1073] Step 2:

[1074] The terminal transmits this data to the server.

[1075] Generate individual driving routes

[1076] Step 3:

[1077] The server inputs the collected user data into a generative AI model to generate a driving course based on the user's hobbies and preferences.

[1078] Step 4:

[1079] The generative AI suggests routes that stop off at natural landscapes and specific tourist spots.

[1080] Providing tourist spot information

[1081] Step 5:

[1082] The server obtains information on tourist spots along the proposed driving course in real time.

[1083] Step 6:

[1084] The server transmits tourist spot information to the vehicle navigation system (terminal).

[1085] User Notifications

[1086] Step 7:

[1087] The device will notify the user of guide information such as "The autumn leaves are beautiful on this road" and "Once you turn the next corner, you'll see a spectacular view."

[1088] Step 8:

[1089] Users can enjoy real-time guidance as they drive.

[1090] Incorporating an emotion engine

[1091] Collecting Emotional Data

[1092] Step 1:

[1093] The device collects the user's voice and facial expression data in real time.

[1094] Emotion analysis

[1095] Step 2:

[1096] The device uses an emotion engine that analyzes collected voice and facial expression data to recognize the user's emotions.

[1097] Step 3:

[1098] The emotion engine identifies the user's current emotional state.

[1099] Route suggestions and content adjustments

[1100] Step 4:

[1101] The server adjusts the generated avoidance routes and tourist information based on the emotional state recognized by the emotion engine.

[1102] Step 5:

[1103] The server sends the adjusted route information and tourist information to the vehicle navigation system (terminal).

[1104] Specific examples

[1105] For example, while a user is driving on a major road, the server receives information from a news API that "an accident occurred on major road A." The generation AI analyzes this information, predicts that a traffic jam will occur on major road A, calculates an alternative route, and sends it to the device. The device then collects the user's voice data, and the emotion engine recognizes that the user is frustrated. Based on this information, the server suggests a scenic route that will allow the user to relax and notifies the user. The user then accepts the suggestion and heads to their destination via the new route. In this way, the user can enjoy a comfortable and safe drive.

[1106] Example 2

[1107] 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."

[1108] Conventional navigation systems are limited to simple route guidance and are unable to flexibly respond to the user's emotions and circumstances. This makes it difficult to present optimal routes that take traffic congestion and accident information into account. It is also difficult to provide a driving experience based on the user's individual preferences. Furthermore, because they are unable to propose routes based on the user's emotional state, they are unable to reduce stress or provide comfort during driving.

[1109] 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 news data, weather data, and social media data, means for preprocessing the collected data and inputting it into a generative AI model that predicts congestion, means for predicting congestion using the generative AI model and calculating an optimal avoidance route, means for transmitting the calculated avoidance route information to a vehicle navigation system, means for the vehicle navigation system to notify the user of the proposed avoidance route, and means for collecting voice and facial expression data of the user to recognize emotions and adjust the route proposal based on the emotions. This makes it possible for the user to avoid congestion, be provided with a safe route, and receive optimal route guidance according to their emotions.

[1110] "News Data" refers to data including traffic conditions, accident information, and other related information obtained through the News API.

[1111] "Weather Data" means data regarding current and forecasted weather conditions obtained through the Weather API.

[1112] "Social media data" refers to data including user posts and real-time comments obtained through SNS APIs.

[1113] "Preprocessing" is the process of converting collected data into a format that is easier to analyze and removing unnecessary information.

[1114] A "generative AI model" is an artificial intelligence model that predicts congestion and traffic conditions based on collected data.

[1115] An "emotion engine" is software or algorithm that analyzes a user's voice and facial expression data to recognize their current emotional state.

[1116] A "vehicle navigation system" is an in-vehicle device equipped with a computer that provides route guidance and displays various information.

[1117] An "avoidance route" is an alternative travel route calculated to avoid congestion or accidents.

[1118] A "safe route" is a travel route that is deemed to have low risk based on past accident data.

[1119] "Tourist attraction information" is information about sights and tourist attractions that can be visited during navigation.

[1120] This invention relates to an autonomous driving system that improves traffic conditions and road safety, and provides a more comfortable and emotionally satisfying driving experience for users. The system collects news, weather, and social media data and predicts traffic congestion using a generative AI model. It also incorporates an emotion engine that recognizes the user's emotions, analyzes their voice and facial expression data, and provides route suggestions and feedback based on their emotional state.

[1121] Traffic congestion prediction and avoidance function

[1122] The server collects traffic and weather information, as well as real-time posting data, from news APIs, weather APIs, and social media APIs. The collected data is preprocessed, and text analysis and data cleansing are performed. The preprocessed data is then input into a generative AI model to perform congestion prediction. The generative AI model predicts the probability of congestion on highways and major intersections. Based on the prediction results, the server calculates the optimal avoidance route and sends this information to the vehicle navigation system. The device displays the new route information on the navigation screen and notifies the user. The user then approves the proposed route and heads to their destination via the new route.

[1123] Providing a safe route

[1124] The server extracts accident data for specific areas from a database of past accidents, inputs it into a generative AI model for analysis, and identifies risk areas. Based on the generative AI model, the server calculates a safe route that avoids accident-prone areas and sends this information to the vehicle navigation system. The device notifies the user of the safe route, and the user selects a new, safer route.

[1125] Real-time guide that takes into account individual interests

[1126] The device collects data such as the user's age, hobbies, and past driving history, and sends this to a server. The server inputs the collected data into a generative AI model to generate a driving course based on the user's hobbies and preferences. Information on tourist spots along the generated driving course is obtained in real time and sent to the vehicle navigation system. The device notifies the user of guide information such as "The autumn leaves are beautiful on this road" or "A spectacular view will unfold once you turn the next corner," allowing the user to enjoy their drive.

[1127] Incorporating an emotion engine

[1128] The device collects the user's voice and facial expression data in real time and analyzes it using an emotion engine. The emotion engine identifies the user's current emotional state and sends the results to the server. The server then adjusts route suggestions and tourist information based on the user's emotional state and sends the new information to the vehicle navigation system. This allows the user to enjoy an optimal driving experience tailored to their emotions.

[1129] Specific examples

[1130] For example, while a user is driving on a major road, the server receives information from a news API that "an accident occurred on major road A." The generative AI model analyzes this information, predicts that a traffic jam will occur on major road A, calculates an alternative route, and sends it to the device. The device then collects the user's voice data, and the emotion engine recognizes that the user is frustrated. Based on this information, the server suggests a scenic route that will allow the user to relax and notifies the user. The user then accepts the suggestion and heads to their destination via the new route. In this way, the user can enjoy a comfortable and safe drive.

[1131] Prompt Sentence Examples

[1132] "Please explain how to obtain traffic accident information from a server, predict congestion, and provide an alternative route while the user is driving on main road A."

[1133] "Give us a concrete example of how you designed a system that uses an emotion engine to improve the driving experience based on the user's emotional state."

[1134] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1135] Traffic congestion prediction and avoidance function

[1136] Data collection and preprocessing

[1137] Step 1:

[1138] The server collects traffic conditions, weather information, and real-time social media posting data from news APIs, weather APIs, and social media APIs.

[1139] Input: Data request from API

[1140] Output: JSON format data

[1141] Specific operation: The server sends an HTTP GET request to each API and receives JSON formatted data as a response. Example: "https: / / newsapi.org / v2 / top-headlines?category=traffic&apiKey=YOUR_API_KEY".

[1142] Step 2:

[1143] The server preprocesses the collected data and performs text analysis and data cleansing.

[1144] Input: Collected JSON data

[1145] Output: Cleansed data

[1146] Specific operation: The server parses the received data and removes unnecessary information. For example, it extracts only data containing keywords such as "accident" or "traffic jam." This process uses text analysis libraries and regular expressions.

[1147] Traffic congestion forecast

[1148] Step 3:

[1149] The server inputs the preprocessed data into a generative AI model to perform congestion prediction.

[1150] Input: Preprocessed data

[1151] Output: Traffic congestion prediction results

[1152] Specific operation: The server converts the preprocessed data into a format suitable for the AI ​​model and inputs it into the model, for example, using TensorFlow or PyTorch to make predictions.

[1153] Step 4:

[1154] The generative AI model predicts the probability of traffic jams occurring on highways and major intersections.

[1155] Input: Transformed data

[1156] Output: Probability of congestion

[1157] Specific operation: The model processes input data and outputs the probability of congestion at each point. Example: "The probability of congestion on Expressway A is 80%."

[1158] Evasion route calculation

[1159] Step 5:

[1160] The server calculates the optimal avoidance route based on the prediction results of the generative AI model.

[1161] Input: Traffic congestion prediction results

[1162] Output: Optimal avoidance route information

[1163] Specific operation: The server takes the prediction results into consideration and calculates an alternative route that can reach the destination in the shortest time. The route calculation is performed using Dijkstra or A algorithm.

[1164] Step 6:

[1165] The server transmits the calculated avoidance route information to the vehicle navigation system (terminal).

[1166] Input: Optimal avoidance route information

[1167] Output: Sent to terminal

[1168] Specific operation: The server encodes the route information in JSON format and sends it to the device, often using an HTTP POST request.

[1169] User Notifications

[1170] Step 7:

[1171] The terminal displays the new route on the navigation screen and notifies the user.

[1172] Input: Optimal avoidance route information

[1173] Output: Update navigation screen

[1174] Specific operation: The device updates the navigation screen based on the received data and notifies the user, "Main road A is congested. Please use alternative route B."

[1175] Step 8:

[1176] The user reviews the proposed route and approves it if necessary.

[1177] Input: New route information

[1178] Output: Route approval

[1179] Specific operation: The user checks the new route on the screen and presses the approval button on a touch panel or the like.

[1180] Providing a safe route

[1181] Accident data collection and analysis

[1182] Step 1:

[1183] The server extracts accident data for a specific area from a database of past accidents.

[1184] Input:Specify a specific area

[1185] Output: Accident data

[1186] Specific operation: The server retrieves accident data for the target region from the database using an SQL query, e.g., "SELECT FROM accident_data WHERE region='specified region'".

[1187] Step 2:

[1188] The server uses a generative AI model to analyze the extracted accident data and identify risk areas.

[1189] Input: Extracted accident data

[1190] Output: Identification of dangerous areas

[1191] Specific operation: The server inputs the accident data as features into the AI ​​model and identifies risk areas. Example: "Intersection C has a high accident rate."

[1192] Safe Route Calculation

[1193] Step 3:

[1194] The server calculates a safe route that avoids accident-prone areas based on a generative AI model.

[1195] Input: Identification results of dangerous areas

[1196] Output: Safe route information

[1197] Specific operation: The server executes a safe route calculation algorithm based on the risk assessment. Example: "Choose route D to avoid intersection C."

[1198] Step 4:

[1199] The server transmits the calculated safe route information to the vehicle navigation system (terminal).

[1200] Input: Secure route information

[1201] Output: Sent to terminal

[1202] Specific operation: The server encodes the secure route information in JSON format and sends it to the terminal.

[1203] User Notifications

[1204] Step 5:

[1205] The terminal notifies the user of a safe route and displays it on the navigation screen.

[1206] Input: Secure route information

[1207] Output: Update navigation screen

[1208] Specific operation: The device displays the new route information on the screen and notifies the user that "this route avoids areas prone to accidents."

[1209] Step 6:

[1210] The user reviews the suggested safe routes and selects one.

[1211] Input: Secure route information

[1212] Output: Route selection

[1213] Specific operation: The user looks at the navigation screen and selects a new route.

[1214] Real-time guide that takes into account individual interests

[1215] User Data Collection

[1216] Step 1:

[1217] The terminal collects data such as the user's age, hobbies, and past driving history.

[1218] Input: User input information, past navigation records

[1219] Output: Collected user data

[1220] Specific operation: The device collects necessary data from the user's input data and past navigation records. For example, "The user's age is 30, and his hobby is hiking."

[1221] Step 2:

[1222] The terminal transmits this data to the server.

[1223] Input: Collected user data

[1224] Output: Sending to server completed

[1225] Specific operation: The device sends the collected data to the server in JSON format.

[1226] Generate individual driving routes

[1227] Step 3:

[1228] The server inputs the collected user data into a generative AI model and generates a driving course based on the user's hobbies and preferences.

[1229] Input: Collected user data

[1230] Output: Generated driving course information

[1231] Specific operation: Based on the collected data, the server uses an AI model to calculate the optimal driving route for the user. For example, it generates a "route that allows you to enjoy natural scenery" or a "route that visits tourist spots."

[1232] Step 4:

[1233] The generative AI model suggests routes that stop off at natural landscapes and specific tourist spots.

[1234] Input: Transformed user data

[1235] Output: Proposed route

[1236] How it works: The generative AI model suggests routes tailored to the user's hobbies and preferences. For example, "This route passes through popular tourist spots."

[1237] Providing tourist spot information

[1238] Step 5:

[1239] The server obtains information on tourist spots along the proposed driving course in real time.

[1240] Input: Proposed driving route information

[1241] Output: Tourist attraction information

[1242] Specific operation: The server retrieves spot data from the tourist information API. Example: "https: / / touristapi.com / getSpots?routeID=123"

[1243] Step 6:

[1244] The server transmits the tourist spot information to the vehicle navigation system (terminal).

[1245] Input: Tourist attraction information

[1246] Output: Sent to terminal

[1247] Specific operation: The server sends the acquired tourist information to the terminal in JSON format.

