System

Abstract

To provide a system for effectively reducing accident risk.SOLUTION: A means for acquiring position information of a vehicle is provided. Next, a means for using artificial intelligence for predicting the movement of the vehicle based on the acquired position information is provided. Then, means for instructing the driver to take an avoidance action based on the information predicted by the artificial intelligence is provided. Further, the system is provided with a display means for visually presenting the avoidance action and a voice guide means for presenting it by voice, so that the driver can intuitively and quickly take an appropriate action.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] Recently, the incidence of traffic accidents remains high, and the main causes of accidents are driver misjudgment and delayed reactions, especially in vehicles that are not equipped with autonomous driving or driver assistance functions. Even in such vehicles, there is a strong demand for retrofit systems that can effectively reduce the risk of accidents. [Means for solving the problem]

[0005] In order to solve the above problems, the present invention provides the following means. First, a means for acquiring vehicle position information is provided. Next, a means for using artificial intelligence to predict vehicle movement based on the acquired position information is provided. Finally, a means for instructing the driver to take evasive action based on the information predicted by the artificial intelligence is provided. Furthermore, by providing a display means for visually presenting evasive action and an audio guidance means for audibly presenting the evasive action, a system is provided that allows the driver to intuitively and quickly take appropriate action.

[0006] "Means for obtaining vehicle location information" refers to devices and their functions, including GPS modules and sensors for obtaining the vehicle's current latitude and longitude.

[0007] "Artificial intelligence for predicting vehicle movements based on location information" refers to artificial intelligence that processes acquired location information as input data and has an algorithm that analyzes and predicts the vehicle's future location and behavior.

[0008] "Means for instructing the driver to take evasive action based on predicted information" refers to a system that includes a display or audio device to prompt the driver to perform specific operations or actions based on predicted vehicle movement and risk information.

[0009] "Visual display means" refers to a monitor or car navigation system that visually displays evasive action instructions in a form that is easily understandable to the driver.

[0010] "Audio guidance means for providing audio information" refers to a speaker or voice synthesis device that provides audio instructions to the driver on how to take evasive action. [Brief explanation of the drawings]

[0011] [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

[0012] 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.

[0013] First, the terms used in the following description will be explained.

[0014] 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).

[0015] 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.

[0016] 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.

[0017] 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.

[0018] 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."

[0019] [First embodiment]

[0020] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0021] 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.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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.

[0027] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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."

[0032] This invention is a system that predicts vehicle movements based on GPS information and provides specific instructions to the driver on how to avoid accidents. This system can be retrofitted to vehicles and is an effective means of supporting safe driving even in vehicles without driving assistance functions.

[0033] 1. Obtaining GPS information on the device

[0034] The device (smartphone or tablet) acquires the vehicle's current location in real time. To do this, the device is equipped with a GPS module and has the function of periodically acquiring the vehicle's current latitude and longitude. The acquired location information is sent to a server where it is used for analysis.

[0035] 2. Risk prediction by server

[0036] The server uses artificial intelligence (AI) to predict the vehicle's movements based on the GPS information sent from the device. The AI ​​learns from past data and surrounding traffic conditions, and uses this information to predict future movements with high accuracy. If the risk is deemed high, the server calculates specific evasive action. For example, if the AI ​​predicts that "there is a car rapidly approaching from the right rear of the vehicle," it will use that information to calculate "changing to the left lane" as an evasive action.

[0037] 3. Display and audio guidance on terminals

[0038] The device displays the evasive maneuvers sent from the server on the car navigation system or display. It also uses voice guidance to guide the driver in evasive maneuvers. Specifically, the device gives the driver easy-to-understand instructions, such as, "A vehicle is rapidly approaching from the rear right. Slow down and move to the left."

[0039] As a concrete example, consider the following scenario:

[0040] Real-life scenario:

[0041] The device obtains location information of latitude: 35.6895, longitude: 139.6917 and sends it to the server.

[0042] The server analyzes the new location information and surrounding traffic data and uses an AI model to predict the risk to the vehicle, such as a vehicle rapidly approaching from the right rear.

[0043] The server calculates that "changing to the left lane" is the optimal avoidance action and transmits this avoidance action to the terminal.

[0044] The device will display evasive action on the car navigation display and provide a voice message saying, "Please change to the left lane."

[0045] The driver will then confirm this and follow the instructions to move into the left lane to avoid any risk.

[0046] In this way, the system, which can be retrofitted into vehicles, enables drivers to take appropriate evasive action in real time, significantly reducing the risk of traffic accidents.

[0047] The processing flow will be explained below.

[0048] Step 1:

[0049] The terminal uses a GPS module to obtain the vehicle's current location, which is expressed in the form of latitude and longitude and is updated periodically.

[0050] Step 2:

[0051] The device sends the acquired location information to the server using a communication protocol (e.g., HTTP or WebSocket).

[0052] Step 3:

[0053] The server uses artificial intelligence (AI) to predict vehicle movements based on the received GPS information, integrating and analyzing past data and surrounding traffic information.

[0054] Step 4:

[0055] If the risk is deemed high based on the risk level calculated by the AI, the server calculates the optimal avoidance action. For example, if a vehicle is rapidly approaching from the rear right, the server will recommend slowing down and moving to the left.

[0056] Step 5:

[0057] The server then transmits the calculated evasive maneuvers to the device, again using a pre-configured communication protocol.

[0058] Step 6:

[0059] The device receives the evasive action from the server and displays it on the car navigation display, allowing the driver to visually confirm the evasive action.

[0060] Step 7:

[0061] At the same time, the device uses its voice guidance function to provide specific evasive maneuvers, such as "change to the left lane," through a speaker.

[0062] Step 8:

[0063] The user (driver) checks the presented visual and audio instructions and takes appropriate evasive action, such as changing lanes to the left or slowing down.

[0064] This series of processes allows drivers to take appropriate evasive action in real time, reducing the risk of traffic accidents.

[0065] Example 1

[0066] 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."

[0067] Many current vehicles do not have driving assistance functions, and drivers of these vehicles lack the information necessary for safe driving. This leaves them unable to respond to unexpected traffic situations, increasing the risk of accidents. In particular, it is difficult to predict the movement of one's own vehicle and the surrounding traffic conditions in real time and take appropriate evasive action. Therefore, there is a need for technology that can be easily installed even in vehicles without driving assistance functions and that can effectively instruct drivers on how to avoid accidents.

[0068] 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.

[0069] In this invention, the server includes a location information acquisition means for acquiring current location information of the vehicle, a prediction means for using a generative AI model to predict the future movement of the vehicle based on the location information, and an instruction means for instructing the driver on specific avoidance behavior based on the movement predicted by the generative AI model. This allows for easy installation even in vehicles without driving assistance functions, and makes it possible to instruct the driver on appropriate accident avoidance behavior in real time.

[0070] "Location information acquisition means" refers to a device or function for measuring the current location of the vehicle and transmitting that location information to a server.

[0071] A "generative AI model" is a model built on artificial intelligence technology that learns from past data and current situations to predict future behavior.

[0072] "Prediction means" refers to a device or function that uses a generative AI model to predict the future behavior of a vehicle.

[0073] "Instruction means" refers to devices or functions that instruct the driver to take evasive action based on information predicted by the generative AI model.

[0074] "Display means" refers to a display device or function for visually presenting avoidance actions.

[0075] "Voice guidance means" refers to devices or functions that verbally inform the driver of evasive action.

[0076] "GPS module" refers to a receiver for the satellite positioning system that precisely measures one's position on Earth.

[0077] An "artificial intelligence framework" refers to a software environment that supports the building and learning of generative AI models.

[0078] This invention is a system that predicts vehicle movements based on GPS information and instructs the driver on specific actions to avoid accidents. This system can be retrofitted to vehicles and provides an effective means of supporting safe driving even in vehicles without driving assistance functions.

[0079] First, the terminal (smartphone or tablet) obtains the vehicle's current location in real time. To do this, the terminal is equipped with a GPS module that periodically calculates the current latitude and longitude and transmits the obtained location information to a server. The specific hardware used is a smartphone or tablet, and the software includes a GPS module.

[0080] The server then receives the GPS information sent from the device and uses an artificial intelligence (AI) model to predict the vehicle's future movements. The AI ​​model learns from past data and surrounding traffic conditions, and uses this information to predict future movements with high accuracy. The specific AI framework used is a generative AI model built using TensorFlow, PyTorch, and other frameworks.

[0081] The server then instructs the driver on evasive action based on the predicted risk information. For example, if the AI ​​model predicts that a vehicle is rapidly approaching from the right rear of the vehicle, the server calculates that the optimal evasive action is to change to the left lane and sends that instruction to the device.

[0082] The device receives instructions for evasive action sent from the server and displays them on the car navigation system or display. It also uses voice guidance to guide the driver through specific evasive actions. For example, it may provide a voice message such as, "A vehicle is rapidly approaching from the rear right. Slow down and move to the left."

[0083] As a concrete example, consider the following scenario:

[0084] The device obtains its current location information (latitude: 35.6895, longitude: 139.6917) and sends it to the server.

[0085] The server analyzes the new location information and surrounding traffic data and uses an AI model to predict the risk of a vehicle rapidly approaching from the right rear.

[0086] The server calculates that "changing to the left lane" is the optimal avoidance action and sends that instruction to the terminal.

[0087] The terminal displays instructions from the server on the car navigation display and provides a voice message saying, "Please change to the left lane."

[0088] The driver sees this instruction and moves to the left lane to avoid the risk.

[0089] An example prompt might look like this:

[0090] "Predict the vehicle's movement based on the following latitude and longitude location information. Latitude: 35.6895, Longitude: 139.6917. Please explain in detail the evasive action you would take if a vehicle were rapidly approaching from the right rear."

[0091] This makes it possible to easily install the system even in vehicles that do not have driving assistance functions, and it is possible to instruct the driver on appropriate accident avoidance actions in real time.

[0092] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0093] Step 1:

[0094] Activating the GPS module on the device

[0095] The terminal activates the built-in GPS module. This module receives signals from satellites and obtains the vehicle's current position (latitude and longitude). Specifically, it utilizes the GPS function of a smartphone or tablet. The input is a signal from a GPS satellite, and the output is the current position information (latitude and longitude).

[0096] Step 2:

[0097] Acquisition and transmission of location information by the device

[0098] The device periodically collects the current latitude and longitude and sends them to the server. For example, if the device obtains vehicle position information of latitude 35.6895 and longitude 139.6917, it sends this information to the server via the Internet. The input is the position information from the GPS module, and the output is the position information sent to the server.

[0099] Step 3:

[0100] Receiving and storing location information by the server

[0101] The server receives the location information sent from the device and stores it in a database in real time. The input is the location information sent from the device, and the output is the location information stored in the database.

[0102] Step 4:

[0103] Server calls the generated AI model

[0104] The server calls a generative AI model based on the received location information to predict the vehicle's future movements. The generative AI model is built using an AI framework such as TensorFlow or PyTorch. The input is location information, and the output is predicted risk information.

[0105] Step 5:

[0106] Server predicts risk and calculates avoidance actions

[0107] The generative AI model receives past traffic data and current location information as inputs and predicts risks. For example, if it predicts that "there is a vehicle rapidly approaching from the rear right," it uses that information to calculate the optimal evasive action to "change to the left lane." The inputs are location information and past traffic data, and the output is specific instructions for evasive action.

[0108] Step 6:

[0109] Server sends evasive action instructions

[0110] The server sends the calculated avoidance action instructions to the terminal. The input is the avoidance action instructions calculated by the server, and the output is the avoidance action instructions sent to the terminal.

[0111] Step 7:

[0112] Display of avoidance actions on the device

[0113] The terminal receives the evasive action instructions sent from the server and displays them on the car navigation system or display. For example, it displays a message such as "Please change to the left lane." The input is the evasive action instructions sent from the server, and the output is the evasive action instructions displayed on the display.

[0114] Step 8:

[0115] Voice guidance provided by the device

[0116] The terminal also provides voice guidance based on the received instructions for evasive action. Specifically, it plays a message such as, "A vehicle is rapidly approaching from the rear right. Slow down and move to the left." The input is the instruction for evasive action sent from the server, and the output is voice guidance.

[0117] Step 9:

[0118] User performs avoidance action

[0119] The user (driver) confirms the instructions from the terminal and takes specific avoidance action, such as changing to the left lane. The input is the avoidance action instruction from the terminal, and the output is the actual avoidance action.

[0120] (Application example 1)

[0121] 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."

[0122] Although autonomous vehicle technology has made remarkable advances in recent years, it remains difficult to completely eliminate the risk of unexpected traffic accidents. There is also a growing demand for advanced risk avoidance systems to ensure the safety of drivers and passengers. Such systems must provide comprehensive driving assistance, including real-time location information acquisition, traffic situation analysis, and prompt instruction on evasive action. Conventional technologies rely primarily on information from sensors inside the vehicle, making it difficult to grasp the overall picture of traffic conditions. Furthermore, there is a risk that accidents cannot be avoided due to delayed instruction on evasive action. There is a need to resolve these issues and provide safer and more reliable driving assistance systems.

[0123] 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.

[0124] In this invention, the server includes a means for transmitting vehicle location information and surrounding traffic data to a central server, calculating risk predictions and avoidance actions, a means for feeding back the calculated avoidance actions to the automated driving system, and a means for presenting the avoidance actions on a display and by voice. This makes it possible to reduce accident risk by analyzing traffic conditions in real time and prompting appropriate avoidance actions based on the predictions. Furthermore, the accuracy and reliability of avoidance actions are significantly improved by using a generative AI model for analysis and the creation of prompts.

[0125] "Vehicle location information" is data on the latitude and longitude of the vehicle's current location.

[0126] "Artificial intelligence" refers to the technology that allows computer systems to mimic human intelligence, in this case to predict vehicle behavior.

[0127] "Avoidance actions" refer to driving maneuvers and actions taken by a vehicle to prevent an accident from occurring.

[0128] "Central server" refers to a computer server that receives and analyzes all data sent from vehicles and calculates evasive actions.

[0129] "Risk prediction" refers to the use of artificial intelligence to predict possible future dangers based on the vehicle and its surrounding traffic conditions.

[0130] "Display" means a display device used to visually present information regarding evasive maneuvers to the driver.

[0131] "Voice guidance means" refers to a means for providing audible instructions for evasive action to the driver.

[0132] A "generative AI model" is an artificial intelligence model trained using large amounts of learning data, and is capable of predicting risks and calculating avoidance actions with high accuracy.

[0133] "Prompt sentence" refers to an instruction sentence created by a generative AI model for an autonomous driving system.

[0134] As a concrete example for implementing this invention, we will explain the "Safety Assistance System (AOSS)" applied to autonomous vehicles. This system provides the function of predicting risks based on the vehicle's position information and instructing appropriate avoidance actions.

[0135] Generating a Program

[0136] First, the vehicle acquires real-time location information using a GPS module. This location information is then transmitted from a device inside the vehicle (e.g., a car navigation system or dedicated tablet) to a central server. The central server analyzes the received location information and surrounding traffic data, and performs risk prediction using a generative AI model (e.g., using TensorFlow or PyTorch).

[0137] If the central server detects a risk, it calculates evasive action. The calculated evasive action (e.g., lane change, speed adjustment) is fed back to the autonomous driving system and reflected in vehicle control. The evasive action is also displayed visually on the in-car display and instructed to the driver audibly through the voice guidance system (e.g., linked to Google Assistant or Amazon Alexa).

[0138] Detailed system description

[0139] 1. Obtaining real-time GPS information

[0140] The server uses a GPS module to obtain the vehicle's latitude and longitude, and the obtained location information is sent to a central server.

[0141] 2. Risk prediction by a central server

[0142] The central server receives location information and other surrounding traffic data (such as the location and speed of surrounding vehicles) and predicts future risks using a generative AI model that is trained on a large amount of learning data.

[0143] 3. Calculation and avoidance behavior generation

[0144] If a risk is detected, the central server calculates the optimal avoidance action and sends information about the avoidance action to the automated driving system.

[0145] 4. Display and audio guidance

[0146] Evasive maneuvers are visually displayed on the in-car display, and the driver is given instructions via the voice guidance system. For example, a message saying "Please change to the left lane" is displayed on the display, and the driver is notified with a message such as "A vehicle is rapidly approaching from the rear right. Slow down and move to the left."

[0147] Specific examples

[0148] As a concrete example, consider the following scenario:

[0149] The vehicle sends its location information: latitude 35.6895, longitude 139.6917 to the central server.

[0150] The server analyzes surrounding traffic data and predicts that "there is a vehicle rapidly approaching from the rear right."

[0151] The server calculates "changing to the left lane" as an evasive maneuver and sends this information to the autonomous driving system.

[0152] The in-car display will show a message saying "Please change to the left lane," and the voice guidance system will inform the driver, "A vehicle is rapidly approaching from the rear right. Please slow down and move to the left."

[0153] The driver will then confirm this and follow the instructions to move into the left lane to avoid any risk.

[0154] Prompt Sentence Examples

[0155] Examples of prompts are:

[0156] "New location information acquired. Latitude: 35.6895, Longitude: 139.6917. Analyze surrounding traffic conditions and perform risk prediction. If there is a vehicle approaching quickly from the rear right, generate an instruction to change to the left lane as an evasive action."

[0157] In this way, the technology of the present invention can be applied to autonomous vehicles and contribute to improving safety.

[0158] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0159] Step 1:

[0160] The terminal uses the GPS module to obtain the vehicle's current location (latitude and longitude) in real time. Specifically, the terminal periodically reads data from the GPS module to obtain the current latitude and longitude information. This location information becomes the input data for the system.

[0161] Step 2:

[0162] The device transmits its current location information to a central server using an internet connection and sending the data as a POST request via a RESTful API. Specifically, the device sends latitude and longitude data in JSON format to the server.

[0163] Step 3:

[0164] The server collects surrounding traffic data based on the received location information. Based on the location information, the server uses external APIs to obtain current traffic conditions and the locations of nearby vehicles. At this stage, the server integrates all the acquired data and creates an input dataset for prediction.

[0165] Step 4:

[0166] The server uses the generative AI model to perform risk prediction. Specifically, it inputs acquired location information and surrounding traffic data into the AI ​​model to calculate future risks. The generative AI model is trained based on past learning data and makes highly accurate predictions based on the input data. The output includes information on when a risk is detected and suggested avoidance actions to address that risk.

[0167] Step 5:

[0168] The server feeds back the calculated evasive maneuvers to the autonomous driving system and the device. The server sends the evasive maneuver information in JSON format to the autonomous driving system and also sends the same information to the device. Specifically, the feedback information from the server includes instructions for lane changes and speed adjustments.