[1248] User Notifications

[1249] Step 7:

[1250] The device will notify the user of guide information such as "The autumn leaves are beautiful on this road" and "Once you turn the next corner, you'll see a spectacular view."

[1251] Input: Tourist attraction information

[1252] Output: Navigation screen update, voice notification

[1253] Specific operation: The terminal updates the navigation screen based on the received tourist spot information and provides visual and audio guidance to the user.

[1254] Step 8:

[1255] Users can enjoy real-time guidance as they drive.

[1256] Input: Guide information

[1257] Output: Drive progress

[1258] Specific operation: The user enjoys driving based on the guidance on the device and proceeds while referring to the tourist information provided.

[1259] Incorporating an emotion engine

[1260] Collecting Emotional Data

[1261] Step 1:

[1262] The device collects the user's voice and facial expression data in real time.

[1263] Input: User's voice and facial expression data

[1264] Output: Collected emotion data

[1265] Specific operation: The device uses the built-in microphone and camera to capture the user's voice and facial expressions. For example, the microphone captures the tone of voice and the camera records facial expressions.

[1266] Emotion analysis

[1267] Step 2:

[1268] The device uses an emotion engine that analyzes collected voice and facial expression data to recognize the user's emotions.

[1269] Input: Collected emotion data

[1270] Output: User's emotional state

[1271] Specific behavior: The device analyzes voice and facial expression data using emotion recognition algorithms. Examples: "The user is irritated" or "Relaxed."

[1272] Step 3:

[1273] The emotional engine identifies the user's current emotional state.

[1274] Input: Parsed emotion data

[1275] Output: Identified emotional state

[1276] Specific operation: The emotion engine evaluates the user's emotional state based on the analysis results and suggests a response appropriate to the situation.

[1277] Route suggestions and content adjustments

[1278] Step 4:

[1279] The server adjusts the generated avoidance routes and tourist information based on the emotional state recognized by the emotion engine.

[1280] Input: Identified emotional state, route information, tourist information

[1281] Output: Adjusted route information, tourist information

[1282] Specific behavior: The server optimizes routes and tourist information by taking into account the user's emotional state. Example: "For an irritated user, suggest a scenic route that will help them relax."

[1283] Step 5:

[1284] The server transmits the adjusted route information and tourist information to the vehicle navigation system (terminal).

[1285] Input: Adjusted route information, tourist information

[1286] Output: Sent to terminal

[1287] Specific operation: The server sends information according to the emotional state to the terminal in JSON format.

[1288] Specific examples

[1289] For example, while a user is driving on a major road, the server receives information from a news API that "an accident occurred on major road A." The generation AI analyzes this information, predicts that a traffic jam will occur on major road A, calculates an alternative route, and sends it to the device. The device then collects the user's voice data, and the emotion engine recognizes that the user is frustrated. Based on this information, the server suggests a scenic route that will allow the user to relax and notifies the user. The user then accepts the suggestion and heads to their destination via the new route. In this way, the user can enjoy a comfortable and safe drive.

[1290] (Application example 2)

[1291] 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."

[1292] Conventional autonomous driving systems mainly calculate routes based on traffic congestion and accident information, but do not provide sufficient feedback or route suggestions based on the user's emotions and preferences. Furthermore, because the user's emotional state is not reflected, the driving experience can be uncomfortable. This poses a challenge: how to reduce user stress and provide a more satisfying driving experience.

[1293] The specific processing by the specific 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 news data, weather data, and social media data, means for preprocessing the collected data and inputting it into a generative AI model that predicts congestion, means for predicting congestion using the generative AI model and calculating an optimal avoidance route, means for transmitting the calculated avoidance route information to a vehicle navigation system, means for collecting user voice and facial expression data, means for analyzing the collected voice and facial expression data and using an emotion engine that recognizes the user's emotions, means for the generative AI model to adjust the avoidance route based on the recognized emotional state, and means for transmitting the adjusted route information to the vehicle navigation system. This enables real-time route suggestions and feedback based on the user's current emotional state and preferences.

[1294] "News data" refers to data on traffic conditions and accident information collected from online news sources.

[1295] "Weather data" refers to data on weather conditions such as temperature, precipitation, and wind speed obtained from a service that provides weather information.

[1296] "Social media data" refers to data regarding user posts and reactions obtained from social networking services (SNS).

[1297] "Collection means" refers to a system for obtaining information such as news data, weather data, and social media data through online APIs, etc.

[1298] "Preprocessing means" refers to a system that processes collected data using methods such as text analysis and data cleansing to prepare it in a format that can be input into a generative AI model.

[1299] A "generative AI model" is an artificial intelligence model that uses machine learning and deep learning techniques to predict traffic congestion and recognize the user's emotional state.

[1300] The "route calculation means" is a system that calculates optimal avoidance routes and safe routes based on the prediction results of the generative AI model.

[1301] A "vehicle navigation system" is a system that uses a navigation device installed in a vehicle to notify the user of calculated route information.

[1302] "Voice data" refers to data relating to the user's speaking voice or voice input collected using a microphone.

[1303] "Facial expression data" refers to data relating to the facial expressions and movements of a user collected using a camera.

[1304] The "emotion engine" is a system that analyzes collected voice data and facial expression data to recognize the user's emotional state.

[1305] The "adjustment method" is a system in which the generative AI model adjusts the optimal avoidance route or route that suits the user's preferences based on the recognized emotional state.

[1306] The "notification means" is a system for notifying the user of calculated or adjusted route information and tourist spot information via the vehicle navigation system.

[1307] This invention relates to an autonomous driving system that improves traffic conditions and road safety, and provides a more comfortable and satisfying driving experience for users. The system not only collects news data, weather data, and social media data and uses generative AI models to predict traffic congestion, but also includes an emotion engine that recognizes user emotions. The following describes specific embodiments of the invention.

[1308] System configuration

[1309] The system includes the following major hardware and software components:

[1310] Hardware:

[1311] In-vehicle display

[1312] Smartphone (iPhone, Android)

[1313] Emotion recognition camera (facial recognition compatible)

[1314] Microphone (for collecting audio data)

[1315] software:

[1316] News API (certain news services)

[1317] Weather API (OpenWeatherMap)

[1318] SNS API (Twitter API, etc.)

[1319] Generative AI models (e.g., GPT-4)

[1320] Emotion engine (Microsoft Azure Emotion API, Watson Tone Analyzer, etc.)

[1321] Data processing libraries (Pandas, NumPy, etc.)

[1322] Front-end (React Native, Flutter, etc.)

[1323] What the system does

[1324] 1. Data Collection and Preprocessing:

[1325] The server collects traffic, weather, and social media data using news APIs, weather APIs, and social media APIs.

[1326] The collected data is pre-processed using text analysis and data cleansing.

[1327] 2. Congestion prediction and avoidance route calculation:

[1328] The server inputs the preprocessed data into a generative AI model to perform congestion prediction.

[1329] The generative AI model predicts traffic congestion and calculates optimal avoidance routes.

[1330] The calculated avoidance path information is transmitted to the vehicle navigation system.

[1331] 3. Providing a safe route:

[1332] The server extracts past accident data around the destination and inputs it into a generative AI model to calculate a safe route.

[1333] The calculated safe route information is transmitted to the vehicle navigation system.

[1334] 4. Providing real-time guides:

[1335] The server collects the user's age, hobbies, and past driving history, and inputs this into a generative AI model to generate a driving course based on the user's hobbies and preferences.

[1336] The generated tourist spot information along the driving course is transmitted to the vehicle navigation system and notified to the user.

[1337] 5. Incorporating an emotional engine:

[1338] The device collects the user's voice and facial expression data in real time and analyzes it using an emotion engine.

[1339] The emotional engine identifies the user's current emotional state.

[1340] The server adjusts avoidance routes and tourist information using a generative AI model based on the emotional state recognized by the emotion engine.

[1341] The adjusted route and tourist information is sent to the vehicle navigation system.

[1342] Specific examples

[1343] For example, if the user is in a hurry, a prompt might look like this:

[1344] "There's been an accident on major road A, and traffic congestion is expected. The user is calm but concerned about time. Please suggest a route that prioritizes the shortest time over comfort."

[1345] In this way, the system can provide a comfortable and satisfying driving experience based on the user's emotional state.

[1346] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1347] Step 1:

[1348] The server collects news data, weather data, and social media data using the news API, weather API, and SNS API. The input is data from each API, and the output is the collected raw data. Traffic article data is obtained from the news API, local weather data from the weather API, and related post data from SNS.

[1349] Step 2:

[1350] The server preprocesses the collected raw data. The input is the collected raw data, and the output is the preprocessed data. Specifically, it performs text analysis and data cleansing to remove noise and extract necessary data. It uses data processing libraries such as Pandas and NumPy.

[1351] Step 3:

[1352] The server inputs the preprocessed data into a generative AI model to predict traffic congestion. The input is the preprocessed data, and the output is the congestion prediction result. A generative AI model (e.g., GPT-4) is used to predict the probability of congestion occurring on highways and major intersections.

[1353] Step 4:

[1354] The server calculates the optimal avoidance route based on the prediction results of the generative AI model. The input is the congestion prediction result, and the output is the avoidance route information. Multiple route candidates are evaluated, and the route with good traffic conditions that allows the driver to reach the destination in the shortest time is selected.

[1355] Step 5:

[1356] The server sends the calculated avoidance route information to the vehicle navigation system. The input is the avoidance route information, and the output is the route information sent to the vehicle navigation system. The server notifies the user via hardware such as an in-vehicle display.

[1357] Step 6:

[1358] The device collects the user's voice and facial expression data in real time. The input is the user's voice and facial expression, and the output is the collected voice and facial expression data. It uses a facial recognition-enabled camera and microphone.

[1359] Step 7:

[1360] The device uses an emotion engine that analyzes collected voice and facial expression data and recognizes the user's emotions. The input is the collected voice and facial expression data, and the output is the user's emotional state. It uses the Microsoft Azure Emotion API and Watson Tone Analyzer.

[1361] Step 8:

[1362] The server adjusts the avoidance route and tourist information based on the recognized emotional state. The input is the user's emotional state and existing avoidance route information, and the output is the adjusted route information and tourist information. The route selection and tourist attraction list are updated according to the emotional state.

[1363] Step 9:

[1364] The server transmits the adjusted route information and sightseeing information to the vehicle navigation system. The input is the adjusted route information and sightseeing information, and the output is the information transmitted to the vehicle navigation system. This allows the user to have a more satisfying driving experience based on the recognized emotional state.

[1365] Through the above processing steps, the user can enjoy appropriate traffic situation prediction and a comfortable driving experience.

[1366] 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.

[1367] 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.

[1368] 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.

[1369] [Third embodiment]

[1370] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1371] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1372] 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).

[1373] 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.

[1374] 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.

[1375] 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).

[1376] 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.

[1377] 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.

[1378] 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.

[1379] 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.

[1380] 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.

[1381] 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."

[1382] This invention relates to an autonomous driving system that improves traffic conditions and road safety and makes users' driving experiences more comfortable. The system collects news data, weather data, and social media data and uses a generative AI model to predict traffic congestion. The system also utilizes the collected data and the generative AI model to provide safe routes and real-time driving guidance tailored to the user's preferences.

[1383] Traffic congestion prediction and avoidance function

[1384] 1. Data Collection and Preprocessing:

[1385] The server collects traffic conditions, weather information, and social media posts from news APIs, weather APIs, and social media APIs.

[1386] The server preprocesses the collected data and performs text analysis and data cleansing.

[1387] 2. Traffic congestion prediction:

[1388] The server inputs the preprocessed data into a generative AI model to perform traffic congestion predictions.

[1389] Generative AI predicts the probability of traffic jams occurring on highways and major intersections.

[1390] 3. Calculating the Evasive Path:

[1391] The server calculates the optimal avoidance route based on the prediction results of the generated AI model.

[1392] The server sends the calculated avoidance route information to the terminal (vehicle navigation system).

[1393] 4. User Notice:

[1394] The device will display the new route on the navigation screen and notify the user.

[1395] The user reviews the proposed route and approves it if necessary.

[1396] Providing a safe route

[1397] 1. Accident data collection and analysis:

[1398] The server extracts accident data for a specific area from a database of past accidents.

[1399] The server uses the generated AI model to analyze the extracted accident data and identify dangerous areas.

[1400] 2. Calculating the safe path:

[1401] The server calculates a safe route that avoids accident-prone areas based on the generated AI model.

[1402] The server sends the calculated safe route information to the terminal.

[1403] 3. User Notice:

[1404] The device notifies the user of safe routes and displays them on the navigation screen.

[1405] The user reviews the suggested safe routes and selects one.

[1406] Real-time guide that takes into account individual interests

[1407] 1. Collection of User Data:

[1408] The device collects data such as the user's age, hobbies, and past driving history.

[1409] The terminal transmits this data to the server.

[1410] 2. Generate personalized driving itineraries:

[1411] The server inputs the collected user data into a generative AI model to generate a driving course based on the user's hobbies and preferences.

[1412] Generative AI suggests routes that stop off at natural landscapes and specific tourist spots.

[1413] 3. Providing tourist information:

[1414] The server acquires information on tourist spots along the proposed driving course in real time.

[1415] The server transmits tourist spot information to the terminal.

[1416] 4. User Notice:

[1417] The device will notify the user of guide information such as "The autumn leaves are beautiful on this road" and "Once you turn the next corner, you'll see a spectacular view."

[1418] Users can enjoy real-time guidance while driving.