[0169] Step 6:

[0170] The device displays information on evasive action visually and provides audio guidance. The device then displays the received instructions on the screen and communicates them to the driver using the voice guidance system. Specifically, the display will show the message "Change to the left lane," and the voice guidance system will notify the driver, "A vehicle is rapidly approaching from the rear right. Slow down and move left."

[0171] Step 7:

[0172] The user (driver) follows the displayed avoidance action instructions and performs appropriate driving maneuvers. The driver follows the display and voice guidance to take driving actions such as changing lanes and adjusting speed. At this stage, the user actually takes action to avoid risk.

[0173] 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.

[0174] This invention is a system that predicts vehicle movement based on GPS information and instructs the driver to take action to avoid accidents. Furthermore, this system incorporates an emotion engine that recognizes the user's emotions, allowing it to provide flexible avoidance instructions according to the user's emotional state. This system can be retrofitted into automobiles, providing high safety even in vehicles without driving assistance functions.

[0175] 1. Obtaining GPS information on the device

[0176] The device (smartphone or tablet) acquires the vehicle's current location in real time. The device uses a GPS module to periodically acquire current location information in the form of latitude and longitude. The acquired location information is sent to a server where it is used for analysis.

[0177] 2. Risk prediction by server

[0178] The server uses artificial intelligence (AI) to predict vehicle movements based on GPS information sent from the device. The AI ​​learns from past data and surrounding traffic conditions to predict future movements with high accuracy. If a risk is determined to be high, the server calculates specific evasive actions.

[0179] 3. Understanding user state using emotion engine

[0180] The device is equipped with a camera and sensors to recognize the user's emotions. Using these sensors, the device grasps the user's emotional state in real time through facial recognition and voice analysis. The emotion engine analyzes whether the user is in a stressed or relaxed state and sends that information to the server.

[0181] 4. Server-based coordination of evasive actions

[0182] The server adjusts the instructions and methods for avoidance actions based on the user's emotional information obtained from the emotion engine. For example, if the user is feeling stressed, the server will devise ways to alleviate anxiety by giving instructions in a relaxed tone.

[0183] 5. Display and audio guidance on terminals

[0184] The device displays the evasive action sent from the server on the car navigation display. It also uses voice guidance adjusted based on the user's emotional state to guide the driver through the evasive action. For example, the device may display and voice instructions such as "A vehicle is rapidly approaching from the rear right. Slow down and move to the left." If the user is feeling stressed, the device may provide guidance in a gentler voice.

[0185] As a concrete example, consider the following scenario:

[0186] Real-life scenario:

[0187] The device obtains location information of latitude: 35.6895, longitude: 139.6917 and sends it to the server.

[0188] The server analyzes the new location information and surrounding traffic data and uses an AI model to predict the risk to the vehicle, such as a vehicle rapidly approaching from the right rear.

[0189] The emotion engine recognizes the user's face and determines that the user is in a stressful state.

[0190] Based on the information that "the user is in a stressful state," the server decides to take the evasive action of "changing to the left lane" and provides guidance in a gentle voice.

[0191] The device displays the message "Please change to the left lane" on the car navigation display and provides voice guidance in a gentle voice saying, "When changing to the left lane, reduce your speed and proceed slowly."

[0192] The driver will then confirm this and follow the instructions to move into the left lane to avoid any risk.

[0193] In this way, by combining a system that can be retrofitted into vehicles with emotion analysis using an emotion engine, drivers can take appropriate, emotion-sensitive evasive action in real time, significantly reducing the risk of traffic accidents.

[0194] The processing flow will be explained below.

[0195] Step 1:

[0196] The device uses a GPS module to obtain the vehicle's current location, which is obtained as latitude and longitude and updated periodically over time.

[0197] Step 2:

[0198] The device sends the acquired location information to the server using a transmission protocol (e.g., HTTP, WebSocket).

[0199] Step 3:

[0200] The server uses artificial intelligence (AI) to predict vehicle movements based on the received GPS information, and the AI ​​performs analysis based on past data and surrounding traffic conditions.

[0201] Step 4:

[0202] The device uses cameras and sensors to recognize the user's face and perform voice analysis, and analyzes their emotions in real time, with an emotion engine identifying emotional states such as stress or relaxation.

[0203] Step 5:

[0204] The terminal transmits the identified user's emotion information to the server.

[0205] Step 6:

[0206] The server calculates the optimal avoidance action based on the risk level calculated by the AI ​​when the risk is deemed high. For example, if a vehicle is predicted to be rapidly approaching from the rear right, it will recommend changing to the left lane.

[0207] Step 7:

[0208] The server adjusts the instructions and methods for avoidance actions based on the user's emotional information. For example, if the user is feeling stressed, the server will set the instructions to be given in a relaxed tone.

[0209] Step 8:

[0210] The server transmits the calculated avoidance actions to the terminal.

[0211] Step 9:

[0212] The device then displays the received instructions for avoidance actions on the car navigation display, with specific instructions visually displayed.

[0213] Step 10:

[0214] The device uses a voice guidance function to inform the user of specific avoidance actions, such as "A vehicle is rapidly approaching from the rear right. Slow down and move to the left."

[0215] Step 11:

[0216] The user checks the displayed instructions and audio guidance and takes appropriate evasive action, such as changing to the left lane or slowing down.

[0217] This series of processes allows users to take appropriate avoidance actions in real time based on their own emotions, reducing the risk of traffic accidents.

[0218] Example 2

[0219] 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."

[0220] Conventional vehicle driving assistance systems were able to predict risks and provide instructions for evasive action based on vehicle position information, but they were unable to adjust their instructions to take into account the driver's emotional state. This could lead to the driver continuing to drive while feeling stressed, increasing the risk. Therefore, a system is needed that can recognize the driver's emotional state and provide instructions for evasive action accordingly.

[0221] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0222] In this invention, the server includes means for acquiring vehicle position information, means for using artificial intelligence to predict vehicle movement based on the position information, means for instructing the driver to take avoidance action based on the information predicted by the artificial intelligence, sensor means for recognizing the emotional state of the user, and means for adjusting the avoidance action based on the emotional state of the user, thereby making it possible to instruct appropriate avoidance action according to the emotional state of the driver.

[0223] "Vehicle location information" is data indicating the vehicle's current latitude and longitude, and is obtained from a GPS module or the like.

[0224] "Artificial intelligence for predicting vehicle movement" refers to algorithms and systems that can predict future vehicle movement with high accuracy by learning from past data and current traffic conditions.

[0225] "Means for instructing the driver to take evasive action" refers to means for visually or audibly instructing the driver to take specific evasive action based on the results of predicting the vehicle's movement.

[0226] "Sensor means" refers to devices such as cameras and microphones for recognizing the user's emotional state.

[0227] "User's emotional state" is information that indicates the psychological state, such as stress or relaxation, that the user is currently feeling.

[0228] The "means for adjusting avoidance behavior" is a means for appropriately changing the content of avoidance behavior and the method of instruction according to the emotional state of the user.

[0229] "Display means" refers to a screen, monitor, or the like that visually presents avoidance actions to the user.

[0230] The "voice guidance means" refers to a speaker or voice synthesis system that uses voice to guide the user on how to take evasive action.

[0231] This invention is a system that acquires the current location of a vehicle, predicts risks, and instructs the driver to take evasive action. This system includes a function that recognizes the user's emotional state and provides instructions according to the emotion. The specific configuration and processing method of the hardware and software for implementing this system are described below.

[0232] Hardware and Software Configuration

[0233] Terminal

[0234] GPS module: Obtains the vehicle's current location in real time.

[0235] Camera: Used for facial recognition and analyzing the user's emotional state.

[0236] Microphone: Used to collect voice data and analyze emotions from the user's voice.

[0237] Display: A display device that visually instructs the driver on evasive action.

[0238] Speaker: An audio output device for providing audio guidance.

[0239] server

[0240] AI model (using TensorFlow, for example): Used to predict vehicle behavior.

[0241] Emotion engine (using Scikit-learn, for example): Analyzes the user's emotional state and adjusts avoidance behavior based on that information.

[0242] Database: Stores historical traffic and location data and uses it to train AI models.

[0243] Processing flow

[0244] This system operates in the following manner.

[0245] 1. Obtaining GPS information on the device

[0246] The terminal uses a GPS module to obtain the vehicle's current location and transmits it to the server as latitude and longitude data.

[0247] 2. Risk prediction by server

[0248] The server inputs the received GPS information into an AI model to predict the vehicle's future movements. If there is a risk, it generates specific risk information, such as "A vehicle is rapidly approaching from the rear right."

[0249] 3. Understanding user state using emotion engine

[0250] The device uses a camera and microphone to analyze the user's emotional state, recognizing whether the user is stressed or relaxed from facial expressions and voice, and sends that information to a server.

[0251] 4. Server-based coordination of evasive actions

[0252] The server adjusts the avoidance behavior based on the risk information and the user's emotional state. For example, if the user is stressed, the server will set the instructions to be given in a gentle tone.

[0253] 5. Display and audio guidance on terminals

[0254] The device displays the evasive actions sent from the server on its display and provides voice guidance through the speaker. For example, it displays specific instructions such as "Please change to the left lane," and then provides gentle voice guidance such as "When changing to the left lane, please reduce your speed and proceed slowly."

[0255] Specific examples

[0256] Real-life scenario

[0257] Obtaining and sending location information: The device obtains location information of latitude: 35.6895, longitude: 139.6917 and sends it to the server.

[0258] Risk prediction: The server analyzes new location information and surrounding traffic data and predicts that a vehicle is rapidly approaching from the right rear.

[0259] Emotion Recognition: The emotion engine recognizes the user's face and determines that the user is in a stressful state.

[0260] Adjusting evasive behavior: The server decides to instruct the user to change to the left lane using a gentle voice based on the user's emotional state.

[0261] Provides visual and audio guidance: The device displays the message "Please change to the left lane" on the car navigation display and provides gentle audio guidance such as "When changing to the left lane, reduce your speed and proceed slowly."

[0262] Prompt Sentence Examples

[0263] The user's location information was sent: latitude: 35.6895, longitude: 139.6917. Based on historical data and current traffic conditions, predict vehicle movements and suggest specific avoidance actions if there is a risk. Also, take into account the user's emotional state and adjust the content and tone of instructions as needed. For example, if the user is stressed, provide instructions in a calm voice.

[0264] In this way, the present invention is a system that can significantly reduce the risk of traffic accidents by providing appropriate avoidance actions based on the vehicle's current location and the user's emotional state.

[0265] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0266] Step 1: Get GPS information from your device

[0267] Input: Real-time location information obtained by the GPS module

[0268] Operation: The device uses the GPS module to obtain the vehicle's current location as latitude and longitude data, once per second.

[0269] Data processing: The acquired location data is temporarily stored in local storage and converted into an HTTP POST request format.

[0270] Output: Latitude and longitude location data sent to the server as an HTTP POST request

[0271] Step 2: Risk prediction by the server

[0272] Input: GPS location information sent from the device

[0273] How it works: The server inputs the received location information into an AI model (TensorFlow), which predicts the vehicle's future movements based on past data and current traffic conditions.

[0274] Data calculation: The AI ​​model uses a neural network to assess risk based on input location information and output a prediction such as "there is a vehicle rapidly approaching from the rear right."

[0275] Output: Predicted risk information (e.g., sudden approach from the rear right)

[0276] Step 3: Understanding the user's state using the emotion engine

[0277] Input: User's facial image and voice data acquired from the device's camera and microphone

[0278] How it works: The device uses the camera to recognize the user's face and the microphone to collect voice data. It uses the OpenCV library for face recognition and the Google Cloud Speech-to-Text API to convert the voice to text.

[0279] Data processing: Facial expressions and voice data are input into a machine learning model (Scikit-learn) to analyze whether the user is in a stressed or relaxed state.

[0280] Output: User's emotional state (e.g., stress state) as a result of the analysis

[0281] Step 4: Server Coordination of Evasive Behavior

[0282] Input: Risk prediction results and user's emotional state

[0283] How it works: The server adjusts the avoidance behavior based on the risk prediction result and the user's emotional state. For example, if the user is stressed, the server will set the tone to be gentler and give avoidance instructions.

[0284] Data Calculation: Determines customized content and audio tone of avoidance actions based on specific conditions.

[0285] Output: Coordinated evasive maneuver instructions (e.g., a gentle voice prompt saying "Move to the left lane")

[0286] Step 5: Display and voice guidance on the device

[0287] Input: Adjusted evasive maneuver instructions sent from the server

[0288] Operation: The device displays instructions from the server on the screen and provides voice guidance using a speech synthesis engine (Google Text-to-Speech).

[0289] Data processing: Evasive action instructions from the server are visually displayed on a GUI and audio data is generated.

[0290] Output: Visual instructions on the display and voice guidance from the speaker (e.g., a calm voice saying "Please change to the left lane")

[0291] This series of steps allows the system to provide the driver with targeted, risk-minimizing evasive action based on both the vehicle's current location and the user's emotional state.

[0292] (Application example 2)

[0293] 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."

[0294] Conventional driving assistance systems provide instructions for accident avoidance actions based on the vehicle's movement, but they have the problem of being unable to provide appropriate instructions based on the driver's emotional state. As a result, if the driver is stressed or nervous, the instructions may not be communicated effectively, which may reduce the effectiveness of accident avoidance. In addition, avoidance actions based solely on visual displays and audio guidance have the problem of being difficult to provide appropriate support tailored to the individual driver's situation.

[0295] 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 acquiring vehicle position information, means for using artificial intelligence to predict vehicle movement based on the position information, means for instructing the driver to take evasive action based on the information predicted by the artificial intelligence, means for acquiring the user's emotional state using an emotion engine that recognizes the user's emotions, and means for adjusting the content and method of instructions for evasive action based on the emotional state. This makes it possible to instruct evasive action flexibly and effectively according to the driver's emotional state.

[0296] "Vehicle location information" refers to data on the current latitude and longitude of a vehicle obtained using a positioning system such as a GPS.

[0297] "Artificial intelligence" refers to computational techniques and algorithms that predict a vehicle's future movements based on historical data and current traffic conditions.

[0298] "Means for instructing the driver to take evasive action" refers to a system that has the function of instructing the driver to take appropriate evasive action based on predicted risk information.

[0299] An "emotion engine" is a combination of software and hardware that performs facial recognition and voice analysis of the user to recognize their emotional state in real time.

[0300] "Emotional state" refers to the mental state of the driver, such as stress or relaxation.

[0301] "Display means" refers to a device or system for visually presenting information, and typically includes a car navigation display or a smartphone screen.

[0302] "Audio guidance means" refers to a device or system for providing information or instructions by voice through a speaker or earphone.

[0303] "Means for adjusting the content and method of instructions for avoidance behavior" refers to a system for changing the specific content of instructions for avoidance behavior and the method of conveying them based on the user's emotional state.

[0304] This invention is a system for tracking a vehicle's position in real time and providing driving assistance, particularly a system that can take into account the driver's emotional state and provide flexible evasive maneuvers.

[0305] First, the device (e.g., a smartphone) uses a GPS module to obtain the vehicle's location information (latitude and longitude). This location information is periodically sent to a server. The server then uses artificial intelligence (AI) to predict the vehicle's future movements based on the received location information. In this case, the AI ​​uses a model that has learned from past data and current traffic conditions.

[0306] Next, the emotion engine uses the device's camera and microphone to analyze the driver's emotional state in real time. For example, it uses facial recognition to determine stress or relaxation from facial expressions. It also uses voice analysis to estimate the driver's emotions from the way they speak and their tone of voice. This information is sent to the server.

[0307] The server integrates the predicted vehicle movement results with the driver's emotional state to calculate the optimal evasive action. If the driver is feeling stressed, it is important to give instructions in a tone that will help them relax. For example, the device might display a message on the car navigation display saying, "A vehicle is rapidly approaching from the rear right. Please slow down and move to the left," and provide voice guidance in a calm voice saying, "When changing to the left lane, please slow down and move slowly."

[0308] This system enables flexible accident avoidance by taking into account the user's emotional state. The specific hardware used is a smartphone, with a built-in camera, microphone, and display. The software uses a GPS module, OpenCV (for emotion recognition), Google Cloud Speech-to-Text API (for voice analysis), and Flask (for server-side processing).

[0309] As a concrete example, let's say a user is feeling stressed while driving. The device acquires location information of latitude: 35.6895, longitude: 139.6917 and sends it to the server. The server analyzes the new location information and surrounding traffic data and predicts the risk of "a vehicle rapidly approaching from the rear right." The emotion engine recognizes the user's face and determines that the user is in a stressed state. Based on the information that "the user is in a stressed state," the server decides to "change to the left lane" and provides guidance in a calm voice. The device displays the message "Please change to the left lane" on the car navigation display and provides voice guidance in a calm voice, "When changing to the left lane, please reduce your speed and proceed slowly."

[0310] Example prompt sentence:

[0311] "Your current location is latitude 35.6895, longitude 139.6917. You are in a stressed state. A vehicle is approaching you from behind on the right. Please slow down and move to the left. When changing to the left lane, slow down and move slowly."

[0312] In this way, the driver can receive appropriate accident avoidance instructions according to their emotional state, improving safety.

[0313] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0314] Step 1:

[0315] The terminal uses the GPS module to obtain the vehicle's current location information. At that time, it obtains latitude and longitude data and temporarily stores this information inside the terminal. The input of this step is GPS data, and the output is the vehicle's current location information.

[0316] Step 2:

[0317] The device sends the acquired location information to the server. It uses an HTTP POST request to send the vehicle's latitude and longitude to the server. The input of this step is the location information stored inside the device, and the output is the location information sent to the server.

[0318] Step 3:

[0319] The server receives the location information sent from the device. It uses artificial intelligence (AI) to predict the vehicle's future movements based on the received location information. In this process, it also analyzes past data and current traffic conditions. The input of this step is the received location information and past traffic data, and the output is the predicted future movements.

[0320] Step 4:

[0321] The device uses a camera and microphone to acquire the driver's emotional state. Specifically, it performs facial recognition using the camera and voice analysis using the microphone, and passes the results to the emotion engine. The input of this step is camera image and voice data, and the output is emotional state data.

[0322] Step 5:

[0323] The emotion engine analyzes the acquired facial recognition data and voice data to determine the driver's emotional state, such as stress or relaxation, and sends that information to the server. The input to this step is the emotional state data analyzed by the emotion engine, and the output is the emotional state information sent to the server.

[0324] Step 6:

[0325] The server calculates the optimal avoidance action based on the predicted vehicle movement and the emotional state information sent from the emotion engine. If the driver is stressed, the server will give instructions in a more relaxing tone. The inputs of this step are the predicted movement and the emotional state information, and the output is the adjusted avoidance action instructions.

[0326] Step 7:

[0327] The terminal receives the evasive action instructions sent from the server and presents them to the driver using a display and voice guidance. For example, it displays instructions such as "Change to the left lane" and provides voice guidance such as "When changing to the left lane, reduce your speed and proceed slowly." The input for this step is the evasive action instructions sent from the server, and the output is the display and voice guidance.

[0328] The above is the flow of processing steps in the system program.

[0329] 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.

[0330] 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.

[0331] 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.

[0332] [Second embodiment]

[0333] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0334] 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.

[0335] 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).

[0336] 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.

[0337] 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.

[0338] 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).

[0339] 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.

[0340] 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.

[0341] 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.

[0342] 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.

[0343] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0344] 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."

[0345] This invention is a system that predicts vehicle movements based on GPS information and provides specific instructions to the driver on how to avoid accidents. This system can be retrofitted to vehicles and is an effective means of supporting safe driving even in vehicles without driving assistance functions.

[0346] 1. Obtaining GPS information on the device

[0347] The device (smartphone or tablet) acquires the vehicle's current location in real time. To do this, the device is equipped with a GPS module and has the function of periodically acquiring the vehicle's current latitude and longitude. The acquired location information is sent to a server where it is used for analysis.

[0348] 2. Risk prediction by server

[0349] The server uses artificial intelligence (AI) to predict the vehicle's movements based on the GPS information sent from the device. The AI ​​learns from past data and surrounding traffic conditions, and uses this information to predict future movements with high accuracy. If the risk is deemed high, the server calculates specific evasive action. For example, if the AI ​​predicts that "there is a car rapidly approaching from the right rear of the vehicle," it will use that information to calculate "changing to the left lane" as an evasive action.

[0350] 3. Display and audio guidance on terminals

[0351] The device displays the evasive maneuvers sent from the server on the car navigation system or display. It also uses voice guidance to guide the driver in evasive maneuvers. Specifically, the device gives the driver easy-to-understand instructions, such as, "A vehicle is rapidly approaching from the rear right. Slow down and move to the left."

[0352] As a concrete example, consider the following scenario:

[0353] Real-life scenario:

[0354] The device obtains location information of latitude: 35.6895, longitude: 139.6917 and sends it to the server.

[0355] The server analyzes the new location information and surrounding traffic data and uses an AI model to predict the risk to the vehicle, such as a vehicle rapidly approaching from the right rear.

[0356] The server calculates that "changing to the left lane" is the optimal avoidance action and transmits this avoidance action to the terminal.

[0357] The device will display evasive action on the car navigation display and provide a voice message saying, "Please change to the left lane."

[0358] The driver will then confirm this and follow the instructions to move into the left lane to avoid any risk.

[0359] In this way, the system, which can be retrofitted into vehicles, enables drivers to take appropriate evasive action in real time, significantly reducing the risk of traffic accidents.

[0360] The processing flow will be explained below.

[0361] Step 1:

[0362] The terminal uses a GPS module to obtain the vehicle's current location, which is expressed in the form of latitude and longitude and is updated periodically.

[0363] Step 2:

[0364] The device sends the acquired location information to the server using a communication protocol (e.g., HTTP or WebSocket).

[0365] Step 3:

[0366] The server uses artificial intelligence (AI) to predict vehicle movements based on the received GPS information, integrating and analyzing past data and surrounding traffic information.

[0367] Step 4:

[0368] If the risk is deemed high based on the risk level calculated by the AI, the server calculates the optimal avoidance action. For example, if a vehicle is rapidly approaching from the rear right, the server will recommend slowing down and moving to the left.

[0369] Step 5:

[0370] The server then transmits the calculated evasive maneuvers to the device, again using a pre-configured communication protocol.

[0371] Step 6:

[0372] The device receives the evasive action from the server and displays it on the car navigation display, allowing the driver to visually confirm the evasive action.

[0373] Step 7:

[0374] At the same time, the device uses its voice guidance function to provide specific evasive maneuvers, such as "change to the left lane," through a speaker.

[0375] Step 8:

[0376] The user (driver) checks the presented visual and audio instructions and takes appropriate evasive action, such as changing lanes to the left or slowing down.

[0377] This series of processes allows drivers to take appropriate evasive action in real time, reducing the risk of traffic accidents.

[0378] Example 1

[0379] 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."

[0380] Many current vehicles do not have driving assistance functions, and drivers of these vehicles lack the information necessary for safe driving. This leaves them unable to respond to unexpected traffic situations, increasing the risk of accidents. In particular, it is difficult to predict the movement of one's own vehicle and the surrounding traffic conditions in real time and take appropriate evasive action. Therefore, there is a need for technology that can be easily installed even in vehicles without driving assistance functions and that can effectively instruct drivers on how to avoid accidents.

[0381] 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.

[0382] In this invention, the server includes a location information acquisition means for acquiring current location information of the vehicle, a prediction means for using a generative AI model to predict the future movement of the vehicle based on the location information, and an instruction means for instructing the driver on specific avoidance behavior based on the movement predicted by the generative AI model. This allows for easy installation even in vehicles without driving assistance functions, and makes it possible to instruct the driver on appropriate accident avoidance behavior in real time.

[0383] "Location information acquisition means" refers to a device or function for measuring the current location of the vehicle and transmitting that location information to a server.

[0384] A "generative AI model" is a model built on artificial intelligence technology that learns from past data and current situations to predict future behavior.

[0385] "Prediction means" refers to a device or function that uses a generative AI model to predict the future behavior of a vehicle.

[0386] "Instruction means" refers to devices or functions that instruct the driver to take evasive action based on information predicted by the generative AI model.

[0387] "Display means" refers to a display device or function for visually presenting avoidance actions.

[0388] "Voice guidance means" refers to devices or functions that verbally inform the driver of evasive action.

[0389] "GPS module" refers to a receiver for the satellite positioning system that precisely measures one's position on Earth.

[0390] An "artificial intelligence framework" refers to a software environment that supports the building and learning of generative AI models.

[0391] This invention is a system that predicts vehicle movements based on GPS information and instructs the driver on specific actions to avoid accidents. This system can be retrofitted to vehicles and provides an effective means of supporting safe driving even in vehicles without driving assistance functions.

[0392] First, the terminal (smartphone or tablet) obtains the vehicle's current location in real time. To do this, the terminal is equipped with a GPS module that periodically calculates the current latitude and longitude and transmits the obtained location information to a server. The specific hardware used is a smartphone or tablet, and the software includes a GPS module.

[0393] The server then receives the GPS information sent from the device and uses an artificial intelligence (AI) model to predict the vehicle's future movements. The AI ​​model learns from past data and surrounding traffic conditions, and uses this information to predict future movements with high accuracy. The specific AI framework used is a generative AI model built using TensorFlow, PyTorch, and other frameworks.

[0394] The server then instructs the driver on evasive action based on the predicted risk information. For example, if the AI ​​model predicts that a vehicle is rapidly approaching from the right rear of the vehicle, the server calculates that the optimal evasive action is to change to the left lane and sends that instruction to the device.

[0395] The device receives instructions for evasive action sent from the server and displays them on the car navigation system or display. It also uses voice guidance to guide the driver through specific evasive actions. For example, it may provide a voice message such as, "A vehicle is rapidly approaching from the rear right. Slow down and move to the left."

[0396] As a concrete example, consider the following scenario:

[0397] The device obtains its current location information (latitude: 35.6895, longitude: 139.6917) and sends it to the server.

[0398] The server analyzes the new location information and surrounding traffic data and uses an AI model to predict the risk of a vehicle rapidly approaching from the right rear.

[0399] The server calculates that "changing to the left lane" is the optimal avoidance action and sends that instruction to the terminal.

[0400] The terminal displays instructions from the server on the car navigation display and provides a voice message saying, "Please change to the left lane."

[0401] The driver sees this instruction and moves to the left lane to avoid the risk.

[0402] An example prompt might look like this:

[0403] "Predict the vehicle's movement based on the following latitude and longitude location information. Latitude: 35.6895, Longitude: 139.6917. Please explain in detail the evasive action you would take if a vehicle were rapidly approaching from the right rear."

[0404] This makes it possible to easily install the system even in vehicles that do not have driving assistance functions, and it is possible to instruct the driver on appropriate accident avoidance actions in real time.

[0405] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0406] Step 1:

[0407] Activating the GPS module on the device

[0408] The terminal activates the built-in GPS module. This module receives signals from satellites and obtains the vehicle's current position (latitude and longitude). Specifically, it utilizes the GPS function of a smartphone or tablet. The input is a signal from a GPS satellite, and the output is the current position information (latitude and longitude).

[0409] Step 2:

[0410] Acquisition and transmission of location information by the device

[0411] The device periodically collects the current latitude and longitude and sends them to the server. For example, if the device obtains vehicle position information of latitude 35.6895 and longitude 139.6917, it sends this information to the server via the Internet. The input is the position information from the GPS module, and the output is the position information sent to the server.

[0412] Step 3:

[0413] Receiving and storing location information by the server

[0414] The server receives the location information sent from the device and stores it in a database in real time. The input is the location information sent from the device, and the output is the location information stored in the database.

[0415] Step 4:

[0416] Server calls the generated AI model

[0417] The server calls a generative AI model based on the received location information to predict the vehicle's future movements. The generative AI model is built using an AI framework such as TensorFlow or PyTorch. The input is location information, and the output is predicted risk information.

[0418] Step 5:

[0419] Server predicts risk and calculates avoidance actions

[0420] The generative AI model receives past traffic data and current location information as inputs and predicts risks. For example, if it predicts that "there is a vehicle rapidly approaching from the rear right," it uses that information to calculate the optimal evasive action to "change to the left lane." The inputs are location information and past traffic data, and the output is specific instructions for evasive action.

[0421] Step 6:

[0422] Server sends evasive action instructions

[0423] The server sends the calculated avoidance action instructions to the terminal. The input is the avoidance action instructions calculated by the server, and the output is the avoidance action instructions sent to the terminal.

[0424] Step 7:

[0425] Display of avoidance actions on the device

[0426] The terminal receives the evasive action instructions sent from the server and displays them on the car navigation system or display. For example, it displays a message such as "Please change to the left lane." The input is the evasive action instructions sent from the server, and the output is the evasive action instructions displayed on the display.

[0427] Step 8:

[0428] Voice guidance provided by the device

[0429] The terminal also provides voice guidance based on the received instructions for evasive action. Specifically, it plays a message such as, "A vehicle is rapidly approaching from the rear right. Slow down and move to the left." The input is the instruction for evasive action sent from the server, and the output is voice guidance.

[0430] Step 9:

[0431] User performs avoidance action

[0432] The user (driver) confirms the instructions from the terminal and takes specific avoidance action, such as changing to the left lane. The input is the avoidance action instruction from the terminal, and the output is the actual avoidance action.

[0433] (Application example 1)

[0434] 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."

[0435] Although autonomous vehicle technology has made remarkable advances in recent years, it remains difficult to completely eliminate the risk of unexpected traffic accidents. There is also a growing demand for advanced risk avoidance systems to ensure the safety of drivers and passengers. Such systems must provide comprehensive driving assistance, including real-time location information acquisition, traffic situation analysis, and prompt instruction on evasive action. Conventional technologies rely primarily on information from sensors inside the vehicle, making it difficult to grasp the overall picture of traffic conditions. Furthermore, there is a risk that accidents cannot be avoided due to delayed instruction on evasive action. There is a need to resolve these issues and provide safer and more reliable driving assistance systems.

[0436] 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.

[0437] In this invention, the server includes a means for transmitting vehicle location information and surrounding traffic data to a central server, calculating risk predictions and avoidance actions, a means for feeding back the calculated avoidance actions to the automated driving system, and a means for presenting the avoidance actions on a display and by voice. This makes it possible to reduce accident risk by analyzing traffic conditions in real time and prompting appropriate avoidance actions based on the predictions. Furthermore, the accuracy and reliability of avoidance actions are significantly improved by using a generative AI model for analysis and the creation of prompts.

[0438] "Vehicle location information" is data on the latitude and longitude of the vehicle's current location.

[0439] "Artificial intelligence" refers to the technology that allows computer systems to mimic human intelligence, in this case to predict vehicle behavior.

[0440] "Avoidance actions" refer to driving maneuvers and actions taken by a vehicle to prevent an accident from occurring.

[0441] "Central server" refers to a computer server that receives and analyzes all data sent from vehicles and calculates evasive actions.

[0442] "Risk prediction" refers to the use of artificial intelligence to predict possible future dangers based on the vehicle and its surrounding traffic conditions.

[0443] "Display" means a display device used to visually present information regarding evasive maneuvers to the driver.

[0444] "Voice guidance means" refers to a means for providing audible instructions for evasive action to the driver.

[0445] A "generative AI model" is an artificial intelligence model trained using large amounts of learning data, and is capable of predicting risks and calculating avoidance actions with high accuracy.

[0446] "Prompt sentence" refers to an instruction sentence created by a generative AI model for an autonomous driving system.

[0447] As a concrete example for implementing this invention, we will explain the "Safety Assistance System (AOSS)" applied to autonomous vehicles. This system provides the function of predicting risks based on the vehicle's position information and instructing appropriate avoidance actions.

[0448] Generating a Program

[0449] First, the vehicle acquires real-time location information using a GPS module. This location information is then transmitted from a device inside the vehicle (e.g., a car navigation system or dedicated tablet) to a central server. The central server analyzes the received location information and surrounding traffic data, and performs risk prediction using a generative AI model (e.g., using TensorFlow or PyTorch).

[0450] If the central server detects a risk, it calculates evasive action. The calculated evasive action (e.g., lane change, speed adjustment) is fed back to the autonomous driving system and reflected in vehicle control. The evasive action is also displayed visually on the in-car display and instructed to the driver audibly through the voice guidance system (e.g., linked to Google Assistant or Amazon Alexa).

[0451] Detailed system description

[0452] 1. Obtaining real-time GPS information

[0453] The server uses a GPS module to obtain the vehicle's latitude and longitude, and the obtained location information is sent to a central server.

[0454] 2. Risk prediction by a central server

[0455] The central server receives location information and other surrounding traffic data (such as the location and speed of surrounding vehicles) and predicts future risks using a generative AI model that is trained on a large amount of learning data.

[0456] 3. Calculation and avoidance behavior generation

[0457] If a risk is detected, the central server calculates the optimal avoidance action and sends information about the avoidance action to the automated driving system.

[0458] 4. Display and audio guidance

[0459] Evasive maneuvers are visually displayed on the in-car display, and the driver is given instructions via the voice guidance system. For example, a message saying "Please change to the left lane" is displayed on the display, and the driver is notified with a message such as "A vehicle is rapidly approaching from the rear right. Slow down and move to the left."

[0460] Specific examples

[0461] As a concrete example, consider the following scenario:

[0462] The vehicle sends its location information: latitude 35.6895, longitude 139.6917 to the central server.

[0463] The server analyzes surrounding traffic data and predicts that "there is a vehicle rapidly approaching from the rear right."

[0464] The server calculates "changing to the left lane" as an evasive maneuver and sends this information to the autonomous driving system.

[0465] The in-car display will show a message saying "Please change to the left lane," and the voice guidance system will inform the driver, "A vehicle is rapidly approaching from the rear right. Please slow down and move to the left."

[0466] The driver will then confirm this and follow the instructions to move into the left lane to avoid any risk.

[0467] Prompt Sentence Examples

[0468] Examples of prompts are:

[0469] "New location information acquired. Latitude: 35.6895, Longitude: 139.6917. Analyze surrounding traffic conditions and perform risk prediction. If there is a vehicle approaching quickly from the rear right, generate an instruction to change to the left lane as an evasive action."

[0470] In this way, the technology of the present invention can be applied to autonomous vehicles and contribute to improving safety.

[0471] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0472] Step 1:

[0473] The terminal uses the GPS module to obtain the vehicle's current location (latitude and longitude) in real time. Specifically, the terminal periodically reads data from the GPS module to obtain the current latitude and longitude information. This location information becomes the input data for the system.

[0474] Step 2:

[0475] The device transmits its current location information to a central server using an internet connection and sending the data as a POST request via a RESTful API. Specifically, the device sends latitude and longitude data in JSON format to the server.

[0476] Step 3:

[0477] The server collects surrounding traffic data based on the received location information. Based on the location information, the server uses external APIs to obtain current traffic conditions and the locations of nearby vehicles. At this stage, the server integrates all the acquired data and creates an input dataset for prediction.

[0478] Step 4:

[0479] The server uses the generative AI model to perform risk prediction. Specifically, it inputs acquired location information and surrounding traffic data into the AI ​​model to calculate future risks. The generative AI model is trained based on past learning data and makes highly accurate predictions based on the input data. The output includes information on when a risk is detected and suggested avoidance actions to address that risk.

[0480] Step 5:

[0481] The server feeds back the calculated evasive maneuvers to the autonomous driving system and the device. The server sends the evasive maneuver information in JSON format to the autonomous driving system and also sends the same information to the device. Specifically, the feedback information from the server includes instructions for lane changes and speed adjustments.

[0482] Step 6:

[0483] The device displays information on evasive action visually and provides audio guidance. The device then displays the received instructions on the screen and communicates them to the driver using the voice guidance system. Specifically, the display will show the message "Change to the left lane," and the voice guidance system will notify the driver, "A vehicle is rapidly approaching from the rear right. Slow down and move left."

[0484] Step 7:

[0485] The user (driver) follows the displayed avoidance action instructions and performs appropriate driving maneuvers. The driver follows the display and voice guidance to take driving actions such as changing lanes and adjusting speed. At this stage, the user actually takes action to avoid risk.

[0486] 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.

[0487] This invention is a system that predicts vehicle movement based on GPS information and instructs the driver to take action to avoid accidents. Furthermore, this system incorporates an emotion engine that recognizes the user's emotions, allowing it to provide flexible avoidance instructions according to the user's emotional state. This system can be retrofitted into automobiles, providing high safety even in vehicles without driving assistance functions.

[0488] 1. Obtaining GPS information on the device

[0489] The device (smartphone or tablet) acquires the vehicle's current location in real time. The device uses a GPS module to periodically acquire current location information in the form of latitude and longitude. The acquired location information is sent to a server where it is used for analysis.

[0490] 2. Risk prediction by server

[0491] The server uses artificial intelligence (AI) to predict vehicle movements based on GPS information sent from the device. The AI ​​learns from past data and surrounding traffic conditions to predict future movements with high accuracy. If a risk is determined to be high, the server calculates specific evasive actions.