[1419] Specific examples

[1420] For example, while a user is driving on a major road, the server receives information from a news API that "an accident has occurred on major road A." The generation AI analyzes this information, predicts that congestion will occur on major road A, calculates an alternative route, and sends it to the device. The device notifies the user of the new route, and the user accepts the proposal and heads to their destination via the new route.

[1421] Additionally, while the user is enjoying a drive, the device sends information about the user's hobbies to the server, and the AI ​​generator suggests driving routes with beautiful natural scenery based on the user's "love of nature" information. The server obtains tourist spot information in real time, and the device guides the user by saying, "Once you pass the next curve, you'll see a beautiful lake." In this way, the user can enjoy a comfortable and safe drive.

[1422] The processing flow will be explained below.

[1423] Traffic congestion prediction and avoidance function

[1424] Data collection and preprocessing

[1425] Step 1:

[1426] The server collects data about traffic conditions from the news API.

[1427] Step 2:

[1428] The server collects current weather information from a weather API.

[1429] Step 3:

[1430] The server retrieves real-time posting data from the social media API.

[1431] Step 4:

[1432] The server preprocesses the collected data, performing text analysis and data cleansing.

[1433] Traffic congestion forecast

[1434] Step 5:

[1435] The server inputs the preprocessed data into a generative AI model to perform congestion prediction.

[1436] Step 6:

[1437] The generative AI predicts the probability of traffic jams occurring on highways and major intersections.

[1438] Evasion route calculation

[1439] Step 7:

[1440] The server calculates the optimal avoidance route based on the prediction results of the generative AI model.

[1441] Step 8:

[1442] The server transmits the calculated avoidance route information to the terminal (vehicle navigation system).

[1443] User Notifications

[1444] Step 9:

[1445] The device will display the new route on the navigation screen and notify the user.

[1446] Step 10:

[1447] The user reviews the proposed route and approves it if necessary.

[1448] Providing a safe route

[1449] Accident data collection and analysis

[1450] Step 1:

[1451] The server extracts accident data for a specific area from a database of past accidents.

[1452] Step 2:

[1453] The server uses a generative AI model to analyze the extracted accident data and identify risky areas.

[1454] Safe Route Calculation

[1455] Step 3:

[1456] The server calculates a safe route that avoids accident-prone areas based on the generative AI model.

[1457] Step 4:

[1458] The server sends the calculated secure route information to the terminal.

[1459] User Notifications

[1460] Step 5:

[1461] The device notifies the user of safe routes and displays them on the navigation screen.

[1462] Step 6:

[1463] The user reviews the suggested safe routes and selects one.

[1464] Real-time guide that takes into account individual interests

[1465] User Data Collection

[1466] Step 1:

[1467] The device collects data such as the user's age, hobbies, and past driving history.

[1468] Step 2:

[1469] The terminal transmits this data to the server.

[1470] Generate individual driving routes

[1471] Step 3:

[1472] The server inputs the collected user data into a generative AI model to generate a driving course based on the user's hobbies and preferences.

[1473] Step 4:

[1474] The generative AI suggests routes that stop off at natural landscapes and specific tourist spots.

[1475] Providing tourist spot information

[1476] Step 5:

[1477] The server obtains information on tourist spots along the proposed driving course in real time.

[1478] Step 6:

[1479] The server transmits tourist spot information to the terminal.

[1480] User Notifications

[1481] Step 7:

[1482] The device will notify the user of guide information such as "The autumn leaves are beautiful on this road" and "Once you turn the next corner, you'll see a spectacular view."

[1483] Step 8:

[1484] Users can enjoy real-time guidance as they drive.

[1485] Example 1

[1486] 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."

[1487] For autonomous vehicles to operate safely and comfortably, it is necessary to acquire and analyze real-time traffic conditions, weather information, and accident data. However, there is no effective system for efficiently collecting this information and accurately predicting congestion and calculating safe routes. There is also a lack of technology to provide driving guidance tailored to the hobbies and preferences of individual users. There is a need to solve these issues.

[1488] 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.

[1489] In this invention, the server includes a means for collecting news data, weather data, and social networking service data, a means for preprocessing the collected data and performing text analysis and data cleansing, and a means for inputting the preprocessed data into a generative AI model to predict traffic congestion. This enables accurate analysis of traffic conditions, calculation of optimal avoidance routes, and transmission of the route to the vehicle navigation system. It also includes a function for analyzing past accident data to provide safe routes and suggest driving courses based on the user's age, preferences, and past travel history. This improves the safety and comfort of autonomous vehicles.

[1490] "News data" is data collected from the Internet and other sources, including information about traffic conditions and related events.

[1491] "Weather data" refers to data that includes information about weather conditions such as temperature, precipitation, and wind speed.

[1492] "Social networking service data" refers to data that includes information such as user posts and comments collected from social networking services.

[1493] "Preprocessing" is the process of processing collected data using techniques such as text analysis and data cleansing to extract necessary information.

[1494] A "generative AI model" is a model that uses machine learning and artificial intelligence techniques to analyze collected and preprocessed data as input and make predictions and judgments.

[1495] "Traffic congestion forecasting" refers to the use of generative AI models to predict the likelihood of traffic congestion in specific areas and at specific times.

[1496] An "avoidance route" is an alternative route proposed to avoid a predicted congestion or accident.

[1497] A "navigation system" is a system installed in a vehicle that uses GPS and other technologies to provide optimal routes and guide users to their destinations.

[1498] "Accident data" is data extracted from a database containing information about past traffic accidents.

[1499] "User data" refers to data that includes information about the user's age, preferences, and past travel history.

[1500] "Tourist destination information" is data that includes real-time information about tourist attractions and scenic spots.

[1501] A "safe route" is a route calculated to avoid areas prone to accidents and reach the destination as safely as possible.

[1502] A "driving course" is a driving route suggested based on the user's preferences and tastes.

[1503] This invention relates to an autonomous driving system that improves traffic conditions and road safety and makes users' driving experiences more comfortable. This system collects news data, weather data, and social networking service data and predicts traffic congestion using a generative AI model. It also utilizes the collected data and the generative AI model to provide safe routes and real-time driving guidance tailored to the user's preferences.

[1504] Traffic congestion prediction and avoidance function

[1505] Data collection and preprocessing

[1506] The server collects data on traffic conditions, weather information, and social media posts from news APIs (e.g., Google News API), weather APIs (e.g., OpenWeatherMap API), and social media APIs (e.g., Twitter API). The server sends requests to these APIs to retrieve the latest news articles, weather information, and social media posts every hour. The collected data is preprocessed using text analysis and data cleansing techniques. For news data, text mining techniques are used to extract information about traffic accidents and cleanse unnecessary information. For weather data, variables such as temperature, precipitation, and wind speed are analyzed to identify traffic-related factors.

[1507] Traffic congestion forecast

[1508] The server inputs the preprocessed data into a generative AI model (e.g., LSTM model) to predict traffic congestion. The generative AI predicts traffic conditions and calculates the probability of congestion occurring at a specific location and time. For example, it predicts that there is a 70% chance of congestion occurring on major road A at 8 a.m.

[1509] Evasion route calculation

[1510] The server calculates the optimal avoidance route based on the prediction results of the generative AI model. It uses the Google Maps API to obtain alternative route information and searches for and verifies routes with a low probability of congestion and accidents. The calculated avoidance route information is sent to the vehicle's navigation system.

[1511] User Notifications

[1512] The device will display the new route on the navigation screen and notify the user. For example, it will display a message such as, "Congestion is predicted on main road A, so we suggest a route via main road B." The user can then review the proposed route and approve it if necessary.

[1513] Providing a safe route

[1514] Accident data collection and analysis

[1515] The server extracts accident data for a specific area from a database of past accidents (e.g., a public traffic accident statistics database). The extracted accident data is input into a generative AI model to identify areas where accidents frequently occur. The server uses the generative AI model to calculate a safe route that avoids areas where accidents frequently occur. The calculated safe route information is sent to the vehicle's navigation system. The device notifies the user of the safe route and displays it on the navigation screen.

[1516] Real-time guide that takes into account individual interests

[1517] User Data Collection

[1518] The device collects data such as the user's age, hobbies, past driving history, etc. For example, if the user has set information such as "I like nature," the device sends that information to the server.

[1519] Generate individual driving routes

[1520] The server inputs the collected user data into a generative AI model to generate a driving course based on the user's hobbies and preferences. The generative AI then suggests routes that stop off at natural landscapes and specific tourist spots.

[1521] Providing tourist spot information

[1522] The server retrieves tourist spot information along the proposed driving course in real time. The tourist spot information is obtained from the tourist information API and sent to the device. The device then displays a notification to the user saying, "You will see a beautiful lake after passing the next curve."

[1523] Here are some example prompts to input to the generative AI model:

[1524] "Please explain a program that uses news APIs, weather APIs, and social media APIs to collect traffic information and use this data to predict congestion."

[1525] In this way, the user can enjoy a comfortable and safe drive.

[1526] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1527] Step 1: Data collection

[1528] Input: Requests to the news API, weather API, or social media API

[1529] Processing: The server accesses these APIs to collect data on traffic conditions, weather information, and social media posts.

[1530] Output: Collected news data, weather data, and social media data

[1531] Specifically, the server sends a request to the API every hour to retrieve new news articles, the latest weather information, and the latest social media posts.

[1532] Step 2: Data Preprocessing

[1533] Input: Collected news data, weather data, and social media data

[1534] Processing: The server preprocesses the data using text analysis and data cleansing techniques. For example, it extracts information about traffic accidents from news data and removes unnecessary information. For weather data, it normalizes variables such as temperature, precipitation, and wind speed.

[1535] Output: Preprocessed and clean data

[1536] Specifically, the server uses a text mining algorithm to extract keywords related to traffic accidents from news articles, and only retains the necessary weather data.

[1537] Step 3: Traffic congestion prediction

[1538] Input: Preprocessed clean data

[1539] Processing: The server inputs the preprocessed data into a generative AI model (e.g., an LSTM model) to predict traffic congestion.

[1540] Output: Predicted probability of traffic jams

[1541] Specifically, the server converts the preprocessed data into tensor format and sends it to the generative AI model, which then obtains a prediction result such as "There is a 70% probability that traffic congestion will occur on major road A at 8 a.m."

[1542] Step 4: Calculate the optimal escape path

[1543] Input: Predicted result of traffic congestion probability

[1544] Processing: The server calculates the optimal avoidance route based on the prediction results of the generated AI model using Google Maps API etc.

[1545] Output: Calculated avoidance path information

[1546] Specifically, the server uses the Google Maps API to search for alternative routes to avoid areas where congestion is predicted, and finds the optimal avoidance route.

[1547] Step 5: Sending avoidance route information

[1548] Input: Calculated avoidance path information

[1549] Processing: The server sends the calculated avoidance route information to the vehicle's navigation system.

[1550] Output: Avoidance route information displayed on the vehicle navigation system

[1551] Specifically, the server sends an API request to the navigation system to transmit the new route information.

[1552] Step 6: User Notification

[1553] Input: Avoidance route information displayed on the vehicle navigation system

[1554] Processing: The terminal (vehicle navigation system) notifies the user of the new route.

[1555] Output: Avoidance route information displayed and notified to the user

[1556] Specifically, the navigation system will display a message on its screen saying, "Congestion is predicted on main road A, so we suggest a route via main road B," to notify the user.

[1557] Step 7: Collect and analyze accident data

[1558] Input: Past accident database

[1559] Processing: The server extracts accident data for specific areas from a database of past accidents and inputs it into a generative AI model to identify risky areas.

[1560] Output: Information on identified dangerous areas

[1561] Specifically, the server executes a query to retrieve accident information from the accident database for the past 10 years, and then analyzes it using an AI model to identify dangerous intersections and roads.

[1562] Step 8: Calculating a safe path

[1563] Input: Information on identified risk areas

[1564] Processing: The server uses the generative AI model to calculate a safe route that avoids accident-prone areas.

[1565] Output: Calculated safe route information

[1566] Specifically, the server inputs parameters to avoid dangerous areas into the generative AI model and generates a safe route.

[1567] Step 9: Send secure routing information

[1568] Input: Calculated safe route information

[1569] Processing: The server sends the calculated safe route information to the vehicle's navigation system.

[1570] Output: Safe route information displayed on the vehicle navigation system

[1571] Specifically, the server sends an API request to the navigation system again and transmits safe route information.

[1572] Step 10: Generate individual driving routes

[1573] Input: User's age, hobbies, past driving history

[1574] Processing: The device collects this data and sends it to a server. The server inputs the collected user data into a generative AI model to generate a driving course based on the user's hobbies and preferences.

[1575] Output: Generated driving course information

[1576] Specifically, the device collects user information such as "I like nature" and sends it to the server, which then uses a generative AI model to generate a driving course, for example, a "mountain route."

[1577] Step 11: Providing tourist spot information

[1578] Input: Generated driving course information

[1579] Processing: The server obtains tourist spot information along the proposed driving course in real time. It uses the tourist information API to obtain the spot information and sends it to the device.

[1580] Output: Tourist attraction information displayed on the vehicle navigation system

[1581] Specifically, the server obtains information such as "Once you go around the next curve, you will see a beautiful lake" and sends it to the terminal.

[1582] Step 12: User Notification

[1583] Input: Tourist attraction information displayed on vehicle navigation system

[1584] Processing: The terminal notifies the user of tourist spot information.

[1585] Output: Tourist spot information displayed and notified to the user

[1586] Specifically, the device displays a notification to the user saying, "Once you turn the next curve, you'll see a beautiful lake," allowing the user to enjoy the scenery.

[1587] (Application example 1)

[1588] 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."

[1589] Autonomous vehicles are expected to improve traffic congestion and road safety, and to provide a more comfortable driving experience for users. However, conventional technologies have had difficulty in effectively predicting congestion in real time, providing avoidance routes, and providing travel guidance based on users' hobbies and interests. Therefore, the present invention aims to solve these problems and make navigation systems for autonomous vehicles more advanced and useful for users.

[1590] 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.

[1591] In this invention, the server includes means for collecting news data, weather data, and social media data, means for preprocessing the collected data and inputting it into a generative AI model that predicts congestion, means for predicting congestion using the generative AI model and calculating an optimal avoidance route, means for transmitting the calculated avoidance route information to a mobile navigation system, means for the mobile navigation system to notify the user of the proposed avoidance route, means for collecting tourist spot information based on the user's hobbies and interests, means for inputting the collected tourist spot information into the generative AI model and generating travel guidance based on the user's interests, and means for transmitting the generated travel guidance to the mobile navigation system and notifying the user. This makes it possible to provide effective congestion predictions and avoidance routes in real time, and further makes it possible to provide travel guidance based on the user's hobbies and interests in real time.

[1592] "News data" refers to data containing the latest events and information distributed via the Internet or other information media.

[1593] "Weather data" refers to data that includes meteorological information such as temperature, humidity, precipitation, and wind speed.

[1594] "Social media data" refers to data that includes information such as text, images, and videos posted on SNS (social networking services).

[1595] A "generative AI model" is an algorithm that uses machine learning and deep learning to learn patterns from large amounts of data and makes predictions and generates data based on new data.

[1596] A "mobile navigation system" is a system installed in a vehicle or other mobile object that provides map information, route guidance, and traffic information.

[1597] "User" means an individual or group of people who use an automated driving vehicle.

[1598] "Hobbies" are activities or interests that a user is interested in and engages in for enjoyment.

[1599] "Tourist spot information" is data including the location, characteristics, and usage information of tourist spots and famous places.

[1600] "Travel guidance" is a service that provides information on routes to destinations and tourist spots, as well as guidance and advice to help users travel comfortably and enjoyably.

[1601] "Real-time" refers to a state in which current information can be processed immediately and provided without delay.

[1602] The present invention relates to a navigation system for autonomous vehicles. The system aims to improve traffic congestion and road safety and to provide a comfortable driving experience for users. Specific embodiments for carrying out the present invention will be described below.

[1603] System Configuration

[1604] The system according to the present invention includes the following main components:

[1605] server

[1606] Mobile navigation systems (vehicle navigation systems, smartphones, etc.)

[1607] Internet connection

[1608] News data, weather data, social media data APIs

[1609] Data collection

[1610] The server collects data in real time from news APIs, weather APIs, and social media APIs. The data is automatically retrieved via the internet, allowing you to get the latest traffic and weather information, as well as the information you need from social media posts.

[1611] Data Preprocessing

[1612] The server preprocesses the collected data, which includes removing unnecessary data and normalizing and cleaning the text, preparing the data for input into the generative AI model.

[1613] Traffic congestion prediction and calculation of avoidance routes

[1614] The server inputs the preprocessed data into a generative AI model to predict congestion. This generative AI model uses a machine learning algorithm and learns from past data. Based on the results of the congestion prediction, it calculates the optimal avoidance route.

[1615] Sending and notifying route information

[1616] The server sends the calculated avoidance route information to the mobile navigation system, which then notifies the user of the new route information. Notification methods include voice guidance and visual navigation displays.

[1617] Travel guides based on hobbies and interests

[1618] The server collects tourist spot information based on the user's hobbies and interests. The collected information is input into a generative AI model to generate travel guides based on the user's interests. The generated travel guides are sent to the mobile navigation system and notified to the user.

[1619] Hardware and software used

[1620] Hardware: Servers, smartphones, vehicle navigation systems

[1621] Software: Python, generative AI model, external API (news API, weather API, SNS API)

[1622] Specific examples

[1623] For example, while a user is on a long-distance drive, the server receives information from a news API that "an accident occurred on major road A." This information is analyzed by a generative AI model, which predicts that a traffic jam will occur on major road A. The server calculates an alternative route and sends it to the mobile navigation system. The mobile navigation system notifies the user of the new route, and the user accepts the suggestion and heads to their destination via the new route.

[1624] Additionally, while the user is enjoying their drive, the server collects information about the user's hobbies, and the generative AI model suggests driving routes with beautiful natural scenery based on the user's "love of nature" information. The server obtains tourist spot information in real time, and the mobile navigation system guides the user, saying, "Once you turn the next corner, you'll see a beautiful lake." In this way, users can enjoy a comfortable and safe drive.

[1625] Prompt Sentence Examples

[1626] Get the latest information on "traffic accidents" from the news API

[1627] Preprocess social media data to extract posts related to traffic congestion

[1628] Calculate the best route to avoid traffic congestion based on the results of generative AI models.

[1629] Notify your driver of new suggested routes

[1630] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1631] Step 1:

[1632] The server collects data in real time from news APIs, weather APIs, and SNS APIs. Specifically, it sends requests to each API to collect news data, weather data, and social media data, and receives the acquired data. The input is the response data from each API, and the output is the collected news, weather, and SNS post data.

[1633] Step 2:

[1634] The server preprocesses the collected data. Data preprocessing includes removing unnecessary data, normalizing text, and cleaning. For example, summarizing news articles or extracting important parts of weather information. The input is the collected news, weather, and social media data, and the output is the preprocessed data.

[1635] Step 3:

[1636] The server inputs the preprocessed data into a generative AI model to perform congestion prediction. The generative AI model uses patterns learned from past data to predict future traffic congestion. The input is the preprocessed data, and the output is the congestion prediction result.

[1637] Step 4:

[1638] The server calculates the optimal avoidance route based on the congestion prediction results of the generated AI model. The avoidance route calculation also includes map database and road condition data. Specifically, a routing algorithm is used to calculate a route that avoids the predicted congestion. The inputs are the congestion prediction results, map data, and road condition data, and the output is information on the optimal avoidance route.

[1639] Step 5:

[1640] The server sends the calculated avoidance route information to the mobile navigation system. The sent avoidance route information is reflected in the navigation system display in real time. The input is the optimal avoidance route information, and the output is the route guidance information in the navigation system.

[1641] Step 6:

[1642] The terminal (mobile navigation system) notifies the user of the proposed avoidance route. This notification is done both audibly and visually. Specifically, the new route is displayed on the navigation screen and guided by voice. The input is the avoidance route information sent from the server, and the output is the notification and guidance to the user.

[1643] Step 7:

[1644] The server collects tourist spot information based on the user's hobbies and interests. For example, it obtains tourist spot information from the Internet and uses data that reflects the user's past driving history and interests. The input is the user's hobby data and tourist spot information, and the output is input data for the generative AI model.

[1645] Step 8:

[1646] The server inputs the collected information into a generative AI model to generate travel guides based on the user's interests. The generative AI model suggests optimal sightseeing routes and spots based on the user's hobbies and past history. The input is the collected user hobby data and tourist spot information, and the output is travel guide information.

[1647] Step 9:

[1648] The server sends the generated travel guide to the mobile navigation system and notifies the user. In this way, tourist information is provided in real time while traveling. Specifically, the navigation system displays information about tourist spots and provides audio guidance. The input is the generated travel guide, and the output is notifications and guidance for the user.

[1649] 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.

[1650] This invention relates to an autonomous driving system that improves traffic conditions and road safety and makes the user's driving experience more comfortable and emotionally satisfying. The system not only collects news data, weather data, and social media data and predicts traffic congestion using a generative AI model, but also includes an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's voice and facial expression data and provides personalized feedback and suggestions based on their emotional state.

[1651] Traffic congestion prediction and avoidance function

[1652] Data collection and preprocessing

[1653] 1. The server collects traffic and weather information, as well as real-time social media posting data, from news APIs, weather APIs, and social media APIs.

[1654] 2. The server preprocesses the collected data and performs text analysis and data cleansing.

[1655] Traffic congestion forecast

[1656] 3. The server inputs the preprocessed data into the generative AI model to perform congestion prediction.

[1657] 4. Generative AI predicts the probability of traffic jams occurring on highways and major intersections.

[1658] Evasion route calculation

[1659] 5. The server calculates the optimal avoidance path based on the prediction results of the generative AI model.

[1660] 6. The server sends the calculated avoidance route information to the vehicle navigation system (terminal).

[1661] User Notifications

[1662] 7. The device displays the new route on the navigation screen and notifies the user.

[1663] 8. The user reviews the proposed route and approves it if necessary.

[1664] Providing a safe route

[1665] Accident data collection and analysis

[1666] 1. The server extracts accident data for a specific area from a database of past accidents.

[1667] 2. The server uses a generative AI model to analyze the extracted accident data and identify risk areas.

[1668] Safe Route Calculation

[1669] 3. The server calculates a safe route that avoids accident-prone areas based on the generative AI model.

[1670] 4. The server sends the calculated safe route information to the vehicle navigation system (terminal).

[1671] User Notifications

[1672] 5. The device notifies the user of the safe route and displays it on the navigation screen.

[1673] 6. The user reviews the suggested safe routes and selects one.

[1674] Real-time guide that takes into account individual interests

[1675] User Data Collection

[1676] 1. The device collects data such as the user's age, hobbies, and past driving history.

[1677] 2. The device sends this data to the server.

[1678] Generate individual driving routes

[1679] 3. The server inputs the collected user data into a generative AI model and generates a driving course based on the user's hobbies and preferences.

[1680] 4. The generative AI suggests routes that stop off at natural landscapes and specific tourist spots.

[1681] Providing tourist spot information

[1682] 5. The server obtains real-time information about tourist spots along the proposed driving course.

[1683] 6. The server sends the tourist spot information to the vehicle navigation system (terminal).

[1684] User Notifications

[1685] 7. The device notifies the user of guide information such as, "The autumn leaves are beautiful on this road," or "A spectacular view will unfold once you turn the next corner."

[1686] 8. Users can enjoy real-time guidance while driving.

[1687] Incorporating an emotion engine

[1688] Collecting Emotional Data

[1689] 1. The device collects the user's voice and facial expression data in real time.

[1690] Emotion analysis

[1691] 2. The device uses an emotion engine that analyzes collected voice and facial expression data to recognize the user's emotions.

[1692] 3. The emotion engine identifies the user's current emotional state.

[1693] Route suggestions and content adjustments

[1694] 4. The server adjusts the generated avoidance routes and tourist information based on the emotional state recognized by the emotion engine.

[1695] 5. The server sends the adjusted route information and tourist information to the vehicle navigation system (terminal).

[1696] Specific examples

[1697] For example, while a user is driving on a major road, the server receives information from a news API that "an accident occurred on major road A." The generation AI analyzes this information, predicts that a traffic jam will occur on major road A, calculates an alternative route, and sends it to the device. The device then collects the user's voice data, and the emotion engine recognizes that the user is frustrated. Based on this information, the server suggests a scenic route that will allow the user to relax and notifies the user. The user then accepts the suggestion and heads to their destination via the new route. In this way, the user can enjoy a comfortable and safe drive.

[1698] The processing flow will be explained below.

[1699] Traffic congestion prediction and avoidance function

[1700] Data collection and preprocessing

[1701] Step 1:

[1702] The server collects the latest traffic data from the news API.

[1703] Step 2:

[1704] The server retrieves current and forecast weather information from a weather API.

[1705] Step 3:

[1706] The server collects real-time posting data from social media APIs.

[1707] Step 4:

[1708] The server preprocesses the collected news, weather, and social media data, removing unnecessary information and converting it into a unified format.

[1709] Traffic congestion forecast

[1710] Step 5:

[1711] The server inputs the preprocessed data into the generative AI model.

[1712] Step 6:

[1713] The generative AI analyzes the input data and predicts the probability of traffic jams occurring on highways and major intersections.

[1714] Evasion route calculation

[1715] Step 7:

[1716] The server calculates the optimal avoidance route based on the prediction results of the generative AI model.

[1717] Step 8:

[1718] The server transmits the calculated avoidance route information to the vehicle navigation system (terminal).

[1719] User Notifications

[1720] Step 9:

[1721] The device will display the new route on the navigation screen and notify the user.

[1722] Step 10:

[1723] The user reviews the proposed route and approves it if necessary.

[1724] Providing a safe route

[1725] Accident data collection and analysis

[1726] Step 1:

[1727] The server extracts accident data for a specific area from a database of past accidents.

[1728] Step 2:

[1729] The server uses a generative AI model to analyze the extracted accident data and identify risky areas.

[1730] Safe Route Calculation

[1731] Step 3:

[1732] The server calculates a safe route that avoids accident-prone areas based on the generative AI model.

[1733] Step 4:

[1734] The server sends the calculated safe route information to the vehicle navigation system (terminal).

[1735] User Notifications

[1736] Step 5:

[1737] The device notifies the user of safe routes and displays them on the navigation screen.

[1738] Step 6:

[1739] The user reviews the suggested safe routes and selects one.

[1740] Real-time guide that takes into account individual interests

[1741] User Data Collection

[1742] Step 1:

[1743] The device collects data such as the user's age, hobbies, and past driving history.

[1744] Step 2:

[1745] The terminal transmits this data to the server.

[1746] Generate individual driving routes

[1747] Step 3:

[1748] The server inputs the collected user data into a generative AI model to generate a driving course based on the user's hobbies and preferences.