[0492] 3. Understanding user state using emotion engine

[0493] The device is equipped with a camera and sensors to recognize the user's emotions. Using these sensors, the device grasps the user's emotional state in real time through facial recognition and voice analysis. The emotion engine analyzes whether the user is in a stressed or relaxed state and sends that information to the server.

[0494] 4. Server-based coordination of evasive actions

[0495] The server adjusts the instructions and methods for avoidance actions based on the user's emotional information obtained from the emotion engine. For example, if the user is feeling stressed, the server will devise ways to alleviate anxiety by giving instructions in a relaxed tone.

[0496] 5. Display and audio guidance on terminals

[0497] The device displays the evasive action sent from the server on the car navigation display. It also uses voice guidance adjusted based on the user's emotional state to guide the driver through the evasive action. For example, the device may display and voice instructions such as "A vehicle is rapidly approaching from the rear right. Slow down and move to the left." If the user is feeling stressed, the device may provide guidance in a gentler voice.

[0498] As a concrete example, consider the following scenario:

[0499] Real-life scenario:

[0500] The device obtains location information of latitude: 35.6895, longitude: 139.6917 and sends it to the server.

[0501] The server analyzes the new location information and surrounding traffic data and uses an AI model to predict the risk to the vehicle, such as a vehicle rapidly approaching from the right rear.

[0502] The emotion engine recognizes the user's face and determines that the user is in a stressful state.

[0503] Based on the information that "the user is in a stressful state," the server decides to take the evasive action of "changing to the left lane" and provides guidance in a gentle voice.

[0504] The device displays the message "Please change to the left lane" on the car navigation display and provides voice guidance in a gentle voice saying, "When changing to the left lane, reduce your speed and proceed slowly."

[0505] The driver will then confirm this and follow the instructions to move into the left lane to avoid any risk.

[0506] In this way, by combining a system that can be retrofitted into vehicles with emotion analysis using an emotion engine, drivers can take appropriate, emotion-sensitive evasive action in real time, significantly reducing the risk of traffic accidents.

[0507] The processing flow will be explained below.

[0508] Step 1:

[0509] The device uses a GPS module to obtain the vehicle's current location, which is obtained as latitude and longitude and updated periodically over time.

[0510] Step 2:

[0511] The device sends the acquired location information to the server using a transmission protocol (e.g., HTTP, WebSocket).

[0512] Step 3:

[0513] The server uses artificial intelligence (AI) to predict vehicle movements based on the received GPS information, and the AI ​​performs analysis based on past data and surrounding traffic conditions.

[0514] Step 4:

[0515] The device uses cameras and sensors to recognize the user's face and perform voice analysis, and analyzes their emotions in real time, with an emotion engine identifying emotional states such as stress or relaxation.

[0516] Step 5:

[0517] The terminal transmits the identified user's emotion information to the server.

[0518] Step 6:

[0519] The server calculates the optimal avoidance action based on the risk level calculated by the AI ​​when the risk is deemed high. For example, if a vehicle is predicted to be rapidly approaching from the rear right, it will recommend changing to the left lane.

[0520] Step 7:

[0521] The server adjusts the instructions and methods for avoidance actions based on the user's emotional information. For example, if the user is feeling stressed, the server will set the instructions to be given in a relaxed tone.

[0522] Step 8:

[0523] The server transmits the calculated avoidance actions to the terminal.

[0524] Step 9:

[0525] The device then displays the received instructions for avoidance actions on the car navigation display, with specific instructions visually displayed.

[0526] Step 10:

[0527] The device uses a voice guidance function to inform the user of specific avoidance actions, such as "A vehicle is rapidly approaching from the rear right. Slow down and move to the left."

[0528] Step 11:

[0529] The user checks the displayed instructions and audio guidance and takes appropriate evasive action, such as changing to the left lane or slowing down.

[0530] This series of processes allows users to take appropriate avoidance actions in real time based on their own emotions, reducing the risk of traffic accidents.

[0531] Example 2

[0532] 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."

[0533] Conventional vehicle driving assistance systems were able to predict risks and provide instructions for evasive action based on vehicle position information, but they were unable to adjust their instructions to take into account the driver's emotional state. This could lead to the driver continuing to drive while feeling stressed, increasing the risk. Therefore, a system is needed that can recognize the driver's emotional state and provide instructions for evasive action accordingly.

[0534] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0535] In this invention, the server includes means for acquiring vehicle position information, means for using artificial intelligence to predict vehicle movement based on the position information, means for instructing the driver to take avoidance action based on the information predicted by the artificial intelligence, sensor means for recognizing the emotional state of the user, and means for adjusting the avoidance action based on the emotional state of the user, thereby making it possible to instruct appropriate avoidance action according to the emotional state of the driver.

[0536] "Vehicle location information" is data indicating the vehicle's current latitude and longitude, and is obtained from a GPS module or the like.

[0537] "Artificial intelligence for predicting vehicle movement" refers to algorithms and systems that can predict future vehicle movement with high accuracy by learning from past data and current traffic conditions.

[0538] "Means for instructing the driver to take evasive action" refers to means for visually or audibly instructing the driver to take specific evasive action based on the results of predicting the vehicle's movement.

[0539] "Sensor means" refers to devices such as cameras and microphones for recognizing the user's emotional state.

[0540] "User's emotional state" is information that indicates the psychological state, such as stress or relaxation, that the user is currently feeling.

[0541] The "means for adjusting avoidance behavior" is a means for appropriately changing the content of avoidance behavior and the method of instruction according to the emotional state of the user.

[0542] "Display means" refers to a screen, monitor, or the like that visually presents avoidance actions to the user.

[0543] The "voice guidance means" refers to a speaker or voice synthesis system that uses voice to guide the user on how to take evasive action.

[0544] This invention is a system that acquires the current location of a vehicle, predicts risks, and instructs the driver to take evasive action. This system includes a function that recognizes the user's emotional state and provides instructions according to the emotion. The specific configuration and processing method of the hardware and software for implementing this system are described below.

[0545] Hardware and Software Configuration

[0546] Terminal

[0547] GPS module: Obtains the vehicle's current location in real time.

[0548] Camera: Used for facial recognition and analyzing the user's emotional state.

[0549] Microphone: Used to collect voice data and analyze emotions from the user's voice.

[0550] Display: A display device that visually instructs the driver on evasive action.

[0551] Speaker: An audio output device for providing audio guidance.

[0552] server

[0553] AI model (using TensorFlow, for example): Used to predict vehicle behavior.

[0554] Emotion engine (using Scikit-learn, for example): Analyzes the user's emotional state and adjusts avoidance behavior based on that information.

[0555] Database: Stores historical traffic and location data and uses it to train AI models.

[0556] Processing flow

[0557] This system operates in the following manner.

[0558] 1. Obtaining GPS information on the device

[0559] The terminal uses a GPS module to obtain the vehicle's current location and transmits it to the server as latitude and longitude data.

[0560] 2. Risk prediction by server

[0561] The server inputs the received GPS information into an AI model to predict the vehicle's future movements. If there is a risk, it generates specific risk information, such as "A vehicle is rapidly approaching from the rear right."

[0562] 3. Understanding user state using emotion engine

[0563] The device uses a camera and microphone to analyze the user's emotional state, recognizing whether the user is stressed or relaxed from facial expressions and voice, and sends that information to a server.

[0564] 4. Server-based coordination of evasive actions

[0565] The server adjusts the avoidance behavior based on the risk information and the user's emotional state. For example, if the user is stressed, the server will set the instructions to be given in a gentle tone.

[0566] 5. Display and audio guidance on terminals

[0567] The device displays the evasive actions sent from the server on its display and provides voice guidance through the speaker. For example, it displays specific instructions such as "Please change to the left lane," and then provides gentle voice guidance such as "When changing to the left lane, please reduce your speed and proceed slowly."

[0568] Specific examples

[0569] Real-life scenario

[0570] Obtaining and sending location information: The device obtains location information of latitude: 35.6895, longitude: 139.6917 and sends it to the server.

[0571] Risk prediction: The server analyzes new location information and surrounding traffic data and predicts that a vehicle is rapidly approaching from the right rear.

[0572] Emotion Recognition: The emotion engine recognizes the user's face and determines that the user is in a stressful state.

[0573] Adjusting evasive behavior: The server decides to instruct the user to change to the left lane using a gentle voice based on the user's emotional state.

[0574] Provides visual and audio guidance: The device displays the message "Please change to the left lane" on the car navigation display and provides gentle audio guidance such as "When changing to the left lane, reduce your speed and proceed slowly."

[0575] Prompt Sentence Examples

[0576] The user's location information was sent: latitude: 35.6895, longitude: 139.6917. Based on historical data and current traffic conditions, predict vehicle movements and suggest specific avoidance actions if there is a risk. Also, take into account the user's emotional state and adjust the content and tone of instructions as needed. For example, if the user is stressed, provide instructions in a calm voice.

[0577] In this way, the present invention is a system that can significantly reduce the risk of traffic accidents by providing appropriate avoidance actions based on the vehicle's current location and the user's emotional state.

[0578] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0579] Step 1: Get GPS information from your device

[0580] Input: Real-time location information obtained by the GPS module

[0581] Operation: The device uses the GPS module to obtain the vehicle's current location as latitude and longitude data, once per second.

[0582] Data processing: The acquired location data is temporarily stored in local storage and converted into an HTTP POST request format.

[0583] Output: Latitude and longitude location data sent to the server as an HTTP POST request

[0584] Step 2: Risk prediction by the server

[0585] Input: GPS location information sent from the device

[0586] How it works: The server inputs the received location information into an AI model (TensorFlow), which predicts the vehicle's future movements based on past data and current traffic conditions.

[0587] Data calculation: The AI ​​model uses a neural network to assess risk based on input location information and output a prediction such as "there is a vehicle rapidly approaching from the rear right."

[0588] Output: Predicted risk information (e.g., sudden approach from the rear right)

[0589] Step 3: Understanding the user's state using the emotion engine

[0590] Input: User's facial image and voice data acquired from the device's camera and microphone

[0591] How it works: The device uses the camera to recognize the user's face and the microphone to collect voice data. It uses the OpenCV library for face recognition and the Google Cloud Speech-to-Text API to convert the voice to text.

[0592] Data processing: Facial expressions and voice data are input into a machine learning model (Scikit-learn) to analyze whether the user is in a stressed or relaxed state.

[0593] Output: User's emotional state (e.g., stress state) as a result of the analysis

[0594] Step 4: Server Coordination of Evasive Behavior

[0595] Input: Risk prediction results and user's emotional state

[0596] How it works: The server adjusts the avoidance behavior based on the risk prediction result and the user's emotional state. For example, if the user is stressed, the server will set the tone to be gentler and give avoidance instructions.

[0597] Data Calculation: Determines customized content and audio tone of avoidance actions based on specific conditions.

[0598] Output: Coordinated evasive maneuver instructions (e.g., a gentle voice prompt saying "Move to the left lane")

[0599] Step 5: Display and voice guidance on the device

[0600] Input: Adjusted evasive maneuver instructions sent from the server

[0601] Operation: The device displays instructions from the server on the screen and provides voice guidance using a speech synthesis engine (Google Text-to-Speech).

[0602] Data processing: Evasive action instructions from the server are visually displayed on a GUI and audio data is generated.

[0603] Output: Visual instructions on the display and voice guidance from the speaker (e.g., a calm voice saying "Please change to the left lane")

[0604] This series of steps allows the system to provide the driver with targeted, risk-minimizing evasive action based on both the vehicle's current location and the user's emotional state.

[0605] (Application example 2)

[0606] 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."

[0607] Conventional driving assistance systems provide instructions for accident avoidance actions based on the vehicle's movement, but they have the problem of being unable to provide appropriate instructions based on the driver's emotional state. As a result, if the driver is stressed or nervous, the instructions may not be communicated effectively, which may reduce the effectiveness of accident avoidance. In addition, avoidance actions based solely on visual displays and audio guidance have the problem of being difficult to provide appropriate support tailored to the individual driver's situation.

[0608] 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 acquiring vehicle position information, means for using artificial intelligence to predict vehicle movement based on the position information, means for instructing the driver to take evasive action based on the information predicted by the artificial intelligence, means for acquiring the user's emotional state using an emotion engine that recognizes the user's emotions, and means for adjusting the content and method of instructions for evasive action based on the emotional state. This makes it possible to instruct evasive action flexibly and effectively according to the driver's emotional state.

[0609] "Vehicle location information" refers to data on the current latitude and longitude of a vehicle obtained using a positioning system such as a GPS.

[0610] "Artificial intelligence" refers to computational techniques and algorithms that predict a vehicle's future movements based on historical data and current traffic conditions.

[0611] "Means for instructing the driver to take evasive action" refers to a system that has the function of instructing the driver to take appropriate evasive action based on predicted risk information.

[0612] An "emotion engine" is a combination of software and hardware that performs facial recognition and voice analysis of the user to recognize their emotional state in real time.

[0613] "Emotional state" refers to the mental state of the driver, such as stress or relaxation.

[0614] "Display means" refers to a device or system for visually presenting information, and typically includes a car navigation display or a smartphone screen.

[0615] "Audio guidance means" refers to a device or system for providing information or instructions by voice through a speaker or earphone.

[0616] "Means for adjusting the content and method of instructions for avoidance behavior" refers to a system for changing the specific content of instructions for avoidance behavior and the method of conveying them based on the user's emotional state.

[0617] This invention is a system for tracking a vehicle's position in real time and providing driving assistance, particularly a system that can take into account the driver's emotional state and provide flexible evasive maneuvers.

[0618] First, the device (e.g., a smartphone) uses a GPS module to obtain the vehicle's location information (latitude and longitude). This location information is periodically sent to a server. The server then uses artificial intelligence (AI) to predict the vehicle's future movements based on the received location information. In this case, the AI ​​uses a model that has learned from past data and current traffic conditions.

[0619] Next, the emotion engine uses the device's camera and microphone to analyze the driver's emotional state in real time. For example, it uses facial recognition to determine stress or relaxation from facial expressions. It also uses voice analysis to estimate the driver's emotions from the way they speak and their tone of voice. This information is sent to the server.

[0620] The server integrates the predicted vehicle movement results with the driver's emotional state to calculate the optimal evasive action. If the driver is feeling stressed, it is important to give instructions in a tone that will help them relax. For example, the device might display a message on the car navigation display saying, "A vehicle is rapidly approaching from the rear right. Please slow down and move to the left," and provide voice guidance in a calm voice saying, "When changing to the left lane, please slow down and move slowly."

[0621] This system enables flexible accident avoidance by taking into account the user's emotional state. The specific hardware used is a smartphone, with a built-in camera, microphone, and display. The software uses a GPS module, OpenCV (for emotion recognition), Google Cloud Speech-to-Text API (for voice analysis), and Flask (for server-side processing).

[0622] As a concrete example, let's say a user is feeling stressed while driving. The device acquires location information of latitude: 35.6895, longitude: 139.6917 and sends it to the server. The server analyzes the new location information and surrounding traffic data and predicts the risk of "a vehicle rapidly approaching from the rear right." The emotion engine recognizes the user's face and determines that the user is in a stressed state. Based on the information that "the user is in a stressed state," the server decides to "change to the left lane" and provides guidance in a calm voice. The device displays the message "Please change to the left lane" on the car navigation display and provides voice guidance in a calm voice, "When changing to the left lane, please reduce your speed and proceed slowly."

[0623] Example prompt sentence:

[0624] "Your current location is latitude 35.6895, longitude 139.6917. You are in a stressed state. A vehicle is approaching you from behind on the right. Please slow down and move to the left. When changing to the left lane, slow down and move slowly."

[0625] In this way, the driver can receive appropriate accident avoidance instructions according to their emotional state, improving safety.

[0626] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0627] Step 1:

[0628] The terminal uses the GPS module to obtain the vehicle's current location information. At that time, it obtains latitude and longitude data and temporarily stores this information inside the terminal. The input of this step is GPS data, and the output is the vehicle's current location information.

[0629] Step 2:

[0630] The device sends the acquired location information to the server. It uses an HTTP POST request to send the vehicle's latitude and longitude to the server. The input of this step is the location information stored inside the device, and the output is the location information sent to the server.

[0631] Step 3:

[0632] The server receives the location information sent from the device. It uses artificial intelligence (AI) to predict the vehicle's future movements based on the received location information. In this process, it also analyzes past data and current traffic conditions. The input of this step is the received location information and past traffic data, and the output is the predicted future movements.

[0633] Step 4:

[0634] The device uses a camera and microphone to acquire the driver's emotional state. Specifically, it performs facial recognition using the camera and voice analysis using the microphone, and passes the results to the emotion engine. The input of this step is camera image and voice data, and the output is emotional state data.

[0635] Step 5:

[0636] The emotion engine analyzes the acquired facial recognition data and voice data to determine the driver's emotional state, such as stress or relaxation, and sends that information to the server. The input to this step is the emotional state data analyzed by the emotion engine, and the output is the emotional state information sent to the server.

[0637] Step 6:

[0638] The server calculates the optimal avoidance action based on the predicted vehicle movement and the emotional state information sent from the emotion engine. If the driver is stressed, the server will give instructions in a more relaxing tone. The inputs of this step are the predicted movement and the emotional state information, and the output is the adjusted avoidance action instructions.

[0639] Step 7:

[0640] The terminal receives the evasive action instructions sent from the server and presents them to the driver using a display and voice guidance. For example, it displays instructions such as "Change to the left lane" and provides voice guidance such as "When changing to the left lane, reduce your speed and proceed slowly." The input for this step is the evasive action instructions sent from the server, and the output is the display and voice guidance.

[0641] The above is the flow of processing steps in the system program.

[0642] 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.

[0643] 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.

[0644] 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.

[0645] [Third embodiment]

[0646] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0647] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0648] 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).

[0649] 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.

[0650] 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.

[0651] 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).

[0652] 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.

[0653] 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.

[0654] 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.

[0655] 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.

[0656] 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.

[0657] 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."

[0658] This invention is a system that predicts vehicle movements based on GPS information and provides specific instructions to the driver on how to avoid accidents. This system can be retrofitted to vehicles and is an effective means of supporting safe driving even in vehicles without driving assistance functions.

[0659] 1. Obtaining GPS information on the device

[0660] The device (smartphone or tablet) acquires the vehicle's current location in real time. To do this, the device is equipped with a GPS module and has the function of periodically acquiring the vehicle's current latitude and longitude. The acquired location information is sent to a server where it is used for analysis.

[0661] 2. Risk prediction by server

[0662] The server uses artificial intelligence (AI) to predict the vehicle's movements based on the GPS information sent from the device. The AI ​​learns from past data and surrounding traffic conditions, and uses this information to predict future movements with high accuracy. If the risk is deemed high, the server calculates specific evasive action. For example, if the AI ​​predicts that "there is a car rapidly approaching from the right rear of the vehicle," it will use that information to calculate "changing to the left lane" as an evasive action.