[1749] Step 4:

[1750] The generative AI suggests routes that stop off at natural landscapes and specific tourist spots.

[1751] Providing tourist spot information

[1752] Step 5:

[1753] The server obtains information on tourist spots along the proposed driving course in real time.

[1754] Step 6:

[1755] The server transmits tourist spot information to the vehicle navigation system (terminal).

[1756] User Notifications

[1757] Step 7:

[1758] The device will notify the user of guide information such as "The autumn leaves are beautiful on this road" and "Once you turn the next corner, you'll see a spectacular view."

[1759] Step 8:

[1760] Users can enjoy real-time guidance as they drive.

[1761] Incorporating an emotion engine

[1762] Collecting Emotional Data

[1763] Step 1:

[1764] The device collects the user's voice and facial expression data in real time.

[1765] Emotion analysis

[1766] Step 2:

[1767] The device uses an emotion engine that analyzes collected voice and facial expression data to recognize the user's emotions.

[1768] Step 3:

[1769] The emotion engine identifies the user's current emotional state.

[1770] Route suggestions and content adjustments

[1771] Step 4:

[1772] The server adjusts the generated avoidance routes and tourist information based on the emotional state recognized by the emotion engine.

[1773] Step 5:

[1774] The server sends the adjusted route information and tourist information to the vehicle navigation system (terminal).

[1775] Specific examples

[1776] For example, while a user is driving on a major road, the server receives information from a news API that "an accident occurred on major road A." The generation AI analyzes this information, predicts that a traffic jam will occur on major road A, calculates an alternative route, and sends it to the device. The device then collects the user's voice data, and the emotion engine recognizes that the user is frustrated. Based on this information, the server suggests a scenic route that will allow the user to relax and notifies the user. The user then accepts the suggestion and heads to their destination via the new route. In this way, the user can enjoy a comfortable and safe drive.

[1777] Example 2

[1778] 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."

[1779] Conventional navigation systems are limited to simple route guidance and are unable to flexibly respond to the user's emotions and circumstances. This makes it difficult to present optimal routes that take traffic congestion and accident information into account. It is also difficult to provide a driving experience based on the user's individual preferences. Furthermore, because they are unable to propose routes based on the user's emotional state, they are unable to reduce stress or provide comfort during driving.

[1780] 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 news data, weather data, and social media data, means for preprocessing the collected data and inputting it into a generative AI model that predicts congestion, means for predicting congestion using the generative AI model and calculating an optimal avoidance route, means for transmitting the calculated avoidance route information to a vehicle navigation system, means for the vehicle navigation system to notify the user of the proposed avoidance route, and means for collecting voice and facial expression data of the user to recognize emotions and adjust the route proposal based on the emotions. This makes it possible for the user to avoid congestion, be provided with a safe route, and receive optimal route guidance according to their emotions.

[1781] "News Data" refers to data including traffic conditions, accident information, and other related information obtained through the News API.

[1782] "Weather Data" means data regarding current and forecasted weather conditions obtained through the Weather API.

[1783] "Social media data" refers to data including user posts and real-time comments obtained through SNS APIs.

[1784] "Preprocessing" is the process of converting collected data into a format that is easier to analyze and removing unnecessary information.

[1785] A "generative AI model" is an artificial intelligence model that predicts congestion and traffic conditions based on collected data.

[1786] An "emotion engine" is software or algorithm that analyzes a user's voice and facial expression data to recognize their current emotional state.

[1787] A "vehicle navigation system" is an in-vehicle device equipped with a computer that provides route guidance and displays various information.

[1788] An "avoidance route" is an alternative travel route calculated to avoid congestion or accidents.

[1789] A "safe route" is a travel route that is deemed to have low risk based on past accident data.

[1790] "Tourist attraction information" is information about sights and tourist attractions that can be visited during navigation.

[1791] This invention relates to an autonomous driving system that improves traffic conditions and road safety, and provides a more comfortable and emotionally satisfying driving experience for users. The system collects news, weather, and social media data and predicts traffic congestion using a generative AI model. It also incorporates an emotion engine that recognizes the user's emotions, analyzes their voice and facial expression data, and provides route suggestions and feedback based on their emotional state.

[1792] Traffic congestion prediction and avoidance function

[1793] The server collects traffic and weather information, as well as real-time posting data, from news APIs, weather APIs, and social media APIs. The collected data is preprocessed, and text analysis and data cleansing are performed. The preprocessed data is then input into a generative AI model to perform congestion prediction. The generative AI model predicts the probability of congestion on highways and major intersections. Based on the prediction results, the server calculates the optimal avoidance route and sends this information to the vehicle navigation system. The device displays the new route information on the navigation screen and notifies the user. The user then approves the proposed route and heads to their destination via the new route.

[1794] Providing a safe route

[1795] The server extracts accident data for specific areas from a database of past accidents, inputs it into a generative AI model for analysis, and identifies risk areas. Based on the generative AI model, the server calculates a safe route that avoids accident-prone areas and sends this information to the vehicle navigation system. The device notifies the user of the safe route, and the user selects a new, safer route.

[1796] Real-time guide that takes into account individual interests

[1797] The device collects data such as the user's age, hobbies, and past driving history, and sends this to a server. The server inputs the collected data into a generative AI model to generate a driving course based on the user's hobbies and preferences. Information on tourist spots along the generated driving course is obtained in real time and sent to the vehicle navigation system. The device notifies the user of guide information such as "The autumn leaves are beautiful on this road" or "A spectacular view will unfold once you turn the next corner," allowing the user to enjoy their drive.

[1798] Incorporating an emotion engine

[1799] The device collects the user's voice and facial expression data in real time and analyzes it using an emotion engine. The emotion engine identifies the user's current emotional state and sends the results to the server. The server then adjusts route suggestions and tourist information based on the user's emotional state and sends the new information to the vehicle navigation system. This allows the user to enjoy an optimal driving experience tailored to their emotions.

[1800] Specific examples

[1801] For example, while a user is driving on a major road, the server receives information from a news API that "an accident occurred on major road A." The generative AI model analyzes this information, predicts that a traffic jam will occur on major road A, calculates an alternative route, and sends it to the device. The device then collects the user's voice data, and the emotion engine recognizes that the user is frustrated. Based on this information, the server suggests a scenic route that will allow the user to relax and notifies the user. The user then accepts the suggestion and heads to their destination via the new route. In this way, the user can enjoy a comfortable and safe drive.

[1802] Prompt Sentence Examples

[1803] "Please explain how to obtain traffic accident information from a server, predict congestion, and provide an alternative route while the user is driving on main road A."

[1804] "Give us a concrete example of how you designed a system that uses an emotion engine to improve the driving experience based on the user's emotional state."

[1805] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1806] Traffic congestion prediction and avoidance function

[1807] Data collection and preprocessing

[1808] Step 1:

[1809] The server collects traffic conditions, weather information, and real-time social media posting data from news APIs, weather APIs, and social media APIs.

[1810] Input: Data request from API

[1811] Output: JSON format data

[1812] Specific operation: The server sends an HTTP GET request to each API and receives JSON formatted data as a response. Example: "https: / / newsapi.org / v2 / top-headlines?category=traffic&apiKey=YOUR_API_KEY".

[1813] Step 2:

[1814] The server preprocesses the collected data and performs text analysis and data cleansing.

[1815] Input: Collected JSON data

[1816] Output: Cleansed data

[1817] Specific operation: The server parses the received data and removes unnecessary information. For example, it extracts only data containing keywords such as "accident" or "traffic jam." This process uses text analysis libraries and regular expressions.

[1818] Traffic congestion forecast

[1819] Step 3:

[1820] The server inputs the preprocessed data into a generative AI model to perform congestion prediction.

[1821] Input: Preprocessed data

[1822] Output: Traffic congestion prediction results

[1823] Specific operation: The server converts the preprocessed data into a format suitable for the AI ​​model and inputs it into the model, for example, using TensorFlow or PyTorch to make predictions.

[1824] Step 4:

[1825] The generative AI model predicts the probability of traffic jams occurring on highways and major intersections.

[1826] Input: Transformed data

[1827] Output: Probability of congestion

[1828] Specific operation: The model processes input data and outputs the probability of congestion at each point. Example: "The probability of congestion on Expressway A is 80%."

[1829] Evasion route calculation

[1830] Step 5:

[1831] The server calculates the optimal avoidance route based on the prediction results of the generative AI model.

[1832] Input: Traffic congestion prediction results

[1833] Output: Optimal avoidance route information

[1834] Specific operation: The server takes the prediction results into consideration and calculates an alternative route that can reach the destination in the shortest time. The route calculation is performed using Dijkstra or A algorithm.

[1835] Step 6:

[1836] The server transmits the calculated avoidance route information to the vehicle navigation system (terminal).

[1837] Input: Optimal avoidance route information

[1838] Output: Sent to terminal

[1839] Specific operation: The server encodes the route information in JSON format and sends it to the device, often using an HTTP POST request.

[1840] User Notifications

[1841] Step 7:

[1842] The terminal displays the new route on the navigation screen and notifies the user.

[1843] Input: Optimal avoidance route information

[1844] Output: Update navigation screen

[1845] Specific operation: The device updates the navigation screen based on the received data and notifies the user, "Main road A is congested. Please use alternative route B."

[1846] Step 8:

[1847] The user reviews the proposed route and approves it if necessary.

[1848] Input: New route information

[1849] Output: Route approval

[1850] Specific operation: The user checks the new route on the screen and presses the approval button on a touch panel or the like.

[1851] Providing a safe route

[1852] Accident data collection and analysis

[1853] Step 1:

[1854] The server extracts accident data for a specific area from a database of past accidents.

[1855] Input:Specify a specific area

[1856] Output: Accident data

[1857] Specific operation: The server retrieves accident data for the target region from the database using an SQL query, e.g., "SELECT FROM accident_data WHERE region='specified region'".

[1858] Step 2:

[1859] The server uses a generative AI model to analyze the extracted accident data and identify risk areas.

[1860] Input: Extracted accident data

[1861] Output: Identification of dangerous areas

[1862] Specific operation: The server inputs the accident data as features into the AI ​​model and identifies risk areas. Example: "Intersection C has a high accident rate."

[1863] Safe Route Calculation

[1864] Step 3:

[1865] The server calculates a safe route that avoids accident-prone areas based on a generative AI model.

[1866] Input: Identification results of dangerous areas

[1867] Output: Safe route information

[1868] Specific operation: The server executes a safe route calculation algorithm based on the risk assessment. Example: "Choose route D to avoid intersection C."

[1869] Step 4:

[1870] The server transmits the calculated safe route information to the vehicle navigation system (terminal).

[1871] Input: Secure route information

[1872] Output: Sent to terminal

[1873] Specific operation: The server encodes the secure route information in JSON format and sends it to the terminal.

[1874] User Notifications

[1875] Step 5:

[1876] The terminal notifies the user of a safe route and displays it on the navigation screen.

[1877] Input: Secure route information

[1878] Output: Update navigation screen

[1879] Specific operation: The device displays the new route information on the screen and notifies the user that "this route avoids areas prone to accidents."

[1880] Step 6:

[1881] The user reviews the suggested safe routes and selects one.

[1882] Input: Secure route information

[1883] Output: Route selection

[1884] Specific operation: The user looks at the navigation screen and selects a new route.

[1885] Real-time guide that takes into account individual interests

[1886] User Data Collection

[1887] Step 1:

[1888] The terminal collects data such as the user's age, hobbies, and past driving history.

[1889] Input: User input information, past navigation records

[1890] Output: Collected user data

[1891] Specific operation: The device collects necessary data from the user's input data and past navigation records. For example, "The user's age is 30, and his hobby is hiking."

[1892] Step 2:

[1893] The terminal transmits this data to the server.

[1894] Input: Collected user data

[1895] Output: Sending to server completed

[1896] Specific operation: The device sends the collected data to the server in JSON format.

[1897] Generate individual driving routes

[1898] Step 3:

[1899] The server inputs the collected user data into a generative AI model and generates a driving course based on the user's hobbies and preferences.

[1900] Input: Collected user data

[1901] Output: Generated driving course information

[1902] Specific operation: Based on the collected data, the server uses an AI model to calculate the optimal driving route for the user. For example, it generates a "route that allows you to enjoy natural scenery" or a "route that visits tourist spots."

[1903] Step 4:

[1904] The generative AI model suggests routes that stop off at natural landscapes and specific tourist spots.

[1905] Input: Transformed user data

[1906] Output: Proposed route

[1907] How it works: The generative AI model suggests routes tailored to the user's hobbies and preferences. For example, "This route passes through popular tourist spots."

[1908] Providing tourist spot information

[1909] Step 5:

[1910] The server obtains information on tourist spots along the proposed driving course in real time.

[1911] Input: Proposed driving route information

[1912] Output: Tourist attraction information

[1913] Specific operation: The server retrieves spot data from the tourist information API. Example: "https: / / touristapi.com / getSpots?routeID=123"

[1914] Step 6:

[1915] The server transmits the tourist spot information to the vehicle navigation system (terminal).

[1916] Input: Tourist attraction information

[1917] Output: Sent to terminal

[1918] Specific operation: The server sends the acquired tourist information to the terminal in JSON format.

[1919] User Notifications

[1920] Step 7:

[1921] The device will notify the user of guide information such as "The autumn leaves are beautiful on this road" and "Once you turn the next corner, you'll see a spectacular view."

[1922] Input: Tourist attraction information

[1923] Output: Navigation screen update, voice notification

[1924] Specific operation: The terminal updates the navigation screen based on the received tourist spot information and provides visual and audio guidance to the user.

[1925] Step 8:

[1926] Users can enjoy real-time guidance as they drive.

[1927] Input: Guide information

[1928] Output: Drive progress

[1929] Specific operation: The user enjoys driving based on the guidance on the device and proceeds while referring to the tourist information provided.

[1930] Incorporating an emotion engine

[1931] Collecting Emotional Data

[1932] Step 1:

[1933] The device collects the user's voice and facial expression data in real time.

[1934] Input: User's voice and facial expression data

[1935] Output: Collected emotion data

[1936] Specific operation: The device uses the built-in microphone and camera to capture the user's voice and facial expressions. For example, the microphone captures the tone of voice and the camera records facial expressions.

[1937] Emotion analysis

[1938] Step 2:

[1939] The device uses an emotion engine that analyzes collected voice and facial expression data to recognize the user's emotions.

[1940] Input: Collected emotion data

[1941] Output: User's emotional state

[1942] Specific behavior: The device analyzes voice and facial expression data using emotion recognition algorithms. Examples: "The user is irritated" or "Relaxed."

[1943] Step 3:

[1944] The emotional engine identifies the user's current emotional state.

[1945] Input: Parsed emotion data

[1946] Output: Identified emotional state

[1947] Specific operation: The emotion engine evaluates the user's emotional state based on the analysis results and suggests a response appropriate to the situation.

[1948] Route suggestions and content adjustments

[1949] Step 4:

[1950] The server adjusts the generated avoidance routes and tourist information based on the emotional state recognized by the emotion engine.

[1951] Input: Identified emotional state, route information, tourist information

[1952] Output: Adjusted route information, tourist information

[1953] Specific behavior: The server optimizes routes and tourist information by taking into account the user's emotional state. Example: "For an irritated user, suggest a scenic route that will help them relax."

[1954] Step 5:

[1955] The server transmits the adjusted route information and tourist information to the vehicle navigation system (terminal).

[1956] Input: Adjusted route information, tourist information

[1957] Output: Sent to terminal

[1958] Specific operation: The server sends information according to the emotional state to the terminal in JSON format.

[1959] Specific examples

[1960] For example, while a user is driving on a major road, the server receives information from a news API that "an accident occurred on major road A." The generation AI analyzes this information, predicts that a traffic jam will occur on major road A, calculates an alternative route, and sends it to the device. The device then collects the user's voice data, and the emotion engine recognizes that the user is frustrated. Based on this information, the server suggests a scenic route that will allow the user to relax and notifies the user. The user then accepts the suggestion and heads to their destination via the new route. In this way, the user can enjoy a comfortable and safe drive.

[1961] (Application example 2)

[1962] 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."

[1963] Conventional autonomous driving systems mainly calculate routes based on traffic congestion and accident information, but do not provide sufficient feedback or route suggestions based on the user's emotions and preferences. Furthermore, because the user's emotional state is not reflected, the driving experience can be uncomfortable. This poses a challenge: how to reduce user stress and provide a more satisfying driving experience.

[1964] The specific processing by the specific 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 news data, weather data, and social media data, means for preprocessing the collected data and inputting it into a generative AI model that predicts congestion, means for predicting congestion using the generative AI model and calculating an optimal avoidance route, means for transmitting the calculated avoidance route information to a vehicle navigation system, means for collecting user voice and facial expression data, means for analyzing the collected voice and facial expression data and using an emotion engine that recognizes the user's emotions, means for the generative AI model to adjust the avoidance route based on the recognized emotional state, and means for transmitting the adjusted route information to the vehicle navigation system. This enables real-time route suggestions and feedback based on the user's current emotional state and preferences.

[1965] "News data" refers to data on traffic conditions and accident information collected from online news sources.

[1966] "Weather data" refers to data on weather conditions such as temperature, precipitation, and wind speed obtained from a service that provides weather information.

[1967] "Social media data" refers to data regarding user posts and reactions obtained from social networking services (SNS).

[1968] "Collection means" refers to a system for obtaining information such as news data, weather data, and social media data through online APIs, etc.

[1969] "Preprocessing means" refers to a system that processes collected data using methods such as text analysis and data cleansing to prepare it in a format that can be input into a generative AI model.

[1970] A "generative AI model" is an artificial intelligence model that uses machine learning and deep learning techniques to predict traffic congestion and recognize the user's emotional state.

[1971] The "route calculation means" is a system that calculates optimal avoidance routes and safe routes based on the prediction results of the generative AI model.

[1972] A "vehicle navigation system" is a system that uses a navigation device installed in a vehicle to notify the user of calculated route information.

[1973] "Voice data" refers to data relating to the user's speaking voice or voice input collected using a microphone.

[1974] "Facial expression data" refers to data relating to the facial expressions and movements of a user collected using a camera.

[1975] The "emotion engine" is a system that analyzes collected voice data and facial expression data to recognize the user's emotional state.

[1976] The "adjustment method" is a system in which the generative AI model adjusts the optimal avoidance route or route that suits the user's preferences based on the recognized emotional state.

[1977] The "notification means" is a system for notifying the user of calculated or adjusted route information and tourist spot information via the vehicle navigation system.

[1978] This invention relates to an autonomous driving system that improves traffic conditions and road safety, and provides a more comfortable and satisfying driving experience for users. The system not only collects news data, weather data, and social media data and uses generative AI models to predict traffic congestion, but also includes an emotion engine that recognizes user emotions. The following describes specific embodiments of the invention.

[1979] System configuration

[1980] The system includes the following major hardware and software components:

[1981] Hardware:

[1982] In-vehicle display

[1983] Smartphone (iPhone, Android)

[1984] Emotion recognition camera (facial recognition compatible)

[1985] Microphone (for collecting audio data)

[1986] software:

[1987] News API (certain news services)

[1988] Weather API (OpenWeatherMap)

[1989] SNS API (Twitter API, etc.)

[1990] Generative AI models (e.g., GPT-4)

[1991] Emotion engine (Microsoft Azure Emotion API, Watson Tone Analyzer, etc.)

[1992] Data processing libraries (Pandas, NumPy, etc.)

[1993] Front-end (React Native, Flutter, etc.)

[1994] What the system does

[1995] 1. Data Collection and Preprocessing:

[1996] The server collects traffic, weather, and social media data using news APIs, weather APIs, and social media APIs.

[1997] The collected data is pre-processed using text analysis and data cleansing.

[1998] 2. Congestion prediction and avoidance route calculation:

[1999] The server inputs the preprocessed data into a generative AI model to perform congestion prediction.

[2000] The generative AI model predicts traffic congestion and calculates optimal avoidance routes.

[2001] The calculated avoidance path information is transmitted to the vehicle navigation system.

[2002] 3. Providing a safe route:

[2003] The server extracts past accident data around the destination and inputs it into a generative AI model to calculate a safe route.

[2004] The calculated safe route information is transmitted to the vehicle navigation system.

[2005] 4. Providing real-time guides:

[2006] The server collects the user's age, hobbies, and past driving history, and inputs this into a generative AI model to generate a driving course based on the user's hobbies and preferences.

[2007] The generated tourist spot information along the driving course is transmitted to the vehicle navigation system and notified to the user.

[2008] 5. Incorporating an emotional engine:

[2009] The device collects the user's voice and facial expression data in real time and analyzes it using an emotion engine.

[2010] The emotional engine identifies the user's current emotional state.

[2011] The server adjusts avoidance routes and tourist information using a generative AI model based on the emotional state recognized by the emotion engine.

[2012] The adjusted route and tourist information is sent to the vehicle navigation system.

[2013] Specific examples

[2014] For example, if the user is in a hurry, a prompt might look like this:

[2015] "There's been an accident on major road A, and traffic congestion is expected. The user is calm but concerned about time. Please suggest a route that prioritizes the shortest time over comfort."

[2016] In this way, the system can provide a comfortable and satisfying driving experience based on the user's emotional state.

[2017] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2018] Step 1:

[2019] The server collects news data, weather data, and social media data using the news API, weather API, and SNS API. The input is data from each API, and the output is the collected raw data. Traffic article data is obtained from the news API, local weather data from the weather API, and related post data from SNS.

[2020] Step 2:

[2021] The server preprocesses the collected raw data. The input is the collected raw data, and the output is the preprocessed data. Specifically, it performs text analysis and data cleansing to remove noise and extract necessary data. It uses data processing libraries such as Pandas and NumPy.

[2022] Step 3:

[2023] The server inputs the preprocessed data into a generative AI model to predict traffic congestion. The input is the preprocessed data, and the output is the congestion prediction result. A generative AI model (e.g., GPT-4) is used to predict the probability of congestion occurring on highways and major intersections.

[2024] Step 4:

[2025] The server calculates the optimal avoidance route based on the prediction results of the generative AI model. The input is the congestion prediction result, and the output is the avoidance route information. Multiple route candidates are evaluated, and the route with good traffic conditions that allows the driver to reach the destination in the shortest time is selected.

[2026] Step 5:

[2027] The server sends the calculated avoidance route information to the vehicle navigation system. The input is the avoidance route information, and the output is the route information sent to the vehicle navigation system. The server notifies the user via hardware such as an in-vehicle display.

[2028] Step 6:

[2029] The device collects the user's voice and facial expression data in real time. The input is the user's voice and facial expression, and the output is the collected voice and facial expression data. It uses a facial recognition-enabled camera and microphone.

[2030] Step 7:

[2031] The device uses an emotion engine that analyzes collected voice and facial expression data and recognizes the user's emotions. The input is the collected voice and facial expression data, and the output is the user's emotional state. It uses the Microsoft Azure Emotion API and Watson Tone Analyzer.

[2032] Step 8:

[2033] The server adjusts the avoidance route and tourist information based on the recognized emotional state. The input is the user's emotional state and existing avoidance route information, and the output is the adjusted route information and tourist information. The route selection and tourist attraction list are updated according to the emotional state.

[2034] Step 9:

[2035] The server transmits the adjusted route information and sightseeing information to the vehicle navigation system. The input is the adjusted route information and sightseeing information, and the output is the information transmitted to the vehicle navigation system. This allows the user to have a more satisfying driving experience based on the recognized emotional state.

[2036] Through the above processing steps, the user can enjoy appropriate traffic situation prediction and a comfortable driving experience.

[2037] 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.

[2038] 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.

[2039] 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.

[2040] [Fourth embodiment]

[2041] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[2042] 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.

[2043] 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).

[2044] 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.

[2045] 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.

[2046] 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).

[2047] 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. 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.

[2048] 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.

[2049] 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.

[2050] 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.

[2051] 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.

[2052] 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.

[2053] 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."

[2054] This invention relates to an autonomous driving system that improves traffic conditions and road safety and makes users' driving experiences more comfortable. The system collects news data, weather data, and social media data and uses a generative AI model to predict traffic congestion. The system also utilizes the collected data and the generative AI model to provide safe routes and real-time driving guidance tailored to the user's preferences.

[2055] Traffic congestion prediction and avoidance function

[2056] 1. Data Collection and Preprocessing:

[2057] The server collects traffic conditions, weather information, and social media posts from news APIs, weather APIs, and social media APIs.

[2058] The server preprocesses the collected data and performs text analysis and data cleansing.

[2059] 2. Traffic congestion prediction:

[2060] The server inputs the preprocessed data into a generative AI model to perform traffic congestion predictions.

[2061] Generative AI predicts the probability of traffic jams occurring on highways and major intersections.

[2062] 3. Calculating the Evasive Path:

[2063] The server calculates the optimal avoidance route based on the prediction results of the generated AI model.

[2064] The server sends the calculated avoidance route information to the terminal (vehicle navigation system).

[2065] 4. User Notice:

[2066] The device will display the new route on the navigation screen and notify the user.

[2067] The user reviews the proposed route and approves it if necessary.

[2068] Providing a safe route

[2069] 1. Accident data collection and analysis:

[2070] The server extracts accident data for a specific area from a database of past accidents.

[2071] The server uses the generated AI model to analyze the extracted accident data and identify dangerous areas.

[2072] 2. Calculating the safe path:

[2073] The server calculates a safe route that avoids accident-prone areas based on the generated AI model.

[2074] The server sends the calculated safe route information to the terminal.

[2075] 3. User Notice:

[2076] The device notifies the user of safe routes and displays them on the navigation screen.

[2077] The user reviews the suggested safe routes and selects one.

[2078] Real-time guide that takes into account individual interests

[2079] 1. Collection of User Data:

[2080] The device collects data such as the user's age, hobbies, and past driving history.

[2081] The terminal transmits this data to the server.

[2082] 2. Generate personalized driving itineraries:

[2083] The server inputs the collected user data into a generative AI model to generate a driving course based on the user's hobbies and preferences.

[2084] Generative AI suggests routes that stop off at natural landscapes and specific tourist spots.

[2085] 3. Providing tourist information:

[2086] The server acquires information on tourist spots along the proposed driving course in real time.

[2087] The server transmits tourist spot information to the terminal.

[2088] 4. User Notice:

[2089] The device will notify the user of guide information such as "The autumn leaves are beautiful on this road" and "Once you turn the next corner, you'll see a spectacular view."

[2090] Users can enjoy real-time guidance while driving.

[2091] Specific examples

[2092] For example, while a user is driving on a major road, the server receives information from a news API that "an accident has occurred on major road A." The generation AI analyzes this information, predicts that congestion will occur on major road A, calculates an alternative route, and sends it to the device. The device notifies the user of the new route, and the user accepts the proposal and heads to their destination via the new route.