[0663] 3. Display and audio guidance on terminals

[0664] The device displays the evasive maneuvers sent from the server on the car navigation system or display. It also uses voice guidance to guide the driver in evasive maneuvers. Specifically, the device gives the driver easy-to-understand instructions, such as, "A vehicle is rapidly approaching from the rear right. Slow down and move to the left."

[0665] As a concrete example, consider the following scenario:

[0666] Real-life scenario:

[0667] The device obtains location information of latitude: 35.6895, longitude: 139.6917 and sends it to the server.

[0668] The server analyzes the new location information and surrounding traffic data and uses an AI model to predict the risk to the vehicle, such as a vehicle rapidly approaching from the right rear.

[0669] The server calculates that "changing to the left lane" is the optimal avoidance action and transmits this avoidance action to the terminal.

[0670] The device will display evasive action on the car navigation display and provide a voice message saying, "Please change to the left lane."

[0671] The driver will then confirm this and follow the instructions to move into the left lane to avoid any risk.

[0672] In this way, the system, which can be retrofitted into vehicles, enables drivers to take appropriate evasive action in real time, significantly reducing the risk of traffic accidents.

[0673] The processing flow will be explained below.

[0674] Step 1:

[0675] The terminal uses a GPS module to obtain the vehicle's current location, which is expressed in the form of latitude and longitude and is updated periodically.

[0676] Step 2:

[0677] The device sends the acquired location information to the server using a communication protocol (e.g., HTTP or WebSocket).

[0678] Step 3:

[0679] The server uses artificial intelligence (AI) to predict vehicle movements based on the received GPS information, integrating and analyzing past data and surrounding traffic information.

[0680] Step 4:

[0681] If the risk is deemed high based on the risk level calculated by the AI, the server calculates the optimal avoidance action. For example, if a vehicle is rapidly approaching from the rear right, the server will recommend slowing down and moving to the left.

[0682] Step 5:

[0683] The server then transmits the calculated evasive maneuvers to the device, again using a pre-configured communication protocol.

[0684] Step 6:

[0685] The device receives the evasive action from the server and displays it on the car navigation display, allowing the driver to visually confirm the evasive action.

[0686] Step 7:

[0687] At the same time, the device uses its voice guidance function to provide specific evasive maneuvers, such as "change to the left lane," through a speaker.

[0688] Step 8:

[0689] The user (driver) checks the presented visual and audio instructions and takes appropriate evasive action, such as changing lanes to the left or slowing down.

[0690] This series of processes allows drivers to take appropriate evasive action in real time, reducing the risk of traffic accidents.

[0691] Example 1

[0692] 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."

[0693] Many current vehicles do not have driving assistance functions, and drivers of these vehicles lack the information necessary for safe driving. This leaves them unable to respond to unexpected traffic situations, increasing the risk of accidents. In particular, it is difficult to predict the movement of one's own vehicle and the surrounding traffic conditions in real time and take appropriate evasive action. Therefore, there is a need for technology that can be easily installed even in vehicles without driving assistance functions and that can effectively instruct drivers on how to avoid accidents.

[0694] 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.

[0695] In this invention, the server includes a location information acquisition means for acquiring current location information of the vehicle, a prediction means for using a generative AI model to predict the future movement of the vehicle based on the location information, and an instruction means for instructing the driver on specific avoidance behavior based on the movement predicted by the generative AI model. This allows for easy installation even in vehicles without driving assistance functions, and makes it possible to instruct the driver on appropriate accident avoidance behavior in real time.

[0696] "Location information acquisition means" refers to a device or function for measuring the current location of the vehicle and transmitting that location information to a server.

[0697] A "generative AI model" is a model built on artificial intelligence technology that learns from past data and current situations to predict future behavior.

[0698] "Prediction means" refers to a device or function that uses a generative AI model to predict the future behavior of a vehicle.

[0699] "Instruction means" refers to devices or functions that instruct the driver to take evasive action based on information predicted by the generative AI model.

[0700] "Display means" refers to a display device or function for visually presenting avoidance actions.

[0701] "Voice guidance means" refers to devices or functions that verbally inform the driver of evasive action.

[0702] "GPS module" refers to a receiver for the satellite positioning system that precisely measures one's position on Earth.

[0703] An "artificial intelligence framework" refers to a software environment that supports the building and learning of generative AI models.

[0704] This invention is a system that predicts vehicle movements based on GPS information and instructs the driver on specific actions to avoid accidents. This system can be retrofitted to vehicles and provides an effective means of supporting safe driving even in vehicles without driving assistance functions.

[0705] First, the terminal (smartphone or tablet) obtains the vehicle's current location in real time. To do this, the terminal is equipped with a GPS module that periodically calculates the current latitude and longitude and transmits the obtained location information to a server. The specific hardware used is a smartphone or tablet, and the software includes a GPS module.

[0706] The server then receives the GPS information sent from the device and uses an artificial intelligence (AI) model to predict the vehicle's future movements. The AI ​​model learns from past data and surrounding traffic conditions, and uses this information to predict future movements with high accuracy. The specific AI framework used is a generative AI model built using TensorFlow, PyTorch, and other frameworks.

[0707] The server then instructs the driver on evasive action based on the predicted risk information. For example, if the AI ​​model predicts that a vehicle is rapidly approaching from the right rear of the vehicle, the server calculates that the optimal evasive action is to change to the left lane and sends that instruction to the device.

[0708] The device receives instructions for evasive action sent from the server and displays them on the car navigation system or display. It also uses voice guidance to guide the driver through specific evasive actions. For example, it may provide a voice message such as, "A vehicle is rapidly approaching from the rear right. Slow down and move to the left."

[0709] As a concrete example, consider the following scenario:

[0710] The device obtains its current location information (latitude: 35.6895, longitude: 139.6917) and sends it to the server.

[0711] The server analyzes the new location information and surrounding traffic data and uses an AI model to predict the risk of a vehicle rapidly approaching from the right rear.

[0712] The server calculates that "changing to the left lane" is the optimal avoidance action and sends that instruction to the terminal.

[0713] The terminal displays instructions from the server on the car navigation display and provides a voice message saying, "Please change to the left lane."

[0714] The driver sees this instruction and moves to the left lane to avoid the risk.

[0715] An example prompt might look like this:

[0716] "Predict the vehicle's movement based on the following latitude and longitude location information. Latitude: 35.6895, Longitude: 139.6917. Please explain in detail the evasive action you would take if a vehicle were rapidly approaching from the right rear."

[0717] This makes it possible to easily install the system even in vehicles that do not have driving assistance functions, and it is possible to instruct the driver on appropriate accident avoidance actions in real time.

[0718] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0719] Step 1:

[0720] Activating the GPS module on the device

[0721] The terminal activates the built-in GPS module. This module receives signals from satellites and obtains the vehicle's current position (latitude and longitude). Specifically, it utilizes the GPS function of a smartphone or tablet. The input is a signal from a GPS satellite, and the output is the current position information (latitude and longitude).

[0722] Step 2:

[0723] Acquisition and transmission of location information by the device

[0724] The device periodically collects the current latitude and longitude and sends them to the server. For example, if the device obtains vehicle position information of latitude 35.6895 and longitude 139.6917, it sends this information to the server via the Internet. The input is the position information from the GPS module, and the output is the position information sent to the server.

[0725] Step 3:

[0726] Receiving and storing location information by the server

[0727] The server receives the location information sent from the device and stores it in a database in real time. The input is the location information sent from the device, and the output is the location information stored in the database.

[0728] Step 4:

[0729] Server calls the generated AI model

[0730] The server calls a generative AI model based on the received location information to predict the vehicle's future movements. The generative AI model is built using an AI framework such as TensorFlow or PyTorch. The input is location information, and the output is predicted risk information.

[0731] Step 5:

[0732] Server predicts risk and calculates avoidance actions

[0733] The generative AI model receives past traffic data and current location information as inputs and predicts risks. For example, if it predicts that "there is a vehicle rapidly approaching from the rear right," it uses that information to calculate the optimal evasive action to "change to the left lane." The inputs are location information and past traffic data, and the output is specific instructions for evasive action.

[0734] Step 6:

[0735] Server sends evasive action instructions

[0736] The server sends the calculated avoidance action instructions to the terminal. The input is the avoidance action instructions calculated by the server, and the output is the avoidance action instructions sent to the terminal.

[0737] Step 7:

[0738] Display of avoidance actions on the device

[0739] The terminal receives the evasive action instructions sent from the server and displays them on the car navigation system or display. For example, it displays a message such as "Please change to the left lane." The input is the evasive action instructions sent from the server, and the output is the evasive action instructions displayed on the display.

[0740] Step 8:

[0741] Voice guidance provided by the device

[0742] The terminal also provides voice guidance based on the received instructions for evasive action. Specifically, it plays a message such as, "A vehicle is rapidly approaching from the rear right. Slow down and move to the left." The input is the instruction for evasive action sent from the server, and the output is voice guidance.

[0743] Step 9:

[0744] User performs avoidance action

[0745] The user (driver) confirms the instructions from the terminal and takes specific avoidance action, such as changing to the left lane. The input is the avoidance action instruction from the terminal, and the output is the actual avoidance action.

[0746] (Application example 1)

[0747] 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."

[0748] Although autonomous vehicle technology has made remarkable advances in recent years, it remains difficult to completely eliminate the risk of unexpected traffic accidents. There is also a growing demand for advanced risk avoidance systems to ensure the safety of drivers and passengers. Such systems must provide comprehensive driving assistance, including real-time location information acquisition, traffic situation analysis, and prompt instruction on evasive action. Conventional technologies rely primarily on information from sensors inside the vehicle, making it difficult to grasp the overall picture of traffic conditions. Furthermore, there is a risk that accidents cannot be avoided due to delayed instruction on evasive action. There is a need to resolve these issues and provide safer and more reliable driving assistance systems.

[0749] 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.

[0750] In this invention, the server includes a means for transmitting vehicle location information and surrounding traffic data to a central server, calculating risk predictions and avoidance actions, a means for feeding back the calculated avoidance actions to the automated driving system, and a means for presenting the avoidance actions on a display and by voice. This makes it possible to reduce accident risk by analyzing traffic conditions in real time and prompting appropriate avoidance actions based on the predictions. Furthermore, the accuracy and reliability of avoidance actions are significantly improved by using a generative AI model for analysis and the creation of prompts.

[0751] "Vehicle location information" is data on the latitude and longitude of the vehicle's current location.

[0752] "Artificial intelligence" refers to the technology that allows computer systems to mimic human intelligence, in this case to predict vehicle behavior.

[0753] "Avoidance actions" refer to driving maneuvers and actions taken by a vehicle to prevent an accident from occurring.

[0754] "Central server" refers to a computer server that receives and analyzes all data sent from vehicles and calculates evasive actions.

[0755] "Risk prediction" refers to the use of artificial intelligence to predict possible future dangers based on the vehicle and its surrounding traffic conditions.

[0756] "Display" means a display device used to visually present information regarding evasive maneuvers to the driver.

[0757] "Voice guidance means" refers to a means for providing audible instructions for evasive action to the driver.

[0758] A "generative AI model" is an artificial intelligence model trained using large amounts of learning data, and is capable of predicting risks and calculating avoidance actions with high accuracy.

[0759] "Prompt sentence" refers to an instruction sentence created by a generative AI model for an autonomous driving system.

[0760] As a concrete example for implementing this invention, we will explain the "Safety Assistance System (AOSS)" applied to autonomous vehicles. This system provides the function of predicting risks based on the vehicle's position information and instructing appropriate avoidance actions.

[0761] Generating a Program

[0762] First, the vehicle acquires real-time location information using a GPS module. This location information is then transmitted from a device inside the vehicle (e.g., a car navigation system or dedicated tablet) to a central server. The central server analyzes the received location information and surrounding traffic data, and performs risk prediction using a generative AI model (e.g., using TensorFlow or PyTorch).

[0763] If the central server detects a risk, it calculates evasive action. The calculated evasive action (e.g., lane change, speed adjustment) is fed back to the autonomous driving system and reflected in vehicle control. The evasive action is also displayed visually on the in-car display and instructed to the driver audibly through the voice guidance system (e.g., linked to Google Assistant or Amazon Alexa).

[0764] Detailed system description

[0765] 1. Obtaining real-time GPS information

[0766] The server uses a GPS module to obtain the vehicle's latitude and longitude, and the obtained location information is sent to a central server.

[0767] 2. Risk prediction by a central server

[0768] The central server receives location information and other surrounding traffic data (such as the location and speed of surrounding vehicles) and predicts future risks using a generative AI model that is trained on a large amount of learning data.

[0769] 3. Calculation and avoidance behavior generation

[0770] If a risk is detected, the central server calculates the optimal avoidance action and sends information about the avoidance action to the automated driving system.

[0771] 4. Display and audio guidance

[0772] Evasive maneuvers are visually displayed on the in-car display, and the driver is given instructions via the voice guidance system. For example, a message saying "Please change to the left lane" is displayed on the display, and the driver is notified with a message such as "A vehicle is rapidly approaching from the rear right. Slow down and move to the left."

[0773] Specific examples

[0774] As a concrete example, consider the following scenario:

[0775] The vehicle sends its location information: latitude 35.6895, longitude 139.6917 to the central server.

[0776] The server analyzes surrounding traffic data and predicts that "there is a vehicle rapidly approaching from the rear right."

[0777] The server calculates "changing to the left lane" as an evasive maneuver and sends this information to the autonomous driving system.

[0778] The in-car display will show a message saying "Please change to the left lane," and the voice guidance system will inform the driver, "A vehicle is rapidly approaching from the rear right. Please slow down and move to the left."

[0779] The driver will then confirm this and follow the instructions to move into the left lane to avoid any risk.

[0780] Prompt Sentence Examples

[0781] Examples of prompts are:

[0782] "New location information acquired. Latitude: 35.6895, Longitude: 139.6917. Analyze surrounding traffic conditions and perform risk prediction. If there is a vehicle approaching quickly from the rear right, generate an instruction to change to the left lane as an evasive action."

[0783] In this way, the technology of the present invention can be applied to autonomous vehicles and contribute to improving safety.

[0784] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0785] Step 1:

[0786] The terminal uses the GPS module to obtain the vehicle's current location (latitude and longitude) in real time. Specifically, the terminal periodically reads data from the GPS module to obtain the current latitude and longitude information. This location information becomes the input data for the system.

[0787] Step 2:

[0788] The device transmits its current location information to a central server using an internet connection and sending the data as a POST request via a RESTful API. Specifically, the device sends latitude and longitude data in JSON format to the server.

[0789] Step 3:

[0790] The server collects surrounding traffic data based on the received location information. Based on the location information, the server uses external APIs to obtain current traffic conditions and the locations of nearby vehicles. At this stage, the server integrates all the acquired data and creates an input dataset for prediction.

[0791] Step 4:

[0792] The server uses the generative AI model to perform risk prediction. Specifically, it inputs acquired location information and surrounding traffic data into the AI ​​model to calculate future risks. The generative AI model is trained based on past learning data and makes highly accurate predictions based on the input data. The output includes information on when a risk is detected and suggested avoidance actions to address that risk.

[0793] Step 5:

[0794] The server feeds back the calculated evasive maneuvers to the autonomous driving system and the device. The server sends the evasive maneuver information in JSON format to the autonomous driving system and also sends the same information to the device. Specifically, the feedback information from the server includes instructions for lane changes and speed adjustments.

[0795] Step 6:

[0796] The device displays information on evasive action visually and provides audio guidance. The device then displays the received instructions on the screen and communicates them to the driver using the voice guidance system. Specifically, the display will show the message "Change to the left lane," and the voice guidance system will notify the driver, "A vehicle is rapidly approaching from the rear right. Slow down and move left."

[0797] Step 7:

[0798] The user (driver) follows the displayed avoidance action instructions and performs appropriate driving maneuvers. The driver follows the display and voice guidance to take driving actions such as changing lanes and adjusting speed. At this stage, the user actually takes action to avoid risk.

[0799] 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.

[0800] This invention is a system that predicts vehicle movement based on GPS information and instructs the driver to take action to avoid accidents. Furthermore, this system incorporates an emotion engine that recognizes the user's emotions, allowing it to provide flexible avoidance instructions according to the user's emotional state. This system can be retrofitted into automobiles, providing high safety even in vehicles without driving assistance functions.

[0801] 1. Obtaining GPS information on the device

[0802] The device (smartphone or tablet) acquires the vehicle's current location in real time. The device uses a GPS module to periodically acquire current location information in the form of latitude and longitude. The acquired location information is sent to a server where it is used for analysis.

[0803] 2. Risk prediction by server

[0804] The server uses artificial intelligence (AI) to predict vehicle movements based on GPS information sent from the device. The AI ​​learns from past data and surrounding traffic conditions to predict future movements with high accuracy. If a risk is determined to be high, the server calculates specific evasive actions.

[0805] 3. Understanding user state using emotion engine

[0806] The device is equipped with a camera and sensors to recognize the user's emotions. Using these sensors, the device grasps the user's emotional state in real time through facial recognition and voice analysis. The emotion engine analyzes whether the user is in a stressed or relaxed state and sends that information to the server.

[0807] 4. Server-based coordination of evasive actions

[0808] The server adjusts the instructions and methods for avoidance actions based on the user's emotional information obtained from the emotion engine. For example, if the user is feeling stressed, the server will devise ways to alleviate anxiety by giving instructions in a relaxed tone.

[0809] 5. Display and audio guidance on terminals

[0810] The device displays the evasive action sent from the server on the car navigation display. It also uses voice guidance adjusted based on the user's emotional state to guide the driver through the evasive action. For example, the device may display and voice instructions such as "A vehicle is rapidly approaching from the rear right. Slow down and move to the left." If the user is feeling stressed, the device may provide guidance in a gentler voice.

[0811] As a concrete example, consider the following scenario:

[0812] Real-life scenario:

[0813] The device obtains location information of latitude: 35.6895, longitude: 139.6917 and sends it to the server.

[0814] The server analyzes the new location information and surrounding traffic data and uses an AI model to predict the risk to the vehicle, such as a vehicle rapidly approaching from the right rear.

[0815] The emotion engine recognizes the user's face and determines that the user is in a stressful state.

[0816] Based on the information that "the user is in a stressful state," the server decides to take the evasive action of "changing to the left lane" and provides guidance in a gentle voice.

[0817] The device displays the message "Please change to the left lane" on the car navigation display and provides voice guidance in a gentle voice saying, "When changing to the left lane, reduce your speed and proceed slowly."