[2093] Additionally, while the user is enjoying a drive, the device sends information about the user's hobbies to the server, and the AI ​​generator suggests driving routes with beautiful natural scenery based on the user's "love of nature" information. The server obtains tourist spot information in real time, and the device guides the user by saying, "Once you pass the next curve, you'll see a beautiful lake." In this way, the user can enjoy a comfortable and safe drive.

[2094] The processing flow will be explained below.

[2095] Traffic congestion prediction and avoidance function

[2096] Data collection and preprocessing

[2097] Step 1:

[2098] The server collects data about traffic conditions from the news API.

[2099] Step 2:

[2100] The server collects current weather information from a weather API.

[2101] Step 3:

[2102] The server retrieves real-time posting data from the social media API.

[2103] Step 4:

[2104] The server preprocesses the collected data, performing text analysis and data cleansing.

[2105] Traffic congestion forecast

[2106] Step 5:

[2107] The server inputs the preprocessed data into a generative AI model to perform congestion prediction.

[2108] Step 6:

[2109] The generative AI predicts the probability of traffic jams occurring on highways and major intersections.

[2110] Evasion route calculation

[2111] Step 7:

[2112] The server calculates the optimal avoidance route based on the prediction results of the generative AI model.

[2113] Step 8:

[2114] The server transmits the calculated avoidance route information to the terminal (vehicle navigation system).

[2115] User Notifications

[2116] Step 9:

[2117] The device will display the new route on the navigation screen and notify the user.

[2118] Step 10:

[2119] The user reviews the proposed route and approves it if necessary.

[2120] Providing a safe route

[2121] Accident data collection and analysis

[2122] Step 1:

[2123] The server extracts accident data for a specific area from a database of past accidents.

[2124] Step 2:

[2125] The server uses a generative AI model to analyze the extracted accident data and identify risky areas.

[2126] Safe Route Calculation

[2127] Step 3:

[2128] The server calculates a safe route that avoids accident-prone areas based on the generative AI model.

[2129] Step 4:

[2130] The server sends the calculated secure route information to the terminal.

[2131] User Notifications

[2132] Step 5:

[2133] The device notifies the user of safe routes and displays them on the navigation screen.

[2134] Step 6:

[2135] The user reviews the suggested safe routes and selects one.

[2136] Real-time guide that takes into account individual interests

[2137] User Data Collection

[2138] Step 1:

[2139] The device collects data such as the user's age, hobbies, and past driving history.

[2140] Step 2:

[2141] The terminal transmits this data to the server.

[2142] Generate individual driving routes

[2143] Step 3:

[2144] The server inputs the collected user data into a generative AI model to generate a driving course based on the user's hobbies and preferences.

[2145] Step 4:

[2146] The generative AI suggests routes that stop off at natural landscapes and specific tourist spots.

[2147] Providing tourist spot information

[2148] Step 5:

[2149] The server obtains information on tourist spots along the proposed driving course in real time.

[2150] Step 6:

[2151] The server transmits tourist spot information to the terminal.

[2152] User Notifications

[2153] Step 7:

[2154] The device will notify the user of guide information such as "The autumn leaves are beautiful on this road" and "Once you turn the next corner, you'll see a spectacular view."

[2155] Step 8:

[2156] Users can enjoy real-time guidance as they drive.

[2157] Example 1

[2158] 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."

[2159] For autonomous vehicles to operate safely and comfortably, it is necessary to acquire and analyze real-time traffic conditions, weather information, and accident data. However, there is no effective system for efficiently collecting this information and accurately predicting congestion and calculating safe routes. There is also a lack of technology to provide driving guidance tailored to the hobbies and preferences of individual users. There is a need to solve these issues.

[2160] 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.

[2161] In this invention, the server includes a means for collecting news data, weather data, and social networking service data, a means for preprocessing the collected data and performing text analysis and data cleansing, and a means for inputting the preprocessed data into a generative AI model to predict traffic congestion. This enables accurate analysis of traffic conditions, calculation of optimal avoidance routes, and transmission of the route to the vehicle navigation system. It also includes a function for analyzing past accident data to provide safe routes and suggest driving courses based on the user's age, preferences, and past travel history. This improves the safety and comfort of autonomous vehicles.

[2162] "News data" is data collected from the Internet and other sources, including information about traffic conditions and related events.

[2163] "Weather data" refers to data that includes information about weather conditions such as temperature, precipitation, and wind speed.

[2164] "Social networking service data" refers to data that includes information such as user posts and comments collected from social networking services.

[2165] "Preprocessing" is the process of processing collected data using techniques such as text analysis and data cleansing to extract necessary information.

[2166] A "generative AI model" is a model that uses machine learning and artificial intelligence techniques to analyze collected and preprocessed data as input and make predictions and judgments.

[2167] "Traffic congestion forecasting" refers to the use of generative AI models to predict the likelihood of traffic congestion in specific areas and at specific times.

[2168] An "avoidance route" is an alternative route proposed to avoid a predicted congestion or accident.

[2169] A "navigation system" is a system installed in a vehicle that uses GPS and other technologies to provide optimal routes and guide users to their destinations.

[2170] "Accident data" is data extracted from a database containing information about past traffic accidents.

[2171] "User data" refers to data that includes information about the user's age, preferences, and past travel history.

[2172] "Tourist destination information" is data that includes real-time information about tourist attractions and scenic spots.

[2173] A "safe route" is a route calculated to avoid areas prone to accidents and reach the destination as safely as possible.

[2174] A "driving course" is a driving route suggested based on the user's preferences and tastes.

[2175] This invention relates to an autonomous driving system that improves traffic conditions and road safety and makes users' driving experiences more comfortable. This system collects news data, weather data, and social networking service data and predicts traffic congestion using a generative AI model. It also utilizes the collected data and the generative AI model to provide safe routes and real-time driving guidance tailored to the user's preferences.

[2176] Traffic congestion prediction and avoidance function

[2177] Data collection and preprocessing

[2178] The server collects data on traffic conditions, weather information, and social media posts from news APIs (e.g., Google News API), weather APIs (e.g., OpenWeatherMap API), and social media APIs (e.g., Twitter API). The server sends requests to these APIs to retrieve the latest news articles, weather information, and social media posts every hour. The collected data is preprocessed using text analysis and data cleansing techniques. For news data, text mining techniques are used to extract information about traffic accidents and cleanse unnecessary information. For weather data, variables such as temperature, precipitation, and wind speed are analyzed to identify traffic-related factors.

[2179] Traffic congestion forecast

[2180] The server inputs the preprocessed data into a generative AI model (e.g., LSTM model) to predict traffic congestion. The generative AI predicts traffic conditions and calculates the probability of congestion occurring at a specific location and time. For example, it predicts that there is a 70% chance of congestion occurring on major road A at 8 a.m.

[2181] Evasion route calculation

[2182] The server calculates the optimal avoidance route based on the prediction results of the generative AI model. It uses the Google Maps API to obtain alternative route information and searches for and verifies routes with a low probability of congestion and accidents. The calculated avoidance route information is sent to the vehicle's navigation system.

[2183] User Notifications

[2184] The device will display the new route on the navigation screen and notify the user. For example, it will display a message such as, "Congestion is predicted on main road A, so we suggest a route via main road B." The user can then review the proposed route and approve it if necessary.

[2185] Providing a safe route

[2186] Accident data collection and analysis

[2187] The server extracts accident data for a specific area from a database of past accidents (e.g., a public traffic accident statistics database). The extracted accident data is input into a generative AI model to identify areas where accidents frequently occur. The server uses the generative AI model to calculate a safe route that avoids areas where accidents frequently occur. The calculated safe route information is sent to the vehicle's navigation system. The device notifies the user of the safe route and displays it on the navigation screen.

[2188] Real-time guide that takes into account individual interests

[2189] User Data Collection

[2190] The device collects data such as the user's age, hobbies, past driving history, etc. For example, if the user has set information such as "I like nature," the device sends that information to the server.

[2191] Generate individual driving routes

[2192] The server inputs the collected user data into a generative AI model to generate a driving course based on the user's hobbies and preferences. The generative AI then suggests routes that stop off at natural landscapes and specific tourist spots.

[2193] Providing tourist spot information

[2194] The server retrieves tourist spot information along the proposed driving course in real time. The tourist spot information is obtained from the tourist information API and sent to the device. The device then displays a notification to the user saying, "You will see a beautiful lake after passing the next curve."

[2195] Here are some example prompts to input to the generative AI model:

[2196] "Please explain a program that uses news APIs, weather APIs, and social media APIs to collect traffic information and use this data to predict congestion."

[2197] In this way, the user can enjoy a comfortable and safe drive.

[2198] The flow of the identification process in the first embodiment will be described with reference to FIG.

[2199] Step 1: Data collection

[2200] Input: Requests to the news API, weather API, or social media API

[2201] Processing: The server accesses these APIs to collect data on traffic conditions, weather information, and social media posts.

[2202] Output: Collected news data, weather data, and social media data

[2203] Specifically, the server sends a request to the API every hour to retrieve new news articles, the latest weather information, and the latest social media posts.

[2204] Step 2: Data Preprocessing

[2205] Input: Collected news data, weather data, and social media data

[2206] Processing: The server preprocesses the data using text analysis and data cleansing techniques. For example, it extracts information about traffic accidents from news data and removes unnecessary information. For weather data, it normalizes variables such as temperature, precipitation, and wind speed.

[2207] Output: Preprocessed and clean data

[2208] Specifically, the server uses a text mining algorithm to extract keywords related to traffic accidents from news articles, and only retains the necessary weather data.

[2209] Step 3: Traffic congestion prediction

[2210] Input: Preprocessed clean data

[2211] Processing: The server inputs the preprocessed data into a generative AI model (e.g., an LSTM model) to predict traffic congestion.

[2212] Output: Predicted probability of traffic jams

[2213] Specifically, the server converts the preprocessed data into tensor format and sends it to the generative AI model, which then obtains a prediction result such as "There is a 70% probability that traffic congestion will occur on major road A at 8 a.m."

[2214] Step 4: Calculate the optimal escape path

[2215] Input: Predicted result of traffic congestion probability

[2216] Processing: The server calculates the optimal avoidance route based on the prediction results of the generated AI model using Google Maps API etc.

[2217] Output: Calculated avoidance path information

[2218] Specifically, the server uses the Google Maps API to search for alternative routes to avoid areas where congestion is predicted, and finds the optimal avoidance route.

[2219] Step 5: Sending avoidance route information

[2220] Input: Calculated avoidance path information

[2221] Processing: The server sends the calculated avoidance route information to the vehicle's navigation system.

[2222] Output: Avoidance route information displayed on the vehicle navigation system

[2223] Specifically, the server sends an API request to the navigation system to transmit the new route information.

[2224] Step 6: User Notification

[2225] Input: Avoidance route information displayed on the vehicle navigation system

[2226] Processing: The terminal (vehicle navigation system) notifies the user of the new route.

[2227] Output: Avoidance route information displayed and notified to the user

[2228] Specifically, the navigation system will display a message on its screen saying, "Congestion is predicted on main road A, so we suggest a route via main road B," to notify the user.

[2229] Step 7: Collect and analyze accident data

[2230] Input: Past accident database

[2231] Processing: The server extracts accident data for specific areas from a database of past accidents and inputs it into a generative AI model to identify risky areas.

[2232] Output: Information on identified dangerous areas

[2233] Specifically, the server executes a query to retrieve accident information from the accident database for the past 10 years, and then analyzes it using an AI model to identify dangerous intersections and roads.

[2234] Step 8: Calculating a safe path

[2235] Input: Information on identified risk areas

[2236] Processing: The server uses the generative AI model to calculate a safe route that avoids accident-prone areas.

[2237] Output: Calculated safe route information

[2238] Specifically, the server inputs parameters to avoid dangerous areas into the generative AI model and generates a safe route.

[2239] Step 9: Send secure routing information

[2240] Input: Calculated safe route information

[2241] Processing: The server sends the calculated safe route information to the vehicle's navigation system.

[2242] Output: Safe route information displayed on the vehicle navigation system

[2243] Specifically, the server sends an API request to the navigation system again and transmits safe route information.

[2244] Step 10: Generate individual driving routes

[2245] Input: User's age, hobbies, past driving history

[2246] Processing: The device collects this data and sends it to a server. The server inputs the collected user data into a generative AI model to generate a driving course based on the user's hobbies and preferences.

[2247] Output: Generated driving course information

[2248] Specifically, the device collects user information such as "I like nature" and sends it to the server, which then uses a generative AI model to generate a driving course, for example, a "mountain route."

[2249] Step 11: Providing tourist spot information

[2250] Input: Generated driving course information

[2251] Processing: The server obtains tourist spot information along the proposed driving course in real time. It uses the tourist information API to obtain the spot information and sends it to the device.

[2252] Output: Tourist attraction information displayed on the vehicle navigation system

[2253] Specifically, the server obtains information such as "Once you go around the next curve, you will see a beautiful lake" and sends it to the terminal.

[2254] Step 12: User Notification

[2255] Input: Tourist attraction information displayed on vehicle navigation system

[2256] Processing: The terminal notifies the user of tourist spot information.

[2257] Output: Tourist spot information displayed and notified to the user

[2258] Specifically, the device displays a notification to the user saying, "Once you turn the next curve, you'll see a beautiful lake," allowing the user to enjoy the scenery.

[2259] (Application example 1)

[2260] 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."

[2261] Autonomous vehicles are expected to improve traffic congestion and road safety, and to provide a more comfortable driving experience for users. However, conventional technologies have had difficulty in effectively predicting congestion in real time, providing avoidance routes, and providing travel guidance based on users' hobbies and interests. Therefore, the present invention aims to solve these problems and make navigation systems for autonomous vehicles more advanced and useful for users.

[2262] 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.

[2263] In this invention, the server includes means for collecting news data, weather data, and social media data, means for preprocessing the collected data and inputting it into a generative AI model that predicts congestion, means for predicting congestion using the generative AI model and calculating an optimal avoidance route, means for transmitting the calculated avoidance route information to a mobile navigation system, means for the mobile navigation system to notify the user of the proposed avoidance route, means for collecting tourist spot information based on the user's hobbies and interests, means for inputting the collected tourist spot information into the generative AI model and generating travel guidance based on the user's interests, and means for transmitting the generated travel guidance to the mobile navigation system and notifying the user. This makes it possible to provide effective congestion predictions and avoidance routes in real time, and further makes it possible to provide travel guidance based on the user's hobbies and interests in real time.

[2264] "News data" refers to data containing the latest events and information distributed via the Internet or other information media.

[2265] "Weather data" refers to data that includes meteorological information such as temperature, humidity, precipitation, and wind speed.

[2266] "Social media data" refers to data that includes information such as text, images, and videos posted on SNS (social networking services).

[2267] A "generative AI model" is an algorithm that uses machine learning and deep learning to learn patterns from large amounts of data and makes predictions and generates data based on new data.

[2268] A "mobile navigation system" is a system installed in a vehicle or other mobile object that provides map information, route guidance, and traffic information.

[2269] "User" means an individual or group of people who use an automated driving vehicle.

[2270] "Hobbies" are activities or interests that a user is interested in and engages in for enjoyment.

[2271] "Tourist spot information" is data including the location, characteristics, and usage information of tourist spots and famous places.

[2272] "Travel guidance" is a service that provides information on routes to destinations and tourist spots, as well as guidance and advice to help users travel comfortably and enjoyably.

[2273] "Real-time" refers to a state in which current information can be processed immediately and provided without delay.

[2274] The present invention relates to a navigation system for autonomous vehicles. The system aims to improve traffic congestion and road safety and to provide a comfortable driving experience for users. Specific embodiments for carrying out the present invention will be described below.

[2275] System Configuration

[2276] The system according to the present invention includes the following main components:

[2277] server

[2278] Mobile navigation systems (vehicle navigation systems, smartphones, etc.)

[2279] Internet connection

[2280] News data, weather data, social media data APIs

[2281] Data collection

[2282] The server collects data in real time from news APIs, weather APIs, and social media APIs. The data is automatically retrieved via the internet, allowing you to get the latest traffic and weather information, as well as the information you need from social media posts.

[2283] Data Preprocessing

[2284] The server preprocesses the collected data, which includes removing unnecessary data and normalizing and cleaning the text, preparing the data for input into the generative AI model.

[2285] Traffic congestion prediction and calculation of avoidance routes

[2286] The server inputs the preprocessed data into a generative AI model to predict congestion. This generative AI model uses a machine learning algorithm and learns from past data. Based on the results of the congestion prediction, it calculates the optimal avoidance route.

[2287] Sending and notifying route information

[2288] The server sends the calculated avoidance route information to the mobile navigation system, which then notifies the user of the new route information. Notification methods include voice guidance and visual navigation displays.

[2289] Travel guides based on hobbies and interests

[2290] The server collects tourist spot information based on the user's hobbies and interests. The collected information is input into a generative AI model to generate travel guides based on the user's interests. The generated travel guides are sent to the mobile navigation system and notified to the user.

[2291] Hardware and software used

[2292] Hardware: Servers, smartphones, vehicle navigation systems

[2293] Software: Python, generative AI model, external API (news API, weather API, SNS API)

[2294] Specific examples

[2295] For example, while a user is on a long-distance drive, the server receives information from a news API that "an accident occurred on major road A." This information is analyzed by a generative AI model, which predicts that a traffic jam will occur on major road A. The server calculates an alternative route and sends it to the mobile navigation system. The mobile navigation system notifies the user of the new route, and the user accepts the suggestion and heads to their destination via the new route.

[2296] Additionally, while the user is enjoying their drive, the server collects information about the user's hobbies, and the generative AI model suggests driving routes with beautiful natural scenery based on the user's "love of nature" information. The server obtains tourist spot information in real time, and the mobile navigation system guides the user, saying, "Once you turn the next corner, you'll see a beautiful lake." In this way, users can enjoy a comfortable and safe drive.

[2297] Prompt Sentence Examples

[2298] Get the latest information on "traffic accidents" from the news API

[2299] Preprocess social media data to extract posts related to traffic congestion

[2300] Calculate the best route to avoid traffic congestion based on the results of generative AI models.

[2301] Notify your driver of new suggested routes

[2302] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[2303] Step 1:

[2304] The server collects data in real time from news APIs, weather APIs, and SNS APIs. Specifically, it sends requests to each API to collect news data, weather data, and social media data, and receives the acquired data. The input is the response data from each API, and the output is the collected news, weather, and SNS post data.

[2305] Step 2:

[2306] The server preprocesses the collected data. Data preprocessing includes removing unnecessary data, normalizing text, and cleaning. For example, summarizing news articles or extracting important parts of weather information. The input is the collected news, weather, and social media data, and the output is the preprocessed data.

[2307] Step 3:

[2308] The server inputs the preprocessed data into a generative AI model to perform congestion prediction. The generative AI model uses patterns learned from past data to predict future traffic congestion. The input is the preprocessed data, and the output is the congestion prediction result.

[2309] Step 4:

[2310] The server calculates the optimal avoidance route based on the congestion prediction results of the generated AI model. The avoidance route calculation also includes map database and road condition data. Specifically, a routing algorithm is used to calculate a route that avoids the predicted congestion. The inputs are the congestion prediction results, map data, and road condition data, and the output is information on the optimal avoidance route.

[2311] Step 5:

[2312] The server sends the calculated avoidance route information to the mobile navigation system. The sent avoidance route information is reflected in the navigation system display in real time. The input is the optimal avoidance route information, and the output is the route guidance information in the navigation system.

[2313] Step 6:

[2314] The terminal (mobile navigation system) notifies the user of the proposed avoidance route. This notification is done both audibly and visually. Specifically, the new route is displayed on the navigation screen and guided by voice. The input is the avoidance route information sent from the server, and the output is the notification and guidance to the user.

[2315] Step 7:

[2316] The server collects tourist spot information based on the user's hobbies and interests. For example, it obtains tourist spot information from the Internet and uses data that reflects the user's past driving history and interests. The input is the user's hobby data and tourist spot information, and the output is input data for the generative AI model.

[2317] Step 8:

[2318] The server inputs the collected information into a generative AI model to generate travel guides based on the user's interests. The generative AI model suggests optimal sightseeing routes and spots based on the user's hobbies and past history. The input is the collected user hobby data and tourist spot information, and the output is travel guide information.

[2319] Step 9:

[2320] The server sends the generated travel guide to the mobile navigation system and notifies the user. In this way, tourist information is provided in real time while traveling. Specifically, the navigation system displays information about tourist spots and provides audio guidance. The input is the generated travel guide, and the output is notifications and guidance for the user.

[2321] 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.

[2322] This invention relates to an autonomous driving system that improves traffic conditions and road safety and makes the user's driving experience more comfortable and emotionally satisfying. The system not only collects news data, weather data, and social media data and predicts traffic congestion using a generative AI model, but also includes an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's voice and facial expression data and provides personalized feedback and suggestions based on their emotional state.

[2323] Traffic congestion prediction and avoidance function

[2324] Data collection and preprocessing

[2325] 1. The server collects traffic and weather information, as well as real-time social media posting data, from news APIs, weather APIs, and social media APIs.

[2326] 2. The server preprocesses the collected data and performs text analysis and data cleansing.

[2327] Traffic congestion forecast

[2328] 3. The server inputs the preprocessed data into the generative AI model to perform congestion prediction.

[2329] 4. Generative AI predicts the probability of traffic jams occurring on highways and major intersections.

[2330] Evasion route calculation

[2331] 5. The server calculates the optimal avoidance path based on the prediction results of the generative AI model.

[2332] 6. The server sends the calculated avoidance route information to the vehicle navigation system (terminal).

[2333] User Notifications

[2334] 7. The device displays the new route on the navigation screen and notifies the user.

[2335] 8. The user reviews the proposed route and approves it if necessary.

[2336] Providing a safe route

[2337] Accident data collection and analysis

[2338] 1. The server extracts accident data for a specific area from a database of past accidents.

[2339] 2. The server uses a generative AI model to analyze the extracted accident data and identify risk areas.

[2340] Safe Route Calculation

[2341] 3. The server calculates a safe route that avoids accident-prone areas based on the generative AI model.

[2342] 4. The server sends the calculated safe route information to the vehicle navigation system (terminal).

[2343] User Notifications

[2344] 5. The device notifies the user of the safe route and displays it on the navigation screen.

[2345] 6. The user reviews the suggested safe routes and selects one.

[2346] Real-time guide that takes into account individual interests

[2347] User Data Collection

[2348] 1. The device collects data such as the user's age, hobbies, and past driving history.

[2349] 2. The device sends this data to the server.

[2350] Generate individual driving routes

[2351] 3. The server inputs the collected user data into a generative AI model and generates a driving course based on the user's hobbies and preferences.

[2352] 4. The generative AI suggests routes that stop off at natural landscapes and specific tourist spots.

[2353] Providing tourist spot information

[2354] 5. The server obtains real-time information about tourist spots along the proposed driving course.

[2355] 6. The server sends the tourist spot information to the vehicle navigation system (terminal).

[2356] User Notifications

[2357] 7. The device notifies the user of guide information such as, "The autumn leaves are beautiful on this road," or "A spectacular view will unfold once you turn the next corner."

[2358] 8. Users can enjoy real-time guidance while driving.

[2359] Incorporating an emotion engine

[2360] Collecting Emotional Data

[2361] 1. The device collects the user's voice and facial expression data in real time.

[2362] Emotion analysis

[2363] 2. The device uses an emotion engine that analyzes collected voice and facial expression data to recognize the user's emotions.

[2364] 3. The emotion engine identifies the user's current emotional state.

[2365] Route suggestions and content adjustments

[2366] 4. The server adjusts the generated avoidance routes and tourist information based on the emotional state recognized by the emotion engine.

[2367] 5. The server sends the adjusted route information and tourist information to the vehicle navigation system (terminal).

[2368] Specific examples

[2369] For example, while a user is driving on a major road, the server receives information from a news API that "an accident occurred on major road A." The generation AI analyzes this information, predicts that a traffic jam will occur on major road A, calculates an alternative route, and sends it to the device. The device then collects the user's voice data, and the emotion engine recognizes that the user is frustrated. Based on this information, the server suggests a scenic route that will allow the user to relax and notifies the user. The user then accepts the suggestion and heads to their destination via the new route. In this way, the user can enjoy a comfortable and safe drive.

[2370] The processing flow will be explained below.

[2371] Traffic congestion prediction and avoidance function

[2372] Data collection and preprocessing

[2373] Step 1:

[2374] The server collects the latest traffic data from the news API.

[2375] Step 2:

[2376] The server retrieves current and forecast weather information from a weather API.

[2377] Step 3:

[2378] The server collects real-time posting data from social media APIs.

[2379] Step 4:

[2380] The server preprocesses the collected news, weather, and social media data, removing unnecessary information and converting it into a unified format.

[2381] Traffic congestion forecast

[2382] Step 5:

[2383] The server inputs the preprocessed data into the generative AI model.

[2384] Step 6:

[2385] The generative AI analyzes the input data and predicts the probability of traffic jams occurring on highways and major intersections.

[2386] Evasion route calculation

[2387] Step 7:

[2388] The server calculates the optimal avoidance route based on the prediction results of the generative AI model.

[2389] Step 8:

[2390] The server transmits the calculated avoidance route information to the vehicle navigation system (terminal).

[2391] User Notifications

[2392] Step 9:

[2393] The device will display the new route on the navigation screen and notify the user.

[2394] Step 10:

[2395] The user reviews the proposed route and approves it if necessary.

[2396] Providing a safe route

[2397] Accident data collection and analysis

[2398] Step 1:

[2399] The server extracts accident data for a specific area from a database of past accidents.

[2400] Step 2:

[2401] The server uses a generative AI model to analyze the extracted accident data and identify risky areas.

[2402] Safe Route Calculation 【...

Claims

1. a means for collecting news data, weather data, and social media data; A means to preprocess the collected data and input it into a generative AI model that predicts congestion; A means of using generative AI models to predict congestion and calculate optimal avoidance routes; means for transmitting the calculated avoidance route information to a vehicle navigation system; A system including a vehicle navigation system that notifies a user of a suggested avoidance route.

2. A means of extracting past accident data around the destination; A means to input the extracted accident data into a generative AI model and calculate a safe route; means for transmitting the calculated safe route information to a vehicle navigation system; 10. The system of claim 1, wherein the vehicle navigation system includes means for notifying the user of suggested safe routes.

3. A means for collecting information about the user's age, hobbies, and past driving history; A means for inputting collected user data into a generative AI model to generate driving courses based on hobbies and preferences; A means for acquiring tourist spot information along the generated driving course; 2. The system according to claim 1, further comprising means for transmitting the acquired tourist spot information to a vehicle navigation system and notifying the user of the information. That's all.

Images