[0818] The driver will then confirm this and follow the instructions to move into the left lane to avoid any risk.

[0819] In this way, by combining a system that can be retrofitted into vehicles with emotion analysis using an emotion engine, drivers can take appropriate, emotion-sensitive evasive action in real time, significantly reducing the risk of traffic accidents.

[0820] The processing flow will be explained below.

[0821] Step 1:

[0822] The device uses a GPS module to obtain the vehicle's current location, which is obtained as latitude and longitude and updated periodically over time.

[0823] Step 2:

[0824] The device sends the acquired location information to the server using a transmission protocol (e.g., HTTP, WebSocket).

[0825] Step 3:

[0826] The server uses artificial intelligence (AI) to predict vehicle movements based on the received GPS information, and the AI ​​performs analysis based on past data and surrounding traffic conditions.

[0827] Step 4:

[0828] The device uses cameras and sensors to recognize the user's face and perform voice analysis, and analyzes their emotions in real time, with an emotion engine identifying emotional states such as stress or relaxation.

[0829] Step 5:

[0830] The terminal transmits the identified user's emotion information to the server.

[0831] Step 6:

[0832] The server calculates the optimal avoidance action based on the risk level calculated by the AI ​​when the risk is deemed high. For example, if a vehicle is predicted to be rapidly approaching from the rear right, it will recommend changing to the left lane.

[0833] Step 7:

[0834] The server adjusts the instructions and methods for avoidance actions based on the user's emotional information. For example, if the user is feeling stressed, the server will set the instructions to be given in a relaxed tone.

[0835] Step 8:

[0836] The server transmits the calculated avoidance actions to the terminal.

[0837] Step 9:

[0838] The device then displays the received instructions for avoidance actions on the car navigation display, with specific instructions visually displayed.

[0839] Step 10:

[0840] The device uses a voice guidance function to inform the user of specific avoidance actions, such as "A vehicle is rapidly approaching from the rear right. Slow down and move to the left."

[0841] Step 11:

[0842] The user checks the displayed instructions and audio guidance and takes appropriate evasive action, such as changing to the left lane or slowing down.

[0843] This series of processes allows users to take appropriate avoidance actions in real time based on their own emotions, reducing the risk of traffic accidents.

[0844] Example 2

[0845] 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."

[0846] Conventional vehicle driving assistance systems were able to predict risks and provide instructions for evasive action based on vehicle position information, but they were unable to adjust their instructions to take into account the driver's emotional state. This could lead to the driver continuing to drive while feeling stressed, increasing the risk. Therefore, a system is needed that can recognize the driver's emotional state and provide instructions for evasive action accordingly.

[0847] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0848] In this invention, the server includes means for acquiring vehicle position information, means for using artificial intelligence to predict vehicle movement based on the position information, means for instructing the driver to take avoidance action based on the information predicted by the artificial intelligence, sensor means for recognizing the emotional state of the user, and means for adjusting the avoidance action based on the emotional state of the user, thereby making it possible to instruct appropriate avoidance action according to the emotional state of the driver.

[0849] "Vehicle location information" is data indicating the vehicle's current latitude and longitude, and is obtained from a GPS module or the like.

[0850] "Artificial intelligence for predicting vehicle movement" refers to algorithms and systems that can predict future vehicle movement with high accuracy by learning from past data and current traffic conditions.

[0851] "Means for instructing the driver to take evasive action" refers to means for visually or audibly instructing the driver to take specific evasive action based on the results of predicting the vehicle's movement.

[0852] "Sensor means" refers to devices such as cameras and microphones for recognizing the user's emotional state.

[0853] "User's emotional state" is information that indicates the psychological state, such as stress or relaxation, that the user is currently feeling.

[0854] The "means for adjusting avoidance behavior" is a means for appropriately changing the content of avoidance behavior and the method of instruction according to the emotional state of the user.

[0855] "Display means" refers to a screen, monitor, or the like that visually presents avoidance actions to the user.

[0856] The "voice guidance means" refers to a speaker or voice synthesis system that uses voice to guide the user on how to take evasive action.

[0857] This invention is a system that acquires the current location of a vehicle, predicts risks, and instructs the driver to take evasive action. This system includes a function that recognizes the user's emotional state and provides instructions according to the emotion. The specific configuration and processing method of the hardware and software for implementing this system are described below.

[0858] Hardware and Software Configuration

[0859] Terminal

[0860] GPS module: Obtains the vehicle's current location in real time.

[0861] Camera: Used for facial recognition and analyzing the user's emotional state.

[0862] Microphone: Used to collect voice data and analyze emotions from the user's voice.

[0863] Display: A display device that visually instructs the driver on evasive action.

[0864] Speaker: An audio output device for providing audio guidance.

[0865] server

[0866] AI model (using TensorFlow, for example): Used to predict vehicle behavior.

[0867] Emotion engine (using Scikit-learn, for example): Analyzes the user's emotional state and adjusts avoidance behavior based on that information.

[0868] Database: Stores historical traffic and location data and uses it to train AI models.

[0869] Processing flow

[0870] This system operates in the following manner.

[0871] 1. Obtaining GPS information on the device

[0872] The terminal uses a GPS module to obtain the vehicle's current location and transmits it to the server as latitude and longitude data.

[0873] 2. Risk prediction by server

[0874] The server inputs the received GPS information into an AI model to predict the vehicle's future movements. If there is a risk, it generates specific risk information, such as "A vehicle is rapidly approaching from the rear right."

[0875] 3. Understanding user state using emotion engine

[0876] The device uses a camera and microphone to analyze the user's emotional state, recognizing whether the user is stressed or relaxed from facial expressions and voice, and sends that information to a server.

[0877] 4. Server-based coordination of evasive actions

[0878] The server adjusts the avoidance behavior based on the risk information and the user's emotional state. For example, if the user is stressed, the server will set the instructions to be given in a gentle tone.

[0879] 5. Display and audio guidance on terminals

[0880] The device displays the evasive actions sent from the server on its display and provides voice guidance through the speaker. For example, it displays specific instructions such as "Please change to the left lane," and then provides gentle voice guidance such as "When changing to the left lane, please reduce your speed and proceed slowly."

[0881] Specific examples

[0882] Real-life scenario

[0883] Obtaining and sending location information: The device obtains location information of latitude: 35.6895, longitude: 139.6917 and sends it to the server.

[0884] Risk prediction: The server analyzes new location information and surrounding traffic data and predicts that a vehicle is rapidly approaching from the right rear.

[0885] Emotion Recognition: The emotion engine recognizes the user's face and determines that the user is in a stressful state.

[0886] Adjusting evasive behavior: The server decides to instruct the user to change to the left lane using a gentle voice based on the user's emotional state.

[0887] Provides visual and audio guidance: The device displays the message "Please change to the left lane" on the car navigation display and provides gentle audio guidance such as "When changing to the left lane, reduce your speed and proceed slowly."

[0888] Prompt Sentence Examples

[0889] The user's location information was sent: latitude: 35.6895, longitude: 139.6917. Based on historical data and current traffic conditions, predict vehicle movements and suggest specific avoidance actions if there is a risk. Also, take into account the user's emotional state and adjust the content and tone of instructions as needed. For example, if the user is stressed, provide instructions in a calm voice.

[0890] In this way, the present invention is a system that can significantly reduce the risk of traffic accidents by providing appropriate avoidance actions based on the vehicle's current location and the user's emotional state.

[0891] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0892] Step 1: Get GPS information from your device

[0893] Input: Real-time location information obtained by the GPS module

[0894] Operation: The device uses the GPS module to obtain the vehicle's current location as latitude and longitude data, once per second.

[0895] Data processing: The acquired location data is temporarily stored in local storage and converted into an HTTP POST request format.

[0896] Output: Latitude and longitude location data sent to the server as an HTTP POST request

[0897] Step 2: Risk prediction by the server

[0898] Input: GPS location information sent from the device

[0899] How it works: The server inputs the received location information into an AI model (TensorFlow), which predicts the vehicle's future movements based on past data and current traffic conditions.

[0900] Data calculation: The AI ​​model uses a neural network to assess risk based on input location information and output a prediction such as "there is a vehicle rapidly approaching from the rear right."

[0901] Output: Predicted risk information (e.g., sudden approach from the rear right)

[0902] Step 3: Understanding the user's state using the emotion engine

[0903] Input: User's facial image and voice data acquired from the device's camera and microphone

[0904] How it works: The device uses the camera to recognize the user's face and the microphone to collect voice data. It uses the OpenCV library for face recognition and the Google Cloud Speech-to-Text API to convert the voice to text.

[0905] Data processing: Facial expressions and voice data are input into a machine learning model (Scikit-learn) to analyze whether the user is in a stressed or relaxed state.

[0906] Output: User's emotional state (e.g., stress state) as a result of the analysis

[0907] Step 4: Server Coordination of Evasive Behavior

[0908] Input: Risk prediction results and user's emotional state

[0909] How it works: The server adjusts the avoidance behavior based on the risk prediction result and the user's emotional state. For example, if the user is stressed, the server will set the tone to be gentler and give avoidance instructions.

[0910] Data Calculation: Determines customized content and audio tone of avoidance actions based on specific conditions.

[0911] Output: Coordinated evasive maneuver instructions (e.g., a gentle voice prompt saying "Move to the left lane")

[0912] Step 5: Display and voice guidance on the device

[0913] Input: Adjusted evasive maneuver instructions sent from the server

[0914] Operation: The device displays instructions from the server on the screen and provides voice guidance using a speech synthesis engine (Google Text-to-Speech).

[0915] Data processing: Evasive action instructions from the server are visually displayed on a GUI and audio data is generated.

[0916] Output: Visual instructions on the display and voice guidance from the speaker (e.g., a calm voice saying "Please change to the left lane")

[0917] This series of steps allows the system to provide the driver with targeted, risk-minimizing evasive action based on both the vehicle's current location and the user's emotional state.

[0918] (Application example 2)

[0919] 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."

[0920] Conventional driving assistance systems provide instructions for accident avoidance actions based on the vehicle's movement, but they have the problem of being unable to provide appropriate instructions based on the driver's emotional state. As a result, if the driver is stressed or nervous, the instructions may not be communicated effectively, which may reduce the effectiveness of accident avoidance. In addition, avoidance actions based solely on visual displays and audio guidance have the problem of being difficult to provide appropriate support tailored to the individual driver's situation.

[0921] 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 acquiring vehicle position information, means for using artificial intelligence to predict vehicle movement based on the position information, means for instructing the driver to take evasive action based on the information predicted by the artificial intelligence, means for acquiring the user's emotional state using an emotion engine that recognizes the user's emotions, and means for adjusting the content and method of instructions for evasive action based on the emotional state. This makes it possible to instruct evasive action flexibly and effectively according to the driver's emotional state.

[0922] "Vehicle location information" refers to data on the current latitude and longitude of a vehicle obtained using a positioning system such as a GPS.

[0923] "Artificial intelligence" refers to computational techniques and algorithms that predict a vehicle's future movements based on historical data and current traffic conditions.

[0924] "Means for instructing the driver to take evasive action" refers to a system that has the function of instructing the driver to take appropriate evasive action based on predicted risk information.

[0925] An "emotion engine" is a combination of software and hardware that performs facial recognition and voice analysis of the user to recognize their emotional state in real time.

[0926] "Emotional state" refers to the mental state of the driver, such as stress or relaxation.

[0927] "Display means" refers to a device or system for visually presenting information, and typically includes a car navigation display or a smartphone screen.

[0928] "Audio guidance means" refers to a device or system for providing information or instructions by voice through a speaker or earphone.

[0929] "Means for adjusting the content and method of instructions for avoidance behavior" refers to a system for changing the specific content of instructions for avoidance behavior and the method of conveying them based on the user's emotional state.

[0930] This invention is a system for tracking a vehicle's position in real time and providing driving assistance, particularly a system that can take into account the driver's emotional state and provide flexible evasive maneuvers.

[0931] First, the device (e.g., a smartphone) uses a GPS module to obtain the vehicle's location information (latitude and longitude). This location information is periodically sent to a server. The server then uses artificial intelligence (AI) to predict the vehicle's future movements based on the received location information. In this case, the AI ​​uses a model that has learned from past data and current traffic conditions.

[0932] Next, the emotion engine uses the device's camera and microphone to analyze the driver's emotional state in real time. For example, it uses facial recognition to determine stress or relaxation from facial expressions. It also uses voice analysis to estimate the driver's emotions from the way they speak and their tone of voice. This information is sent to the server.

[0933] The server integrates the predicted vehicle movement results with the driver's emotional state to calculate the optimal evasive action. If the driver is feeling stressed, it is important to give instructions in a tone that will help them relax. For example, the device might display a message on the car navigation display saying, "A vehicle is rapidly approaching from the rear right. Please slow down and move to the left," and provide voice guidance in a calm voice saying, "When changing to the left lane, please slow down and move slowly."

[0934] This system enables flexible accident avoidance by taking into account the user's emotional state. The specific hardware used is a smartphone, with a built-in camera, microphone, and display. The software uses a GPS module, OpenCV (for emotion recognition), Google Cloud Speech-to-Text API (for voice analysis), and Flask (for server-side processing).

[0935] As a concrete example, let's say a user is feeling stressed while driving. The device acquires location information of latitude: 35.6895, longitude: 139.6917 and sends it to the server. The server analyzes the new location information and surrounding traffic data and predicts the risk of "a vehicle rapidly approaching from the rear right." The emotion engine recognizes the user's face and determines that the user is in a stressed state. Based on the information that "the user is in a stressed state," the server decides to "change to the left lane" and provides guidance in a calm voice. The device displays the message "Please change to the left lane" on the car navigation display and provides voice guidance in a calm voice, "When changing to the left lane, please reduce your speed and proceed slowly."

[0936] Example prompt sentence:

[0937] "Your current location is latitude 35.6895, longitude 139.6917. You are in a stressed state. A vehicle is approaching you from behind on the right. Please slow down and move to the left. When changing to the left lane, slow down and move slowly."

[0938] In this way, the driver can receive appropriate accident avoidance instructions according to their emotional state, improving safety.

[0939] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0940] Step 1:

[0941] The terminal uses the GPS module to obtain the vehicle's current location information. At that time, it obtains latitude and longitude data and temporarily stores this information inside the terminal. The input of this step is GPS data, and the output is the vehicle's current location information.

[0942] Step 2:

[0943] The device sends the acquired location information to the server. It uses an HTTP POST request to send the vehicle's latitude and longitude to the server. The input of this step is the location information stored inside the device, and the output is the location information sent to the server.

[0944] Step 3:

[0945] The server receives the location information sent from the device. It uses artificial intelligence (AI) to predict the vehicle's future movements based on the received location information. In this process, it also analyzes past data and current traffic conditions. The input of this step is the received location information and past traffic data, and the output is the predicted future movements.

[0946] Step 4:

[0947] The device uses a camera and microphone to acquire the driver's emotional state. Specifically, it performs facial recognition using the camera and voice analysis using the microphone, and passes the results to the emotion engine. The input of this step is camera image and voice data, and the output is emotional state data.

[0948] Step 5:

[0949] The emotion engine analyzes the acquired facial recognition data and voice data to determine the driver's emotional state, such as stress or relaxation, and sends that information to the server. The input to this step is the emotional state data analyzed by the emotion engine, and the output is the emotional state information sent to the server.

[0950] Step 6:

[0951] The server calculates the optimal avoidance action based on the predicted vehicle movement and the emotional state information sent from the emotion engine. If the driver is stressed, the server will give instructions in a more relaxing tone. The inputs of this step are the predicted movement and the emotional state information, and the output is the adjusted avoidance action instructions.

[0952] Step 7:

[0953] The terminal receives the evasive action instructions sent from the server and presents them to the driver using a display and voice guidance. For example, it displays instructions such as "Change to the left lane" and provides voice guidance such as "When changing to the left lane, reduce your speed and proceed slowly." The input for this step is the evasive action instructions sent from the server, and the output is the display and voice guidance.

[0954] The above is the flow of processing steps in the system program.

[0955] 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.

[0956] 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.

[0957] 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.

[0958] [Fourth embodiment]

[0959] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0960] 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.

[0961] 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).

[0962] 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.

[0963] 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.

[0964] 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).

[0965] 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.

[0966] 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.

[0967] 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.

[0968] 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.

[0969] 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.

[0970] 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.

[0971] 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."

[0972] This invention is a system that predicts vehicle movements based on GPS information and provides specific instructions to the driver on how to avoid accidents. This system can be retrofitted to vehicles and is an effective means of supporting safe driving even in vehicles without driving assistance functions.

[0973] 1. Obtaining GPS information on the device

[0974] The device (smartphone or tablet) acquires the vehicle's current location in real time. To do this, the device is equipped with a GPS module and has the function of periodically acquiring the vehicle's current latitude and longitude. The acquired location information is sent to a server where it is used for analysis.

[0975] 2. Risk prediction by server

[0976] The server uses artificial intelligence (AI) to predict the vehicle's movements based on the GPS information sent from the device. The AI ​​learns from past data and surrounding traffic conditions, and uses this information to predict future movements with high accuracy. If the risk is deemed high, the server calculates specific evasive action. For example, if the AI ​​predicts that "there is a car rapidly approaching from the right rear of the vehicle," it will use that information to calculate "changing to the left lane" as an evasive action.

[0977] 3. Display and audio guidance on terminals

[0978] The device displays the evasive maneuvers sent from the server on the car navigation system or display. It also uses voice guidance to guide the driver in evasive maneuvers. Specifically, the device gives the driver easy-to-understand instructions, such as, "A vehicle is rapidly approaching from the rear right. Slow down and move to the left."

[0979] As a concrete example, consider the following scenario:

[0980] Real-life scenario:

[0981] The device obtains location information of latitude: 35.6895, longitude: 139.6917 and sends it to the server.

[0982] The server analyzes the new location information and surrounding traffic data and uses an AI model to predict the risk to the vehicle, such as a vehicle rapidly approaching from the right rear.

[0983] The server calculates that "changing to the left lane" is the optimal avoidance action and transmits this avoidance action to the terminal.

[0984] The device will display evasive action on the car navigation display and provide a voice message saying, "Please change to the left lane."

[0985] The driver will then confirm this and follow the instructions to move into the left lane to avoid any risk.

[0986] In this way, the system, which can be retrofitted into vehicles, enables drivers to take appropriate evasive action in real time, significantly reducing the risk of traffic accidents.

[0987] The processing flow will be explained below.

[0988] Step 1:

[0989] The terminal uses a GPS module to obtain the vehicle's current location, which is expressed in the form of latitude and longitude and is updated periodically.

[0990] Step 2:

[0991] The device sends the acquired location information to the server using a communication protocol (e.g., HTTP or WebSocket).

[0992] Step 3:

[0993] The server uses artificial intelligence (AI) to predict vehicle movements based on the received GPS information, integrating and analyzing past data and surrounding traffic information.

[0994] Step 4:

[0995] If the risk is deemed high based on the risk level calculated by the AI, the server calculates the optimal avoidance action. For example, if a vehicle is rapidly approaching from the rear right, the server will recommend slowing down and moving to the left.

[0996] Step 5:

[0997] The server then transmits the calculated evasive maneuvers to the device, again using a pre-configured communication protocol.

[0998] Step 6:

[0999] The device receives the evasive action from the server and displays it on the car navigation display, allowing the driver to visually confirm the evasive action.

[1000] Step 7:

[1001] At the same time, the device uses its voice guidance function to provide specific evasive maneuvers, such as "change to the left lane," through a speaker.

[1002] Step 8:

[1003] The user (driver) checks the presented visual and audio instructions and takes appropriate evasive action, such as changing lanes to the left or slowing down.

[1004] This series of processes allows drivers to take appropriate evasive action in real time, reducing the risk of traffic accidents.

[1005] Example 1

[1006] 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."

[1007] Many current vehicles do not have driving assistance functions, and drivers of these vehicles lack the information necessary for safe driving. This leaves them unable to respond to unexpected traffic situations, increasing the risk of accidents. In particular, it is difficult to predict the movement of one's own vehicle and the surrounding traffic conditions in real time and take appropriate evasive action. Therefore, there is a need for technology that can be easily installed even in vehicles without driving assistance functions and that can effectively instruct drivers on how to avoid accidents.

[1008] 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.

[1009] In this invention, the server includes a location information acquisition means for acquiring current location information of the vehicle, a prediction means for using a generative AI model to predict the future movement of the vehicle based on the location information, and an instruction means for instructing the driver on specific avoidance behavior based on the movement predicted by the generative AI model. This allows for easy installation even in vehicles without driving assistance functions, and makes it possible to instruct the driver on appropriate accident avoidance behavior in real time.

[1010] "Location information acquisition means" refers to a device or function for measuring the current location of the vehicle and transmitting that location information to a server.

[1011] A "generative AI model" is a model built on artificial intelligence technology that learns from past data and current situations to predict future behavior.

[1012] "Prediction means" refers to a device or function that uses a generative AI model to predict the future behavior of a vehicle.

[1013] "Instruction means" refers to devices or functions that instruct the driver to take evasive action based on information predicted by the generative AI model.

[1014] "Display means" refers to a display device or function for visually presenting avoidance actions.

[1015] "Voice guidance means" refers to devices or functions that verbally inform the driver of evasive action.

[1016] "GPS module" refers to a receiver for the satellite positioning system that precisely measures one's position on Earth.

[1017] An "artificial intelligence framework" refers to a software environment that supports the building and learning of generative AI models.

[1018] This invention is a system that predicts vehicle movements based on GPS information and instructs the driver on specific actions to avoid accidents. This system can be retrofitted to vehicles and provides an effective means of supporting safe driving even in vehicles without driving assistance functions.

[1019] First, the terminal (smartphone or tablet) obtains the vehicle's current location in real time. To do this, the terminal is equipped with a GPS module that periodically calculates the current latitude and longitude and transmits the obtained location information to a server. The specific hardware used is a smartphone or tablet, and the software includes a GPS module.

[1020] The server then receives the GPS information sent from the device and uses an artificial intelligence (AI) model to predict the vehicle's future movements. The AI ​​model learns from past data and surrounding traffic conditions, and uses this information to predict future movements with high accuracy. The specific AI framework used is a generative AI model built using TensorFlow, PyTorch, and other frameworks.

[1021] The server then instructs the driver on evasive action based on the predicted risk information. For example, if the AI ​​model predicts that a vehicle is rapidly approaching from the right rear of the vehicle, the server calculates that the optimal evasive action is to change to the left lane and sends that instruction to the device.

[1022] The device receives instructions for evasive action sent from the server and displays them on the car navigation system or display. It also uses voice guidance to guide the driver through specific evasive actions. For example, it may provide a voice message such as, "A vehicle is rapidly approaching from the rear right. Slow down and move to the left."

[1023] As a concrete example, consider the following scenario:

[1024] The device obtains its current location information (latitude: 35.6895, longitude: 139.6917) and sends it to the server.

[1025] The server analyzes the new location information and surrounding traffic data and uses an AI model to predict the risk of a vehicle rapidly approaching from the right rear.

[1026] The server calculates that "changing to the left lane" is the optimal avoidance action and sends that instruction to the terminal.

[1027] The terminal displays instructions from the server on the car navigation display and provides a voice message saying, "Please change to the left lane."

[1028] The driver sees this instruction and moves to the left lane to avoid the risk.

[1029] An example prompt might look like this:

[1030] "Predict the vehicle's movement based on the following latitude and longitude location information. Latitude: 35.6895, Longitude: 139.6917. Please explain in detail the evasive action you would take if a vehicle were rapidly approaching from the right rear."

[1031] This makes it possible to easily install the system even in vehicles that do not have driving assistance functions, and it is possible to instruct the driver on appropriate accident avoidance actions in real time.

[1032] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1033] Step 1:

[1034] Activating the GPS module on the device

[1035] The terminal activates the built-in GPS module. This module receives signals from satellites and obtains the vehicle's current position (latitude and longitude). Specifically, it utilizes the GPS function of a smartphone or tablet. The input is a signal from a GPS satellite, and the output is the current position information (latitude and longitude).

[1036] Step 2:

[1037] Acquisition and transmission of location information by the device

[1038] The device periodically collects the current latitude and longitude and sends them to the server. For example, if the device obtains vehicle position information of latitude 35.6895 and longitude 139.6917, it sends this information to the server via the Internet. The input is the position information from the GPS module, and the output is the position information sent to the server.

[1039] Step 3:

[1040] Receiving and storing location information by the server

[1041] The server receives the location information sent from the device and stores it in a database in real time. The input is the location information sent from the device, and the output is the location information stored in the database.

[1042] Step 4:

[1043] Server calls the generated AI model

[1044] The server calls a generative AI model based on the received location information to predict the vehicle's future movements. The generative AI model is built using an AI framework such as TensorFlow or PyTorch. The input is location information, and the output is predicted risk information.

[1045] Step 5:

[1046] Server predicts risk and calculates avoidance actions

[1047] The generative AI model receives past traffic data and current location information as inputs and predicts risks. For example, if it predicts that "there is a vehicle rapidly approaching from the rear right," it uses that information to calculate the optimal evasive action to "change to the left lane." The inputs are location information and past traffic data, and the output is specific instructions for evasive action.

[1048] Step 6:

[1049] Server sends evasive action instructions

[1050] The server sends the calculated avoidance action instructions to the terminal. The input is the avoidance action instructions calculated by the server, and the output is the avoidance action instructions sent to the terminal.

[1051] Step 7:

[1052] Display of avoidance actions on the device

[1053] The terminal receives the evasive action instructions sent from the server and displays them on the car navigation system or display. For example, it displays a message such as "Please change to the left lane." The input is the evasive action instructions sent from the server, and the output is the evasive action instructions displayed on the display.

[1054] Step 8:

[1055] Voice guidance provided by the device

[1056] The terminal also provides voice guidance based on the received instructions for evasive action. Specifically, it plays a message such as, "A vehicle is rapidly approaching from the rear right. Slow down and move to the left." The input is the instruction for evasive action sent from the server, and the output is voice guidance.

[1057] Step 9:

[1058] User performs avoidance action

[1059] The user (driver) confirms the instructions from the terminal and takes specific avoidance action, such as changing to the left lane. The input is the avoidance action instruction from the terminal, and the output is the actual avoidance action.

[1060] (Application example 1)

[1061] 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."

[1062] Although autonomous vehicle technology has made remarkable advances in recent years, it remains difficult to completely eliminate the risk of unexpected traffic accidents. There is also a growing demand for advanced risk avoidance systems to ensure the safety of drivers and passengers. Such systems must provide comprehensive driving assistance, including real-time location information acquisition, traffic situation analysis, and prompt instruction on evasive action. Conventional technologies rely primarily on information from sensors inside the vehicle, making it difficult to grasp the overall picture of traffic conditions. Furthermore, there is a risk that accidents cannot be avoided due to delayed instruction on evasive action. There is a need to resolve these issues and provide safer and more reliable driving assistance systems.

[1063] 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.

[1064] In this invention, the server includes a means for transmitting vehicle location information and surrounding traffic data to a central server, calculating risk predictions and avoidance actions, a means for feeding back the calculated avoidance actions to the automated driving system, and a means for presenting the avoidance actions on a display and by voice. This makes it possible to reduce accident risk by analyzing traffic conditions in real time and prompting appropriate avoidance actions based on the predictions. Furthermore, the accuracy and reliability of avoidance actions are significantly improved by using a generative AI model for analysis and the creation of prompts.

[1065] "Vehicle location information" is data on the latitude and longitude of the vehicle's current location.

[1066] "Artificial intelligence" refers to the technology that allows computer systems to mimic human intelligence, in this case to predict vehicle behavior.

[1067] "Avoidance actions" refer to driving maneuvers and actions taken by a vehicle to prevent an accident from occurring.

[1068] "Central server" refers to a computer server that receives and analyzes all data sent from vehicles and calculates evasive actions.

[1069] "Risk prediction" refers to the use of artificial intelligence to predict possible future dangers based on the vehicle and its surrounding traffic conditions.

[1070] "Display" means a display device used to visually present information regarding evasive maneuvers to the driver.

[1071] "Voice guidance means" refers to a means for providing audible instructions for evasive action to the driver.

[1072] A "generative AI model" is an artificial intelligence model trained using large amounts of learning data, and is capable of predicting risks and calculating avoidance actions with high accuracy.

[1073] "Prompt sentence" refers to an instruction sentence created by a generative AI model for an autonomous driving system.

[1074] As a concrete example for implementing this invention, we will explain the "Safety Assistance System (AOSS)" applied to autonomous vehicles. This system provides the function of predicting risks based on the vehicle's position information and instructing appropriate avoidance actions.

[1075] Generating a Program

[1076] First, the vehicle acquires real-time location information using a GPS module. This location information is then transmitted from a device inside the vehicle (e.g., a car navigation system or dedicated tablet) to a central server. The central server analyzes the received location information and surrounding traffic data, and performs risk prediction using a generative AI model (e.g., using TensorFlow or PyTorch).

[1077] If the central server detects a risk, it calculates evasive action. The calculated evasive action (e.g., lane change, speed adjustment) is fed back to the autonomous driving system and reflected in vehicle control. The evasive action is also displayed visually on the in-car display and instructed to the driver audibly through the voice guidance system (e.g., linked to Google Assistant or Amazon Alexa).

[1078] Detailed system description

[1079] 1. Obtaining real-time GPS information

[1080] The server uses a GPS module to obtain the vehicle's latitude and longitude, and the obtained location information is sent to a central server.

[1081] 2. Risk prediction by a central server

[1082] The central server receives location information and other surrounding traffic data (such as the location and speed of surrounding vehicles) and predicts future risks using a generative AI model that is trained on a large amount of learning data.

[1083] 3. Calculation and avoidance behavior generation

[1084] If a risk is detected, the central server calculates the optimal avoidance action and sends information about the avoidance action to the automated driving system.

[1085] 4. Display and audio guidance

[1086] Evasive maneuvers are visually displayed on the in-car display, and the driver is given instructions via the voice guidance system. For example, a message saying "Please change to the left lane" is displayed on the display, and the driver is notified with a message such as "A vehicle is rapidly approaching from the rear right. Slow down and move to the left."

[1087] Specific examples

[1088] As a concrete example, consider the following scenario:

[1089] The vehicle sends its location information: latitude 35.6895, longitude 139.6917 to the central server.

[1090] The server analyzes surrounding traffic data and predicts that "there is a vehicle rapidly approaching from the rear right."

[1091] The server calculates "changing to the left lane" as an evasive maneuver and sends this information to the autonomous driving system.

[1092] The in-car display will show a message saying "Please change to the left lane," and the voice guidance system will inform the driver, "A vehicle is rapidly approaching from the rear right. Please slow down and move to the left."

[1093] The driver will then confirm this and follow the instructions to move into the left lane to avoid any risk.

[1094] Prompt Sentence Examples

[1095] Examples of prompts are:

[1096] "New location information acquired. Latitude: 35.6895, Longitude: 139.6917. Analyze surrounding traffic conditions and perform risk prediction. If there is a vehicle approaching quickly from the rear right, generate an instruction to change to the left lane as an evasive action."

[1097] In this way, the technology of the present invention can be applied to autonomous vehicles and contribute to improving safety.

[1098] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1099] Step 1:

[1100] The terminal uses the GPS module to obtain the vehicle's current location (latitude and longitude) in real time. Specifically, the terminal periodically reads data from the GPS module to obtain the current latitude and longitude information. This location information becomes the input data for the system.

[1101] Step 2:

[1102] The device transmits its current location information to a central server using an internet connection and sending the data as a POST request via a RESTful API. Specifically, the device sends latitude and longitude data in JSON format to the server.

[1103] Step 3:

[1104] The server collects surrounding traffic data based on the received location information. Based on the location information, the server uses external APIs to obtain current traffic conditions and the locations of nearby vehicles. At this stage, the server integrates all the acquired data and creates an input dataset for prediction.

[1105] Step 4:

[1106] The server uses the generative AI model to perform risk prediction. Specifically, it inputs acquired location information and surrounding traffic data into the AI ​​model to calculate future risks. The generative AI model is trained based on past learning data and makes highly accurate predictions based on the input data. The output includes information on when a risk is detected and suggested avoidance actions to address that risk.

[1107] Step 5:

[1108] The server feeds back the calculated evasive maneuvers to the autonomous driving system and the device. The server sends the evasive maneuver information in JSON format to the autonomous driving system and also sends the same information to the device. Specifically, the feedback information from the server includes instructions for lane changes and speed adjustments.

[1109] Step 6:

[1110] The device displays information on evasive action visually and provides audio guidance. The device then displays the received instructions on the screen and communicates them to the driver using the voice guidance system. Specifically, the display will show the message "Change to the left lane," and the voice guidance system will notify the driver, "A vehicle is rapidly approaching from the rear right. Slow down and move left."

[1111] Step 7:

[1112] The user (driver) follows the displayed avoidance action instructions and performs appropriate driving maneuvers. The driver follows the display and voice guidance to take driving actions such as changing lanes and adjusting speed. At this stage, the user actually takes action to avoid risk.

[1113] 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.

[1114] This invention is a system that predicts vehicle movement based on GPS information and instructs the driver to take action to avoid accidents. Furthermore, this system incorporates an emotion engine that recognizes the user's emotions, allowing it to provide flexible avoidance instructions according to the user's emotional state. This system can be retrofitted into automobiles, providing high safety even in vehicles without driving assistance functions.

[1115] 1. Obtaining GPS information on the device

[1116] The device (smartphone or tablet) acquires the vehicle's current location in real time. The device uses a GPS module to periodically acquire current location information in the form of latitude and longitude. The acquired location information is sent to a server where it is used for analysis.

[1117] 2. Risk prediction by server

[1118] The server uses artificial intelligence (AI) to predict vehicle movements based on GPS information sent from the device. The AI ​​learns from past data and surrounding traffic conditions to predict future movements with high accuracy. If a risk is determined to be high, the server calculates specific evasive actions.

[1119] 3. Understanding user state using emotion engine

[1120] The device is equipped with a camera and sensors to recognize the user's emotions. Using these sensors, the device grasps the user's emotional state in real time through facial recognition and voice analysis. The emotion engine analyzes whether the user is in a stressed or relaxed state and sends that information to the server.

[1121] 4. Server-based coordination of evasive actions

[1122] The server adjusts the instructions and methods for avoidance actions based on the user's emotional information obtained from the emotion engine. For example, if the user is feeling stressed, the server will devise ways to alleviate anxiety by giving instructions in a relaxed tone.

[1123] 5. Display and audio guidance on terminals

[1124] The device displays the evasive action sent from the server on the car navigation display. It also uses voice guidance adjusted based on the user's emotional state to guide the driver through the evasive action. For example, the device may display and voice instructions such as "A vehicle is rapidly approaching from the rear right. Slow down and move to the left." If the user is feeling stressed, the device may provide guidance in a gentler voice.

[1125] As a concrete example, consider the following scenario:

[1126] Real-life scenario:

[1127] The device obtains location information of latitude: 35.6895, longitude: 139.6917 and sends it to the server.

[1128] The server analyzes the new location information and surrounding traffic data and uses an AI model to predict the risk to the vehicle, such as a vehicle rapidly approaching from the right rear.

[1129] The emotion engine recognizes the user's face and determines that the user is in a stressful state.

[1130] Based on the information that "the user is in a stressful state," the server decides to take the evasive action of "changing to the left lane" and provides guidance in a gentle voice.

[1131] The device displays the message "Please change to the left lane" on the car navigation display and provides voice guidance in a gentle voice saying, "When changing to the left lane, reduce your speed and proceed slowly."

[1132] The driver will then confirm this and follow the instructions to move into the left lane to avoid any risk.

[1133] In this way, by combining a system that can be retrofitted into vehicles with emotion analysis using an emotion engine, drivers can take appropriate, emotion-sensitive evasive action in real time, significantly reducing the risk of traffic accidents.

[1134] The processing flow will be explained below.

[1135] Step 1:

[1136] The device uses a GPS module to obtain the vehicle's current location, which is obtained as latitude and longitude and updated periodically over time.

[1137] Step 2:

[1138] The device sends the acquired location information to the server using a transmission protocol (e.g., HTTP, WebSocket).

[1139] Step 3:

[1140] The server uses artificial intelligence (AI) to predict vehicle movements based on the received GPS information, and the AI ​​performs analysis based on past data and surrounding traffic conditions.

[1141] Step 4:

[1142] The device uses cameras and sensors to recognize the user's face and perform voice analysis, and analyzes their emotions in real time, with an emotion engine identifying emotional states such as stress or relaxation.

[1143] Step 5:

[1144] The terminal transmits the identified user's emotion information to the server.

[1145] Step 6:

[1146] The server calculates the optimal avoidance action based on the risk level calculated by the AI ​​when the risk is deemed high. For example, if a vehicle is predicted to be rapidly approaching from the rear right, it will recommend changing to the left lane.

[1147] Step 7:

[1148] The server adjusts the instructions and methods for avoidance actions based on the user's emotional information. For example, if the user is feeling stressed, the server will set the instructions to be given in a relaxed tone.

[1149] Step 8:

[1150] The server transmits the calculated avoidance actions to the terminal.

[1151] Step 9:

[1152] The device then displays the received instructions for avoidance actions on the car navigation display, with specific instructions visually displayed.

[1153] Step 10:

[1154] The device uses a voice guidance function to inform the user of specific avoidance actions, such as "A vehicle is rapidly approaching from the rear right. Slow down and move to the left."

[1155] Step 11:

[1156] The user checks the displayed instructions and audio guidance and takes appropriate evasive action, such as changing to the left lane or slowing down.

[1157] This series of processes allows users to take appropriate avoidance actions in real time based on their own emotions, reducing the risk of traffic accidents.

[1158] Example 2

[1159] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1160] Conventional vehicle driving assistance systems were able to predict risks and provide instructions for evasive action based on vehicle position information, but they were unable to adjust their instructions to take into account the driver's emotional state. This could lead to the driver continuing to drive while feeling stressed, increasing the risk. Therefore, a system is needed that can recognize the driver's emotional state and provide instructions for evasive action accordingly.

[1161] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1162] In this invention, the server includes means for acquiring vehicle position information, means for using artificial intelligence to predict vehicle movement based on the position information, means for instructing the driver to take avoidance action based on the information predicted by the artificial intelligence, sensor means for recognizing the emotional state of the user, and means for adjusting the avoidance action based on the emotional state of the user, thereby making it possible to instruct appropriate avoidance action according to the emotional state of the driver.

[1163] "Vehicle location information" is data indicating the vehicle's current latitude and longitude, and is obtained from a GPS module or the like.

[1164] "Artificial intelligence for predicting vehicle movement" refers to algorithms and systems that can predict future vehicle movement with high accuracy by learning from past data and current traffic conditions.

[1165] "Means for instructing the driver to take evasive action" refers to means for visually or audibly instructing the driver to take specific evasive action based on the results of predicting the vehicle's movement.

[1166] "Sensor means" refers to devices such as cameras and microphones for recognizing the user's emotional state.

[1167] "User's emotional state" is information that indicates the psychological state, such as stress or relaxation, that the user is currently feeling.

[1168] The "means for adjusting avoidance behavior" is a means for appropriately changing the content of avoidance behavior and the method of instruction according to the emotional state of the user.

[1169] "Display means" refers to a screen, monitor, or the like that visually presents avoidance actions to the user.

[1170] The "voice guidance means" refers to a speaker or voice synthesis system that uses voice to guide the user on how to take evasive action.

[1171] This invention is a system that acquires the current location of a vehicle, predicts risks, and instructs the driver to take evasive action. This system includes a function that recognizes the user's emotional state and provides instructions according to the emotion. The specific configuration and processing method of the hardware and software for implementing this system are described below.

[1172] Hardware and Software Configuration

[1173] Terminal

[1174] GPS module: Obtains the vehicle's current location in real time.

[1175] Camera: Used for facial recognition and analyzing the user's emotional state.

[1176] Microphone: Used to collect voice data and analyze emotions from the user's voice.

[1177] Display: A display device that visually instructs the driver on evasive action.

[1178] Speaker: An audio output device for providing audio guidance.

[1179] server

[1180] AI model (using TensorFlow, for example): Used to predict vehicle behavior.

[1181] Emotion engine (using Scikit-learn, for example): Analyzes the user's emotional state and adjusts avoidance behavior based on that information.

[1182] Database: Stores historical traffic and location data and uses it to train AI models.

[1183] Processing flow

[1184] This system operates in the following manner.

[1185] 1. Obtaining GPS information on the device

[1186] The terminal uses a GPS module to obtain the vehicle's current location and transmits it to the server as latitude and longitude data.

[1187] 2. Risk prediction by server

[1188] The server inputs the received GPS information into an AI model to predict the vehicle's future movements. If there is a risk, it generates specific risk information, such as "A vehicle is rapidly approaching from the rear right."

[1189] 3. Understanding user state using emotion engine

[1190] The device uses a camera and microphone to analyze the user's emotional state, recognizing whether the user is stressed or relaxed from facial expressions and voice, and sends that information to a server.

[1191] 4. Server-based coordination of evasive actions

[1192] The server adjusts the avoidance behavior based on the risk information and the user's emotional state. For example, if the user is stressed, the server will set the instructions to be given in a gentle tone.

[1193] 5. Display and audio guidance on terminals

[1194] The device displays the evasive actions sent from the server on its display and provides voice guidance through the speaker. For example, it displays specific instructions such as "Please change to the left lane," and then provides gentle voice guidance such as "When changing to the left lane, please reduce your speed and proceed slowly."

[1195] Specific examples

[1196] Real-life scenario

[1197] Obtaining and sending location information: The device obtains location information of latitude: 35.6895, longitude: 139.6917 and sends it to the server.

[1198] Risk prediction: The server analyzes new location information and surrounding traffic data and predicts that a vehicle is rapidly approaching from the right rear.

[1199] Emotion Recognition: The emotion engine recognizes the user's face and determines that the user is in a stressful state.

[1200] Adjusting evasive behavior: The server decides to instruct the user to change to the left lane using a gentle voice based on the user's emotional state.

[1201] Provides visual and audio guidance: The device displays the message "Please change to the left lane" on the car navigation display and provides gentle audio guidance such as "When changing to the left lane, reduce your speed and proceed slowly."

[1202] Prompt Sentence Examples

[1203] The user's location information was sent: latitude: 35.6895, longitude: 139.6917. Based on historical data and current traffic conditions, predict vehicle movements and suggest specific avoidance actions if there is a risk. Also, take into account the user's emotional state and adjust the content and tone of instructions as needed. For example, if the user is stressed, provide instructions in a calm voice.

[1204] In this way, the present invention is a system that can significantly reduce the risk of traffic accidents by providing appropriate avoidance actions based on the vehicle's current location and the user's emotional state.

[1205] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1206] Step 1: Get GPS information from your device

[1207] Input: Real-time location information obtained by the GPS module

[1208] Operation: The device uses the GPS module to obtain the vehicle's current location as latitude and longitude data, once per second.

[1209] Data processing: The acquired location data is temporarily stored in local storage and converted into an HTTP POST request format.

[1210] Output: Latitude and longitude location data sent to the server as an HTTP POST request

[1211] Step 2: Risk prediction by the server

[1212] Input: GPS location information sent from the device

[1213] How it works: The server inputs the received location information into an AI model (TensorFlow), which predicts the vehicle's future movements based on past data and current traffic conditions.

[1214] Data calculation: The AI ​​model uses a neural network to assess risk based on input location information and output a prediction such as "there is a vehicle rapidly approaching from the rear right."

[1215] Output: Predicted risk information (e.g., sudden approach from the rear right)

[1216] Step 3: Understanding the user's state using the emotion engine

[1217] Input: User's facial image and voice data acquired from the device's camera and microphone

[1218] How it works: The device uses the camera to recognize the user's face and the microphone to collect voice data. It uses the OpenCV library for face recognition and the Google Cloud Speech-to-Text API to convert the voice to text.

[1219] Data processing: Facial expressions and voice data are input into a machine learning model (Scikit-learn) to analyze whether the user is in a stressed or relaxed state.

[1220] Output: User's emotional state (e.g., stress state) as a result of the analysis

[1221] Step 4: Server Coordination of Evasive Behavior

[1222] Input: Risk prediction results and user's emotional state

[1223] How it works: The server adjusts the avoidance behavior based on the risk prediction result and the user's emotional state. For example, if the user is stressed, the server will set the tone to be gentler and give avoidance instructions.

[1224] Data Calculation: Determines customized content and audio tone of avoidance actions based on specific conditions.

[1225] Output: Coordinated evasive maneuver instructions (e.g., a gentle voice prompt saying "Move to the left lane")

[1226] Step 5: Display and voice guidance on the device

[1227] Input: Adjusted evasive maneuver instructions sent from the server

[1228] Operation: The device displays instructions from the server on the screen and provides voice guidance using a speech synthesis engine (Google Text-to-Speech).

[1229] Data processing: Evasive action instructions from the server are visually displayed on a GUI and audio data is generated.

[1230] Output: Visual instructions on the display and voice guidance from the speaker (e.g., a calm voice saying "Please change to the left lane")

[1231] This series of steps allows the system to provide the driver with targeted, risk-minimizing evasive action based on both the vehicle's current location and the user's emotional state.

[1232] (Application example 2)

[1233] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1234] Conventional driving assistance systems provide instructions for accident avoidance actions based on the vehicle's movement, but they have the problem of being unable to provide appropriate instructions based on the driver's emotional state. As a result, if the driver is stressed or nervous, the instructions may not be communicated effectively, which may reduce the effectiveness of accident avoidance. In addition, avoidance actions based solely on visual displays and audio guidance have the problem of being difficult to provide appropriate support tailored to the individual driver's situation.

[1235] 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 acquiring vehicle position information, means for using artificial intelligence to predict vehicle movement based on the position information, means for instructing the driver to take evasive action based on the information predicted by the artificial intelligence, means for acquiring the user's emotional state using an emotion engine that recognizes the user's emotions, and means for adjusting the content and method of instructions for evasive action based on the emotional state. This makes it possible to instruct evasive action flexibly and effectively according to the driver's emotional state.

[1236] "Vehicle location information" refers to data on the current latitude and longitude of a vehicle obtained using a positioning system such as a GPS.

[1237] "Artificial intelligence" refers to computational techniques and algorithms that predict a vehicle's future movements based on historical data and current traffic conditions.

[1238] "Means for instructing the driver to take evasive action" refers to a system that has the function of instructing the driver to take appropriate evasive action based on predicted risk information.

[1239] An "emotion engine" is a combination of software and hardware that performs facial recognition and voice analysis of the user to recognize their emotional state in real time.

[1240] "Emotional state" refers to the mental state of the driver, such as stress or relaxation.

[1241] "Display means" refers to a device or system for visually presenting information, and typically includes a car navigation display or a smartphone screen.

[1242] "Audio guidance means" refers to a device or system for providing information or instructions by voice through a speaker or earphone.

[1243] "Means for adjusting the content and method of instructions for avoidance behavior" refers to a system for changing the specific content of instructions for avoidance behavior and the method of conveying them based on the user's emotional state.

[1244] This invention is a system for tracking a vehicle's position in real time and providing driving assistance, particularly a system that can take into account the driver's emotional state and provide flexible evasive maneuvers.

[1245] First, the device (e.g., a smartphone) uses a GPS module to obtain the vehicle's location information (latitude and longitude). This location information is periodically sent to a server. The server then uses artificial intelligence (AI) to predict the vehicle's future movements based on the received location information. In this case, the AI ​​uses a model that has learned from past data and current traffic conditions.

[1246] Next, the emotion engine uses the device's camera and microphone to analyze the driver's emotional state in real time. For example, it uses facial recognition to determine stress or relaxation from facial expressions. It also uses voice analysis to estimate the driver's emotions from the way they speak and their tone of voice. This information is sent to the server.

[1247] The server integrates the predicted vehicle movement results with the driver's emotional state to calculate the optimal evasive action. If the driver is feeling stressed, it is important to give instructions in a tone that will help them relax. For example, the device might display a message on the car navigation display saying, "A vehicle is rapidly approaching from the rear right. Please slow down and move to the left," and provide voice guidance in a calm voice saying, "When changing to the left lane, please slow down and move slowly."

[1248] This system enables flexible accident avoidance by taking into account the user's emotional state. The specific hardware used is a smartphone, with a built-in camera, microphone, and display. The software uses a GPS module, OpenCV (for emotion recognition), Google Cloud Speech-to-Text API (for voice analysis), and Flask (for server-side processing).

[1249] As a concrete example, let's say a user is feeling stressed while driving. The device acquires location information of latitude: 35.6895, longitude: 139.6917 and sends it to the server. The server analyzes the new location information and surrounding traffic data and predicts the risk of "a vehicle rapidly approaching from the rear right." The emotion engine recognizes the user's face and determines that the user is in a stressed state. Based on the information that "the user is in a stressed state," the server decides to "change to the left lane" and provides guidance in a calm voice. The device displays the message "Please change to the left lane" on the car navigation display and provides voice guidance in a calm voice, "When changing to the left lane, please reduce your speed and proceed slowly."

[1250] Example prompt sentence:

[1251] "Your current location is latitude 35.6895, longitude 139.6917. You are in a stressed state. A vehicle is approaching you from behind on the right. Please slow down and move to the left. When changing to the left lane, slow down and move slowly."

[1252] In this way, the driver can receive appropriate accident avoidance instructions according to their emotional state, improving safety.

[1253] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1254] Step 1:

[1255] The terminal uses the GPS module to obtain the vehicle's current location information. At that time, it obtains latitude and longitude data and temporarily stores this information inside the terminal. The input of this step is GPS data, and the output is the vehicle's current location information.

[1256] Step 2:

[1257] The device sends the acquired location information to the server. It uses an HTTP POST request to send the vehicle's latitude and longitude to the server. The input of this step is the location information stored inside the device, and the output is the location information sent to the server.

[1258] Step 3:

[1259] The server receives the location information sent from the device. It uses artificial intelligence (AI) to predict the vehicle's future movements based on the received location information. In this process, it also analyzes past data and current traffic conditions. The input of this step is the received location information and past traffic data, and the output is the predicted future movements.

[1260] Step 4:

[1261] The device uses a camera and microphone to acquire the driver's emotional state. Specifically, it performs facial recognition using the camera and voice analysis using the microphone, and passes the results to the emotion engine. The input of this step is camera image and voice data, and the output is emotional state data.

[1262] Step 5:

[1263] The emotion engine analyzes the acquired facial recognition data and voice data to determine the driver's emotional state, such as stress or relaxation, and sends that information to the server. The input to this step is the emotional state data analyzed by the emotion engine, and the output is the emotional state information sent to the server.

[1264] Step 6:

[1265] The server calculates the optimal avoidance action based on the predicted vehicle movement and the emotional state information sent from the emotion engine. If the driver is stressed, the server will give instructions in a more relaxing tone. The inputs of this step are the predicted movement and the emotional state information, and the output is the adjusted avoidance action instructions.

[1266] Step 7:

[1267] The terminal receives the evasive action instructions sent from the server and presents them to the driver using a display and voice guidance. For example, it displays instructions such as "Change to the left lane" and provides voice guidance such as "When changing to the left lane, reduce your speed and proceed slowly." The input for this step is the evasive action instructions sent from the server, and the output is the display and voice guidance.

[1268] The above is the flow of processing steps in the system program.

[1269] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1270] 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.

[1271] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1272] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1273] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1274] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1275] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1276] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1277] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1278] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1279] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1280] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1281] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1282] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1283] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1284] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1285] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1286] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1287] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1288] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1289] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1290] The following is further disclosed regarding the above embodiment.

[1291] (Claim 1)

[1292] A means for acquiring vehicle location information;

[1293] means for using artificial intelligence to predict vehicle movement based on said location information;

[1294] a means for instructing a driver to take evasive action based on the information predicted by the artificial intelligence;

[1295] A system including:

[1296] (Claim 2)

[1297] 10. The system of claim 1, further comprising display means for visually presenting said avoidance maneuver.

[1298] (Claim 3)

[1299] The system of claim 1 , further comprising audio guidance means for audibly presenting the avoidance action.

[1300] "Example 1"

[1301] (Claim 1)

[1302] a location information acquisition means for acquiring current location information of the vehicle;

[1303] a prediction means for using a generative AI model to predict future vehicle movements based on the location information;

[1304] an instruction means for instructing a driver to take specific avoidance actions based on the movement predicted by the generative AI model;

[1305] display means for displaying the avoidance behavior;

[1306] a voice guidance means for providing voice guidance on the avoidance behavior;

[1307] A system including:

[1308] (Claim 2)

[1309] 2. The system according to claim 1, wherein the location information acquisition means includes a GPS module mounted on the vehicle.

[1310] (Claim 3)

[1311] 2. The system of claim 1, wherein the predictive means uses a generative AI model built using an artificial intelligence framework.

[1312] "Application Example 1"

[1313] (Claim 1)

[1314] A means for acquiring vehicle location information;

[1315] means for using artificial intelligence to predict vehicle movement based on said location information;

[1316] a means for instructing a driver to take evasive action based on the information predicted by the artificial intelligence;

[1317] means for transmitting the location information and surrounding traffic data to a central server, and calculating risk prediction and avoidance actions;

[1318] means for feeding back the calculated avoidance behavior to an automated driving system;

[1319] means for presenting the avoidance behavior by display and sound;

[1320] A system including:

[1321] (Claim 2)

[1322] The system of claim 1 , further comprising display means and audio guidance means for visually presenting said avoidance maneuver.

[1323] (Claim 3)

[1324] 10. The system of claim 1, further comprising: means for using a generative AI model to analyze data received from a central server to improve the avoidance behavior; and means for creating prompt sentences based on the generative AI model.

[1325] "Example 2: Combining Emotion Engines"

[1326] (Claim 1)

[1327] A means for acquiring vehicle location information;

[1328] means for using artificial intelligence to predict vehicle movement based on said location information;

[1329] a means for instructing a driver to take evasive action based on the information predicted by the artificial intelligence;

[1330] sensor means for recognizing an emotional state of a user;

[1331] means for adjusting avoidance behavior based on the emotional state of the user;

[1332] A system including:

[1333] (Claim 2)

[1334] 10. The system of claim 1, further comprising display means for visually presenting said avoidance maneuver.

[1335] (Claim 3)

[1336] The system of claim 1 , further comprising audio guidance means for audibly presenting the avoidance action.

[1337] "Application example 2 when combining emotion engines"

[1338] (Claim 1)

[1339] A means for acquiring vehicle location information;

[1340] means for using artificial intelligence to predict vehicle movement based on said location information;

[1341] a means for instructing a driver to take evasive action based on the information predicted by the artificial intelligence;

[1342] means for obtaining an emotional state of the user using an emotion engine that recognizes emotions of the user;

[1343] a means for adjusting the instruction content and method of avoidance behavior based on the emotional state;

[1344] A system including:

[1345] (Claim 2)

[1346] 10. The system of claim 1, further comprising display means for visually presenting said avoidance maneuver.

[1347] (Claim 3)

[1348] The system of claim 1 , further comprising audio guidance means for audibly presenting the avoidance action. [Explanation of symbols]

[1349] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for acquiring vehicle location information; means for using artificial intelligence to predict vehicle movement based on said location information; a means for instructing a driver to take evasive action based on the information predicted by the artificial intelligence; A system including:

2. 10. The system of claim 1, further comprising display means for visually presenting said avoidance maneuver.

3. The system of claim 1 further comprising audio guidance means for audibly presenting said avoidance action.

Images